mirror of
https://github.com/SuperClaude-Org/SuperClaude_Framework.git
synced 2025-12-17 17:56:46 +00:00
882a0d8356
* 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>
SuperClaude Framework Reference Documentation
Navigation Hub: Structured learning paths and technical references for all skill levels.
Documentation Status: ✅ Status: Current - All content verified for accuracy and completeness.
How to Use This Reference Library
This documentation is organized for progressive learning with multiple entry points:
- 📱 Quick Reference: Jump to specific solutions for immediate needs
- 📚 Learning Paths: Structured progression from beginner to expert
- 🔍 Problem-Solving: Targeted troubleshooting and diagnostic guidance
- ⚡ Performance: Optimization patterns and advanced techniques
Verification Standards: All examples tested, commands validated, patterns proven in real-world usage.
Documentation Navigation Matrix
| Document | Purpose | Target Audience | Complexity | |
|---|---|---|---|---|
| basic-examples.md | Copy-paste ready commands and patterns | All users, quick reference | Basic | |
| examples-cookbook.md | Recipe collection hub and organization | All users, navigation | Reference | |
| common-issues.md | Essential troubleshooting and solutions | All users, problem-solving | Basic | As needed |
| mcp-server-guide.md | MCP server configuration and usage | Technical users, integration | Intermediate |
| advanced-patterns.md | Expert coordination and orchestration | Experienced users | Advanced | | | advanced-workflows.md | Complex multi-agent orchestration | Expert users | Advanced | | | integration-patterns.md | Framework and system integration | Architects, experts | Advanced | | | troubleshooting.md | Comprehensive diagnostic guide | All levels, deep debugging | Variable | As needed | | diagnostic-reference.md | Advanced debugging and analysis | Expert users, complex issues | Advanced | |
Recommended Learning Paths
New Users (Week 1 Foundation)
Goal: Establish confident SuperClaude usage with essential workflows
Day 1-2: ../getting-started/quick-start.md
↓ Foundation building and first commands
Day 3-4: basic-examples.md
↓ Practical application and pattern recognition
Day 5-7: common-issues.md
↓ Problem resolution and confidence building
Success Metrics: Can execute basic commands, manage sessions, resolve common issues independently.
Intermediate Users (Week 2-3 Enhancement)
Goal: Master coordination patterns and technical depth
Week 2: advanced-patterns.md
↓ Multi-agent coordination and orchestration mastery
Week 3: mcp-server-guide.md + advanced-workflows.md
↓ Performance excellence and technical configuration
Success Metrics: Can orchestrate complex workflows, optimize performance, configure MCP servers.
Expert Users (Advanced Mastery)
Goal: Complete framework mastery and complex system integration
Phase 1: advanced-workflows.md
↓ Complex orchestration and enterprise patterns
Phase 2: integration-patterns.md
↓ Framework integration and architectural mastery
Phase 3: diagnostic-reference.md
↓ Advanced debugging and system analysis
Success Metrics: Can design custom workflows, integrate with any framework, diagnose complex issues.
Problem-Solving Path (As Needed)
Goal: Immediate issue resolution and diagnostic guidance
Quick Issues: common-issues.md
↓ Common problems and immediate solutions
Complex Debugging: troubleshooting.md
↓ Comprehensive diagnostic approach
Advanced Analysis: diagnostic-reference.md
↓ Expert-level debugging and analysis
Command Quick Reference
Essential SuperClaude Commands
| Command Pattern | Purpose | Example |
|---|---|---|
/sc:load |
Restore session context | /sc:load project_name |
/sc:save |
Preserve session state | /sc:save "milestone checkpoint" |
--think |
Enable structured analysis | --think analyze performance bottlenecks |
--brainstorm |
Collaborative requirement discovery | --brainstorm new authentication system |
--task-manage |
Multi-step operation orchestration | --task-manage refactor user module |
Performance & Efficiency Flags
| Flag | Purpose | Best For |
|---|---|---|
--uc / --ultracompressed |
Token-efficient communication | Large operations, context pressure |
--orchestrate |
Optimize tool selection | Multi-tool operations, performance needs |
--loop |
Iterative improvement cycles | Code refinement, quality enhancement |
--validate |
Pre-execution risk assessment | Production environments, critical operations |
MCP Server Activation
| Flag | Server | Best For |
|---|---|---|
--c7 / --context7 |
Context7 | Official documentation, framework patterns |
--seq / --sequential |
Sequential | Complex analysis, debugging, system design |
--magic |
Magic | UI components, design systems, frontend work |
--morph / --morphllm |
Morphllm | Bulk transformations, pattern-based edits |
--serena |
Serena | Symbol operations, project memory, large codebases |
--play / --playwright |
Playwright | Browser testing, E2E scenarios, visual validation |
Framework Integration Quick Start
React/Next.js Projects
# Initialize with React patterns
--c7 --magic "implement Next.js authentication with TypeScript"
# Component development workflow
--magic --think "create responsive dashboard component"
Node.js/Express Backend
# API development with best practices
--c7 --seq "design RESTful API with Express and MongoDB"
# Performance optimization
--think --orchestrate "optimize database queries and caching"
Full-Stack Development
# Complete application workflow
--task-manage --all-mcp "build full-stack e-commerce platform"
# Integration testing
--play --seq "implement end-to-end testing strategy"
Problem-Solving Quick Reference
Immediate Issues
- Command not working: Check common-issues.md → Common SuperClaude Problems
- Session lost: Use
/sc:load→ See Session Management - Flag confusion: Check basic-examples.md → Flag Usage Examples
Development Blockers
- Performance slow: See Advanced Workflows → Performance Patterns
- Complex debugging: Use troubleshooting.md → Systematic Debugging
- Integration issues: Check integration-patterns.md → Framework Patterns
System-Level Issues
- Architecture problems: Use advanced-workflows.md → System Design
- Expert debugging: Apply diagnostic-reference.md → Advanced Analysis
- Custom workflow needs: Study advanced-patterns.md → Custom Orchestration advanced-patterns.md → Custom Orchestration
Documentation Health & Verification
Quality Assurance
- ✅ Commands Tested: All examples tested and functional
- ✅ Patterns Proven: Real-world usage validation in production environments
- ✅ Cross-References: Internal links verified and maintained
- ✅ Regular Updates: Documentation synchronized with framework evolution
Accuracy Standards
- Command Syntax: Verified against latest SuperClaude implementation
- Flag Behavior: Tested in multiple scenarios and environments
- MCP Integration: Confirmed compatibility with current MCP server versions
- Performance Claims: Benchmarked and measured in realistic conditions
Reporting Issues
Found outdated information or broken examples?
- Quick Fixes: Check common-issues.md first
- Documentation Bugs: Report via project issues with specific file and line
- Missing Patterns: Suggest additions with use case description
- Verification Requests: Request re-testing of specific examples
Expert Tips for Maximum Productivity
Daily Workflow Optimization
- Session Management: Always start with
/sc:load, end with/sc:save - Flag Combinations: Combine complementary flags:
--think --c7for documented analysis - Progressive Complexity: Start simple, add sophistication incrementally
- Tool Specialization: Match tools to tasks: Magic for UI, Sequential for analysis
Learning Acceleration
- Follow the Paths: Use recommended learning sequences for structured growth
- Practice Patterns: Repeat common workflows until they become intuitive
- Experiment Safely: Use feature branches and checkpoints for exploration
- Community Learning: Share discoveries and learn from others' approaches
Troubleshooting Mastery
- Systematic Approach: Always start with common-issues.md
- Evidence Gathering: Use
--thinkfor complex problem analysis - Root Cause Focus: Address underlying issues, not just symptoms
- Documentation First: Check official docs before experimental solutions
Advanced Resources & Integration
Framework-Specific Guides
- React/Next.js: See integration-patterns.md → React Integration
- Vue/Nuxt: See integration-patterns.md → Vue Ecosystem
- Node.js/Express: See integration-patterns.md → Backend Patterns
- Python/Django: See integration-patterns.md → Python Workflows
Specialized Workflows
- DevOps Integration: advanced-workflows.md → CI/CD Patterns
- Testing Strategies: advanced-patterns.md → Testing Orchestration
- Performance Engineering: Advanced Patterns → Complex Coordination
- Security Implementation: integration-patterns.md → Security Patterns
Community & Support
- Best Practices: Continuously updated based on community feedback
- Pattern Library: Growing collection of proven workflow patterns
- Expert Network: Connect with experienced SuperClaude practitioners
- Regular Updates: Documentation evolves with framework capabilities
Start Your Journey: New to SuperClaude? Begin with Quick Start Guide for immediate productivity gains.
Need Answers Now: Jump to basic-examples.md for copy-paste solutions.
Ready for Advanced: Explore advanced-patterns.md for expert-level orchestration.