fix(codex): yield app-server notification projection (#82333)

* fix(codex): yield app-server notification projection

* docs(changelog): note codex notification yield fix

CHANGELOG.md

@@ -44,6 +44,7 @@ Docs: https://docs.openclaw.ai
 - LINE: stop cron recovery from inferring lowercased LINE recipients from canonical session keys, so long-running task replies do not silently retry undeliverable push targets. Fixes #81628. (#81704) Thanks @edenfunf.
 - TTS: preserve channel-derived voice-note delivery for `/tts audio` replies even when the provider output is not natively voice-compatible. (#82174) Thanks @xuruiray.
 - Codex app-server: preserve inbound sender metadata and source-channel provenance on mirrored user prompts, including failure snapshots, so channel history keeps the original sender identity. (#82184) Thanks @zknicker.
+- Codex app-server: yield projector work to the event loop between embedded-run notifications while preserving pre-turn rate-limit capture, reducing gateway stalls from account and MCP status notifications. Fixes #81936. (#82333) Thanks @joshavant.
 - Codex account/status: treat metadata-only rate-limit buckets as returned but empty so `/codex status` and `/codex account` report `none returned` instead of counting phantom limits.
 - Codex/Lossless: keep Codex explicit compaction on native app-server threads while allowing Lossless through the context-engine slot; `openclaw doctor --fix` now migrates legacy `compaction.provider: "lossless-claw"` config to `plugins.slots.contextEngine`.
 - Cron/doctor: report scheduled jobs with explicit `payload.model` overrides, including provider namespace counts and default-model mismatches, so stale cron model pins are visible during auth or billing investigations. Fixes #82151. Thanks @mgonto.

extensions/codex/src/app-server/run-attempt.test.ts

@@ -39,7 +39,11 @@ import {
   resolveCodexPluginAppCacheEndpoint,
 } from "./plugin-app-cache-key.js";
 import type { CodexServerNotification } from "./protocol.js";
-import { rememberCodexRateLimits, resetCodexRateLimitCacheForTests } from "./rate-limit-cache.js";
+import {
+  readRecentCodexRateLimits,
+  rememberCodexRateLimits,
+  resetCodexRateLimitCacheForTests,
+} from "./rate-limit-cache.js";
 import {
   runCodexAppServerAttempt as runCodexAppServerAttemptImpl,
   __testing,
@@ -1982,6 +1986,29 @@ describe("runCodexAppServerAttempt", () => {
     );
   });
 
+  it("yields a macrotask before processing queued app-server notifications", async () => {
+    const harness = createStartedThreadHarness();
+    const params = createParams(
+      path.join(tempDir, "session.jsonl"),
+      path.join(tempDir, "workspace"),
+    );
+    params.timeoutMs = 1_000;
+
+    const run = runCodexAppServerAttempt(params);
+    await harness.waitForMethod("turn/start");
+
+    const notification = rateLimitsUpdated(Date.now() + 60_000);
+    const processing = harness.notify(notification);
+    await Promise.resolve();
+
+    expect(readRecentCodexRateLimits()).toBeUndefined();
+    await processing;
+    expect(readRecentCodexRateLimits()).toEqual(notification.params);
+
+    await harness.completeTurn({ threadId: "thread-1", turnId: "turn-1" });
+    await expect(run).resolves.toMatchObject({ aborted: false, timedOut: false });
+  });
+
   it("releases the session when a completed agent message item goes quiet", async () => {
     let notify: (notification: CodexServerNotification) => Promise<void> = async () => undefined;
     const request = vi.fn(async (method: string) => {
@@ -3250,7 +3277,7 @@ describe("runCodexAppServerAttempt", () => {
         if (!harnessRef.current) {
           throw new Error("Expected Codex app-server harness to be initialized");
         }
-        await harnessRef.current.notify(rateLimitsUpdated(resetsAt));
+        void harnessRef.current.notify(rateLimitsUpdated(resetsAt));
         throw Object.assign(new Error("You've reached your usage limit."), {
           data: { codexErrorInfo: "usageLimitExceeded" },
         });

extensions/codex/src/app-server/run-attempt.ts

@@ -1319,6 +1319,7 @@ export async function runCodexAppServerAttempt(
       isCodexTurnAbortMarkerNotification(notification, { currentPromptText: promptBuild.prompt });
     const isTurnTerminal = isTurnCompletion || isTurnAbortMarker;
     try {
+      await waitForCodexNotificationDispatchTurn();
       await projector.handleNotification(notification);
     } catch (error) {
       embeddedAgentLog.debug("codex app-server projector notification threw", {
@@ -1342,6 +1343,11 @@ export async function runCodexAppServerAttempt(
     }
   };
   const enqueueNotification = (notification: CodexServerNotification): Promise<void> => {
+    if (!projector || !turnId) {
+      userInputBridge?.handleNotification(notification);
+      pendingNotifications.push(notification);
+      return Promise.resolve();
+    }
     notificationQueue = notificationQueue.then(
       () => handleNotification(notification),
       () => handleNotification(notification),
@@ -3255,6 +3261,12 @@ function prependCurrentTurnContext(
   return text ? [text, prompt].filter(Boolean).join("\n\n") : prompt;
 }
 
+function waitForCodexNotificationDispatchTurn(): Promise<void> {
+  return new Promise((resolve) => {
+    setImmediate(resolve);
+  });
+}
+
 function handleApprovalRequest(params: {
   method: string;
   params: JsonValue | undefined;