kazuki nakai 050d5ea2ab
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 08:47:09 +05:30

516 lines
17 KiB
Python

"""
SuperClaude Update Operation Module
Refactored from update.py for unified CLI hub
"""
import sys
import time
from pathlib import Path
from ...utils.paths import get_home_directory
from typing import List, Optional, Dict, Any
import argparse
from ...core.installer import Installer
from ...core.registry import ComponentRegistry
from ...services.settings import SettingsService
from ...core.validator import Validator
from ...utils.ui import (
display_header,
display_info,
display_success,
display_error,
display_warning,
Menu,
confirm,
ProgressBar,
Colors,
format_size,
prompt_api_key,
)
from ...utils.environment import setup_environment_variables
from ...utils.logger import get_logger
from ... import DEFAULT_INSTALL_DIR, PROJECT_ROOT, DATA_DIR
from . import OperationBase
class UpdateOperation(OperationBase):
"""Update operation implementation"""
def __init__(self):
super().__init__("update")
def register_parser(subparsers, global_parser=None) -> argparse.ArgumentParser:
"""Register update CLI arguments"""
parents = [global_parser] if global_parser else []
parser = subparsers.add_parser(
"update",
help="Update existing SuperClaude installation",
description="Update SuperClaude Framework components to latest versions",
epilog="""
Examples:
SuperClaude update # Interactive update
SuperClaude update --check --verbose # Check for updates (verbose)
SuperClaude update --components core mcp # Update specific components
SuperClaude update --backup --force # Create backup before update (forced)
""",
formatter_class=argparse.RawDescriptionHelpFormatter,
parents=parents,
)
# Update mode options
parser.add_argument(
"--check",
action="store_true",
help="Check for available updates without installing",
)
parser.add_argument(
"--components", type=str, nargs="+", help="Specific components to update"
)
# Backup options
parser.add_argument(
"--backup", action="store_true", help="Create backup before update"
)
parser.add_argument("--no-backup", action="store_true", help="Skip backup creation")
# Update options
parser.add_argument(
"--reinstall",
action="store_true",
help="Reinstall components even if versions match",
)
return parser
def check_installation_exists(install_dir: Path) -> bool:
"""Check if SuperClaude installation exists"""
settings_manager = SettingsService(install_dir)
return settings_manager.check_installation_exists()
def get_installed_components(install_dir: Path) -> Dict[str, Dict[str, Any]]:
"""Get currently installed components and their versions"""
try:
settings_manager = SettingsService(install_dir)
return settings_manager.get_installed_components()
except Exception:
return {}
def get_available_updates(
installed_components: Dict[str, str], registry: ComponentRegistry
) -> Dict[str, Dict[str, str]]:
"""Check for available updates"""
updates = {}
for component_name, current_version in installed_components.items():
try:
metadata = registry.get_component_metadata(component_name)
if metadata:
available_version = metadata.get("version", "unknown")
if available_version != current_version:
updates[component_name] = {
"current": current_version,
"available": available_version,
"description": metadata.get("description", "No description"),
}
except Exception:
continue
return updates
def display_update_check(
installed_components: Dict[str, str], available_updates: Dict[str, Dict[str, str]]
) -> None:
"""Display update check results"""
print(f"\n{Colors.CYAN}{Colors.BRIGHT}Update Check Results{Colors.RESET}")
print("=" * 50)
if not installed_components:
print(f"{Colors.YELLOW}No SuperClaude installation found{Colors.RESET}")
return
print(f"{Colors.BLUE}Currently installed components:{Colors.RESET}")
for component, version in installed_components.items():
print(f" {component}: v{version}")
if available_updates:
print(f"\n{Colors.GREEN}Available updates:{Colors.RESET}")
for component, info in available_updates.items():
print(f" {component}: v{info['current']} → v{info['available']}")
print(f" {info['description']}")
else:
print(f"\n{Colors.GREEN}All components are up to date{Colors.RESET}")
print()
def get_components_to_update(
args: argparse.Namespace,
installed_components: Dict[str, str],
available_updates: Dict[str, Dict[str, str]],
) -> Optional[List[str]]:
"""Determine which components to update"""
logger = get_logger()
# Explicit components specified
if args.components:
# Validate that specified components are installed
invalid_components = [
c for c in args.components if c not in installed_components
]
if invalid_components:
logger.error(f"Components not installed: {invalid_components}")
return None
return args.components
# If no updates available and not forcing reinstall
if not available_updates and not args.reinstall:
logger.info("No updates available")
return []
# Interactive selection
if available_updates:
return interactive_update_selection(available_updates, installed_components)
elif args.reinstall:
# Reinstall all components
return list(installed_components.keys())
return []
def collect_api_keys_for_servers(
selected_servers: List[str], mcp_instance
) -> Dict[str, str]:
"""
Collect API keys for servers that require them during update
Args:
selected_servers: List of selected server keys
mcp_instance: MCP component instance
Returns:
Dictionary of environment variable names to API key values
"""
# Filter servers needing keys
servers_needing_keys = [
(server_key, mcp_instance.mcp_servers[server_key])
for server_key in selected_servers
if server_key in mcp_instance.mcp_servers
and mcp_instance.mcp_servers[server_key].get("requires_api_key", False)
]
if not servers_needing_keys:
return {}
# Display API key configuration header
print(f"\n{Colors.CYAN}{Colors.BRIGHT}=== API Key Configuration ==={Colors.RESET}")
print(
f"{Colors.YELLOW}New MCP servers require API keys for full functionality:{Colors.RESET}\n"
)
collected_keys = {}
for server_key, server_info in servers_needing_keys:
api_key_env = server_info.get("api_key_env")
service_name = server_info["name"]
if api_key_env:
key = prompt_api_key(service_name, api_key_env)
if key:
collected_keys[api_key_env] = key
return collected_keys
def interactive_update_selection(
available_updates: Dict[str, Dict[str, str]], installed_components: Dict[str, str]
) -> Optional[List[str]]:
"""Interactive update selection"""
if not available_updates:
return []
print(f"\n{Colors.CYAN}Available Updates:{Colors.RESET}")
# Create menu options
update_options = []
component_names = []
for component, info in available_updates.items():
update_options.append(f"{component}: v{info['current']} → v{info['available']}")
component_names.append(component)
# Add bulk options
preset_options = [
"Update All Components",
"Select Individual Components",
"Cancel Update",
]
menu = Menu("Select update option:", preset_options)
choice = menu.display()
if choice == -1 or choice == 2: # Cancelled
return None
elif choice == 0: # Update all
return component_names
elif choice == 1: # Select individual
component_menu = Menu(
"Select components to update:", update_options, multi_select=True
)
selections = component_menu.display()
if not selections:
return None
return [component_names[i] for i in selections]
return None
def display_update_plan(
components: List[str],
available_updates: Dict[str, Dict[str, str]],
installed_components: Dict[str, str],
install_dir: Path,
) -> None:
"""Display update plan"""
print(f"\n{Colors.CYAN}{Colors.BRIGHT}Update Plan{Colors.RESET}")
print("=" * 50)
print(f"{Colors.BLUE}Installation Directory:{Colors.RESET} {install_dir}")
print(f"{Colors.BLUE}Components to update:{Colors.RESET}")
for i, component_name in enumerate(components, 1):
if component_name in available_updates:
info = available_updates[component_name]
print(f" {i}. {component_name}: v{info['current']} → v{info['available']}")
else:
current_version = installed_components.get(component_name, "unknown")
print(f" {i}. {component_name}: v{current_version} (reinstall)")
print()
def perform_update(
components: List[str], args: argparse.Namespace, registry: ComponentRegistry
) -> bool:
"""Perform the actual update"""
logger = get_logger()
start_time = time.time()
try:
# Create installer
installer = Installer(args.install_dir, dry_run=args.dry_run)
# Create component instances
component_instances = registry.create_component_instances(
components, args.install_dir
)
if not component_instances:
logger.error("No valid component instances created")
return False
# Handle MCP component specially - collect API keys for new servers
collected_api_keys = {}
if "mcp" in components and "mcp" in component_instances:
mcp_instance = component_instances["mcp"]
if hasattr(mcp_instance, "mcp_servers"):
# Get all available MCP servers
all_server_keys = list(mcp_instance.mcp_servers.keys())
# Collect API keys for any servers that require them
collected_api_keys = collect_api_keys_for_servers(
all_server_keys, mcp_instance
)
# Set up environment variables if any keys were collected
if collected_api_keys:
setup_environment_variables(collected_api_keys)
# Store keys for MCP component to use during update
mcp_instance.collected_api_keys = collected_api_keys
logger.info(
f"Collected {len(collected_api_keys)} API keys for MCP server update"
)
# Register components with installer
installer.register_components(list(component_instances.values()))
# Setup progress tracking
progress = ProgressBar(total=len(components), prefix="Updating: ", suffix="")
# Update components
logger.info(f"Updating {len(components)} components...")
# Determine backup strategy
backup = args.backup or (not args.no_backup and not args.dry_run)
config = {
"force": args.force,
"backup": backup,
"dry_run": args.dry_run,
"update_mode": True,
"selected_mcp_servers": (
list(mcp_instance.mcp_servers.keys())
if "mcp" in component_instances
else []
),
}
success = installer.update_components(components, config)
# Update progress
for i, component_name in enumerate(components):
if component_name in installer.updated_components:
progress.update(i + 1, f"Updated {component_name}")
else:
progress.update(i + 1, f"Failed {component_name}")
time.sleep(0.1) # Brief pause for visual effect
progress.finish("Update complete")
# Show results
duration = time.time() - start_time
if success:
logger.success(f"Update completed successfully in {duration:.1f} seconds")
# Show summary
summary = installer.get_update_summary()
if summary.get("updated"):
logger.info(f"Updated components: {', '.join(summary['updated'])}")
if summary.get("backup_path"):
logger.info(f"Backup created: {summary['backup_path']}")
else:
logger.error(f"Update completed with errors in {duration:.1f} seconds")
summary = installer.get_update_summary()
if summary.get("failed"):
logger.error(f"Failed components: {', '.join(summary['failed'])}")
return success
except Exception as e:
logger.exception(f"Unexpected error during update: {e}")
return False
def run(args: argparse.Namespace) -> int:
"""Execute update operation with parsed arguments"""
operation = UpdateOperation()
operation.setup_operation_logging(args)
logger = get_logger()
from setup.cli.base import __version__
# ✅ Inserted validation code
expected_home = get_home_directory().resolve()
actual_dir = args.install_dir.resolve()
if not str(actual_dir).startswith(str(expected_home)):
print(f"\n[x] Installation must be inside your user profile directory.")
print(f" Expected prefix: {expected_home}")
print(f" Provided path: {actual_dir}")
sys.exit(1)
try:
# Validate global arguments
success, errors = operation.validate_global_args(args)
if not success:
for error in errors:
logger.error(error)
return 1
# Display header
if not args.quiet:
display_header(
f"SuperClaude Update v{__version__}",
"Updating SuperClaude framework components",
)
# Check if SuperClaude is installed
if not check_installation_exists(args.install_dir):
logger.error(f"SuperClaude installation not found in {args.install_dir}")
logger.info("Use 'superclaude install' to install SuperClaude first")
return 1
# Create component registry
logger.info("Checking for available updates...")
registry = ComponentRegistry(PROJECT_ROOT / "setup" / "components")
registry.discover_components()
# Get installed components
installed_components = get_installed_components(args.install_dir)
if not installed_components:
logger.error("Could not determine installed components")
return 1
# Check for available updates
available_updates = get_available_updates(installed_components, registry)
# Display update check results
if not args.quiet:
display_update_check(installed_components, available_updates)
# If only checking for updates, exit here
if args.check:
return 0
# Get components to update
components = get_components_to_update(
args, installed_components, available_updates
)
if components is None:
logger.info("Update cancelled by user")
return 0
elif not components:
logger.info("No components selected for update")
return 0
# Display update plan
if not args.quiet:
display_update_plan(
components, available_updates, installed_components, args.install_dir
)
if not args.dry_run:
if not args.yes and not confirm("Proceed with update?", default=True):
logger.info("Update cancelled by user")
return 0
# Perform update
success = perform_update(components, args, registry)
if success:
if not args.quiet:
display_success("SuperClaude update completed successfully!")
if not args.dry_run:
print(f"\n{Colors.CYAN}Next steps:{Colors.RESET}")
print(f"1. Restart your Claude Code session")
print(f"2. Updated components are now available")
print(f"3. Check for any breaking changes in documentation")
return 0
else:
display_error("Update failed. Check logs for details.")
return 1
except KeyboardInterrupt:
print(f"\n{Colors.YELLOW}Update cancelled by user{Colors.RESET}")
return 130
except Exception as e:
return operation.handle_operation_error("update", e)