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

test/shared-libs-rendering.test.ts

@@ -65,18 +65,35 @@ describe('shared-code skill distribution', () => {
       expect(texts[2]).toContain('snapshot_covered_paths');
       expect(texts[2]).toContain('Exclude assume-unchanged, skip-worktree');
       expect(texts[2]).toContain('byte-for-byte with its blob');
-      for (const parent of [texts[2], rendered(host, 'ship')]) {
-        const validation = parent.indexOf('**Validate advisory severity first.**');
+      for (const [skill, parent] of [['review', texts[2]], ['ship', rendered(host, 'ship')]]) {
+        const validation = parent.indexOf(skill === 'ship' ? '1. **Validate severity.**' : '**Validate advisory severity first.**');
         expect(validation).toBeGreaterThanOrEqual(0);
-        expect(validation).toBeLessThan(parent.indexOf('Before classifying findings, check'));
-        expect(parent).toContain('remove `advisory` and retain its `CRITICAL` severity');
-        expect(parent).toContain('Never downgrade severity to make advisory metadata consistent');
-        expect(parent).toContain('Valid INFORMATIONAL advisories remain advisory in every category, including simplification');
-        expect(parent).toContain('contradictory CRITICAL/advisory metadata cannot establish a skipped defect or advisory decision');
-        const merge = parent.indexOf('**Parse findings:**');
-        if (merge >= 0) {
-          expect(parent.indexOf('**Validate advisory severity first.**', merge))
-            .toBeLessThan(parent.indexOf('**Fingerprint and deduplicate:**', merge));
+        expect(validation).toBeLessThan(parent.indexOf(skill === 'ship' ? '2. **Read decisions.**' : 'Before classifying findings, check'));
+        if (skill === 'ship') {
+          const matching = parent.slice(validation).replace(/\s+/g, ' ');
+          expect(matching).toContain('For CRITICAL/advisory contradictions, remove `advisory`, never downgrade severity');
+          expect(matching).toContain('Valid INFORMATIONAL advisories stay advisory, including simplification');
+          expect(matching).toContain('Reject contradictory saved decisions');
+          expect(matching).toContain('they cannot suppress defects');
+        } else {
+          expect(parent).toContain('remove `advisory` and retain its `CRITICAL` severity');
+          expect(parent).toContain('Never downgrade severity to make advisory metadata consistent');
+          expect(parent).toContain('Valid INFORMATIONAL advisories remain advisory in every category, including simplification');
+          expect(parent).toContain('contradictory CRITICAL/advisory metadata cannot establish a skipped defect or advisory decision');
+        }
+        if (host.name !== 'codex' && !host.suppressedResolvers?.includes('REVIEW_ARMY')) {
+          const stages = ['#### 1. Parse outputs', '#### 2. Validate severity', '#### 3. Identify and merge',
+            '#### 4. Apply specialist confidence gates', '#### 5. Score and present specialists'];
+          const positions = stages.map(stage => parent.indexOf(stage));
+          expect(positions.every(position => position >= 0)).toBe(true);
+          expect(positions).toEqual([...positions].sort((a, b) => a - b));
+          const merge = parent.slice(positions[1], positions[2]).replace(/\s+/g, ' ');
+          expect(merge).toContain('remove `advisory` and retain its `CRITICAL` severity');
+          expect(merge).toContain('Never downgrade severity');
+          expect(parent).toContain('Only specialist findings enter this header and `quality_score`; core findings do not');
+        } else {
+          expect(parent).not.toContain('#### 1. Parse outputs');
+          expect(parent).not.toContain('SPECIALIST REVIEW: N findings');
         }
       }
     });
@@ -99,9 +116,9 @@ describe('shared-code skill distribution', () => {
     const headings = ['## AskUserQuestion Format', '## My engineering preferences',
       '## Review record and write policy', '**Plan-review evidence:**',
       '## Confidence Calibration', '## Decision procedure',
-      '### 1. Establish current state', '### 2. Separate independent choices',
-      '### 3. Compare one choice', '### 4. Save the pending record',
-      '### 5. Ask and wait', '### 6. Apply and refresh',
+      '### Prepare an unanswered choice', '**Separate independent choices.**',
+      '**Compare one choice.**', '**Pending-record checkpoint.**',
+      '### Send once and wait', '### Record the answer',
       '### 2. Code quality review', '### Shared-code evaluation rubric', '**Blocked outcome:**'];
     const positions = headings.map(heading => excerpt.indexOf(heading));
     expect(positions.every(index => index >= 0)).toBe(true);