test: PTY harness handles clipped reviews and bundled setup tabs; AUQ judge uses structured output; design-consultation carve declines optional outside voices

- ceo mode routing: a Submit review taller than the viewport, a setup tab
  bundled after the mode tab, and a clip through the mode question each hung
  or misread the run; the native answer is still verified after Submit.
- judgeRecommendation requests a 1-5 enum schema; a malformed Haiku reply had
  scored substance 0 for a 4/5 brief. Judge failures now propagate.
- carve section-loading for design-consultation declines the optional outside
  voices (a supported path) and treats DESIGN.md as the report; timeout unchanged.
The Step 0E handoff defect is not fixed (0/15 samples across four wordings,
none shipped) and is filed in TODOS.

test/helpers/auq-sdk-capture.ts

@@ -53,7 +53,8 @@ export function scoreAuqFormat(text: string): { present: number; total: number;
  * whether the ORIGINAL used the literal "because" — a soft style signal, since
  * the format spec prefers it and the voice rule forbids the em-dash form.
  *
- * This does NOT touch judgeRecommendation or its pinned fixtures.
+ * This does NOT touch judgeRecommendation or its pinned fixtures. A judge
+ * failure propagates with its cause; it is never reported as substance 0.
  */
 export async function gradeAuqRecommendation(
   text: string,
@@ -75,12 +76,8 @@ export async function gradeAuqRecommendation(
     }
   }
 
-  try {
-    const r = await judgeRecommendation(graded);
-    return { substance: r.reason_substance, present: r.present, hadLiteralBecause, reason: r.reason_text };
-  } catch {
-    return { substance: 0, present: !!recLine, hadLiteralBecause, reason: '' };
-  }
+  const r = await judgeRecommendation(graded);
+  return { substance: r.reason_substance, present: r.present, hadLiteralBecause, reason: r.reason_text };
 }
 
 /**

test/helpers/carve-guards.ts

@@ -387,7 +387,7 @@ do not launch the downstream skill or open a browser.`,
     expectedSections: ['proposal-and-preview.md'],
     requiredReads: ['proposal-and-preview.md'],
     scenario:
-      'The user gave product context (a B2B analytics dashboard for ops teams) and declined the research phase. Skip browser/design tool setup. Proceed to build the complete design-system proposal, then write DESIGN.md. Produce the proposal and the DESIGN.md content.',
+      'The user gave product context (a B2B analytics dashboard for ops teams), declined the research phase and declined the optional outside design voices. Skip browser/design tool setup. Proceed to build the complete design-system proposal, then write DESIGN.md and its CLAUDE.md guidance.',
     staticInvariants: {
       mustStayInSkeleton: ['## Phase 0: Pre-checks', '## Phase 1: Product Context', '## Phase 2: Research'],
       mustMoveToSection: ['## Phase 3: The Complete Proposal', '## Phase 6: Write DESIGN.md'],

test/helpers/carve-section-case.ts

@@ -108,11 +108,15 @@ export function registerCarveSectionCase(skill: string): void {
             ? '- Proceed directly with the requested engineering review; skip the optional /office-hours prerequisite. You represent the plan author, whose scope and proposed steps are in PLAN.md. At each decision, choose the complete alternative that preserves those requirements and existing contracts; choose the recommended option only among alternatives within that scope. Do not authorize optional scope, extra public input guarantees, arbitrary size limits, or optional proof projects. Decline work explicitly listed out of scope, including creating TODOs for it. Record the decision and its actual authority as the skill requires, then continue without asking a human. A demonstrated incompatibility or missing required proof still requires resolution; do not hide it or claim approval when no offered alternative meets these constraints.'
             : undefined,
           // Both plan reviews persist their required report in the reviewed plan.
-          reportFile: ['plan-devex-review', 'plan-eng-review'].includes(guard.skill) ? 'PLAN.md' : undefined,
+          // design-consultation's final output is DESIGN.md itself; a second
+          // REPORT.md only duplicated the proposal (census 36641820398 timeout).
+          reportFile: ['plan-devex-review', 'plan-eng-review'].includes(guard.skill) ? 'PLAN.md'
+            : guard.skill === 'design-consultation' ? 'DESIGN.md' : undefined,
           // This scenario produces an HTML implementation, whose complete
           // document need not contain any of the prose report keywords.
           reportMarker: guard.skill === 'design-html'
             ? /<!doctype\s+html\s*>\s*<html\b[^>]*>[\s\S]*?<head\b[^>]*>[\s\S]*?<\/head\s*>[\s\S]*?<body\b[^>]*>[\s\S]*?<\/body\s*>\s*<\/html\s*>/i
+            : guard.skill === 'design-consultation' ? /^# gstack: design-md-format=spec$/m
             : /report|review|summary|design doc|handoff/i,
           testName: `${guard.skill} section-loading`,
           runId,
@@ -125,7 +129,7 @@ export function registerCarveSectionCase(skill: string): void {
         });
         // Require the HTML artifact itself; a terminal-only claim is insufficient.
         // captureSectionReads already requires a successful native completion.
-        const reportProduced = completionMarked && (guard.skill !== 'design-html' || reportWritten);
+        const reportProduced = completionMarked && (!['design-html', 'design-consultation'].includes(guard.skill) || reportWritten);
 
         const missing = guard.requiredReads.filter((s) => !readSections.has(s));
         // Named failure output (codex #2): skill + expected + observed.

test/helpers/ceo-mode-option.ts

@@ -146,6 +146,77 @@ function hasNativePostureProse(text: string, posture: RegExp): boolean {
   return hasPostAnswerCeoPosture(`● ${prose}`, posture);
 }
 
+const CLIPPED_PREFIX_MIN = 120;
+
+/**
+ * A review taller than the viewport can clip its heading and earlier questions
+ * before they ever render, and it truncates a long question with "…". Authenticate
+ * the visible tail from the Submit prompt backwards: every visible answer is an
+ * offered option, each question below the clip matches its native text (or a long
+ * native prefix before "…"), the mode question's target answer is visible, and only
+ * the topmost segment may be cut off above the viewport; a cut mode question must
+ * still show a long native tail. The native answer is verified again after Submit.
+ */
+function clippedReviewMatches(visible: string, selected: NativePlanQuestionCall,
+  modeQuestion: NativePlanQuestionCall['questions'][number], targetMode: CeoMode): boolean {
+  const compact = (text: string) => text.replace(/\s+/g, '');
+  let body = compact(visible.replace(/^[ \t]*[│┃] ?/gm, '').replace(/^[ \t]*[●⏺] ?/gm, ''));
+  if (!body.endsWith(BARLESS_SUBMIT_END) || /[←☐☒]/.test(body)) return false;
+  body = body.slice(0, -BARLESS_SUBMIT_END.length);
+  const modeIndex = selected.questions.indexOf(modeQuestion);
+  for (let i = selected.questions.length - 1; i >= 0; i--) {
+    const question = selected.questions[i]!;
+    const answers = (i === modeIndex
+      ? question.options.filter(o => modeTitle(o.label) === targetMode.replace(/\s+/g, ''))
+      : question.options).map(o => `→${compact(o.label)}`).filter(answer => body.endsWith(answer));
+    if (answers.length !== 1) return false;
+    body = body.slice(0, -answers[0]!.length);
+    const text = compact(question.question);
+    let shown = 0;
+    if (body.endsWith(text)) shown = text.length;
+    else if (body.endsWith('…')) {
+      for (let length = text.length - 1; length >= CLIPPED_PREFIX_MIN && !shown; length--) {
+        if (body.slice(0, -1).endsWith(text.slice(0, length))) shown = length + 1;
+      }
+    }
+    if (!shown) {
+      if (i > modeIndex || (i === modeIndex && body.replace(/…$/, '').length < CLIPPED_PREFIX_MIN)) return false;
+      return body.endsWith('…') ? text.includes(body.slice(0, -1)) : text.endsWith(body);
+    }
+    body = body.slice(0, -shown);
+    if (!body) return i <= modeIndex;
+  }
+  return 'Reviewyouranswers'.endsWith(body);
+}
+
+/**
+ * A packet can bundle setup tabs after the mode tab. Once the mode tab is
+ * answered, answer each later non-mode tab of the same unsubmitted call once,
+ * with the navigation rule (prerequisite pick, else option 1), so Submit is reachable.
+ */
+export function ceoModePacketTabAnswer(
+  visible: string, selected: NativePlanQuestionCall | undefined, transcript: PlanCountTranscript, answered: Set<string>,
+): { question: AskUserQuestionFingerprint; index: number } | null {
+  if (!selected || !selected.sessionId || !selected.toolUseId || transcript.status !== 'ready' ||
+      selected.questions.length < 2 || selected.questions.length > 4 || selected.questions.some(q => q.multiSelect)) return null;
+  const id = `${selected.sessionId}:${selected.toolUseId}`;
+  const current = transcript.calls.filter(call => `${call.sessionId}:${call.toolUseId}` === id);
+  if (current.length !== 1 || current[0]!.answered || current[0]!.failed ||
+      JSON.stringify(current[0]!.questions) !== JSON.stringify(selected.questions)) return null;
+  const bar = posturePacketBar(visible);
+  if (!bar || JSON.stringify(bar.headers) !== JSON.stringify(selected.questions.map(q => q.header.trim().replace(/\s+/g, ' ')))) return null;
+  const modeIndex = selected.questions.findIndex(q => q.options.filter(o => modeTitle(o.label)).length >= 2);
+  if (modeIndex < 0 || !bar.answered[modeIndex]) return null;
+  const question = capturePlanCountQuestion(visible, new Set(), 0, true, selected);
+  const tab = question?.nativeQuestionIndex;
+  if (!question || question.nativeCall !== selected || tab === undefined || tab <= modeIndex || bar.answered[tab] ||
+      JSON.stringify(question.options.map(o => o.label)) !== JSON.stringify(selected.questions[tab]!.options.map(o => o.label))) return null;
+  const key = `${id}:${tab}`;
+  if (answered.has(key)) return null;
+  answered.add(key);
+  return { question, index: planCountPrerequisitePick(question) ?? 1 };
+}
+
 /** Finish the selected native mode packet before waiting for its answer. */
 export function ceoModeSubmissionInput(
   visible: string, selected: NativePlanQuestionCall | undefined, targetMode: CeoMode,
@@ -178,6 +249,11 @@ export function ceoModeSubmissionInput(
     // focused Submit prompt; the accumulated screen text then supplies the
     // one complete review panel, authenticated below exactly as with a bar.
     const heading = screenText.lastIndexOf('Review your answers');
+    if (heading < 0 && compact(screenText).endsWith(BARLESS_SUBMIT_END) &&
+        clippedReviewMatches(visible, selected, modeQuestions[0]!, targetMode)) {
+      submitted.add(id);
+      return '\r';
+    }
     if (heading < 0 || !compact(visible).endsWith(BARLESS_SUBMIT_END) ||
         quotedContext.test(screenText.slice(0, heading).split('\n').slice(-3).join('\n'))) return null;
     review = screenText.slice(heading);

test/helpers/llm-judge.ts

@@ -397,6 +397,16 @@ ${text}`, undefined, { signal });
  * Format spec: scripts/resolvers/preamble/generate-ask-user-format.ts
  *   Recommendation: <choice> because <one-line reason>
  */
+export const RECOMMENDATION_JUDGE_SCHEMA = {
+  type: 'object',
+  properties: {
+    reason_substance: { type: 'integer', enum: [1, 2, 3, 4, 5] },
+    reasoning: { type: 'string' },
+  },
+  required: ['reason_substance', 'reasoning'],
+  additionalProperties: false,
+};
+
 export async function judgeRecommendation(askUserText: string, signal?: AbortSignal): Promise<RecommendationScore> {
   signal?.throwIfAborted();
   // Deterministic checks. The format spec requires:
@@ -472,7 +482,7 @@ Respond with ONLY valid JSON:
   const out = await callJudge<{ reason_substance: number; reasoning: string }>(
     prompt,
     'claude-haiku-4-5-20251001',
-    { signal },
+    { signal, jsonSchema: RECOMMENDATION_JUDGE_SCHEMA },
   );
 
   // Defensive clamp: rubric is 1-5. If Haiku returns out-of-range or non-numeric,