fix(cli): avoid voice TTS restart race

cli.py

@@ -8375,6 +8375,17 @@ class HermesCLI:
                         _cprint(f"{_DIM}Voice auto-restart failed: {e}{_RST}")
                 threading.Thread(target=_restart_recording, daemon=True).start()
 
+    def _voice_speak_response_async(self, text: str) -> None:
+        """Schedule TTS and mark it pending before continuous recording can restart."""
+        if not self._voice_tts or not text:
+            return
+        self._voice_tts_done.clear()
+        threading.Thread(
+            target=self._voice_speak_response,
+            args=(text,),
+            daemon=True,
+        ).start()
+
     def _voice_speak_response(self, text: str):
         """Speak the agent's response aloud using TTS (runs in background thread)."""
         if not self._voice_tts:
@@ -9535,11 +9546,7 @@ class HermesCLI:
             # Speak response aloud if voice TTS is enabled
             # Skip batch TTS when streaming TTS already handled it
             if self._voice_tts and response and not use_streaming_tts:
-                threading.Thread(
-                    target=self._voice_speak_response,
-                    args=(response,),
-                    daemon=True,
-                ).start()
+                self._voice_speak_response_async(response)
 
 
             # Re-queue the interrupt message (and any that arrived while we were

tests/tools/test_voice_cli_integration.py

@@ -1040,6 +1040,25 @@ class TestDisableVoiceModeReal:
 class TestVoiceSpeakResponseReal:
     """Tests _voice_speak_response with real CLI instance."""
 
+    def test_async_scheduling_clears_done_before_thread_start(self):
+        cli = _make_voice_cli(_voice_tts=True)
+        starts = []
+
+        class FakeThread:
+            def __init__(self, target=None, args=(), daemon=None):
+                self.target = target
+                self.args = args
+                self.daemon = daemon
+
+            def start(self):
+                starts.append(cli._voice_tts_done.is_set())
+
+        with patch("cli.threading.Thread", FakeThread):
+            cli._voice_speak_response_async("Hello")
+
+        assert starts == [False]
+        assert not cli._voice_tts_done.is_set()
+
     @patch("cli._cprint")
     def test_early_return_when_tts_off(self, _cp):
         cli = _make_voice_cli(_voice_tts=False)