1269 lines
49 KiB
Python
Raw Normal View History

2025-08-14 08:56:04 +05:30
"""
MCP component for MCP server integration
2025-08-14 08:56:04 +05:30
"""
import os
import platform
import shlex
import subprocess
import sys
2025-08-14 08:56:04 +05:30
from pathlib import Path
from typing import Any, Dict, List, Optional, Tuple
from setup import __version__
2025-08-14 08:56:04 +05:30
AIRIS_MCP_GITHUB_REPO = "https://github.com/agiletec-inc/airis-mcp-gateway"
AIRIS_MCP_CLONE_COMMAND = [
"git",
"clone",
AIRIS_MCP_GITHUB_REPO,
str(Path.home() / ".airis-mcp-gateway"),
]
AIRIS_MCP_UPDATE_COMMAND = ["git", "pull", "origin", "master"]
AIRIS_MCP_INSTALL_COMMAND = ["make", "install-claude"]
AIRIS_MCP_GATEWAY_DIR = Path.home() / ".airis-mcp-gateway"
AIRIS_MCP_CONFIG_PATH = Path.home() / ".claude" / "mcp.json"
AIRIS_MCP_EXPECTED_CONFIG_TARGET = "mcp.json"
from ..core.base import Component
2025-08-14 08:56:04 +05:30
class MCPComponent(Component):
"""MCP servers integration component"""
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
2025-08-14 08:56:04 +05:30
def __init__(self, install_dir: Optional[Path] = None):
"""Initialize MCP component"""
super().__init__(install_dir)
Fixed Some Bugs (#355) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> --------- Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>
2025-09-13 17:28:52 +05:30
self.installed_servers_in_session: List[str] = []
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
# Define MCP servers to install
refactor: PM Agent complete independence from external MCP servers (#439) * refactor: PM Agent complete independence from external MCP servers ## Summary Implement graceful degradation to ensure PM Agent operates fully without any MCP server dependencies. MCP servers now serve as optional enhancements rather than required components. ## Changes ### Responsibility Separation (NEW) - **PM Agent**: Development workflow orchestration (PDCA cycle, task management) - **mindbase**: Memory management (long-term, freshness, error learning) - **Built-in memory**: Session-internal context (volatile) ### 3-Layer Memory Architecture with Fallbacks 1. **Built-in Memory** [OPTIONAL]: Session context via MCP memory server 2. **mindbase** [OPTIONAL]: Long-term semantic search via airis-mcp-gateway 3. **Local Files** [ALWAYS]: Core functionality in docs/memory/ ### Graceful Degradation Implementation - All MCP operations marked with [ALWAYS] or [OPTIONAL] - Explicit IF/ELSE fallback logic for every MCP call - Dual storage: Always write to local files + optionally to mindbase - Smart lookup: Semantic search (if available) → Text search (always works) ### Key Fallback Strategies **Session Start**: - mindbase available: search_conversations() for semantic context - mindbase unavailable: Grep docs/memory/*.jsonl for text-based lookup **Error Detection**: - mindbase available: Semantic search for similar past errors - mindbase unavailable: Grep docs/mistakes/ + solutions_learned.jsonl **Knowledge Capture**: - Always: echo >> docs/memory/patterns_learned.jsonl (persistent) - Optional: mindbase.store() for semantic search enhancement ## Benefits - ✅ Zero external dependencies (100% functionality without MCP) - ✅ Enhanced capabilities when MCPs available (semantic search, freshness) - ✅ No functionality loss, only reduced search intelligence - ✅ Transparent degradation (no error messages, automatic fallback) ## Related Research - Serena MCP investigation: Exposes tools (not resources), memory = markdown files - mindbase superiority: PostgreSQL + pgvector > Serena memory features - Best practices alignment: /Users/kazuki/github/airis-mcp-gateway/docs/mcp-best-practices.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: add PR template and pre-commit config - Add structured PR template with Git workflow checklist - Add pre-commit hooks for secret detection and Conventional Commits - Enforce code quality gates (YAML/JSON/Markdown lint, shellcheck) NOTE: Execute pre-commit inside Docker container to avoid host pollution: docker compose exec workspace uv tool install pre-commit docker compose exec workspace pre-commit run --all-files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: update PM Agent context with token efficiency architecture - Add Layer 0 Bootstrap (150 tokens, 95% reduction) - Document Intent Classification System (5 complexity levels) - Add Progressive Loading strategy (5-layer) - Document mindbase integration incentive (38% savings) - Update with 2025-10-17 redesign details * refactor: PM Agent command with progressive loading - Replace auto-loading with User Request First philosophy - Add 5-layer progressive context loading - Implement intent classification system - Add workflow metrics collection (.jsonl) - Document graceful degradation strategy * fix: installer improvements Update installer logic for better reliability * docs: add comprehensive development documentation - Add architecture overview - Add PM Agent improvements analysis - Add parallel execution architecture - Add CLI install improvements - Add code style guide - Add project overview - Add install process analysis * docs: add research documentation Add LLM agent token efficiency research and analysis * docs: add suggested commands reference * docs: add session logs and testing documentation - Add session analysis logs - Add testing documentation * feat: migrate CLI to typer + rich for modern UX ## What Changed ### New CLI Architecture (typer + rich) - Created `superclaude/cli/` module with modern typer-based CLI - Replaced custom UI utilities with rich native features - Added type-safe command structure with automatic validation ### Commands Implemented - **install**: Interactive installation with rich UI (progress, panels) - **doctor**: System diagnostics with rich table output - **config**: API key management with format validation ### Technical Improvements - Dependencies: Added typer>=0.9.0, rich>=13.0.0, click>=8.0.0 - Entry Point: Updated pyproject.toml to use `superclaude.cli.app:cli_main` - Tests: Added comprehensive smoke tests (11 passed) ### User Experience Enhancements - Rich formatted help messages with panels and tables - Automatic input validation with retry loops - Clear error messages with actionable suggestions - Non-interactive mode support for CI/CD ## Testing ```bash uv run superclaude --help # ✓ Works uv run superclaude doctor # ✓ Rich table output uv run superclaude config show # ✓ API key management pytest tests/test_cli_smoke.py # ✓ 11 passed, 1 skipped ``` ## Migration Path - ✅ P0: Foundation complete (typer + rich + smoke tests) - 🔜 P1: Pydantic validation models (next sprint) - 🔜 P2: Enhanced error messages (next sprint) - 🔜 P3: API key retry loops (next sprint) ## Performance Impact - **Code Reduction**: Prepared for -300 lines (custom UI → rich) - **Type Safety**: Automatic validation from type hints - **Maintainability**: Framework primitives vs custom code 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate documentation directories Merged claudedocs/ into docs/research/ for consistent documentation structure. Changes: - Moved all claudedocs/*.md files to docs/research/ - Updated all path references in documentation (EN/KR) - Updated RULES.md and research.md command templates - Removed claudedocs/ directory - Removed ClaudeDocs/ from .gitignore Benefits: - Single source of truth for all research reports - PEP8-compliant lowercase directory naming - Clearer documentation organization - Prevents future claudedocs/ directory creation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: reduce /sc:pm command output from 1652 to 15 lines - Remove 1637 lines of documentation from command file - Keep only minimal bootstrap message - 99% token reduction on command execution - Detailed specs remain in superclaude/agents/pm-agent.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: split PM Agent into execution workflows and guide - Reduce pm-agent.md from 735 to 429 lines (42% reduction) - Move philosophy/examples to docs/agents/pm-agent-guide.md - Execution workflows (PDCA, file ops) stay in pm-agent.md - Guide (examples, quality standards) read once when needed Token savings: - Agent loading: ~6K → ~3.5K tokens (42% reduction) - Total with pm.md: 71% overall reduction 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate PM Agent optimization and pending changes PM Agent optimization (already committed separately): - superclaude/commands/pm.md: 1652→14 lines - superclaude/agents/pm-agent.md: 735→429 lines - docs/agents/pm-agent-guide.md: new guide file Other pending changes: - setup: framework_docs, mcp, logger, remove ui.py - superclaude: __main__, cli/app, cli/commands/install - tests: test_ui updates - scripts: workflow metrics analysis tools - docs/memory: session state updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: simplify MCP installer to unified gateway with legacy mode ## Changes ### MCP Component (setup/components/mcp.py) - Simplified to single airis-mcp-gateway by default - Added legacy mode for individual official servers (sequential-thinking, context7, magic, playwright) - Dynamic prerequisites based on mode: - Default: uv + claude CLI only - Legacy: node (18+) + npm + claude CLI - Removed redundant server definitions ### CLI Integration - Added --legacy flag to setup/cli/commands/install.py - Added --legacy flag to superclaude/cli/commands/install.py - Config passes legacy_mode to component installer ## Benefits - ✅ Simpler: 1 gateway vs 9+ individual servers - ✅ Lighter: No Node.js/npm required (default mode) - ✅ Unified: All tools in one gateway (sequential-thinking, context7, magic, playwright, serena, morphllm, tavily, chrome-devtools, git, puppeteer) - ✅ Flexible: --legacy flag for official servers if needed ## Usage ```bash superclaude install # Default: airis-mcp-gateway (推奨) superclaude install --legacy # Legacy: individual official servers ``` 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename CoreComponent to FrameworkDocsComponent and add PM token tracking ## Changes ### Component Renaming (setup/components/) - Renamed CoreComponent → FrameworkDocsComponent for clarity - Updated all imports in __init__.py, agents.py, commands.py, mcp_docs.py, modes.py - Better reflects the actual purpose (framework documentation files) ### PM Agent Enhancement (superclaude/commands/pm.md) - Added token usage tracking instructions - PM Agent now reports: 1. Current token usage from system warnings 2. Percentage used (e.g., "27% used" for 54K/200K) 3. Status zone: 🟢 <75% | 🟡 75-85% | 🔴 >85% - Helps prevent token exhaustion during long sessions ### UI Utilities (setup/utils/ui.py) - Added new UI utility module for installer - Provides consistent user interface components ## Benefits - ✅ Clearer component naming (FrameworkDocs vs Core) - ✅ PM Agent token awareness for efficiency - ✅ Better visual feedback with status zones 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor(pm-agent): minimize output verbosity (471→284 lines, 40% reduction) **Problem**: PM Agent generated excessive output with redundant explanations - "System Status Report" with decorative formatting - Repeated "Common Tasks" lists user already knows - Verbose session start/end protocols - Duplicate file operations documentation **Solution**: Compress without losing functionality - Session Start: Reduced to symbol-only status (🟢 branch | nM nD | token%) - Session End: Compressed to essential actions only - File Operations: Consolidated from 2 sections to 1 line reference - Self-Improvement: 5 phases → 1 unified workflow - Output Rules: Explicit constraints to prevent Claude over-explanation **Quality Preservation**: - ✅ All core functions retained (PDCA, memory, patterns, mistakes) - ✅ PARALLEL Read/Write preserved (performance critical) - ✅ Workflow unchanged (session lifecycle intact) - ✅ Added output constraints (prevents verbose generation) **Reduction Method**: - Deleted: Explanatory text, examples, redundant sections - Retained: Action definitions, file paths, core workflows - Added: Explicit output constraints to enforce minimalism **Token Impact**: 40% reduction in agent documentation size **Before**: Verbose multi-section report with task lists **After**: Single line status: 🟢 integration | 15M 17D | 36% 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate MCP integration to unified gateway **Changes**: - Remove individual MCP server docs (superclaude/mcp/*.md) - Remove MCP server configs (superclaude/mcp/configs/*.json) - Delete MCP docs component (setup/components/mcp_docs.py) - Simplify installer (setup/core/installer.py) - Update components for unified gateway approach **Rationale**: - Unified gateway (airis-mcp-gateway) provides all MCP servers - Individual docs/configs no longer needed (managed centrally) - Reduces maintenance burden and file count - Simplifies installation process **Files Removed**: 17 MCP files (docs + configs) **Installer Changes**: Removed legacy MCP installation logic 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: update version and component metadata - Bump version (pyproject.toml, setup/__init__.py) - Update CLAUDE.md import service references - Reflect component structure changes 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-17 09:13:06 +09:00
# Default: airis-mcp-gateway (unified gateway with all tools)
# Legacy mode (--legacy flag): individual official servers
self.mcp_servers_default = {
"airis-mcp-gateway": {
"name": "airis-mcp-gateway",
"description": "Unified MCP Gateway with all tools (sequential-thinking, context7, magic, playwright, serena, morphllm, tavily, chrome-devtools, git, puppeteer)",
"install_method": "airis_gateway",
refactor: PM Agent complete independence from external MCP servers (#439) * refactor: PM Agent complete independence from external MCP servers ## Summary Implement graceful degradation to ensure PM Agent operates fully without any MCP server dependencies. MCP servers now serve as optional enhancements rather than required components. ## Changes ### Responsibility Separation (NEW) - **PM Agent**: Development workflow orchestration (PDCA cycle, task management) - **mindbase**: Memory management (long-term, freshness, error learning) - **Built-in memory**: Session-internal context (volatile) ### 3-Layer Memory Architecture with Fallbacks 1. **Built-in Memory** [OPTIONAL]: Session context via MCP memory server 2. **mindbase** [OPTIONAL]: Long-term semantic search via airis-mcp-gateway 3. **Local Files** [ALWAYS]: Core functionality in docs/memory/ ### Graceful Degradation Implementation - All MCP operations marked with [ALWAYS] or [OPTIONAL] - Explicit IF/ELSE fallback logic for every MCP call - Dual storage: Always write to local files + optionally to mindbase - Smart lookup: Semantic search (if available) → Text search (always works) ### Key Fallback Strategies **Session Start**: - mindbase available: search_conversations() for semantic context - mindbase unavailable: Grep docs/memory/*.jsonl for text-based lookup **Error Detection**: - mindbase available: Semantic search for similar past errors - mindbase unavailable: Grep docs/mistakes/ + solutions_learned.jsonl **Knowledge Capture**: - Always: echo >> docs/memory/patterns_learned.jsonl (persistent) - Optional: mindbase.store() for semantic search enhancement ## Benefits - ✅ Zero external dependencies (100% functionality without MCP) - ✅ Enhanced capabilities when MCPs available (semantic search, freshness) - ✅ No functionality loss, only reduced search intelligence - ✅ Transparent degradation (no error messages, automatic fallback) ## Related Research - Serena MCP investigation: Exposes tools (not resources), memory = markdown files - mindbase superiority: PostgreSQL + pgvector > Serena memory features - Best practices alignment: /Users/kazuki/github/airis-mcp-gateway/docs/mcp-best-practices.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: add PR template and pre-commit config - Add structured PR template with Git workflow checklist - Add pre-commit hooks for secret detection and Conventional Commits - Enforce code quality gates (YAML/JSON/Markdown lint, shellcheck) NOTE: Execute pre-commit inside Docker container to avoid host pollution: docker compose exec workspace uv tool install pre-commit docker compose exec workspace pre-commit run --all-files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: update PM Agent context with token efficiency architecture - Add Layer 0 Bootstrap (150 tokens, 95% reduction) - Document Intent Classification System (5 complexity levels) - Add Progressive Loading strategy (5-layer) - Document mindbase integration incentive (38% savings) - Update with 2025-10-17 redesign details * refactor: PM Agent command with progressive loading - Replace auto-loading with User Request First philosophy - Add 5-layer progressive context loading - Implement intent classification system - Add workflow metrics collection (.jsonl) - Document graceful degradation strategy * fix: installer improvements Update installer logic for better reliability * docs: add comprehensive development documentation - Add architecture overview - Add PM Agent improvements analysis - Add parallel execution architecture - Add CLI install improvements - Add code style guide - Add project overview - Add install process analysis * docs: add research documentation Add LLM agent token efficiency research and analysis * docs: add suggested commands reference * docs: add session logs and testing documentation - Add session analysis logs - Add testing documentation * feat: migrate CLI to typer + rich for modern UX ## What Changed ### New CLI Architecture (typer + rich) - Created `superclaude/cli/` module with modern typer-based CLI - Replaced custom UI utilities with rich native features - Added type-safe command structure with automatic validation ### Commands Implemented - **install**: Interactive installation with rich UI (progress, panels) - **doctor**: System diagnostics with rich table output - **config**: API key management with format validation ### Technical Improvements - Dependencies: Added typer>=0.9.0, rich>=13.0.0, click>=8.0.0 - Entry Point: Updated pyproject.toml to use `superclaude.cli.app:cli_main` - Tests: Added comprehensive smoke tests (11 passed) ### User Experience Enhancements - Rich formatted help messages with panels and tables - Automatic input validation with retry loops - Clear error messages with actionable suggestions - Non-interactive mode support for CI/CD ## Testing ```bash uv run superclaude --help # ✓ Works uv run superclaude doctor # ✓ Rich table output uv run superclaude config show # ✓ API key management pytest tests/test_cli_smoke.py # ✓ 11 passed, 1 skipped ``` ## Migration Path - ✅ P0: Foundation complete (typer + rich + smoke tests) - 🔜 P1: Pydantic validation models (next sprint) - 🔜 P2: Enhanced error messages (next sprint) - 🔜 P3: API key retry loops (next sprint) ## Performance Impact - **Code Reduction**: Prepared for -300 lines (custom UI → rich) - **Type Safety**: Automatic validation from type hints - **Maintainability**: Framework primitives vs custom code 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate documentation directories Merged claudedocs/ into docs/research/ for consistent documentation structure. Changes: - Moved all claudedocs/*.md files to docs/research/ - Updated all path references in documentation (EN/KR) - Updated RULES.md and research.md command templates - Removed claudedocs/ directory - Removed ClaudeDocs/ from .gitignore Benefits: - Single source of truth for all research reports - PEP8-compliant lowercase directory naming - Clearer documentation organization - Prevents future claudedocs/ directory creation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: reduce /sc:pm command output from 1652 to 15 lines - Remove 1637 lines of documentation from command file - Keep only minimal bootstrap message - 99% token reduction on command execution - Detailed specs remain in superclaude/agents/pm-agent.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: split PM Agent into execution workflows and guide - Reduce pm-agent.md from 735 to 429 lines (42% reduction) - Move philosophy/examples to docs/agents/pm-agent-guide.md - Execution workflows (PDCA, file ops) stay in pm-agent.md - Guide (examples, quality standards) read once when needed Token savings: - Agent loading: ~6K → ~3.5K tokens (42% reduction) - Total with pm.md: 71% overall reduction 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate PM Agent optimization and pending changes PM Agent optimization (already committed separately): - superclaude/commands/pm.md: 1652→14 lines - superclaude/agents/pm-agent.md: 735→429 lines - docs/agents/pm-agent-guide.md: new guide file Other pending changes: - setup: framework_docs, mcp, logger, remove ui.py - superclaude: __main__, cli/app, cli/commands/install - tests: test_ui updates - scripts: workflow metrics analysis tools - docs/memory: session state updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: simplify MCP installer to unified gateway with legacy mode ## Changes ### MCP Component (setup/components/mcp.py) - Simplified to single airis-mcp-gateway by default - Added legacy mode for individual official servers (sequential-thinking, context7, magic, playwright) - Dynamic prerequisites based on mode: - Default: uv + claude CLI only - Legacy: node (18+) + npm + claude CLI - Removed redundant server definitions ### CLI Integration - Added --legacy flag to setup/cli/commands/install.py - Added --legacy flag to superclaude/cli/commands/install.py - Config passes legacy_mode to component installer ## Benefits - ✅ Simpler: 1 gateway vs 9+ individual servers - ✅ Lighter: No Node.js/npm required (default mode) - ✅ Unified: All tools in one gateway (sequential-thinking, context7, magic, playwright, serena, morphllm, tavily, chrome-devtools, git, puppeteer) - ✅ Flexible: --legacy flag for official servers if needed ## Usage ```bash superclaude install # Default: airis-mcp-gateway (推奨) superclaude install --legacy # Legacy: individual official servers ``` 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename CoreComponent to FrameworkDocsComponent and add PM token tracking ## Changes ### Component Renaming (setup/components/) - Renamed CoreComponent → FrameworkDocsComponent for clarity - Updated all imports in __init__.py, agents.py, commands.py, mcp_docs.py, modes.py - Better reflects the actual purpose (framework documentation files) ### PM Agent Enhancement (superclaude/commands/pm.md) - Added token usage tracking instructions - PM Agent now reports: 1. Current token usage from system warnings 2. Percentage used (e.g., "27% used" for 54K/200K) 3. Status zone: 🟢 <75% | 🟡 75-85% | 🔴 >85% - Helps prevent token exhaustion during long sessions ### UI Utilities (setup/utils/ui.py) - Added new UI utility module for installer - Provides consistent user interface components ## Benefits - ✅ Clearer component naming (FrameworkDocs vs Core) - ✅ PM Agent token awareness for efficiency - ✅ Better visual feedback with status zones 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor(pm-agent): minimize output verbosity (471→284 lines, 40% reduction) **Problem**: PM Agent generated excessive output with redundant explanations - "System Status Report" with decorative formatting - Repeated "Common Tasks" lists user already knows - Verbose session start/end protocols - Duplicate file operations documentation **Solution**: Compress without losing functionality - Session Start: Reduced to symbol-only status (🟢 branch | nM nD | token%) - Session End: Compressed to essential actions only - File Operations: Consolidated from 2 sections to 1 line reference - Self-Improvement: 5 phases → 1 unified workflow - Output Rules: Explicit constraints to prevent Claude over-explanation **Quality Preservation**: - ✅ All core functions retained (PDCA, memory, patterns, mistakes) - ✅ PARALLEL Read/Write preserved (performance critical) - ✅ Workflow unchanged (session lifecycle intact) - ✅ Added output constraints (prevents verbose generation) **Reduction Method**: - Deleted: Explanatory text, examples, redundant sections - Retained: Action definitions, file paths, core workflows - Added: Explicit output constraints to enforce minimalism **Token Impact**: 40% reduction in agent documentation size **Before**: Verbose multi-section report with task lists **After**: Single line status: 🟢 integration | 15M 17D | 36% 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate MCP integration to unified gateway **Changes**: - Remove individual MCP server docs (superclaude/mcp/*.md) - Remove MCP server configs (superclaude/mcp/configs/*.json) - Delete MCP docs component (setup/components/mcp_docs.py) - Simplify installer (setup/core/installer.py) - Update components for unified gateway approach **Rationale**: - Unified gateway (airis-mcp-gateway) provides all MCP servers - Individual docs/configs no longer needed (managed centrally) - Reduces maintenance burden and file count - Simplifies installation process **Files Removed**: 17 MCP files (docs + configs) **Installer Changes**: Removed legacy MCP installation logic 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: update version and component metadata - Bump version (pyproject.toml, setup/__init__.py) - Update CLAUDE.md import service references - Reflect component structure changes 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-17 09:13:06 +09:00
"required": True,
},
}
self.mcp_servers_legacy = {
"sequential-thinking": {
"name": "sequential-thinking",
"description": "Multi-step problem solving and systematic analysis",
"npm_package": "@modelcontextprotocol/server-sequential-thinking",
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
"required": True,
},
2025-08-14 08:56:04 +05:30
"context7": {
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
"name": "context7",
2025-08-14 08:56:04 +05:30
"description": "Official library documentation and code examples",
"npm_package": "@upstash/context7-mcp",
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
"required": True,
2025-08-14 08:56:04 +05:30
},
"magic": {
"name": "magic",
"description": "Modern UI component generation and design systems",
"npm_package": "@21st-dev/magic",
"required": False,
"api_key_env": "TWENTYFIRST_API_KEY",
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
"api_key_description": "21st.dev API key for UI component generation",
2025-08-14 08:56:04 +05:30
},
"playwright": {
"name": "playwright",
"description": "Cross-browser E2E testing and automation",
"npm_package": "@playwright/mcp@latest",
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
"required": False,
},
2025-08-14 08:56:04 +05:30
}
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
refactor: PM Agent complete independence from external MCP servers (#439) * refactor: PM Agent complete independence from external MCP servers ## Summary Implement graceful degradation to ensure PM Agent operates fully without any MCP server dependencies. MCP servers now serve as optional enhancements rather than required components. ## Changes ### Responsibility Separation (NEW) - **PM Agent**: Development workflow orchestration (PDCA cycle, task management) - **mindbase**: Memory management (long-term, freshness, error learning) - **Built-in memory**: Session-internal context (volatile) ### 3-Layer Memory Architecture with Fallbacks 1. **Built-in Memory** [OPTIONAL]: Session context via MCP memory server 2. **mindbase** [OPTIONAL]: Long-term semantic search via airis-mcp-gateway 3. **Local Files** [ALWAYS]: Core functionality in docs/memory/ ### Graceful Degradation Implementation - All MCP operations marked with [ALWAYS] or [OPTIONAL] - Explicit IF/ELSE fallback logic for every MCP call - Dual storage: Always write to local files + optionally to mindbase - Smart lookup: Semantic search (if available) → Text search (always works) ### Key Fallback Strategies **Session Start**: - mindbase available: search_conversations() for semantic context - mindbase unavailable: Grep docs/memory/*.jsonl for text-based lookup **Error Detection**: - mindbase available: Semantic search for similar past errors - mindbase unavailable: Grep docs/mistakes/ + solutions_learned.jsonl **Knowledge Capture**: - Always: echo >> docs/memory/patterns_learned.jsonl (persistent) - Optional: mindbase.store() for semantic search enhancement ## Benefits - ✅ Zero external dependencies (100% functionality without MCP) - ✅ Enhanced capabilities when MCPs available (semantic search, freshness) - ✅ No functionality loss, only reduced search intelligence - ✅ Transparent degradation (no error messages, automatic fallback) ## Related Research - Serena MCP investigation: Exposes tools (not resources), memory = markdown files - mindbase superiority: PostgreSQL + pgvector > Serena memory features - Best practices alignment: /Users/kazuki/github/airis-mcp-gateway/docs/mcp-best-practices.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: add PR template and pre-commit config - Add structured PR template with Git workflow checklist - Add pre-commit hooks for secret detection and Conventional Commits - Enforce code quality gates (YAML/JSON/Markdown lint, shellcheck) NOTE: Execute pre-commit inside Docker container to avoid host pollution: docker compose exec workspace uv tool install pre-commit docker compose exec workspace pre-commit run --all-files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: update PM Agent context with token efficiency architecture - Add Layer 0 Bootstrap (150 tokens, 95% reduction) - Document Intent Classification System (5 complexity levels) - Add Progressive Loading strategy (5-layer) - Document mindbase integration incentive (38% savings) - Update with 2025-10-17 redesign details * refactor: PM Agent command with progressive loading - Replace auto-loading with User Request First philosophy - Add 5-layer progressive context loading - Implement intent classification system - Add workflow metrics collection (.jsonl) - Document graceful degradation strategy * fix: installer improvements Update installer logic for better reliability * docs: add comprehensive development documentation - Add architecture overview - Add PM Agent improvements analysis - Add parallel execution architecture - Add CLI install improvements - Add code style guide - Add project overview - Add install process analysis * docs: add research documentation Add LLM agent token efficiency research and analysis * docs: add suggested commands reference * docs: add session logs and testing documentation - Add session analysis logs - Add testing documentation * feat: migrate CLI to typer + rich for modern UX ## What Changed ### New CLI Architecture (typer + rich) - Created `superclaude/cli/` module with modern typer-based CLI - Replaced custom UI utilities with rich native features - Added type-safe command structure with automatic validation ### Commands Implemented - **install**: Interactive installation with rich UI (progress, panels) - **doctor**: System diagnostics with rich table output - **config**: API key management with format validation ### Technical Improvements - Dependencies: Added typer>=0.9.0, rich>=13.0.0, click>=8.0.0 - Entry Point: Updated pyproject.toml to use `superclaude.cli.app:cli_main` - Tests: Added comprehensive smoke tests (11 passed) ### User Experience Enhancements - Rich formatted help messages with panels and tables - Automatic input validation with retry loops - Clear error messages with actionable suggestions - Non-interactive mode support for CI/CD ## Testing ```bash uv run superclaude --help # ✓ Works uv run superclaude doctor # ✓ Rich table output uv run superclaude config show # ✓ API key management pytest tests/test_cli_smoke.py # ✓ 11 passed, 1 skipped ``` ## Migration Path - ✅ P0: Foundation complete (typer + rich + smoke tests) - 🔜 P1: Pydantic validation models (next sprint) - 🔜 P2: Enhanced error messages (next sprint) - 🔜 P3: API key retry loops (next sprint) ## Performance Impact - **Code Reduction**: Prepared for -300 lines (custom UI → rich) - **Type Safety**: Automatic validation from type hints - **Maintainability**: Framework primitives vs custom code 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate documentation directories Merged claudedocs/ into docs/research/ for consistent documentation structure. Changes: - Moved all claudedocs/*.md files to docs/research/ - Updated all path references in documentation (EN/KR) - Updated RULES.md and research.md command templates - Removed claudedocs/ directory - Removed ClaudeDocs/ from .gitignore Benefits: - Single source of truth for all research reports - PEP8-compliant lowercase directory naming - Clearer documentation organization - Prevents future claudedocs/ directory creation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: reduce /sc:pm command output from 1652 to 15 lines - Remove 1637 lines of documentation from command file - Keep only minimal bootstrap message - 99% token reduction on command execution - Detailed specs remain in superclaude/agents/pm-agent.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: split PM Agent into execution workflows and guide - Reduce pm-agent.md from 735 to 429 lines (42% reduction) - Move philosophy/examples to docs/agents/pm-agent-guide.md - Execution workflows (PDCA, file ops) stay in pm-agent.md - Guide (examples, quality standards) read once when needed Token savings: - Agent loading: ~6K → ~3.5K tokens (42% reduction) - Total with pm.md: 71% overall reduction 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate PM Agent optimization and pending changes PM Agent optimization (already committed separately): - superclaude/commands/pm.md: 1652→14 lines - superclaude/agents/pm-agent.md: 735→429 lines - docs/agents/pm-agent-guide.md: new guide file Other pending changes: - setup: framework_docs, mcp, logger, remove ui.py - superclaude: __main__, cli/app, cli/commands/install - tests: test_ui updates - scripts: workflow metrics analysis tools - docs/memory: session state updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: simplify MCP installer to unified gateway with legacy mode ## Changes ### MCP Component (setup/components/mcp.py) - Simplified to single airis-mcp-gateway by default - Added legacy mode for individual official servers (sequential-thinking, context7, magic, playwright) - Dynamic prerequisites based on mode: - Default: uv + claude CLI only - Legacy: node (18+) + npm + claude CLI - Removed redundant server definitions ### CLI Integration - Added --legacy flag to setup/cli/commands/install.py - Added --legacy flag to superclaude/cli/commands/install.py - Config passes legacy_mode to component installer ## Benefits - ✅ Simpler: 1 gateway vs 9+ individual servers - ✅ Lighter: No Node.js/npm required (default mode) - ✅ Unified: All tools in one gateway (sequential-thinking, context7, magic, playwright, serena, morphllm, tavily, chrome-devtools, git, puppeteer) - ✅ Flexible: --legacy flag for official servers if needed ## Usage ```bash superclaude install # Default: airis-mcp-gateway (推奨) superclaude install --legacy # Legacy: individual official servers ``` 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename CoreComponent to FrameworkDocsComponent and add PM token tracking ## Changes ### Component Renaming (setup/components/) - Renamed CoreComponent → FrameworkDocsComponent for clarity - Updated all imports in __init__.py, agents.py, commands.py, mcp_docs.py, modes.py - Better reflects the actual purpose (framework documentation files) ### PM Agent Enhancement (superclaude/commands/pm.md) - Added token usage tracking instructions - PM Agent now reports: 1. Current token usage from system warnings 2. Percentage used (e.g., "27% used" for 54K/200K) 3. Status zone: 🟢 <75% | 🟡 75-85% | 🔴 >85% - Helps prevent token exhaustion during long sessions ### UI Utilities (setup/utils/ui.py) - Added new UI utility module for installer - Provides consistent user interface components ## Benefits - ✅ Clearer component naming (FrameworkDocs vs Core) - ✅ PM Agent token awareness for efficiency - ✅ Better visual feedback with status zones 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor(pm-agent): minimize output verbosity (471→284 lines, 40% reduction) **Problem**: PM Agent generated excessive output with redundant explanations - "System Status Report" with decorative formatting - Repeated "Common Tasks" lists user already knows - Verbose session start/end protocols - Duplicate file operations documentation **Solution**: Compress without losing functionality - Session Start: Reduced to symbol-only status (🟢 branch | nM nD | token%) - Session End: Compressed to essential actions only - File Operations: Consolidated from 2 sections to 1 line reference - Self-Improvement: 5 phases → 1 unified workflow - Output Rules: Explicit constraints to prevent Claude over-explanation **Quality Preservation**: - ✅ All core functions retained (PDCA, memory, patterns, mistakes) - ✅ PARALLEL Read/Write preserved (performance critical) - ✅ Workflow unchanged (session lifecycle intact) - ✅ Added output constraints (prevents verbose generation) **Reduction Method**: - Deleted: Explanatory text, examples, redundant sections - Retained: Action definitions, file paths, core workflows - Added: Explicit output constraints to enforce minimalism **Token Impact**: 40% reduction in agent documentation size **Before**: Verbose multi-section report with task lists **After**: Single line status: 🟢 integration | 15M 17D | 36% 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate MCP integration to unified gateway **Changes**: - Remove individual MCP server docs (superclaude/mcp/*.md) - Remove MCP server configs (superclaude/mcp/configs/*.json) - Delete MCP docs component (setup/components/mcp_docs.py) - Simplify installer (setup/core/installer.py) - Update components for unified gateway approach **Rationale**: - Unified gateway (airis-mcp-gateway) provides all MCP servers - Individual docs/configs no longer needed (managed centrally) - Reduces maintenance burden and file count - Simplifies installation process **Files Removed**: 17 MCP files (docs + configs) **Installer Changes**: Removed legacy MCP installation logic 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: update version and component metadata - Bump version (pyproject.toml, setup/__init__.py) - Update CLAUDE.md import service references - Reflect component structure changes 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-17 09:13:06 +09:00
# Default to unified gateway
self.mcp_servers = self.mcp_servers_default
2025-08-14 08:56:04 +05:30
def get_metadata(self) -> Dict[str, str]:
"""Get component metadata"""
return {
"name": "mcp",
"version": __version__,
refactor: PM Agent complete independence from external MCP servers (#439) * refactor: PM Agent complete independence from external MCP servers ## Summary Implement graceful degradation to ensure PM Agent operates fully without any MCP server dependencies. MCP servers now serve as optional enhancements rather than required components. ## Changes ### Responsibility Separation (NEW) - **PM Agent**: Development workflow orchestration (PDCA cycle, task management) - **mindbase**: Memory management (long-term, freshness, error learning) - **Built-in memory**: Session-internal context (volatile) ### 3-Layer Memory Architecture with Fallbacks 1. **Built-in Memory** [OPTIONAL]: Session context via MCP memory server 2. **mindbase** [OPTIONAL]: Long-term semantic search via airis-mcp-gateway 3. **Local Files** [ALWAYS]: Core functionality in docs/memory/ ### Graceful Degradation Implementation - All MCP operations marked with [ALWAYS] or [OPTIONAL] - Explicit IF/ELSE fallback logic for every MCP call - Dual storage: Always write to local files + optionally to mindbase - Smart lookup: Semantic search (if available) → Text search (always works) ### Key Fallback Strategies **Session Start**: - mindbase available: search_conversations() for semantic context - mindbase unavailable: Grep docs/memory/*.jsonl for text-based lookup **Error Detection**: - mindbase available: Semantic search for similar past errors - mindbase unavailable: Grep docs/mistakes/ + solutions_learned.jsonl **Knowledge Capture**: - Always: echo >> docs/memory/patterns_learned.jsonl (persistent) - Optional: mindbase.store() for semantic search enhancement ## Benefits - ✅ Zero external dependencies (100% functionality without MCP) - ✅ Enhanced capabilities when MCPs available (semantic search, freshness) - ✅ No functionality loss, only reduced search intelligence - ✅ Transparent degradation (no error messages, automatic fallback) ## Related Research - Serena MCP investigation: Exposes tools (not resources), memory = markdown files - mindbase superiority: PostgreSQL + pgvector > Serena memory features - Best practices alignment: /Users/kazuki/github/airis-mcp-gateway/docs/mcp-best-practices.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: add PR template and pre-commit config - Add structured PR template with Git workflow checklist - Add pre-commit hooks for secret detection and Conventional Commits - Enforce code quality gates (YAML/JSON/Markdown lint, shellcheck) NOTE: Execute pre-commit inside Docker container to avoid host pollution: docker compose exec workspace uv tool install pre-commit docker compose exec workspace pre-commit run --all-files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: update PM Agent context with token efficiency architecture - Add Layer 0 Bootstrap (150 tokens, 95% reduction) - Document Intent Classification System (5 complexity levels) - Add Progressive Loading strategy (5-layer) - Document mindbase integration incentive (38% savings) - Update with 2025-10-17 redesign details * refactor: PM Agent command with progressive loading - Replace auto-loading with User Request First philosophy - Add 5-layer progressive context loading - Implement intent classification system - Add workflow metrics collection (.jsonl) - Document graceful degradation strategy * fix: installer improvements Update installer logic for better reliability * docs: add comprehensive development documentation - Add architecture overview - Add PM Agent improvements analysis - Add parallel execution architecture - Add CLI install improvements - Add code style guide - Add project overview - Add install process analysis * docs: add research documentation Add LLM agent token efficiency research and analysis * docs: add suggested commands reference * docs: add session logs and testing documentation - Add session analysis logs - Add testing documentation * feat: migrate CLI to typer + rich for modern UX ## What Changed ### New CLI Architecture (typer + rich) - Created `superclaude/cli/` module with modern typer-based CLI - Replaced custom UI utilities with rich native features - Added type-safe command structure with automatic validation ### Commands Implemented - **install**: Interactive installation with rich UI (progress, panels) - **doctor**: System diagnostics with rich table output - **config**: API key management with format validation ### Technical Improvements - Dependencies: Added typer>=0.9.0, rich>=13.0.0, click>=8.0.0 - Entry Point: Updated pyproject.toml to use `superclaude.cli.app:cli_main` - Tests: Added comprehensive smoke tests (11 passed) ### User Experience Enhancements - Rich formatted help messages with panels and tables - Automatic input validation with retry loops - Clear error messages with actionable suggestions - Non-interactive mode support for CI/CD ## Testing ```bash uv run superclaude --help # ✓ Works uv run superclaude doctor # ✓ Rich table output uv run superclaude config show # ✓ API key management pytest tests/test_cli_smoke.py # ✓ 11 passed, 1 skipped ``` ## Migration Path - ✅ P0: Foundation complete (typer + rich + smoke tests) - 🔜 P1: Pydantic validation models (next sprint) - 🔜 P2: Enhanced error messages (next sprint) - 🔜 P3: API key retry loops (next sprint) ## Performance Impact - **Code Reduction**: Prepared for -300 lines (custom UI → rich) - **Type Safety**: Automatic validation from type hints - **Maintainability**: Framework primitives vs custom code 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate documentation directories Merged claudedocs/ into docs/research/ for consistent documentation structure. Changes: - Moved all claudedocs/*.md files to docs/research/ - Updated all path references in documentation (EN/KR) - Updated RULES.md and research.md command templates - Removed claudedocs/ directory - Removed ClaudeDocs/ from .gitignore Benefits: - Single source of truth for all research reports - PEP8-compliant lowercase directory naming - Clearer documentation organization - Prevents future claudedocs/ directory creation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: reduce /sc:pm command output from 1652 to 15 lines - Remove 1637 lines of documentation from command file - Keep only minimal bootstrap message - 99% token reduction on command execution - Detailed specs remain in superclaude/agents/pm-agent.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: split PM Agent into execution workflows and guide - Reduce pm-agent.md from 735 to 429 lines (42% reduction) - Move philosophy/examples to docs/agents/pm-agent-guide.md - Execution workflows (PDCA, file ops) stay in pm-agent.md - Guide (examples, quality standards) read once when needed Token savings: - Agent loading: ~6K → ~3.5K tokens (42% reduction) - Total with pm.md: 71% overall reduction 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate PM Agent optimization and pending changes PM Agent optimization (already committed separately): - superclaude/commands/pm.md: 1652→14 lines - superclaude/agents/pm-agent.md: 735→429 lines - docs/agents/pm-agent-guide.md: new guide file Other pending changes: - setup: framework_docs, mcp, logger, remove ui.py - superclaude: __main__, cli/app, cli/commands/install - tests: test_ui updates - scripts: workflow metrics analysis tools - docs/memory: session state updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: simplify MCP installer to unified gateway with legacy mode ## Changes ### MCP Component (setup/components/mcp.py) - Simplified to single airis-mcp-gateway by default - Added legacy mode for individual official servers (sequential-thinking, context7, magic, playwright) - Dynamic prerequisites based on mode: - Default: uv + claude CLI only - Legacy: node (18+) + npm + claude CLI - Removed redundant server definitions ### CLI Integration - Added --legacy flag to setup/cli/commands/install.py - Added --legacy flag to superclaude/cli/commands/install.py - Config passes legacy_mode to component installer ## Benefits - ✅ Simpler: 1 gateway vs 9+ individual servers - ✅ Lighter: No Node.js/npm required (default mode) - ✅ Unified: All tools in one gateway (sequential-thinking, context7, magic, playwright, serena, morphllm, tavily, chrome-devtools, git, puppeteer) - ✅ Flexible: --legacy flag for official servers if needed ## Usage ```bash superclaude install # Default: airis-mcp-gateway (推奨) superclaude install --legacy # Legacy: individual official servers ``` 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename CoreComponent to FrameworkDocsComponent and add PM token tracking ## Changes ### Component Renaming (setup/components/) - Renamed CoreComponent → FrameworkDocsComponent for clarity - Updated all imports in __init__.py, agents.py, commands.py, mcp_docs.py, modes.py - Better reflects the actual purpose (framework documentation files) ### PM Agent Enhancement (superclaude/commands/pm.md) - Added token usage tracking instructions - PM Agent now reports: 1. Current token usage from system warnings 2. Percentage used (e.g., "27% used" for 54K/200K) 3. Status zone: 🟢 <75% | 🟡 75-85% | 🔴 >85% - Helps prevent token exhaustion during long sessions ### UI Utilities (setup/utils/ui.py) - Added new UI utility module for installer - Provides consistent user interface components ## Benefits - ✅ Clearer component naming (FrameworkDocs vs Core) - ✅ PM Agent token awareness for efficiency - ✅ Better visual feedback with status zones 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor(pm-agent): minimize output verbosity (471→284 lines, 40% reduction) **Problem**: PM Agent generated excessive output with redundant explanations - "System Status Report" with decorative formatting - Repeated "Common Tasks" lists user already knows - Verbose session start/end protocols - Duplicate file operations documentation **Solution**: Compress without losing functionality - Session Start: Reduced to symbol-only status (🟢 branch | nM nD | token%) - Session End: Compressed to essential actions only - File Operations: Consolidated from 2 sections to 1 line reference - Self-Improvement: 5 phases → 1 unified workflow - Output Rules: Explicit constraints to prevent Claude over-explanation **Quality Preservation**: - ✅ All core functions retained (PDCA, memory, patterns, mistakes) - ✅ PARALLEL Read/Write preserved (performance critical) - ✅ Workflow unchanged (session lifecycle intact) - ✅ Added output constraints (prevents verbose generation) **Reduction Method**: - Deleted: Explanatory text, examples, redundant sections - Retained: Action definitions, file paths, core workflows - Added: Explicit output constraints to enforce minimalism **Token Impact**: 40% reduction in agent documentation size **Before**: Verbose multi-section report with task lists **After**: Single line status: 🟢 integration | 15M 17D | 36% 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate MCP integration to unified gateway **Changes**: - Remove individual MCP server docs (superclaude/mcp/*.md) - Remove MCP server configs (superclaude/mcp/configs/*.json) - Delete MCP docs component (setup/components/mcp_docs.py) - Simplify installer (setup/core/installer.py) - Update components for unified gateway approach **Rationale**: - Unified gateway (airis-mcp-gateway) provides all MCP servers - Individual docs/configs no longer needed (managed centrally) - Reduces maintenance burden and file count - Simplifies installation process **Files Removed**: 17 MCP files (docs + configs) **Installer Changes**: Removed legacy MCP installation logic 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: update version and component metadata - Bump version (pyproject.toml, setup/__init__.py) - Update CLAUDE.md import service references - Reflect component structure changes 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-17 09:13:06 +09:00
"description": "Unified MCP Gateway (airis-mcp-gateway) with all integrated tools",
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
"category": "integration",
2025-08-14 08:56:04 +05:30
}
Fixed Some Bugs (#355) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> --------- Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>
2025-09-13 17:28:52 +05:30
def is_reinstallable(self) -> bool:
"""This component manages sub-components (servers) and should be re-run."""
return True
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
def _run_command_cross_platform(
self, cmd: List[str], **kwargs
) -> subprocess.CompletedProcess:
"""
Run a command with proper cross-platform shell handling.
Args:
cmd: Command as list of strings
**kwargs: Additional subprocess.run arguments
Returns:
CompletedProcess result
"""
if platform.system() == "Windows":
Fixes and improvement (#393) * The -i flag has been removed from the `_run_command_cross_platform` function in `setup/components/mcp.py`. * fix: Prevent installer from hanging during MCP installation The SuperClaude installer was hanging during the installation of MCP components on non-Windows systems. This was caused by the use of an interactive shell (`-i`) when executing the `claude mcp add` command. The interactive shell would attempt to read from standard input, causing the process to be suspended by the shell. This commit fixes the issue by removing the `-i` flag from the `_run_command_cross_platform` function in `setup/components/mcp.py`. This ensures that the installation process runs non-interactively and completes without hanging. * fix: Add 'cmd /c' for Windows and refactor shell execution This commit resolves an issue with `npx` command execution on Windows by prepending `cmd /c` to the command. It also refactors the shell command execution for non-Windows systems to use the `executable` argument in `subprocess.run` for a cleaner and more robust implementation. * fix: Add 'cmd /c' for Windows and refactor shell execution This commit resolves an issue with `npx` command execution on Windows by prepending `cmd /c` to the command. It also refactors the shell command execution for non-Windows systems to use the `executable` argument in `subprocess.run` for a cleaner and more robust implementation. * docs: Update Chrome DevTools MCP documentation This commit updates the documentation for the Chrome DevTools MCP server to be more comprehensive and consistent with the existing documentation structure. The file `SuperClaude/MCP/MCP_Chrome-DevTools.md` has been updated with detailed information about the server's purpose, triggers, and usage examples. * docs: Update documentation for Chrome DevTools MCP This commit updates the main README.md and the MCP servers user guide to include information about the new Chrome DevTools MCP server. The documentation has been updated to reflect the new server count and provide details about the new server's functionality. ---------
2025-09-26 18:27:19 +05:30
# On Windows, wrap command in 'cmd /c' to properly handle commands like npx
cmd = ["cmd", "/c"] + cmd
return subprocess.run(cmd, **kwargs)
else:
# macOS/Linux: Use string format with proper shell to support aliases
cmd_str = " ".join(shlex.quote(str(arg)) for arg in cmd)
Fixes and improvement (#393) * The -i flag has been removed from the `_run_command_cross_platform` function in `setup/components/mcp.py`. * fix: Prevent installer from hanging during MCP installation The SuperClaude installer was hanging during the installation of MCP components on non-Windows systems. This was caused by the use of an interactive shell (`-i`) when executing the `claude mcp add` command. The interactive shell would attempt to read from standard input, causing the process to be suspended by the shell. This commit fixes the issue by removing the `-i` flag from the `_run_command_cross_platform` function in `setup/components/mcp.py`. This ensures that the installation process runs non-interactively and completes without hanging. * fix: Add 'cmd /c' for Windows and refactor shell execution This commit resolves an issue with `npx` command execution on Windows by prepending `cmd /c` to the command. It also refactors the shell command execution for non-Windows systems to use the `executable` argument in `subprocess.run` for a cleaner and more robust implementation. * fix: Add 'cmd /c' for Windows and refactor shell execution This commit resolves an issue with `npx` command execution on Windows by prepending `cmd /c` to the command. It also refactors the shell command execution for non-Windows systems to use the `executable` argument in `subprocess.run` for a cleaner and more robust implementation. * docs: Update Chrome DevTools MCP documentation This commit updates the documentation for the Chrome DevTools MCP server to be more comprehensive and consistent with the existing documentation structure. The file `SuperClaude/MCP/MCP_Chrome-DevTools.md` has been updated with detailed information about the server's purpose, triggers, and usage examples. * docs: Update documentation for Chrome DevTools MCP This commit updates the main README.md and the MCP servers user guide to include information about the new Chrome DevTools MCP server. The documentation has been updated to reflect the new server count and provide details about the new server's functionality. ---------
2025-09-26 18:27:19 +05:30
# Use the user's shell to execute the command, supporting aliases
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
user_shell = os.environ.get("SHELL", "/bin/bash")
return subprocess.run(
cmd_str, shell=True, env=os.environ, executable=user_shell, **kwargs
)
def validate_prerequisites(
self, installSubPath: Optional[Path] = None
) -> Tuple[bool, List[str]]:
refactor: PM Agent complete independence from external MCP servers (#439) * refactor: PM Agent complete independence from external MCP servers ## Summary Implement graceful degradation to ensure PM Agent operates fully without any MCP server dependencies. MCP servers now serve as optional enhancements rather than required components. ## Changes ### Responsibility Separation (NEW) - **PM Agent**: Development workflow orchestration (PDCA cycle, task management) - **mindbase**: Memory management (long-term, freshness, error learning) - **Built-in memory**: Session-internal context (volatile) ### 3-Layer Memory Architecture with Fallbacks 1. **Built-in Memory** [OPTIONAL]: Session context via MCP memory server 2. **mindbase** [OPTIONAL]: Long-term semantic search via airis-mcp-gateway 3. **Local Files** [ALWAYS]: Core functionality in docs/memory/ ### Graceful Degradation Implementation - All MCP operations marked with [ALWAYS] or [OPTIONAL] - Explicit IF/ELSE fallback logic for every MCP call - Dual storage: Always write to local files + optionally to mindbase - Smart lookup: Semantic search (if available) → Text search (always works) ### Key Fallback Strategies **Session Start**: - mindbase available: search_conversations() for semantic context - mindbase unavailable: Grep docs/memory/*.jsonl for text-based lookup **Error Detection**: - mindbase available: Semantic search for similar past errors - mindbase unavailable: Grep docs/mistakes/ + solutions_learned.jsonl **Knowledge Capture**: - Always: echo >> docs/memory/patterns_learned.jsonl (persistent) - Optional: mindbase.store() for semantic search enhancement ## Benefits - ✅ Zero external dependencies (100% functionality without MCP) - ✅ Enhanced capabilities when MCPs available (semantic search, freshness) - ✅ No functionality loss, only reduced search intelligence - ✅ Transparent degradation (no error messages, automatic fallback) ## Related Research - Serena MCP investigation: Exposes tools (not resources), memory = markdown files - mindbase superiority: PostgreSQL + pgvector > Serena memory features - Best practices alignment: /Users/kazuki/github/airis-mcp-gateway/docs/mcp-best-practices.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: add PR template and pre-commit config - Add structured PR template with Git workflow checklist - Add pre-commit hooks for secret detection and Conventional Commits - Enforce code quality gates (YAML/JSON/Markdown lint, shellcheck) NOTE: Execute pre-commit inside Docker container to avoid host pollution: docker compose exec workspace uv tool install pre-commit docker compose exec workspace pre-commit run --all-files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: update PM Agent context with token efficiency architecture - Add Layer 0 Bootstrap (150 tokens, 95% reduction) - Document Intent Classification System (5 complexity levels) - Add Progressive Loading strategy (5-layer) - Document mindbase integration incentive (38% savings) - Update with 2025-10-17 redesign details * refactor: PM Agent command with progressive loading - Replace auto-loading with User Request First philosophy - Add 5-layer progressive context loading - Implement intent classification system - Add workflow metrics collection (.jsonl) - Document graceful degradation strategy * fix: installer improvements Update installer logic for better reliability * docs: add comprehensive development documentation - Add architecture overview - Add PM Agent improvements analysis - Add parallel execution architecture - Add CLI install improvements - Add code style guide - Add project overview - Add install process analysis * docs: add research documentation Add LLM agent token efficiency research and analysis * docs: add suggested commands reference * docs: add session logs and testing documentation - Add session analysis logs - Add testing documentation * feat: migrate CLI to typer + rich for modern UX ## What Changed ### New CLI Architecture (typer + rich) - Created `superclaude/cli/` module with modern typer-based CLI - Replaced custom UI utilities with rich native features - Added type-safe command structure with automatic validation ### Commands Implemented - **install**: Interactive installation with rich UI (progress, panels) - **doctor**: System diagnostics with rich table output - **config**: API key management with format validation ### Technical Improvements - Dependencies: Added typer>=0.9.0, rich>=13.0.0, click>=8.0.0 - Entry Point: Updated pyproject.toml to use `superclaude.cli.app:cli_main` - Tests: Added comprehensive smoke tests (11 passed) ### User Experience Enhancements - Rich formatted help messages with panels and tables - Automatic input validation with retry loops - Clear error messages with actionable suggestions - Non-interactive mode support for CI/CD ## Testing ```bash uv run superclaude --help # ✓ Works uv run superclaude doctor # ✓ Rich table output uv run superclaude config show # ✓ API key management pytest tests/test_cli_smoke.py # ✓ 11 passed, 1 skipped ``` ## Migration Path - ✅ P0: Foundation complete (typer + rich + smoke tests) - 🔜 P1: Pydantic validation models (next sprint) - 🔜 P2: Enhanced error messages (next sprint) - 🔜 P3: API key retry loops (next sprint) ## Performance Impact - **Code Reduction**: Prepared for -300 lines (custom UI → rich) - **Type Safety**: Automatic validation from type hints - **Maintainability**: Framework primitives vs custom code 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate documentation directories Merged claudedocs/ into docs/research/ for consistent documentation structure. Changes: - Moved all claudedocs/*.md files to docs/research/ - Updated all path references in documentation (EN/KR) - Updated RULES.md and research.md command templates - Removed claudedocs/ directory - Removed ClaudeDocs/ from .gitignore Benefits: - Single source of truth for all research reports - PEP8-compliant lowercase directory naming - Clearer documentation organization - Prevents future claudedocs/ directory creation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: reduce /sc:pm command output from 1652 to 15 lines - Remove 1637 lines of documentation from command file - Keep only minimal bootstrap message - 99% token reduction on command execution - Detailed specs remain in superclaude/agents/pm-agent.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: split PM Agent into execution workflows and guide - Reduce pm-agent.md from 735 to 429 lines (42% reduction) - Move philosophy/examples to docs/agents/pm-agent-guide.md - Execution workflows (PDCA, file ops) stay in pm-agent.md - Guide (examples, quality standards) read once when needed Token savings: - Agent loading: ~6K → ~3.5K tokens (42% reduction) - Total with pm.md: 71% overall reduction 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate PM Agent optimization and pending changes PM Agent optimization (already committed separately): - superclaude/commands/pm.md: 1652→14 lines - superclaude/agents/pm-agent.md: 735→429 lines - docs/agents/pm-agent-guide.md: new guide file Other pending changes: - setup: framework_docs, mcp, logger, remove ui.py - superclaude: __main__, cli/app, cli/commands/install - tests: test_ui updates - scripts: workflow metrics analysis tools - docs/memory: session state updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: simplify MCP installer to unified gateway with legacy mode ## Changes ### MCP Component (setup/components/mcp.py) - Simplified to single airis-mcp-gateway by default - Added legacy mode for individual official servers (sequential-thinking, context7, magic, playwright) - Dynamic prerequisites based on mode: - Default: uv + claude CLI only - Legacy: node (18+) + npm + claude CLI - Removed redundant server definitions ### CLI Integration - Added --legacy flag to setup/cli/commands/install.py - Added --legacy flag to superclaude/cli/commands/install.py - Config passes legacy_mode to component installer ## Benefits - ✅ Simpler: 1 gateway vs 9+ individual servers - ✅ Lighter: No Node.js/npm required (default mode) - ✅ Unified: All tools in one gateway (sequential-thinking, context7, magic, playwright, serena, morphllm, tavily, chrome-devtools, git, puppeteer) - ✅ Flexible: --legacy flag for official servers if needed ## Usage ```bash superclaude install # Default: airis-mcp-gateway (推奨) superclaude install --legacy # Legacy: individual official servers ``` 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename CoreComponent to FrameworkDocsComponent and add PM token tracking ## Changes ### Component Renaming (setup/components/) - Renamed CoreComponent → FrameworkDocsComponent for clarity - Updated all imports in __init__.py, agents.py, commands.py, mcp_docs.py, modes.py - Better reflects the actual purpose (framework documentation files) ### PM Agent Enhancement (superclaude/commands/pm.md) - Added token usage tracking instructions - PM Agent now reports: 1. Current token usage from system warnings 2. Percentage used (e.g., "27% used" for 54K/200K) 3. Status zone: 🟢 <75% | 🟡 75-85% | 🔴 >85% - Helps prevent token exhaustion during long sessions ### UI Utilities (setup/utils/ui.py) - Added new UI utility module for installer - Provides consistent user interface components ## Benefits - ✅ Clearer component naming (FrameworkDocs vs Core) - ✅ PM Agent token awareness for efficiency - ✅ Better visual feedback with status zones 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor(pm-agent): minimize output verbosity (471→284 lines, 40% reduction) **Problem**: PM Agent generated excessive output with redundant explanations - "System Status Report" with decorative formatting - Repeated "Common Tasks" lists user already knows - Verbose session start/end protocols - Duplicate file operations documentation **Solution**: Compress without losing functionality - Session Start: Reduced to symbol-only status (🟢 branch | nM nD | token%) - Session End: Compressed to essential actions only - File Operations: Consolidated from 2 sections to 1 line reference - Self-Improvement: 5 phases → 1 unified workflow - Output Rules: Explicit constraints to prevent Claude over-explanation **Quality Preservation**: - ✅ All core functions retained (PDCA, memory, patterns, mistakes) - ✅ PARALLEL Read/Write preserved (performance critical) - ✅ Workflow unchanged (session lifecycle intact) - ✅ Added output constraints (prevents verbose generation) **Reduction Method**: - Deleted: Explanatory text, examples, redundant sections - Retained: Action definitions, file paths, core workflows - Added: Explicit output constraints to enforce minimalism **Token Impact**: 40% reduction in agent documentation size **Before**: Verbose multi-section report with task lists **After**: Single line status: 🟢 integration | 15M 17D | 36% 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate MCP integration to unified gateway **Changes**: - Remove individual MCP server docs (superclaude/mcp/*.md) - Remove MCP server configs (superclaude/mcp/configs/*.json) - Delete MCP docs component (setup/components/mcp_docs.py) - Simplify installer (setup/core/installer.py) - Update components for unified gateway approach **Rationale**: - Unified gateway (airis-mcp-gateway) provides all MCP servers - Individual docs/configs no longer needed (managed centrally) - Reduces maintenance burden and file count - Simplifies installation process **Files Removed**: 17 MCP files (docs + configs) **Installer Changes**: Removed legacy MCP installation logic 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: update version and component metadata - Bump version (pyproject.toml, setup/__init__.py) - Update CLAUDE.md import service references - Reflect component structure changes 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-17 09:13:06 +09:00
"""Check prerequisites (varies based on legacy mode)"""
2025-08-14 08:56:04 +05:30
errors = []
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
refactor: PM Agent complete independence from external MCP servers (#439) * refactor: PM Agent complete independence from external MCP servers ## Summary Implement graceful degradation to ensure PM Agent operates fully without any MCP server dependencies. MCP servers now serve as optional enhancements rather than required components. ## Changes ### Responsibility Separation (NEW) - **PM Agent**: Development workflow orchestration (PDCA cycle, task management) - **mindbase**: Memory management (long-term, freshness, error learning) - **Built-in memory**: Session-internal context (volatile) ### 3-Layer Memory Architecture with Fallbacks 1. **Built-in Memory** [OPTIONAL]: Session context via MCP memory server 2. **mindbase** [OPTIONAL]: Long-term semantic search via airis-mcp-gateway 3. **Local Files** [ALWAYS]: Core functionality in docs/memory/ ### Graceful Degradation Implementation - All MCP operations marked with [ALWAYS] or [OPTIONAL] - Explicit IF/ELSE fallback logic for every MCP call - Dual storage: Always write to local files + optionally to mindbase - Smart lookup: Semantic search (if available) → Text search (always works) ### Key Fallback Strategies **Session Start**: - mindbase available: search_conversations() for semantic context - mindbase unavailable: Grep docs/memory/*.jsonl for text-based lookup **Error Detection**: - mindbase available: Semantic search for similar past errors - mindbase unavailable: Grep docs/mistakes/ + solutions_learned.jsonl **Knowledge Capture**: - Always: echo >> docs/memory/patterns_learned.jsonl (persistent) - Optional: mindbase.store() for semantic search enhancement ## Benefits - ✅ Zero external dependencies (100% functionality without MCP) - ✅ Enhanced capabilities when MCPs available (semantic search, freshness) - ✅ No functionality loss, only reduced search intelligence - ✅ Transparent degradation (no error messages, automatic fallback) ## Related Research - Serena MCP investigation: Exposes tools (not resources), memory = markdown files - mindbase superiority: PostgreSQL + pgvector > Serena memory features - Best practices alignment: /Users/kazuki/github/airis-mcp-gateway/docs/mcp-best-practices.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: add PR template and pre-commit config - Add structured PR template with Git workflow checklist - Add pre-commit hooks for secret detection and Conventional Commits - Enforce code quality gates (YAML/JSON/Markdown lint, shellcheck) NOTE: Execute pre-commit inside Docker container to avoid host pollution: docker compose exec workspace uv tool install pre-commit docker compose exec workspace pre-commit run --all-files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: update PM Agent context with token efficiency architecture - Add Layer 0 Bootstrap (150 tokens, 95% reduction) - Document Intent Classification System (5 complexity levels) - Add Progressive Loading strategy (5-layer) - Document mindbase integration incentive (38% savings) - Update with 2025-10-17 redesign details * refactor: PM Agent command with progressive loading - Replace auto-loading with User Request First philosophy - Add 5-layer progressive context loading - Implement intent classification system - Add workflow metrics collection (.jsonl) - Document graceful degradation strategy * fix: installer improvements Update installer logic for better reliability * docs: add comprehensive development documentation - Add architecture overview - Add PM Agent improvements analysis - Add parallel execution architecture - Add CLI install improvements - Add code style guide - Add project overview - Add install process analysis * docs: add research documentation Add LLM agent token efficiency research and analysis * docs: add suggested commands reference * docs: add session logs and testing documentation - Add session analysis logs - Add testing documentation * feat: migrate CLI to typer + rich for modern UX ## What Changed ### New CLI Architecture (typer + rich) - Created `superclaude/cli/` module with modern typer-based CLI - Replaced custom UI utilities with rich native features - Added type-safe command structure with automatic validation ### Commands Implemented - **install**: Interactive installation with rich UI (progress, panels) - **doctor**: System diagnostics with rich table output - **config**: API key management with format validation ### Technical Improvements - Dependencies: Added typer>=0.9.0, rich>=13.0.0, click>=8.0.0 - Entry Point: Updated pyproject.toml to use `superclaude.cli.app:cli_main` - Tests: Added comprehensive smoke tests (11 passed) ### User Experience Enhancements - Rich formatted help messages with panels and tables - Automatic input validation with retry loops - Clear error messages with actionable suggestions - Non-interactive mode support for CI/CD ## Testing ```bash uv run superclaude --help # ✓ Works uv run superclaude doctor # ✓ Rich table output uv run superclaude config show # ✓ API key management pytest tests/test_cli_smoke.py # ✓ 11 passed, 1 skipped ``` ## Migration Path - ✅ P0: Foundation complete (typer + rich + smoke tests) - 🔜 P1: Pydantic validation models (next sprint) - 🔜 P2: Enhanced error messages (next sprint) - 🔜 P3: API key retry loops (next sprint) ## Performance Impact - **Code Reduction**: Prepared for -300 lines (custom UI → rich) - **Type Safety**: Automatic validation from type hints - **Maintainability**: Framework primitives vs custom code 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate documentation directories Merged claudedocs/ into docs/research/ for consistent documentation structure. Changes: - Moved all claudedocs/*.md files to docs/research/ - Updated all path references in documentation (EN/KR) - Updated RULES.md and research.md command templates - Removed claudedocs/ directory - Removed ClaudeDocs/ from .gitignore Benefits: - Single source of truth for all research reports - PEP8-compliant lowercase directory naming - Clearer documentation organization - Prevents future claudedocs/ directory creation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: reduce /sc:pm command output from 1652 to 15 lines - Remove 1637 lines of documentation from command file - Keep only minimal bootstrap message - 99% token reduction on command execution - Detailed specs remain in superclaude/agents/pm-agent.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: split PM Agent into execution workflows and guide - Reduce pm-agent.md from 735 to 429 lines (42% reduction) - Move philosophy/examples to docs/agents/pm-agent-guide.md - Execution workflows (PDCA, file ops) stay in pm-agent.md - Guide (examples, quality standards) read once when needed Token savings: - Agent loading: ~6K → ~3.5K tokens (42% reduction) - Total with pm.md: 71% overall reduction 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate PM Agent optimization and pending changes PM Agent optimization (already committed separately): - superclaude/commands/pm.md: 1652→14 lines - superclaude/agents/pm-agent.md: 735→429 lines - docs/agents/pm-agent-guide.md: new guide file Other pending changes: - setup: framework_docs, mcp, logger, remove ui.py - superclaude: __main__, cli/app, cli/commands/install - tests: test_ui updates - scripts: workflow metrics analysis tools - docs/memory: session state updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: simplify MCP installer to unified gateway with legacy mode ## Changes ### MCP Component (setup/components/mcp.py) - Simplified to single airis-mcp-gateway by default - Added legacy mode for individual official servers (sequential-thinking, context7, magic, playwright) - Dynamic prerequisites based on mode: - Default: uv + claude CLI only - Legacy: node (18+) + npm + claude CLI - Removed redundant server definitions ### CLI Integration - Added --legacy flag to setup/cli/commands/install.py - Added --legacy flag to superclaude/cli/commands/install.py - Config passes legacy_mode to component installer ## Benefits - ✅ Simpler: 1 gateway vs 9+ individual servers - ✅ Lighter: No Node.js/npm required (default mode) - ✅ Unified: All tools in one gateway (sequential-thinking, context7, magic, playwright, serena, morphllm, tavily, chrome-devtools, git, puppeteer) - ✅ Flexible: --legacy flag for official servers if needed ## Usage ```bash superclaude install # Default: airis-mcp-gateway (推奨) superclaude install --legacy # Legacy: individual official servers ``` 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename CoreComponent to FrameworkDocsComponent and add PM token tracking ## Changes ### Component Renaming (setup/components/) - Renamed CoreComponent → FrameworkDocsComponent for clarity - Updated all imports in __init__.py, agents.py, commands.py, mcp_docs.py, modes.py - Better reflects the actual purpose (framework documentation files) ### PM Agent Enhancement (superclaude/commands/pm.md) - Added token usage tracking instructions - PM Agent now reports: 1. Current token usage from system warnings 2. Percentage used (e.g., "27% used" for 54K/200K) 3. Status zone: 🟢 <75% | 🟡 75-85% | 🔴 >85% - Helps prevent token exhaustion during long sessions ### UI Utilities (setup/utils/ui.py) - Added new UI utility module for installer - Provides consistent user interface components ## Benefits - ✅ Clearer component naming (FrameworkDocs vs Core) - ✅ PM Agent token awareness for efficiency - ✅ Better visual feedback with status zones 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor(pm-agent): minimize output verbosity (471→284 lines, 40% reduction) **Problem**: PM Agent generated excessive output with redundant explanations - "System Status Report" with decorative formatting - Repeated "Common Tasks" lists user already knows - Verbose session start/end protocols - Duplicate file operations documentation **Solution**: Compress without losing functionality - Session Start: Reduced to symbol-only status (🟢 branch | nM nD | token%) - Session End: Compressed to essential actions only - File Operations: Consolidated from 2 sections to 1 line reference - Self-Improvement: 5 phases → 1 unified workflow - Output Rules: Explicit constraints to prevent Claude over-explanation **Quality Preservation**: - ✅ All core functions retained (PDCA, memory, patterns, mistakes) - ✅ PARALLEL Read/Write preserved (performance critical) - ✅ Workflow unchanged (session lifecycle intact) - ✅ Added output constraints (prevents verbose generation) **Reduction Method**: - Deleted: Explanatory text, examples, redundant sections - Retained: Action definitions, file paths, core workflows - Added: Explicit output constraints to enforce minimalism **Token Impact**: 40% reduction in agent documentation size **Before**: Verbose multi-section report with task lists **After**: Single line status: 🟢 integration | 15M 17D | 36% 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate MCP integration to unified gateway **Changes**: - Remove individual MCP server docs (superclaude/mcp/*.md) - Remove MCP server configs (superclaude/mcp/configs/*.json) - Delete MCP docs component (setup/components/mcp_docs.py) - Simplify installer (setup/core/installer.py) - Update components for unified gateway approach **Rationale**: - Unified gateway (airis-mcp-gateway) provides all MCP servers - Individual docs/configs no longer needed (managed centrally) - Reduces maintenance burden and file count - Simplifies installation process **Files Removed**: 17 MCP files (docs + configs) **Installer Changes**: Removed legacy MCP installation logic 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: update version and component metadata - Bump version (pyproject.toml, setup/__init__.py) - Update CLAUDE.md import service references - Reflect component structure changes 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-17 09:13:06 +09:00
# Check which server set we're using
is_legacy = self.mcp_servers == self.mcp_servers_legacy
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
refactor: PM Agent complete independence from external MCP servers (#439) * refactor: PM Agent complete independence from external MCP servers ## Summary Implement graceful degradation to ensure PM Agent operates fully without any MCP server dependencies. MCP servers now serve as optional enhancements rather than required components. ## Changes ### Responsibility Separation (NEW) - **PM Agent**: Development workflow orchestration (PDCA cycle, task management) - **mindbase**: Memory management (long-term, freshness, error learning) - **Built-in memory**: Session-internal context (volatile) ### 3-Layer Memory Architecture with Fallbacks 1. **Built-in Memory** [OPTIONAL]: Session context via MCP memory server 2. **mindbase** [OPTIONAL]: Long-term semantic search via airis-mcp-gateway 3. **Local Files** [ALWAYS]: Core functionality in docs/memory/ ### Graceful Degradation Implementation - All MCP operations marked with [ALWAYS] or [OPTIONAL] - Explicit IF/ELSE fallback logic for every MCP call - Dual storage: Always write to local files + optionally to mindbase - Smart lookup: Semantic search (if available) → Text search (always works) ### Key Fallback Strategies **Session Start**: - mindbase available: search_conversations() for semantic context - mindbase unavailable: Grep docs/memory/*.jsonl for text-based lookup **Error Detection**: - mindbase available: Semantic search for similar past errors - mindbase unavailable: Grep docs/mistakes/ + solutions_learned.jsonl **Knowledge Capture**: - Always: echo >> docs/memory/patterns_learned.jsonl (persistent) - Optional: mindbase.store() for semantic search enhancement ## Benefits - ✅ Zero external dependencies (100% functionality without MCP) - ✅ Enhanced capabilities when MCPs available (semantic search, freshness) - ✅ No functionality loss, only reduced search intelligence - ✅ Transparent degradation (no error messages, automatic fallback) ## Related Research - Serena MCP investigation: Exposes tools (not resources), memory = markdown files - mindbase superiority: PostgreSQL + pgvector > Serena memory features - Best practices alignment: /Users/kazuki/github/airis-mcp-gateway/docs/mcp-best-practices.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: add PR template and pre-commit config - Add structured PR template with Git workflow checklist - Add pre-commit hooks for secret detection and Conventional Commits - Enforce code quality gates (YAML/JSON/Markdown lint, shellcheck) NOTE: Execute pre-commit inside Docker container to avoid host pollution: docker compose exec workspace uv tool install pre-commit docker compose exec workspace pre-commit run --all-files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: update PM Agent context with token efficiency architecture - Add Layer 0 Bootstrap (150 tokens, 95% reduction) - Document Intent Classification System (5 complexity levels) - Add Progressive Loading strategy (5-layer) - Document mindbase integration incentive (38% savings) - Update with 2025-10-17 redesign details * refactor: PM Agent command with progressive loading - Replace auto-loading with User Request First philosophy - Add 5-layer progressive context loading - Implement intent classification system - Add workflow metrics collection (.jsonl) - Document graceful degradation strategy * fix: installer improvements Update installer logic for better reliability * docs: add comprehensive development documentation - Add architecture overview - Add PM Agent improvements analysis - Add parallel execution architecture - Add CLI install improvements - Add code style guide - Add project overview - Add install process analysis * docs: add research documentation Add LLM agent token efficiency research and analysis * docs: add suggested commands reference * docs: add session logs and testing documentation - Add session analysis logs - Add testing documentation * feat: migrate CLI to typer + rich for modern UX ## What Changed ### New CLI Architecture (typer + rich) - Created `superclaude/cli/` module with modern typer-based CLI - Replaced custom UI utilities with rich native features - Added type-safe command structure with automatic validation ### Commands Implemented - **install**: Interactive installation with rich UI (progress, panels) - **doctor**: System diagnostics with rich table output - **config**: API key management with format validation ### Technical Improvements - Dependencies: Added typer>=0.9.0, rich>=13.0.0, click>=8.0.0 - Entry Point: Updated pyproject.toml to use `superclaude.cli.app:cli_main` - Tests: Added comprehensive smoke tests (11 passed) ### User Experience Enhancements - Rich formatted help messages with panels and tables - Automatic input validation with retry loops - Clear error messages with actionable suggestions - Non-interactive mode support for CI/CD ## Testing ```bash uv run superclaude --help # ✓ Works uv run superclaude doctor # ✓ Rich table output uv run superclaude config show # ✓ API key management pytest tests/test_cli_smoke.py # ✓ 11 passed, 1 skipped ``` ## Migration Path - ✅ P0: Foundation complete (typer + rich + smoke tests) - 🔜 P1: Pydantic validation models (next sprint) - 🔜 P2: Enhanced error messages (next sprint) - 🔜 P3: API key retry loops (next sprint) ## Performance Impact - **Code Reduction**: Prepared for -300 lines (custom UI → rich) - **Type Safety**: Automatic validation from type hints - **Maintainability**: Framework primitives vs custom code 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate documentation directories Merged claudedocs/ into docs/research/ for consistent documentation structure. Changes: - Moved all claudedocs/*.md files to docs/research/ - Updated all path references in documentation (EN/KR) - Updated RULES.md and research.md command templates - Removed claudedocs/ directory - Removed ClaudeDocs/ from .gitignore Benefits: - Single source of truth for all research reports - PEP8-compliant lowercase directory naming - Clearer documentation organization - Prevents future claudedocs/ directory creation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: reduce /sc:pm command output from 1652 to 15 lines - Remove 1637 lines of documentation from command file - Keep only minimal bootstrap message - 99% token reduction on command execution - Detailed specs remain in superclaude/agents/pm-agent.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: split PM Agent into execution workflows and guide - Reduce pm-agent.md from 735 to 429 lines (42% reduction) - Move philosophy/examples to docs/agents/pm-agent-guide.md - Execution workflows (PDCA, file ops) stay in pm-agent.md - Guide (examples, quality standards) read once when needed Token savings: - Agent loading: ~6K → ~3.5K tokens (42% reduction) - Total with pm.md: 71% overall reduction 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate PM Agent optimization and pending changes PM Agent optimization (already committed separately): - superclaude/commands/pm.md: 1652→14 lines - superclaude/agents/pm-agent.md: 735→429 lines - docs/agents/pm-agent-guide.md: new guide file Other pending changes: - setup: framework_docs, mcp, logger, remove ui.py - superclaude: __main__, cli/app, cli/commands/install - tests: test_ui updates - scripts: workflow metrics analysis tools - docs/memory: session state updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: simplify MCP installer to unified gateway with legacy mode ## Changes ### MCP Component (setup/components/mcp.py) - Simplified to single airis-mcp-gateway by default - Added legacy mode for individual official servers (sequential-thinking, context7, magic, playwright) - Dynamic prerequisites based on mode: - Default: uv + claude CLI only - Legacy: node (18+) + npm + claude CLI - Removed redundant server definitions ### CLI Integration - Added --legacy flag to setup/cli/commands/install.py - Added --legacy flag to superclaude/cli/commands/install.py - Config passes legacy_mode to component installer ## Benefits - ✅ Simpler: 1 gateway vs 9+ individual servers - ✅ Lighter: No Node.js/npm required (default mode) - ✅ Unified: All tools in one gateway (sequential-thinking, context7, magic, playwright, serena, morphllm, tavily, chrome-devtools, git, puppeteer) - ✅ Flexible: --legacy flag for official servers if needed ## Usage ```bash superclaude install # Default: airis-mcp-gateway (推奨) superclaude install --legacy # Legacy: individual official servers ``` 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename CoreComponent to FrameworkDocsComponent and add PM token tracking ## Changes ### Component Renaming (setup/components/) - Renamed CoreComponent → FrameworkDocsComponent for clarity - Updated all imports in __init__.py, agents.py, commands.py, mcp_docs.py, modes.py - Better reflects the actual purpose (framework documentation files) ### PM Agent Enhancement (superclaude/commands/pm.md) - Added token usage tracking instructions - PM Agent now reports: 1. Current token usage from system warnings 2. Percentage used (e.g., "27% used" for 54K/200K) 3. Status zone: 🟢 <75% | 🟡 75-85% | 🔴 >85% - Helps prevent token exhaustion during long sessions ### UI Utilities (setup/utils/ui.py) - Added new UI utility module for installer - Provides consistent user interface components ## Benefits - ✅ Clearer component naming (FrameworkDocs vs Core) - ✅ PM Agent token awareness for efficiency - ✅ Better visual feedback with status zones 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor(pm-agent): minimize output verbosity (471→284 lines, 40% reduction) **Problem**: PM Agent generated excessive output with redundant explanations - "System Status Report" with decorative formatting - Repeated "Common Tasks" lists user already knows - Verbose session start/end protocols - Duplicate file operations documentation **Solution**: Compress without losing functionality - Session Start: Reduced to symbol-only status (🟢 branch | nM nD | token%) - Session End: Compressed to essential actions only - File Operations: Consolidated from 2 sections to 1 line reference - Self-Improvement: 5 phases → 1 unified workflow - Output Rules: Explicit constraints to prevent Claude over-explanation **Quality Preservation**: - ✅ All core functions retained (PDCA, memory, patterns, mistakes) - ✅ PARALLEL Read/Write preserved (performance critical) - ✅ Workflow unchanged (session lifecycle intact) - ✅ Added output constraints (prevents verbose generation) **Reduction Method**: - Deleted: Explanatory text, examples, redundant sections - Retained: Action definitions, file paths, core workflows - Added: Explicit output constraints to enforce minimalism **Token Impact**: 40% reduction in agent documentation size **Before**: Verbose multi-section report with task lists **After**: Single line status: 🟢 integration | 15M 17D | 36% 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate MCP integration to unified gateway **Changes**: - Remove individual MCP server docs (superclaude/mcp/*.md) - Remove MCP server configs (superclaude/mcp/configs/*.json) - Delete MCP docs component (setup/components/mcp_docs.py) - Simplify installer (setup/core/installer.py) - Update components for unified gateway approach **Rationale**: - Unified gateway (airis-mcp-gateway) provides all MCP servers - Individual docs/configs no longer needed (managed centrally) - Reduces maintenance burden and file count - Simplifies installation process **Files Removed**: 17 MCP files (docs + configs) **Installer Changes**: Removed legacy MCP installation logic 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: update version and component metadata - Bump version (pyproject.toml, setup/__init__.py) - Update CLAUDE.md import service references - Reflect component structure changes 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-17 09:13:06 +09:00
# Check if Claude CLI is available (always required)
try:
result = self._run_command_cross_platform(
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
["claude", "--version"], capture_output=True, text=True, timeout=10
)
if result.returncode != 0:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
errors.append(
"Claude CLI not found - required for MCP server management"
)
else:
version = result.stdout.strip()
self.logger.debug(f"Found Claude CLI {version}")
except (subprocess.TimeoutExpired, FileNotFoundError):
errors.append("Claude CLI not found - required for MCP server management")
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
refactor: PM Agent complete independence from external MCP servers (#439) * refactor: PM Agent complete independence from external MCP servers ## Summary Implement graceful degradation to ensure PM Agent operates fully without any MCP server dependencies. MCP servers now serve as optional enhancements rather than required components. ## Changes ### Responsibility Separation (NEW) - **PM Agent**: Development workflow orchestration (PDCA cycle, task management) - **mindbase**: Memory management (long-term, freshness, error learning) - **Built-in memory**: Session-internal context (volatile) ### 3-Layer Memory Architecture with Fallbacks 1. **Built-in Memory** [OPTIONAL]: Session context via MCP memory server 2. **mindbase** [OPTIONAL]: Long-term semantic search via airis-mcp-gateway 3. **Local Files** [ALWAYS]: Core functionality in docs/memory/ ### Graceful Degradation Implementation - All MCP operations marked with [ALWAYS] or [OPTIONAL] - Explicit IF/ELSE fallback logic for every MCP call - Dual storage: Always write to local files + optionally to mindbase - Smart lookup: Semantic search (if available) → Text search (always works) ### Key Fallback Strategies **Session Start**: - mindbase available: search_conversations() for semantic context - mindbase unavailable: Grep docs/memory/*.jsonl for text-based lookup **Error Detection**: - mindbase available: Semantic search for similar past errors - mindbase unavailable: Grep docs/mistakes/ + solutions_learned.jsonl **Knowledge Capture**: - Always: echo >> docs/memory/patterns_learned.jsonl (persistent) - Optional: mindbase.store() for semantic search enhancement ## Benefits - ✅ Zero external dependencies (100% functionality without MCP) - ✅ Enhanced capabilities when MCPs available (semantic search, freshness) - ✅ No functionality loss, only reduced search intelligence - ✅ Transparent degradation (no error messages, automatic fallback) ## Related Research - Serena MCP investigation: Exposes tools (not resources), memory = markdown files - mindbase superiority: PostgreSQL + pgvector > Serena memory features - Best practices alignment: /Users/kazuki/github/airis-mcp-gateway/docs/mcp-best-practices.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: add PR template and pre-commit config - Add structured PR template with Git workflow checklist - Add pre-commit hooks for secret detection and Conventional Commits - Enforce code quality gates (YAML/JSON/Markdown lint, shellcheck) NOTE: Execute pre-commit inside Docker container to avoid host pollution: docker compose exec workspace uv tool install pre-commit docker compose exec workspace pre-commit run --all-files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: update PM Agent context with token efficiency architecture - Add Layer 0 Bootstrap (150 tokens, 95% reduction) - Document Intent Classification System (5 complexity levels) - Add Progressive Loading strategy (5-layer) - Document mindbase integration incentive (38% savings) - Update with 2025-10-17 redesign details * refactor: PM Agent command with progressive loading - Replace auto-loading with User Request First philosophy - Add 5-layer progressive context loading - Implement intent classification system - Add workflow metrics collection (.jsonl) - Document graceful degradation strategy * fix: installer improvements Update installer logic for better reliability * docs: add comprehensive development documentation - Add architecture overview - Add PM Agent improvements analysis - Add parallel execution architecture - Add CLI install improvements - Add code style guide - Add project overview - Add install process analysis * docs: add research documentation Add LLM agent token efficiency research and analysis * docs: add suggested commands reference * docs: add session logs and testing documentation - Add session analysis logs - Add testing documentation * feat: migrate CLI to typer + rich for modern UX ## What Changed ### New CLI Architecture (typer + rich) - Created `superclaude/cli/` module with modern typer-based CLI - Replaced custom UI utilities with rich native features - Added type-safe command structure with automatic validation ### Commands Implemented - **install**: Interactive installation with rich UI (progress, panels) - **doctor**: System diagnostics with rich table output - **config**: API key management with format validation ### Technical Improvements - Dependencies: Added typer>=0.9.0, rich>=13.0.0, click>=8.0.0 - Entry Point: Updated pyproject.toml to use `superclaude.cli.app:cli_main` - Tests: Added comprehensive smoke tests (11 passed) ### User Experience Enhancements - Rich formatted help messages with panels and tables - Automatic input validation with retry loops - Clear error messages with actionable suggestions - Non-interactive mode support for CI/CD ## Testing ```bash uv run superclaude --help # ✓ Works uv run superclaude doctor # ✓ Rich table output uv run superclaude config show # ✓ API key management pytest tests/test_cli_smoke.py # ✓ 11 passed, 1 skipped ``` ## Migration Path - ✅ P0: Foundation complete (typer + rich + smoke tests) - 🔜 P1: Pydantic validation models (next sprint) - 🔜 P2: Enhanced error messages (next sprint) - 🔜 P3: API key retry loops (next sprint) ## Performance Impact - **Code Reduction**: Prepared for -300 lines (custom UI → rich) - **Type Safety**: Automatic validation from type hints - **Maintainability**: Framework primitives vs custom code 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate documentation directories Merged claudedocs/ into docs/research/ for consistent documentation structure. Changes: - Moved all claudedocs/*.md files to docs/research/ - Updated all path references in documentation (EN/KR) - Updated RULES.md and research.md command templates - Removed claudedocs/ directory - Removed ClaudeDocs/ from .gitignore Benefits: - Single source of truth for all research reports - PEP8-compliant lowercase directory naming - Clearer documentation organization - Prevents future claudedocs/ directory creation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: reduce /sc:pm command output from 1652 to 15 lines - Remove 1637 lines of documentation from command file - Keep only minimal bootstrap message - 99% token reduction on command execution - Detailed specs remain in superclaude/agents/pm-agent.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: split PM Agent into execution workflows and guide - Reduce pm-agent.md from 735 to 429 lines (42% reduction) - Move philosophy/examples to docs/agents/pm-agent-guide.md - Execution workflows (PDCA, file ops) stay in pm-agent.md - Guide (examples, quality standards) read once when needed Token savings: - Agent loading: ~6K → ~3.5K tokens (42% reduction) - Total with pm.md: 71% overall reduction 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate PM Agent optimization and pending changes PM Agent optimization (already committed separately): - superclaude/commands/pm.md: 1652→14 lines - superclaude/agents/pm-agent.md: 735→429 lines - docs/agents/pm-agent-guide.md: new guide file Other pending changes: - setup: framework_docs, mcp, logger, remove ui.py - superclaude: __main__, cli/app, cli/commands/install - tests: test_ui updates - scripts: workflow metrics analysis tools - docs/memory: session state updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: simplify MCP installer to unified gateway with legacy mode ## Changes ### MCP Component (setup/components/mcp.py) - Simplified to single airis-mcp-gateway by default - Added legacy mode for individual official servers (sequential-thinking, context7, magic, playwright) - Dynamic prerequisites based on mode: - Default: uv + claude CLI only - Legacy: node (18+) + npm + claude CLI - Removed redundant server definitions ### CLI Integration - Added --legacy flag to setup/cli/commands/install.py - Added --legacy flag to superclaude/cli/commands/install.py - Config passes legacy_mode to component installer ## Benefits - ✅ Simpler: 1 gateway vs 9+ individual servers - ✅ Lighter: No Node.js/npm required (default mode) - ✅ Unified: All tools in one gateway (sequential-thinking, context7, magic, playwright, serena, morphllm, tavily, chrome-devtools, git, puppeteer) - ✅ Flexible: --legacy flag for official servers if needed ## Usage ```bash superclaude install # Default: airis-mcp-gateway (推奨) superclaude install --legacy # Legacy: individual official servers ``` 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename CoreComponent to FrameworkDocsComponent and add PM token tracking ## Changes ### Component Renaming (setup/components/) - Renamed CoreComponent → FrameworkDocsComponent for clarity - Updated all imports in __init__.py, agents.py, commands.py, mcp_docs.py, modes.py - Better reflects the actual purpose (framework documentation files) ### PM Agent Enhancement (superclaude/commands/pm.md) - Added token usage tracking instructions - PM Agent now reports: 1. Current token usage from system warnings 2. Percentage used (e.g., "27% used" for 54K/200K) 3. Status zone: 🟢 <75% | 🟡 75-85% | 🔴 >85% - Helps prevent token exhaustion during long sessions ### UI Utilities (setup/utils/ui.py) - Added new UI utility module for installer - Provides consistent user interface components ## Benefits - ✅ Clearer component naming (FrameworkDocs vs Core) - ✅ PM Agent token awareness for efficiency - ✅ Better visual feedback with status zones 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor(pm-agent): minimize output verbosity (471→284 lines, 40% reduction) **Problem**: PM Agent generated excessive output with redundant explanations - "System Status Report" with decorative formatting - Repeated "Common Tasks" lists user already knows - Verbose session start/end protocols - Duplicate file operations documentation **Solution**: Compress without losing functionality - Session Start: Reduced to symbol-only status (🟢 branch | nM nD | token%) - Session End: Compressed to essential actions only - File Operations: Consolidated from 2 sections to 1 line reference - Self-Improvement: 5 phases → 1 unified workflow - Output Rules: Explicit constraints to prevent Claude over-explanation **Quality Preservation**: - ✅ All core functions retained (PDCA, memory, patterns, mistakes) - ✅ PARALLEL Read/Write preserved (performance critical) - ✅ Workflow unchanged (session lifecycle intact) - ✅ Added output constraints (prevents verbose generation) **Reduction Method**: - Deleted: Explanatory text, examples, redundant sections - Retained: Action definitions, file paths, core workflows - Added: Explicit output constraints to enforce minimalism **Token Impact**: 40% reduction in agent documentation size **Before**: Verbose multi-section report with task lists **After**: Single line status: 🟢 integration | 15M 17D | 36% 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate MCP integration to unified gateway **Changes**: - Remove individual MCP server docs (superclaude/mcp/*.md) - Remove MCP server configs (superclaude/mcp/configs/*.json) - Delete MCP docs component (setup/components/mcp_docs.py) - Simplify installer (setup/core/installer.py) - Update components for unified gateway approach **Rationale**: - Unified gateway (airis-mcp-gateway) provides all MCP servers - Individual docs/configs no longer needed (managed centrally) - Reduces maintenance burden and file count - Simplifies installation process **Files Removed**: 17 MCP files (docs + configs) **Installer Changes**: Removed legacy MCP installation logic 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: update version and component metadata - Bump version (pyproject.toml, setup/__init__.py) - Update CLAUDE.md import service references - Reflect component structure changes 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-17 09:13:06 +09:00
if is_legacy:
# Legacy mode: requires Node.js and npm for official servers
try:
result = self._run_command_cross_platform(
["node", "--version"], capture_output=True, text=True, timeout=10
)
if result.returncode != 0:
errors.append("Node.js not found - required for legacy MCP servers")
else:
version = result.stdout.strip()
self.logger.debug(f"Found Node.js {version}")
# Check version (require 18+)
try:
version_num = int(version.lstrip("v").split(".")[0])
if version_num < 18:
errors.append(
f"Node.js version {version} found, but version 18+ required"
)
except:
self.logger.warning(f"Could not parse Node.js version: {version}")
except (subprocess.TimeoutExpired, FileNotFoundError):
errors.append("Node.js not found - required for legacy MCP servers")
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
refactor: PM Agent complete independence from external MCP servers (#439) * refactor: PM Agent complete independence from external MCP servers ## Summary Implement graceful degradation to ensure PM Agent operates fully without any MCP server dependencies. MCP servers now serve as optional enhancements rather than required components. ## Changes ### Responsibility Separation (NEW) - **PM Agent**: Development workflow orchestration (PDCA cycle, task management) - **mindbase**: Memory management (long-term, freshness, error learning) - **Built-in memory**: Session-internal context (volatile) ### 3-Layer Memory Architecture with Fallbacks 1. **Built-in Memory** [OPTIONAL]: Session context via MCP memory server 2. **mindbase** [OPTIONAL]: Long-term semantic search via airis-mcp-gateway 3. **Local Files** [ALWAYS]: Core functionality in docs/memory/ ### Graceful Degradation Implementation - All MCP operations marked with [ALWAYS] or [OPTIONAL] - Explicit IF/ELSE fallback logic for every MCP call - Dual storage: Always write to local files + optionally to mindbase - Smart lookup: Semantic search (if available) → Text search (always works) ### Key Fallback Strategies **Session Start**: - mindbase available: search_conversations() for semantic context - mindbase unavailable: Grep docs/memory/*.jsonl for text-based lookup **Error Detection**: - mindbase available: Semantic search for similar past errors - mindbase unavailable: Grep docs/mistakes/ + solutions_learned.jsonl **Knowledge Capture**: - Always: echo >> docs/memory/patterns_learned.jsonl (persistent) - Optional: mindbase.store() for semantic search enhancement ## Benefits - ✅ Zero external dependencies (100% functionality without MCP) - ✅ Enhanced capabilities when MCPs available (semantic search, freshness) - ✅ No functionality loss, only reduced search intelligence - ✅ Transparent degradation (no error messages, automatic fallback) ## Related Research - Serena MCP investigation: Exposes tools (not resources), memory = markdown files - mindbase superiority: PostgreSQL + pgvector > Serena memory features - Best practices alignment: /Users/kazuki/github/airis-mcp-gateway/docs/mcp-best-practices.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: add PR template and pre-commit config - Add structured PR template with Git workflow checklist - Add pre-commit hooks for secret detection and Conventional Commits - Enforce code quality gates (YAML/JSON/Markdown lint, shellcheck) NOTE: Execute pre-commit inside Docker container to avoid host pollution: docker compose exec workspace uv tool install pre-commit docker compose exec workspace pre-commit run --all-files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: update PM Agent context with token efficiency architecture - Add Layer 0 Bootstrap (150 tokens, 95% reduction) - Document Intent Classification System (5 complexity levels) - Add Progressive Loading strategy (5-layer) - Document mindbase integration incentive (38% savings) - Update with 2025-10-17 redesign details * refactor: PM Agent command with progressive loading - Replace auto-loading with User Request First philosophy - Add 5-layer progressive context loading - Implement intent classification system - Add workflow metrics collection (.jsonl) - Document graceful degradation strategy * fix: installer improvements Update installer logic for better reliability * docs: add comprehensive development documentation - Add architecture overview - Add PM Agent improvements analysis - Add parallel execution architecture - Add CLI install improvements - Add code style guide - Add project overview - Add install process analysis * docs: add research documentation Add LLM agent token efficiency research and analysis * docs: add suggested commands reference * docs: add session logs and testing documentation - Add session analysis logs - Add testing documentation * feat: migrate CLI to typer + rich for modern UX ## What Changed ### New CLI Architecture (typer + rich) - Created `superclaude/cli/` module with modern typer-based CLI - Replaced custom UI utilities with rich native features - Added type-safe command structure with automatic validation ### Commands Implemented - **install**: Interactive installation with rich UI (progress, panels) - **doctor**: System diagnostics with rich table output - **config**: API key management with format validation ### Technical Improvements - Dependencies: Added typer>=0.9.0, rich>=13.0.0, click>=8.0.0 - Entry Point: Updated pyproject.toml to use `superclaude.cli.app:cli_main` - Tests: Added comprehensive smoke tests (11 passed) ### User Experience Enhancements - Rich formatted help messages with panels and tables - Automatic input validation with retry loops - Clear error messages with actionable suggestions - Non-interactive mode support for CI/CD ## Testing ```bash uv run superclaude --help # ✓ Works uv run superclaude doctor # ✓ Rich table output uv run superclaude config show # ✓ API key management pytest tests/test_cli_smoke.py # ✓ 11 passed, 1 skipped ``` ## Migration Path - ✅ P0: Foundation complete (typer + rich + smoke tests) - 🔜 P1: Pydantic validation models (next sprint) - 🔜 P2: Enhanced error messages (next sprint) - 🔜 P3: API key retry loops (next sprint) ## Performance Impact - **Code Reduction**: Prepared for -300 lines (custom UI → rich) - **Type Safety**: Automatic validation from type hints - **Maintainability**: Framework primitives vs custom code 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate documentation directories Merged claudedocs/ into docs/research/ for consistent documentation structure. Changes: - Moved all claudedocs/*.md files to docs/research/ - Updated all path references in documentation (EN/KR) - Updated RULES.md and research.md command templates - Removed claudedocs/ directory - Removed ClaudeDocs/ from .gitignore Benefits: - Single source of truth for all research reports - PEP8-compliant lowercase directory naming - Clearer documentation organization - Prevents future claudedocs/ directory creation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: reduce /sc:pm command output from 1652 to 15 lines - Remove 1637 lines of documentation from command file - Keep only minimal bootstrap message - 99% token reduction on command execution - Detailed specs remain in superclaude/agents/pm-agent.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: split PM Agent into execution workflows and guide - Reduce pm-agent.md from 735 to 429 lines (42% reduction) - Move philosophy/examples to docs/agents/pm-agent-guide.md - Execution workflows (PDCA, file ops) stay in pm-agent.md - Guide (examples, quality standards) read once when needed Token savings: - Agent loading: ~6K → ~3.5K tokens (42% reduction) - Total with pm.md: 71% overall reduction 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate PM Agent optimization and pending changes PM Agent optimization (already committed separately): - superclaude/commands/pm.md: 1652→14 lines - superclaude/agents/pm-agent.md: 735→429 lines - docs/agents/pm-agent-guide.md: new guide file Other pending changes: - setup: framework_docs, mcp, logger, remove ui.py - superclaude: __main__, cli/app, cli/commands/install - tests: test_ui updates - scripts: workflow metrics analysis tools - docs/memory: session state updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: simplify MCP installer to unified gateway with legacy mode ## Changes ### MCP Component (setup/components/mcp.py) - Simplified to single airis-mcp-gateway by default - Added legacy mode for individual official servers (sequential-thinking, context7, magic, playwright) - Dynamic prerequisites based on mode: - Default: uv + claude CLI only - Legacy: node (18+) + npm + claude CLI - Removed redundant server definitions ### CLI Integration - Added --legacy flag to setup/cli/commands/install.py - Added --legacy flag to superclaude/cli/commands/install.py - Config passes legacy_mode to component installer ## Benefits - ✅ Simpler: 1 gateway vs 9+ individual servers - ✅ Lighter: No Node.js/npm required (default mode) - ✅ Unified: All tools in one gateway (sequential-thinking, context7, magic, playwright, serena, morphllm, tavily, chrome-devtools, git, puppeteer) - ✅ Flexible: --legacy flag for official servers if needed ## Usage ```bash superclaude install # Default: airis-mcp-gateway (推奨) superclaude install --legacy # Legacy: individual official servers ``` 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename CoreComponent to FrameworkDocsComponent and add PM token tracking ## Changes ### Component Renaming (setup/components/) - Renamed CoreComponent → FrameworkDocsComponent for clarity - Updated all imports in __init__.py, agents.py, commands.py, mcp_docs.py, modes.py - Better reflects the actual purpose (framework documentation files) ### PM Agent Enhancement (superclaude/commands/pm.md) - Added token usage tracking instructions - PM Agent now reports: 1. Current token usage from system warnings 2. Percentage used (e.g., "27% used" for 54K/200K) 3. Status zone: 🟢 <75% | 🟡 75-85% | 🔴 >85% - Helps prevent token exhaustion during long sessions ### UI Utilities (setup/utils/ui.py) - Added new UI utility module for installer - Provides consistent user interface components ## Benefits - ✅ Clearer component naming (FrameworkDocs vs Core) - ✅ PM Agent token awareness for efficiency - ✅ Better visual feedback with status zones 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor(pm-agent): minimize output verbosity (471→284 lines, 40% reduction) **Problem**: PM Agent generated excessive output with redundant explanations - "System Status Report" with decorative formatting - Repeated "Common Tasks" lists user already knows - Verbose session start/end protocols - Duplicate file operations documentation **Solution**: Compress without losing functionality - Session Start: Reduced to symbol-only status (🟢 branch | nM nD | token%) - Session End: Compressed to essential actions only - File Operations: Consolidated from 2 sections to 1 line reference - Self-Improvement: 5 phases → 1 unified workflow - Output Rules: Explicit constraints to prevent Claude over-explanation **Quality Preservation**: - ✅ All core functions retained (PDCA, memory, patterns, mistakes) - ✅ PARALLEL Read/Write preserved (performance critical) - ✅ Workflow unchanged (session lifecycle intact) - ✅ Added output constraints (prevents verbose generation) **Reduction Method**: - Deleted: Explanatory text, examples, redundant sections - Retained: Action definitions, file paths, core workflows - Added: Explicit output constraints to enforce minimalism **Token Impact**: 40% reduction in agent documentation size **Before**: Verbose multi-section report with task lists **After**: Single line status: 🟢 integration | 15M 17D | 36% 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate MCP integration to unified gateway **Changes**: - Remove individual MCP server docs (superclaude/mcp/*.md) - Remove MCP server configs (superclaude/mcp/configs/*.json) - Delete MCP docs component (setup/components/mcp_docs.py) - Simplify installer (setup/core/installer.py) - Update components for unified gateway approach **Rationale**: - Unified gateway (airis-mcp-gateway) provides all MCP servers - Individual docs/configs no longer needed (managed centrally) - Reduces maintenance burden and file count - Simplifies installation process **Files Removed**: 17 MCP files (docs + configs) **Installer Changes**: Removed legacy MCP installation logic 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: update version and component metadata - Bump version (pyproject.toml, setup/__init__.py) - Update CLAUDE.md import service references - Reflect component structure changes 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-17 09:13:06 +09:00
try:
result = self._run_command_cross_platform(
["npm", "--version"], capture_output=True, text=True, timeout=10
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
)
refactor: PM Agent complete independence from external MCP servers (#439) * refactor: PM Agent complete independence from external MCP servers ## Summary Implement graceful degradation to ensure PM Agent operates fully without any MCP server dependencies. MCP servers now serve as optional enhancements rather than required components. ## Changes ### Responsibility Separation (NEW) - **PM Agent**: Development workflow orchestration (PDCA cycle, task management) - **mindbase**: Memory management (long-term, freshness, error learning) - **Built-in memory**: Session-internal context (volatile) ### 3-Layer Memory Architecture with Fallbacks 1. **Built-in Memory** [OPTIONAL]: Session context via MCP memory server 2. **mindbase** [OPTIONAL]: Long-term semantic search via airis-mcp-gateway 3. **Local Files** [ALWAYS]: Core functionality in docs/memory/ ### Graceful Degradation Implementation - All MCP operations marked with [ALWAYS] or [OPTIONAL] - Explicit IF/ELSE fallback logic for every MCP call - Dual storage: Always write to local files + optionally to mindbase - Smart lookup: Semantic search (if available) → Text search (always works) ### Key Fallback Strategies **Session Start**: - mindbase available: search_conversations() for semantic context - mindbase unavailable: Grep docs/memory/*.jsonl for text-based lookup **Error Detection**: - mindbase available: Semantic search for similar past errors - mindbase unavailable: Grep docs/mistakes/ + solutions_learned.jsonl **Knowledge Capture**: - Always: echo >> docs/memory/patterns_learned.jsonl (persistent) - Optional: mindbase.store() for semantic search enhancement ## Benefits - ✅ Zero external dependencies (100% functionality without MCP) - ✅ Enhanced capabilities when MCPs available (semantic search, freshness) - ✅ No functionality loss, only reduced search intelligence - ✅ Transparent degradation (no error messages, automatic fallback) ## Related Research - Serena MCP investigation: Exposes tools (not resources), memory = markdown files - mindbase superiority: PostgreSQL + pgvector > Serena memory features - Best practices alignment: /Users/kazuki/github/airis-mcp-gateway/docs/mcp-best-practices.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: add PR template and pre-commit config - Add structured PR template with Git workflow checklist - Add pre-commit hooks for secret detection and Conventional Commits - Enforce code quality gates (YAML/JSON/Markdown lint, shellcheck) NOTE: Execute pre-commit inside Docker container to avoid host pollution: docker compose exec workspace uv tool install pre-commit docker compose exec workspace pre-commit run --all-files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: update PM Agent context with token efficiency architecture - Add Layer 0 Bootstrap (150 tokens, 95% reduction) - Document Intent Classification System (5 complexity levels) - Add Progressive Loading strategy (5-layer) - Document mindbase integration incentive (38% savings) - Update with 2025-10-17 redesign details * refactor: PM Agent command with progressive loading - Replace auto-loading with User Request First philosophy - Add 5-layer progressive context loading - Implement intent classification system - Add workflow metrics collection (.jsonl) - Document graceful degradation strategy * fix: installer improvements Update installer logic for better reliability * docs: add comprehensive development documentation - Add architecture overview - Add PM Agent improvements analysis - Add parallel execution architecture - Add CLI install improvements - Add code style guide - Add project overview - Add install process analysis * docs: add research documentation Add LLM agent token efficiency research and analysis * docs: add suggested commands reference * docs: add session logs and testing documentation - Add session analysis logs - Add testing documentation * feat: migrate CLI to typer + rich for modern UX ## What Changed ### New CLI Architecture (typer + rich) - Created `superclaude/cli/` module with modern typer-based CLI - Replaced custom UI utilities with rich native features - Added type-safe command structure with automatic validation ### Commands Implemented - **install**: Interactive installation with rich UI (progress, panels) - **doctor**: System diagnostics with rich table output - **config**: API key management with format validation ### Technical Improvements - Dependencies: Added typer>=0.9.0, rich>=13.0.0, click>=8.0.0 - Entry Point: Updated pyproject.toml to use `superclaude.cli.app:cli_main` - Tests: Added comprehensive smoke tests (11 passed) ### User Experience Enhancements - Rich formatted help messages with panels and tables - Automatic input validation with retry loops - Clear error messages with actionable suggestions - Non-interactive mode support for CI/CD ## Testing ```bash uv run superclaude --help # ✓ Works uv run superclaude doctor # ✓ Rich table output uv run superclaude config show # ✓ API key management pytest tests/test_cli_smoke.py # ✓ 11 passed, 1 skipped ``` ## Migration Path - ✅ P0: Foundation complete (typer + rich + smoke tests) - 🔜 P1: Pydantic validation models (next sprint) - 🔜 P2: Enhanced error messages (next sprint) - 🔜 P3: API key retry loops (next sprint) ## Performance Impact - **Code Reduction**: Prepared for -300 lines (custom UI → rich) - **Type Safety**: Automatic validation from type hints - **Maintainability**: Framework primitives vs custom code 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate documentation directories Merged claudedocs/ into docs/research/ for consistent documentation structure. Changes: - Moved all claudedocs/*.md files to docs/research/ - Updated all path references in documentation (EN/KR) - Updated RULES.md and research.md command templates - Removed claudedocs/ directory - Removed ClaudeDocs/ from .gitignore Benefits: - Single source of truth for all research reports - PEP8-compliant lowercase directory naming - Clearer documentation organization - Prevents future claudedocs/ directory creation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: reduce /sc:pm command output from 1652 to 15 lines - Remove 1637 lines of documentation from command file - Keep only minimal bootstrap message - 99% token reduction on command execution - Detailed specs remain in superclaude/agents/pm-agent.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: split PM Agent into execution workflows and guide - Reduce pm-agent.md from 735 to 429 lines (42% reduction) - Move philosophy/examples to docs/agents/pm-agent-guide.md - Execution workflows (PDCA, file ops) stay in pm-agent.md - Guide (examples, quality standards) read once when needed Token savings: - Agent loading: ~6K → ~3.5K tokens (42% reduction) - Total with pm.md: 71% overall reduction 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate PM Agent optimization and pending changes PM Agent optimization (already committed separately): - superclaude/commands/pm.md: 1652→14 lines - superclaude/agents/pm-agent.md: 735→429 lines - docs/agents/pm-agent-guide.md: new guide file Other pending changes: - setup: framework_docs, mcp, logger, remove ui.py - superclaude: __main__, cli/app, cli/commands/install - tests: test_ui updates - scripts: workflow metrics analysis tools - docs/memory: session state updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: simplify MCP installer to unified gateway with legacy mode ## Changes ### MCP Component (setup/components/mcp.py) - Simplified to single airis-mcp-gateway by default - Added legacy mode for individual official servers (sequential-thinking, context7, magic, playwright) - Dynamic prerequisites based on mode: - Default: uv + claude CLI only - Legacy: node (18+) + npm + claude CLI - Removed redundant server definitions ### CLI Integration - Added --legacy flag to setup/cli/commands/install.py - Added --legacy flag to superclaude/cli/commands/install.py - Config passes legacy_mode to component installer ## Benefits - ✅ Simpler: 1 gateway vs 9+ individual servers - ✅ Lighter: No Node.js/npm required (default mode) - ✅ Unified: All tools in one gateway (sequential-thinking, context7, magic, playwright, serena, morphllm, tavily, chrome-devtools, git, puppeteer) - ✅ Flexible: --legacy flag for official servers if needed ## Usage ```bash superclaude install # Default: airis-mcp-gateway (推奨) superclaude install --legacy # Legacy: individual official servers ``` 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename CoreComponent to FrameworkDocsComponent and add PM token tracking ## Changes ### Component Renaming (setup/components/) - Renamed CoreComponent → FrameworkDocsComponent for clarity - Updated all imports in __init__.py, agents.py, commands.py, mcp_docs.py, modes.py - Better reflects the actual purpose (framework documentation files) ### PM Agent Enhancement (superclaude/commands/pm.md) - Added token usage tracking instructions - PM Agent now reports: 1. Current token usage from system warnings 2. Percentage used (e.g., "27% used" for 54K/200K) 3. Status zone: 🟢 <75% | 🟡 75-85% | 🔴 >85% - Helps prevent token exhaustion during long sessions ### UI Utilities (setup/utils/ui.py) - Added new UI utility module for installer - Provides consistent user interface components ## Benefits - ✅ Clearer component naming (FrameworkDocs vs Core) - ✅ PM Agent token awareness for efficiency - ✅ Better visual feedback with status zones 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor(pm-agent): minimize output verbosity (471→284 lines, 40% reduction) **Problem**: PM Agent generated excessive output with redundant explanations - "System Status Report" with decorative formatting - Repeated "Common Tasks" lists user already knows - Verbose session start/end protocols - Duplicate file operations documentation **Solution**: Compress without losing functionality - Session Start: Reduced to symbol-only status (🟢 branch | nM nD | token%) - Session End: Compressed to essential actions only - File Operations: Consolidated from 2 sections to 1 line reference - Self-Improvement: 5 phases → 1 unified workflow - Output Rules: Explicit constraints to prevent Claude over-explanation **Quality Preservation**: - ✅ All core functions retained (PDCA, memory, patterns, mistakes) - ✅ PARALLEL Read/Write preserved (performance critical) - ✅ Workflow unchanged (session lifecycle intact) - ✅ Added output constraints (prevents verbose generation) **Reduction Method**: - Deleted: Explanatory text, examples, redundant sections - Retained: Action definitions, file paths, core workflows - Added: Explicit output constraints to enforce minimalism **Token Impact**: 40% reduction in agent documentation size **Before**: Verbose multi-section report with task lists **After**: Single line status: 🟢 integration | 15M 17D | 36% 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate MCP integration to unified gateway **Changes**: - Remove individual MCP server docs (superclaude/mcp/*.md) - Remove MCP server configs (superclaude/mcp/configs/*.json) - Delete MCP docs component (setup/components/mcp_docs.py) - Simplify installer (setup/core/installer.py) - Update components for unified gateway approach **Rationale**: - Unified gateway (airis-mcp-gateway) provides all MCP servers - Individual docs/configs no longer needed (managed centrally) - Reduces maintenance burden and file count - Simplifies installation process **Files Removed**: 17 MCP files (docs + configs) **Installer Changes**: Removed legacy MCP installation logic 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: update version and component metadata - Bump version (pyproject.toml, setup/__init__.py) - Update CLAUDE.md import service references - Reflect component structure changes 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-17 09:13:06 +09:00
if result.returncode != 0:
errors.append("npm not found - required for legacy MCP server installation")
else:
version = result.stdout.strip()
self.logger.debug(f"Found npm {version}")
except (subprocess.TimeoutExpired, FileNotFoundError):
errors.append("npm not found - required for legacy MCP server installation")
else:
# Default mode: requires Node.js toolchain and Docker for AIRIS MCP Gateway
tool_checks = [
(["git", "--version"], "Git not found - required for cloning airis-mcp-gateway"),
(["docker", "--version"], "Docker not found - required for airis-mcp-gateway services"),
(["docker", "compose", "version"], "Docker Compose not found - required for managing airis-mcp-gateway containers"),
(["make", "--version"], "make not found - required for airis-mcp-gateway automation"),
]
for cmd, error_msg in tool_checks:
try:
result = self._run_command_cross_platform(
cmd, capture_output=True, text=True, timeout=10
)
if result.returncode != 0:
errors.append(error_msg)
else:
self.logger.debug(
f"Found dependency for airis-mcp-gateway: {cmd[0]} {result.stdout.strip()}"
)
except (subprocess.TimeoutExpired, FileNotFoundError):
errors.append(error_msg)
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
2025-08-14 08:56:04 +05:30
return len(errors) == 0, errors
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
2025-08-14 08:56:04 +05:30
def get_files_to_install(self) -> List[Tuple[Path, Path]]:
"""Get files to install (none for MCP component)"""
2025-08-14 08:56:04 +05:30
return []
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
def get_metadata_modifications(self) -> Dict[str, Any]:
"""Get metadata modifications for MCP component"""
return {
"components": {
"mcp": {
"version": __version__,
"installed": True,
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
"servers_count": len(self.installed_servers_in_session),
}
},
"mcp": {
"enabled": True,
Fixed Some Bugs (#355) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> --------- Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>
2025-09-13 17:28:52 +05:30
"servers": self.installed_servers_in_session,
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
"auto_update": False,
},
}
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
def _install_uv_mcp_server(
self, server_info: Dict[str, Any], config: Dict[str, Any]
) -> bool:
"""Install a single MCP server using uv"""
server_name = server_info["name"]
install_command = server_info.get("install_command")
run_command = server_info.get("run_command")
if not install_command:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.error(
f"No install_command found for uv-based server {server_name}"
)
return False
if not run_command:
self.logger.error(f"No run_command found for uv-based server {server_name}")
return False
try:
self.logger.info(f"Installing MCP server using uv: {server_name}")
if self._check_mcp_server_installed(server_name):
self.logger.info(f"MCP server {server_name} already installed")
return True
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
# Check if uv is available
try:
uv_check = self._run_command_cross_platform(
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
["uv", "--version"], capture_output=True, text=True, timeout=10
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
)
if uv_check.returncode != 0:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.error(
f"uv not found - required for {server_name} installation"
)
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
return False
except (subprocess.TimeoutExpired, FileNotFoundError):
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.error(
f"uv not found - required for {server_name} installation"
)
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
return False
if config.get("dry_run"):
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.info(
f"Would install MCP server (user scope): {install_command}"
)
self.logger.info(
f"Would register MCP server run command: {run_command}"
)
return True
# Run install command
self.logger.debug(f"Running: {install_command}")
cmd_parts = shlex.split(install_command)
result = self._run_command_cross_platform(
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
cmd_parts, capture_output=True, text=True, timeout=900 # 15 minutes
)
if result.returncode == 0:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.success(
f"Successfully installed MCP server (user scope): {server_name}"
)
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
# For Serena, we need to handle the run command specially
if server_name == "serena":
# Serena needs project-specific registration, use current working directory
current_dir = os.getcwd()
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
serena_run_cmd = (
f"{run_command} --project {shlex.quote(current_dir)}"
)
self.logger.info(
f"Registering {server_name} with Claude CLI for project: {current_dir}"
)
reg_cmd = [
"claude",
"mcp",
"add",
"-s",
"user",
"--",
server_name,
] + shlex.split(serena_run_cmd)
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
else:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.info(
f"Registering {server_name} with Claude CLI. Run command: {run_command}"
)
reg_cmd = [
"claude",
"mcp",
"add",
"-s",
"user",
"--",
server_name,
] + shlex.split(run_command)
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
reg_result = self._run_command_cross_platform(
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
reg_cmd, capture_output=True, text=True, timeout=120
)
if reg_result.returncode == 0:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.success(
f"Successfully registered {server_name} with Claude CLI."
)
return True
else:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
error_msg = (
reg_result.stderr.strip()
if reg_result.stderr
else "Unknown error"
)
self.logger.error(
f"Failed to register MCP server {server_name} with Claude CLI: {error_msg}"
)
return False
else:
error_msg = result.stderr.strip() if result.stderr else "Unknown error"
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.error(
f"Failed to install MCP server {server_name} using uv: {error_msg}\n{result.stdout}"
)
return False
except subprocess.TimeoutExpired:
self.logger.error(f"Timeout installing MCP server {server_name} using uv")
return False
except Exception as e:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.error(
f"Error installing MCP server {server_name} using uv: {e}"
)
return False
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
def _install_github_mcp_server(
self, server_info: Dict[str, Any], config: Dict[str, Any]
) -> bool:
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
"""Install a single MCP server from GitHub using uvx"""
server_name = server_info["name"]
install_command = server_info.get("install_command")
run_command = server_info.get("run_command")
if not install_command:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.error(
f"No install_command found for GitHub-based server {server_name}"
)
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
return False
if not run_command:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.error(
f"No run_command found for GitHub-based server {server_name}"
)
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
return False
try:
self.logger.info(f"Installing MCP server from GitHub: {server_name}")
if self._check_mcp_server_installed(server_name):
self.logger.info(f"MCP server {server_name} already installed")
return True
# Check if uvx is available
try:
uvx_check = self._run_command_cross_platform(
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
["uvx", "--version"], capture_output=True, text=True, timeout=10
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
)
if uvx_check.returncode != 0:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.error(
f"uvx not found - required for {server_name} installation"
)
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
return False
except (subprocess.TimeoutExpired, FileNotFoundError):
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.error(
f"uvx not found - required for {server_name} installation"
)
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
return False
if config.get("dry_run"):
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.info(
f"Would install MCP server from GitHub: {install_command}"
)
self.logger.info(
f"Would register MCP server run command: {run_command}"
)
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
return True
# Run install command to test the GitHub installation
self.logger.debug(f"Testing GitHub installation: {install_command}")
cmd_parts = shlex.split(install_command)
result = self._run_command_cross_platform(
cmd_parts,
capture_output=True,
text=True,
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
timeout=300, # 5 minutes for GitHub clone and build
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
)
if result.returncode == 0:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.success(
f"Successfully tested GitHub MCP server: {server_name}"
)
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
# Register with Claude CLI using the run command
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.info(
f"Registering {server_name} with Claude CLI. Run command: {run_command}"
)
reg_cmd = [
"claude",
"mcp",
"add",
"-s",
"user",
"--",
server_name,
] + shlex.split(run_command)
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
reg_result = self._run_command_cross_platform(
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
reg_cmd, capture_output=True, text=True, timeout=120
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
)
if reg_result.returncode == 0:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.success(
f"Successfully registered {server_name} with Claude CLI."
)
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
return True
else:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
error_msg = (
reg_result.stderr.strip()
if reg_result.stderr
else "Unknown error"
)
self.logger.error(
f"Failed to register MCP server {server_name} with Claude CLI: {error_msg}"
)
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
return False
else:
error_msg = result.stderr.strip() if result.stderr else "Unknown error"
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.error(
f"Failed to install MCP server {server_name} from GitHub: {error_msg}\n{result.stdout}"
)
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
return False
except subprocess.TimeoutExpired:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.error(
f"Timeout installing MCP server {server_name} from GitHub"
)
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
return False
except Exception as e:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.error(
f"Error installing MCP server {server_name} from GitHub: {e}"
)
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
return False
def _check_mcp_server_installed(self, server_name: str) -> bool:
"""Check if MCP server is already installed"""
2025-08-14 08:56:04 +05:30
try:
result = self._run_command_cross_platform(
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
["claude", "mcp", "list"], capture_output=True, text=True, timeout=60
)
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
if result.returncode != 0:
self.logger.warning(f"Could not list MCP servers: {result.stderr}")
return False
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
# Parse output to check if server is installed
output = result.stdout.lower()
return server_name.lower() in output
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
except (subprocess.TimeoutExpired, subprocess.SubprocessError) as e:
self.logger.warning(f"Error checking MCP server status: {e}")
return False
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
def _detect_existing_mcp_servers_from_config(self) -> List[str]:
"""Detect existing MCP servers from Claude Desktop config"""
detected_servers = []
try:
# Try to find Claude Desktop config file
config_paths = [
self.install_dir / "claude_desktop_config.json",
Path.home() / ".claude" / "claude_desktop_config.json",
Path.home() / ".claude.json", # Claude CLI config
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
Path.home()
/ "AppData"
/ "Roaming"
/ "Claude"
/ "claude_desktop_config.json", # Windows
Path.home()
/ "Library"
/ "Application Support"
/ "Claude"
/ "claude_desktop_config.json", # macOS
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
]
config_file = None
for path in config_paths:
if path.exists():
config_file = path
break
if not config_file:
self.logger.debug("No Claude Desktop config file found")
return detected_servers
import json
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
with open(config_file, "r") as f:
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
config = json.load(f)
# Extract MCP server names from mcpServers section
mcp_servers = config.get("mcpServers", {})
for server_name in mcp_servers.keys():
# Map common name variations to our standard names
normalized_name = self._normalize_server_name(server_name)
if normalized_name and normalized_name in self.mcp_servers:
detected_servers.append(normalized_name)
if detected_servers:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.info(
f"Detected existing MCP servers from config: {detected_servers}"
)
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
except Exception as e:
self.logger.warning(f"Could not read Claude Desktop config: {e}")
return detected_servers
def _detect_existing_mcp_servers_from_cli(self) -> List[str]:
"""Detect existing MCP servers from Claude CLI"""
detected_servers = []
try:
result = self._run_command_cross_platform(
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
["claude", "mcp", "list"], capture_output=True, text=True, timeout=60
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
)
if result.returncode != 0:
self.logger.debug(f"Could not list MCP servers: {result.stderr}")
return detected_servers
# Parse the output to extract server names
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
output_lines = result.stdout.strip().split("\n")
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
for line in output_lines:
line = line.strip().lower()
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
if line and not line.startswith("#") and not line.startswith("no"):
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
# Extract server name (usually the first word or before first space/colon)
server_name = line.split()[0] if line.split() else ""
normalized_name = self._normalize_server_name(server_name)
if normalized_name and normalized_name in self.mcp_servers:
detected_servers.append(normalized_name)
if detected_servers:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.info(
f"Detected existing MCP servers from CLI: {detected_servers}"
)
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
except Exception as e:
self.logger.warning(f"Could not detect existing MCP servers from CLI: {e}")
return detected_servers
def _normalize_server_name(self, server_name: str) -> Optional[str]:
"""Normalize server name to match our internal naming"""
if not server_name:
return None
server_name = server_name.lower().strip()
# Map common variations to our standard names
name_mappings = {
refactor: PM Agent complete independence from external MCP servers (#439) * refactor: PM Agent complete independence from external MCP servers ## Summary Implement graceful degradation to ensure PM Agent operates fully without any MCP server dependencies. MCP servers now serve as optional enhancements rather than required components. ## Changes ### Responsibility Separation (NEW) - **PM Agent**: Development workflow orchestration (PDCA cycle, task management) - **mindbase**: Memory management (long-term, freshness, error learning) - **Built-in memory**: Session-internal context (volatile) ### 3-Layer Memory Architecture with Fallbacks 1. **Built-in Memory** [OPTIONAL]: Session context via MCP memory server 2. **mindbase** [OPTIONAL]: Long-term semantic search via airis-mcp-gateway 3. **Local Files** [ALWAYS]: Core functionality in docs/memory/ ### Graceful Degradation Implementation - All MCP operations marked with [ALWAYS] or [OPTIONAL] - Explicit IF/ELSE fallback logic for every MCP call - Dual storage: Always write to local files + optionally to mindbase - Smart lookup: Semantic search (if available) → Text search (always works) ### Key Fallback Strategies **Session Start**: - mindbase available: search_conversations() for semantic context - mindbase unavailable: Grep docs/memory/*.jsonl for text-based lookup **Error Detection**: - mindbase available: Semantic search for similar past errors - mindbase unavailable: Grep docs/mistakes/ + solutions_learned.jsonl **Knowledge Capture**: - Always: echo >> docs/memory/patterns_learned.jsonl (persistent) - Optional: mindbase.store() for semantic search enhancement ## Benefits - ✅ Zero external dependencies (100% functionality without MCP) - ✅ Enhanced capabilities when MCPs available (semantic search, freshness) - ✅ No functionality loss, only reduced search intelligence - ✅ Transparent degradation (no error messages, automatic fallback) ## Related Research - Serena MCP investigation: Exposes tools (not resources), memory = markdown files - mindbase superiority: PostgreSQL + pgvector > Serena memory features - Best practices alignment: /Users/kazuki/github/airis-mcp-gateway/docs/mcp-best-practices.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: add PR template and pre-commit config - Add structured PR template with Git workflow checklist - Add pre-commit hooks for secret detection and Conventional Commits - Enforce code quality gates (YAML/JSON/Markdown lint, shellcheck) NOTE: Execute pre-commit inside Docker container to avoid host pollution: docker compose exec workspace uv tool install pre-commit docker compose exec workspace pre-commit run --all-files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: update PM Agent context with token efficiency architecture - Add Layer 0 Bootstrap (150 tokens, 95% reduction) - Document Intent Classification System (5 complexity levels) - Add Progressive Loading strategy (5-layer) - Document mindbase integration incentive (38% savings) - Update with 2025-10-17 redesign details * refactor: PM Agent command with progressive loading - Replace auto-loading with User Request First philosophy - Add 5-layer progressive context loading - Implement intent classification system - Add workflow metrics collection (.jsonl) - Document graceful degradation strategy * fix: installer improvements Update installer logic for better reliability * docs: add comprehensive development documentation - Add architecture overview - Add PM Agent improvements analysis - Add parallel execution architecture - Add CLI install improvements - Add code style guide - Add project overview - Add install process analysis * docs: add research documentation Add LLM agent token efficiency research and analysis * docs: add suggested commands reference * docs: add session logs and testing documentation - Add session analysis logs - Add testing documentation * feat: migrate CLI to typer + rich for modern UX ## What Changed ### New CLI Architecture (typer + rich) - Created `superclaude/cli/` module with modern typer-based CLI - Replaced custom UI utilities with rich native features - Added type-safe command structure with automatic validation ### Commands Implemented - **install**: Interactive installation with rich UI (progress, panels) - **doctor**: System diagnostics with rich table output - **config**: API key management with format validation ### Technical Improvements - Dependencies: Added typer>=0.9.0, rich>=13.0.0, click>=8.0.0 - Entry Point: Updated pyproject.toml to use `superclaude.cli.app:cli_main` - Tests: Added comprehensive smoke tests (11 passed) ### User Experience Enhancements - Rich formatted help messages with panels and tables - Automatic input validation with retry loops - Clear error messages with actionable suggestions - Non-interactive mode support for CI/CD ## Testing ```bash uv run superclaude --help # ✓ Works uv run superclaude doctor # ✓ Rich table output uv run superclaude config show # ✓ API key management pytest tests/test_cli_smoke.py # ✓ 11 passed, 1 skipped ``` ## Migration Path - ✅ P0: Foundation complete (typer + rich + smoke tests) - 🔜 P1: Pydantic validation models (next sprint) - 🔜 P2: Enhanced error messages (next sprint) - 🔜 P3: API key retry loops (next sprint) ## Performance Impact - **Code Reduction**: Prepared for -300 lines (custom UI → rich) - **Type Safety**: Automatic validation from type hints - **Maintainability**: Framework primitives vs custom code 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate documentation directories Merged claudedocs/ into docs/research/ for consistent documentation structure. Changes: - Moved all claudedocs/*.md files to docs/research/ - Updated all path references in documentation (EN/KR) - Updated RULES.md and research.md command templates - Removed claudedocs/ directory - Removed ClaudeDocs/ from .gitignore Benefits: - Single source of truth for all research reports - PEP8-compliant lowercase directory naming - Clearer documentation organization - Prevents future claudedocs/ directory creation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: reduce /sc:pm command output from 1652 to 15 lines - Remove 1637 lines of documentation from command file - Keep only minimal bootstrap message - 99% token reduction on command execution - Detailed specs remain in superclaude/agents/pm-agent.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: split PM Agent into execution workflows and guide - Reduce pm-agent.md from 735 to 429 lines (42% reduction) - Move philosophy/examples to docs/agents/pm-agent-guide.md - Execution workflows (PDCA, file ops) stay in pm-agent.md - Guide (examples, quality standards) read once when needed Token savings: - Agent loading: ~6K → ~3.5K tokens (42% reduction) - Total with pm.md: 71% overall reduction 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate PM Agent optimization and pending changes PM Agent optimization (already committed separately): - superclaude/commands/pm.md: 1652→14 lines - superclaude/agents/pm-agent.md: 735→429 lines - docs/agents/pm-agent-guide.md: new guide file Other pending changes: - setup: framework_docs, mcp, logger, remove ui.py - superclaude: __main__, cli/app, cli/commands/install - tests: test_ui updates - scripts: workflow metrics analysis tools - docs/memory: session state updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: simplify MCP installer to unified gateway with legacy mode ## Changes ### MCP Component (setup/components/mcp.py) - Simplified to single airis-mcp-gateway by default - Added legacy mode for individual official servers (sequential-thinking, context7, magic, playwright) - Dynamic prerequisites based on mode: - Default: uv + claude CLI only - Legacy: node (18+) + npm + claude CLI - Removed redundant server definitions ### CLI Integration - Added --legacy flag to setup/cli/commands/install.py - Added --legacy flag to superclaude/cli/commands/install.py - Config passes legacy_mode to component installer ## Benefits - ✅ Simpler: 1 gateway vs 9+ individual servers - ✅ Lighter: No Node.js/npm required (default mode) - ✅ Unified: All tools in one gateway (sequential-thinking, context7, magic, playwright, serena, morphllm, tavily, chrome-devtools, git, puppeteer) - ✅ Flexible: --legacy flag for official servers if needed ## Usage ```bash superclaude install # Default: airis-mcp-gateway (推奨) superclaude install --legacy # Legacy: individual official servers ``` 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename CoreComponent to FrameworkDocsComponent and add PM token tracking ## Changes ### Component Renaming (setup/components/) - Renamed CoreComponent → FrameworkDocsComponent for clarity - Updated all imports in __init__.py, agents.py, commands.py, mcp_docs.py, modes.py - Better reflects the actual purpose (framework documentation files) ### PM Agent Enhancement (superclaude/commands/pm.md) - Added token usage tracking instructions - PM Agent now reports: 1. Current token usage from system warnings 2. Percentage used (e.g., "27% used" for 54K/200K) 3. Status zone: 🟢 <75% | 🟡 75-85% | 🔴 >85% - Helps prevent token exhaustion during long sessions ### UI Utilities (setup/utils/ui.py) - Added new UI utility module for installer - Provides consistent user interface components ## Benefits - ✅ Clearer component naming (FrameworkDocs vs Core) - ✅ PM Agent token awareness for efficiency - ✅ Better visual feedback with status zones 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor(pm-agent): minimize output verbosity (471→284 lines, 40% reduction) **Problem**: PM Agent generated excessive output with redundant explanations - "System Status Report" with decorative formatting - Repeated "Common Tasks" lists user already knows - Verbose session start/end protocols - Duplicate file operations documentation **Solution**: Compress without losing functionality - Session Start: Reduced to symbol-only status (🟢 branch | nM nD | token%) - Session End: Compressed to essential actions only - File Operations: Consolidated from 2 sections to 1 line reference - Self-Improvement: 5 phases → 1 unified workflow - Output Rules: Explicit constraints to prevent Claude over-explanation **Quality Preservation**: - ✅ All core functions retained (PDCA, memory, patterns, mistakes) - ✅ PARALLEL Read/Write preserved (performance critical) - ✅ Workflow unchanged (session lifecycle intact) - ✅ Added output constraints (prevents verbose generation) **Reduction Method**: - Deleted: Explanatory text, examples, redundant sections - Retained: Action definitions, file paths, core workflows - Added: Explicit output constraints to enforce minimalism **Token Impact**: 40% reduction in agent documentation size **Before**: Verbose multi-section report with task lists **After**: Single line status: 🟢 integration | 15M 17D | 36% 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate MCP integration to unified gateway **Changes**: - Remove individual MCP server docs (superclaude/mcp/*.md) - Remove MCP server configs (superclaude/mcp/configs/*.json) - Delete MCP docs component (setup/components/mcp_docs.py) - Simplify installer (setup/core/installer.py) - Update components for unified gateway approach **Rationale**: - Unified gateway (airis-mcp-gateway) provides all MCP servers - Individual docs/configs no longer needed (managed centrally) - Reduces maintenance burden and file count - Simplifies installation process **Files Removed**: 17 MCP files (docs + configs) **Installer Changes**: Removed legacy MCP installation logic 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: update version and component metadata - Bump version (pyproject.toml, setup/__init__.py) - Update CLAUDE.md import service references - Reflect component structure changes 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-17 09:13:06 +09:00
"airis-mcp-gateway": "airis-mcp-gateway",
"airis": "airis-mcp-gateway",
"gateway": "airis-mcp-gateway",
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
}
return name_mappings.get(server_name)
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
def _merge_server_lists(
self,
existing_servers: List[str],
selected_servers: List[str],
previous_servers: List[str],
) -> List[str]:
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
"""Merge existing, selected, and previously installed servers"""
all_servers = set()
# Add all detected servers
all_servers.update(existing_servers)
all_servers.update(selected_servers)
all_servers.update(previous_servers)
# Filter to only include servers we know how to install
valid_servers = [s for s in all_servers if s in self.mcp_servers]
if valid_servers:
self.logger.info(f"Total servers to manage: {valid_servers}")
if existing_servers:
self.logger.info(f" - Existing: {existing_servers}")
if selected_servers:
self.logger.info(f" - Newly selected: {selected_servers}")
if previous_servers:
self.logger.info(f" - Previously installed: {previous_servers}")
return valid_servers
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
def _install_mcp_server(
self, server_info: Dict[str, Any], config: Dict[str, Any]
) -> bool:
"""Install a single MCP server"""
if server_info.get("install_method") == "uv":
return self._install_uv_mcp_server(server_info, config)
elif server_info.get("install_method") == "airis_gateway":
return self._install_airis_gateway(server_info, config)
Some fixes (#372) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
2025-09-19 19:03:50 +05:30
elif server_info.get("install_method") == "github":
return self._install_github_mcp_server(server_info, config)
server_name = server_info["name"]
npm_package = server_info.get("npm_package")
feat: Add Deep Research System v4.2.0 (#380) feat: Add Deep Research System v4.2.0 - Autonomous web research capabilities ## Overview Comprehensive implementation of Deep Research framework aligned with DR Agent architecture, enabling autonomous, adaptive, and intelligent web research capabilities. ## Key Features ### 🔬 Deep Research Agent - 15th specialized agent for comprehensive research orchestration - Adaptive planning strategies: Planning-Only, Intent-Planning, Unified Intent-Planning - Multi-hop reasoning with genealogy tracking (up to 5 hops) - Self-reflective mechanisms with confidence scoring (0.0-1.0) - Case-based learning for cross-session intelligence ### 🎯 New /sc:research Command - Intelligent web research with depth control (quick/standard/deep/exhaustive) - Parallel-first execution for optimal performance - Domain filtering and time-based search options - Automatic report generation in claudedocs/ ### 🔍 Tavily MCP Integration - 7th MCP server for real-time web search - News search with time filtering - Content extraction from search results - Multi-round searching with iterative refinement - Free tier available with optional API key ### 🎨 MODE_DeepResearch - 7th behavioral mode for systematic investigation - 6-phase workflow: Understand → Plan → TodoWrite → Execute → Track → Validate - Evidence-based reasoning with citation management - Parallel operation defaults for efficiency ## Technical Changes ### Framework Updates - Updated agent count: 14 → 15 agents - Updated mode count: 6 → 7 modes - Updated MCP server count: 6 → 7 servers - Updated command count: 24 → 25 commands ### Configuration - Added RESEARCH_CONFIG.md for research settings - Added deep_research_workflows.md with examples - Standardized file naming conventions (UPPERCASE for Core) - Removed multi-source investigation features for simplification ### Integration Points - Enhanced MCP component with remote server support - Added check_research_prerequisites() in environment.py - Created verify_research_integration.sh script - Updated all documentation guides ## Requirements - TAVILY_API_KEY environment variable (free tier available) - Node.js and npm for Tavily MCP execution ## Documentation - Complete user guide integration - Workflow examples and best practices - API configuration instructions - Depth level explanations 🤖 Generated with Claude Code Co-authored-by: moshe_anconina <moshe_a@ituran.com> Co-authored-by: Claude <noreply@anthropic.com>
2025-09-21 04:54:42 +03:00
install_command = server_info.get("install_command")
feat: Add Deep Research System v4.2.0 (#380) feat: Add Deep Research System v4.2.0 - Autonomous web research capabilities ## Overview Comprehensive implementation of Deep Research framework aligned with DR Agent architecture, enabling autonomous, adaptive, and intelligent web research capabilities. ## Key Features ### 🔬 Deep Research Agent - 15th specialized agent for comprehensive research orchestration - Adaptive planning strategies: Planning-Only, Intent-Planning, Unified Intent-Planning - Multi-hop reasoning with genealogy tracking (up to 5 hops) - Self-reflective mechanisms with confidence scoring (0.0-1.0) - Case-based learning for cross-session intelligence ### 🎯 New /sc:research Command - Intelligent web research with depth control (quick/standard/deep/exhaustive) - Parallel-first execution for optimal performance - Domain filtering and time-based search options - Automatic report generation in claudedocs/ ### 🔍 Tavily MCP Integration - 7th MCP server for real-time web search - News search with time filtering - Content extraction from search results - Multi-round searching with iterative refinement - Free tier available with optional API key ### 🎨 MODE_DeepResearch - 7th behavioral mode for systematic investigation - 6-phase workflow: Understand → Plan → TodoWrite → Execute → Track → Validate - Evidence-based reasoning with citation management - Parallel operation defaults for efficiency ## Technical Changes ### Framework Updates - Updated agent count: 14 → 15 agents - Updated mode count: 6 → 7 modes - Updated MCP server count: 6 → 7 servers - Updated command count: 24 → 25 commands ### Configuration - Added RESEARCH_CONFIG.md for research settings - Added deep_research_workflows.md with examples - Standardized file naming conventions (UPPERCASE for Core) - Removed multi-source investigation features for simplification ### Integration Points - Enhanced MCP component with remote server support - Added check_research_prerequisites() in environment.py - Created verify_research_integration.sh script - Updated all documentation guides ## Requirements - TAVILY_API_KEY environment variable (free tier available) - Node.js and npm for Tavily MCP execution ## Documentation - Complete user guide integration - Workflow examples and best practices - API configuration instructions - Depth level explanations 🤖 Generated with Claude Code Co-authored-by: moshe_anconina <moshe_a@ituran.com> Co-authored-by: Claude <noreply@anthropic.com>
2025-09-21 04:54:42 +03:00
if not npm_package and not install_command:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.error(
f"No npm_package or install_command found for server {server_name}"
)
return False
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
command = "npx"
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
try:
self.logger.info(f"Installing MCP server: {server_name}")
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
# Check if already installed
if self._check_mcp_server_installed(server_name):
self.logger.info(f"MCP server {server_name} already installed")
return True
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
# Handle API key requirements
if "api_key_env" in server_info:
api_key_env = server_info["api_key_env"]
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
api_key_desc = server_info.get(
"api_key_description", f"API key for {server_name}"
)
if not config.get("dry_run", False):
refactor: PM Agent complete independence from external MCP servers (#439) * refactor: PM Agent complete independence from external MCP servers ## Summary Implement graceful degradation to ensure PM Agent operates fully without any MCP server dependencies. MCP servers now serve as optional enhancements rather than required components. ## Changes ### Responsibility Separation (NEW) - **PM Agent**: Development workflow orchestration (PDCA cycle, task management) - **mindbase**: Memory management (long-term, freshness, error learning) - **Built-in memory**: Session-internal context (volatile) ### 3-Layer Memory Architecture with Fallbacks 1. **Built-in Memory** [OPTIONAL]: Session context via MCP memory server 2. **mindbase** [OPTIONAL]: Long-term semantic search via airis-mcp-gateway 3. **Local Files** [ALWAYS]: Core functionality in docs/memory/ ### Graceful Degradation Implementation - All MCP operations marked with [ALWAYS] or [OPTIONAL] - Explicit IF/ELSE fallback logic for every MCP call - Dual storage: Always write to local files + optionally to mindbase - Smart lookup: Semantic search (if available) → Text search (always works) ### Key Fallback Strategies **Session Start**: - mindbase available: search_conversations() for semantic context - mindbase unavailable: Grep docs/memory/*.jsonl for text-based lookup **Error Detection**: - mindbase available: Semantic search for similar past errors - mindbase unavailable: Grep docs/mistakes/ + solutions_learned.jsonl **Knowledge Capture**: - Always: echo >> docs/memory/patterns_learned.jsonl (persistent) - Optional: mindbase.store() for semantic search enhancement ## Benefits - ✅ Zero external dependencies (100% functionality without MCP) - ✅ Enhanced capabilities when MCPs available (semantic search, freshness) - ✅ No functionality loss, only reduced search intelligence - ✅ Transparent degradation (no error messages, automatic fallback) ## Related Research - Serena MCP investigation: Exposes tools (not resources), memory = markdown files - mindbase superiority: PostgreSQL + pgvector > Serena memory features - Best practices alignment: /Users/kazuki/github/airis-mcp-gateway/docs/mcp-best-practices.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: add PR template and pre-commit config - Add structured PR template with Git workflow checklist - Add pre-commit hooks for secret detection and Conventional Commits - Enforce code quality gates (YAML/JSON/Markdown lint, shellcheck) NOTE: Execute pre-commit inside Docker container to avoid host pollution: docker compose exec workspace uv tool install pre-commit docker compose exec workspace pre-commit run --all-files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: update PM Agent context with token efficiency architecture - Add Layer 0 Bootstrap (150 tokens, 95% reduction) - Document Intent Classification System (5 complexity levels) - Add Progressive Loading strategy (5-layer) - Document mindbase integration incentive (38% savings) - Update with 2025-10-17 redesign details * refactor: PM Agent command with progressive loading - Replace auto-loading with User Request First philosophy - Add 5-layer progressive context loading - Implement intent classification system - Add workflow metrics collection (.jsonl) - Document graceful degradation strategy * fix: installer improvements Update installer logic for better reliability * docs: add comprehensive development documentation - Add architecture overview - Add PM Agent improvements analysis - Add parallel execution architecture - Add CLI install improvements - Add code style guide - Add project overview - Add install process analysis * docs: add research documentation Add LLM agent token efficiency research and analysis * docs: add suggested commands reference * docs: add session logs and testing documentation - Add session analysis logs - Add testing documentation * feat: migrate CLI to typer + rich for modern UX ## What Changed ### New CLI Architecture (typer + rich) - Created `superclaude/cli/` module with modern typer-based CLI - Replaced custom UI utilities with rich native features - Added type-safe command structure with automatic validation ### Commands Implemented - **install**: Interactive installation with rich UI (progress, panels) - **doctor**: System diagnostics with rich table output - **config**: API key management with format validation ### Technical Improvements - Dependencies: Added typer>=0.9.0, rich>=13.0.0, click>=8.0.0 - Entry Point: Updated pyproject.toml to use `superclaude.cli.app:cli_main` - Tests: Added comprehensive smoke tests (11 passed) ### User Experience Enhancements - Rich formatted help messages with panels and tables - Automatic input validation with retry loops - Clear error messages with actionable suggestions - Non-interactive mode support for CI/CD ## Testing ```bash uv run superclaude --help # ✓ Works uv run superclaude doctor # ✓ Rich table output uv run superclaude config show # ✓ API key management pytest tests/test_cli_smoke.py # ✓ 11 passed, 1 skipped ``` ## Migration Path - ✅ P0: Foundation complete (typer + rich + smoke tests) - 🔜 P1: Pydantic validation models (next sprint) - 🔜 P2: Enhanced error messages (next sprint) - 🔜 P3: API key retry loops (next sprint) ## Performance Impact - **Code Reduction**: Prepared for -300 lines (custom UI → rich) - **Type Safety**: Automatic validation from type hints - **Maintainability**: Framework primitives vs custom code 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate documentation directories Merged claudedocs/ into docs/research/ for consistent documentation structure. Changes: - Moved all claudedocs/*.md files to docs/research/ - Updated all path references in documentation (EN/KR) - Updated RULES.md and research.md command templates - Removed claudedocs/ directory - Removed ClaudeDocs/ from .gitignore Benefits: - Single source of truth for all research reports - PEP8-compliant lowercase directory naming - Clearer documentation organization - Prevents future claudedocs/ directory creation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: reduce /sc:pm command output from 1652 to 15 lines - Remove 1637 lines of documentation from command file - Keep only minimal bootstrap message - 99% token reduction on command execution - Detailed specs remain in superclaude/agents/pm-agent.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: split PM Agent into execution workflows and guide - Reduce pm-agent.md from 735 to 429 lines (42% reduction) - Move philosophy/examples to docs/agents/pm-agent-guide.md - Execution workflows (PDCA, file ops) stay in pm-agent.md - Guide (examples, quality standards) read once when needed Token savings: - Agent loading: ~6K → ~3.5K tokens (42% reduction) - Total with pm.md: 71% overall reduction 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate PM Agent optimization and pending changes PM Agent optimization (already committed separately): - superclaude/commands/pm.md: 1652→14 lines - superclaude/agents/pm-agent.md: 735→429 lines - docs/agents/pm-agent-guide.md: new guide file Other pending changes: - setup: framework_docs, mcp, logger, remove ui.py - superclaude: __main__, cli/app, cli/commands/install - tests: test_ui updates - scripts: workflow metrics analysis tools - docs/memory: session state updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: simplify MCP installer to unified gateway with legacy mode ## Changes ### MCP Component (setup/components/mcp.py) - Simplified to single airis-mcp-gateway by default - Added legacy mode for individual official servers (sequential-thinking, context7, magic, playwright) - Dynamic prerequisites based on mode: - Default: uv + claude CLI only - Legacy: node (18+) + npm + claude CLI - Removed redundant server definitions ### CLI Integration - Added --legacy flag to setup/cli/commands/install.py - Added --legacy flag to superclaude/cli/commands/install.py - Config passes legacy_mode to component installer ## Benefits - ✅ Simpler: 1 gateway vs 9+ individual servers - ✅ Lighter: No Node.js/npm required (default mode) - ✅ Unified: All tools in one gateway (sequential-thinking, context7, magic, playwright, serena, morphllm, tavily, chrome-devtools, git, puppeteer) - ✅ Flexible: --legacy flag for official servers if needed ## Usage ```bash superclaude install # Default: airis-mcp-gateway (推奨) superclaude install --legacy # Legacy: individual official servers ``` 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename CoreComponent to FrameworkDocsComponent and add PM token tracking ## Changes ### Component Renaming (setup/components/) - Renamed CoreComponent → FrameworkDocsComponent for clarity - Updated all imports in __init__.py, agents.py, commands.py, mcp_docs.py, modes.py - Better reflects the actual purpose (framework documentation files) ### PM Agent Enhancement (superclaude/commands/pm.md) - Added token usage tracking instructions - PM Agent now reports: 1. Current token usage from system warnings 2. Percentage used (e.g., "27% used" for 54K/200K) 3. Status zone: 🟢 <75% | 🟡 75-85% | 🔴 >85% - Helps prevent token exhaustion during long sessions ### UI Utilities (setup/utils/ui.py) - Added new UI utility module for installer - Provides consistent user interface components ## Benefits - ✅ Clearer component naming (FrameworkDocs vs Core) - ✅ PM Agent token awareness for efficiency - ✅ Better visual feedback with status zones 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor(pm-agent): minimize output verbosity (471→284 lines, 40% reduction) **Problem**: PM Agent generated excessive output with redundant explanations - "System Status Report" with decorative formatting - Repeated "Common Tasks" lists user already knows - Verbose session start/end protocols - Duplicate file operations documentation **Solution**: Compress without losing functionality - Session Start: Reduced to symbol-only status (🟢 branch | nM nD | token%) - Session End: Compressed to essential actions only - File Operations: Consolidated from 2 sections to 1 line reference - Self-Improvement: 5 phases → 1 unified workflow - Output Rules: Explicit constraints to prevent Claude over-explanation **Quality Preservation**: - ✅ All core functions retained (PDCA, memory, patterns, mistakes) - ✅ PARALLEL Read/Write preserved (performance critical) - ✅ Workflow unchanged (session lifecycle intact) - ✅ Added output constraints (prevents verbose generation) **Reduction Method**: - Deleted: Explanatory text, examples, redundant sections - Retained: Action definitions, file paths, core workflows - Added: Explicit output constraints to enforce minimalism **Token Impact**: 40% reduction in agent documentation size **Before**: Verbose multi-section report with task lists **After**: Single line status: 🟢 integration | 15M 17D | 36% 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate MCP integration to unified gateway **Changes**: - Remove individual MCP server docs (superclaude/mcp/*.md) - Remove MCP server configs (superclaude/mcp/configs/*.json) - Delete MCP docs component (setup/components/mcp_docs.py) - Simplify installer (setup/core/installer.py) - Update components for unified gateway approach **Rationale**: - Unified gateway (airis-mcp-gateway) provides all MCP servers - Individual docs/configs no longer needed (managed centrally) - Reduces maintenance burden and file count - Simplifies installation process **Files Removed**: 17 MCP files (docs + configs) **Installer Changes**: Removed legacy MCP installation logic 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: update version and component metadata - Bump version (pyproject.toml, setup/__init__.py) - Update CLAUDE.md import service references - Reflect component structure changes 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-17 09:13:06 +09:00
self.logger.info(f"MCP server '{server_name}' requires an API key")
self.logger.info(f"Environment variable: {api_key_env}")
self.logger.info(f"Description: {api_key_desc}")
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
# Check if API key is already set
import os
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
if not os.getenv(api_key_env):
refactor: PM Agent complete independence from external MCP servers (#439) * refactor: PM Agent complete independence from external MCP servers ## Summary Implement graceful degradation to ensure PM Agent operates fully without any MCP server dependencies. MCP servers now serve as optional enhancements rather than required components. ## Changes ### Responsibility Separation (NEW) - **PM Agent**: Development workflow orchestration (PDCA cycle, task management) - **mindbase**: Memory management (long-term, freshness, error learning) - **Built-in memory**: Session-internal context (volatile) ### 3-Layer Memory Architecture with Fallbacks 1. **Built-in Memory** [OPTIONAL]: Session context via MCP memory server 2. **mindbase** [OPTIONAL]: Long-term semantic search via airis-mcp-gateway 3. **Local Files** [ALWAYS]: Core functionality in docs/memory/ ### Graceful Degradation Implementation - All MCP operations marked with [ALWAYS] or [OPTIONAL] - Explicit IF/ELSE fallback logic for every MCP call - Dual storage: Always write to local files + optionally to mindbase - Smart lookup: Semantic search (if available) → Text search (always works) ### Key Fallback Strategies **Session Start**: - mindbase available: search_conversations() for semantic context - mindbase unavailable: Grep docs/memory/*.jsonl for text-based lookup **Error Detection**: - mindbase available: Semantic search for similar past errors - mindbase unavailable: Grep docs/mistakes/ + solutions_learned.jsonl **Knowledge Capture**: - Always: echo >> docs/memory/patterns_learned.jsonl (persistent) - Optional: mindbase.store() for semantic search enhancement ## Benefits - ✅ Zero external dependencies (100% functionality without MCP) - ✅ Enhanced capabilities when MCPs available (semantic search, freshness) - ✅ No functionality loss, only reduced search intelligence - ✅ Transparent degradation (no error messages, automatic fallback) ## Related Research - Serena MCP investigation: Exposes tools (not resources), memory = markdown files - mindbase superiority: PostgreSQL + pgvector > Serena memory features - Best practices alignment: /Users/kazuki/github/airis-mcp-gateway/docs/mcp-best-practices.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: add PR template and pre-commit config - Add structured PR template with Git workflow checklist - Add pre-commit hooks for secret detection and Conventional Commits - Enforce code quality gates (YAML/JSON/Markdown lint, shellcheck) NOTE: Execute pre-commit inside Docker container to avoid host pollution: docker compose exec workspace uv tool install pre-commit docker compose exec workspace pre-commit run --all-files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: update PM Agent context with token efficiency architecture - Add Layer 0 Bootstrap (150 tokens, 95% reduction) - Document Intent Classification System (5 complexity levels) - Add Progressive Loading strategy (5-layer) - Document mindbase integration incentive (38% savings) - Update with 2025-10-17 redesign details * refactor: PM Agent command with progressive loading - Replace auto-loading with User Request First philosophy - Add 5-layer progressive context loading - Implement intent classification system - Add workflow metrics collection (.jsonl) - Document graceful degradation strategy * fix: installer improvements Update installer logic for better reliability * docs: add comprehensive development documentation - Add architecture overview - Add PM Agent improvements analysis - Add parallel execution architecture - Add CLI install improvements - Add code style guide - Add project overview - Add install process analysis * docs: add research documentation Add LLM agent token efficiency research and analysis * docs: add suggested commands reference * docs: add session logs and testing documentation - Add session analysis logs - Add testing documentation * feat: migrate CLI to typer + rich for modern UX ## What Changed ### New CLI Architecture (typer + rich) - Created `superclaude/cli/` module with modern typer-based CLI - Replaced custom UI utilities with rich native features - Added type-safe command structure with automatic validation ### Commands Implemented - **install**: Interactive installation with rich UI (progress, panels) - **doctor**: System diagnostics with rich table output - **config**: API key management with format validation ### Technical Improvements - Dependencies: Added typer>=0.9.0, rich>=13.0.0, click>=8.0.0 - Entry Point: Updated pyproject.toml to use `superclaude.cli.app:cli_main` - Tests: Added comprehensive smoke tests (11 passed) ### User Experience Enhancements - Rich formatted help messages with panels and tables - Automatic input validation with retry loops - Clear error messages with actionable suggestions - Non-interactive mode support for CI/CD ## Testing ```bash uv run superclaude --help # ✓ Works uv run superclaude doctor # ✓ Rich table output uv run superclaude config show # ✓ API key management pytest tests/test_cli_smoke.py # ✓ 11 passed, 1 skipped ``` ## Migration Path - ✅ P0: Foundation complete (typer + rich + smoke tests) - 🔜 P1: Pydantic validation models (next sprint) - 🔜 P2: Enhanced error messages (next sprint) - 🔜 P3: API key retry loops (next sprint) ## Performance Impact - **Code Reduction**: Prepared for -300 lines (custom UI → rich) - **Type Safety**: Automatic validation from type hints - **Maintainability**: Framework primitives vs custom code 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate documentation directories Merged claudedocs/ into docs/research/ for consistent documentation structure. Changes: - Moved all claudedocs/*.md files to docs/research/ - Updated all path references in documentation (EN/KR) - Updated RULES.md and research.md command templates - Removed claudedocs/ directory - Removed ClaudeDocs/ from .gitignore Benefits: - Single source of truth for all research reports - PEP8-compliant lowercase directory naming - Clearer documentation organization - Prevents future claudedocs/ directory creation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: reduce /sc:pm command output from 1652 to 15 lines - Remove 1637 lines of documentation from command file - Keep only minimal bootstrap message - 99% token reduction on command execution - Detailed specs remain in superclaude/agents/pm-agent.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: split PM Agent into execution workflows and guide - Reduce pm-agent.md from 735 to 429 lines (42% reduction) - Move philosophy/examples to docs/agents/pm-agent-guide.md - Execution workflows (PDCA, file ops) stay in pm-agent.md - Guide (examples, quality standards) read once when needed Token savings: - Agent loading: ~6K → ~3.5K tokens (42% reduction) - Total with pm.md: 71% overall reduction 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate PM Agent optimization and pending changes PM Agent optimization (already committed separately): - superclaude/commands/pm.md: 1652→14 lines - superclaude/agents/pm-agent.md: 735→429 lines - docs/agents/pm-agent-guide.md: new guide file Other pending changes: - setup: framework_docs, mcp, logger, remove ui.py - superclaude: __main__, cli/app, cli/commands/install - tests: test_ui updates - scripts: workflow metrics analysis tools - docs/memory: session state updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: simplify MCP installer to unified gateway with legacy mode ## Changes ### MCP Component (setup/components/mcp.py) - Simplified to single airis-mcp-gateway by default - Added legacy mode for individual official servers (sequential-thinking, context7, magic, playwright) - Dynamic prerequisites based on mode: - Default: uv + claude CLI only - Legacy: node (18+) + npm + claude CLI - Removed redundant server definitions ### CLI Integration - Added --legacy flag to setup/cli/commands/install.py - Added --legacy flag to superclaude/cli/commands/install.py - Config passes legacy_mode to component installer ## Benefits - ✅ Simpler: 1 gateway vs 9+ individual servers - ✅ Lighter: No Node.js/npm required (default mode) - ✅ Unified: All tools in one gateway (sequential-thinking, context7, magic, playwright, serena, morphllm, tavily, chrome-devtools, git, puppeteer) - ✅ Flexible: --legacy flag for official servers if needed ## Usage ```bash superclaude install # Default: airis-mcp-gateway (推奨) superclaude install --legacy # Legacy: individual official servers ``` 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename CoreComponent to FrameworkDocsComponent and add PM token tracking ## Changes ### Component Renaming (setup/components/) - Renamed CoreComponent → FrameworkDocsComponent for clarity - Updated all imports in __init__.py, agents.py, commands.py, mcp_docs.py, modes.py - Better reflects the actual purpose (framework documentation files) ### PM Agent Enhancement (superclaude/commands/pm.md) - Added token usage tracking instructions - PM Agent now reports: 1. Current token usage from system warnings 2. Percentage used (e.g., "27% used" for 54K/200K) 3. Status zone: 🟢 <75% | 🟡 75-85% | 🔴 >85% - Helps prevent token exhaustion during long sessions ### UI Utilities (setup/utils/ui.py) - Added new UI utility module for installer - Provides consistent user interface components ## Benefits - ✅ Clearer component naming (FrameworkDocs vs Core) - ✅ PM Agent token awareness for efficiency - ✅ Better visual feedback with status zones 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor(pm-agent): minimize output verbosity (471→284 lines, 40% reduction) **Problem**: PM Agent generated excessive output with redundant explanations - "System Status Report" with decorative formatting - Repeated "Common Tasks" lists user already knows - Verbose session start/end protocols - Duplicate file operations documentation **Solution**: Compress without losing functionality - Session Start: Reduced to symbol-only status (🟢 branch | nM nD | token%) - Session End: Compressed to essential actions only - File Operations: Consolidated from 2 sections to 1 line reference - Self-Improvement: 5 phases → 1 unified workflow - Output Rules: Explicit constraints to prevent Claude over-explanation **Quality Preservation**: - ✅ All core functions retained (PDCA, memory, patterns, mistakes) - ✅ PARALLEL Read/Write preserved (performance critical) - ✅ Workflow unchanged (session lifecycle intact) - ✅ Added output constraints (prevents verbose generation) **Reduction Method**: - Deleted: Explanatory text, examples, redundant sections - Retained: Action definitions, file paths, core workflows - Added: Explicit output constraints to enforce minimalism **Token Impact**: 40% reduction in agent documentation size **Before**: Verbose multi-section report with task lists **After**: Single line status: 🟢 integration | 15M 17D | 36% 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate MCP integration to unified gateway **Changes**: - Remove individual MCP server docs (superclaude/mcp/*.md) - Remove MCP server configs (superclaude/mcp/configs/*.json) - Delete MCP docs component (setup/components/mcp_docs.py) - Simplify installer (setup/core/installer.py) - Update components for unified gateway approach **Rationale**: - Unified gateway (airis-mcp-gateway) provides all MCP servers - Individual docs/configs no longer needed (managed centrally) - Reduces maintenance burden and file count - Simplifies installation process **Files Removed**: 17 MCP files (docs + configs) **Installer Changes**: Removed legacy MCP installation logic 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: update version and component metadata - Bump version (pyproject.toml, setup/__init__.py) - Update CLAUDE.md import service references - Reflect component structure changes 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-17 09:13:06 +09:00
self.logger.warning(
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
f"API key {api_key_env} not found in environment"
)
self.logger.warning(
f"Proceeding without {api_key_env} - server may not function properly"
)
# Install using Claude CLI
feat: Add Deep Research System v4.2.0 (#380) feat: Add Deep Research System v4.2.0 - Autonomous web research capabilities ## Overview Comprehensive implementation of Deep Research framework aligned with DR Agent architecture, enabling autonomous, adaptive, and intelligent web research capabilities. ## Key Features ### 🔬 Deep Research Agent - 15th specialized agent for comprehensive research orchestration - Adaptive planning strategies: Planning-Only, Intent-Planning, Unified Intent-Planning - Multi-hop reasoning with genealogy tracking (up to 5 hops) - Self-reflective mechanisms with confidence scoring (0.0-1.0) - Case-based learning for cross-session intelligence ### 🎯 New /sc:research Command - Intelligent web research with depth control (quick/standard/deep/exhaustive) - Parallel-first execution for optimal performance - Domain filtering and time-based search options - Automatic report generation in claudedocs/ ### 🔍 Tavily MCP Integration - 7th MCP server for real-time web search - News search with time filtering - Content extraction from search results - Multi-round searching with iterative refinement - Free tier available with optional API key ### 🎨 MODE_DeepResearch - 7th behavioral mode for systematic investigation - 6-phase workflow: Understand → Plan → TodoWrite → Execute → Track → Validate - Evidence-based reasoning with citation management - Parallel operation defaults for efficiency ## Technical Changes ### Framework Updates - Updated agent count: 14 → 15 agents - Updated mode count: 6 → 7 modes - Updated MCP server count: 6 → 7 servers - Updated command count: 24 → 25 commands ### Configuration - Added RESEARCH_CONFIG.md for research settings - Added deep_research_workflows.md with examples - Standardized file naming conventions (UPPERCASE for Core) - Removed multi-source investigation features for simplification ### Integration Points - Enhanced MCP component with remote server support - Added check_research_prerequisites() in environment.py - Created verify_research_integration.sh script - Updated all documentation guides ## Requirements - TAVILY_API_KEY environment variable (free tier available) - Node.js and npm for Tavily MCP execution ## Documentation - Complete user guide integration - Workflow examples and best practices - API configuration instructions - Depth level explanations 🤖 Generated with Claude Code Co-authored-by: moshe_anconina <moshe_a@ituran.com> Co-authored-by: Claude <noreply@anthropic.com>
2025-09-21 04:54:42 +03:00
if install_command:
# Use the full install command (e.g., for tavily-mcp@0.1.2)
install_args = install_command.split()
if config.get("dry_run"):
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.info(
f"Would install MCP server (user scope): claude mcp add -s user {server_name} {' '.join(install_args)}"
)
feat: Add Deep Research System v4.2.0 (#380) feat: Add Deep Research System v4.2.0 - Autonomous web research capabilities ## Overview Comprehensive implementation of Deep Research framework aligned with DR Agent architecture, enabling autonomous, adaptive, and intelligent web research capabilities. ## Key Features ### 🔬 Deep Research Agent - 15th specialized agent for comprehensive research orchestration - Adaptive planning strategies: Planning-Only, Intent-Planning, Unified Intent-Planning - Multi-hop reasoning with genealogy tracking (up to 5 hops) - Self-reflective mechanisms with confidence scoring (0.0-1.0) - Case-based learning for cross-session intelligence ### 🎯 New /sc:research Command - Intelligent web research with depth control (quick/standard/deep/exhaustive) - Parallel-first execution for optimal performance - Domain filtering and time-based search options - Automatic report generation in claudedocs/ ### 🔍 Tavily MCP Integration - 7th MCP server for real-time web search - News search with time filtering - Content extraction from search results - Multi-round searching with iterative refinement - Free tier available with optional API key ### 🎨 MODE_DeepResearch - 7th behavioral mode for systematic investigation - 6-phase workflow: Understand → Plan → TodoWrite → Execute → Track → Validate - Evidence-based reasoning with citation management - Parallel operation defaults for efficiency ## Technical Changes ### Framework Updates - Updated agent count: 14 → 15 agents - Updated mode count: 6 → 7 modes - Updated MCP server count: 6 → 7 servers - Updated command count: 24 → 25 commands ### Configuration - Added RESEARCH_CONFIG.md for research settings - Added deep_research_workflows.md with examples - Standardized file naming conventions (UPPERCASE for Core) - Removed multi-source investigation features for simplification ### Integration Points - Enhanced MCP component with remote server support - Added check_research_prerequisites() in environment.py - Created verify_research_integration.sh script - Updated all documentation guides ## Requirements - TAVILY_API_KEY environment variable (free tier available) - Node.js and npm for Tavily MCP execution ## Documentation - Complete user guide integration - Workflow examples and best practices - API configuration instructions - Depth level explanations 🤖 Generated with Claude Code Co-authored-by: moshe_anconina <moshe_a@ituran.com> Co-authored-by: Claude <noreply@anthropic.com>
2025-09-21 04:54:42 +03:00
return True
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.debug(
f"Running: claude mcp add -s user {server_name} {' '.join(install_args)}"
)
feat: Add Deep Research System v4.2.0 (#380) feat: Add Deep Research System v4.2.0 - Autonomous web research capabilities ## Overview Comprehensive implementation of Deep Research framework aligned with DR Agent architecture, enabling autonomous, adaptive, and intelligent web research capabilities. ## Key Features ### 🔬 Deep Research Agent - 15th specialized agent for comprehensive research orchestration - Adaptive planning strategies: Planning-Only, Intent-Planning, Unified Intent-Planning - Multi-hop reasoning with genealogy tracking (up to 5 hops) - Self-reflective mechanisms with confidence scoring (0.0-1.0) - Case-based learning for cross-session intelligence ### 🎯 New /sc:research Command - Intelligent web research with depth control (quick/standard/deep/exhaustive) - Parallel-first execution for optimal performance - Domain filtering and time-based search options - Automatic report generation in claudedocs/ ### 🔍 Tavily MCP Integration - 7th MCP server for real-time web search - News search with time filtering - Content extraction from search results - Multi-round searching with iterative refinement - Free tier available with optional API key ### 🎨 MODE_DeepResearch - 7th behavioral mode for systematic investigation - 6-phase workflow: Understand → Plan → TodoWrite → Execute → Track → Validate - Evidence-based reasoning with citation management - Parallel operation defaults for efficiency ## Technical Changes ### Framework Updates - Updated agent count: 14 → 15 agents - Updated mode count: 6 → 7 modes - Updated MCP server count: 6 → 7 servers - Updated command count: 24 → 25 commands ### Configuration - Added RESEARCH_CONFIG.md for research settings - Added deep_research_workflows.md with examples - Standardized file naming conventions (UPPERCASE for Core) - Removed multi-source investigation features for simplification ### Integration Points - Enhanced MCP component with remote server support - Added check_research_prerequisites() in environment.py - Created verify_research_integration.sh script - Updated all documentation guides ## Requirements - TAVILY_API_KEY environment variable (free tier available) - Node.js and npm for Tavily MCP execution ## Documentation - Complete user guide integration - Workflow examples and best practices - API configuration instructions - Depth level explanations 🤖 Generated with Claude Code Co-authored-by: moshe_anconina <moshe_a@ituran.com> Co-authored-by: Claude <noreply@anthropic.com>
2025-09-21 04:54:42 +03:00
result = self._run_command_cross_platform(
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
["claude", "mcp", "add", "-s", "user", "--", server_name]
+ install_args,
feat: Add Deep Research System v4.2.0 (#380) feat: Add Deep Research System v4.2.0 - Autonomous web research capabilities ## Overview Comprehensive implementation of Deep Research framework aligned with DR Agent architecture, enabling autonomous, adaptive, and intelligent web research capabilities. ## Key Features ### 🔬 Deep Research Agent - 15th specialized agent for comprehensive research orchestration - Adaptive planning strategies: Planning-Only, Intent-Planning, Unified Intent-Planning - Multi-hop reasoning with genealogy tracking (up to 5 hops) - Self-reflective mechanisms with confidence scoring (0.0-1.0) - Case-based learning for cross-session intelligence ### 🎯 New /sc:research Command - Intelligent web research with depth control (quick/standard/deep/exhaustive) - Parallel-first execution for optimal performance - Domain filtering and time-based search options - Automatic report generation in claudedocs/ ### 🔍 Tavily MCP Integration - 7th MCP server for real-time web search - News search with time filtering - Content extraction from search results - Multi-round searching with iterative refinement - Free tier available with optional API key ### 🎨 MODE_DeepResearch - 7th behavioral mode for systematic investigation - 6-phase workflow: Understand → Plan → TodoWrite → Execute → Track → Validate - Evidence-based reasoning with citation management - Parallel operation defaults for efficiency ## Technical Changes ### Framework Updates - Updated agent count: 14 → 15 agents - Updated mode count: 6 → 7 modes - Updated MCP server count: 6 → 7 servers - Updated command count: 24 → 25 commands ### Configuration - Added RESEARCH_CONFIG.md for research settings - Added deep_research_workflows.md with examples - Standardized file naming conventions (UPPERCASE for Core) - Removed multi-source investigation features for simplification ### Integration Points - Enhanced MCP component with remote server support - Added check_research_prerequisites() in environment.py - Created verify_research_integration.sh script - Updated all documentation guides ## Requirements - TAVILY_API_KEY environment variable (free tier available) - Node.js and npm for Tavily MCP execution ## Documentation - Complete user guide integration - Workflow examples and best practices - API configuration instructions - Depth level explanations 🤖 Generated with Claude Code Co-authored-by: moshe_anconina <moshe_a@ituran.com> Co-authored-by: Claude <noreply@anthropic.com>
2025-09-21 04:54:42 +03:00
capture_output=True,
text=True,
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
timeout=120, # 2 minutes timeout for installation
feat: Add Deep Research System v4.2.0 (#380) feat: Add Deep Research System v4.2.0 - Autonomous web research capabilities ## Overview Comprehensive implementation of Deep Research framework aligned with DR Agent architecture, enabling autonomous, adaptive, and intelligent web research capabilities. ## Key Features ### 🔬 Deep Research Agent - 15th specialized agent for comprehensive research orchestration - Adaptive planning strategies: Planning-Only, Intent-Planning, Unified Intent-Planning - Multi-hop reasoning with genealogy tracking (up to 5 hops) - Self-reflective mechanisms with confidence scoring (0.0-1.0) - Case-based learning for cross-session intelligence ### 🎯 New /sc:research Command - Intelligent web research with depth control (quick/standard/deep/exhaustive) - Parallel-first execution for optimal performance - Domain filtering and time-based search options - Automatic report generation in claudedocs/ ### 🔍 Tavily MCP Integration - 7th MCP server for real-time web search - News search with time filtering - Content extraction from search results - Multi-round searching with iterative refinement - Free tier available with optional API key ### 🎨 MODE_DeepResearch - 7th behavioral mode for systematic investigation - 6-phase workflow: Understand → Plan → TodoWrite → Execute → Track → Validate - Evidence-based reasoning with citation management - Parallel operation defaults for efficiency ## Technical Changes ### Framework Updates - Updated agent count: 14 → 15 agents - Updated mode count: 6 → 7 modes - Updated MCP server count: 6 → 7 servers - Updated command count: 24 → 25 commands ### Configuration - Added RESEARCH_CONFIG.md for research settings - Added deep_research_workflows.md with examples - Standardized file naming conventions (UPPERCASE for Core) - Removed multi-source investigation features for simplification ### Integration Points - Enhanced MCP component with remote server support - Added check_research_prerequisites() in environment.py - Created verify_research_integration.sh script - Updated all documentation guides ## Requirements - TAVILY_API_KEY environment variable (free tier available) - Node.js and npm for Tavily MCP execution ## Documentation - Complete user guide integration - Workflow examples and best practices - API configuration instructions - Depth level explanations 🤖 Generated with Claude Code Co-authored-by: moshe_anconina <moshe_a@ituran.com> Co-authored-by: Claude <noreply@anthropic.com>
2025-09-21 04:54:42 +03:00
)
else:
# Use npm_package
if config.get("dry_run"):
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.info(
f"Would install MCP server (user scope): claude mcp add -s user {server_name} {command} -y {npm_package}"
)
feat: Add Deep Research System v4.2.0 (#380) feat: Add Deep Research System v4.2.0 - Autonomous web research capabilities ## Overview Comprehensive implementation of Deep Research framework aligned with DR Agent architecture, enabling autonomous, adaptive, and intelligent web research capabilities. ## Key Features ### 🔬 Deep Research Agent - 15th specialized agent for comprehensive research orchestration - Adaptive planning strategies: Planning-Only, Intent-Planning, Unified Intent-Planning - Multi-hop reasoning with genealogy tracking (up to 5 hops) - Self-reflective mechanisms with confidence scoring (0.0-1.0) - Case-based learning for cross-session intelligence ### 🎯 New /sc:research Command - Intelligent web research with depth control (quick/standard/deep/exhaustive) - Parallel-first execution for optimal performance - Domain filtering and time-based search options - Automatic report generation in claudedocs/ ### 🔍 Tavily MCP Integration - 7th MCP server for real-time web search - News search with time filtering - Content extraction from search results - Multi-round searching with iterative refinement - Free tier available with optional API key ### 🎨 MODE_DeepResearch - 7th behavioral mode for systematic investigation - 6-phase workflow: Understand → Plan → TodoWrite → Execute → Track → Validate - Evidence-based reasoning with citation management - Parallel operation defaults for efficiency ## Technical Changes ### Framework Updates - Updated agent count: 14 → 15 agents - Updated mode count: 6 → 7 modes - Updated MCP server count: 6 → 7 servers - Updated command count: 24 → 25 commands ### Configuration - Added RESEARCH_CONFIG.md for research settings - Added deep_research_workflows.md with examples - Standardized file naming conventions (UPPERCASE for Core) - Removed multi-source investigation features for simplification ### Integration Points - Enhanced MCP component with remote server support - Added check_research_prerequisites() in environment.py - Created verify_research_integration.sh script - Updated all documentation guides ## Requirements - TAVILY_API_KEY environment variable (free tier available) - Node.js and npm for Tavily MCP execution ## Documentation - Complete user guide integration - Workflow examples and best practices - API configuration instructions - Depth level explanations 🤖 Generated with Claude Code Co-authored-by: moshe_anconina <moshe_a@ituran.com> Co-authored-by: Claude <noreply@anthropic.com>
2025-09-21 04:54:42 +03:00
return True
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.debug(
f"Running: claude mcp add -s user {server_name} {command} -y {npm_package}"
)
feat: Add Deep Research System v4.2.0 (#380) feat: Add Deep Research System v4.2.0 - Autonomous web research capabilities ## Overview Comprehensive implementation of Deep Research framework aligned with DR Agent architecture, enabling autonomous, adaptive, and intelligent web research capabilities. ## Key Features ### 🔬 Deep Research Agent - 15th specialized agent for comprehensive research orchestration - Adaptive planning strategies: Planning-Only, Intent-Planning, Unified Intent-Planning - Multi-hop reasoning with genealogy tracking (up to 5 hops) - Self-reflective mechanisms with confidence scoring (0.0-1.0) - Case-based learning for cross-session intelligence ### 🎯 New /sc:research Command - Intelligent web research with depth control (quick/standard/deep/exhaustive) - Parallel-first execution for optimal performance - Domain filtering and time-based search options - Automatic report generation in claudedocs/ ### 🔍 Tavily MCP Integration - 7th MCP server for real-time web search - News search with time filtering - Content extraction from search results - Multi-round searching with iterative refinement - Free tier available with optional API key ### 🎨 MODE_DeepResearch - 7th behavioral mode for systematic investigation - 6-phase workflow: Understand → Plan → TodoWrite → Execute → Track → Validate - Evidence-based reasoning with citation management - Parallel operation defaults for efficiency ## Technical Changes ### Framework Updates - Updated agent count: 14 → 15 agents - Updated mode count: 6 → 7 modes - Updated MCP server count: 6 → 7 servers - Updated command count: 24 → 25 commands ### Configuration - Added RESEARCH_CONFIG.md for research settings - Added deep_research_workflows.md with examples - Standardized file naming conventions (UPPERCASE for Core) - Removed multi-source investigation features for simplification ### Integration Points - Enhanced MCP component with remote server support - Added check_research_prerequisites() in environment.py - Created verify_research_integration.sh script - Updated all documentation guides ## Requirements - TAVILY_API_KEY environment variable (free tier available) - Node.js and npm for Tavily MCP execution ## Documentation - Complete user guide integration - Workflow examples and best practices - API configuration instructions - Depth level explanations 🤖 Generated with Claude Code Co-authored-by: moshe_anconina <moshe_a@ituran.com> Co-authored-by: Claude <noreply@anthropic.com>
2025-09-21 04:54:42 +03:00
result = self._run_command_cross_platform(
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
[
"claude",
"mcp",
"add",
"-s",
"user",
"--",
server_name,
command,
"-y",
npm_package,
],
feat: Add Deep Research System v4.2.0 (#380) feat: Add Deep Research System v4.2.0 - Autonomous web research capabilities ## Overview Comprehensive implementation of Deep Research framework aligned with DR Agent architecture, enabling autonomous, adaptive, and intelligent web research capabilities. ## Key Features ### 🔬 Deep Research Agent - 15th specialized agent for comprehensive research orchestration - Adaptive planning strategies: Planning-Only, Intent-Planning, Unified Intent-Planning - Multi-hop reasoning with genealogy tracking (up to 5 hops) - Self-reflective mechanisms with confidence scoring (0.0-1.0) - Case-based learning for cross-session intelligence ### 🎯 New /sc:research Command - Intelligent web research with depth control (quick/standard/deep/exhaustive) - Parallel-first execution for optimal performance - Domain filtering and time-based search options - Automatic report generation in claudedocs/ ### 🔍 Tavily MCP Integration - 7th MCP server for real-time web search - News search with time filtering - Content extraction from search results - Multi-round searching with iterative refinement - Free tier available with optional API key ### 🎨 MODE_DeepResearch - 7th behavioral mode for systematic investigation - 6-phase workflow: Understand → Plan → TodoWrite → Execute → Track → Validate - Evidence-based reasoning with citation management - Parallel operation defaults for efficiency ## Technical Changes ### Framework Updates - Updated agent count: 14 → 15 agents - Updated mode count: 6 → 7 modes - Updated MCP server count: 6 → 7 servers - Updated command count: 24 → 25 commands ### Configuration - Added RESEARCH_CONFIG.md for research settings - Added deep_research_workflows.md with examples - Standardized file naming conventions (UPPERCASE for Core) - Removed multi-source investigation features for simplification ### Integration Points - Enhanced MCP component with remote server support - Added check_research_prerequisites() in environment.py - Created verify_research_integration.sh script - Updated all documentation guides ## Requirements - TAVILY_API_KEY environment variable (free tier available) - Node.js and npm for Tavily MCP execution ## Documentation - Complete user guide integration - Workflow examples and best practices - API configuration instructions - Depth level explanations 🤖 Generated with Claude Code Co-authored-by: moshe_anconina <moshe_a@ituran.com> Co-authored-by: Claude <noreply@anthropic.com>
2025-09-21 04:54:42 +03:00
capture_output=True,
text=True,
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
timeout=120, # 2 minutes timeout for installation
feat: Add Deep Research System v4.2.0 (#380) feat: Add Deep Research System v4.2.0 - Autonomous web research capabilities ## Overview Comprehensive implementation of Deep Research framework aligned with DR Agent architecture, enabling autonomous, adaptive, and intelligent web research capabilities. ## Key Features ### 🔬 Deep Research Agent - 15th specialized agent for comprehensive research orchestration - Adaptive planning strategies: Planning-Only, Intent-Planning, Unified Intent-Planning - Multi-hop reasoning with genealogy tracking (up to 5 hops) - Self-reflective mechanisms with confidence scoring (0.0-1.0) - Case-based learning for cross-session intelligence ### 🎯 New /sc:research Command - Intelligent web research with depth control (quick/standard/deep/exhaustive) - Parallel-first execution for optimal performance - Domain filtering and time-based search options - Automatic report generation in claudedocs/ ### 🔍 Tavily MCP Integration - 7th MCP server for real-time web search - News search with time filtering - Content extraction from search results - Multi-round searching with iterative refinement - Free tier available with optional API key ### 🎨 MODE_DeepResearch - 7th behavioral mode for systematic investigation - 6-phase workflow: Understand → Plan → TodoWrite → Execute → Track → Validate - Evidence-based reasoning with citation management - Parallel operation defaults for efficiency ## Technical Changes ### Framework Updates - Updated agent count: 14 → 15 agents - Updated mode count: 6 → 7 modes - Updated MCP server count: 6 → 7 servers - Updated command count: 24 → 25 commands ### Configuration - Added RESEARCH_CONFIG.md for research settings - Added deep_research_workflows.md with examples - Standardized file naming conventions (UPPERCASE for Core) - Removed multi-source investigation features for simplification ### Integration Points - Enhanced MCP component with remote server support - Added check_research_prerequisites() in environment.py - Created verify_research_integration.sh script - Updated all documentation guides ## Requirements - TAVILY_API_KEY environment variable (free tier available) - Node.js and npm for Tavily MCP execution ## Documentation - Complete user guide integration - Workflow examples and best practices - API configuration instructions - Depth level explanations 🤖 Generated with Claude Code Co-authored-by: moshe_anconina <moshe_a@ituran.com> Co-authored-by: Claude <noreply@anthropic.com>
2025-09-21 04:54:42 +03:00
)
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
if result.returncode == 0:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.success(
f"Successfully installed MCP server (user scope): {server_name}"
)
return True
else:
error_msg = result.stderr.strip() if result.stderr else "Unknown error"
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.error(
f"Failed to install MCP server {server_name}: {error_msg}"
)
return False
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
except subprocess.TimeoutExpired:
self.logger.error(f"Timeout installing MCP server {server_name}")
return False
except Exception as e:
self.logger.error(f"Error installing MCP server {server_name}: {e}")
return False
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
def _install_airis_gateway(
self, server_info: Dict[str, Any], config: Dict[str, Any]
) -> bool:
"""Install AIRIS MCP Gateway via official repository automation"""
server_name = server_info["name"]
if self._check_mcp_server_installed(server_name):
self.logger.info(f"MCP server {server_name} already installed")
return True
if config.get("dry_run"):
self.logger.info(
"Would install AIRIS MCP Gateway by cloning repository and running make install-claude"
)
return True
self.logger.info(
f"Installing {server_name} from {AIRIS_MCP_GITHUB_REPO} into {AIRIS_MCP_GATEWAY_DIR}"
)
# Step 1: Clone repository if necessary
if not AIRIS_MCP_GATEWAY_DIR.exists():
self.logger.info("Cloning AIRIS MCP Gateway repository...")
try:
clone_result = self._run_command_cross_platform(
AIRIS_MCP_CLONE_COMMAND,
capture_output=True,
text=True,
timeout=600,
)
except subprocess.TimeoutExpired:
self.logger.error(
f"Timeout while cloning {AIRIS_MCP_GITHUB_REPO}"
)
return False
except Exception as exc:
self.logger.error(
f"Error cloning AIRIS MCP Gateway repository: {exc}"
)
return False
if clone_result.returncode != 0:
stderr = (
clone_result.stderr.strip()
if clone_result.stderr
else "Unknown error"
)
self.logger.error(
f"Failed to clone AIRIS MCP Gateway repository: {stderr}"
)
if clone_result.stdout:
self.logger.debug(clone_result.stdout)
return False
else:
self.logger.info("Updating existing AIRIS MCP Gateway checkout...")
try:
update_result = self._run_command_cross_platform(
AIRIS_MCP_UPDATE_COMMAND,
capture_output=True,
text=True,
timeout=180,
cwd=str(AIRIS_MCP_GATEWAY_DIR),
)
except subprocess.TimeoutExpired:
self.logger.warning(
"Timeout while updating AIRIS MCP Gateway repository (continuing with current version)"
)
update_result = None
except Exception as exc:
self.logger.warning(
f"Error updating AIRIS MCP Gateway repository: {exc}"
)
update_result = None
if update_result and update_result.returncode != 0:
stderr = (
update_result.stderr.strip()
if update_result.stderr
else "Unknown error"
)
self.logger.warning(
f"Failed to update AIRIS MCP Gateway repository: {stderr}"
)
if update_result.stdout:
self.logger.debug(update_result.stdout)
# Step 2: Run make install-claude to provision MCP configuration
try:
install_result = self._run_command_cross_platform(
AIRIS_MCP_INSTALL_COMMAND,
capture_output=True,
text=True,
timeout=900,
cwd=str(AIRIS_MCP_GATEWAY_DIR),
)
except subprocess.TimeoutExpired:
self.logger.error(
f"Timeout while running make install-claude for {server_name}"
)
return False
except Exception as exc:
self.logger.error(
f"Error running make install-claude for {server_name}: {exc}"
)
return False
if install_result.returncode != 0:
stderr = (
install_result.stderr.strip()
if install_result.stderr
else "Unknown error"
)
self.logger.error(
f"Failed to configure {server_name} via make install-claude: {stderr}"
)
if install_result.stdout:
self.logger.debug(install_result.stdout)
return False
if install_result.stdout:
self.logger.debug(install_result.stdout)
# Re-check using Claude CLI to confirm registration
if self._check_mcp_server_installed(server_name):
self.logger.success(f"Successfully installed MCP server: {server_name}")
return True
# Fallback: inspect ~/.claude/mcp.json symlink to ensure installation completed
try:
if AIRIS_MCP_CONFIG_PATH.is_symlink():
target_path = AIRIS_MCP_CONFIG_PATH.resolve()
if (
target_path.name == AIRIS_MCP_EXPECTED_CONFIG_TARGET
and AIRIS_MCP_GATEWAY_DIR in target_path.parents
):
self.logger.success(
f"Linked Claude configuration to AIRIS MCP Gateway ({target_path})"
)
self.logger.info(
"Please restart Claude Code to refresh MCP server list."
)
return True
elif AIRIS_MCP_CONFIG_PATH.exists():
self.logger.warning(
"Claude MCP configuration exists but is not linked to AIRIS Gateway."
)
except OSError as exc:
self.logger.warning(f"Could not inspect Claude MCP configuration: {exc}")
self.logger.error(
"AIRIS MCP Gateway installer finished, but the server was not detected. "
"Verify Docker containers are running with `airis-gateway status`."
)
return False
def _uninstall_mcp_server(self, server_name: str) -> bool:
"""Uninstall a single MCP server"""
try:
self.logger.info(f"Uninstalling MCP server: {server_name}")
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
# Check if installed
if not self._check_mcp_server_installed(server_name):
self.logger.info(f"MCP server {server_name} not installed")
return True
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.debug(
f"Running: claude mcp remove {server_name} (auto-detect scope)"
)
result = self._run_command_cross_platform(
["claude", "mcp", "remove", server_name],
capture_output=True,
text=True,
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
timeout=60,
)
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
if result.returncode == 0:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.success(
f"Successfully uninstalled MCP server: {server_name}"
)
return True
else:
error_msg = result.stderr.strip() if result.stderr else "Unknown error"
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.error(
f"Failed to uninstall MCP server {server_name}: {error_msg}"
)
return False
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
except subprocess.TimeoutExpired:
self.logger.error(f"Timeout uninstalling MCP server {server_name}")
return False
except Exception as e:
self.logger.error(f"Error uninstalling MCP server {server_name}: {e}")
return False
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
2025-08-14 08:56:04 +05:30
def _install(self, config: Dict[str, Any]) -> bool:
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
"""Install MCP component with auto-detection of existing servers"""
refactor: PM Agent complete independence from external MCP servers (#439) * refactor: PM Agent complete independence from external MCP servers ## Summary Implement graceful degradation to ensure PM Agent operates fully without any MCP server dependencies. MCP servers now serve as optional enhancements rather than required components. ## Changes ### Responsibility Separation (NEW) - **PM Agent**: Development workflow orchestration (PDCA cycle, task management) - **mindbase**: Memory management (long-term, freshness, error learning) - **Built-in memory**: Session-internal context (volatile) ### 3-Layer Memory Architecture with Fallbacks 1. **Built-in Memory** [OPTIONAL]: Session context via MCP memory server 2. **mindbase** [OPTIONAL]: Long-term semantic search via airis-mcp-gateway 3. **Local Files** [ALWAYS]: Core functionality in docs/memory/ ### Graceful Degradation Implementation - All MCP operations marked with [ALWAYS] or [OPTIONAL] - Explicit IF/ELSE fallback logic for every MCP call - Dual storage: Always write to local files + optionally to mindbase - Smart lookup: Semantic search (if available) → Text search (always works) ### Key Fallback Strategies **Session Start**: - mindbase available: search_conversations() for semantic context - mindbase unavailable: Grep docs/memory/*.jsonl for text-based lookup **Error Detection**: - mindbase available: Semantic search for similar past errors - mindbase unavailable: Grep docs/mistakes/ + solutions_learned.jsonl **Knowledge Capture**: - Always: echo >> docs/memory/patterns_learned.jsonl (persistent) - Optional: mindbase.store() for semantic search enhancement ## Benefits - ✅ Zero external dependencies (100% functionality without MCP) - ✅ Enhanced capabilities when MCPs available (semantic search, freshness) - ✅ No functionality loss, only reduced search intelligence - ✅ Transparent degradation (no error messages, automatic fallback) ## Related Research - Serena MCP investigation: Exposes tools (not resources), memory = markdown files - mindbase superiority: PostgreSQL + pgvector > Serena memory features - Best practices alignment: /Users/kazuki/github/airis-mcp-gateway/docs/mcp-best-practices.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: add PR template and pre-commit config - Add structured PR template with Git workflow checklist - Add pre-commit hooks for secret detection and Conventional Commits - Enforce code quality gates (YAML/JSON/Markdown lint, shellcheck) NOTE: Execute pre-commit inside Docker container to avoid host pollution: docker compose exec workspace uv tool install pre-commit docker compose exec workspace pre-commit run --all-files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: update PM Agent context with token efficiency architecture - Add Layer 0 Bootstrap (150 tokens, 95% reduction) - Document Intent Classification System (5 complexity levels) - Add Progressive Loading strategy (5-layer) - Document mindbase integration incentive (38% savings) - Update with 2025-10-17 redesign details * refactor: PM Agent command with progressive loading - Replace auto-loading with User Request First philosophy - Add 5-layer progressive context loading - Implement intent classification system - Add workflow metrics collection (.jsonl) - Document graceful degradation strategy * fix: installer improvements Update installer logic for better reliability * docs: add comprehensive development documentation - Add architecture overview - Add PM Agent improvements analysis - Add parallel execution architecture - Add CLI install improvements - Add code style guide - Add project overview - Add install process analysis * docs: add research documentation Add LLM agent token efficiency research and analysis * docs: add suggested commands reference * docs: add session logs and testing documentation - Add session analysis logs - Add testing documentation * feat: migrate CLI to typer + rich for modern UX ## What Changed ### New CLI Architecture (typer + rich) - Created `superclaude/cli/` module with modern typer-based CLI - Replaced custom UI utilities with rich native features - Added type-safe command structure with automatic validation ### Commands Implemented - **install**: Interactive installation with rich UI (progress, panels) - **doctor**: System diagnostics with rich table output - **config**: API key management with format validation ### Technical Improvements - Dependencies: Added typer>=0.9.0, rich>=13.0.0, click>=8.0.0 - Entry Point: Updated pyproject.toml to use `superclaude.cli.app:cli_main` - Tests: Added comprehensive smoke tests (11 passed) ### User Experience Enhancements - Rich formatted help messages with panels and tables - Automatic input validation with retry loops - Clear error messages with actionable suggestions - Non-interactive mode support for CI/CD ## Testing ```bash uv run superclaude --help # ✓ Works uv run superclaude doctor # ✓ Rich table output uv run superclaude config show # ✓ API key management pytest tests/test_cli_smoke.py # ✓ 11 passed, 1 skipped ``` ## Migration Path - ✅ P0: Foundation complete (typer + rich + smoke tests) - 🔜 P1: Pydantic validation models (next sprint) - 🔜 P2: Enhanced error messages (next sprint) - 🔜 P3: API key retry loops (next sprint) ## Performance Impact - **Code Reduction**: Prepared for -300 lines (custom UI → rich) - **Type Safety**: Automatic validation from type hints - **Maintainability**: Framework primitives vs custom code 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate documentation directories Merged claudedocs/ into docs/research/ for consistent documentation structure. Changes: - Moved all claudedocs/*.md files to docs/research/ - Updated all path references in documentation (EN/KR) - Updated RULES.md and research.md command templates - Removed claudedocs/ directory - Removed ClaudeDocs/ from .gitignore Benefits: - Single source of truth for all research reports - PEP8-compliant lowercase directory naming - Clearer documentation organization - Prevents future claudedocs/ directory creation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: reduce /sc:pm command output from 1652 to 15 lines - Remove 1637 lines of documentation from command file - Keep only minimal bootstrap message - 99% token reduction on command execution - Detailed specs remain in superclaude/agents/pm-agent.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: split PM Agent into execution workflows and guide - Reduce pm-agent.md from 735 to 429 lines (42% reduction) - Move philosophy/examples to docs/agents/pm-agent-guide.md - Execution workflows (PDCA, file ops) stay in pm-agent.md - Guide (examples, quality standards) read once when needed Token savings: - Agent loading: ~6K → ~3.5K tokens (42% reduction) - Total with pm.md: 71% overall reduction 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate PM Agent optimization and pending changes PM Agent optimization (already committed separately): - superclaude/commands/pm.md: 1652→14 lines - superclaude/agents/pm-agent.md: 735→429 lines - docs/agents/pm-agent-guide.md: new guide file Other pending changes: - setup: framework_docs, mcp, logger, remove ui.py - superclaude: __main__, cli/app, cli/commands/install - tests: test_ui updates - scripts: workflow metrics analysis tools - docs/memory: session state updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: simplify MCP installer to unified gateway with legacy mode ## Changes ### MCP Component (setup/components/mcp.py) - Simplified to single airis-mcp-gateway by default - Added legacy mode for individual official servers (sequential-thinking, context7, magic, playwright) - Dynamic prerequisites based on mode: - Default: uv + claude CLI only - Legacy: node (18+) + npm + claude CLI - Removed redundant server definitions ### CLI Integration - Added --legacy flag to setup/cli/commands/install.py - Added --legacy flag to superclaude/cli/commands/install.py - Config passes legacy_mode to component installer ## Benefits - ✅ Simpler: 1 gateway vs 9+ individual servers - ✅ Lighter: No Node.js/npm required (default mode) - ✅ Unified: All tools in one gateway (sequential-thinking, context7, magic, playwright, serena, morphllm, tavily, chrome-devtools, git, puppeteer) - ✅ Flexible: --legacy flag for official servers if needed ## Usage ```bash superclaude install # Default: airis-mcp-gateway (推奨) superclaude install --legacy # Legacy: individual official servers ``` 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename CoreComponent to FrameworkDocsComponent and add PM token tracking ## Changes ### Component Renaming (setup/components/) - Renamed CoreComponent → FrameworkDocsComponent for clarity - Updated all imports in __init__.py, agents.py, commands.py, mcp_docs.py, modes.py - Better reflects the actual purpose (framework documentation files) ### PM Agent Enhancement (superclaude/commands/pm.md) - Added token usage tracking instructions - PM Agent now reports: 1. Current token usage from system warnings 2. Percentage used (e.g., "27% used" for 54K/200K) 3. Status zone: 🟢 <75% | 🟡 75-85% | 🔴 >85% - Helps prevent token exhaustion during long sessions ### UI Utilities (setup/utils/ui.py) - Added new UI utility module for installer - Provides consistent user interface components ## Benefits - ✅ Clearer component naming (FrameworkDocs vs Core) - ✅ PM Agent token awareness for efficiency - ✅ Better visual feedback with status zones 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor(pm-agent): minimize output verbosity (471→284 lines, 40% reduction) **Problem**: PM Agent generated excessive output with redundant explanations - "System Status Report" with decorative formatting - Repeated "Common Tasks" lists user already knows - Verbose session start/end protocols - Duplicate file operations documentation **Solution**: Compress without losing functionality - Session Start: Reduced to symbol-only status (🟢 branch | nM nD | token%) - Session End: Compressed to essential actions only - File Operations: Consolidated from 2 sections to 1 line reference - Self-Improvement: 5 phases → 1 unified workflow - Output Rules: Explicit constraints to prevent Claude over-explanation **Quality Preservation**: - ✅ All core functions retained (PDCA, memory, patterns, mistakes) - ✅ PARALLEL Read/Write preserved (performance critical) - ✅ Workflow unchanged (session lifecycle intact) - ✅ Added output constraints (prevents verbose generation) **Reduction Method**: - Deleted: Explanatory text, examples, redundant sections - Retained: Action definitions, file paths, core workflows - Added: Explicit output constraints to enforce minimalism **Token Impact**: 40% reduction in agent documentation size **Before**: Verbose multi-section report with task lists **After**: Single line status: 🟢 integration | 15M 17D | 36% 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate MCP integration to unified gateway **Changes**: - Remove individual MCP server docs (superclaude/mcp/*.md) - Remove MCP server configs (superclaude/mcp/configs/*.json) - Delete MCP docs component (setup/components/mcp_docs.py) - Simplify installer (setup/core/installer.py) - Update components for unified gateway approach **Rationale**: - Unified gateway (airis-mcp-gateway) provides all MCP servers - Individual docs/configs no longer needed (managed centrally) - Reduces maintenance burden and file count - Simplifies installation process **Files Removed**: 17 MCP files (docs + configs) **Installer Changes**: Removed legacy MCP installation logic 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: update version and component metadata - Bump version (pyproject.toml, setup/__init__.py) - Update CLAUDE.md import service references - Reflect component structure changes 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-17 09:13:06 +09:00
# Check for legacy mode flag
use_legacy = config.get("legacy_mode", False) or config.get("official_servers", False)
if use_legacy:
self.logger.info("Installing individual official MCP servers (legacy mode)...")
self.mcp_servers = self.mcp_servers_legacy
else:
self.logger.info("Installing unified MCP gateway (airis-mcp-gateway)...")
self.mcp_servers = self.mcp_servers_default
2025-08-14 08:56:04 +05:30
# Validate prerequisites
success, errors = self.validate_prerequisites()
if not success:
for error in errors:
self.logger.error(error)
return False
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
# Auto-detect existing servers
self.logger.info("Auto-detecting existing MCP servers...")
existing_from_config = self._detect_existing_mcp_servers_from_config()
existing_from_cli = self._detect_existing_mcp_servers_from_cli()
existing_servers = list(set(existing_from_config + existing_from_cli))
Fixed Some Bugs (#355) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> --------- Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>
2025-09-13 17:28:52 +05:30
# Get selected servers from config
selected_servers = config.get("selected_mcp_servers", [])
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
# Get previously installed servers from metadata
previous_servers = self.settings_manager.get_metadata_setting("mcp.servers", [])
# Merge all server lists
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
all_servers = self._merge_server_lists(
existing_servers, selected_servers, previous_servers
)
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
if not all_servers:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.info(
"No MCP servers detected or selected. Skipping MCP installation."
)
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
# Still run post-install to update metadata
Fixed Some Bugs (#355) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> --------- Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>
2025-09-13 17:28:52 +05:30
return self._post_install()
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
self.logger.info(f"Managing MCP servers: {', '.join(all_servers)}")
Fixed Some Bugs (#355) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> --------- Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>
2025-09-13 17:28:52 +05:30
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
# Install/verify each server
installed_count = 0
failed_servers = []
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
verified_servers = []
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
for server_name in all_servers:
Fixed Some Bugs (#355) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> --------- Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>
2025-09-13 17:28:52 +05:30
if server_name in self.mcp_servers:
server_info = self.mcp_servers[server_name]
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
# Check if already installed and working
if self._check_mcp_server_installed(server_name):
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.info(
f"MCP server {server_name} already installed and working"
)
Fixed Some Bugs (#355) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> --------- Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>
2025-09-13 17:28:52 +05:30
installed_count += 1
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
verified_servers.append(server_name)
Fixed Some Bugs (#355) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> --------- Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>
2025-09-13 17:28:52 +05:30
else:
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
# Try to install
if self._install_mcp_server(server_info, config):
installed_count += 1
verified_servers.append(server_name)
else:
failed_servers.append(server_name)
# Check if this is a required server
if server_info.get("required", False):
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.error(
f"Required MCP server {server_name} failed to install"
)
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
return False
else:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.warning(
f"Unknown MCP server '{server_name}' cannot be managed by SuperClaude"
)
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
# Update the list of successfully managed servers
self.installed_servers_in_session = verified_servers
# Verify installation
if not config.get("dry_run", False):
self.logger.info("Verifying MCP server installation...")
try:
result = self._run_command_cross_platform(
["claude", "mcp", "list"],
capture_output=True,
text=True,
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
timeout=60,
)
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
if result.returncode == 0:
self.logger.debug("MCP servers list:")
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
for line in result.stdout.strip().split("\n"):
if line.strip():
self.logger.debug(f" {line.strip()}")
else:
self.logger.warning("Could not verify MCP server installation")
Fixes and improvement (#378) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Add Docker support and framework enhancements - Add serena-docker.json MCP configuration - Update MCP configs and installer components - Enhance CLI commands with new functionality - Add symbols utility for framework operations - Improve UI and logging components 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Bump version from 4.1.1 to 4.1.2 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Bump version from 4.1.2 to 4.1.3 - Update version across all package files - Update documentation and README files - Update Python module version strings - Update feature configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix home directory detection for immutable distros - Add get_home_directory() function to handle /var/home/$USER paths - Support Fedora Silverblue, Universal Blue, and other immutable distros - Replace all Path.home() calls throughout the setup system - Add fallback methods for edge cases and compatibility - Create test script for immutable distro validation Fixes: - Incorrect home path detection on immutable Linux distributions - Installation failures on Fedora Silverblue/Universal Blue - Issues with Claude Code configuration paths Technical changes: - New get_home_directory() in utils/environment.py - Updated all CLI commands, validators, and core components - Maintains backward compatibility with standard systems - Robust fallback chain for edge cases 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix circular import and complete immutable distro support - Move get_home_directory() to separate paths.py module - Resolve circular import between environment.py and logger.py - Update all import statements across the setup system - Verify functionality with comprehensive testing Technical changes: - Created setup/utils/paths.py for path utilities - Updated imports in all affected modules - Maintains full backward compatibility - Fixes installation on immutable distros Testing completed: - ✅ Basic home directory detection works - ✅ Installation system integration works - ✅ Environment utilities integration works - ✅ Immutable distro logic validated 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com> * Fix mcp_docs installation bugs - Fix mcp_docs component incorrectly marking as installed when no MCP servers selected - Add MCP server selection prompt when mcp_docs component is explicitly requested - Return False instead of calling _post_install() when no servers selected or files found - Add user-friendly warning when mcp_docs requested without server selection - Remove mcp_docs from installation when no servers are available 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP server name mapping for documentation files - Add mapping for sequential-thinking -> MCP_Sequential.md - Add mapping for morphllm-fast-apply -> MCP_Morphllm.md - Ensures mcp_docs installation works with all MCP server naming conventions 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Enable mcp_docs component reinstallation - Add is_reinstallable() method returning True to allow repeat installations - Fixes issue where mcp_docs was skipped on subsequent installation attempts - Enables users to change MCP server selections and update documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix repeat installation issues for mcp_docs - Ensure mcp component is auto-added when mcp_docs is selected with servers - Fix component_files tracking to only include successfully copied files - Ensures CLAUDE.md gets properly updated with MCP documentation imports - Fixes issue where MCP servers weren't installed on repeat attempts 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP component metadata tracking and debug logging - Fix servers_count to track actually installed servers instead of total available - Add installed_servers list to metadata for better tracking - Add debug logging to trace component auto-addition - Ensures MCP component appears properly in metadata when servers are installed 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix pyproject.toml license format and add missing classifier - Fix license format from string to {text = "MIT"} format - Add missing "License :: OSI Approved :: MIT License" classifier - Fix indentation consistency in classifiers section - Resolves setup.py installation errors and PEP 621 compliance 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Fix MCP incremental installation and auto-detection system PROBLEM FIXED: - MCP component only registered servers selected during current session - mcp_docs component only installed docs for newly selected servers - Users had to reinstall everything when adding new MCP servers - Installation failed if no servers selected but servers existed SOLUTION IMPLEMENTED: - Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json) - Add CLI detection via 'claude mcp list' output parsing - Add smart server merging (existing + selected + previously installed) - Add server name normalization for common variations - Fix CLI logic to allow mcp_docs installation without server selection - Add graceful error handling for corrupted configs KEY FEATURES: ✅ Auto-detects existing MCP servers from multiple config locations ✅ Supports incremental installation (add new servers without breaking existing) ✅ Works with or without --install-dir argument ✅ Handles server name variations (sequential vs sequential-thinking, etc.) ✅ Maintains metadata persistence across installation sessions ✅ Graceful fallback when config files are corrupted ✅ Compatible with both interactive and non-interactive modes TESTED SCENARIOS: - Fresh installation with no MCP servers ✅ - Auto-detection with existing servers ✅ - Incremental server additions ✅ - Mixed mode (new + existing servers) ✅ - Error handling with corrupted configs ✅ - Default vs custom installation directories ✅ - Interactive vs command-line modes ✅ Files changed: - setup/cli/commands/install.py: Allow mcp_docs auto-detection mode - setup/components/mcp.py: Add comprehensive auto-detection logic - setup/components/mcp_docs.py: Add auto-detection for documentation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Integrate SuperClaude framework flags into help command ENHANCEMENT: - Add comprehensive flag documentation to /sc:help command - Include all 25 SuperClaude framework flags with descriptions - Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output) - Add practical usage examples showing flag combinations - Include flag priority rules and precedence hierarchy NEW SECTIONS ADDED: ✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient ✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp ✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink ✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode ✅ Output Optimization Flags (3 flags): --uc, --scope, --focus ✅ Flag Priority Rules: Clear hierarchy and precedence guidelines ✅ Usage Examples: 4 practical examples showing real-world flag combinations IMPACT: - Users can now discover all SuperClaude capabilities from /sc:help - Single source of truth for commands AND flags - Improved discoverability of advanced features - Clear guidance on flag usage and combinations - Help content nearly doubled (68 → 148 lines) with valuable reference information Files changed: - SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Remove non-existent commands from modes.md documentation PROBLEM FIXED: - Documentation contained references to fake/non-existent commands - Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI - Confusing users who try to use these commands and get errors - Inconsistency between documentation and actual SuperClaude command availability COMMANDS REMOVED/REPLACED: ❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command) ❌ /sc:develop → ✅ /sc:implement (real command) ❌ /sc:modernize → ✅ /sc:improve (real command) AFFECTED FILES: - Docs/User-Guide/modes.md: Fixed all non-existent command references - Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues - Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues VERIFICATION: ✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/ ✅ No more references to fake commands in any language version ✅ Examples now use only real, working SuperClaude commands ✅ User experience improved - no more confusion from non-working commands REAL COMMANDS REFERENCED: - /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement - /sc:improve, /sc:reflect, /sc:troubleshoot - All verified to exist in CLI implementation 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * Version bump to 4.1.4 CHANGELOG: ✅ Added comprehensive flag documentation to /sc:help command ✅ Fixed MCP incremental installation and auto-detection system ✅ Cleaned up documentation by removing non-existent commands ✅ Enhanced user experience with complete capability reference VERSION UPDATES: - Updated VERSION file: 4.1.3 → 4.1.4 - Updated pyproject.toml: 4.1.3 → 4.1.4 - Updated package.json: 4.1.3 → 4.1.4 - Updated all Python __init__.py fallback versions - Updated all documentation references across all languages - Updated setup/data/features.json component versions - Updated CHANGELOG.md with comprehensive 4.1.4 release notes SCOPE OF CHANGES: 📦 Core files: VERSION, pyproject.toml, package.json, __init__.py files 📚 Documentation: All .md files across English, Japanese, Chinese 🔧 Setup files: features.json, base.py version references 📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING VERIFICATION: ✅ No remaining 4.1.3 references found ✅ 29 files now properly reference 4.1.4 ✅ All language versions consistently updated ✅ Package metadata properly versioned for distribution 🤖 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 10:38:42 +02:00
except Exception as e:
self.logger.warning(f"Could not verify MCP installation: {e}")
if failed_servers:
self.logger.warning(f"Some MCP servers failed to install: {failed_servers}")
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.success(
f"MCP component partially managed ({installed_count} servers)"
)
2025-08-14 08:56:04 +05:30
else:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.success(
f"MCP component successfully managing ({installed_count} servers)"
)
return self._post_install()
2025-08-14 08:56:04 +05:30
def _post_install(self) -> bool:
"""Post-installation tasks"""
# Update metadata
2025-08-14 08:56:04 +05:30
try:
metadata_mods = self.get_metadata_modifications()
2025-08-14 08:56:04 +05:30
self.settings_manager.update_metadata(metadata_mods)
# Add component registration to metadata
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.settings_manager.add_component_registration(
"mcp",
{
"version": __version__,
"category": "integration",
"servers_count": len(self.installed_servers_in_session),
"installed_servers": self.installed_servers_in_session,
},
)
2025-08-14 08:56:04 +05:30
self.logger.info("Updated metadata with MCP component registration")
return True
2025-08-14 08:56:04 +05:30
except Exception as e:
self.logger.error(f"Failed to update metadata: {e}")
return False
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
2025-08-14 08:56:04 +05:30
def uninstall(self) -> bool:
"""Uninstall MCP component"""
2025-08-14 08:56:04 +05:30
try:
self.logger.info("Uninstalling SuperClaude MCP servers...")
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
# Uninstall each MCP server
uninstalled_count = 0
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
for server_name in self.mcp_servers.keys():
if self._uninstall_mcp_server(server_name):
uninstalled_count += 1
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
# Update metadata to remove MCP component
2025-08-14 08:56:04 +05:30
try:
if self.settings_manager.is_component_installed("mcp"):
self.settings_manager.remove_component_registration("mcp")
# Also remove MCP configuration from metadata
metadata = self.settings_manager.load_metadata()
if "mcp" in metadata:
del metadata["mcp"]
self.settings_manager.save_metadata(metadata)
self.logger.info("Removed MCP component from metadata")
2025-08-14 08:56:04 +05:30
except Exception as e:
self.logger.warning(f"Could not update metadata: {e}")
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.success(
f"MCP component uninstalled ({uninstalled_count} servers removed)"
)
return True
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
except Exception as e:
self.logger.exception(f"Unexpected error during MCP uninstallation: {e}")
2025-08-14 08:56:04 +05:30
return False
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
def get_dependencies(self) -> List[str]:
"""Get dependencies"""
return ["framework_docs"]
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
def update(self, config: Dict[str, Any]) -> bool:
"""Update MCP component"""
try:
self.logger.info("Updating SuperClaude MCP servers...")
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
# Check current version
current_version = self.settings_manager.get_component_version("mcp")
target_version = self.get_metadata()["version"]
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
if current_version == target_version:
self.logger.info(f"MCP component already at version {target_version}")
return True
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.info(
f"Updating MCP component from {current_version} to {target_version}"
)
# For MCP servers, update means reinstall to get latest versions
updated_count = 0
failed_servers = []
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
for server_name, server_info in self.mcp_servers.items():
try:
# Uninstall old version
if self._check_mcp_server_installed(server_name):
self._uninstall_mcp_server(server_name)
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
# Install new version
if self._install_mcp_server(server_info, config):
updated_count += 1
else:
failed_servers.append(server_name)
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
except Exception as e:
self.logger.error(f"Error updating MCP server {server_name}: {e}")
failed_servers.append(server_name)
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
# Update metadata
try:
# Update component version in metadata
metadata = self.settings_manager.load_metadata()
if "components" in metadata and "mcp" in metadata["components"]:
metadata["components"]["mcp"]["version"] = target_version
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
metadata["components"]["mcp"]["servers_count"] = len(
self.mcp_servers
)
if "mcp" in metadata:
metadata["mcp"]["servers"] = list(self.mcp_servers.keys())
self.settings_manager.save_metadata(metadata)
except Exception as e:
self.logger.warning(f"Could not update metadata: {e}")
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
if failed_servers:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.warning(
f"Some MCP servers failed to update: {failed_servers}"
)
return False
else:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
self.logger.success(
f"MCP component updated to version {target_version}"
)
return True
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
except Exception as e:
self.logger.exception(f"Unexpected error during MCP update: {e}")
return False
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
def validate_installation(self) -> Tuple[bool, List[str]]:
"""Validate MCP component installation"""
errors = []
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
# Check metadata registration
if not self.settings_manager.is_component_installed("mcp"):
errors.append("MCP component not registered in metadata")
return False, errors
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
# Check version matches
installed_version = self.settings_manager.get_component_version("mcp")
expected_version = self.get_metadata()["version"]
if installed_version != expected_version:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
errors.append(
f"Version mismatch: installed {installed_version}, expected {expected_version}"
)
Fixed Some Bugs (#355) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> --------- Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>
2025-09-13 17:28:52 +05:30
# Check if Claude CLI is available and validate installed servers
try:
result = self._run_command_cross_platform(
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
["claude", "mcp", "list"], capture_output=True, text=True, timeout=60
)
Fixed Some Bugs (#355) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> --------- Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>
2025-09-13 17:28:52 +05:30
if result.returncode != 0:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
errors.append(
"Could not communicate with Claude CLI for MCP server verification"
)
else:
Fixed Some Bugs (#355) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> --------- Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>
2025-09-13 17:28:52 +05:30
claude_mcp_output = result.stdout.lower()
# Get the list of servers that should be installed from metadata
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
installed_servers = self.settings_manager.get_metadata_setting(
"mcp.servers", []
)
Fixed Some Bugs (#355) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> --------- Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>
2025-09-13 17:28:52 +05:30
for server_name in installed_servers:
if server_name.lower() not in claude_mcp_output:
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
errors.append(
f"Installed MCP server '{server_name}' not found in 'claude mcp list' output."
)
Fixed Some Bugs (#355) * Fix: Install only selected MCP servers and ensure valid empty backups This commit addresses two separate issues: 1. **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix. 2. **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Correct installer validation for MCP and MCP Docs components This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers. The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers. The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied. New tests have been added for both components to verify the corrected logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * Fix: Allow re-installation of components and correct validation logic This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation. The key changes are: 1. A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed. 2. The installer logic has been updated to respect this new method. 3. The `MCPComponent` now correctly stores only the installed servers in the metadata. 4. The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures. New tests have been added to verify all aspects of the new logic. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Display authors in UI header and update author info This commit implements the user's request to display author names and emails in the UI header of the installer. The key changes are: 1. The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails. 2. The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it. 3. A new test has been added to `tests/test_ui.py` to verify the new UI output. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Version bump to 4.1.0 and various fixes This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks. Key changes in this release: - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code. - **Installer Fixes**: - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added. - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures. - A bug in the backup creation process that created invalid empty archives has been fixed. - **UI Enhancements**: - Author names and emails are now displayed in the installer UI header. - **Metadata Updates**: - Mithun Gowda B has been added as an author. - **New Tests**: - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Resolve dependencies for partial installs and other fixes This commit addresses several issues, the main one being a dependency resolution failure during partial installations. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers. - **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures. - **UI and Metadata**: Author information has been added to the UI header and source files. - **Version Bump**: The project version has been updated to 4.1.0. - **Tests**: New tests have been added to cover all the above changes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * fix: Installer fixes and version bump to 4.1.0 This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0. Key changes: - **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error. - **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers. - **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers. - **UI & Metadata**: Author information has been added to the UI and source files. - **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files. - **Tests**: New tests have been added to cover all the bug fixes. Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> * feat: Add --authors flag and multiple installer fixes This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic. Key changes: - **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors. - **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies. - **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs. - **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection. - **Validation Logic**: Corrected the post-installation validation to prevent spurious errors. - **Version Bump**: The project version has been updated to 4.1.0. - **Metadata**: Author and GitHub information has been added to the source files. - **UI**: The installer header now displays author information. - **Tests**: Added new tests for all new features and bug fixes. Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com> --------- Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com> Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>
2025-09-13 17:28:52 +05:30
except Exception as e:
errors.append(f"Could not verify MCP server installation: {e}")
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
return len(errors) == 0, errors
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
def _get_source_dir(self):
"""Get source directory for framework files"""
return None
2025-08-14 08:56:04 +05:30
def get_size_estimate(self) -> int:
"""Get estimated installation size"""
# MCP servers are installed via npm, estimate based on typical sizes
base_size = 50 * 1024 * 1024 # ~50MB for all servers combined
return base_size
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
def get_installation_summary(self) -> Dict[str, Any]:
"""Get installation summary"""
return {
"component": self.get_metadata()["name"],
"version": self.get_metadata()["version"],
refactor: PM Agent complete independence from external MCP servers (#439) * refactor: PM Agent complete independence from external MCP servers ## Summary Implement graceful degradation to ensure PM Agent operates fully without any MCP server dependencies. MCP servers now serve as optional enhancements rather than required components. ## Changes ### Responsibility Separation (NEW) - **PM Agent**: Development workflow orchestration (PDCA cycle, task management) - **mindbase**: Memory management (long-term, freshness, error learning) - **Built-in memory**: Session-internal context (volatile) ### 3-Layer Memory Architecture with Fallbacks 1. **Built-in Memory** [OPTIONAL]: Session context via MCP memory server 2. **mindbase** [OPTIONAL]: Long-term semantic search via airis-mcp-gateway 3. **Local Files** [ALWAYS]: Core functionality in docs/memory/ ### Graceful Degradation Implementation - All MCP operations marked with [ALWAYS] or [OPTIONAL] - Explicit IF/ELSE fallback logic for every MCP call - Dual storage: Always write to local files + optionally to mindbase - Smart lookup: Semantic search (if available) → Text search (always works) ### Key Fallback Strategies **Session Start**: - mindbase available: search_conversations() for semantic context - mindbase unavailable: Grep docs/memory/*.jsonl for text-based lookup **Error Detection**: - mindbase available: Semantic search for similar past errors - mindbase unavailable: Grep docs/mistakes/ + solutions_learned.jsonl **Knowledge Capture**: - Always: echo >> docs/memory/patterns_learned.jsonl (persistent) - Optional: mindbase.store() for semantic search enhancement ## Benefits - ✅ Zero external dependencies (100% functionality without MCP) - ✅ Enhanced capabilities when MCPs available (semantic search, freshness) - ✅ No functionality loss, only reduced search intelligence - ✅ Transparent degradation (no error messages, automatic fallback) ## Related Research - Serena MCP investigation: Exposes tools (not resources), memory = markdown files - mindbase superiority: PostgreSQL + pgvector > Serena memory features - Best practices alignment: /Users/kazuki/github/airis-mcp-gateway/docs/mcp-best-practices.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: add PR template and pre-commit config - Add structured PR template with Git workflow checklist - Add pre-commit hooks for secret detection and Conventional Commits - Enforce code quality gates (YAML/JSON/Markdown lint, shellcheck) NOTE: Execute pre-commit inside Docker container to avoid host pollution: docker compose exec workspace uv tool install pre-commit docker compose exec workspace pre-commit run --all-files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: update PM Agent context with token efficiency architecture - Add Layer 0 Bootstrap (150 tokens, 95% reduction) - Document Intent Classification System (5 complexity levels) - Add Progressive Loading strategy (5-layer) - Document mindbase integration incentive (38% savings) - Update with 2025-10-17 redesign details * refactor: PM Agent command with progressive loading - Replace auto-loading with User Request First philosophy - Add 5-layer progressive context loading - Implement intent classification system - Add workflow metrics collection (.jsonl) - Document graceful degradation strategy * fix: installer improvements Update installer logic for better reliability * docs: add comprehensive development documentation - Add architecture overview - Add PM Agent improvements analysis - Add parallel execution architecture - Add CLI install improvements - Add code style guide - Add project overview - Add install process analysis * docs: add research documentation Add LLM agent token efficiency research and analysis * docs: add suggested commands reference * docs: add session logs and testing documentation - Add session analysis logs - Add testing documentation * feat: migrate CLI to typer + rich for modern UX ## What Changed ### New CLI Architecture (typer + rich) - Created `superclaude/cli/` module with modern typer-based CLI - Replaced custom UI utilities with rich native features - Added type-safe command structure with automatic validation ### Commands Implemented - **install**: Interactive installation with rich UI (progress, panels) - **doctor**: System diagnostics with rich table output - **config**: API key management with format validation ### Technical Improvements - Dependencies: Added typer>=0.9.0, rich>=13.0.0, click>=8.0.0 - Entry Point: Updated pyproject.toml to use `superclaude.cli.app:cli_main` - Tests: Added comprehensive smoke tests (11 passed) ### User Experience Enhancements - Rich formatted help messages with panels and tables - Automatic input validation with retry loops - Clear error messages with actionable suggestions - Non-interactive mode support for CI/CD ## Testing ```bash uv run superclaude --help # ✓ Works uv run superclaude doctor # ✓ Rich table output uv run superclaude config show # ✓ API key management pytest tests/test_cli_smoke.py # ✓ 11 passed, 1 skipped ``` ## Migration Path - ✅ P0: Foundation complete (typer + rich + smoke tests) - 🔜 P1: Pydantic validation models (next sprint) - 🔜 P2: Enhanced error messages (next sprint) - 🔜 P3: API key retry loops (next sprint) ## Performance Impact - **Code Reduction**: Prepared for -300 lines (custom UI → rich) - **Type Safety**: Automatic validation from type hints - **Maintainability**: Framework primitives vs custom code 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate documentation directories Merged claudedocs/ into docs/research/ for consistent documentation structure. Changes: - Moved all claudedocs/*.md files to docs/research/ - Updated all path references in documentation (EN/KR) - Updated RULES.md and research.md command templates - Removed claudedocs/ directory - Removed ClaudeDocs/ from .gitignore Benefits: - Single source of truth for all research reports - PEP8-compliant lowercase directory naming - Clearer documentation organization - Prevents future claudedocs/ directory creation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: reduce /sc:pm command output from 1652 to 15 lines - Remove 1637 lines of documentation from command file - Keep only minimal bootstrap message - 99% token reduction on command execution - Detailed specs remain in superclaude/agents/pm-agent.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: split PM Agent into execution workflows and guide - Reduce pm-agent.md from 735 to 429 lines (42% reduction) - Move philosophy/examples to docs/agents/pm-agent-guide.md - Execution workflows (PDCA, file ops) stay in pm-agent.md - Guide (examples, quality standards) read once when needed Token savings: - Agent loading: ~6K → ~3.5K tokens (42% reduction) - Total with pm.md: 71% overall reduction 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate PM Agent optimization and pending changes PM Agent optimization (already committed separately): - superclaude/commands/pm.md: 1652→14 lines - superclaude/agents/pm-agent.md: 735→429 lines - docs/agents/pm-agent-guide.md: new guide file Other pending changes: - setup: framework_docs, mcp, logger, remove ui.py - superclaude: __main__, cli/app, cli/commands/install - tests: test_ui updates - scripts: workflow metrics analysis tools - docs/memory: session state updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: simplify MCP installer to unified gateway with legacy mode ## Changes ### MCP Component (setup/components/mcp.py) - Simplified to single airis-mcp-gateway by default - Added legacy mode for individual official servers (sequential-thinking, context7, magic, playwright) - Dynamic prerequisites based on mode: - Default: uv + claude CLI only - Legacy: node (18+) + npm + claude CLI - Removed redundant server definitions ### CLI Integration - Added --legacy flag to setup/cli/commands/install.py - Added --legacy flag to superclaude/cli/commands/install.py - Config passes legacy_mode to component installer ## Benefits - ✅ Simpler: 1 gateway vs 9+ individual servers - ✅ Lighter: No Node.js/npm required (default mode) - ✅ Unified: All tools in one gateway (sequential-thinking, context7, magic, playwright, serena, morphllm, tavily, chrome-devtools, git, puppeteer) - ✅ Flexible: --legacy flag for official servers if needed ## Usage ```bash superclaude install # Default: airis-mcp-gateway (推奨) superclaude install --legacy # Legacy: individual official servers ``` 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename CoreComponent to FrameworkDocsComponent and add PM token tracking ## Changes ### Component Renaming (setup/components/) - Renamed CoreComponent → FrameworkDocsComponent for clarity - Updated all imports in __init__.py, agents.py, commands.py, mcp_docs.py, modes.py - Better reflects the actual purpose (framework documentation files) ### PM Agent Enhancement (superclaude/commands/pm.md) - Added token usage tracking instructions - PM Agent now reports: 1. Current token usage from system warnings 2. Percentage used (e.g., "27% used" for 54K/200K) 3. Status zone: 🟢 <75% | 🟡 75-85% | 🔴 >85% - Helps prevent token exhaustion during long sessions ### UI Utilities (setup/utils/ui.py) - Added new UI utility module for installer - Provides consistent user interface components ## Benefits - ✅ Clearer component naming (FrameworkDocs vs Core) - ✅ PM Agent token awareness for efficiency - ✅ Better visual feedback with status zones 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor(pm-agent): minimize output verbosity (471→284 lines, 40% reduction) **Problem**: PM Agent generated excessive output with redundant explanations - "System Status Report" with decorative formatting - Repeated "Common Tasks" lists user already knows - Verbose session start/end protocols - Duplicate file operations documentation **Solution**: Compress without losing functionality - Session Start: Reduced to symbol-only status (🟢 branch | nM nD | token%) - Session End: Compressed to essential actions only - File Operations: Consolidated from 2 sections to 1 line reference - Self-Improvement: 5 phases → 1 unified workflow - Output Rules: Explicit constraints to prevent Claude over-explanation **Quality Preservation**: - ✅ All core functions retained (PDCA, memory, patterns, mistakes) - ✅ PARALLEL Read/Write preserved (performance critical) - ✅ Workflow unchanged (session lifecycle intact) - ✅ Added output constraints (prevents verbose generation) **Reduction Method**: - Deleted: Explanatory text, examples, redundant sections - Retained: Action definitions, file paths, core workflows - Added: Explicit output constraints to enforce minimalism **Token Impact**: 40% reduction in agent documentation size **Before**: Verbose multi-section report with task lists **After**: Single line status: 🟢 integration | 15M 17D | 36% 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate MCP integration to unified gateway **Changes**: - Remove individual MCP server docs (superclaude/mcp/*.md) - Remove MCP server configs (superclaude/mcp/configs/*.json) - Delete MCP docs component (setup/components/mcp_docs.py) - Simplify installer (setup/core/installer.py) - Update components for unified gateway approach **Rationale**: - Unified gateway (airis-mcp-gateway) provides all MCP servers - Individual docs/configs no longer needed (managed centrally) - Reduces maintenance burden and file count - Simplifies installation process **Files Removed**: 17 MCP files (docs + configs) **Installer Changes**: Removed legacy MCP installation logic 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: update version and component metadata - Bump version (pyproject.toml, setup/__init__.py) - Update CLAUDE.md import service references - Reflect component structure changes 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-17 09:13:06 +09:00
"servers_count": 1, # Only airis-mcp-gateway
"mcp_servers": ["airis-mcp-gateway"],
"included_tools": [
"sequential-thinking",
"context7",
"magic",
"playwright",
"serena",
"morphllm",
"tavily",
"chrome-devtools",
"git",
"puppeteer",
],
"estimated_size": self.get_size_estimate(),
"dependencies": self.get_dependencies(),
refactor: PM Agent complete independence from external MCP servers (#439) * refactor: PM Agent complete independence from external MCP servers ## Summary Implement graceful degradation to ensure PM Agent operates fully without any MCP server dependencies. MCP servers now serve as optional enhancements rather than required components. ## Changes ### Responsibility Separation (NEW) - **PM Agent**: Development workflow orchestration (PDCA cycle, task management) - **mindbase**: Memory management (long-term, freshness, error learning) - **Built-in memory**: Session-internal context (volatile) ### 3-Layer Memory Architecture with Fallbacks 1. **Built-in Memory** [OPTIONAL]: Session context via MCP memory server 2. **mindbase** [OPTIONAL]: Long-term semantic search via airis-mcp-gateway 3. **Local Files** [ALWAYS]: Core functionality in docs/memory/ ### Graceful Degradation Implementation - All MCP operations marked with [ALWAYS] or [OPTIONAL] - Explicit IF/ELSE fallback logic for every MCP call - Dual storage: Always write to local files + optionally to mindbase - Smart lookup: Semantic search (if available) → Text search (always works) ### Key Fallback Strategies **Session Start**: - mindbase available: search_conversations() for semantic context - mindbase unavailable: Grep docs/memory/*.jsonl for text-based lookup **Error Detection**: - mindbase available: Semantic search for similar past errors - mindbase unavailable: Grep docs/mistakes/ + solutions_learned.jsonl **Knowledge Capture**: - Always: echo >> docs/memory/patterns_learned.jsonl (persistent) - Optional: mindbase.store() for semantic search enhancement ## Benefits - ✅ Zero external dependencies (100% functionality without MCP) - ✅ Enhanced capabilities when MCPs available (semantic search, freshness) - ✅ No functionality loss, only reduced search intelligence - ✅ Transparent degradation (no error messages, automatic fallback) ## Related Research - Serena MCP investigation: Exposes tools (not resources), memory = markdown files - mindbase superiority: PostgreSQL + pgvector > Serena memory features - Best practices alignment: /Users/kazuki/github/airis-mcp-gateway/docs/mcp-best-practices.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: add PR template and pre-commit config - Add structured PR template with Git workflow checklist - Add pre-commit hooks for secret detection and Conventional Commits - Enforce code quality gates (YAML/JSON/Markdown lint, shellcheck) NOTE: Execute pre-commit inside Docker container to avoid host pollution: docker compose exec workspace uv tool install pre-commit docker compose exec workspace pre-commit run --all-files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: update PM Agent context with token efficiency architecture - Add Layer 0 Bootstrap (150 tokens, 95% reduction) - Document Intent Classification System (5 complexity levels) - Add Progressive Loading strategy (5-layer) - Document mindbase integration incentive (38% savings) - Update with 2025-10-17 redesign details * refactor: PM Agent command with progressive loading - Replace auto-loading with User Request First philosophy - Add 5-layer progressive context loading - Implement intent classification system - Add workflow metrics collection (.jsonl) - Document graceful degradation strategy * fix: installer improvements Update installer logic for better reliability * docs: add comprehensive development documentation - Add architecture overview - Add PM Agent improvements analysis - Add parallel execution architecture - Add CLI install improvements - Add code style guide - Add project overview - Add install process analysis * docs: add research documentation Add LLM agent token efficiency research and analysis * docs: add suggested commands reference * docs: add session logs and testing documentation - Add session analysis logs - Add testing documentation * feat: migrate CLI to typer + rich for modern UX ## What Changed ### New CLI Architecture (typer + rich) - Created `superclaude/cli/` module with modern typer-based CLI - Replaced custom UI utilities with rich native features - Added type-safe command structure with automatic validation ### Commands Implemented - **install**: Interactive installation with rich UI (progress, panels) - **doctor**: System diagnostics with rich table output - **config**: API key management with format validation ### Technical Improvements - Dependencies: Added typer>=0.9.0, rich>=13.0.0, click>=8.0.0 - Entry Point: Updated pyproject.toml to use `superclaude.cli.app:cli_main` - Tests: Added comprehensive smoke tests (11 passed) ### User Experience Enhancements - Rich formatted help messages with panels and tables - Automatic input validation with retry loops - Clear error messages with actionable suggestions - Non-interactive mode support for CI/CD ## Testing ```bash uv run superclaude --help # ✓ Works uv run superclaude doctor # ✓ Rich table output uv run superclaude config show # ✓ API key management pytest tests/test_cli_smoke.py # ✓ 11 passed, 1 skipped ``` ## Migration Path - ✅ P0: Foundation complete (typer + rich + smoke tests) - 🔜 P1: Pydantic validation models (next sprint) - 🔜 P2: Enhanced error messages (next sprint) - 🔜 P3: API key retry loops (next sprint) ## Performance Impact - **Code Reduction**: Prepared for -300 lines (custom UI → rich) - **Type Safety**: Automatic validation from type hints - **Maintainability**: Framework primitives vs custom code 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate documentation directories Merged claudedocs/ into docs/research/ for consistent documentation structure. Changes: - Moved all claudedocs/*.md files to docs/research/ - Updated all path references in documentation (EN/KR) - Updated RULES.md and research.md command templates - Removed claudedocs/ directory - Removed ClaudeDocs/ from .gitignore Benefits: - Single source of truth for all research reports - PEP8-compliant lowercase directory naming - Clearer documentation organization - Prevents future claudedocs/ directory creation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: reduce /sc:pm command output from 1652 to 15 lines - Remove 1637 lines of documentation from command file - Keep only minimal bootstrap message - 99% token reduction on command execution - Detailed specs remain in superclaude/agents/pm-agent.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * perf: split PM Agent into execution workflows and guide - Reduce pm-agent.md from 735 to 429 lines (42% reduction) - Move philosophy/examples to docs/agents/pm-agent-guide.md - Execution workflows (PDCA, file ops) stay in pm-agent.md - Guide (examples, quality standards) read once when needed Token savings: - Agent loading: ~6K → ~3.5K tokens (42% reduction) - Total with pm.md: 71% overall reduction 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate PM Agent optimization and pending changes PM Agent optimization (already committed separately): - superclaude/commands/pm.md: 1652→14 lines - superclaude/agents/pm-agent.md: 735→429 lines - docs/agents/pm-agent-guide.md: new guide file Other pending changes: - setup: framework_docs, mcp, logger, remove ui.py - superclaude: __main__, cli/app, cli/commands/install - tests: test_ui updates - scripts: workflow metrics analysis tools - docs/memory: session state updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: simplify MCP installer to unified gateway with legacy mode ## Changes ### MCP Component (setup/components/mcp.py) - Simplified to single airis-mcp-gateway by default - Added legacy mode for individual official servers (sequential-thinking, context7, magic, playwright) - Dynamic prerequisites based on mode: - Default: uv + claude CLI only - Legacy: node (18+) + npm + claude CLI - Removed redundant server definitions ### CLI Integration - Added --legacy flag to setup/cli/commands/install.py - Added --legacy flag to superclaude/cli/commands/install.py - Config passes legacy_mode to component installer ## Benefits - ✅ Simpler: 1 gateway vs 9+ individual servers - ✅ Lighter: No Node.js/npm required (default mode) - ✅ Unified: All tools in one gateway (sequential-thinking, context7, magic, playwright, serena, morphllm, tavily, chrome-devtools, git, puppeteer) - ✅ Flexible: --legacy flag for official servers if needed ## Usage ```bash superclaude install # Default: airis-mcp-gateway (推奨) superclaude install --legacy # Legacy: individual official servers ``` 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename CoreComponent to FrameworkDocsComponent and add PM token tracking ## Changes ### Component Renaming (setup/components/) - Renamed CoreComponent → FrameworkDocsComponent for clarity - Updated all imports in __init__.py, agents.py, commands.py, mcp_docs.py, modes.py - Better reflects the actual purpose (framework documentation files) ### PM Agent Enhancement (superclaude/commands/pm.md) - Added token usage tracking instructions - PM Agent now reports: 1. Current token usage from system warnings 2. Percentage used (e.g., "27% used" for 54K/200K) 3. Status zone: 🟢 <75% | 🟡 75-85% | 🔴 >85% - Helps prevent token exhaustion during long sessions ### UI Utilities (setup/utils/ui.py) - Added new UI utility module for installer - Provides consistent user interface components ## Benefits - ✅ Clearer component naming (FrameworkDocs vs Core) - ✅ PM Agent token awareness for efficiency - ✅ Better visual feedback with status zones 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor(pm-agent): minimize output verbosity (471→284 lines, 40% reduction) **Problem**: PM Agent generated excessive output with redundant explanations - "System Status Report" with decorative formatting - Repeated "Common Tasks" lists user already knows - Verbose session start/end protocols - Duplicate file operations documentation **Solution**: Compress without losing functionality - Session Start: Reduced to symbol-only status (🟢 branch | nM nD | token%) - Session End: Compressed to essential actions only - File Operations: Consolidated from 2 sections to 1 line reference - Self-Improvement: 5 phases → 1 unified workflow - Output Rules: Explicit constraints to prevent Claude over-explanation **Quality Preservation**: - ✅ All core functions retained (PDCA, memory, patterns, mistakes) - ✅ PARALLEL Read/Write preserved (performance critical) - ✅ Workflow unchanged (session lifecycle intact) - ✅ Added output constraints (prevents verbose generation) **Reduction Method**: - Deleted: Explanatory text, examples, redundant sections - Retained: Action definitions, file paths, core workflows - Added: Explicit output constraints to enforce minimalism **Token Impact**: 40% reduction in agent documentation size **Before**: Verbose multi-section report with task lists **After**: Single line status: 🟢 integration | 15M 17D | 36% 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: consolidate MCP integration to unified gateway **Changes**: - Remove individual MCP server docs (superclaude/mcp/*.md) - Remove MCP server configs (superclaude/mcp/configs/*.json) - Delete MCP docs component (setup/components/mcp_docs.py) - Simplify installer (setup/core/installer.py) - Update components for unified gateway approach **Rationale**: - Unified gateway (airis-mcp-gateway) provides all MCP servers - Individual docs/configs no longer needed (managed centrally) - Reduces maintenance burden and file count - Simplifies installation process **Files Removed**: 17 MCP files (docs + configs) **Installer Changes**: Removed legacy MCP installation logic 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: update version and component metadata - Bump version (pyproject.toml, setup/__init__.py) - Update CLAUDE.md import service references - Reflect component structure changes 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-17 09:13:06 +09:00
"required_tools": ["uv", "claude"],
refactor: PEP8 compliance - directory rename and code formatting (#425) * fix(orchestration): add WebFetch auto-trigger for infrastructure configuration Problem: Infrastructure configuration changes (e.g., Traefik port settings) were being made based on assumptions without consulting official documentation, violating the 'Evidence > assumptions' principle in PRINCIPLES.md. Solution: - Added Infrastructure Configuration Validation section to MODE_Orchestration.md - Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.) - Enforces MODE_DeepResearch activation for investigation - BLOCKS assumption-based configuration changes Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default) This prevents production outages from infrastructure misconfiguration by ensuring all technical recommendations are backed by official documentation. * feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add Claude Code conversation history management research Research covering .jsonl file structure, performance impact, and retention policies. Content: - Claude Code .jsonl file format and message types - Performance issues from GitHub (memory leaks, conversation compaction) - Retention policies (consumer vs enterprise) - Rotation recommendations based on actual data - File history snapshot tracking mechanics Source: Moved from agiletec project (research applicable to all Claude Code projects) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add Development documentation structure Phase 1: Documentation Structure complete - Add Docs/Development/ directory for development documentation - Add ARCHITECTURE.md - System architecture with PM Agent meta-layer - Add ROADMAP.md - 5-phase development plan with checkboxes - Add TASKS.md - Daily task tracking with progress indicators - Add PROJECT_STATUS.md - Current status dashboard and metrics - Add pm-agent-integration.md - Implementation guide for PM Agent mode This establishes comprehensive documentation foundation for: - System architecture understanding - Development planning and tracking - Implementation guidance - Progress visibility Related: #pm-agent-mode #documentation #phase-1 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: PM Agent session lifecycle and PDCA implementation Phase 2: PM Agent Mode Integration (Design Phase) Commands/pm.md updates: - Add "Always-Active Foundation Layer" concept - Add Session Lifecycle (Session Start/During Work/Session End) - Add PDCA Cycle (Plan/Do/Check/Act) automation - Add Serena MCP Memory Integration (list/read/write_memory) - Document auto-activation triggers Agents/pm-agent.md updates: - Add Session Start Protocol (MANDATORY auto-activation) - Add During Work PDCA Cycle with example workflows - Add Session End Protocol with state preservation - Add PDCA Self-Evaluation Pattern - Add Documentation Strategy (temp → patterns/mistakes) - Add Memory Operations Reference Key Features: - Session start auto-activation for context restoration - 30-minute checkpoint saves during work - Self-evaluation with think_about_* operations - Systematic documentation lifecycle - Knowledge evolution to CLAUDE.md Implementation Status: - ✅ Design complete (Commands/pm.md, Agents/pm-agent.md) - ⏳ Implementation pending (Core components) - ⏳ Serena MCP integration pending Salvaged from mistaken development in ~/.claude directory Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: disable Serena MCP auto-browser launch Disable web dashboard and GUI log window auto-launch in Serena MCP server to prevent intrusive browser popups on startup. Users can still manually access the dashboard at http://localhost:24282/dashboard/ if needed. Changes: - Add CLI flags to Serena run command: - --enable-web-dashboard false - --enable-gui-log-window false - Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml) - Aligns with AIRIS MCP Gateway integration approach 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rename directories to lowercase for PEP8 compliance - Rename superclaude/Agents -> superclaude/agents - Rename superclaude/Commands -> superclaude/commands - Rename superclaude/Core -> superclaude/core - Rename superclaude/Examples -> superclaude/examples - Rename superclaude/MCP -> superclaude/mcp - Rename superclaude/Modes -> superclaude/modes This change follows Python PEP8 naming conventions for package directories. * style: fix PEP8 violations and update package name to lowercase Changes: - Format all Python files with black (43 files reformatted) - Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml - Fix import statements to use lowercase package name - Add missing imports (timedelta, __version__) - Remove old SuperClaude.egg-info directory PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit). * docs: add PM Agent development documentation Add comprehensive PM Agent development documentation: - PM Agent ideal workflow (7-phase autonomous cycle) - Project structure understanding (Git vs installed environment) - Installation flow understanding (CommandsComponent behavior) - Task management system (current-tasks.md) Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(pm-agent): add self-correcting execution and warning investigation culture ## Changes ### superclaude/commands/pm.md - Add "Self-Correcting Execution" section with root cause analysis protocol - Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal - Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute - Document anti-patterns (retry without understanding) and correct patterns (research-first) ### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md - Add PDCA workflow hypothesis document for PM Agent autonomous enhancement ## Rationale PM Agent must never retry failed operations without understanding root causes. All warnings and errors require investigation via context7/WebFetch/documentation to ensure production-quality code and prevent technical debt accumulation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(installer): add airis-mcp-gateway MCP server option ## Changes - Add airis-mcp-gateway to MCP server options in installer - Configuration: GitHub-based installation via uvx - Repository: https://github.com/oraios/airis-mcp-gateway - Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading ## Implementation Added to setup/components/mcp.py self.mcp_servers dictionary with: - install_method: github - install_command: uvx test installation - run_command: uvx runtime execution - required: False (optional server) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 12:17:09 +09:00
}