fix(agent): retry transient LLM HTTP errors#2768
Open
afjcjsbx wants to merge 1 commit intosipeed:mainfrom
Open
fix(agent): retry transient LLM HTTP errors#2768afjcjsbx wants to merge 1 commit intosipeed:mainfrom
afjcjsbx wants to merge 1 commit intosipeed:mainfrom
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
📝 Description
Fixes LLM request retry handling for transient provider HTTP errors. Previously, OpenRouter/OpenAI-compatible
Status: 500responses could fail the agent turn immediately when no model fallback candidate was available. This PR reuses the existing provider error classifier in the main LLM retry loop so transient HTTP/server errors are retried according to the configured retry policy.🗣️ Type of Change
🤖 AI Code Generation
🔗 Related Issue
Fixes #629
📚 Technical Context (Skip for Docs)
500,502, and503to retryable failover reasons. The main LLM retry loop now uses that classifier too, so single-provider runs can retry transient provider failures instead of dropping the task.🧪 Test Environment
📸 Evidence (Optional)
Click to view Logs/Screenshots
☑️ Checklist