Repository navigation
fix: eval scores acceptance lines by case id and fails on a nonzero acceptance exit - #73
Merged
Merged
Conversation
…ro exit of the acceptance run With several reviewers run.ts tags each line with the case id and the reviewer name. The eval strips the longest reviewer name that ends the tag, keeps the worst outcome per case, scores a case a reviewer did not report as MISSING, and fails checks 1 and 2 when the acceptance run exits nonzero. A hold for a human on a clean control is still a false alarm.
alsoknownaswill
force-pushed
the
pub-eval-suffix
branch
from
November 3, 2026 07:50
aca446e to
a8e5cd8
Compare
alsoknownaswill
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The eval harness tagged each acceptance line with the reviewer name when several reviewers run, so lines did not match case ids and scored as missing.
The eval now strips the longest reviewer name that ends the tag, keeps the worst outcome per case, and scores a case a reviewer did not report as missing. Checks 1 and 2 also fail when the acceptance run exits nonzero. A hold for a human on a clean control is still a false alarm, and a size hold never counts as correct.
Tests cover the suffix parsing, worst-outcome ordering, missing cases and the exit code.