feat: add retry logic for chat completion streaming#1381
Open
PortRoyale wants to merge 1 commit intoelie222:mainfrom
Open
feat: add retry logic for chat completion streaming#1381PortRoyale wants to merge 1 commit intoelie222:mainfrom
PortRoyale wants to merge 1 commit intoelie222:mainfrom
Conversation
Add retry with exponential backoff for transient errors in chatCompletionStream. This helps with smaller models (8B) that may occasionally produce schema mistakes. Changes: - Add retry loop with max 2 retries and exponential backoff (1s, 2s) - Detect JSON parse errors (SyntaxError, "Unexpected token") - Detect tool call/schema validation errors - Detect transient network errors - Improve error logging with error type classification The existing createGenerateObject and createGenerateText functions already have retry logic via withLLMRetry and withNetworkRetry. This brings similar resilience to the streaming chat completion path. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
|
@PortRoyale is attempting to deploy a commit to the Inbox Zero OSS Program Team on Vercel. A member of the Team first needs to authorize it. |
|
|
![cubic-dev-ai[bot]](https://avatars.githubusercontent.com/in/1082092?s=60&v=4){kind=small}
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add retry with exponential backoff for transient errors in
chatCompletionStream. This helps with smaller models (8B) that may occasionally produce schema mistakes or encounter transient network issues.Changes
isTransientNetworkError)Motivation
The existing
createGenerateObjectandcreateGenerateTextfunctions already have retry logic viawithLLMRetryandwithNetworkRetry. This brings similar resilience to the streaming chat completion path.When using smaller local models (like 8B parameter models via Ollama), occasional JSON malformation or schema validation failures can occur. Adding retry logic allows the system to recover gracefully from these transient failures.
Test plan
🤖 Generated with Claude Code