docs(agents): record PR-supersession and constant-change review discipline - #1909
Merged
Merged
Conversation
…pline Two rules from mistakes this session actually made and corrected, per the per-session lane split agreed with the other concurrent sessions (peer 3 took verification discipline in #1907; peer 2 has gate/merge mechanics; host 1 has close-time diff comparison and noema concurrency; host 2 has CI failure diagnosis). - Narrowing a PR does not carry its delta. #1871 was closed in favor of #1877 plus #1879; both successors were green, but neither carried the coverage/docstring delta, leaving main's required 100% gate broken until #1883 recovered it. "Each piece works" and "the pieces together cover the original's scope" are different questions. - Compare content, not ancestry. main mixes squash and merge commits (last 200: 153 single-parent, 47 two-parent, counted directly), so `git merge-base --is-ancestor` gives false negatives for squashed deltas and false positives for reverted merge-commit deltas. - Never endorse a timeout or retry constant on a model-invocation path without reading docs/product-goal-directive.md section 8, which accepts more than two hours per model and states speed is not a core consideration. #1889/#1890/#1892 each capped a model step at 900s on real multi-hour-hang evidence and were all reverted (#1891, #1895). Every PR number, the section-8 quotes, the parent-count distribution, and the 100% gate values were verified against the repository directly. An earlier draft of the timeout bullet cited a section number that does not exist and attributed a sentence to that file which appears only in #1891's PR body; both were caught by grepping rather than trusting the summary that introduced them, and that failure is recorded in the text. Full suite: 2883 passed, 1 skipped. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
|
Warning Review limit reachedNext included review available in 49 seconds. View limit detailsLimit details: You’ve used the included review currently available. You've used all free OSS reviews for now. Wait for the free limit to reset to keep reviewing this public repository. Review configuration: ⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Team Run ID: 📒 Files selected for processing (2)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
#1906 landed "Verifying a 'superseded — closing' claim", which already covers ancestry-vs-content in more depth than my draft's version did (three-dot diff, `git grep -lF`, `git show origin/main:<path>`, and the squash/merge-commit mix that makes `git merge-base --is-ancestor` unreliable in both directions). Removed my duplicate bullet and pointed at that section instead. What remains here is the part a single-PR closure check does not cover: a PR split across several successors fails differently, because no individual successor looks wrong. Added the union question explicitly, and kept the end-to-end check — git-level commands show whether text moved, not whether behaviour is restored. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
…ession-and-constant-review
seonghobae
deleted the
docs/agents-pr-supersession-and-constant-review
branch
September 5, 2026 08:49
This was referenced Sep 5, 2026
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
My lane in the per-session split agreed with the other four concurrent sessions (peer 3 took verification discipline in #1907; peer 2 has gate/merge mechanics; host 1 has close-time diff comparison and noema concurrency; host 2 has CI failure diagnosis). Both rules below come from mistakes this session actually made and corrected today, not from general advice.
main's required 100% gate stayed broken until fix(ci): close the admission-controller coverage/docstring gap on main #1883 recovered it. "Each piece works" and "the pieces together cover the original's scope" are different questions.mainmixes squash and merge commits, sogit merge-base --is-ancestoris unreliable in both directions.Verification
Every factual claim was checked against the repository rather than against the summary that introduced it:
gh pr view.docs/product-goal-directive.mdsection 8 quoted verbatim after grepping the file.git log origin/main -200 --format=%p | awk '{print NF}'→ 153 single-parent, 47 two-parent.fail_under = 100/fail-under = 100confirmed inpyproject.toml.An earlier draft cited a
§8.5–8.6that does not exist in that file and attributed a "timeout defaults to null" sentence to it that appears only in #1891's PR body. Both were wrong and were caught by grepping. That failure is recorded in the added text itself, since it is the same error class the section warns about.Rebased onto #1907; the two AGENTS.md sections sit side by side with no overlap.
🤖 Generated with Claude Code