mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-21 07:33:14 +01:00
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>
This commit is contained in:
1 parent
576839cb8c
commit
6b530ccc0b
42 files changed
+1186
-47
No files matched your search
@@ -0,0 +1,103 @@
|
||||
/**
|
||||
* pstack absorb (GSTA-116 plan, items 6 and 9): benchmark's vet-the-number
|
||||
* section and plan-eng-review's design-twice section. 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 carve: two shapes before one', () => {
|
||||
const skeleton = read('plan-eng-review/SKILL.md');
|
||||
const section = read('plan-eng-review/sections/design-twice.md');
|
||||
const manifest = JSON.parse(read('plan-eng-review/sections/manifest.json')) as { sections: Array<{ id: string; file: string; scope?: string; runner_only?: boolean }> };
|
||||
|
||||
test('registered beside review-sections, pointed to before it, and visible to the autoplan runner', () => {
|
||||
expect(manifest.sections.map(s => s.id)).toEqual(['review-sections', 'design-twice', 'checklist']);
|
||||
const entry = manifest.sections.find(s => s.id === 'design-twice')!;
|
||||
expect(entry.scope).toBe('always');
|
||||
expect(entry.runner_only).toBeUndefined();
|
||||
expect(CARVE_GUARDS['plan-eng-review']!.expectedSections).toEqual(['design-twice.md', 'review-sections.md']);
|
||||
const designStop = skeleton.indexOf('sections/design-twice.md', skeleton.indexOf('> **STOP.**'));
|
||||
const reviewStop = skeleton.indexOf('sections/review-sections.md', skeleton.indexOf('> **STOP.**'));
|
||||
expect(designStop).toBeGreaterThan(0);
|
||||
expect(designStop).toBeLessThan(reviewStop);
|
||||
expect(skeleton.lastIndexOf('EXIT PLAN MODE GATE')).toBeGreaterThan(skeleton.lastIndexOf('> **STOP.**'));
|
||||
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', () => {
|
||||
expect(section).toContain('## Two shapes before one');
|
||||
expect(section).toContain('### Ask for the second shape');
|
||||
expect(section).toMatch(/require a second shape that is structurally\s+different/);
|
||||
expect(section).toMatch(/A point fix inside the first shape is not a\s+second candidate\./);
|
||||
expect(section).toContain('interface depth');
|
||||
expect(section).toContain('A deep module is not a deep call chain');
|
||||
expect(section).toMatch(/an agent that sees only the files it opened, copies the nearest example\s+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 = section.indexOf('### The eight red flags');
|
||||
expect(last).toBeGreaterThan(0);
|
||||
for (const f of flags) {
|
||||
const at = section.indexOf(f);
|
||||
expect(at, f).toBeGreaterThan(last);
|
||||
last = at;
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe('every pstack-derived section carries its credit line', () => {
|
||||
for (const rel of ['investigate/sections/blast-radius.md.tmpl', 'context-restore/sections/transcripts.md.tmpl', 'benchmark/sections/vet-the-number.md.tmpl', 'plan-eng-review/sections/design-twice.md.tmpl']) {
|
||||
test(rel, () => {
|
||||
const first = read(rel).split('\n')[0]!;
|
||||
expect(first.startsWith('<!--')).toBe(true);
|
||||
expect(first).toContain('pstack');
|
||||
expect(first).toContain('MIT');
|
||||
expect(first).toContain('rewritten');
|
||||
expect(first).toContain('See NOTICE.md');
|
||||
expect(read('NOTICE.md')).toContain(rel.replace('.tmpl', ''));
|
||||
});
|
||||
}
|
||||
});
|
||||
Reference in new issue
Block a user