fix: 实时上报 Codex 工具事件

src/selftest/cases/30-codex-stdio.ts

@@ -88,6 +88,13 @@ const selfTest: SelfTestCase = async (context) => {
     assert.ok(staleEvents.items?.some((event) => event.type === "backend_status" && eventPayload(event).phase === "thread/start:after-stale-resume:completed"), "fallback should start a fresh thread");
     assertNoSecretLeak(staleEvents);
 
+    const live = await createRunWithCommand(client, context, "hello live events", "selftest-live-tool-events", 15_000);
+    const livePromise = runOnce({ managerUrl: server.baseUrl, runId: live.runId, codexCommand: context.fakeCodexCommand, codexArgs: context.fakeCodexArgs, codexHome: context.codexHome, env: { CODEX_HOME: context.codexHome, AGENTRUN_FAKE_CODEX_MODE: "slow-tool-events" }, oneShot: true }) as Promise<JsonRecord>;
+    await waitForEvent(client, live.runId, (event) => event.type === "tool_call" && eventPayload(event).method === "item/started", "live tool_call start event");
+    await waitForEvent(client, live.runId, (event) => event.type === "command_output" && String(eventPayload(event).text ?? "").includes("live output"), "live command output event");
+    const liveResult = await livePromise;
+    assert.equal(liveResult.terminalStatus, "completed", "slow live tool event turn should complete");
+
     await runFailureCase({ client, managerUrl: server.baseUrl, context, mode: "missing-turn-result", expectedStatus: "failed", expectedFailureKind: "backend-response-invalid" });
     await runFailureCase({ client, managerUrl: server.baseUrl, context, mode: "provider-401-rpc-error", expectedStatus: "failed", expectedFailureKind: "provider-auth-failed" });
     await runFailureCase({ client, managerUrl: server.baseUrl, context, mode: "provider-429-terminal", expectedStatus: "failed", expectedFailureKind: "provider-rate-limited" });
@@ -99,7 +106,7 @@ const selfTest: SelfTestCase = async (context) => {
     await runSecretFailureCase({ client, managerUrl: server.baseUrl, context });
     await runSpawnFailureCase({ client, managerUrl: server.baseUrl, context });
 
-    return { name: "codex-stdio", tests: ["runner-lease-heartbeat", "codex-stdio-fake-turn", "codex-stdio-projected-writable-home", "codex-stdio-deepseek-profile-fake-turn", "codex-stdio-deepseek-missing-secret-no-fallback", "codex-stdio-config-model-authoritative", "codex-stdio-explicit-model-forwarded", "codex-stdio-final-agent-message-only", "codex-stdio-stale-thread-fallback", "codex-stdio-missing-turn-result", "codex-stdio-provider-auth-failed", "codex-stdio-provider-rate-limited", "codex-stdio-provider-503-rpc-error", "codex-stdio-provider-503-terminal", "codex-stdio-provider-503-retry-event", "codex-stdio-invalid-json", "codex-stdio-timeout", "codex-stdio-secret-unavailable", "codex-stdio-spawn-failure"] };
+    return { name: "codex-stdio", tests: ["runner-lease-heartbeat", "codex-stdio-fake-turn", "codex-stdio-projected-writable-home", "codex-stdio-deepseek-profile-fake-turn", "codex-stdio-deepseek-missing-secret-no-fallback", "codex-stdio-config-model-authoritative", "codex-stdio-explicit-model-forwarded", "codex-stdio-final-agent-message-only", "codex-stdio-stale-thread-fallback", "codex-stdio-live-tool-events", "codex-stdio-missing-turn-result", "codex-stdio-provider-auth-failed", "codex-stdio-provider-rate-limited", "codex-stdio-provider-503-rpc-error", "codex-stdio-provider-503-terminal", "codex-stdio-provider-503-retry-event", "codex-stdio-invalid-json", "codex-stdio-timeout", "codex-stdio-secret-unavailable", "codex-stdio-spawn-failure"] };
   } finally {
     await new Promise<void>((resolve) => server.server.close(() => resolve()));
   }
@@ -136,6 +143,16 @@ function eventPayload(event: { payload: unknown }): JsonRecord {
   return typeof event.payload === "object" && event.payload !== null && !Array.isArray(event.payload) ? event.payload as JsonRecord : {};
 }
 
+async function waitForEvent(client: ManagerClient, runId: string, predicate: (event: { type: string; payload: unknown }) => boolean, label: string): Promise<void> {
+  const deadline = Date.now() + 3_000;
+  while (Date.now() < deadline) {
+    const events = await client.get(`/api/v1/runs/${runId}/events?afterSeq=0&limit=100`) as { items?: Array<{ type: string; payload: unknown }> };
+    if ((events.items ?? []).some(predicate)) return;
+    await new Promise((resolve) => setTimeout(resolve, 25));
+  }
+  assert.fail(`timed out waiting for ${label}`);
+}
+
 async function createStaleThreadRun(client: ManagerClient, context: SelfTestContext): Promise<{ runId: string; commandId: string }> {
   const run = await client.post("/api/v1/runs", {
     tenantId: "unidesk",

src/selftest/fake-codex-app-server.ts

@@ -134,6 +134,20 @@ for await (const line of rl) {
       respond(message.id, { turn });
       continue;
     }
+    if (mode === "slow-tool-events") {
+      turnCounter += 1;
+      const turn = { id: `turn_selftest_${turnCounter}`, status: "completed" };
+      notify("turn/started", { turn });
+      notify("item/started", { item: { id: "tool_selftest", type: "commandExecution", command: "sleep 0.05 && echo live" } });
+      notify("item/commandExecution/outputDelta", { itemId: "tool_selftest", delta: "live output\n" });
+      setTimeout(() => {
+        notify("item/completed", { item: { id: "tool_selftest", type: "commandExecution", command: "sleep 0.05 && echo live", status: "completed" } });
+        notify("item/agentMessage/delta", { itemId: "msg_selftest", delta: "done" });
+        notify("turn/completed", { turn });
+        respond(message.id, { turn });
+      }, 50);
+      continue;
+    }
     turnCounter += 1;
     const turn = { id: `turn_selftest_${turnCounter}`, status: "completed" };
     notify("turn/started", { turn });