fix(rectification): stop stamping pending receipts and document aggregate blocker

Implement BUG-984 F2 option A and reproduce mixed completed identities through real tools. Stop at the required SQL authorization boundary; F1/F3/F4 remain pending.

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

frontend/tests/rectification-engine-version-cross-midnight.test.ts

@@ -109,7 +109,11 @@ test("unreachable versions retain the existing unknown-identity cache fallback,
   assert.equal(cachedEngineScoreIsReusable({ ...fingerprints, algorithmVersion: PREVIOUS }, fingerprints, live), true);
 });
 
-test("new Case scoring writes the new version on both started and completed receipts", async (t) => {
+async function runGoldenToolSequence(t: test.TestContext, options: {
+  compareVersion?: string;
+  diagnosticsVersion?: string;
+  diagnosticsFailure?: boolean;
+} = {}) {
   isolateIdentityEnv(t);
   const request = golden.request;
   const candidateRange = { start_time: request.start_time, end_time: request.end_time };
@@ -123,7 +127,13 @@ test("new Case scoring writes the new version on both started and completed rece
     const path = new URL(String(url)).pathname;
     calls.push(path);
     if (path.endsWith("/versions")) return Response.json(golden.versions);
-    if (path.endsWith("/score") || path.endsWith("/diagnostics")) return Response.json(golden.score);
+    if (path.endsWith("/score")) {
+      return Response.json({ ...golden.score, algorithm_version: options.compareVersion ?? CURRENT });
+    }
+    if (path.endsWith("/diagnostics")) {
+      if (options.diagnosticsFailure) return Response.json({ error: "fixture_unavailable" }, { status: 503 });
+      return Response.json({ ...golden.score, algorithm_version: options.diagnosticsVersion ?? CURRENT });
+    }
     throw new Error(`unexpected engine request ${path}`);
   });
   const accounting = fakeAccounting({
@@ -152,15 +162,44 @@ test("new Case scoring writes the new version on both started and completed rece
   });
   const tools = createRectificationV9Tools({ userId: USER_ID, caseId: CASE_ID, turnId: TURN_ID, accounting: accounting.client as never });
   for (const name of ["rectification-compare-candidates", "rectification-read-diagnostics"] as const) {
-    await (tools[name] as unknown as { execute(input: unknown): Promise<unknown> }).execute({ caseId: CASE_ID });
-    const receipts = accounting.calls.filter((call) => call.fn === "insert_agentic_rectification_tool_receipt" && call.args.p_tool_name === name);
-    assert.deepEqual(receipts.map((call) => [call.args.p_status, call.args.p_engine_version]), [
-      ["started", CURRENT], ["completed", CURRENT],
-    ]);
+    const execute = () => (tools[name] as unknown as { execute(input: unknown): Promise<unknown> }).execute({ caseId: CASE_ID });
+    if (options.diagnosticsFailure && name === "rectification-read-diagnostics") await assert.rejects(execute);
+    else await execute();
   }
   assert.ok(calls.includes("/api/rectification/v5/score"));
   const persisted = accounting.calls.find((call) => call.fn === "persist_agentic_rectification_candidate_v2");
-  assert.equal(persisted?.args.p_algorithm_version, CURRENT);
+  assert.equal(persisted?.args.p_algorithm_version, options.compareVersion ?? CURRENT);
+  return accounting.calls.filter((call) => call.fn === "insert_agentic_rectification_tool_receipt");
+}
+
+test("new Case scoring writes actual identity only on completed receipts", async (t) => {
+  const receipts = await runGoldenToolSequence(t);
+  assert.deepEqual(receipts.map((call) => [call.args.p_status, call.args.p_engine_version]), [
+    // 原值: started=CURRENT；新值: null；原因: BUG-984，开始不是成功结果身份。
+    ["started", null], ["completed", CURRENT], ["started", null], ["completed", CURRENT],
+  ]);
+});
+
+test("failed diagnostics do not claim an engine result identity", async (t) => {
+  const receipts = await runGoldenToolSequence(t, { diagnosticsFailure: true });
+  assert.deepEqual(receipts.map((call) => [call.args.p_status, call.args.p_engine_version]), [
+    ["started", null], ["completed", CURRENT], ["started", null], ["failed", null],
+  ]);
+});
+
+test("BUG-984 blocker: real tool sequence permits mixed completed identities in one turn", async (t) => {
+  // Identity-only mutation models rolling backend versions; all response shape and values
+  // remain the real native golden. This is not a claim to have run future algorithms.
+  const version9 = "rectification-v5-matrix-scoring-9";
+  const version10 = "rectification-v5-matrix-scoring-10";
+  const receipts = await runGoldenToolSequence(t, { compareVersion: version9, diagnosticsVersion: version10 });
+  const completed = receipts.filter((call) => call.args.p_status === "completed");
+  assert.equal(new Set(completed.map((call) => call.args.p_turn_id)).size, 1);
+  assert.deepEqual(completed.map((call) => call.args.p_engine_version), [version9, version10]);
+  // Preserve the blocker as positive evidence, not a false passing acceptance test.
+  // F2 acceptance must replace this diagnostic once the approved aggregate fix lands.
+  assert.equal([version9, version10].sort().at(-1), version9);
+  assert.notEqual([version9, version10].sort().at(-1), completed.at(-1)?.args.p_engine_version);
 });
 
 test("history opens with its bound Skill and reads old engine receipt values unchanged", async (t) => {