Answer stability round 1: 0 🔴, 3 🟡 (1 misread); name the claimed-output file per round, run as the project runs tools, leave files untouched
This commit is contained in:
@@ -45,7 +45,7 @@ Before anything else, **read the technical principles** in the folder your promp
|
|||||||
|
|
||||||
6. **Assess reasonableness of usage paths**: Are there paths that exist but no real persona would use?
|
6. **Assess reasonableness of usage paths**: Are there paths that exist but no real persona would use?
|
||||||
|
|
||||||
7. **Check each claim about output against its run.** A doc line that says what a command, flag or error prints is true only if the real output says so. Where your prompt has a `Claimed output:` line, read that file, which holds the command and real output of each such claim. Report a claim the output doesn't bear out, such as an error that is said to name the fix and doesn't, and say which words are missing. Don't settle such a claim by reading code. A claim marked `not run` is a ❓ naming what would run it. A claim in your scope that the file doesn't hold is a ❓ too.
|
7. **Check each claim about output against its run.** A changed doc line that says what a command, flag or error prints is true only if the real output says so. Where your prompt has a `Claimed output:` line, that file holds each such claim's command and real output. Report a claim the output doesn't bear out, such as an error said to name the fix that doesn't, and name the missing words. Never settle one by reading code. A claim marked `not run`, or one you find that the prompt doesn't hand you a run of, is a ❓ naming the command that would run it.
|
||||||
|
|
||||||
## Your Output Format
|
## Your Output Format
|
||||||
|
|
||||||
|
|||||||
@@ -26,7 +26,9 @@ Run them in this order. A fix for a later check never breaks an earlier one.
|
|||||||
3. **Default to delete.** A line the reader does not need fails. Fix: **Delete** what the code, a type, a test name, the README or another rule already says. Fix: **Move** a choice made in one place to a comment there, one made in more places to `docs/decisions.md` with its title in `AGENTS.md` unless a project principle there covers it, and a goal to the README. A pointer standing where a definition belongs (the review standards' `comments.md` → "Links and pointers", "A pointer is not a definition") gets the fix **Move back**: inline the definition, and leave the reasoning where it is.
|
3. **Default to delete.** A line the reader does not need fails. Fix: **Delete** what the code, a type, a test name, the README or another rule already says. Fix: **Move** a choice made in one place to a comment there, one made in more places to `docs/decisions.md` with its title in `AGENTS.md` unless a project principle there covers it, and a goal to the README. A pointer standing where a definition belongs (the review standards' `comments.md` → "Links and pointers", "A pointer is not a definition") gets the fix **Move back**: inline the definition, and leave the reasoning where it is.
|
||||||
4. **Short.** Words that do not clearly help 1–3 fail. Fix: **Cut**.
|
4. **Short.** Words that do not clearly help 1–3 fail. Fix: **Cut**.
|
||||||
|
|
||||||
Also report a list whose order carries no meaning and is not sorted (the technical principles' "Deterministic order", in the folder your prompt's `Technical principles:` line names; without one, open your report by saying so), a sentence contradicting another, a claim the code shows false, a claim about what a command prints that the real output in the file your prompt's `Claimed output:` line names doesn't bear out, and a word used against `CLAUDE.md` → "Vocabulary".
|
Also report a list whose order carries no meaning and is not sorted (the technical principles' "Deterministic order", in the folder your prompt's `Technical principles:` line names; without one, open your report by saying so), a sentence contradicting another, a claim the code shows false, and a word used against `CLAUDE.md` → "Vocabulary".
|
||||||
|
|
||||||
|
Where your prompt has a `Claimed output:` line, that file holds the command and real output of each changed line that says what a command prints. Report a claim its output doesn't bear out, and name the missing words. A claim marked `not run` is a ❓ naming the command that would run it.
|
||||||
|
|
||||||
## Growth
|
## Growth
|
||||||
|
|
||||||
|
|||||||
@@ -74,11 +74,10 @@ Give a reviewer without Bash `git ls-files`'s output in its prompt, since some h
|
|||||||
|
|
||||||
**Reports.** Run `~/.claude/bin/larv-review reviewer-header <pass>` in the chunk's worktree, and open each prompt to an agent under `~/.claude/agents/` with what it prints; then say in a few lines what the change does and which files it touches. The command makes the chunk's review folder and writes the branch diff and the plan's listing into it. The header names that diff, the reviewer's full report, `<pass>-round-<n>.md`, in the folder, the folders of technical principles and review standards the project's config sets, the files of coding conventions where it lists any, the listing, and for architecture and stability the places too. For a reviewer whose definition starts it without `CLAUDE.md`, the header's last line names the file that holds the project principles and decision titles, which the reviewer reads first. For a relaunch one rung up, add `--rerun`: the report becomes `<pass>-round-<n>-rerun.md`, and the header names the report that asked. Before you answer a 🔴 or 🟡, read its entry: Grep the report for the finding's place, with the lines after it, rather than Read the whole report. rule-hook refuses a reviewer's Edit and MultiEdit, and any Write outside `~/.local/state/larv-review/`. Keep the folder after the merge: `review-replay` replays a round from the reports its prompt names, and `compress-archives` gzips each file 30 days after it last changed.
|
**Reports.** Run `~/.claude/bin/larv-review reviewer-header <pass>` in the chunk's worktree, and open each prompt to an agent under `~/.claude/agents/` with what it prints; then say in a few lines what the change does and which files it touches. The command makes the chunk's review folder and writes the branch diff and the plan's listing into it. The header names that diff, the reviewer's full report, `<pass>-round-<n>.md`, in the folder, the folders of technical principles and review standards the project's config sets, the files of coding conventions where it lists any, the listing, and for architecture and stability the places too. For a reviewer whose definition starts it without `CLAUDE.md`, the header's last line names the file that holds the project principles and decision titles, which the reviewer reads first. For a relaunch one rung up, add `--rerun`: the report becomes `<pass>-round-<n>-rerun.md`, and the header names the report that asked. Before you answer a 🔴 or 🟡, read its entry: Grep the report for the finding's place, with the lines after it, rather than Read the whole report. rule-hook refuses a reviewer's Edit and MultiEdit, and any Write outside `~/.local/state/larv-review/`. Keep the folder after the merge: `review-replay` replays a round from the reports its prompt names, and `compress-archives` gzips each file 30 days after it last changed.
|
||||||
|
|
||||||
**Claimed output.** Before the Product-owner or Prose pass launches, in each round, find the lines the diff adds or changes that say what a command, flag or error prints: "the error names the fix", "prints one row per task". A reviewer can't run anything, and reading code can't show that the output holds the words the line claims.
|
**Claimed output.** Before the Product-owner or Prose pass launches in a round, find the lines the diff adds or changes that say what a command, flag or error prints, such as "the error names the fix". In round 2, take only the lines the round's fixes changed. Those reviewers have no shell, and reading code can't show that an output holds the words a line claims.
|
||||||
|
|
||||||
- **Run.** For each claim, run its command in the chunk's worktree, through the project's container setup, with the input that triggers the output the line describes, such as the input that raises the error. Run only what changes nothing outside the worktree and sends nothing out; list any other claim as `not run: <why>`.
|
- **Run.** Run each claim's command in the chunk's worktree, the way the project runs its tools (its container setup, unless its config sets `tooling-on-host`), with the input that triggers the output the line describes, such as the input that raises the error. Run only a command that leaves every file as it was, in the worktree and outside it, and sends no data out. List any other claim as `not run: <why>`.
|
||||||
- **Hand over.** Write each claim with its file and line, the command, its exit code and its real output into `claimed-output.md` in the chunk's review folder. Add `Claimed output: <that path>` to each reviewer's prompt, the Product-owner and Prose reviewers'; with no claim, leave the line out.
|
- **Hand over.** Write each claim into `claimed-output-round-<n>.md` in the chunk's review folder, `<n>` the round's number: its file and line, the command, the exit code and the real output, or `not run: <why>`. Add `Claimed output: <that path>` to the prompts of the Product-owner and Prose reviewers. With no claim, write no file and add no line.
|
||||||
- **Round 2.** Run again only the claims the round's fixes changed.
|
|
||||||
|
|
||||||
**Precedent, then ask** — for the full scan:
|
**Precedent, then ask** — for the full scan:
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user