fix(hub-ws): skip no-op reconfigure to prevent agent recreate loop - #642
Open
cunzhiwang wants to merge 1 commit into
Open
fix(hub-ws): skip no-op reconfigure to prevent agent recreate loop#642cunzhiwang wants to merge 1 commit into
cunzhiwang wants to merge 1 commit into
Conversation
When MCP passes env vars (LLM_BASE_URL / LLM_API_KEY / LLM_MODEL_NAME) on every execute_task call, onExecute unconditionally invoked configure(...) with the same values. Each call created a new config object, retriggering the useEffect that disposes and recreates the agent, racing with the in-flight execute() and causing an infinite retry loop from the MCP client side. onExecute now only calls configure when incomingConfig actually differs from the current config (shallow diff over incoming keys). Non-MCP paths (settings UI) are unaffected. Closes alibaba#639
|
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When MCP passes env vars (LLM_BASE_URL / LLM_API_KEY / LLM_MODEL_NAME) on every execute_task call, onExecute unconditionally invoked configure(...) with the same values. Each call created a new config object, retriggering the useEffect that disposes and recreates the agent, racing with the in-flight execute() and causing an infinite retry loop from the MCP client side.
onExecute now only calls configure when incomingConfig actually differs from the current config (shallow diff over incoming keys). Non-MCP paths (settings UI) are unaffected.
Closes #639
What
Brief description of changes.
Closes #(issue)
Type
Testing
npm run cipassesRequirements / 要求