v1.26.2.0 fix: plan-eng-review STOP gates always fire AskUserQuestion + report-at-bottom contract enforcement (#1313)

* fix(plan-eng-review): tighten STOP gates with anti-rationalization clause

Five sites in SKILL.md.tmpl uplift to the office-hours b512be71 pattern:
the four review-section gates (Architecture, Code Quality, Test, Performance)
plus the Step 0 complexity-check trigger. Adds tool_use reminder ("call the
tool directly"), names blocked next steps explicitly, anti-rationalization
clause naming the precise failure mode (loading the schema via ToolSearch
and writing the recommendation as chat prose).

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

* feat(test/helpers): initialPlanContent + wrote_findings_before_asking + shared report-at-bottom assertion

Three additions to claude-pty-runner.ts:

1. runPlanSkillObservation gains initialPlanContent?: string. Pre-pumps a
   user message containing the seeded plan before invoking the skill, with
   a 3s gap so the message renders before the slash command. claude has no
   --plan-file flag (verified via claude --help), so message-pump is the
   route. Lets STOP-gate regression tests force complexity findings.

2. ClassifyResult gains wrote_findings_before_asking with companion
   strictPlanWrites?: boolean opt on classifyVisible. Fires when a Write/
   Edit to .claude/plans/* precedes any AskUserQuestion render in the
   session window. Default off — preserves zero-findings → write plan →
   plan_ready as legitimate for unseeded smokes. Six new unit tests cover
   before/after-AUQ ordering, permission-dialog edge case, strict-off path.

3. assertReportAtBottomIfPlanWritten(obs) shared helper. Wraps the existing
   assertReviewReportAtBottom(content) and gates on obs.planFile (artifact
   existing), so the assertion fires under both 'asked' and 'plan_ready'
   when a plan was actually written.

Also: runPlanSkillObservation now captures obs.planFile on every classifier
outcome, not just 'plan_ready'. Catches the case where the skill wrote a
plan partway through then paused on a question.

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

* 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>

* fix(touchfiles): delete duplicate plan-design-review-plan-mode keys

Verified duplicates in test/helpers/touchfiles.ts:
- E2E_TOUCHFILES had plan-design-review-plan-mode at line 94 (full deps)
  AND line 243 (smaller deps); JS object literals: later wins.
- E2E_TIERS had it at line 399 ('gate') AND line 524 ('periodic'); same
  later-wins rule.

Effective tier was 'periodic', not 'gate'. Three of four plan-mode siblings
ran on every PR; design ran weekly only.

Delete the line-243 and line-524 duplicates. Keep line 94 (full deps) and
line 399 ('gate'). Also extend the four plan-mode-test entries to include
scripts/resolvers/review.ts so changes to {{PLAN_FILE_REVIEW_REPORT}}
trigger all four siblings in bun run eval:select.

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

* chore: bump version and changelog (v1.26.2.0)

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

* docs: tighten CHANGELOG voice for v1.26.2.0

Move contributor-flavored bullet (runPlanSkillObservation seeding) into
For contributors. Drop branch-internal narrative (Codex review pass,
plan iteration tracking) per CHANGELOG-for-users style.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

---------

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

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);
 });