mirror of
https://github.com/openai/codex.git
synced 2026-11-18 22:20:48 +00:00
Treat model-not-found provider errors as terminal failures (#56445)
## Why Provider errors with code `model_not_found` should end the turn immediately and preserve the provider's message instead of triggering retries. ## What changed - Recognize `model_not_found` in HTTP 400, 403, and 404 responses and in streamed `error` and `response.failed` events. - Preserve the provider message and any available HTTP status, and expose `modelNotFound` through the app-server protocol and generated schemas and SDK types. ## Testing Add coverage for HTTP classification, statusless stream errors, and terminal failures without retries across HTTP, SSE, and WebSocket responses. Verify that `thread/read` preserves the error reported by the live notification. GitOrigin-RevId: 88f824ac03c8c9669915b1e40c67b76c08326fbe
This commit is contained in:
@@ -23,6 +23,7 @@ enum CodexErrorInfoWire {
|
||||
RateLimitExceeded,
|
||||
FlexUnavailable,
|
||||
ServerOverloaded,
|
||||
ModelNotFound,
|
||||
CyberPolicy,
|
||||
BioPolicy,
|
||||
MisalignmentPolicyViolation,
|
||||
|
||||
Reference in New Issue
Block a user