From 4f9e43c7cb8ba860bcde32d489f2464103ae2700 Mon Sep 17 00:00:00 2001
From: Garry Tan <garrytan@gmail.com>
Date: Tue, 5 May 2026 17:29:37 -0700
Subject: [PATCH] test: static template assertions for delete-then-append +
 revert autoplan E2E shape

5 new static tests in test/gen-skill-docs.test.ts (4 plan-review SKILL.md
files + 1 source resolver) verify the new prompt language is present and
the old contradictory bullets are absent. Synthetic regression check
confirmed all 5 fail when the prompt fix is reverted.

The autoplan E2E (skill-e2e-autoplan-auto-mode.test.ts) reverts to its
original AUQ-blocked-gate-surface shape. The mid-file regression scenario
the plan briefly proposed isn't reachable in the current PTY harness because
--disallowedTools AskUserQuestion makes autoplan bail at the Phase 1
premise gate before any review-write code path runs. Static prompt-text
verification covers the load-bearing change.
---
 test/gen-skill-docs.test.ts               | 45 +++++++++++++++++++++++
 test/skill-e2e-autoplan-auto-mode.test.ts | 10 +++++
 2 files changed, 55 insertions(+)

diff --git a/test/gen-skill-docs.test.ts b/test/gen-skill-docs.test.ts
index aa2e2d9f..7249a448 100644
--- a/test/gen-skill-docs.test.ts
+++ b/test/gen-skill-docs.test.ts
@@ -2977,3 +2977,48 @@ describe('plan-mode-info resolver (handshake-replacement)', () => {
     expect(between).toContain('Do NOT proceed to Step 0D or 0F until the user responds to 0C-bis');
   });
 });
+
+// GSTACK REVIEW REPORT report-at-bottom contract — verifies the prompt-text
+// fix in scripts/resolvers/review.ts (the load-bearing change for the
+// "report not at bottom of plan in plan mode" bug). The bug is in the
+// prompt's contradictory write-flow instructions, not in observable
+// runtime behavior we can cheaply gate in CI. Verifying the prompt text
+// directly is the deterministic equivalent of the regression test the
+// PTY harness can't reliably drive (autoplan needs auto-progression of
+// AskUserQuestions to reach the report-write step, which the harness
+// doesn't support today).
+describe('GSTACK REVIEW REPORT delete-then-append flow', () => {
+  const PLAN_REVIEW_SKILLS = [
+    'plan-ceo-review',
+    'plan-design-review',
+    'plan-devex-review',
+    'plan-eng-review',
+  ];
+
+  for (const skill of PLAN_REVIEW_SKILLS) {
+    test(`${skill}/SKILL.md prescribes delete-then-append, not in-place replace`, () => {
+      const content = fs.readFileSync(path.join(ROOT, skill, 'SKILL.md'), 'utf-8');
+
+      // The new (correct) instruction must be present.
+      expect(content).toContain('delete-then-append flow');
+      expect(content).toContain('never mid-file');
+      expect(content).toContain('Do NOT replace the section in place');
+
+      // The old contradictory bullets must be gone. The signature phrase
+      // from the buggy prompt was 'replace it entirely using the Edit tool'
+      // which is what allowed mid-file reports to stay mid-file.
+      expect(content).not.toContain('replace it** entirely using the Edit tool');
+      expect(content).not.toContain('If it was found mid-file, move it');
+    });
+  }
+
+  test('scripts/resolvers/review.ts source has the rewritten flow', () => {
+    const src = fs.readFileSync(path.join(ROOT, 'scripts', 'resolvers', 'review.ts'), 'utf-8');
+    expect(src).toContain('delete-then-append flow');
+    expect(src).toContain('never mid-file');
+    expect(src).toContain('Do NOT replace the section in place');
+    // Old contradictory bullets are gone from the source resolver.
+    expect(src).not.toContain('replace it** entirely using the Edit tool');
+    expect(src).not.toContain('If it was found mid-file, move it');
+  });
+});
diff --git a/test/skill-e2e-autoplan-auto-mode.test.ts b/test/skill-e2e-autoplan-auto-mode.test.ts
index f5fe84db..0677917b 100644
--- a/test/skill-e2e-autoplan-auto-mode.test.ts
+++ b/test/skill-e2e-autoplan-auto-mode.test.ts
@@ -18,6 +18,16 @@
  * Filename keeps `auto-mode` for branch-history continuity. Auto-mode (the
  * AUTO_DECIDE preamble path when QUESTION_TUNING=true) is a related but
  * distinct silencing mechanism; both share the same fix surface.
+ *
+ * Note on report-at-bottom contract: the GSTACK REVIEW REPORT delete-then-
+ * append flow lives in `scripts/resolvers/review.ts` and is exercised when
+ * reviews actually run. The PTY harness can't drive autoplan through its
+ * review phases without auto-progression of AUQs (see runPlanSkillCounting),
+ * and `--disallowedTools AskUserQuestion` makes autoplan bail at the
+ * premise gate via the plan-file fallback before any review runs. The
+ * report-at-bottom prompt change is verified statically in
+ * `test/gen-skill-docs.test.ts` instead — that's the load-bearing
+ * verification for the contradictory-prompt fix.
  */
 
 import { describe, test, expect } from 'bun:test';