Client or integration
Direct HTTP/API client
Area
Google Antigravity provider adapter
Summary
google-antigravity provider cannot use gemini-3.7-flash. The adapter speaks /v1beta/models/{id}:generateContent, but the model exists only on the /v1internal:loadCodeAssist Code Assist surface (the one agy uses). Result: 404 Requested entity was not found when the model is set as the provider's default, and 400 "not supported when using Codex with a ChatGPT account" when requested by name (router sends it to the wrong provider because it isn't matched to antigravity).
Reproduction
ocx provider edit google-antigravity --default-model gemini-3.7-flash
curl -X POST http://127.0.0.1:10100/v1/chat/completions -d '{"model":"gemini-3.7-flash","messages":[{"role":"user","content":"hi"}]}'
- Observe
404 Requested entity was not found (upstream gateway: model only on the Code Assist surface).
- Alternatively request
gemini-3.7-flash by name with the antigravity default restored to gemini-3.6-flash: the router matches no antigravity pattern and sends the request to the ChatGPT pool → 400 model is not supported when using Codex with a ChatGPT account.
Expected behavior
gemini-3.7-flash routes to google-antigravity and completes (same as agy native, where the model id is gemini-3.7-flash-high).
Version
opencodex 2.11.0
Operating system
macOS
Provider and model
google-antigravity / gemini-3.7-flash
Logs or error output
404: Requested entity was not found (v1beta path); 400: The 'gemini-3.7-flash' model is not supported when using Codex with a ChatGPT account (router fallback to ChatGPT pool).
Screenshots and supporting files
n/a
Redacted configuration
n/a
Checks
Client or integration
Direct HTTP/API client
Area
Google Antigravity provider adapter
Summary
google-antigravity provider cannot use gemini-3.7-flash. The adapter speaks
/v1beta/models/{id}:generateContent, but the model exists only on the/v1internal:loadCodeAssistCode Assist surface (the one agy uses). Result:404 Requested entity was not foundwhen the model is set as the provider's default, and400 "not supported when using Codex with a ChatGPT account"when requested by name (router sends it to the wrong provider because it isn't matched to antigravity).Reproduction
ocx provider edit google-antigravity --default-model gemini-3.7-flashcurl -X POST http://127.0.0.1:10100/v1/chat/completions -d '{"model":"gemini-3.7-flash","messages":[{"role":"user","content":"hi"}]}'404 Requested entity was not found(upstream gateway: model only on the Code Assist surface).gemini-3.7-flashby name with the antigravity default restored to gemini-3.6-flash: the router matches no antigravity pattern and sends the request to the ChatGPT pool →400 model is not supported when using Codex with a ChatGPT account.Expected behavior
gemini-3.7-flash routes to google-antigravity and completes (same as
agynative, where the model id isgemini-3.7-flash-high).Version
opencodex 2.11.0
Operating system
macOS
Provider and model
google-antigravity / gemini-3.7-flash
Logs or error output
404: Requested entity was not found(v1beta path);400: The 'gemini-3.7-flash' model is not supported when using Codex with a ChatGPT account(router fallback to ChatGPT pool).Screenshots and supporting files
n/a
Redacted configuration
n/a
Checks