Fail fast on permanent eval sampler API errors - #263
Open
sylvesterkaczmarek wants to merge 3 commits into
Open
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Stop the eval samplers from retrying permanent API failures forever.
Both
ResponsesSamplerandChatCompletionsSamplercurrently put every exception other thanBadRequestErrorinto an unbounded exponential-backoff loop. That includes non-retryable API status failures such as authentication, permission, not-found, and unprocessable-request errors.Fixes #262.
Fix
Both samplers now:
BadRequestErrorbehavior;APIConnectionErrorwith the existing exponential backoff;APIStatusErrorvalues;Chat Completions still retries its intentional empty-success-response condition through a dedicated internal exception, preserving that existing behavior without making arbitrary
ValueErrorinstances retryable.Regression coverage
Adds tests for both sampler implementations verifying that representative permanent status failures are surfaced immediately and do not invoke
time.sleep.The retry delay and retryable-status behavior are otherwise unchanged.