fix: handle LLM and graph errors in weather agent executor - #142
Merged
pdettori merged 1 commit intoMar 3, 2026
Merged
Conversation
The execute() method had no error handling around get_graph() and graph.astream(). When the LLM call fails (bad API key, model unavailable, network error), the unhandled exception left the A2A task stuck in "submitted" state with no artifacts and no error message — making failures invisible to both tests and users. Now graph initialization and LLM execution errors are caught and reported as failed tasks with the actual error message, matching the existing pattern for MCP connection failures. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> Signed-off-by: Paolo Dettori <dettori@us.ibm.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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The execute() method had no error handling around get_graph() and graph.astream(). When the LLM call fails (bad API key, model unavailable, network error), the unhandled exception left the A2A task stuck in "submitted" state with no artifacts and no error message — making failures invisible to both tests and users.
Now graph initialization and LLM execution errors are caught and reported as failed tasks with the actual error message, matching the existing pattern for MCP connection failures.
Summary
Related issue(s)
(Optional) Testing Instructions
Fixes #