v1.89.0.0 feat: add shared-code extraction audit (#2925)

* feat: bind shared-code review advice to source and branch

* feat: add shared-code extraction audit and scoped review checks

* test: recognize complete source reads and explicit coverage legends

* chore: bump version and changelog (v1.88.0.0)

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* test: capture native review questions and retain public evidence

Capture the actual first public native question with strict ownership and display matching. Preserve terminal failures and raw evidence, and retain SDK completion checks.

* test: recognize verified review evidence and complete fixtures

Recognize complete source and diagram evidence, concrete design and developer-experience decisions, and the complete planted scenario contracts. Preserve negative controls and grading thresholds.

* fix: preserve decision brief structure in native questions

Keep the required pros-and-cons heading and final Net field in native question text. Regenerate host outputs and document the release and evaluation repairs.

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* docs: update project documentation for v1.88.0.0

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* fix: correct eval retry accounting and ship workflow gates

* fix: capture native eval evidence and stabilize CI fixtures

* fix: keep shared-code eval skips read-only

Choose explicit no-change answers instead of mixed fix/preservation options.
Reuse the bounded revalidation prompt for path fixtures so required review
metadata is available without repeated discovery. Preserve source checks,
retry limits, and failed native terminal outcomes.

Add captured-question and callback regressions, plus evaluation selection
coverage for the affected fixtures.

---------

Co-authored-by: OpenAI Codex <noreply@openai.com>

test/workflow-excerpt.test.ts

@@ -72,7 +72,8 @@ describe('workflow judge excerpts', () => {
   test('ship uses project-native commands and never jumps over mandatory gates', () => {
     const text = readWorkflowExcerpt('ship/SKILL.md', '# Ship:', '## Important Rules');
     expect(text).toContain("Use the project's test commands discovered in Step 4");
-    expect(text).toContain("Use the project's documented eval selection");
+    expect(text).toContain('**Project-native path:**');
+    expect(text).toContain('Use the documented selector and pre-merge command.');
     expect(text).not.toMatch(/skipping evals[^\n]*Step 9/);
     const reviewAndTriage = text.slice(text.indexOf('## Step 9:'), text.indexOf('## Step 11:'));
     expect(reviewAndTriage.match(/continue to Step 12/i)).toBeNull();
@@ -85,6 +86,16 @@ describe('workflow judge excerpts', () => {
     expect(text).toContain('````text\nYou are running a ship-workflow');
   });
 
+  test('ship review shortcuts retain dedup and fixes repeat the whole review cycle', () => {
+    const text = readWorkflowExcerpt('ship/SKILL.md', '# Ship:', '## Important Rules');
+    expect(text).toContain('Continue to Step 9.3 (cross-review dedup)');
+    expect(text).toContain('## Step 9.4: Fix-First and persistence');
+    expect(text).toContain('including design, specialists, Red Team, and dedup');
+    const audit = text.slice(text.indexOf('## Step 7:'), text.indexOf('## Step 8:'));
+    expect(audit).not.toContain('Scope Challenge');
+    expect(text).toContain('Ship anyway retains VERIFY_RESULT=fail');
+  });
+
   test('a sliced section is not appended again with its generated header', () => {
     const text = readWorkflowExcerpt('plan-design-review/SKILL.md', '## Review Sections', '## CRITICAL RULE');
     expect(text.match(/## Review Sections/g)).toHaveLength(1);
@@ -106,7 +117,7 @@ describe('workflow judge excerpts', () => {
     expect(text).toContain('never create an empty commit');
     const review = text.slice(text.indexOf('## Step 9:'), text.indexOf('## Step 10:'));
     expect(review.indexOf('## Confidence Calibration')).toBeLessThan(review.indexOf('1. Read'));
-    expect(review).toContain('only continue to Step 10 after item 9');
+    expect(review).toContain('Continue to Step 10 only after a completed, converged review is persisted');
   });
 
   test('ship approval gates stay outside the subagent prompts', () => {
@@ -196,15 +207,19 @@ describe('workflow judge excerpts', () => {
   test('CEO capture locates Mode Selection by name for current and frozen skill copies', () => {
     const dir = mkdtempSync(join(tmpdir(), 'ceo-semantic-capture-'));
     const helper = join(import.meta.dir, 'helpers', 'auq-sdk-capture.ts');
-    const runner = join(import.meta.dir, 'helpers', 'session-runner.ts');
+    const runner = join(import.meta.dir, 'helpers', 'agent-sdk-runner.ts');
     const script = join(dir, 'capture.ts');
     writeFileSync(script, `import { mock } from 'bun:test';
 import * as fs from 'node:fs';
 import * as path from 'node:path';
 const calls = [];
-mock.module(${JSON.stringify(runner)}, () => ({runSkillTest: async options => {
+mock.module(${JSON.stringify(runner)}, () => ({resolveClaudeBinary:()=>'/fixture/claude',runAgentSdkTest: async options => {
   calls.push(options);
-  fs.writeFileSync(path.join(options.workingDirectory, 'ask-capture.md'), 'captured mode choice');
+  void options.canUseTool('AskUserQuestion', {questions:[{header:'Mode',question:'captured mode choice',
+    options:['SCOPE EXPANSION','SELECTIVE EXPANSION','HOLD SCOPE','SCOPE REDUCTION'].map(label=>({label,description:''}))}]},
+    {toolUseID:'native-mode',signal:options.signal});
+  options.signal.throwIfAborted();
+  throw Error('capture failed to stop before answering');
 }}));
 const {captureModeSelectionAuq, verboseSkill} = await import(${JSON.stringify(helper)});
 const current = fs.readFileSync(${JSON.stringify(join(import.meta.dir, '..', 'plan-ceo-review', 'SKILL.md'))}, 'utf8');
@@ -224,16 +239,17 @@ console.log(JSON.stringify({calls, results}));
       expect(child.status, `${child.error ?? ''}\n${child.stderr}`).toBe(0);
       const { calls, results } = JSON.parse(child.stdout.trim().split('\n').at(-1)!);
       expect(results).toEqual([
-        { variant: 'current', heading: expect.stringMatching(/^0[A-Z]$/), captured: 'captured mode choice' },
-        { variant: 'frozen', heading: '0F', captured: 'captured mode choice' },
+        { variant: 'current', heading: expect.stringMatching(/^0[A-Z]$/), captured: expect.stringContaining('captured mode choice') },
+        { variant: 'frozen', heading: '0F', captured: expect.stringContaining('captured mode choice') },
       ]);
       expect(calls).toHaveLength(2);
       for (const call of calls) {
-        expect(call.prompt).toContain('Proceed to Mode Selection,');
-        expect(call.prompt).not.toMatch(/Step 0[A-Z]/);
-        expect(call.prompt).toContain(join(call.workingDirectory, 'plan-ceo-review', 'SKILL.md'));
-        expect(call.prompt).toContain('Do NOT search for, Glob, find, or read any OTHER SKILL.md');
-        expect(call).toMatchObject({ allowedTools: ['Read', 'Write'], maxTurns: 12, timeout: 240_000, model: 'fake-model' });
+        expect(call.userPrompt).toContain('Proceed to Mode Selection,');
+        expect(call.userPrompt).not.toMatch(/Step 0[A-Z]/);
+        expect(call.userPrompt).toContain(join(call.workingDirectory, 'plan-ceo-review', 'SKILL.md'));
+        expect(call.userPrompt).toContain('Do NOT search for, Glob, find, or read any OTHER SKILL.md');
+        expect(call.userPrompt).toContain('Ask the user through the AskUserQuestion tool and wait for their answer.');
+        expect(call).toMatchObject({ allowedTools: ['Read', 'Write', 'AskUserQuestion'], maxTurns: 12, maxRetries: 0, model: 'fake-model' });
       }
     } finally { rmSync(dir, { recursive: true, force: true }); }
   });