fix(llm): eradicate gemini-1.5-flash 404 from production

Fork: 0

yangyangxie / cortex-hub

Browse code fix(llm): eradicate gemini-1.5-flash 404 from production - Implemented substring normalization for Gemini models in config.py - Forced redirection of 1.5-flash to 2.5-flash in RAG service - Fixed model name resolution in provider factory to handle suffixed names - Normalized health checks to use 2.5-flash baseline - Removed hardcoded 1.5-flash defaults from STT/TTS providers and agent loop master
1 parent 696b630 commit 0dcd9bf72f02fa26162e38ae8b15e683fda54d26 Antigravity AI authored 4 hours ago

Browse code

- Implemented substring normalization for Gemini models in config.py
- Forced redirection of 1.5-flash to 2.5-flash in RAG service
- Fixed model name resolution in provider factory to handle suffixed names
- Normalized health checks to use 2.5-flash baseline
- Removed hardcoded 1.5-flash defaults from STT/TTS providers and agent loop

master

1 parent 696b630 commit 0dcd9bf72f02fa26162e38ae8b15e683fda54d26

Antigravity AI authored 4 hours ago

Patch

Unified Split

Showing 11 changed files

Ignore Space Show notes View ai-hub/app/api/schemas.py

Ignore Space Show notes View ai-hub/app/app.py

Ignore Space Show notes View ai-hub/app/config.py

Ignore Space Show notes View ai-hub/app/core/orchestration/agent_loop.py

Ignore Space Show notes View ai-hub/app/core/orchestration/scheduler.py 0 → 100644

Ignore Space Show notes View ai-hub/app/core/providers/factory.py

Ignore Space Show notes View ai-hub/app/core/providers/stt/gemini.py

Ignore Space Show notes View ai-hub/app/core/providers/tts/gemini.py

Ignore Space Show notes View ai-hub/app/core/services/rag.py

Ignore Space Show notes View ai-hub/requirements.txt

Ignore Space Show notes View frontend/src/features/agents/components/AgentDrillDown.js

Show line notes below