test(review): regression for #1539 pre-emit verification gate

12 tests pinning the gate behavior:

  - Resolver emits the gate header + #1539 reference
  - Gate requires quoting file:line + verbatim text
  - Unverified findings forced to confidence 4-5 (auto-suppress via
    existing <7-rule, no new mechanism)
  - Framework-meta nudge names Django, Rails, SQLAlchemy, TypeORM,
    Sequelize, Prisma
  - Deferred design doc reference present (1539-framework-aware-review.md)
  - Four named FP classes from #1539 enumerated:
      * field doesn't exist on model
      * dict.get() might be None
      * save() might lose fields
      * update_fields might miss X
  - All four downstream SKILL.md consumers (review, cso, plan-eng-review,
    ship) carry the gate text after gen:skill-docs
  - Existing confidence 9-10 'Show normally' + 3-4 'Suppress' rows
    unchanged (regression on existing behavior)

Failing build if the gate is removed, the suppression mechanism is
re-invented separately, the framework-meta nudge drops a framework, or
gen:skill-docs stops propagating the gate to consumers.

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

test/regression-1539-review-self-verify.test.ts

@@ -0,0 +1,105 @@
+/**
+ * Regression tests for #1539 — /review false positive rate on mature
+ * frameworks (Django, 4/8 FPs).
+ *
+ * The fix extends the Confidence Calibration resolver with a Pre-emit
+ * verification gate: every finding must quote the specific code line that
+ * motivates it; unverified findings are forced to confidence 4-5 so the
+ * existing suppression rule auto-fires.
+ *
+ * Tests pin:
+ *   - The resolver emits the gate text
+ *   - The regenerated SKILL.md files for all consumers carry the gate
+ *   - The framework-meta nudge is present
+ *   - The deferred-design-doc reference is present (T-Codex-2 split)
+ *   - Each named FP class from the issue has an explicit row in the gate
+ *
+ * No paid eval. The static invariants are the durable guarantees that the
+ * FP-killing mechanism doesn't regress — the LLM behavior under it is
+ * separately measured via E2E review evals when this branch is run with
+ * EVALS=1.
+ */
+import { describe, expect, test } from "bun:test";
+import * as fs from "node:fs";
+import * as path from "node:path";
+
+import { generateConfidenceCalibration } from "../scripts/resolvers/confidence";
+
+const ROOT = path.resolve(import.meta.dir, "..");
+
+describe("#1539 confidence resolver — pre-emit verification gate present", () => {
+  test("resolver text includes the gate header", () => {
+    const out = generateConfidenceCalibration({} as never);
+    expect(out).toMatch(/Pre-emit verification gate/);
+    expect(out).toMatch(/#1539/);
+  });
+
+  test("gate requires quoted code snippet (file:line + verbatim text)", () => {
+    const out = generateConfidenceCalibration({} as never);
+    expect(out).toMatch(/Quote the specific code line/);
+    expect(out).toMatch(/file:line/);
+    expect(out).toMatch(/verbatim text/);
+  });
+
+  test("unverified findings auto-suppressed via existing confidence rule", () => {
+    const out = generateConfidenceCalibration({} as never);
+    // The gate must hook the existing "<7 -> suppress" rule rather than
+    // invent new mechanism. Look for both forcing-to-4-5 AND a reference
+    // to suppression.
+    expect(out).toMatch(/Force its confidence to 4-5/);
+    expect(out).toMatch(/suppress/i);
+  });
+
+  test("framework-meta nudge present for Django/Rails/SQLAlchemy/TypeORM/Sequelize/Prisma", () => {
+    const out = generateConfidenceCalibration({} as never);
+    expect(out).toMatch(/Framework-meta nudge/);
+    expect(out).toMatch(/Django/);
+    expect(out).toMatch(/Rails/);
+    expect(out).toMatch(/SQLAlchemy/);
+    expect(out).toMatch(/TypeORM/);
+    expect(out).toMatch(/Sequelize/);
+    expect(out).toMatch(/Prisma/);
+  });
+
+  test("references the deferred design doc for framework-aware verification (T-Codex-2)", () => {
+    const out = generateConfidenceCalibration({} as never);
+    expect(out).toMatch(/1539-framework-aware-review\.md/);
+  });
+
+  test("enumerates the four FP classes the gate kills (#1539 named cases)", () => {
+    const out = generateConfidenceCalibration({} as never);
+    expect(out).toMatch(/field doesn't exist on model/);
+    expect(out).toMatch(/dict\.get\(\) might be None/);
+    expect(out).toMatch(/save\(\) might lose fields/);
+    expect(out).toMatch(/update_fields might miss/);
+  });
+});
+
+describe("#1539 generated SKILL.md files — gate propagated to all consumers", () => {
+  const consumers = [
+    "review/SKILL.md",
+    "cso/SKILL.md",
+    "plan-eng-review/SKILL.md",
+    "ship/SKILL.md",
+  ];
+
+  for (const rel of consumers) {
+    test(`${rel} carries the Pre-emit verification gate`, () => {
+      const body = fs.readFileSync(path.join(ROOT, rel), "utf-8");
+      expect(body).toMatch(/Pre-emit verification gate/);
+      expect(body).toMatch(/Quote the specific code line/);
+    });
+  }
+});
+
+describe("#1539 confidence suppression rule unchanged (regression on existing behavior)", () => {
+  test("confidence 3-4 row still says 'Suppress from main report'", () => {
+    const out = generateConfidenceCalibration({} as never);
+    expect(out).toMatch(/3-4[\s\S]{0,200}Suppress from main report/);
+  });
+
+  test("confidence 9-10 row preserves 'Show normally' behavior", () => {
+    const out = generateConfidenceCalibration({} as never);
+    expect(out).toMatch(/9-10[\s\S]{0,200}Show normally/);
+  });
+});