openai/codex
1
0
Fork 0
mirror of https://github.com/openai/codex.git synced 2026-10-24 18:18:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

Treat model-not-found provider errors as terminal failures (#56445)

Browse Source 
## 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:
Charlie Marsh
2026-10-23 11:43:14 +00:00
committed by copyberry
parent ca9d103f39
commit 60adfa8513
39 changed files with 190 additions and 67 deletions
Download Patch File Download Diff File Expand all files Collapse all files
sdk/python/src/openai_codex/generated/v2_all.py
+1
View File
@@ -512,6 +512,7 @@ class CodexErrorInfoValue(str, Enum):
rate_limit_exceeded = "rateLimitExceeded"
flex_unavailable = "flexUnavailable"
server_overloaded = "serverOverloaded"
model_not_found = "modelNotFound"
cyber_policy = "cyberPolicy"
misalignment_policy_violation = "misalignmentPolicyViolation"
too_many_denials = "tooManyDenials"