fix(llm): honor OpenAI's x-ratelimit-reset-* headers on 429s - #3508
Open
romanbsd wants to merge 1 commit into
Open
fix(llm): honor OpenAI's x-ratelimit-reset-* headers on 429s#3508romanbsd wants to merge 1 commit into
romanbsd wants to merge 1 commit into
Conversation
_rate_limit_retry_at only parsed the Retry-After header and the free-text error body, so a 429 without Retry-After fell back to blind exponential backoff instead of the wait OpenAI actually specified. Parse the x-ratelimit-reset-requests/-tokens headers (Go duration format, e.g. "6m0s") and wait for whichever budget clears later. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0184wdx18AyKn3amtvcqYRkU
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
_rate_limit_retry_atonly parsed theRetry-Afterheader and the free-text error body, so a 429 withoutRetry-After(e.g. OpenAI's daily RPD cap) fell back to blind exponential backoff instead of the wait OpenAI actually specified.x-ratelimit-reset-requests/x-ratelimit-reset-tokensheaders (Go duration format, e.g."6m0s") and wait for whichever budget clears later. Requests/tokens can reset at different times.Retry-Afterand free-text body parsing paths are unchanged.Test plan
uv run pytest tests/test_openai_compatible_response_hardening.py -q(11 passed)uv run ruff check/uv run ruff format --check/uv run ty checkon the changed filev0.9.1tag🤖 Generated with Claude Code
https://claude.ai/code/session_0184wdx18AyKn3amtvcqYRkU