fix(ai): retry transient model stream failures - #424
Closed
prvnsmpth wants to merge 2 commits into
Closed
Conversation
prvnsmpth
commented
Aug 20, 2026
Contributor
- Retry provider-confirmed transport failures once before substantive content is emitted, preventing transient disconnects from failing chats or duplicating output.
- Classify retryability explicitly per provider while leaving HTTP status retries to SDKs, avoiding deterministic-error replays and retry amplification.
- Persist usage from failed attempts and add unit and integration coverage for classification, recovery, and single-message persistence.
- flag transport-level provider errors explicitly - retry once before substantive stream content and persist usage - cover provider classification and stream recovery behavior
- cover Anthropic Bedrock connection failures - recognize raw httpx stream failures alongside botocore errors - add provider classification coverage
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.