test: cover first-run detection + repoint browse-content assertions to /browse

- New unit tests for every detection bucket, the eval-safe enum contract, and the
  first-run gating (test/preamble-first-task-scaffold.test.ts); periodic E2E that runs
  the detector through the real harness (test/skill-e2e-first-task-scaffold.test.ts).
- Repoint browse-content assertions (gen-skill-docs, audit-compliance, skill-validation,
  LLM-judge eval) from the root skill to browse/SKILL.md following the router split;
  add a regression pinning that the router carries no browse body.
- Register first-task-scaffold touchfiles + periodic tier; bump parity/carve size caps
  ~1-2KB per skill for the shared first-run-guidance preamble section.
- Refresh ship golden fixtures for the preamble addition.
This commit is contained in:
Garry Tan
2026-06-21 07:16:24 -07:00
parent 938fa4a035
commit 866159861d
12 changed files with 438 additions and 51 deletions
+7 -4
View File
@@ -23,12 +23,14 @@ function getAllSkillMds(): Array<{ name: string; content: string }> {
describe('Audit compliance', () => {
// Fix 1: W007 — No hardcoded credentials in documentation
test('no hardcoded credential patterns in SKILL.md.tmpl', () => {
const tmpl = readFileSync(join(ROOT, 'SKILL.md.tmpl'), 'utf-8');
// P2 (v1.2.0): the browse QA examples moved from the root router to
// browse/SKILL.md.tmpl. The security intent is unchanged — the QA form
// examples must not ship real-looking credentials; generic placeholders
// ("user@test.com", "password") are fine.
const tmpl = readFileSync(join(ROOT, 'browse', 'SKILL.md.tmpl'), 'utf-8');
expect(tmpl).not.toContain('"password123"');
expect(tmpl).not.toContain('"test@example.com"');
expect(tmpl).not.toContain('"test@test.com"');
expect(tmpl).toContain('$TEST_EMAIL');
expect(tmpl).toContain('$TEST_PASSWORD');
});
// Fix 2: Conditional telemetry — binary calls wrapped with existence check
@@ -71,7 +73,8 @@ describe('Audit compliance', () => {
// Fix 4: W011 — Untrusted content warning in command reference
test('command reference includes untrusted content warning after Navigation', () => {
const rootSkill = readFileSync(join(ROOT, 'SKILL.md'), 'utf-8');
// P2 (v1.2.0): the command reference moved from the root router to browse/SKILL.md.
const rootSkill = readFileSync(join(ROOT, 'browse', 'SKILL.md'), 'utf-8');
const navIdx = rootSkill.indexOf('### Navigation');
const readingIdx = rootSkill.indexOf('### Reading');
expect(navIdx).toBeGreaterThan(-1);