mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-10 15:09:00 +02:00
Garry TanandClaude Fable 5
2e3ba307d8
test/binding-template-drift.test.ts pins the load-bearing prose rules in the GENERATED templates (ship Step 16 evidence check, per-lane wrapped test lanes, land-and-deploy wtree-first grading + UNKNOWN fallback, dashboard content-first rule, release-body banner tripwire, greptile guard pipes) so a template refactor can't silently drop a rule while the bins keep passing their unit tests. Golden ship fixtures re-pinned to the new intentional output (claude/codex/ factory variants). TODOS.md gains the five deferred follow-ups from the review wave: eval-run evidence records, spec-spawn outcome ledger, merge-SHA custody, default-if-silent escalations, and the paid eval case proving agents apply the staleness grading rule. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
62 lines
2.7 KiB
TypeScript
62 lines
2.7 KiB
TypeScript
import { describe, test, expect } from 'bun:test';
|
|
import * as fs from 'fs';
|
|
import * as path from 'path';
|
|
|
|
/**
|
|
* Template-drift tripwire for the content-binding wave. The bins are
|
|
* code-enforced; the GRADING rules live as prose in rendered templates that
|
|
* agents follow. This test pins the load-bearing rule text in the GENERATED
|
|
* files so a template refactor can't silently drop a rule while the bins keep
|
|
* working. (Prompt-followed prose is honest tier-2 enforcement — this tripwire
|
|
* is what keeps it from being tier-3 vibes.)
|
|
*/
|
|
|
|
const ROOT = path.resolve(import.meta.dir, '..');
|
|
|
|
function rendered(rel: string): string {
|
|
return fs.readFileSync(path.join(ROOT, rel), 'utf-8');
|
|
}
|
|
|
|
describe('content-binding template drift', () => {
|
|
test('ship Step 16 carries the evidence check (mechanized IRON LAW)', () => {
|
|
const ship = rendered('ship/SKILL.md');
|
|
expect(ship).toContain('gstack-evidence check --label tests --label vitest --max-age 24 --allow-paths CHANGELOG.md,VERSION,package.json');
|
|
expect(ship).toContain('a failed CHECK never blocks');
|
|
});
|
|
|
|
test('ship Step 5 lanes run wrapped with per-lane labels', () => {
|
|
const tests = rendered('ship/sections/tests.md');
|
|
expect(tests).toContain('gstack-evidence run --label tests');
|
|
expect(tests).toContain('gstack-evidence run --label vitest');
|
|
});
|
|
|
|
test('land-and-deploy grades staleness content-first (wtree rule) and checks evidence', () => {
|
|
const land = rendered('land-and-deploy/SKILL.md');
|
|
expect(land).toContain('wtree');
|
|
expect(land).toContain('---WTREE---');
|
|
expect(land).toContain('gstack-evidence check --label tests --max-age 24');
|
|
expect(land).toContain('UNKNOWN');
|
|
});
|
|
|
|
test('the review dashboard staleness rule is wtree-first for diff-scoped rows', () => {
|
|
// The dashboard text is generated into every skill that embeds
|
|
// {{REVIEW_DASHBOARD}}; ship is the canonical carrier.
|
|
const ship = rendered('ship/SKILL.md');
|
|
expect(ship).toContain('---WTREE---');
|
|
expect(ship).toContain('diff-scoped rows only');
|
|
expect(ship).toContain('grade UNKNOWN and treat as stale');
|
|
});
|
|
|
|
test('release-body write side carries the banner tripwire', () => {
|
|
const body = rendered('document-release/sections/release-body.md');
|
|
expect(body).toContain('grep -q "UNTRUSTED TRACKER CONTENT" /tmp/gstack-pr-body-$$.md');
|
|
expect(body).toContain('banner tripwire clean');
|
|
});
|
|
|
|
test('greptile triage reads bodies through the guard (metadata/body split)', () => {
|
|
const triage = rendered('review/greptile-triage.md');
|
|
expect(triage).toContain('gstack-issue-guard --stdin --source greptile-line');
|
|
expect(triage).toContain('gstack-issue-guard --stdin --source greptile-replies');
|
|
});
|
|
});
|