feat: fully implemented visual emotion recognition agent in pipeline

ref: N25B-393

src/control_backend/agents/communication/ri_communication_agent.py

@@ -7,6 +7,9 @@ from zmq.asyncio import Context
 
 from control_backend.agents import BaseAgent
 from control_backend.agents.actuation.robot_gesture_agent import RobotGestureAgent
+from control_backend.agents.perception.visual_emotion_detection_agent.visual_emotion_recognition_agent import (
+    VisualEmotionRecognitionAgent,
+)
 from control_backend.core.config import settings
 
 from ..actuation.robot_speech_agent import RobotSpeechAgent
@@ -201,6 +204,13 @@ class RICommunicationAgent(BaseAgent):
                 case "audio":
                     vad_agent = VADAgent(audio_in_address=addr, audio_in_bind=bind)
                     await vad_agent.start()
+                case "video":
+                    visual_emotion_agent = VisualEmotionRecognitionAgent(
+                        settings.agent_settings.visual_emotion_recognition_name,
+                        socket_address=addr,
+                        bind=bind,
+                    )
+                    await visual_emotion_agent.start()
                 case _:
                     self.logger.warning("Unhandled negotiation id: %s", id)