Include reason in relevance check failures#1584
Merged
dgageot merged 1 commit intodocker:mainfrom Feb 4, 2026
Merged
Conversation
rumpl
previously approved these changes
Feb 4, 2026
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Review Summary
✅ Approved - No bugs found in the changed code.
This PR successfully adds reason tracking to relevance check failures. The implementation is solid:
- The new
RelevanceResultstruct properly encapsulates both criterion and reason - The refactored
parseJudgeResponsecorrectly returns structured results with proper fallback handling - Concurrent processing in
CheckRelevanceis safe with pre-allocated indexed results - Error handling is consistent across all code paths
- Empty reason strings are handled gracefully with conditional formatting
- All tests have been updated to verify the new behavior
The changes improve debuggability by providing explanations for failed relevance checks without introducing any logic errors or bugs.
dgageot
dismissed stale reviews from github-actions[bot] and rumpl
via
6bc54fa
dgageot
force-pushed
the
relevance-mismatch
branch
from
65c5973 to
6bc54fa
Compare
When running cagent eval with relevance checks, the LLM judge now provides a reason explaining why each check passed or failed. This reason is now captured and displayed in the output, making it easier to understand why a relevance check failed. Output format changed from: ✗ relevance: <criterion> To: ✗ relevance: <criterion> (reason: <explanation>) Assisted-By: cagent
dgageot
force-pushed
the
relevance-mismatch
branch
from
6bc54fa to
7b17fdb
Compare
rumpl
approved these changes
Feb 4, 2026
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 running cagent eval with relevance checks, the LLM judge now provides a reason explaining why each check passed or failed. This reason is now captured and displayed in the output, making it easier to understand why a relevance check failed.
Output format changed from:
✗ relevance:
To:
✗ relevance: (reason: )
Assisted-By: cagent