core: smarter retry backoff for Cerebras rate limits#42
Merged
kevint-cerebras merged 1 commit intokevint-cerebras:devfrom Jan 29, 2026
Merged
core: smarter retry backoff for Cerebras rate limits#42kevint-cerebras merged 1 commit intokevint-cerebras:devfrom
kevint-cerebras merged 1 commit intokevint-cerebras:devfrom
Conversation
Replace fixed retry schedule with exponential backoff + jitter that retries until the next hour boundary when rate limits reset. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Replace fixed retry schedule with exponential backoff + jitter that retries until the next hour boundary when rate limits reset.
The current retry uses a flat [10s, 10s, 10s, 15s, 15s] schedule and gives up after 5 tries — so you're back to staring at an error in the middle of being rate limited.
This replaces that with exponential backoff + jitter that keeps retrying until the next hour rolls over (when limits actually reset). First retry is fast (2s), then it backs off naturally. If the server sends a retry-after header, we respect it instead of ignoring it.
Also catches transient network errors (connection resets, timeouts, socket hangups) and 500/502/503s that the old code just gave up on.
Two files, no new dependencies.