[🔥AUDIT🔥] review: bump installed reviewer to review-v1.13.0; enable blocking-only re-reviews - #340
Conversation
…wer to review-v1.13.0; enable blocking-only re-reviews 🖍 This is an audit! 🖍 Bumps this repo's installed PR reviewer from review-v1.12.0 to review-v1.13.0 (3-way merge, one trivial conflict at the local override comment beside the checkout ref; gh aw compile review). The lock diff is purely version refs plus recompile hashes. v1.13.0 over v1.12.0: #328 (pr-level claims respect open-thread suppression; long body folds collapse), #329 (the blocking-only re-review modifier), #336 (clusterer example fix). And opts this repo into the new dial: ROUTING's re-review line becomes 'scoped blocking-only'. Repeat reviews keep the full scoped roster (blocking recall unchanged) but post only blocking findings inline; validated non-blocking findings collapse to one line each in the review body. First full reviews, tripwire re-arms, and guard-degraded full runs still post everything. No other consumer configuration is needed: v1.13.0 adds no imports, safe outputs, or config files.
|
Review Guidancegithub-actions (2 files)
Common patterns2 files: Version bump: every occurrence of the reviewer lib ref/source tag changes from review-v1.12.0 to review-v1.13.0 (comment headers, - GH_AW_WORKFLOW_SOURCE: "Khan/actions/workflows/review/review.md@review-v1.12.0"
+ GH_AW_WORKFLOW_SOURCE: "Khan/actions/workflows/review/review.md@review-v1.13.0" |
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
| # unchanged) but post only blocking findings inline; validated non-blocking | ||
| # findings collapse to one line each in the review body. First full reviews, | ||
| # tripwire re-arms, and guard-degraded full runs still post everything. | ||
| re-review scoped blocking-only |
There was a problem hiding this comment.
thought (non-blocking): "Blocking recall unchanged" is vacuous for the advisory-only half of the roster kept on re-reviews. The stated justification for keeping the full scoped roster is that blocking recall is unchanged, but that argument only applies to reviewers that can produce blocking findings (holistic, completeness, test-adequacy, plus the correctness pass). first-principles, conventions, and documentation are advisory-only — checked routing-config.ts: blocking-only 'keeps the configured depth's roster' and only changes the posting surface, and the re-review line offers no per-reviewer dial — so on every re-review those three run at full cost to contribute at most one line each in a
Details
fold.A sketch, not a committable replacement:
If the collapsed one-liners from the advisory trio are judged worth their re-review compute, say so in the ROUTING comment; otherwise consider an upstream lib tweak (skip reviewers whose labels are all non-blocking when blocking-only applies) or fold this into the existing 'graduate to flip-gated' criterion, since blocking-only removes the noise cost but not the compute cost that criterion was watching for.
1 participant
🖍 This is an audit! 🖍
What
Two coupled changes, one install:
review-v1.12.0toreview-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 checkoutref:, thengh aw compile review.source:and the lib checkoutref:stay in lockstep atreview-v1.13.0; the lock diff is purely version refs plus recompile hashes.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
PR_LEVEL_FLOORpaying for the missing anchor), and long pr-level body folds collapse past 400 chars.blocking-onlyre-review modifier this PR enables, with the cap-overflow neutral wording and the set-membership modifier parse.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.