feat(reviewing-prs): fix-forward finding routing — native severity as the blocker bit - #12
Merged
Merged
Conversation
… the blocker bit ROUTE flips the burden of proof (agent-harness direction): the engine's critical/high (P1 class) is the blocker bit → FIX NOW; every finding below it defaults to the new LOG bin (was TOO SMALL's argued deferral) and lands on the standing tech-debt issue. Promoting a non-blocker to an in-loop fix is now the exception that needs a stated reason. RE-REVIEW gains a statelessness clause: re-review rounds re-flag logged findings; match by file+substance, never fix/re-log/re-count them, and exit on 'no NEW blocker', not a clean report. SELF-MERGE wording aligned; SKILL.md tech-debt sink updated; spec gets a 2026-07-13 Revision Note. Motivation: SD-5 dogfood routed 7/7 findings FIX NOW across 3 engine rounds — the old default spends momentum on non-blockers.
5 tasks
SSFSKIM
added a commit
that referenced
this pull request
Jul 15, 2026
… tail Adversarial review of the entrypoint restructure found two defects the file-based protocol introduced and one doc drift: - The bootstrap told the worker to 'Use doperpowers:reviewing-prs' without pinning where the protocol resolves from. In the detached review worktree the workspace .agents/skills is PR-controlled, so a PR could ship a same-named skill replacing the merge rubric. The bootstrap now binds SKILL_FILE (dispatcher-owned absolute path), instructs the worker to open it unconditionally, and forbids workspace resolution. - SKILL.md ended with unrendered '---- PR brief ----' template sections that nothing renders (dispatch renders the bootstrap, not SKILL.md). Removed; the protocol now points at the dispatch prompt for briefs and manifests. - operation-manual.md still described the pre-#12 self-merge clause ('only low findings'); it now matches the protocol's non-blocker wording. Regression asserts pin the SKILL_FILE binding, the spoofing rejection, the tail's absence, and the manual wording.
SSFSKIM
added a commit
that referenced
this pull request
Jul 15, 2026
* refactor(reviewing-prs): make skill the worker protocol * fix(reviewing-prs): pin dispatcher-owned protocol, drop dead template tail Adversarial review of the entrypoint restructure found two defects the file-based protocol introduced and one doc drift: - The bootstrap told the worker to 'Use doperpowers:reviewing-prs' without pinning where the protocol resolves from. In the detached review worktree the workspace .agents/skills is PR-controlled, so a PR could ship a same-named skill replacing the merge rubric. The bootstrap now binds SKILL_FILE (dispatcher-owned absolute path), instructs the worker to open it unconditionally, and forbids workspace resolution. - SKILL.md ended with unrendered '---- PR brief ----' template sections that nothing renders (dispatch renders the bootstrap, not SKILL.md). Removed; the protocol now points at the dispatch prompt for briefs and manifests. - operation-manual.md still described the pre-#12 self-merge clause ('only low findings'); it now matches the protocol's non-blocker wording. Regression asserts pin the SKILL_FILE binding, the spoofing rejection, the tail's absence, and the manual wording.
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.
Problem
The review loop's routing default spends momentum on non-blockers. Recorded instance: the SD-5 dogfood run (
docs/doperpowers/2026-07-10-codex-workers-shakedown.md) routed 7/7 findings FIX NOW → 7 commits → 3 engine rounds on a single PR. The old TOO SMALL bin required arguing a triple condition (valid AND non-blocking AND momentum cost) to defer anything, so a diligent worker defaults to fixing everything.Change
Adopts agent-harness's burden-of-proof direction (
core-beliefs#8: minimal blocking gates, fix-forward), using the engine's native severity as the blocker bit — no re-tagging instructions, per the minimal-prompting rule:Validation Evidence
tests/reviewing-prs/test-review-dispatch.sh— all tests passedtests/reviewing-prs/test-review-engine.sh— all greentests/reviewing-prs/test-land-dispatch.sh— all tests passed