Reflect on each outside reviewer's fix and change the setup so review would have caught it
CI / tests (pull_request) Successful in 3m10s

This commit is contained in:
2026-11-18 09:49:13 +01:00
parent fbdc6124df
commit 232327d893
3 changed files with 25 additions and 2 deletions
+6
View File
@@ -18,6 +18,12 @@ How work proceeds in any repo, unless the repo's `AGENTS.md` says otherwise. The
- **Ask, don't guess.** Three choices are always the human's: a goal; a release, meaning the items planned into it and when it is cut; and a change to loop-claude's routing ladder, its rungs included. Any other rule that asks the human's approval reserves that choice too. Ask about a reserved choice. For any other choice, first check whether the goals already answer it. If they nearly do, propose a change to the goals and show how it answers this case: an answer settles one question, a goal settles every question like it. Otherwise take the option you would recommend, and record it with its reason: in the item's detail, or, where it governs later work, as the next sentence says. A recommendation you can give a reason for is not a guess. Ask only where you have no recommendation. Write every answer once, where it belongs, never only in chat: a goal in the goals file, a working rule in `AGENTS.md`, a standing choice in a comment at the one place it governs, or in `docs/decisions.md` once made in more than one place. When an answer holds a goal and a choice, write the goal in the goals file, and record as a choice only what the goal leaves open.
- **Bench a syntax with the people who write it.** Before a new or changed spelling of something users read or write ships — markdown, HTML, a config key, a CLI flag — a panel of fresh-context readers, seated as those users from the goals file's `## Audience`, picks it.
- **Implement the simplest change that solves the item, and ship it with `/larv-review`.** Whenever a test can check the change, write that test first and see it fail. Take its expected values from the item, never from the code. larv-review's reviewers hold the change to the technical principles, and a finding against one names it. Read a file in the principles folder the project's config sets (`~/.claude/bin/project-config principles` prints it) only when the item changes it, a finding or a record you write names it, or you decline a finding.
- **Change the setup for each reasonable fix an outside reviewer asked for on a PR.** An outside reviewer is anyone beyond larv-review's passes: a forge's auto-reviewer, a human. When you fix its comment, ask why our review didn't catch it first, and change the setup so it would; a fix that only answers the comment leaves the same gap open for the next chunk. Put the change in the first place that fits:
1. This repo's core: the reviewers' agents, `larv-review`, the hooks and tools, so every project gains.
2. The technical principles or the review standards, where a rule was missing or too vague.
3. The project's own config or `AGENTS.md`, only where the gap is that project's alone. A client's `AGENTS.md` changes by a proposal of its own, as above.
In this repo the change is a fix of the chunk. In another project, file places 1 and 2 as an item with `todo-item add`, run in `~/code/claude-config`, describing the gap without the client's name, code or comment text. File a change too big for the chunk as its own item. Where the cause is a gap in none of these places, say so in the chunk's summary rather than inventing a change.
- **Remove a finished item from the plan, and revise any decision that cites it.** If the repo publishes something others consume — a package, an image, an API — reword the item for them and move it to `CHANGELOG.md` under `## Unreleased`. A changelog is for the public, never for the next agent. Otherwise delete it; git history is the record. `~/.claude/bin/todo-item finish <ID>` removes the item with its detail, and adds the bullet you pass with `--changelog <bullet>`; it refuses while a decision cites the item. A plan kept in Jira takes no bullet, since the issues' history is its changelog: `finish` there refuses `--changelog`. A chunk finishes its items as it merges, through `chunk-pr merge --finish <ID>`, which takes the same flags (`larv-review` §5).
- **Releases are the human's.** The version bump and the publishing credentials are theirs, whatever another rule says. Prepare everything else, so cutting a release is one decision.
- **Open each plan item or ticket with a bold one-sentence tagline**, so the taglines alone say what a release holds. The tagline states the target state, checkable when done: an imperative verb plus what holds afterwards. A present-tense fact reads as the current state and doesn't say anything about what to do. Add "today X" only where the direction is otherwise ambiguous. GOOD: `**Accept undefined in MetadataValue and drop such keys on output.**` BANNED: `MetadataValue accepts undefined; such keys are dropped on output`.
+17
View File
@@ -2570,3 +2570,20 @@ Read most (opens and searches):
- `bin/failure.py` 1
- `bin/markdown_section/test_markdown_section.py` 1
- `bin/run-tests` 1
## Reading cost, chunk 4655673a30a9, finished 2026-11-17T11:46:22Z
111449 new input tokens before the first commit.
Read most (opens and searches):
- `bin/review_replay/test_review_replay.py` 6
- `README.md` 2
- `bin/review_replay/main.py` 2
- `bin/review_replay/replay.py` 2
- `docs/decisions.md` 2
- `CHANGELOG.md` 1
- `bin/review_replay/omit_comparison.py` 1
- `bin/rung_replay/archive.py` 1
- `bin/rung_replay/search.py` 1
- `bin/rung_replay/test_rung_replay.py` 1
+2 -2
View File
@@ -195,7 +195,7 @@ Launch prose-reviewer with what the diff touched and every section this review c
3. The forge's checks: `chunk-pr merge` waits for them to pass (§5 step 4). A red check is a finding.
4. No CI configured → the gate is local tests only; note it in the summary.
5. The local tests green → mark the PR ready with `~/.claude/bin/chunk-pr ready '<final title>'`, which sets the title as it marks the PR ready.
6. **External auto-reviewer**, when the repo has one — its config file (`.coderabbit.yaml` and the like), or its comments on earlier PRs; none → skip it, say so. Marking the PR ready is what summons it. Wait up to **10 minutes** for its first review, checking about once a minute; nothing by then → note it in the summary and carry on, never waiting twice. Its rounds, §3 → "Round cap". Once it has reviewed, each later return here before its cap, after a fix re-entered per §3, waits up to **5 minutes** for its re-review of the new commit.
6. **External auto-reviewer**, when the repo has one — its config file (`.coderabbit.yaml` and the like), or its comments on earlier PRs; none → skip it, say so. Marking the PR ready is what summons it. Wait up to **10 minutes** for its first review, checking about once a minute; nothing by then → note it in the summary and carry on, never waiting twice. Its rounds, §3 → "Round cap". Each finding of its you fix as reasonable ends with the setup change `~/.claude/CLAUDE.md` → "Working loop" asks for; the same holds for a human's comment on the PR. Once it has reviewed, each later return here before its cap, after a fix re-entered per §3, waits up to **5 minutes** for its re-review of the new commit.
## 5. Goal alignment, then merge
@@ -214,4 +214,4 @@ Launch prose-reviewer with what the diff touched and every section this review c
## 6. Wrap up
Summarize: PR URL and final state, every reviewer's verdict, rounds per pass, passes skipped, principles files left out with why, findings fixed vs answered vs declined vs open — each answer with what settles it, each decline with its reason, a 🟡's with the goal or technical principle it rests on — CI status, rule overrides with their rulings, decisions recorded (file paths), `todo.md`/`CHANGELOG.md` updated, and any 🔀 escalation left for the user.
Summarize: PR URL and final state, every reviewer's verdict, rounds per pass, passes skipped, principles files left out with why, findings fixed vs answered vs declined vs open — each answer with what settles it, each decline with its reason, a 🟡's with the goal or technical principle it rests on — CI status, rule overrides with their rulings, decisions recorded (file paths), the setup change each outside reviewer's fix led to, or that none fit, `todo.md`/`CHANGELOG.md` updated, and any 🔀 escalation left for the user.