Merge branch 'dev' into refactor/logging

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

@@ -9,18 +9,23 @@ from control_backend.core.config import settings
 class BeliefFromText(CyclicBehaviour):
     # TODO: LLM prompt nog hardcoded
     llm_instruction_prompt = """
-    You are an information extraction assistent for a BDI agent. Your task is to extract values from a user's text to bind a list of ungrounded beliefs. Rules:
-    You will receive a JSON object with "beliefs" (a list of ungrounded AgentSpeak beliefs) and "text" (user's transcript).
+    You are an information extraction assistent for a BDI agent. Your task is to extract values \
+    from a user's text to bind a list of ungrounded beliefs. Rules:
+    You will receive a JSON object with "beliefs" (a list of ungrounded AgentSpeak beliefs) \
+    and "text" (user's transcript).
     Analyze the text to find values that sematically match the variables (X,Y,Z) in the beliefs.
     A single piece of text might contain multiple instances that match a belief.
     Respond ONLY with a single JSON object.
     The JSON object's keys should be the belief functors (e.g., "weather").
     The value for each key must be a list of lists.
-    Each inner list must contain the extracted arguments (as strings) for one instance of that belief.
-    CRITICAL: If no information in the text matches a belief, DO NOT include that key in your response.
+    Each inner list must contain the extracted arguments (as strings) for one instance \
+    of that belief.
+    CRITICAL: If no information in the text matches a belief, DO NOT include that key \
+    in your response.
     """
 
-    # on_start agent receives message containing the beliefs to look out for and sets up the LLM with instruction prompt
+    # on_start agent receives message containing the beliefs to look out for and
+    # sets up the LLM with instruction prompt
     # async def on_start(self):
     #    msg = await self.receive(timeout=0.1)
     #    self.beliefs = dict uit message

src/control_backend/agents/belief_collector/behaviours/continuous_collect.py

@@ -7,6 +7,7 @@ from spade.behaviour import CyclicBehaviour
 from control_backend.core.config import settings
 
 
+
 class ContinuousBeliefCollector(CyclicBehaviour):
     """
     Continuously collects beliefs/emotions from extractor agents:
@@ -23,9 +24,12 @@ class ContinuousBeliefCollector(CyclicBehaviour):
         # Parse JSON payload
         try:
             payload = json.loads(msg.body)
-        except JSONDecodeError as e:
-            self.agent.logger.warning(
-                "Failed to parse JSON from %s. Body=%r Error=%s", sender_node, msg.body, e
+        except Exception as e:
+            logger.warning(
+                "BeliefCollector: failed to parse JSON from %s. Body=%r Error=%s",
+                sender_node,
+                msg.body,
+                e,
             )
             return
 
@@ -51,7 +55,7 @@ class ContinuousBeliefCollector(CyclicBehaviour):
         Expected payload:
          {
             "type": "belief_extraction_text",
-            "beliefs": {"user_said": ["hello"","Can you help me?","stop talking to me","No","Pepper do a dance"]}
+            "beliefs": {"user_said": ["Can you help me?"]}
 
         }
 

src/control_backend/agents/mock_agents/belief_text_mock.py

@@ -10,7 +10,11 @@ from control_backend.core.config import settings
 class BeliefTextAgent(Agent):
     class SendOnceBehaviourBlfText(OneShotBehaviour):
         async def run(self):
-            to_jid = f"{settings.agent_settings.belief_collector_agent_name}@{settings.agent_settings.host}"
+            to_jid = (
+                settings.agent_settings.belief_collector_agent_name
+                + "@"
+                + settings.agent_settings.host
+            )
 
             # Send multiple beliefs in one JSON payload
             payload = {

src/control_backend/agents/transcription/speech_recognizer.py

@@ -75,7 +75,8 @@ class MLXWhisperSpeechRecognizer(SpeechRecognizer):
         self.model_name = "mlx-community/whisper-small.en-mlx"
 
     def load_model(self):
-        if self.was_loaded: return
+        if self.was_loaded:
+            return
         # There appears to be no dedicated mechanism to preload a model, but this `get_model` does
         # store it in memory for later usage
         ModelHolder.get_model(self.model_name, mx.float16)
@@ -83,9 +84,9 @@ class MLXWhisperSpeechRecognizer(SpeechRecognizer):
 
     def recognize_speech(self, audio: np.ndarray) -> str:
         self.load_model()
-        return mlx_whisper.transcribe(audio,
-                                      path_or_hf_repo=self.model_name,
-                                      decode_options=self._get_decode_options(audio))["text"]
+        return mlx_whisper.transcribe(
+            audio, path_or_hf_repo=self.model_name, decode_options=self._get_decode_options(audio)
+        )["text"]
         return mlx_whisper.transcribe(audio, path_or_hf_repo=self.model_name)["text"].strip()
 
 
@@ -95,12 +96,13 @@ class OpenAIWhisperSpeechRecognizer(SpeechRecognizer):
         self.model = None
 
     def load_model(self):
-        if self.model is not None: return
+        if self.model is not None:
+            return
         device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
         self.model = whisper.load_model("small.en", device=device)
 
     def recognize_speech(self, audio: np.ndarray) -> str:
         self.load_model()
-        return whisper.transcribe(self.model,
-                                  audio,
-                                  decode_options=self._get_decode_options(audio))["text"]
+        return whisper.transcribe(
+            self.model, audio, decode_options=self._get_decode_options(audio)
+        )["text"]