test: tighten plan-ceo-review smoke to require Step 0 fires first

Assertion narrows from ['asked', 'plan_ready'] to 'asked' only. Reaching
plan_ready first means the agent skipped Step 0 entirely and went
straight to ExitPlanMode — the regression we want to catch.

Why plan-ceo is special: unlike plan-eng / plan-design / plan-devex
(whose smokes legitimately reach plan_ready on certain branches without
asking), plan-ceo-review's template mandates Step 0A premise challenge
plus Step 0F mode selection BEFORE any plan write. There is no
legitimate path to plan_ready that does not first emit a skill-question
numbered prompt.

Failure message now branches on outcome (plan_ready vs timeout vs
silent_write) with a tailored diagnosis line per case. References the
skill template by section name ("Step 0 STOP rules", "One issue = one
AskUserQuestion call") instead of line numbers, so it survives template
edits.

Passes env: { QUESTION_TUNING: 'false', EXPLAIN_LEVEL: 'default' }
through the runner. Today this is advisory — gstack-config reads only
~/.gstack/config.yaml, not env vars — but the wiring is in place for a
future change. Documented honestly in the docstring.

Verified across 4 PTY runs: 3 pre-refactor + 1 post-refactor, all PASS.

test/skill-e2e-plan-ceo-plan-mode.test.ts

@@ -1,22 +1,34 @@
 /**
  * plan-ceo-review plan-mode smoke (gate, paid, real-PTY).
  *
- * Asserts: when /plan-ceo-review is invoked in plan mode, the skill reaches
+ * Asserts: when /plan-ceo-review is invoked in plan mode, the FIRST terminal
- * a terminal outcome that is either:
+ * outcome is 'asked' — a skill-question numbered list. Permission dialogs
- *   - 'asked'      — skill emitted its Step 0 numbered prompt (scope mode
+ * (which also render numbered lists) are filtered out by `runPlanSkillObservation`
- *                    selection, or the routing-injection prompt that runs
+ * via its `isPermissionDialogVisible(visible.slice(-1500))` short-circuit.
- *                    before Step 0)
- *   - 'plan_ready' — skill ran end-to-end and surfaced claude's native
- *                    "Ready to execute" confirmation
  *
- * FAIL conditions: silent Write/Edit before any prompt, claude crash,
+ * Reaching 'plan_ready' first IS the regression we want to catch: the agent
- * timeout.
+ * skipped Step 0 entirely and went straight to ExitPlanMode. The original
+ * failure had the assistant read a diff, write a plan with two issues, and
+ * call ExitPlanMode without ever firing AskUserQuestion — the user had to
+ * manually call out the missing per-issue questions.
  *
- * Replaces the SDK-based test that never worked: the SDK's canUseTool
+ * Why this skill is special: unlike plan-eng-review / plan-design-review /
- * interceptor on AskUserQuestion never fires in plan mode because plan
+ * plan-devex-review (whose smokes accept either 'asked' or 'plan_ready'),
- * mode renders its native confirmation as TTY UI, not via the
+ * plan-ceo-review's template mandates Step 0A premise challenge (3 baked-in
- * AskUserQuestion tool. The real PTY harness observes the rendered
+ * questions) AND Step 0F mode selection BEFORE any plan write. There is no
- * terminal output directly.
+ * legitimate path to plan_ready that does not first emit a skill-question
+ * numbered prompt.
+ *
+ * Env passthrough: passes `QUESTION_TUNING=false` and `EXPLAIN_LEVEL=default`
+ * via the runner's env option. Today these are advisory — `gstack-config`
+ * reads `~/.gstack/config.yaml`, not env vars, so a contributor with
+ * `question_tuning: true` set in their YAML config can still see AUTO_DECIDE
+ * masking. The env passthrough is wired so a future gstack-config change to
+ * honor env overrides will make this test hermetic without further edits.
+ * Tracked as a post-merge follow-up.
+ *
+ * FAIL conditions: 'plan_ready' first, silent Write/Edit before any prompt,
+ * claude crash, timeout.
  *
  * See test/helpers/claude-pty-runner.ts for runner internals.
  */
@@ -28,21 +40,33 @@ const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
 const describeE2E = shouldRun ? describe : describe.skip;
 
 describeE2E('plan-ceo-review plan-mode smoke (gate)', () => {
-  test('reaches a terminal outcome (asked or plan_ready) without silent writes', async () => {
+  test('first terminal outcome is asked (Step 0 fires before any plan write)', async () => {
     const obs = await runPlanSkillObservation({
       skillName: 'plan-ceo-review',
       inPlanMode: true,
       timeoutMs: 300_000,
+      env: { QUESTION_TUNING: 'false', EXPLAIN_LEVEL: 'default' },
     });
 
-    if (obs.outcome === 'silent_write' || obs.outcome === 'exited' || obs.outcome === 'timeout') {
+    if (obs.outcome !== 'asked') {
+      const diagnosis =
+        obs.outcome === 'plan_ready'
+          ? `'plan_ready' first means the agent skipped Step 0 entirely and went straight to ExitPlanMode without asking.`
+          : obs.outcome === 'timeout'
+            ? `Timeout means the agent neither asked nor completed within the budget — likely hung mid-question or stuck on a permission dialog.`
+            : obs.outcome === 'silent_write'
+              ? `Silent Write/Edit fired to an unsanctioned path before any AskUserQuestion — also a Step 0 skip.`
+              : `Outcome '${obs.outcome}' is unexpected; investigate the evidence below.`;
       throw new Error(
-        `plan-ceo-review plan-mode smoke FAILED: outcome=${obs.outcome}\n` +
+        `plan-ceo-review smoke FAILED: outcome=${obs.outcome}\n` +
+          `${diagnosis}\n` +
+          `Expected 'asked'. See plan-ceo-review/SKILL.md.tmpl: the Step 0 STOP rules ` +
+          `and the "One issue = one AskUserQuestion call" rule under "CRITICAL RULE — ` +
+          `How to ask questions".\n` +
           `summary: ${obs.summary}\n` +
           `elapsed: ${obs.elapsedMs}ms\n` +
           `--- evidence (last 2KB visible) ---\n${obs.evidence}`,
       );
     }
-    expect(['asked', 'plan_ready']).toContain(obs.outcome);
   }, 360_000);
 });