Make the paired evaluator harness-agnostic - #6
Merged
Conversation
The runner now takes skill, tasks, harness binary, and opaque model id with no Codex special case. Adapters own argv, listing, and auth copy. Live traces stay in gitignored .eval-output/. Co-authored-by: Cursor <cursoragent@cursor.com>
Relative and home paths now resolve before recording, binaries are found in standard locations without --harness-bin, --force replaces a prior output directory, and invocations emit 15s heartbeats under a 300s default timeout. Co-authored-by: Cursor <cursoragent@cursor.com>
Retain the dated structural audit as a local reference so the working tree is clean for the quality run. Co-authored-by: Cursor <cursoragent@cursor.com>
Color-choice fixtures cannot score the React review suite. Reject mismatched calibration at plan time and ship a shared-dimension v2 dataset. Co-authored-by: Cursor <cursoragent@cursor.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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
.eval-output/.~/and relatives; harness discovery checks common install locations; live runs emit 15s heartbeats and default to a 300s timeout.tasks/react-best-practices-v2.jsonl).Test plan
python3 -m unittest discover -s tests -v(71 tests)skills/skill-eval-loop/scripts/healthcheck.sh(run after push if CI does not).eval-output/dumps are not in the diff (onlyREADME.md)