mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-02 17:40:02 +02:00
- exit-propagation drives the runner's real strict verdict (BunTestOutputClassifier + strictTestExitCode); delete the unused shardRunLooksTruncated predicate. - delete skill-coverage-matrix registry + its gate (nothing reads it; the floor already iterates skillCensus()). - delete touchfiles-facade export-parity tests (Bun fails missing imports at link time) and the duplicated E2E_TIERS tier-value test. - delete brain-cache-spec TRANSPORT_DEFAULT_POLICY, SKILL_RUN_RETENTION_DAYS and the now-unused BrainTrustPolicy type with their literal tests. AUTOPLAN_PREFLIGHT_BUDGET_BYTES stays: skill-preflight-budget enforces it against real resolver output. - delete audit-compliance's JSDoc-comment grep.
99 lines
3.8 KiB
TypeScript
99 lines
3.8 KiB
TypeScript
/**
|
|
* Skill coverage floor — gate-tier, free, runs every PR.
|
|
*
|
|
* Phase 0 of the cathedral parity-eval suite: structural-compliance smoke
|
|
* test that covers every gstack skill with file-IO assertions. The intent
|
|
* is "every skill ships with at least one CI-blocking check" — even when
|
|
* a skill doesn't (yet) have a behavioral E2E test, this floor catches
|
|
* frontmatter regressions, missing generated header, empty/trivial bodies,
|
|
* and dangling SKILL.md.tmpl-without-SKILL.md mismatches.
|
|
*
|
|
* Pairs with test/parity-suite.test.ts (the content-invariant suite).
|
|
* The floor iterates every authored skill from skillCensus(), so a new
|
|
* skill is covered without registering it anywhere.
|
|
*/
|
|
|
|
import { describe, test, expect } from 'bun:test';
|
|
import * as fs from 'fs';
|
|
import * as path from 'path';
|
|
import { skillCensus } from './helpers/skill-census';
|
|
|
|
const REPO_ROOT = path.resolve(import.meta.dir, '..');
|
|
|
|
function readSkillMd(skill: string): string | null {
|
|
const p = path.join(REPO_ROOT, skill, 'SKILL.md');
|
|
try {
|
|
return fs.readFileSync(p, 'utf-8');
|
|
} catch {
|
|
return null;
|
|
}
|
|
}
|
|
|
|
describe('skill-coverage-floor: every skill passes structural compliance', () => {
|
|
const skills = skillCensus(REPO_ROOT).authoredSkills;
|
|
|
|
// Per-skill structural compliance (file IO only, no LLM)
|
|
for (const skill of skills) {
|
|
describe(`skill: ${skill}`, () => {
|
|
test('SKILL.md exists', () => {
|
|
const content = readSkillMd(skill);
|
|
expect(content).not.toBeNull();
|
|
});
|
|
|
|
test('frontmatter is well-formed and contains name + description', () => {
|
|
const content = readSkillMd(skill)!;
|
|
expect(content.startsWith('---\n')).toBe(true);
|
|
const fmEnd = content.indexOf('\n---', 4);
|
|
expect(fmEnd).toBeGreaterThan(0);
|
|
const fm = content.slice(4, fmEnd);
|
|
// name: ...
|
|
expect(/^name:\s*\S/m.test(fm)).toBe(true);
|
|
// description: ... (either inline or block form)
|
|
expect(/^description:\s*(\S|\|)/m.test(fm)).toBe(true);
|
|
});
|
|
|
|
test('frontmatter description fits the catalog-trim contract', () => {
|
|
const content = readSkillMd(skill)!;
|
|
const fmEnd = content.indexOf('\n---', 4);
|
|
const fm = content.slice(4, fmEnd);
|
|
// Inline form: description: <one line>
|
|
const inlineMatch = fm.match(/^description:\s+(.+)$/m);
|
|
// Block form: description: |\n multiline
|
|
const blockMatch = fm.match(/^description:\s*\|/m);
|
|
if (inlineMatch) {
|
|
// Catalog-trimmed: should be ≤ 250 chars
|
|
expect(inlineMatch[1].length).toBeLessThanOrEqual(250);
|
|
} else if (blockMatch) {
|
|
// Block form is acceptable for small skills (under-120-chars baseline
|
|
// didn't trigger catalog trim). No size cap here; the parity-suite
|
|
// and size-budget tests handle bytes.
|
|
} else {
|
|
throw new Error(`${skill}: description field is not in inline or block form`);
|
|
}
|
|
});
|
|
|
|
test('generated header present (only edit .tmpl, not .md)', () => {
|
|
const content = readSkillMd(skill)!;
|
|
expect(content).toContain('AUTO-GENERATED from SKILL.md.tmpl');
|
|
});
|
|
|
|
test('body is non-trivial (≥ 200 bytes after frontmatter)', () => {
|
|
const content = readSkillMd(skill)!;
|
|
const fmEnd = content.indexOf('\n---', 4);
|
|
const body = content.slice(fmEnd + 5).trim();
|
|
expect(body.length).toBeGreaterThanOrEqual(200);
|
|
});
|
|
|
|
test('no unresolved {{TEMPLATE}} placeholders leaked into output', () => {
|
|
const content = readSkillMd(skill)!;
|
|
const leaks = content.match(/\{\{[A-Z_]+(?::[^}]+)?\}\}/g);
|
|
if (leaks) {
|
|
throw new Error(
|
|
`${skill}: ${leaks.length} unresolved placeholder(s) in generated SKILL.md: ${leaks.slice(0, 3).join(', ')}${leaks.length > 3 ? ', ...' : ''}`,
|
|
);
|
|
}
|
|
});
|
|
});
|
|
}
|
|
});
|