Answer prose round 1: 1 🔴, 2 🟡; a fix for a 🟢, ❓ or prose finding reruns no pass whatever it changes, rows follow the pass table, decision title follows
This commit is contained in:
@@ -12,7 +12,7 @@ Decisions live in `docs/decisions.md`:
|
||||
- loop-claude: each project's model lives in `~/.claude/loop-claude-models.json`, which only loop-claude writes
|
||||
- review: a pass gets at most three rounds per chunk; instead of a fourth, the run asks the human
|
||||
- review: a reviewer or comprehension seat that rules the work below standard may ask to rerun once, one rung up, in the same round; the ruling that stands is an escalation trigger for the worker, never for the judge
|
||||
- review: a fix for a 🔴 or 🟡 reruns the pass that found it and each pass whose trigger names fixes like it; from round 2 a pass reviews only the answers to its last round's findings and any other pass's fix that re-entered it; a fix for a 🟢, a ❓ or a prose finding reruns none
|
||||
- review: a fix for a 🔴 or 🟡 reruns the pass that found it and each pass whose row in `larv-review` §3's re-entry table the fix meets; from round 2 a pass reviews only the answers to its last round's findings and any other pass's fix that re-entered it; a fix for a 🟢, a ❓ or a prose finding reruns none
|
||||
- review: the comprehension check records how hard a project is to read and blocks no merge: a paired ruling against the last measured commit where the architecture pass ran, and the four-seat scoring run, once when an item names the floor and twice on one head when a release's items run out
|
||||
- review: a project decision may suspend the comprehension check for the plan items it names
|
||||
- review: a project decision may opt every chunk out of the architect, the product-owner pass or the comprehension check, and a project opting out of the comprehension check voids code health
|
||||
|
||||
+3
-1
@@ -72,12 +72,14 @@ A reviewer's relaunch gets the report that asked and confirms or dismisses each
|
||||
|
||||
Valid while the ladder orders its rungs by competence.
|
||||
|
||||
## review: a fix for a 🔴 or 🟡 reruns the pass that found it and each pass whose trigger names fixes like it; from round 2 a pass reviews only the answers to its last round's findings and any other pass's fix that re-entered it; a fix for a 🟢, a ❓ or a prose finding reruns none
|
||||
## review: a fix for a 🔴 or 🟡 reruns the pass that found it and each pass whose row in `larv-review` §3's re-entry table the fix meets; from round 2 a pass reviews only the answers to its last round's findings and any other pass's fix that re-entered it; a fix for a 🟢, a ❓ or a prose finding reruns none
|
||||
|
||||
2026-10-08, lilleman, replacing the 2026-09-30 rule that every fix, a nit's included, re-enters review. Serves goal 1.4. An audit of the four costliest archived chunks (2026-10-08) found nearly every finding that mattered in a pass's first round; later rounds mostly re-checked the last fix, reworded what an earlier round wrote, or contradicted another round on the same line. A round 2 caught real bugs only where a fix changed behaviour, so stability still reruns on every fix that does, and security on every fix that opens an untrusted-input boundary or touches authn/authz, secrets or crypto. Valid while round-2 reviews of nit and prose fixes keep changing nothing a user would notice.
|
||||
|
||||
2026-10-13, lilleman through todo item 97, implemented by claude: from round 2 a pass reviews only how the chunk answered its previous round, each fix and each dismissal with its reason, and reports only one that is plainly wrong or worse than the change it answered. A fix from another pass that re-enters it is still reviewed as a first round would review it, limited to its lines. Reviewing all that changed had a reviewer find new gaps in each round's fixes, so a pass ran to its cap. Serves goals 1.4 and 1.5. Valid while round-2 findings outside a round's answers keep changing nothing a user would notice.
|
||||
|
||||
2026-10-21, todo item 120: SKILL.md §3 moved the "a fix, only where …" clauses from the pass table into one re-entry table; the rule is unchanged.
|
||||
|
||||
## review: the comprehension check records how hard a project is to read and blocks no merge: a paired ruling against the last measured commit where the architecture pass ran, and the four-seat scoring run, once when an item names the floor and twice on one head when a release's items run out
|
||||
|
||||
2026-10-08, lilleman. Serves goals 1.1 and 1.4. Two independent four-seat runs moved up to 0.4 on near-identical code, so a fall within that noise forced rounds that changed nothing (PR #224). A seat reading both versions judges the difference on the same material, so the noise the versions share cancels. No conventional significance level lets a sign test settle with four votes, so the human chose a lead of two votes over every other ruling, same included. Two seats that agree settle it, so a PR that leaves the reading as it was costs two seats. A third seat alone can never settle it, so the third and fourth launch together. The human chose the last measured commit on the architect's finding that with a merge base as the base, chunks without an architecture pass, and a suspended restructure's steps, could each lower comprehension unseen. Reading the default branch one merged change at a time keeps the rule working for merge commits and squash merges alike. The scoring run also runs on a chunk shipping an item that names the floor, so the chunk that lifts a project to the floor can prove it. A chunk that removes a release's last item without shipping it runs the scoring run too, so no release ends unmeasured, unless `todo.md` marks that release renamed in a `## Renamed` section (`bin/todo_table.py` → `renames`). Valid while seats reading both versions agree more often than two absolute runs do.
|
||||
|
||||
@@ -28,7 +28,7 @@ Follow `~/.claude/CLAUDE.md` → "Git, commits, and PRs". Never commit to the de
|
||||
|
||||
## 3. Passes
|
||||
|
||||
A pass is one kind of review, a row of the table, named by its first column. Its trigger says when it first runs, on the chunk's change; "Re-entry" says when a fix reruns it. Its reviewer reports the findings.
|
||||
A pass is one kind of review, a row of the table, named by its first column. Its trigger says when it first runs, on the chunk's branch; "Re-entry" says when a fix reruns it. Its reviewer reports the findings.
|
||||
|
||||
| Pass | Reviewer | Trigger |
|
||||
|------|----------|----------------------------------------|
|
||||
@@ -70,19 +70,18 @@ Give a reviewer without Bash the branch diff and `git ls-files`'s output in its
|
||||
- **Cap.** A pass takes at most three rounds per chunk. Instead of a fourth, list what is open and ask the user. For the auto-reviewer, ask before the push that would summon its fourth, and hold the fixes unpushed until the answer.
|
||||
- **Answer.** A yes grants that pass one more round, after which the ask repeats; a no leaves the PR unmerged.
|
||||
|
||||
**Re-entry.** A fix is a change no pass has seen. A round's fixes re-enter together: run, in table order, every pass that a row below names for any of them, a done pass included, then §4. A pass at its cap gets "Round cap" → "Cap"'s ask instead.
|
||||
**Re-entry.** A fix is a change no pass has seen. A fix for a 🟢, a ❓ or a prose finding reruns no pass, whatever it changes. A round's fixes for 🔴 and 🟡 findings re-enter together: run, in the pass table's order, every pass that a row below names for any of them, a done pass included, then §4. A pass at its cap gets "Round cap" → "Cap"'s ask instead.
|
||||
|
||||
| The fix | Reruns |
|
||||
|---------|--------|
|
||||
| answers a 🔴 or 🟡 of any pass but prose | that pass |
|
||||
| changes code, config or tests | Principles |
|
||||
| changes behaviour: what the code or its tests do | Stability |
|
||||
| answers a 🔴 or 🟡 of a pass other than prose | that pass |
|
||||
| carries an architectural decision | Architecture |
|
||||
| changes code, config or tests | Principles |
|
||||
| opens an untrusted-input boundary or touches authn/authz, secrets or crypto | Security, unless the full scan reruns on it |
|
||||
| has an override that the hook logged | Overrides |
|
||||
| answers only a 🟢, a ❓ or a prose finding | no pass |
|
||||
| made rule-hook log an override | Overrides |
|
||||
| changes behaviour: what the code or its tests do | Stability |
|
||||
|
||||
Each row a fix meets adds its pass; the last row adds none. Prose never reruns, so a comment or doc edit in a fix adds nothing. Example: a fix for a stability 🟡 that changes code and a comment reruns Stability and Principles, and the comment reruns nothing more.
|
||||
A fix meets every row it fits. Prose has no row, so a comment or doc edit inside a fix reruns nothing. Example: a fix for a stability 🟡 that changes code and a comment reruns Principles and Stability.
|
||||
|
||||
**What a round reviews.** An agent under `~/.claude/agents/` reviews the branch in round 1. From round 2 it reviews only the answers to its last round's findings, and each fix from another pass that re-entered its pass. Prompt it with the path of its last round's report and each finding's answer: the fix's diff, or the reason it was dismissed. Give it each other pass's fix as `git diff <the commit before that fix> <the fix's commit>`, since the fixes may be unpushed, with the finding it answered. It reports only an answer that is plainly wrong or worse than the change it answered, so its pass converges in its second round. Other reviewers review the branch as their tool does.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user