Backend: thread on_fallback callback through analysis chain (gemini_service → agents → analysis_service → handlers). The handler sends a 'model_fallback' WebSocket message exactly once per analysis when the primary model is unavailable. Frontend: handle 'model_fallback' WS message and show a dismissible yellow toast at the bottom of the screen with an 8-second auto-dismiss. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| analysis_service.py | ||
| auth_service.py | ||
| email_service.py | ||
| gemini_service.py | ||
| knowledge_base_service.py | ||
| llamaparse_service.py | ||
| pdf_service.py | ||
| reference_docs.py | ||
| storage_service.py | ||