CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-06-17 23:30:09 +02:00
Code Issues Packages Projects Releases Wiki Activity
Files
a16459784785eec41e27705f901afbf11b7befb4
gstack/test/skill-coverage-matrix.ts
T
Garry Tan 296937d466 test(coverage): T1 — skill coverage matrix + structural-compliance floor 
Phase 0 deliverable — eval-first foundation. Two new test files plus the
registry:

1. test/skill-coverage-matrix.ts — single source of truth mapping each
   skill to its gate-tier + periodic-tier test files. SKILL_COVERAGE
   record with 51 entries; every gstack skill on disk has at least one
   gate-tier entry.

2. test/skill-coverage-matrix.test.ts — CI gate. Asserts every skill on
   disk has a registry entry AND that gate[] is non-empty. Catches
   "skill added but eval not registered" the moment a new SKILL.md
   lands.

3. test/skill-coverage-floor.test.ts — per-skill structural compliance
   (FREE, file-IO only). For each of 51 skills, verifies:
   - SKILL.md exists
   - Frontmatter well-formed (name + description fields)
   - Catalog-trim contract (inline description ≤ 250 chars, or block form)
   - Generated header present (edit .tmpl, not .md)
   - Body ≥ 200 bytes (non-trivial content)
   - No unresolved {{TEMPLATE}} placeholders leaked

The "floor" is the minimum eval that every skill ships with. Skills that
need deeper behavioral testing get additional entries in their coverage
record (e.g., ship has skill-e2e-ship-idempotency + workflow + floor).
Future skills only need to add the floor entry and the matrix gate
unblocks them.

Codex 2nd-pass critique #1 mitigation: eval-first floor is structural
compliance (the testable part) — judgment-skill behavior gets layered
periodic-tier evals on top. We don't pretend the floor proves
correctness, only that the skill structurally compiles.

Test plan:
- bun test test/skill-coverage-matrix.test.ts: 4 pass (matrix shape + coverage)
- bun test test/skill-coverage-floor.test.ts: 309 pass (6 checks × 51 skills + 3 registry-level)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-25 20:38:35 -07:00

182 lines
8.8 KiB
TypeScript
Raw Blame History

/**
* Skill coverage matrix (v1.45.0.0 T1, cathedral Phase 0).
*
* Single source of truth mapping each gstack skill to its E2E test files.
* The CI gate at test/skill-coverage-matrix.test.ts fails if a skill has
* no gate-tier entry, ensuring the eval-first foundation holds: every
* skill has at least one CI-blocking check that asserts must-have
* behavior.
*
* Two tiers per entry:
* gate CI-blocking, runs on every PR, target <$0.50/test or free.
* periodic Weekly cron, deeper coverage, can cost ~$1-$3/test.
*
* The 'floor' entry refers to test/skill-coverage-floor.test.ts —
* a structural-compliance smoke test that covers every skill with
* file-IO checks (free, no LLM cost). When a skill has only 'floor'
* coverage, that's the eval-first minimum; future work can layer
* behavioral checks on top.
*/
export interface SkillCoverage {
/** Gate-tier test file paths (relative to repo root). At least one required per skill. */
gate: string[];
/** Periodic-tier test file paths. Optional but recommended. */
periodic: string[];
/** Brief note on why this coverage is the right shape for this skill. */
rationale?: string;
}
/**
* Per-skill coverage. Keys MUST match the top-level skill directory name.
* The CI test asserts every skill in the repo has an entry here AND that
* gate[] is non-empty.
*
* Adding a new skill: add an entry here AND either reference an existing
* test that covers it OR add 'test/skill-coverage-floor.test.ts' as the
* minimum gate-tier check.
*/
export const SKILL_COVERAGE: Record<string, SkillCoverage> = {
// ─── Core loop ──────────────────────────────────────────────
ship: {
gate: ['test/skill-e2e-ship-idempotency.test.ts', 'test/skill-coverage-floor.test.ts'],
periodic: ['test/skill-e2e-workflow.test.ts'],
},
review: {
gate: ['test/skill-e2e-review.test.ts', 'test/skill-coverage-floor.test.ts'],
periodic: ['test/skill-e2e-review-army.test.ts', 'test/regression-1539-review-self-verify.test.ts'],
},
qa: {
gate: ['test/skill-e2e-qa-workflow.test.ts', 'test/skill-coverage-floor.test.ts'],
periodic: ['test/skill-e2e-qa-bugs.test.ts'],
},
'qa-only': {
gate: ['test/skill-coverage-floor.test.ts'],
periodic: [],
rationale: 'qa-only is qa with --report-only; behavior tested via /qa coverage.',
},
investigate: {
gate: ['test/skill-coverage-floor.test.ts'],
periodic: [],
},
browse: {
gate: ['test/skill-coverage-floor.test.ts'],
periodic: [],
rationale: 'browse binary has its own integration suite under browse/test/.',
},
// ─── Plan triad ─────────────────────────────────────────────
'plan-ceo-review': {
gate: [
'test/skill-e2e-plan-ceo-finding-floor.test.ts',
'test/skill-e2e-plan-ceo-plan-mode.test.ts',
'test/skill-coverage-floor.test.ts',
],
periodic: [
'test/skill-e2e-plan-ceo-finding-count.test.ts',
'test/skill-e2e-plan-ceo-mode-routing.test.ts',
],
},
'plan-eng-review': {
gate: [
'test/skill-e2e-plan-eng-finding-floor.test.ts',
'test/skill-e2e-plan-eng-plan-mode.test.ts',
'test/skill-coverage-floor.test.ts',
],
periodic: [
'test/skill-e2e-plan-eng-finding-count.test.ts',
'test/skill-e2e-plan-eng-multi-finding-batching.test.ts',
],
},
'plan-design-review': {
gate: [
'test/skill-e2e-plan-design-finding-floor.test.ts',
'test/skill-e2e-plan-design-plan-mode.test.ts',
'test/skill-e2e-plan-design-with-ui.test.ts',
'test/skill-coverage-floor.test.ts',
],
periodic: ['test/skill-e2e-plan-design-finding-count.test.ts'],
},
'plan-devex-review': {
gate: [
'test/skill-e2e-plan-devex-finding-floor.test.ts',
'test/skill-e2e-plan-devex-plan-mode.test.ts',
'test/skill-coverage-floor.test.ts',
],
periodic: ['test/skill-e2e-plan-devex-finding-count.test.ts'],
},
autoplan: {
gate: ['test/skill-coverage-floor.test.ts'],
periodic: ['test/skill-e2e-autoplan-chain.test.ts', 'test/skill-e2e-autoplan-dual-voice.test.ts'],
},
'office-hours': {
gate: ['test/skill-e2e-office-hours.test.ts', 'test/skill-coverage-floor.test.ts'],
periodic: ['test/skill-e2e-office-hours-auto-mode.test.ts', 'test/skill-e2e-office-hours-phase4.test.ts'],
},
// ─── Polish + design ────────────────────────────────────────
'design-review': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
'design-consultation': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
'design-shotgun': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
'design-html': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
cso: {
gate: ['test/skill-e2e-cso.test.ts', 'test/cso-preserved.test.ts', 'test/skill-coverage-floor.test.ts'],
periodic: [],
rationale: 'cso-preserved.test.ts pins must-not-strip security guidance phrases.',
},
'document-release': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
'document-generate': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
// ─── Ops + integrations ─────────────────────────────────────
'land-and-deploy': { gate: ['test/skill-e2e-deploy.test.ts', 'test/skill-coverage-floor.test.ts'], periodic: [] },
canary: { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
benchmark: { gate: ['test/skill-e2e-benchmark-providers.test.ts', 'test/skill-coverage-floor.test.ts'], periodic: [] },
'benchmark-models': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
codex: { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
retro: {
gate: ['test/skill-coverage-floor.test.ts'],
periodic: ['test/regression-1624-retro-stale-base.test.ts'],
},
'gstack-upgrade': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
'context-save': { gate: ['test/skill-e2e-context-skills.test.ts', 'test/skill-coverage-floor.test.ts'], periodic: [] },
'context-restore': { gate: ['test/skill-e2e-context-skills.test.ts', 'test/skill-coverage-floor.test.ts'], periodic: [] },
'setup-deploy': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
'setup-browser-cookies': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
'setup-gbrain': {
gate: [
'test/skill-e2e-setup-gbrain-bad-token.test.ts',
'test/skill-e2e-setup-gbrain-path4-local-pglite.test.ts',
'test/skill-e2e-setup-gbrain-remote.test.ts',
'test/skill-coverage-floor.test.ts',
],
periodic: [],
},
'sync-gbrain': {
gate: ['test/skill-coverage-floor.test.ts'],
periodic: ['test/regression-1611-gbrain-sync-resume.test.ts'],
},
'open-gstack-browser': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
'pair-agent': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
scrape: { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
skillify: { gate: ['test/skill-e2e-skillify.test.ts', 'test/skill-coverage-floor.test.ts'], periodic: [] },
learn: { gate: ['test/skill-e2e-learnings.test.ts', 'test/skill-coverage-floor.test.ts'], periodic: [] },
'plan-tune': { gate: ['test/skill-e2e-plan-tune.test.ts', 'test/skill-coverage-floor.test.ts'], periodic: [] },
// ─── iOS family ─────────────────────────────────────────────
'ios-qa': { gate: ['test/skill-e2e-ios.test.ts', 'test/skill-coverage-floor.test.ts'], periodic: ['test/skill-e2e-ios-device.test.ts', 'test/skill-e2e-ios-swift-build.test.ts'] },
'ios-fix': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
'ios-clean': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
'ios-sync': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
'ios-design-review': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
// ─── Safety / housekeeping ──────────────────────────────────
careful: { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
freeze: { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
unfreeze: { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
guard: { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
'landing-report': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
health: { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
'make-pdf': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
'devex-review': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
};
Reference in New Issue View Git Blame Copy Permalink