File items 398, 399 and 400
This commit is contained in:
@@ -6,12 +6,15 @@
|
||||
|
||||
`Bar = 0.1`
|
||||
|
||||
`Next ID = 398`
|
||||
`Next ID = 401`
|
||||
|
||||
## Items
|
||||
|
||||
| ID | Release | Blocked by | Exempt | Item | L | E | I | R | S | Moves | Score |
|
||||
|---|---|---|---|---|---|---|---|---|---|---|---|
|
||||
| 398 | 0.12.0 | | | **Make each reasonable fix an outside reviewer asks for on a PR trigger a reflection that changes the setup so review would have caught it, in this repo first.** | 2 | 2 | 3 | 5 | 3 | 1.1 by 6, 1.2 by 2 | 2.9 |
|
||||
| 399 | 0.12.0 | | | **Rerun the pass that raised a 🟡 when its fix changes what a test asserts or whether it runs.** | 2 | 2 | 3 | 5 | 3 | 1.1 by 6 | 2.2 |
|
||||
| 400 | 0.12.0 | | | **Forbid a test that decides at run time whether to check anything in `principles/technical-principles.md`, and point stability-reviewer's Tests checks at it.** | 1 | 2 | 3 | 4 | 2 | 1.1 by 5 | 2.0 |
|
||||
| 299 | 0.12.0 | | | **Replay the archived judge verdicts through code rules and a classifier trained locally on the archive, and file an item for each verdict kind one of them decides with no missed interrupt.** | 2 | 2 | 2 | 4 | 3 | 1.4 by 3 | 1.0 |
|
||||
| 311 | 0.12.0 | | | **Hand each worker's claude a Bash output ceiling that saves longer output to a file, and refuse a Read of a session transcript under `~/.claude/projects`.** | 2 | 2 | 3 | 5 | 3 | 1.4 by 3 | 1.0 |
|
||||
| 316 | 0.12.0 | | | **Launch comprehension seats as an agent type of their own under `agents/`, without `CLAUDE.md` and the skill and agent listings a general-purpose subagent carries.** | 2 | 2 | 2 | 4 | 3 | 1.4 by 3 | 1.0 |
|
||||
@@ -65,6 +68,48 @@
|
||||
|
||||
## Details
|
||||
|
||||
### 398. Make each reasonable fix an outside reviewer asks for on a PR trigger a reflection that changes the setup so review would have caught it, in this repo first.
|
||||
|
||||
Applies to any reviewer outside the review passes: a forge's auto-reviewer such as CodeRabbit, a human, or any other. When such a reviewer's feedback on a PR is reasonable and we fix it, we also ask why our setup 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.
|
||||
|
||||
Where the change goes, in this order of preference:
|
||||
1. This repo's core: the reviewers' agents, `larv-review`, the hooks and tools, so every project gains.
|
||||
2. The technical principles or review standards, where a rule was missing or too vague.
|
||||
3. The project's own settings or instructions (`config.toml`, `AGENTS.md`), only where the gap is that project's alone.
|
||||
|
||||
Where the cause is a gap in none of these, say so in the chunk's summary rather than inventing a change. File a change too big for the chunk as its own item (`~/.claude/CLAUDE.md` → "Working loop"). The reflection is part of answering the feedback, so `larv-review` §4 step 6 and §3 → "Other scales" are the places to start.
|
||||
|
||||
Touches:
|
||||
|
||||
- `skills/larv-review/SKILL.md`: `## 4. Gate` (small), `## 3. Passes` (small)
|
||||
- `CLAUDE.md`: `## Working loop` (small)
|
||||
|
||||
### 399. Rerun the pass that raised a 🟡 when its fix changes what a test asserts or whether it runs.
|
||||
|
||||
In a client project's pull request, stability round 1 raised a 🟡: an end-to-end payroll test passes on a used database. It proposed asserting the created row counts. The answer commit added that assertion behind a `test.skip` that runs when every count is zero. A broken payroll also creates zero rows, so a regression became a skip. No pass reviewed the fix, because a 🟡 fix reruns none (`skills/larv-review/SKILL.md` §3 → "Re-entry"). The forge's auto-reviewer found it.
|
||||
|
||||
Neither the gate nor the mutation run catches a weakened test, since a skipped test counts as passing. The rerun reviews only the answers (`review-findings.md`), and the cap of two rounds still ends the pass.
|
||||
|
||||
Revise the decision `review: a fix for a 🔴 reruns the pass that found it…` in `docs/decisions.md`. Its 2026-10-29 entry holds only "while 🔴 findings in later chunks, fixing code a 🟡 fix wrote, stay rare".
|
||||
|
||||
Touches:
|
||||
|
||||
- `skills/larv-review/SKILL.md`: `**Re-entry.**` (small)
|
||||
- `docs/decisions.md`: `## review: a fix for a 🔴 reruns the pass that found it, unless that pass is at its cap, and each pass whose row in larv-review §3's re-entry table the fix meets`
|
||||
|
||||
### 400. Forbid a test that decides at run time whether to check anything in `principles/technical-principles.md`, and point stability-reviewer's Tests checks at it.
|
||||
|
||||
Today the rule is only implied, by "fails when that behaviour breaks" and "states what it needs and gets it". Proposed bullet under the tests principle: "A test doesn't decide at run time whether to check anything: no conditional skip, early return, or catch around its assertions. A test that needs a state creates it, or fails and names what is missing. BANNED: `test.skip(created.every((count) => count === 0))`, since a broken payroll also creates zero rows. GOOD: check the precondition before the action, failing with its cause, then `expect(created).toEqual([1, 2, 1])`."
|
||||
|
||||
Add one line to section 11 of `agents/stability-reviewer.md` that points at the bullet.
|
||||
|
||||
Source: a client project's pull request, where a fix hid a regression behind a conditional skip.
|
||||
|
||||
Touches:
|
||||
|
||||
- `principles/technical-principles.md`: the tests bullet group, `A valuable test checks behaviour` (small)
|
||||
- `agents/stability-reviewer.md`: `### 11. Tests` (small)
|
||||
|
||||
### 299. Replay the archived judge verdicts through code rules and a classifier trained locally on the archive, and file an item for each verdict kind one of them decides with no missed interrupt.
|
||||
|
||||
The judge's LLM still decides three things: the verdict kind, the escalation it quotes, and whether a release is ready to cut (`docs/decisions.md` → `routing: loop-claude reads the items a chunk takes …`). This item replays the verdict kind. No single rule found so far separates interrupts: a "?" in the worker's final message appears in 48 interrupts and misses 66. A smaller LLM already failed the replay (`docs/decisions.md` → `routing: on a model judge-replay covered, …`: Sonnet returned another kind on 3 interrupts, Haiku missed 7). Untested are combined code rules, a decision table, and a small classifier trained and run on this machine on the archived verdicts (372 finished, 234 interrupt, 42 unfinished, 20 quoted). Run each offline, nothing sent to an outside service (goal 4), and count disagreements by kind; the bar is zero missed interrupts. A hosted decision model is out of scope, since it would send transcripts to an outside service.
|
||||
|
||||
Reference in New Issue
Block a user