Repository navigation
fix: mcpchecker task timeout, status mapping, and redaction prompt - #121
Merged
Merged
Conversation
- eval.yaml: use correct `defaultTaskLimits.timeout` field instead of
`defaultTaskTimeout` which mcpchecker silently ignored, causing tasks
to run with no timeout (edge-case-handling ran 23 minutes)
- aggregate_mcpchecker.py: distinguish agent execution errors from
judge failures in v1alpha2 output so crashes map to "error" status
(and "not_evaluated" in the summary) instead of "failed"
- sensitive-data-redaction.yaml: rewrite prompt to be bounded like
tool-correctness ("for each tool, invoke it once") instead of
open-ended ("invoke several tools"), which caused incomplete
agent responses with smaller models
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
defaultTaskLimits.timeoutfield instead ofdefaultTaskTimeoutwhich mcpchecker silently ignored — tasks ran with no timeout (edge-case-handling ran 23 minutes instead of 5)"error"status ("not_evaluated"in the summary) instead of"failed"Test plan
behavioral-eval-summary.jsonis created inreports/with correct three-state breakdown:pass=1 fail=1 not_evaluated=1🤖 Generated with Claude Code