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

+13 -8
View File
@@ -116,7 +116,7 @@ const pkgVersion = () =>
test("rendered drift repair rejoins the existing-version queue check", () => {
const ship = readFileSync(join(import.meta.dir, '../ship/SKILL.md'), 'utf8');
const version = ship.slice(ship.indexOf('## Step 12:'), ship.indexOf('## Step 14:'));
const version = ship.slice(ship.indexOf('## Step 12:'), ship.indexOf('## Step 14:')).replace(/\s+/g, ' ');
expect(version).toMatch(/DRIFT_STALE_PKG[^\n]+repair[^\n]+reclassify[^\n]+ALREADY_BUMPED[^\n]+queue/);
expect(version).toContain('--current-version "$BASE_VERSION"');
expect(version).toContain('CANDIDATE_VERSION');
@@ -125,15 +125,20 @@ test("rendered drift repair rejoins the existing-version queue check", () => {
test("rendered queue dispatch preserves offline git candidates without empty fallback fallthrough", () => {
const ship = readFileSync(join(import.meta.dir, '../ship/SKILL.md'), 'utf8');
const usableAt = ship.indexOf('**Usable candidate**');
const missingAt = ship.indexOf('**No usable candidate**');
const qualifyAt = ship.indexOf('**Qualify first:**');
const usableAt = ship.indexOf('**Usable candidate:**');
const missingAt = ship.indexOf('**No usable candidate:**');
expect(qualifyAt).toBeGreaterThanOrEqual(0);
expect(usableAt).toBeGreaterThan(qualifyAt);
expect(usableAt).toBeGreaterThanOrEqual(0);
expect(missingAt).toBeGreaterThan(usableAt);
const usable = ship.slice(usableAt, missingAt);
const missing = ship.slice(missingAt, ship.indexOf('4. **Write the bump**', missingAt));
expect(usable).toContain('offline:true');
expect(usable).toContain('fallback:"git"');
expect(usable).toContain('warnings and any claimed queue');
const qualify = ship.slice(qualifyAt, usableAt).replace(/\s+/g, ' ');
const usable = ship.slice(usableAt, missingAt).replace(/\s+/g, ' ');
const missing = ship.slice(missingAt, ship.indexOf('4. **Write the bump**', missingAt)).replace(/\s+/g, ' ');
expect(qualify).toContain('require successful utility output and a nonempty valid version');
expect(qualify).toContain('`offline:false` qualifies; `offline:true` qualifies only with `fallback:"git"`');
expect(qualify).toContain('Offline output without that fallback, failure, malformed output or an empty version is unusable');
expect(usable).toContain('warnings and claimed queue');
expect(usable).toContain('CANDIDATE_VERSION');
expect(missing).toContain('local `BUMP_LEVEL` arithmetic');
expect(missing).toContain('ALREADY_BUMPED keeps `currentVersion`');