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/eng-scope-entry-ap.test.ts

@@ -41,7 +41,7 @@ test('every host expands its real bootstrap after the mandatory entry gate', ()
 });
 
 test('entry binds a current target and delays bootstrap until scope resolves', () => {
-  expect(scope).toContain('Before tools or preamble, resolve from provided messages, listed tools and explicit host metadata only');
+  expect(scope).toContain('Before discovery tools or preamble, check provided messages, listed tools and explicit host metadata for a target');
   expect(scope).toContain('Do not probe for session state');
   expect(scope).toContain('When no exception above applied:');
   expect(scope).toContain('First tool call = AskUserQuestion (tool_use). Send this exact menu and wait');
@@ -129,11 +129,11 @@ test('the full evaluated bundle routes startup into ordered preparation before s
   expect(startup).toContain('Defer Operational Self-Improvement, Telemetry and Plan Status Footer to finish');
   expect(startup).toContain('format/transport rules apply throughout');
   expect(startup).toContain('full section Read → **Review preparation** → **Scope Challenge**');
-  const preparation = section.slice(section.indexOf('## Review preparation'), section.indexOf('## Review record'));
-  const stages = ['1. Select the report file and permissions under **Review record and write policy**',
-    '2. Run **Prior Learnings**', '3. Run **Retrospective learning**',
-    '4. Read **Confidence Calibration**', '**Decision procedure**',
-    '**Scope Challenge A → B → C**', 'Sections 1–4 in order'];
+  const preparation = section.slice(section.indexOf('## Review preparation'));
+  expect(preparation).toContain('Follow the blocks below in order after startup');
+  const stages = ['## Review record and write policy', '## Prior Learnings',
+    '## Retrospective learning', '## Confidence Calibration', '## Decision procedure',
+    '## Scope Challenge', '## Review Sections'];
   const positions = stages.map(stage=>preparation.indexOf(stage));
   expect(positions.every(position=>position>=0)).toBe(true);
   expect(positions).toEqual([...positions].sort((a,b)=>a-b));
@@ -163,7 +163,7 @@ test('both complexity paths join findings without bypassing answers or persisten
   expect(positions.every(position => position >= 0)).toBe(true);
   expect(positions).toEqual([...positions].sort((a, b) => a - b));
   expect(challenge).toContain('Complete these checks before the complexity decision in B');
-  expect(challenge).toContain("Below both thresholds, skip B's questions and go directly to **C. Resolve findings**");
+  expect(challenge.replace(/\s+/g, ' ')).toContain("With fewer than 8 files AND fewer than 2 new classes/services, skip B's questions and go directly to **C. Resolve findings**");
   expect(challenge).toContain('At 8+ files or 2+ new classes/services, STOP before Section 1');
   expect(challenge).toContain('After verification, apply only accepted scope changes');
   expect(challenge).toContain('Run C whether B was completed or skipped');
@@ -173,12 +173,13 @@ test('both complexity paths join findings without bypassing answers or persisten
   expect(challenge).toContain('A failed save or Read blocks advancement');
   expect(challenge).toContain('Findings and scope answers approve no remedies');
   expect(challenge).toContain('Continue to Section 1 only when no answer is pending');
-  expect(section).toContain('One question for one choice per AskUserQuestion call');
-  expect(section).toContain('Compare every native field with `currentDecision` and the whole grid with step 3');
+  expect(section.replace(/\s+/g, ' ')).toContain('Send one question object for one choice; other IDs wait');
+  expect(section.replace(/\s+/g, ' ')).toContain('Compare every native field with `currentDecision` and the whole saved grid with the prepared comparison');
   expect(section).toContain('Repair any difference and repeat the complete Read before asking');
   expect(section).toContain('Read the selected saved label, full description and grid column together');
   expect(section).toContain('Check the save result, then Read the entire resolution block, including State');
-  expect(section).toContain('Entrypoint: **Paused question** for pending answers; **Blocked outcome** for missing work or failed recovery');
+  expect(section).toContain('**STOP until the actual answer arrives.**');
+  expect(section.replace(/\s+/g, ' ')).toContain('unreadable or unverifiable records use **Recovery routing**');
   expect(template).toContain('**Paused question:** Wait for its actual answer without completion telemetry or ExitPlanMode');
   expect(template).toContain('**Blocked outcome:** Stop the review and report `BLOCKED`');
 });