v1.91.7.0 feat: add functional QA and pre-publication docs checks (#2983)

* feat: add surface-aware exploratory QA and ship documentation gates

* test: preserve delegated QA setup authority after main integration

* fix(qa): clarify exploration order and preserve report artifacts

* test(qa): follow the shared setup reference directly

* refactor(ship): make verification and recovery routes explicit

* test(ship): align evidence and review guards with explicit routes

* fix(workflows): clarify ship recovery and functional QA evidence

* fix(workflows): clarify approval recovery and full QA coverage

* refactor(workflows): order review transactions and clarify ship state

* fix(ship): clarify final verification and fail closed at publication

* fix(evals): attribute native atomic documentation writes

* fix(ship): clarify recovery and documentation lifecycle guidance

* fix(test): preserve observed native placeholder styling in CI

* fix(codex): report watchdog timeouts without a process-exit race

* Checkpoint functional QA implementation and workflow validation repairs

* Fix documentation and shared-review fixture contracts

* docs: clarify judge reuse and evaluation supervision

* test: align review evidence and selected case contracts

* test: verify append-only documentation checkpoints and recovery

* fix: qualify QA workflows and CI validation repairs

* fix: launch shared-libs fixture scripts on Windows

* fix: qualify QA deadlines, fixture isolation, and shard cleanup

* fix: preserve qualified QA and cancellation repairs

* fix: enforce functional fixture authority and share strict event decoding

* fix: retain free-test evidence and explain recovery

* fix: reject malformed native evidence after decoder consolidation

* test: use reliable capture for telemetry privacy filters

* test: refresh measured quick coverage and document validation costs

* Fix native fixture receipts and preserve VM validation evidence

* Align negative judge controls with upstream clarity policy

* Fix report-only QA preparation and public evidence handling

* Clarify QA-only preparation and current-report preservation

* Stream Ship quality judgments with an explicit 64k response contract

* Validate compact judge reasoning locally with supported wire schema

* Align functional QA fixture instructions with evidence acceptance

* Bind native browser diagnostics to execution evidence and align review verdicts

* Preserve native diagnostic line boundaries

* Serialize functional QA evidence from native captures

* Keep large QA evidence fixture payload out of Windows argv
This commit is contained in:
Garry Tan authored and GitHub committed 2026-09-29 06:07:35 -07:00
1 parent 65bfb0ce49
commit dcaea52800
333 files changed
+41755 -7357

No files matched your search

+51
View File
@@ -154,6 +154,45 @@ describe('extractSkillBody (synthetic)', () => {
expect(out).not.toContain('footer junk');
});
test.each([
['plain', '', '# Actual'],
['one-space indent', '', ' # Actual'],
['three-space indent', '', ' # Actual'],
['tab separator', '', '#\tActual'],
['empty title', '', '#'],
['backtick fence', '```md\n# FALSE TITLE\n## FALSE SECTION\n```\n', '# Actual'],
['tilde fence', '~~~md\n# FALSE TITLE\n~~~\n', '# Actual'],
['short nested fence', '````md\n```\n# FALSE TITLE\n```\n````\n', '# Actual'],
['mismatched fence', '~~~md\n```\n# FALSE TITLE\n~~~\n', '# Actual'],
['nonclosing suffix', '```md\n```not-a-close\n# FALSE TITLE\n```\n', '# Actual'],
['indented code', ' # FALSE TITLE\n', '# Actual'],
['missing separator', '#FALSE TITLE\n', '# Actual'],
['quoted title', '> # FALSE TITLE\n', '# Actual'],
])('preserves a post-preamble H1 introduction: %s', (_name, decoy, title) => {
const file = path.join(tmpDir, 'title-boundary.md');
fs.writeFileSync(file, SYNTHETIC_SKILL.replace(
'footer junk, last shared-preamble section\n\n',
`footer junk, last shared-preamble section\n${decoy}${title}\nREAL INTRODUCTION\n\n`,
));
const out = extractSkillBody(file);
expect(out).toBe(extractSkillBody(skillDir).replace(
'## Step 1 — Do the thing', `${title}\nREAL INTRODUCTION\n\n## Step 1 — Do the thing`,
));
expect(out).not.toContain('FALSE TITLE');
expect(out).not.toContain('footer junk');
expect(extractSkillSections(file, ['Plan Status Footer']))
.toContain(`${decoy}${title}\nREAL INTRODUCTION`);
});
test('a post-preamble H1 and introduction are a complete body without another H2', () => {
const file = path.join(tmpDir, 'title-only-body.md');
fs.writeFileSync(file, SYNTHETIC_SKILL.slice(0, SYNTHETIC_SKILL.indexOf('## Step 1 — Do the thing'))
+ '# Actual\nREAL INTRODUCTION\n');
const out = extractSkillBody(file);
expect(out).toContain('# Actual\nREAL INTRODUCTION');
expect(out).not.toContain('footer junk');
});
test('throws when the preamble markers are missing', () => {
const bare = path.join(tmpDir, 'bare');
fs.mkdirSync(bare, { recursive: true });
@@ -321,6 +360,18 @@ describe('real-skill pins: section lists used by E2E fixtures', () => {
});
describe('real-skill pins: body/head extraction used by E2E fixtures', () => {
test.each(['qa-only', 'skillify', 'context-save', 'context-restore'])(
'extractSkillBody(%s) preserves the complete real H1 introduction', (skill) => {
const file = path.join(ROOT, skill, 'SKILL.md');
const full = fs.readFileSync(file, 'utf8');
const title = full.indexOf(`\n# /${skill}`, full.indexOf('## Plan Status Footer'));
const nextSection = full.indexOf('\n## ', title);
expect(title).toBeGreaterThan(0);
expect(nextSection).toBeGreaterThan(title);
expect(extractSkillBody(file)).toContain(full.slice(title + 1, nextSection).trimEnd());
},
);
// scrape/skillify/context-*: skill-e2e-skillify + skill-e2e-context-skills.
// review/plan-eng-review/ship: skill-e2e-coverage-audit + skill-e2e-triage.
const BODY_EXTRACTED_SKILLS = [