Repository navigation
fix(generation): retry a 429 instead of aborting the pipeline - #558
Open
pcbeingused333 wants to merge 1 commit into
Open
pcbeingused333 wants to merge 1 commit into
pcbeingused333 wants to merge 1 commit into
Conversation
The openai and litellm backends already back off and retry 5xx errors and timeouts, but a RateLimitError raised ToolError at once. Treat it like the other transient errors. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The OpenAI and LiteLLM generation backends back off and retry on 5xx errors and timeouts, but a
RateLimitError(HTTP 429) raisedToolErroron the first attempt, so one rate-limited request stopped the whole pipeline step.A 429 now takes the same path as the other transient errors: it is logged and the loop sleeps with the existing backoff before the next attempt. No new retry policy; after
retriesattempts the result is<error>, as for 5xx.Adds
test_rate_limit_is_retried_instead_of_abortingfor the LiteLLM backend and a newtest_openai_backend.pyfor the OpenAI one (a fake client returns 429 then a completion). Both fail onmain(the first attempt raisesToolError) and pass with the change; the existing generation tests still pass. Not run against a live API.This change was prepared with the assistance of an AI agent (Claude), on behalf of the PR author.