diff --git a/test/helpers/claude-pty-runner.ts b/test/helpers/claude-pty-runner.ts
index 5e4c84f13..f06ba05f3 100644
--- a/test/helpers/claude-pty-runner.ts
+++ b/test/helpers/claude-pty-runner.ts
@@ -1402,6 +1402,27 @@ export interface PlanSkillObservation {
    * the section, and that's the regression we want to catch.
    */
   planFile?: string;
+  /**
+   * High-water-mark flag: did the polling loop ever observe a
+   * prose-rendered AskUserQuestion (lettered or numbered options visible)
+   * during the run? Set true the first poll iteration that
+   * isProseAUQVisible returns true on the recent buffer; remains true
+   * for the rest of the observation.
+   *
+   * The 2KB `evidence` window often misses the prose-AUQ moment because
+   * by the time outcome=plan_ready fires, the ExitPlanMode "Ready to
+   * execute" UI has pushed the options out of the tail. Tests that need
+   * to assert "the user saw the question at SOME point" should check
+   * this flag rather than re-running isProseAUQVisible on the truncated
+   * evidence.
+   */
+  proseAUQEverObserved?: boolean;
+  /**
+   * High-water-mark flag: did the LLM judge ever return state='waiting'
+   * during the run? Same shape as proseAUQEverObserved but driven by the
+   * Haiku judge fallback rather than the regex detector.
+   */
+  waitingEverObserved?: boolean;
 }
 
 /**
@@ -1543,6 +1564,8 @@ export async function runPlanSkillObservation(opts: {
           ...classified,
           evidence: visible.slice(-2000),
           elapsedMs: Date.now() - startedAt,
+          proseAUQEverObserved,
+          waitingEverObserved,
         };
         // Capture the plan file path on any outcome where one may have been
         // written. Gating only on 'plan_ready' missed two cases: (1) the
@@ -1594,6 +1617,8 @@ export async function runPlanSkillObservation(opts: {
             : ''),
         evidence: finalVisible.slice(-2000),
         elapsedMs: Date.now() - startedAt,
+        proseAUQEverObserved,
+        waitingEverObserved,
       };
     }
     return {
@@ -1605,6 +1630,8 @@ export async function runPlanSkillObservation(opts: {
           : ''),
       evidence: finalVisible.slice(-2000),
       elapsedMs: Date.now() - startedAt,
+      proseAUQEverObserved,
+      waitingEverObserved,
     };
   } finally {
     await session.close();
diff --git a/test/skill-e2e-autoplan-auto-mode.test.ts b/test/skill-e2e-autoplan-auto-mode.test.ts
index 8c94bad2f..2af602050 100644
--- a/test/skill-e2e-autoplan-auto-mode.test.ts
+++ b/test/skill-e2e-autoplan-auto-mode.test.ts
@@ -66,8 +66,8 @@ describeE2E('autoplan AskUserQuestion-blocked smoke (gate)', () => {
     //   3. Numbered/lettered options visible in TTY as prose (post-v1.28 prose-AUQ rendering)
     // If NONE of these are present, the question was silently buried.
     const blockedVisible = /BLOCKED\s*[—-]\s*AskUserQuestion/i.test(obs.evidence);
-    const proseAUQVisible = isProseAUQVisible(obs.evidence);
-    const surfaceVisible = blockedVisible || proseAUQVisible;
+    const proseAUQVisible = isProseAUQVisible(obs.evidence) || obs.proseAUQEverObserved === true;
+    const surfaceVisible = blockedVisible || proseAUQVisible || obs.waitingEverObserved === true;
 
     if (
       obs.outcome === 'auto_decided' ||
diff --git a/test/skill-e2e-plan-ceo-plan-mode.test.ts b/test/skill-e2e-plan-ceo-plan-mode.test.ts
index b75f5d6f3..f22f6baf8 100644
--- a/test/skill-e2e-plan-ceo-plan-mode.test.ts
+++ b/test/skill-e2e-plan-ceo-plan-mode.test.ts
@@ -115,8 +115,8 @@ describeE2E('plan-ceo-review plan-mode smoke (gate)', () => {
     //   2. `BLOCKED — AskUserQuestion` string visible in TTY (post-v1.28 BLOCKED rule)
     //   3. Numbered/lettered options visible in TTY as prose (post-v1.28 prose-AUQ rendering)
     const blockedVisible = /BLOCKED\s*[—-]\s*AskUserQuestion/i.test(obs.evidence);
-    const proseAUQVisible = isProseAUQVisible(obs.evidence);
-    const surfaceVisible = blockedVisible || proseAUQVisible;
+    const proseAUQVisible = isProseAUQVisible(obs.evidence) || obs.proseAUQEverObserved === true;
+    const surfaceVisible = blockedVisible || proseAUQVisible || obs.waitingEverObserved === true;
 
     if (
       obs.outcome === 'auto_decided' ||
diff --git a/test/skill-e2e-plan-design-plan-mode.test.ts b/test/skill-e2e-plan-design-plan-mode.test.ts
index fcf1fd94b..9c93a7a9e 100644
--- a/test/skill-e2e-plan-design-plan-mode.test.ts
+++ b/test/skill-e2e-plan-design-plan-mode.test.ts
@@ -63,8 +63,8 @@ describeE2E('plan-design-review plan-mode smoke (gate)', () => {
     // Surface visibility check (same as ceo / autoplan migrations): user
     // must SEE the question via BLOCKED string OR prose-rendered AUQ options.
     const blockedVisible = /BLOCKED\s*[—-]\s*AskUserQuestion/i.test(obs.evidence);
-    const proseAUQVisible = isProseAUQVisible(obs.evidence);
-    const surfaceVisible = blockedVisible || proseAUQVisible;
+    const proseAUQVisible = isProseAUQVisible(obs.evidence) || obs.proseAUQEverObserved === true;
+    const surfaceVisible = blockedVisible || proseAUQVisible || obs.waitingEverObserved === true;
 
     if (
       obs.outcome === 'auto_decided' ||
diff --git a/test/skill-e2e-plan-eng-plan-mode.test.ts b/test/skill-e2e-plan-eng-plan-mode.test.ts
index 82bbd6ed2..eea1fb5be 100644
--- a/test/skill-e2e-plan-eng-plan-mode.test.ts
+++ b/test/skill-e2e-plan-eng-plan-mode.test.ts
@@ -83,8 +83,8 @@ describeE2E('plan-eng-review plan-mode smoke (gate)', () => {
     // section in the plan file (legacy) OR a BLOCKED string in TTY OR
     // prose-rendered AUQ options in TTY.
     const blockedVisible = /BLOCKED\s*[—-]\s*AskUserQuestion/i.test(obs.evidence);
-    const proseAUQVisible = isProseAUQVisible(obs.evidence);
-    const surfaceVisible = blockedVisible || proseAUQVisible;
+    const proseAUQVisible = isProseAUQVisible(obs.evidence) || obs.proseAUQEverObserved === true;
+    const surfaceVisible = blockedVisible || proseAUQVisible || obs.waitingEverObserved === true;
 
     if (
       obs.outcome === 'auto_decided' ||