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

+12 -2
View File
@@ -274,10 +274,11 @@ describe('Aside driver contract ({{ASIDE_SETUP}})', () => {
describe('browser fallback ({{BROWSE_FALLBACK}})', () => {
test('shell-probe consumers accept every non-READY status and optional research waives setup before the fallback', () => {
for (const file of ['browse/SKILL.md.tmpl', 'design-consultation/SKILL.md.tmpl', 'scripts/resolvers/utility.ts']) {
for (const file of ['browse/SKILL.md.tmpl', 'design-consultation/SKILL.md.tmpl']) {
const text = fs.readFileSync(path.join(ROOT, file), 'utf8');
expect({ file, nonReady: text.includes('any non-READY') }).toEqual({ file, nonReady: true });
}
expect(RESOLVERS.QA_METHODOLOGY(ctx)).toContain('Reuse the caller\'s BROWSER SETUP and owned artifact paths: Aside READY, otherwise `$B`');
const consultation = fs.readFileSync(path.join(ROOT, 'design-consultation/SKILL.md.tmpl'), 'utf8');
expect(consultation).toContain('do not build or offer a build');
expect(consultation.indexOf('The browser is optional here.')).toBeLessThan(consultation.indexOf('{{BROWSE_FALLBACK}}'));
@@ -438,7 +439,16 @@ describe('web research ({{ASIDE_RESEARCH}})', () => {
describe('browser consolidation tripwires', () => {
test('every browsing skill carries the Aside contract followed by the $B fallback', () => {
for (const skill of BROWSING_SKILLS) {
const md = fs.readFileSync(path.join(ROOT, skill, 'SKILL.md'), 'utf-8');
let md = fs.readFileSync(path.join(ROOT, skill, 'SKILL.md'), 'utf-8');
if (skill === 'qa' || skill === 'qa-only') {
expect(md).toContain('sections/browser-setup.md');
expect(md).not.toContain('## BROWSER SETUP (Aside');
if (skill === 'qa-only') {
expect(md).toContain('Read `sections/browser-setup.md` relative to the installed `qa`');
expect(fs.existsSync(path.join(ROOT, skill, 'sections/browser-setup.md'))).toBe(false);
}
md += fs.readFileSync(path.join(ROOT, 'qa/sections/browser-setup.md'), 'utf8');
}
const aside = md.indexOf('## BROWSER SETUP (Aside');
const fb = md.indexOf("## Browser fallback: gstack's own headless browser");
expect({ skill, hasAside: aside >= 0, hasFallback: fb >= 0, fallbackAfterAside: fb > aside }).toEqual({ skill, hasAside: true, hasFallback: true, fallbackAfterAside: true });