Feat: Add repository documentation storage and processing with comprehensive test suite

[theycallmeswift]

This PR enhances the parse_github_repository tool with comprehensive documentation processing capabilities, storing repository documentation in Supabase for semantic search and RAG operations alongside the existing Neo4j code analysis.

✨ Key Features Added

📚 Documentation Processing

• Multi-format support: Processes .md, .rst, .txt, and .ipynb files from GitHub repositories
• Built-in Jupyter notebook conversion: Custom JSON parsing to convert notebooks to markdown without external dependencies
• Smart content discovery: Automatically discovers documentation files while excluding test directories and large files
• Intelligent chunking: Header-aware markdown chunking for better semantic retrieval
• Code example extraction: Extracts and indexes code blocks for agentic RAG capabilities

🔄 Enhanced Repository Processing

• Dual processing pipeline: Simultaneously handles code analysis (Neo4j) and documentation storage (Supabase)
• Unified repository sources: Creates consistent source IDs for linking code and documentation
• Comprehensive metadata: Stores file paths, types, and repository information for better organization
• Error handling: Graceful partial processing with detailed reporting

🧪 Comprehensive Test Infrastructure

• E2E test suite: End-to-end tests for complete repository processing workflows
• Unit test coverage: Extensive testing for documentation processing functions
• Test utilities: Reusable database helpers and MCP client for consistent testing
• Environment validation: Tests verify all required services are properly configured

📁 Files Changed

• Core functionality: Enhanced src/utils.py with 500+ lines of documentation processing logic
• MCP integration: Updated src/crawl4ai_mcp.py to integrate documentation processing into repository parsing
• Test suite: Added comprehensive test infrastructure with E2E and unit tests
• Configuration: Updated pyproject.toml with new test dependencies and project structure

🚀 Benefits

1. Enhanced RAG capabilities: Repository documentation is now searchable and retrievable for better AI assistance
2. Jupyter notebook support: Seamlessly processes and indexes notebook content for documentation sites
3. Production ready: Comprehensive test coverage ensures reliability and maintainability
4. Extensible architecture: Clean separation of concerns allows for easy future enhancements

🔗 Integration Points

• Works seamlessly with existing Neo4j knowledge graph functionality
• Leverages established Supabase storage patterns
• Maintains compatibility with all existing MCP tools and workflows

🧪 Testing

• All new functionality is covered by both unit and E2E tests
• Tests validate integration with real Supabase and Neo4j instances
• Comprehensive test utilities ensure consistent testing patterns

This enhancement significantly expands the MCP server's capabilities, making it a comprehensive solution for both code analysis and documentation processing from GitHub repositories.