SuperClaude/setup/utils/environment.py
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

536 lines
17 KiB
Python

"""
Environment variable management for SuperClaude
Cross-platform utilities for setting up persistent environment variables
"""
import os
import sys
import subprocess
import json
from pathlib import Path
from typing import Dict, Optional
from datetime import datetime
from .ui import display_info, display_success, display_warning, Colors
from .logger import get_logger
from .paths import get_home_directory
def _get_env_tracking_file() -> Path:
"""Get path to environment variable tracking file"""
from .. import DEFAULT_INSTALL_DIR
install_dir = get_home_directory() / ".claude"
install_dir.mkdir(exist_ok=True)
return install_dir / "superclaude_env_vars.json"
def _load_env_tracking() -> Dict[str, Dict[str, str]]:
"""Load environment variable tracking data"""
tracking_file = _get_env_tracking_file()
try:
if tracking_file.exists():
with open(tracking_file, "r") as f:
return json.load(f)
except Exception as e:
get_logger().warning(f"Could not load environment tracking: {e}")
return {}
def _save_env_tracking(tracking_data: Dict[str, Dict[str, str]]) -> bool:
"""Save environment variable tracking data"""
tracking_file = _get_env_tracking_file()
try:
with open(tracking_file, "w") as f:
json.dump(tracking_data, f, indent=2)
return True
except Exception as e:
get_logger().error(f"Could not save environment tracking: {e}")
return False
def _add_env_tracking(env_vars: Dict[str, str]) -> None:
"""Add environment variables to tracking"""
if not env_vars:
return
tracking_data = _load_env_tracking()
timestamp = datetime.now().isoformat()
for env_var, value in env_vars.items():
tracking_data[env_var] = {
"set_by": "superclaude",
"timestamp": timestamp,
"value_hash": str(hash(value)), # Store hash, not actual value for security
}
_save_env_tracking(tracking_data)
get_logger().info(f"Added {len(env_vars)} environment variables to tracking")
def _remove_env_tracking(env_vars: list) -> None:
"""Remove environment variables from tracking"""
if not env_vars:
return
tracking_data = _load_env_tracking()
for env_var in env_vars:
if env_var in tracking_data:
del tracking_data[env_var]
_save_env_tracking(tracking_data)
get_logger().info(f"Removed {len(env_vars)} environment variables from tracking")
def detect_shell_config() -> Optional[Path]:
"""
Detect user's shell configuration file
Returns:
Path to the shell configuration file, or None if not found
"""
home = get_home_directory()
# Check in order of preference
configs = [
home / ".zshrc", # Zsh (Mac default)
home / ".bashrc", # Bash
home / ".profile", # Generic shell profile
home / ".bash_profile", # Mac Bash profile
]
for config in configs:
if config.exists():
return config
# Default to .bashrc if none exist (will be created)
return home / ".bashrc"
def setup_environment_variables(api_keys: Dict[str, str]) -> bool:
"""
Set up environment variables across platforms
Args:
api_keys: Dictionary of environment variable names to values
Returns:
True if all variables were set successfully, False otherwise
"""
logger = get_logger()
success = True
if not api_keys:
return True
print(f"\n{Colors.BLUE}[INFO] Setting up environment variables...{Colors.RESET}")
for env_var, value in api_keys.items():
try:
# Set for current session
os.environ[env_var] = value
if os.name == "nt": # Windows
# Use setx for persistent user variable
result = subprocess.run(
["setx", env_var, value], capture_output=True, text=True
)
if result.returncode != 0:
display_warning(
f"Could not set {env_var} persistently: {result.stderr.strip()}"
)
success = False
else:
logger.info(
f"Windows environment variable {env_var} set persistently"
)
else: # Unix-like systems
shell_config = detect_shell_config()
# Check if the export already exists
export_line = f'export {env_var}="{value}"'
try:
with open(shell_config, "r") as f:
content = f.read()
# Check if this environment variable is already set
if f"export {env_var}=" in content:
# Variable exists - don't duplicate
logger.info(
f"Environment variable {env_var} already exists in {shell_config.name}"
)
else:
# Append export to shell config
with open(shell_config, "a") as f:
f.write(f"\n# SuperClaude API Key\n{export_line}\n")
display_info(f"Added {env_var} to {shell_config.name}")
logger.info(f"Added {env_var} to {shell_config}")
except Exception as e:
display_warning(f"Could not update {shell_config.name}: {e}")
success = False
logger.info(
f"Environment variable {env_var} configured for current session"
)
except Exception as e:
logger.error(f"Failed to set {env_var}: {e}")
display_warning(f"Failed to set {env_var}: {e}")
success = False
if success:
# Add to tracking
_add_env_tracking(api_keys)
display_success("Environment variables configured successfully")
if os.name != "nt":
display_info(
"Restart your terminal or run 'source ~/.bashrc' to apply changes"
)
else:
display_info(
"New environment variables will be available in new terminal sessions"
)
else:
display_warning("Some environment variables could not be set persistently")
display_info("You can set them manually or check the logs for details")
return success
def validate_environment_setup(env_vars: Dict[str, str]) -> bool:
"""
Validate that environment variables are properly set
Args:
env_vars: Dictionary of environment variable names to expected values
Returns:
True if all variables are set correctly, False otherwise
"""
logger = get_logger()
all_valid = True
for env_var, expected_value in env_vars.items():
current_value = os.environ.get(env_var)
if current_value is None:
logger.warning(f"Environment variable {env_var} is not set")
all_valid = False
elif current_value != expected_value:
logger.warning(f"Environment variable {env_var} has unexpected value")
all_valid = False
else:
logger.info(f"Environment variable {env_var} is set correctly")
return all_valid
def get_shell_name() -> str:
"""
Get the name of the current shell
Returns:
Name of the shell (e.g., 'bash', 'zsh', 'fish')
"""
shell_path = os.environ.get("SHELL", "")
if shell_path:
return Path(shell_path).name
return "unknown"
def get_superclaude_environment_variables() -> Dict[str, str]:
"""
Get environment variables that were set by SuperClaude
Returns:
Dictionary of environment variable names to their current values
"""
# Load tracking data to get SuperClaude-managed variables
tracking_data = _load_env_tracking()
found_vars = {}
for env_var, metadata in tracking_data.items():
if metadata.get("set_by") == "superclaude":
value = os.environ.get(env_var)
if value:
found_vars[env_var] = value
# Fallback: check known SuperClaude API key environment variables
# (for backwards compatibility with existing installations)
known_superclaude_env_vars = [
"TWENTYFIRST_API_KEY", # Magic server
"MORPH_API_KEY", # Morphllm server
]
for env_var in known_superclaude_env_vars:
if env_var not in found_vars:
value = os.environ.get(env_var)
if value:
found_vars[env_var] = value
return found_vars
def cleanup_environment_variables(
env_vars_to_remove: Dict[str, str], create_restore_script: bool = True
) -> bool:
"""
Safely remove environment variables with backup and restore options
Args:
env_vars_to_remove: Dictionary of environment variable names to remove
create_restore_script: Whether to create a script to restore the variables
Returns:
True if cleanup was successful, False otherwise
"""
logger = get_logger()
success = True
if not env_vars_to_remove:
return True
# Create restore script if requested
if create_restore_script:
restore_script_path = _create_restore_script(env_vars_to_remove)
if restore_script_path:
display_info(f"Created restore script: {restore_script_path}")
else:
display_warning("Could not create restore script")
print(f"\n{Colors.BLUE}[INFO] Removing environment variables...{Colors.RESET}")
for env_var, value in env_vars_to_remove.items():
try:
# Remove from current session
if env_var in os.environ:
del os.environ[env_var]
logger.info(f"Removed {env_var} from current session")
if os.name == "nt": # Windows
# Remove persistent user variable using reg command
result = subprocess.run(
["reg", "delete", "HKCU\\Environment", "/v", env_var, "/f"],
capture_output=True,
text=True,
)
if result.returncode != 0:
# Variable might not exist in registry, which is fine
logger.debug(
f"Registry deletion for {env_var}: {result.stderr.strip()}"
)
else:
logger.info(f"Removed {env_var} from Windows registry")
else: # Unix-like systems
shell_config = detect_shell_config()
if shell_config and shell_config.exists():
_remove_env_var_from_shell_config(shell_config, env_var)
except Exception as e:
logger.error(f"Failed to remove {env_var}: {e}")
display_warning(f"Could not remove {env_var}: {e}")
success = False
if success:
# Remove from tracking
_remove_env_tracking(list(env_vars_to_remove.keys()))
display_success("Environment variables removed successfully")
if os.name != "nt":
display_info(
"Restart your terminal or source your shell config to apply changes"
)
else:
display_info("Changes will take effect in new terminal sessions")
else:
display_warning("Some environment variables could not be removed")
return success
def _create_restore_script(env_vars: Dict[str, str]) -> Optional[Path]:
"""Create a script to restore environment variables"""
try:
home = get_home_directory()
if os.name == "nt": # Windows
script_path = home / "restore_superclaude_env.bat"
with open(script_path, "w") as f:
f.write("@echo off\n")
f.write("REM SuperClaude Environment Variable Restore Script\n")
f.write("REM Generated during uninstall\n\n")
for env_var, value in env_vars.items():
f.write(f'setx {env_var} "{value}"\n')
f.write("\necho Environment variables restored\n")
f.write("pause\n")
else: # Unix-like
script_path = home / "restore_superclaude_env.sh"
with open(script_path, "w") as f:
f.write("#!/bin/bash\n")
f.write("# SuperClaude Environment Variable Restore Script\n")
f.write("# Generated during uninstall\n\n")
shell_config = detect_shell_config()
for env_var, value in env_vars.items():
f.write(f'export {env_var}="{value}"\n')
if shell_config:
f.write(
f"echo 'export {env_var}=\"{value}\"' >> {shell_config}\n"
)
f.write("\necho 'Environment variables restored'\n")
# Make script executable
script_path.chmod(0o755)
return script_path
except Exception as e:
get_logger().error(f"Failed to create restore script: {e}")
return None
def _remove_env_var_from_shell_config(shell_config: Path, env_var: str) -> bool:
"""Remove environment variable export from shell configuration file"""
try:
# Read current content
with open(shell_config, "r") as f:
lines = f.readlines()
# Filter out lines that export this variable
filtered_lines = []
skip_next_blank = False
for line in lines:
# Check if this line exports our variable
if f"export {env_var}=" in line or line.strip() == f"# SuperClaude API Key":
skip_next_blank = True
continue
# Skip blank line after removed export
if skip_next_blank and line.strip() == "":
skip_next_blank = False
continue
skip_next_blank = False
filtered_lines.append(line)
# Write back the filtered content
with open(shell_config, "w") as f:
f.writelines(filtered_lines)
get_logger().info(f"Removed {env_var} export from {shell_config.name}")
return True
except Exception as e:
get_logger().error(f"Failed to remove {env_var} from {shell_config}: {e}")
return False
def create_env_file(
api_keys: Dict[str, str], env_file_path: Optional[Path] = None
) -> bool:
"""
Create a .env file with the API keys (alternative to shell config)
Args:
api_keys: Dictionary of environment variable names to values
env_file_path: Path to the .env file (defaults to home directory)
Returns:
True if .env file was created successfully, False otherwise
"""
if env_file_path is None:
env_file_path = get_home_directory() / ".env"
logger = get_logger()
try:
# Read existing .env file if it exists
existing_content = ""
if env_file_path.exists():
with open(env_file_path, "r") as f:
existing_content = f.read()
# Prepare new content
new_lines = []
for env_var, value in api_keys.items():
line = f'{env_var}="{value}"'
# Check if this variable already exists
if f"{env_var}=" in existing_content:
logger.info(f"Variable {env_var} already exists in .env file")
else:
new_lines.append(line)
# Append new lines if any
if new_lines:
with open(env_file_path, "a") as f:
if existing_content and not existing_content.endswith("\n"):
f.write("\n")
f.write("# SuperClaude API Keys\n")
for line in new_lines:
f.write(line + "\n")
# Set file permissions (readable only by owner)
env_file_path.chmod(0o600)
display_success(f"Created .env file at {env_file_path}")
logger.info(f"Created .env file with {len(new_lines)} new variables")
return True
except Exception as e:
logger.error(f"Failed to create .env file: {e}")
display_warning(f"Could not create .env file: {e}")
return False
def check_research_prerequisites() -> tuple[bool, list[str]]:
"""
Check if deep research prerequisites are met
Returns:
Tuple of (success: bool, warnings: List[str])
"""
warnings = []
logger = get_logger()
# Check Tavily API key
if not os.environ.get("TAVILY_API_KEY"):
warnings.append(
"TAVILY_API_KEY not set - Deep research web search will not work\n"
"Get your key from: https://app.tavily.com"
)
logger.warning("TAVILY_API_KEY not found in environment")
else:
logger.info("Found TAVILY_API_KEY in environment")
# Check Node.js for MCP
import shutil
if not shutil.which("node"):
warnings.append(
"Node.js not found - Required for Tavily MCP\n"
"Install from: https://nodejs.org"
)
logger.warning("Node.js not found - required for Tavily MCP")
else:
logger.info("Node.js found")
# Check npm
if not shutil.which("npm"):
warnings.append(
"npm not found - Required for MCP server installation\n"
"Usually installed with Node.js"
)
logger.warning("npm not found - required for MCP installation")
else:
logger.info("npm found")
return len(warnings) == 0, warnings