fix(replies): keep queued followup typing alive

CHANGELOG.md

@@ -27,6 +27,7 @@ Docs: https://docs.openclaw.ai
 - Web search/MiniMax: allow `MINIMAX_OAUTH_TOKEN` to satisfy MiniMax Search credentials, so OAuth-authorized MiniMax Token Plan setups do not need a separate web-search key. Fixes #65768. Thanks @kikibrian and @zhouhe-xydt.
 - Subagents: honor `sessions_spawn` with `expectsCompletionMessage: false` by skipping parent completion handoff delivery while still running child cleanup. Fixes #75848. Thanks @alfredjbclaw.
 - Gateway/logging: keep deferred channel startup logs on the subsystem logger, so Slack, Discord, Telegram, and voice-call startup messages keep timestamped prefixes. Thanks @vincentkoc.
+- Replies/typing: keep typing alive for queued follow-up messages that are genuinely waiting behind an active run, instead of making chat surfaces look idle while work is queued. Fixes #65685. Thanks @papag00se.
 - ACP/Discord: suppress completion announce delivery for inline thread-bound ACP session runs, so Discord thread-bound ACP replies are not delivered twice. Fixes #60780. Thanks @solavrc.
 - Discord/threads: ignore webhook-authored copies in already-bound Discord session threads even when the webhook id differs, preventing PluralKit proxy copies from creating duplicate turn pressure. Fixes #52005. Thanks @acgh213.
 - Discord/threads: return the created thread as partial success when the follow-up initial message fails, so agents do not retry thread creation and create empty duplicate threads. Fixes #48450. Thanks @dahifi.

src/auto-reply/reply/agent-runner.runreplyagent.e2e.test.ts

@@ -219,8 +219,28 @@ describe("runReplyAgent heartbeat followup guard", () => {
     expect(state.runEmbeddedPiAgentMock).not.toHaveBeenCalled();
   });
 
+  it("keeps typing alive when a followup is queued behind a live active run", async () => {
+    const { run, typing } = createMinimalRun({
+      opts: { isHeartbeat: false },
+      isActive: true,
+      isRunActive: () => true,
+      shouldFollowup: true,
+      resolvedQueueMode: "collect",
+    });
+
+    const result = await run();
+
+    expect(result).toBeUndefined();
+    expect(vi.mocked(enqueueFollowupRun)).toHaveBeenCalledTimes(1);
+    expect(vi.mocked(scheduleFollowupDrain)).not.toHaveBeenCalled();
+    expect(state.runEmbeddedPiAgentMock).not.toHaveBeenCalled();
+    expect(typing.startTypingLoop).toHaveBeenCalledTimes(1);
+    expect(typing.refreshTypingTtl).toHaveBeenCalledTimes(1);
+    expect(typing.cleanup).not.toHaveBeenCalled();
+  });
+
   it("starts draining immediately when the active snapshot is already stale", async () => {
-    const { run } = createMinimalRun({
+    const { run, typing } = createMinimalRun({
       opts: { isHeartbeat: false },
       isActive: true,
       isRunActive: () => false,
@@ -234,6 +254,7 @@ describe("runReplyAgent heartbeat followup guard", () => {
     expect(vi.mocked(enqueueFollowupRun)).toHaveBeenCalledTimes(1);
     expect(vi.mocked(scheduleFollowupDrain)).toHaveBeenCalledTimes(1);
     expect(state.runEmbeddedPiAgentMock).not.toHaveBeenCalled();
+    expect(typing.cleanup).toHaveBeenCalledTimes(1);
   });
 
   it("drains followup queue when an unexpected exception escapes the run path", async () => {

src/auto-reply/reply/agent-runner.ts

@@ -1045,11 +1045,16 @@ export async function runReplyAgent(params: {
     );
     // Re-check liveness after enqueue so a stale active snapshot cannot leave
     // the followup queue idle if the original run already finished.
-    if (!isRunActive?.()) {
+    const queuedBehindActiveRun = isRunActive?.() === true;
+    if (!queuedBehindActiveRun) {
       finalizeWithFollowup(undefined, queueKey, queuedRunFollowupTurn);
     }
     await touchActiveSessionEntry();
-    typing.cleanup();
+    if (queuedBehindActiveRun) {
+      await typingSignals.signalToolStart();
+    } else {
+      typing.cleanup();
+    }
     return undefined;
   }