feat: end to end connected for demo

Includes the Transcription agent. Involved updating the RI agent to receive messages from other agents, sending speech commands to the RI agent, and some performance optimizations.

ref: N25B-216

src/control_backend/agents/bdi/behaviours/receive_llm_resp_behaviour.py

@@ -1,15 +1,18 @@
 import logging
 
 from spade.behaviour import CyclicBehaviour
+from spade.message import Message
 
 from control_backend.core.config import settings
+from control_backend.schemas.ri_message import SpeechCommand
 
 
 class ReceiveLLMResponseBehaviour(CyclicBehaviour):
     """
     Adds behavior to receive responses from the LLM Agent.
     """
-    logger = logging.getLogger("BDI/LLM Reciever")
+    logger = logging.getLogger("BDI/LLM Receiver")
+
     async def run(self):
         msg = await self.receive(timeout=2)
         if not msg:
@@ -20,7 +23,17 @@ class ReceiveLLMResponseBehaviour(CyclicBehaviour):
             case settings.agent_settings.llm_agent_name:
                 content = msg.body
                 self.logger.info("Received LLM response: %s", content)
-                #Here the BDI can pass the message back as a response
+
+                speech_command = SpeechCommand(data=content)
+
+                message = Message(to=settings.agent_settings.ri_command_agent_name
+                                  + '@' + settings.agent_settings.host,
+                                  sender=self.agent.jid,
+                                  body=speech_command.model_dump_json())
+
+                self.logger.debug("Sending message: %s", message)
+
+                await self.send(message)
             case _:
                 self.logger.debug("Not from the llm, discarding message")
                 pass