Answer stability round 1: rerun the scoring run every later architecture round, judge applicability from the diff too, and seat the architect in a whole-round rerun

This commit is contained in:
2026-10-04 17:32:23 +02:00
parent 12f743c629
commit e99d640b51
5 changed files with 7 additions and 9 deletions
+1 -1
View File
@@ -2,7 +2,7 @@
## Unreleased
- larv-review's principles audit reads only the files under `~/.claude/principles/` that apply to the project, each file's `Applies to` line saying what it covers; the summary names each file left out. After its first round, the architecture pass reruns only the reviewers whose findings the fixes answer, unless the fixes carry an architectural decision.
- larv-review's principles audit reads only the files under `~/.claude/principles/` that apply to the project, launching a file's auditor when unsure. A file's `Applies to` line says what it covers; one without the line covers every project. The summary names each file left out. After its first round, the architecture pass reruns the scoring run and only the reviewers whose 🔴 or 🟡 the fixes answer, unless the fixes carry an architectural decision.
- When `loop-claude`'s judge rules a chunk unfinished, the resumed worker is shown the passage the judge quoted as the work remaining. A loop started before this change exits 1 at its next reload; rerun it.
- larv-review's architecture pass and full security scan get short names, `Architecture` and `Full scan`. Each round's commit is titled with its pass's name in lower case: `Answer full scan round 1: …`.
- larv-review's comprehension floor now says, without another file open, what the scoring run measures. A project's `docs/decisions.md` keeps the last scoring run's scores, and a later run scoring below them blocks the merge until fixed. After three rounds larv-review asks you; an unattended run leaves the PR unmerged with the question. A PR under the floor that scores no lower than the last run merges once you decide to ship. A decision in `docs/decisions.md` that lets every chunk ship under the floor counts as yours. A project without those scores gets them at its next scoring run.
+1 -1
View File
@@ -1,6 +1,6 @@
# Claude Code configuration
My personal `~/.claude`, version controlled: `CLAUDE.md` and `AGENTS.md` for instructions, the words under `CLAUDE.md` → "Vocabulary"; `agents/` and `skills/`; `principles/` for what the reviewer agents hold every project to; `docs/` for decisions; `settings.json` for the harness and `.claude/settings.json` for the harness inside this repo; `CHANGELOG.md` and `todo.md`; the tools in `bin/`; and `workflow-bench/`, the scripts and prompts of the 2026-09-30 bench of larv-review.
My personal `~/.claude`, version controlled: `CLAUDE.md` and `AGENTS.md` for instructions, the words under `CLAUDE.md` → "Vocabulary"; `agents/` and `skills/`; `principles/` for what the reviewer agents hold projects to; `docs/` for decisions; `settings.json` for the harness and `.claude/settings.json` for the harness inside this repo; `CHANGELOG.md` and `todo.md`; the tools in `bin/`; and `workflow-bench/`, the scripts and prompts of the 2026-09-30 bench of larv-review.
## Goals
+1 -1
View File
@@ -1,6 +1,6 @@
# Logging
Applies to an application that writes logs.
Applies to code that writes logs.
## Levels
-2
View File
@@ -1,7 +1,5 @@
# Purpose and goals of our principles
Applies to every project.
1. Efficiently and sustainably deliver technical solutions with fewer bugs that are easier to resolve.
2. Make our technical solutions easier to maintain and further develop.
+4 -4
View File
@@ -51,10 +51,10 @@ Give a reviewer without Bash the branch diff and `git ls-files`'s output in its
**Round cap.**
- **Round.** A round is one launch of a pass's reviewer: the first, each re-entry, and the rerun after the architect returns Stage 0 questions ("Architecture" below).
- **Architecture round.** The architecture pass's first round is the architect (unless skipped), the principles audit and the scoring run. A later round relaunches only the reviewers whose findings its fixes answer, or the whole round where the fixes fire the pass's trigger.
- **Architecture round.** The architecture pass's first round is the architect (unless skipped), the principles audit and the scoring run. A later round relaunches the scoring run and each reviewer whose 🔴 or 🟡 its fixes answer, or the whole round, the architect included, where the fixes fire the pass's trigger by more than shipping the release's last item.
- **Auto-reviewer.** The external auto-reviewer (§4) is a pass of its own, each review it posts a round.
- **Count.** Close each round with one commit that holds the round's fixes and is titled `Answer <pass> round <n>: …`, `<pass>` being the pass's name in lower case, such as `full scan`. A round that changed nothing gets an empty commit (`git commit --allow-empty`). Push the commits when §4 runs next, where there is a remote. A pass's count is the highest `<n>` among titles holding `Answer <pass> round <n>:` in `git log origin/<default branch>..HEAD` after a `git fetch`, or in `git log <default branch>..HEAD` with no remote. The auto-reviewer's count is the number of its reviews on the PR.
- **Later rounds.** From round 2, prompt an agent under `~/.claude/agents/` with the previous round's findings verbatim and what changed since: `git diff <the commit the previous round reviewed> HEAD`, since the fixes may be unpushed.
- **Later rounds.** From round 2, prompt an agent under `~/.claude/agents/` with its own last round's findings verbatim and what changed since: `git diff <the commit that round reviewed> HEAD`, since the fixes may be unpushed.
- **Done.** A pass is done when its latest round leaves no 🔴 or 🟡 standing: none was reported, or each was shown factually wrong, declined, filed, or named under the bar per "Findings". Resolve that round's 🟢s and ❓s per "Findings" too.
- **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.
@@ -81,7 +81,7 @@ Launch systems-architect: review the system as a whole entered through this chan
- **Stage 0 questions returned**: relay them to the user, record the answers in the README, re-run once.
- **BLOCK** → confirm with the user first when the restructure materially reshapes their PR; until confirmed, no later pass runs.
Then the principles audit, each auditor over the whole project: one principles-auditor for the README's goals, and one per file in `~/.claude/principles/` whose `Applies to` line the project meets, judged from the README and `git ls-files`. Unsure → launch it. Name each file left out, and why, in the summary.
Then the principles audit, each auditor over the whole project: one principles-auditor for the README's goals, and one per file in `~/.claude/principles/` whose `Applies to` line the project meets, judged from the README, `git ls-files` and the branch diff. A file without the line applies to every project. Unsure → launch it.
Then the comprehension floor, which the scoring run measures. Four simulated readers — Junior A, Mid A, the maintainability senior and the inherited architect — each read the whole project, not the diff, and score it from 1 to 10 overall and on four dimensions: Navigation, Locality, Shape and Self-sufficiency. A seat's overall may not exceed its lowest dimension by more than 1. Each score is the mean of the four seats, to two decimals. Launch the seats per `~/.claude/skills/comprehension-panel/SKILL.md` → "The scoring run".
@@ -132,4 +132,4 @@ 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, 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, 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, decisions recorded (file paths), `todo.md`/`CHANGELOG.md` updated, and any 🔀 escalation left for the user.