- Add detailed debug logging throughout the codebase to track model and provider selection
- Fix OllamaProviderHandler to accept optional api_key parameter for cloud models
- Add logging in main.py, handlers.py, providers.py, and config.py
- Add catch-all endpoint for invalid routes with helpful error messages
- Create DEBUG_GUIDE.md with comprehensive documentation
- Enhance error messages to show available providers/rotations/autoselect

Debug logging now shows:
- Request path and provider ID
- Available configurations
- Provider config and handler selection
- Model selection process
- Rate limiting application
- Request/response details

This helps diagnose issues with model and provider selection.