fix: default belief false, user interrupt chat role, vad initial silence, unused import

ref: N25B-453

src/control_backend/agents/bdi/text_belief_extractor_agent.py

@@ -150,6 +150,9 @@ class TextBeliefExtractorAgent(BaseAgent):
             return
 
         available_beliefs = [b for b in belief_list.beliefs if isinstance(b, SemanticBelief)]
+        self._current_beliefs = BeliefState(
+            false={InternalBelief(name=b.name, arguments=None) for b in available_beliefs},
+        )
         self.belief_inferrer.available_beliefs = available_beliefs
         self.logger.debug(
             "Received %d semantic beliefs from the program manager: %s",
@@ -170,6 +173,9 @@ class TextBeliefExtractorAgent(BaseAgent):
         available_goals = {g for g in goals_list.goals if g.can_fail}
         available_goals -= self._force_completed_goals
         self.goal_inferrer.goals = available_goals
+        self._current_goal_completions = {
+            f"achieved_{AgentSpeakGenerator.slugify(goal)}": False for goal in available_goals
+        }
         self.logger.debug(
             "Received %d failable goals from the program manager: %s",
             len(available_goals),

src/control_backend/agents/perception/vad_agent.py

@@ -285,9 +285,10 @@ class VADAgent(BaseAgent):
                 assert self.audio_out_socket is not None
                 await self.audio_out_socket.send(self.audio_buffer[: -2 * len(chunk)].tobytes())
 
-            # At this point, we know that the speech has ended.
+            # At this point, we know that there is no speech.
-            # Prepend the last chunk that had no speech, for a more fluent boundary
+            # Prepend the last few chunks that had no speech, for a more fluent boundary.
-            self.audio_buffer = chunk
+            self.audio_buffer = np.append(self.audio_buffer, chunk)
+            self.audio_buffer = self.audio_buffer[-begin_silence_length * len(chunk) :]
 
     async def handle_message(self, msg: InternalMessage):
         """

src/control_backend/agents/perception/visual_emotion_recognition_agent/visual_emotion_recognition_agent.py

@@ -7,7 +7,6 @@ import numpy as np
 import zmq
 import zmq.asyncio as azmq
 from pydantic_core import ValidationError
-import struct
 
 from control_backend.agents import BaseAgent
 from control_backend.agents.perception.visual_emotion_recognition_agent.visual_emotion_recognizer import (  # noqa
@@ -89,7 +88,7 @@ class VisualEmotionRecognitionAgent(BaseAgent):
         while self._running:
             try:
                 frame_bytes = await self.video_in_socket.recv()
-    
+
                 # Convert bytes to a numpy buffer
                 nparr = np.frombuffer(frame_bytes, np.uint8)
 
@@ -126,7 +125,6 @@ class VisualEmotionRecognitionAgent(BaseAgent):
             except zmq.Again:
                 self.logger.warning("No video frame received within timeout.")
 
-    
     async def update_emotions(self, prev_emotions: set[str], emotions: set[str]):
         """
         Compare emotions from previous window and current emotions,

src/control_backend/agents/user_interrupt/user_interrupt_agent.py

@@ -300,7 +300,7 @@ class UserInterruptAgent(BaseAgent):
 
         :param text_to_say: The string that the robot has to say.
         """
-        experiment_logger.chat(text_to_say, extra={"role": "user"})
+        experiment_logger.chat(text_to_say, extra={"role": "assistant"})
         cmd = SpeechCommand(data=text_to_say, is_priority=True)
         out_msg = InternalMessage(
             to=settings.agent_settings.robot_speech_name,