Files
gstack/test/pstack-sections.test.ts
Garry Tanandcapy-ai[bot] c1900088d5 v1.91.272.0 feat(skills): absorb pstack's blast radius, transcript recall, vet-the-number and design-twice as lazy passes (#3500)
* feat(skills): absorb pstack's blast radius, transcript recall, vet-the-number and design-twice as lazy sections

/investigate gains sections/blast-radius.md (the one safety fact, the five-rung
evidence ladder, look where grep stops, confirmed and cleared risks apart) with a
Phase 4 pointer, and the shared-premise red flag before the 3-strike rule.
/context-restore is carved for the first time: on NO_CHECKPOINTS, sections/transcripts.md
mines this workspace's own transcripts (host stores declared in hosts/*.ts and rendered
by TRANSCRIPT_SOURCES / TRANSCRIPT_DISCOVERY), a fixed 7-day window, never another
project's folder, subagents return only findings, redaction before anything leaves,
git and gh verify every artifact, a status-tagged brief. /benchmark is carved for the
first time: sections/vet-the-number.md asks the seven questions before Phase 5 reports
a comparison. /plan-eng-review gains sections/design-twice.md (a second structurally
distinct shape compared on interface depth, the eight design red flags), bound by the
autoplan methodology snapshot alongside review-sections.md.

Ideas from pstack (Lauren Tan, MIT), rewritten in gstack's words; NOTICE.md. Garry,
2026-10-26: "Do it, send". Guards: carve-guards entries and measured lines, eleven
plan-eng-review pins re-measured, periodic carve-section-loading cases for the two new
carves, free tests with a fixture transcript.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(pstack-c1): fold design-twice into Section 1 of the eng review section, per-host transcript table, fixture and slice-cap repairs

The remote free run reported nine failures in seven files, all from this
branch: four tests encode plan-eng-review's one companion section
(eng-scope-entry-ap, autoplan-methodology-names, plan-review-cases,
review-checklists), so the design-twice pass now lives inside Section 1 of
sections/review-sections.md with the skeleton, manifest and
bin/gstack-autoplan-snapshot.ts back at main; the Codex render of
context-restore named ~/.claude/ through the all-hosts transcript table, so
{{TRANSCRIPT_SOURCES}} renders this host's row only; the transcript fixture
is declared in FREE_FIXTURES; and the two new periodic cases took the census
to 39 slices, so evals-periodic.yml's eval-slices max-parallel goes 38 -> 40.
Pins: 11 plan-eng-review re-pins at +2,896; maxSizeRatio 1.2400 (measured
1.2389); Codex gpt-5.4 overlay 159,588 bytes.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix: pre-landing review fixes

The discovery block takes the none branch from hosts/*.ts's transcripts
declaration instead of a host-name fallthrough, and the resolver header says
where each half lives; the T2 subagent brief frames the transcript as data,
not instructions; the test asserts table/block agreement per host, imports
CAPY_NO_TRANSCRIPTS, and drops the fixture-shape case nothing reads.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* docs: ADDING_A_HOST.md lists the optional transcripts HostConfig field

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-10-27 09:59:09 +00:00

115 lines
6.3 KiB
TypeScript

/**
* pstack absorb (GSTA-116 plan, items 6 and 9): benchmark's vet-the-number
* section and plan-eng-review's design-twice pass. Pins the carve shape
* (manifest ids, STOP pointers, where each pointer sits) and the tokens each
* section must carry; prose is not pinned.
*/
import { describe, expect, test } from 'bun:test';
import * as fs from 'node:fs';
import * as path from 'node:path';
import { CARVE_GUARDS } from './helpers/carve-guards';
const ROOT = path.resolve(import.meta.dir, '..');
const read = (rel: string) => fs.readFileSync(path.join(ROOT, rel), 'utf8');
describe('benchmark carve: vet the number', () => {
const skeleton = read('benchmark/SKILL.md');
const section = read('benchmark/sections/vet-the-number.md');
const manifest = JSON.parse(read('benchmark/sections/manifest.json')) as { skill: string; sections: Array<{ id: string; file: string }> };
test('one section, registered, pointed to at the top of Phase 5 before any comparison is written', () => {
expect(manifest.skill).toBe('benchmark');
expect(manifest.sections.map(s => s.id)).toEqual(['vet-the-number']);
expect(CARVE_GUARDS.benchmark!.expectedSections).toEqual(['vet-the-number.md']);
const phase5 = skeleton.indexOf('### Phase 5: Comparison');
const stop = skeleton.indexOf('> **STOP.**');
expect(skeleton.indexOf('## Arguments')).toBeLessThan(stop);
expect(stop).toBeGreaterThan(phase5);
expect(stop).toBeLessThan(skeleton.indexOf('If baseline exists, compare current metrics against it'));
expect(skeleton.match(/> \*\*STOP\.\*\*/g)).toHaveLength(1);
expect(skeleton).toContain('sections/vet-the-number.md');
expect(skeleton).toMatch(/\*\*Vet every number before reporting it\.\*\*/);
});
test('the seven questions, the one-run ballpark rule, the 11% arithmetic, alternating runs, and the inconclusive verdict', () => {
expect(section).toContain('## Vet the number');
const questions = ['**Why not double?**', '**Was it tuned?**', '**Did it break a limit?**', '**Did it error?**', '**Does it reproduce?**', '**Does it matter?**', '**Did it even happen?**'];
let last = -1;
for (const q of questions) {
const at = section.indexOf(q);
expect(at, q).toBeGreaterThan(last);
last = at;
}
expect(section).toContain('Name the limiter');
expect(section).toMatch(/one run,\s+still answer questions 4 and 7/);
expect(section).toMatch(/10%[\s\S]*at most about 11% faster/);
expect(section).toMatch(/alternating A, B, A, B/);
expect(section).toContain('A gap smaller than the run-to-run');
expect(section).toMatch(/faster, slower, no measurable difference, or\s+inconclusive/);
expect(section).toMatch(/cannot name the limiter/);
});
});
describe('plan-eng-review: two shapes before one inside Section 1 of the lazy review section', () => {
const skeleton = read('plan-eng-review/SKILL.md');
const section = read('plan-eng-review/sections/review-sections.md');
const manifest = JSON.parse(read('plan-eng-review/sections/manifest.json')) as { sections: Array<{ id: string }> };
test('the pass lives in review-sections.md between Sections 1 and 2, the skeleton and manifest are unchanged, and the checklist maps it', () => {
expect(manifest.sections.map(s => s.id)).toEqual(['review-sections', 'checklist']);
expect(CARVE_GUARDS['plan-eng-review']!.expectedSections).toEqual(['review-sections.md']);
expect(skeleton).not.toContain('design-twice');
expect(skeleton.match(/> \*\*STOP\.\*\*/g)).toHaveLength(1);
const one = section.indexOf('### 1. Architecture review');
const pass = section.indexOf('### Two shapes before one (design-twice)');
const two = section.indexOf('### 2. Code quality review');
expect(one).toBeGreaterThan(0);
expect(pass).toBeGreaterThan(one);
expect(two).toBeGreaterThan(pass);
expect(section.slice(pass, two)).toMatch(/only when the plan introduces a new module, service, package or\s+boundary/);
expect(read('plan-eng-review/sections/checklist.md')).toContain('Two shapes before one (design-twice)');
});
test('a second structurally distinct shape, interface depth, the agent-contributor assumption, and the eight red flags in order', () => {
const pass = section.slice(section.indexOf('### Two shapes before one (design-twice)'), section.indexOf('### 2. Code quality review'));
expect(pass).toContain('**Ask for the second shape.**');
expect(pass).toMatch(/require a second\s+shape that is structurally different/);
expect(pass).toMatch(/A point fix inside\s+the first shape is not a second candidate\./);
expect(pass).toContain('interface depth');
expect(pass).toContain('A deep module is not a deep call chain');
expect(pass).toMatch(/an agent that sees only the files it opened,\s+copies the nearest example and takes the shortest path that compiles/);
const flags = ['**Shallow module.**', '**Information leakage.**', '**Temporal decomposition.**', '**Pass-through method.**', '**Split ownership.**', '**Two ways to do one task.**', '**Importable internals.**', '**Hand-synced list.**'];
let last = pass.indexOf('**The eight red flags.**');
expect(last).toBeGreaterThan(0);
for (const f of flags) {
const at = pass.indexOf(f);
expect(at, f).toBeGreaterThan(last);
last = at;
}
});
});
describe('every pstack-derived section carries its credit line', () => {
const credited = {
'investigate/sections/blast-radius.md.tmpl': 0,
'context-restore/sections/transcripts.md.tmpl': 0,
'benchmark/sections/vet-the-number.md.tmpl': 0,
// The design-twice pass lives inside an existing section; its credit sits on the line above its heading.
'plan-eng-review/sections/review-sections.md.tmpl': '### Two shapes before one (design-twice)',
} as const;
for (const [rel, where] of Object.entries(credited)) {
test(rel, () => {
const lines = read(rel).split('\n');
const at = typeof where === 'number' ? where : lines.indexOf(where) - 1;
expect(at).toBeGreaterThanOrEqual(0);
const credit = lines[at]!;
expect(credit.startsWith('<!--')).toBe(true);
expect(credit).toContain('pstack');
expect(credit).toContain('MIT');
expect(credit).toContain('rewritten');
expect(credit).toContain('See NOTICE.md');
expect(read('NOTICE.md')).toContain(rel.replace('.tmpl', ''));
});
}
});