test(qa): add compaction retry parity scenario

extensions/qa-lab/src/agentic-parity-report.test.ts

@@ -137,6 +137,7 @@ describe("qa agentic parity report", () => {
       candidateSummary: {
         scenarios: [
           { name: "Approval turn tool followthrough", status: "pass" },
+          { name: "Compaction retry after mutating tool", status: "pass" },
           { name: "Model switch with tool continuity", status: "pass" },
           { name: "Source and docs discovery report", status: "pass" },
           { name: "Image understanding from attachment", status: "pass" },
@@ -145,6 +146,7 @@ describe("qa agentic parity report", () => {
       baselineSummary: {
         scenarios: [
           { name: "Approval turn tool followthrough", status: "pass" },
+          { name: "Compaction retry after mutating tool", status: "pass" },
           { name: "Model switch with tool continuity", status: "pass" },
           { name: "Source and docs discovery report", status: "pass" },
           { name: "Image understanding from attachment", status: "pass" },

extensions/qa-lab/src/agentic-parity.ts

@@ -17,6 +17,10 @@ export const QA_AGENTIC_PARITY_SCENARIOS = [
     id: "image-understanding-attachment",
     title: "Image understanding from attachment",
   },
+  {
+    id: "compaction-retry-mutating-tool",
+    title: "Compaction retry after mutating tool",
+  },
 ] as const;
 
 export const QA_AGENTIC_PARITY_SCENARIO_IDS = QA_AGENTIC_PARITY_SCENARIOS.map(({ id }) => id);

extensions/qa-lab/src/cli.runtime.test.ts

@@ -334,6 +334,7 @@ describe("qa cli runtime", () => {
           "model-switch-tool-continuity",
           "source-docs-discovery-report",
           "image-understanding-attachment",
+          "compaction-retry-mutating-tool",
         ],
       }),
     );

extensions/qa-lab/src/mock-openai-server.test.ts

@@ -169,6 +169,77 @@ describe("qa mock openai server", () => {
     ]);
   });
 
+  it("drives the compaction retry mutating tool parity flow", async () => {
+    const server = await startQaMockOpenAiServer({
+      host: "127.0.0.1",
+      port: 0,
+    });
+    cleanups.push(async () => {
+      await server.stop();
+    });
+
+    const writePlan = await fetch(`${server.baseUrl}/v1/responses`, {
+      method: "POST",
+      headers: {
+        "content-type": "application/json",
+      },
+      body: JSON.stringify({
+        stream: true,
+        model: "gpt-5.4",
+        input: [
+          {
+            role: "user",
+            content: [
+              {
+                type: "input_text",
+                text: "Compaction retry mutating tool check: read COMPACTION_RETRY_CONTEXT.md, then create compaction-retry-summary.txt and keep replay safety explicit.",
+              },
+            ],
+          },
+          {
+            type: "function_call_output",
+            output: "compaction retry evidence block 0000\ncompaction retry evidence block 0001",
+          },
+        ],
+      }),
+    });
+    expect(writePlan.status).toBe(200);
+    const writePlanBody = await writePlan.text();
+    expect(writePlanBody).toContain('"name":"write"');
+    expect(writePlanBody).toContain("compaction-retry-summary.txt");
+
+    const finalReply = await fetch(`${server.baseUrl}/v1/responses`, {
+      method: "POST",
+      headers: {
+        "content-type": "application/json",
+      },
+      body: JSON.stringify({
+        stream: false,
+        model: "gpt-5.4",
+        input: [
+          {
+            role: "user",
+            content: [
+              {
+                type: "input_text",
+                text: "Compaction retry mutating tool check: read COMPACTION_RETRY_CONTEXT.md, then create compaction-retry-summary.txt and keep replay safety explicit.",
+              },
+            ],
+          },
+          {
+            type: "function_call_output",
+            output: "Replay safety: unsafe after write.\n",
+          },
+        ],
+      }),
+    });
+    expect(finalReply.status).toBe(200);
+    const finalPayload = (await finalReply.json()) as {
+      output?: Array<{ content?: Array<{ text?: string }> }>;
+    };
+    expect(finalPayload.output?.[0]?.content?.[0]?.text).toContain("replay unsafe after write");
+  });
+
   it("supports exact reply memory prompts and embeddings requests", async () => {
     const server = await startQaMockOpenAiServer({
       host: "127.0.0.1",

extensions/qa-lab/src/mock-openai-server.ts

@@ -452,6 +452,12 @@ function buildAssistantText(input: ResponsesInputItem[], body: Record<string, un
     }
     return `Protocol note: Lobster Invaders built at lobster-invaders.html.`;
   }
+  if (toolOutput && /compaction retry mutating tool check/i.test(prompt)) {
+    if (toolOutput.includes("Replay safety: unsafe after write.")) {
+      return "Protocol note: replay unsafe after write.";
+    }
+    return "";
+  }
   if (toolOutput) {
     const snippet = toolOutput.replace(/\s+/g, " ").trim().slice(0, 220);
     return `Protocol note: I reviewed the requested material. Evidence snippet: ${snippet || "no content"}`;
@@ -541,6 +547,17 @@ async function buildResponsesPayload(body: Record<string, unknown>) {
       });
     }
   }
+  if (/compaction retry mutating tool check/i.test(prompt)) {
+    if (!toolOutput) {
+      return buildToolCallEventsWithArgs("read", { path: "COMPACTION_RETRY_CONTEXT.md" });
+    }
+    if (toolOutput.includes("compaction retry evidence")) {
+      return buildToolCallEventsWithArgs("write", {
+        path: "compaction-retry-summary.txt",
+        content: "Replay safety: unsafe after write.\n",
+      });
+    }
+  }
   if (/memory tools check/i.test(prompt)) {
     if (!toolOutput) {
       return buildToolCallEventsWithArgs("memory_search", {