This commit was merged in pull request #501.
This commit is contained in:
@@ -2,6 +2,7 @@
|
||||
|
||||
## Unreleased
|
||||
|
||||
- A reviewer under `agents/` can start without `CLAUDE.md`: `omitClaudeMd: true` in its frontmatter drops the file, a `SubagentStart` hook hands it the "Shared goal", "Prose" and "Vocabulary" sections, and `larv-review reviewer-header` names the project's principles file. `review-replay <pass> <model> --omit-claude-md` tests whether a pass's reviewer finds as much without it; principles-auditor is the first to pass.
|
||||
- Add `workflow-bench/advisor_bench.py`, a bench of the advisor tool on six archived L 1 and L 2 chunks. Sonnet 5.5 alone passed all six, as Opus 5.5 at medium did, for 41% less, and its advisor ran in one of six runs, so workers stay without it.
|
||||
- loop-claude's judge on an Opus 5.5 project now runs on Opus 5.5 at xhigh in every chunk, never at medium: in replays medium sometimes closed a chunk whose worker had asked a question the README or records answer, where xhigh quoted the answer. The judge never runs on Fable 5.2 either, since each Fable 5.2 rung replayed missed an interrupt. `judge-replay` now also replays each rung above the project's that a review climbs to, and reports what each misses.
|
||||
|
||||
|
||||
@@ -14,7 +14,6 @@
|
||||
|---|---|---|---|---|---|---|---|---|---|---|---|
|
||||
| 340 | 0.9.0 | | question | **Decide whether a reviewer may start without `CLAUDE.md` where its replay misses no more findings than an unchanged replay does.** | 2 | 2 | 3 | 5 | 4 | 1.4 by 5 | 1.7 |
|
||||
| 331 | 0.9.0 | | question | **Reword four decisions to expire when the rungs their replays tested change, not whenever a model joins the ladder.** | 1 | 1 | 1 | 1 | 2 | 1.4 by 2 | 0.9 |
|
||||
| 315 | 0.9.0 | | | **Start each reviewer under `agents/` without `CLAUDE.md`, and hand it the vocabulary, the prose rules and the project's decision titles.** | 4 | 2 | 3 | 7 | 4 | 1.4 by 6 | 2.0 |
|
||||
| 312 | 0.9.0 | | | **Research the tooling agents read, search and run commands with, and file an item for each tool that cuts tokens a replay shows keep quality.** | 1 | 2 | 1 | 2 | 3 | 1.4 by 3, 1.5 by 2 | 2.0 |
|
||||
| 325 | 0.9.0 | | | **Give this repo's test suite one command that runs it as README → Test says, prints the failing tests and pytest's summary line, and saves the whole log to a file whose path it prints.** | 3 | 2 | 2 | 5 | 3 | 1.4 by 3, 1.5 by 2 | 2.0 |
|
||||
| 305 | 0.9.0 | | | **Record with each archived verdict the claude-config commit that ran it, the raw tokens each model spent by kind, and each choice of the worker's that the human reversed, so a change to the setup can be judged before and after.** | 3 | 2 | 3 | 6 | 5 | 1.4 by 4, 1.2 by 3 | 1.8 |
|
||||
@@ -98,14 +97,6 @@ The architect's 🔀 answer on PR #493 (item 292): four decisions expire "when a
|
||||
|
||||
Recommendation: reword all four as above. They are decisions the repo held before item 292, so the rewording is lilleman's call.
|
||||
|
||||
### 315. Start each reviewer under `agents/` without `CLAUDE.md`, and hand it the vocabulary, the prose rules and the project's decision titles.
|
||||
|
||||
`omitClaudeMd: true` in an agent's frontmatter (Claude Code 2.1.271 or later) starts it without the user, project and local instruction files. About 77% of `CLAUDE.md` is the worker's: "Working loop", "Working with the codebase", "Git", "Handoffs", "Compact instructions". Over the archive, each 1,000 prefix tokens cost $31 across the six reviewers, so this saves about 1.9% of spend. A reviewer still needs "Vocabulary", "Prose" and the project's decision titles: put the first two in the agent bodies or a `SubagentStart` hook's `additionalContext`, and have `larv-review reviewer-header` print the titles.
|
||||
|
||||
Gate it per pass: keep it only where `review-replay` with the changed definition (through `--agents`) on 10 archived rounds finds what two replays of the unchanged reviewer find; the unchanged reviewer re-finds only 69 to 73% of its own findings, so one baseline doesn't show the noise. Revise the decision `rules/: CLAUDE.md holds the worker's rules that no file path can scope`. lilleman approved on 2026-11-11.
|
||||
|
||||
`review-replay` takes no `--agents` today, so the gate needs a mode for it. Claude Code 2.1.322 ignores `omitClaudeMd` for a main-session `claude --agent`, which is how `review-replay` runs a reviewer. It fires no `SubagentStart` hook there either. So the replay of the changed definition has to drop `CLAUDE.md` itself: the environment variable `CLAUDE_CODE_DISABLE_CLAUDE_MDS`, which the binary reads, does that. The replay must also hand the reviewer what the hook would add.
|
||||
|
||||
### 312. Research the tooling agents read, search and run commands with, and file an item for each tool that cuts tokens a replay shows keep quality.
|
||||
|
||||
lilleman, 2026-11-11: besides an output ceiling, keep evaluating better tooling. The token research of that day found tool results carried in context cost about 21% of spend, reads by subagents the most, and that the tools themselves move fast: deferred tool loading, output saved to files, code-execution over tools, LSP and repo-map navigation, structured test output. Item 231 tried a scout, an outline script and LSP in October and none kept every finding.
|
||||
|
||||
Reference in New Issue
Block a user