[🔥AUDIT🔥] review: fix the clusterer example that promises cross-file grouping the path rule forbids - #336
Merged
Merged
Conversation
…e that promises cross-file grouping the path rule forbids The prompt's 'Group across lines' example listed 'its test' among the anchors one defect is flagged at, but a test lives in a separate _test.go, and the rules section says 'Group only candidates that share a path' - so the example promises a grouping the rule forbids. Found by the reviewer itself on the webapp v1.12.0 bump PR (webapp#41398). Replace 'its test' with a same-file anchor (the call site) and state the cross-file limit explicitly beside the example, so the prompt promises only what the pipeline delivers. Relaxing the path rule for foo.go/foo_test.go pairings stays future work: dedup.ts's tier-1 comment already prices cross-file merging as needing its own strictly higher calibration, and the clustering metrics v1.12.0 started recording are the evidence that decision wants.
🦋 Changeset detectedLatest commit: 41007b5 The changes in this PR will be included in the next version bump. This PR includes changesets to release 1 package
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
khan-actions-bot
requested review from
a team,
jeresig and
somewhatabstract
and removed request for
a team
August 11, 2026 15:03
jwbron
changed the title
Contributor
Review Guidancegithub-actions (1 file)
|
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
jwbron
added a commit
that referenced
this pull request
Aug 11, 2026
…locking-only re-reviews (#340) 🖍 _This is an audit!_ 🖍 ## What Two coupled changes, one install: 1. **Bumps this repo's installed PR reviewer from `review-v1.12.0` to `review-v1.13.0`.** 3-way merge (base = v1.12.0 release source, ours = installed copy, theirs = v1.13.0 release source) with one trivial conflict at the KHAN/ACTIONS LOCAL OVERRIDE comment that rides the checkout `ref:`, then `gh aw compile review`. `source:` and the lib checkout `ref:` stay in lockstep at `review-v1.13.0`; the lock diff is purely version refs plus recompile hashes. 2. **Opts this repo into the new dial**: the ROUTING re-review line becomes `re-review scoped blocking-only` (scoped was already enabled). Repeat reviews keep the full scoped roster, so blocking recall is unchanged; only blocking findings post inline, and validated non-blocking findings collapse to one line each in the review body. First full reviews, divergence-tripwire re-arms, and guard-degraded full runs still post everything. ## What v1.13.0 brings over v1.12.0 - **#328**: pr-level (pathless) claims respect open-thread suppression (stricter `PR_LEVEL_FLOOR` paying for the missing anchor), and long pr-level body folds collapse past 400 chars. - **#329**: the `blocking-only` re-review modifier this PR enables, with the cap-overflow neutral wording and the set-membership modifier parse. - **#336**: the clusterer prompt example no longer promises cross-file grouping the same-path rule forbids. ## Configuration audit No other consumer configuration is needed: v1.13.0 adds no imports, no safe outputs, and no `.github/aw/` config files (verified against the v1.12.0→v1.13.0 diff; the prompt delta is 9 lines). The modifier is consumer-side ROUTING parse in the same release, so the bump and the opt-in belong in one PR: on v1.12.0 the extra field would not parse, and without the ROUTING edit the bump is behavior-neutral. Part of the review-bot feedback effort; the adjudication work (#332/#333/#334) lands in the next release and a follow-up bump. Author: jwbron Reviewers: jeresig, somewhatabstract Required Reviewers: Approved By: Checks: ⌛ 1 check is pending, ✅ 4 checks were successful Pull Request URL: #340
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.
🖍 This is an audit! 🖍
What
One prompt-text correction in the
claim-clustereragent: the 'Group across lines' example listed 'its test' among the anchors one defect is flagged at, but a test lives in a separate_test.go(a differentpath), and the rules section says 'Group only candidates that share apath' — so the example promised a grouping the rule forbids. The example now uses a same-file anchor (the call site) and states the cross-file limit explicitly beside itself.Why
Found by the reviewer itself on the webapp v1.12.0 bump PR (webapp#41398 discussion); issues are disabled in this repo, so this PR is the tracking artifact. A prompt whose example contradicts its rule invites the model to resolve the tension unpredictably; better the example promise only what the pipeline delivers.
Actually relaxing the path rule for
foo.go/foo_test.gopairings stays future work:dedup.ts's tier-1 comment already prices cross-file merging as needing its own strictly higher calibration, and the clustering metrics v1.12.0 started recording (clusterRejections, merge rates) are exactly the evidence that decision wants.Tests
Prompt-text only; no lib code changes. The live A/B on this PR is the behavioral check.