test: wire assertReportAtBottomIfPlanWritten into 4 plan-mode E2E tests + add seeded-plan STOP-gate case

Every test case in skill-e2e-plan-{eng,ceo,design,devex}-plan-mode.test.ts
that produces a plan file now asserts ## GSTACK REVIEW REPORT is the last
## section. The {{PLAN_FILE_REVIEW_REPORT}} resolver mandated this contract;
nothing tested it until now.

Plan-eng additionally gains a third test case: STOP gate fires when seeded
plan forces Step 0 findings. Combines the new initialPlanContent runner
option with --disallowedTools AskUserQuestion to force the Conductor
MCP-variant path through mcp__*__AskUserQuestion. Asserts outcome NOT in
{wrote_findings_before_asking, auto_decided, silent_write, exited, timeout}
and that plan_ready outcomes carry a ## Decisions section.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

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

@@ -34,7 +34,11 @@
  */
 
 import { describe, test, expect } from 'bun:test';
-import { runPlanSkillObservation, planFileHasDecisionsSection } from './helpers/claude-pty-runner';
+import {
+  runPlanSkillObservation,
+  planFileHasDecisionsSection,
+  assertReportAtBottomIfPlanWritten,
+} from './helpers/claude-pty-runner';
 
 const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
 const describeE2E = shouldRun ? describe : describe.skip;
@@ -68,6 +72,7 @@ describeE2E('plan-ceo-review plan-mode smoke (gate)', () => {
           `--- evidence (last 2KB visible) ---\n${obs.evidence}`,
       );
     }
+    assertReportAtBottomIfPlanWritten(obs);
   }, 360_000);
 
   // v1.21+ regression: Conductor launches Claude Code with
@@ -129,5 +134,6 @@ describeE2E('plan-ceo-review plan-mode smoke (gate)', () => {
       }
     }
     expect(['asked', 'plan_ready']).toContain(obs.outcome);
+    assertReportAtBottomIfPlanWritten(obs);
   }, 360_000);
 });

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

@@ -10,7 +10,10 @@
  */
 
 import { describe, test, expect } from 'bun:test';
-import { runPlanSkillObservation, planFileHasDecisionsSection } from './helpers/claude-pty-runner';
+import {
+  runPlanSkillObservation,
+  assertReportAtBottomIfPlanWritten,
+} from './helpers/claude-pty-runner';
 
 const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
 const describeE2E = shouldRun ? describe : describe.skip;
@@ -32,6 +35,7 @@ describeE2E('plan-design-review plan-mode smoke (gate)', () => {
       );
     }
     expect(['asked', 'plan_ready']).toContain(obs.outcome);
+    assertReportAtBottomIfPlanWritten(obs);
   }, 360_000);
 
   // v1.21+ regression: see skill-e2e-plan-ceo-plan-mode.test.ts for the
@@ -68,5 +72,6 @@ describeE2E('plan-design-review plan-mode smoke (gate)', () => {
     // Other plan-mode skills require the decisions section under
     // --disallowedTools; design is the special case.
     expect(['asked', 'plan_ready']).toContain(obs.outcome);
+    assertReportAtBottomIfPlanWritten(obs);
   }, 360_000);
 });

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

@@ -6,7 +6,11 @@
  */
 
 import { describe, test, expect } from 'bun:test';
-import { runPlanSkillObservation, planFileHasDecisionsSection } from './helpers/claude-pty-runner';
+import {
+  runPlanSkillObservation,
+  planFileHasDecisionsSection,
+  assertReportAtBottomIfPlanWritten,
+} from './helpers/claude-pty-runner';
 
 const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
 const describeE2E = shouldRun ? describe : describe.skip;
@@ -28,6 +32,7 @@ describeE2E('plan-devex-review plan-mode smoke (gate)', () => {
       );
     }
     expect(['asked', 'plan_ready']).toContain(obs.outcome);
+    assertReportAtBottomIfPlanWritten(obs);
   }, 360_000);
 
   // v1.21+ regression: see skill-e2e-plan-ceo-plan-mode.test.ts for the
@@ -64,5 +69,6 @@ describeE2E('plan-devex-review plan-mode smoke (gate)', () => {
       }
     }
     expect(['asked', 'plan_ready']).toContain(obs.outcome);
+    assertReportAtBottomIfPlanWritten(obs);
   }, 360_000);
 });

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

@@ -6,11 +6,45 @@
  */
 
 import { describe, test, expect } from 'bun:test';
-import { runPlanSkillObservation, planFileHasDecisionsSection } from './helpers/claude-pty-runner';
+import {
+  runPlanSkillObservation,
+  planFileHasDecisionsSection,
+  assertReportAtBottomIfPlanWritten,
+} from './helpers/claude-pty-runner';
 
 const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
 const describeE2E = shouldRun ? describe : describe.skip;
 
+// SEED_PLAN_FORCING_FINDINGS: 8+ files + custom-vs-builtin smell forces the
+// Step 0 complexity check to trigger. Passed via runPlanSkillObservation's
+// initialPlanContent (D3-B) so the spawned `claude` actually sees it.
+const SEED_PLAN_FORCING_FINDINGS = `
+# Parallelize unit tests
+
+## Plan
+Build a custom test runner: scripts/test-parallel.ts, scripts/test-shard-impl.ts,
+scripts/test-merge-results.ts, scripts/test-progress.ts, scripts/test-watch.ts,
+scripts/test-coverage.ts, scripts/test-cli.ts, scripts/test-config.ts.
+
+Add new TestRunner class, new ShardManager class, new ResultMerger class.
+
+Ignore Bun's native --shard flag because we want full control.
+
+## Files
+- scripts/test-parallel.ts (new)
+- scripts/test-shard-impl.ts (new)
+- scripts/test-merge-results.ts (new)
+- scripts/test-progress.ts (new)
+- scripts/test-watch.ts (new)
+- scripts/test-coverage.ts (new)
+- scripts/test-cli.ts (new)
+- scripts/test-config.ts (new)
+- package.json (add scripts)
+
+## Tests
+None planned — will add later.
+`;
+
 describeE2E('plan-eng-review plan-mode smoke (gate)', () => {
   test('reaches a terminal outcome (asked or plan_ready) without silent writes', async () => {
     const obs = await runPlanSkillObservation({
@@ -28,6 +62,7 @@ describeE2E('plan-eng-review plan-mode smoke (gate)', () => {
       );
     }
     expect(['asked', 'plan_ready']).toContain(obs.outcome);
+    assertReportAtBottomIfPlanWritten(obs);
   }, 360_000);
 
   // v1.21+ regression: see skill-e2e-plan-ceo-plan-mode.test.ts for the
@@ -64,5 +99,51 @@ describeE2E('plan-eng-review plan-mode smoke (gate)', () => {
       }
     }
     expect(['asked', 'plan_ready']).toContain(obs.outcome);
+    assertReportAtBottomIfPlanWritten(obs);
+  }, 360_000);
+
+  // D3-B / D4-B: when a plan with guaranteed-finding-triggering complexity
+  // is seeded, the skill MUST fire AskUserQuestion (or fall back to a
+  // Decisions section) before writing findings to the plan. The
+  // wrote_findings_before_asking outcome catches the precise transcript bug
+  // — model writes findings to the plan before any AUQ render.
+  test('STOP gate fires when seeded plan forces Step 0 findings', async () => {
+    const obs = await runPlanSkillObservation({
+      skillName: 'plan-eng-review',
+      inPlanMode: true,
+      initialPlanContent: SEED_PLAN_FORCING_FINDINGS,
+      // Force the Conductor-style path: native AUQ disallowed → the model
+      // must use mcp__*__AskUserQuestion (outcome='asked') or fall back to
+      // writing Decisions ('plan_ready').
+      extraArgs: ['--disallowedTools', 'AskUserQuestion'],
+      timeoutMs: 300_000,
+    });
+
+    if (
+      obs.outcome === 'wrote_findings_before_asking' ||
+      obs.outcome === 'auto_decided' ||
+      obs.outcome === 'silent_write' ||
+      obs.outcome === 'exited' ||
+      obs.outcome === 'timeout'
+    ) {
+      throw new Error(
+        `STOP-gate regression: outcome=${obs.outcome}\nsummary: ${obs.summary}\n` +
+          `elapsed: ${obs.elapsedMs}ms\n` +
+          `--- evidence (last 2KB) ---\n${obs.evidence}`,
+      );
+    }
+
+    if (obs.outcome === 'plan_ready') {
+      if (!obs.planFile || !planFileHasDecisionsSection(obs.planFile)) {
+        throw new Error(
+          `STOP-gate regression: plan_ready without ## Decisions section in ` +
+            `${obs.planFile ?? '<no plan file>'} — gate skipped after ToolSearch.\n` +
+            `--- evidence (last 2KB) ---\n${obs.evidence}`,
+        );
+      }
+    }
+
+    expect(['asked', 'plan_ready']).toContain(obs.outcome);
+    assertReportAtBottomIfPlanWritten(obs);
   }, 360_000);
 });