fix(0.12.1): retry 429 / 5xx in OpenAI-compatible backend#19
Merged
Conversation
…ckend
When tcloud router returned 429 mid-canonical-eval (legal-agent persona 3
of 36), the runtime stream threw BackendTransportError and the eval
caught it but reported chars=0 with composite=0% — looking like an agent
quality problem instead of a transient rate-limit cascade.
Add `BackendRetryPolicy` to `createOpenAICompatibleBackend`:
- 5 attempts default with exponential backoff (1s → 30s, ±25% jitter)
- Retries 408 / 425 / 429 / 500 / 502 / 503 / 504
- Hard failures (401, 403, 404) propagate immediately
- Honors AbortSignal so callers can still cancel mid-retry
- Drains failed response bodies to free connections
- Set `retry: { maxAttempts: 1 }` to opt out
Closes the failure mode where legal-agent passed personas 1-2 with
real 4-6K-char responses, then every subsequent persona reported
chars=0 because the retry policy was missing.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
When tcloud router returned 429 mid-canonical-eval (legal-agent persona 3 of 36), the runtime stream threw `BackendTransportError` and the eval caught it but reported `chars=0` with `composite=0%` — looking like an agent-quality problem instead of a transient rate-limit cascade.
Adds `BackendRetryPolicy` to `createOpenAICompatibleBackend`:
Test plan