Merge branch 'dev' into refactor/logging

src/control_backend/agents/vad_agent.py

@@ -51,8 +51,20 @@ class Streaming(CyclicBehaviour):
 
         self.audio_buffer = np.array([], dtype=np.float32)
         self.i_since_speech = 100  # Used to allow small pauses in speech
+        self._ready = False
+
+    async def reset(self):
+        """Clears the ZeroMQ queue and tells this behavior to start."""
+        discarded = 0
+        while await self.audio_in_poller.poll(1) is not None:
+            discarded += 1
+        self.agent.logger.info(f"Discarded {discarded} audio packets before starting.")
+        self._ready = True
 
     async def run(self) -> None:
+        if not self._ready:
+            return
+
         data = await self.audio_in_poller.poll()
         if data is None:
             if len(self.audio_buffer) > 0:
@@ -106,6 +118,8 @@ class VADAgent(BaseAgent):
         self.audio_in_socket: azmq.Socket | None = None
         self.audio_out_socket: azmq.Socket | None = None
 
+        self.streaming_behaviour: Streaming | None = None
+
     async def stop(self):
         """
         Stop listening to audio, stop publishing audio, close sockets.
@@ -148,8 +162,8 @@ class VADAgent(BaseAgent):
             return
         audio_out_address = f"tcp://localhost:{audio_out_port}"
 
-        streaming = Streaming(self.audio_in_socket, self.audio_out_socket)
-        self.add_behaviour(streaming)
+        self.streaming_behaviour = Streaming(self.audio_in_socket, self.audio_out_socket)
+        self.add_behaviour(self.streaming_behaviour)
 
         # Start agents dependent on the output audio fragments here
         transcriber = TranscriptionAgent(audio_out_address)