Merge branch 'fix/trigger-subgoal-error' into 'main'

Allow subgoals in triggers and empty plan

See merge request ics/sp/2025/n25b/pepperplus-cb!50

src/control_backend/agents/bdi/agentspeak_generator.py

@@ -4,6 +4,7 @@ University within the Software Project course.
 © Copyright Utrecht University (Department of Information and Computing Sciences)
 """
 
+import logging
 from functools import singledispatchmethod
 
 from slugify import slugify
@@ -30,7 +31,6 @@ from control_backend.schemas.program import (
     BasicNorm,
     ConditionalNorm,
     EmotionBelief,
-    FaceBelief,
     GestureAction,
     Goal,
     InferredBelief,
@@ -67,6 +67,7 @@ class AgentSpeakGenerator:
     """
 
     _asp: AstProgram
+    logger = logging.getLogger(__name__)
 
     def generate(self, program: Program) -> str:
         """
@@ -480,7 +481,8 @@ class AgentSpeakGenerator:
         :param main_goal: Whether this is a main goal (for UI notification purposes).
         """
         context: list[AstExpression] = [self._astify(phase)]
-        context.append(~self._astify(goal, achieved=True))
+        if goal.can_fail:
+            context.append(~self._astify(goal, achieved=True))
         if previous_goal and previous_goal.can_fail:
             context.append(self._astify(previous_goal, achieved=True))
         if not continues_response:
@@ -504,6 +506,10 @@ class AgentSpeakGenerator:
         if not goal.can_fail and not continues_response:
             body.append(AstStatement(StatementType.ADD_BELIEF, self._astify(goal, achieved=True)))
 
+        if len(body) == 0:
+            self.logger.warning("Goal with no plan detected: %s", goal.name)
+            body.append(AstStatement(StatementType.EMPTY, AstLiteral("true")))
+
         self._asp.plans.append(AstPlan(TriggerType.ADDED_GOAL, self._astify(goal), context, body))
 
         self._asp.plans.append(
@@ -564,10 +570,10 @@ class AgentSpeakGenerator:
             )
         )
         for step in trigger.plan.steps:
-            body.append(self._step_to_statement(step))
             if isinstance(step, Goal):
-                step.can_fail = False  # triggers are continuous sequence
+                new_step = step.model_copy(update={"can_fail": False})  # triggers are sequence
-                subgoals.append(step)
+                subgoals.append(new_step)
+            body.append(self._step_to_statement(step))
 
         # Arbitrary wait for UI to display nicely
         body.append(
@@ -688,10 +694,6 @@ class AgentSpeakGenerator:
     def _(self, eb: EmotionBelief) -> AstExpression:
         return AstLiteral("emotion_detected", [AstAtom(eb.emotion)])
 
-    @_astify.register
-    def _(self, fb: FaceBelief) -> AstExpression:
-        return AstLiteral("face_present")
-
     @_astify.register
     def _(self, ib: InferredBelief) -> AstExpression:
         """

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

@@ -14,7 +14,7 @@ from control_backend.agents.perception.visual_emotion_recognition_agent.visual_e
 )
 from control_backend.core.agent_system import InternalMessage
 from control_backend.core.config import settings
-from control_backend.schemas.belief_message import Belief, BeliefMessage
+from control_backend.schemas.belief_message import Belief
 
 
 class VisualEmotionRecognitionAgent(BaseAgent):
@@ -44,7 +44,6 @@ class VisualEmotionRecognitionAgent(BaseAgent):
         self.timeout_ms = timeout_ms
         self.window_duration = window_duration
         self.min_frames_required = min_frames_required
-        self._face_detected = False
 
         # Pause functionality
         # NOTE: flag is set when running, cleared when paused
@@ -90,9 +89,6 @@ class VisualEmotionRecognitionAgent(BaseAgent):
         # Tracks counts of detected emotions per face index
         face_stats = defaultdict(Counter)
 
-        # How many times a face has been detected
-        face_detection_yes_no = [0, 0]
-
         prev_dominant_emotions = set()
 
         while self._running:
@@ -101,8 +97,8 @@ class VisualEmotionRecognitionAgent(BaseAgent):
 
                 width, height, image_bytes = await self.video_in_socket.recv_multipart()
 
-                width = int.from_bytes(width, "little")
+                width = int.from_bytes(width, 'little')
-                height = int.from_bytes(height, "little")
+                height = int.from_bytes(height, 'little')
 
                 # Convert bytes to a numpy buffer
                 image_array = np.frombuffer(image_bytes, np.uint8)
@@ -111,13 +107,6 @@ class VisualEmotionRecognitionAgent(BaseAgent):
 
                 # Get the dominant emotion from each face
                 current_emotions = self.emotion_recognizer.sorted_dominant_emotions(frame)
-
-                # Update face face_detection_yes_no
-                if len(current_emotions) > 0:
-                    face_detection_yes_no[0] += 1
-                else:
-                    face_detection_yes_no[1] += 1
-
                 # Update emotion counts for each detected face
                 for i, emotion in enumerate(current_emotions):
                     face_stats[i][emotion] += 1
@@ -133,20 +122,6 @@ class VisualEmotionRecognitionAgent(BaseAgent):
                             dominant_emotion = counter.most_common(1)[0][0]
                             window_dominant_emotions.add(dominant_emotion)
 
-                    if (
-                        face_detection_yes_no[0] > face_detection_yes_no[1]
-                        and not self._face_detected
-                    ):
-                        self._face_detected = True
-                        await self._inform_face_detected()
-                    elif (
-                        face_detection_yes_no[0] <= face_detection_yes_no[1] and self._face_detected
-                    ):
-                        self._face_detected = False
-                        await self._inform_face_detected()
-
-                    face_detection_yes_no = [0, 0]
-
                     await self.update_emotions(prev_dominant_emotions, window_dominant_emotions)
                     prev_dominant_emotions = window_dominant_emotions
                     face_stats.clear()
@@ -158,6 +133,7 @@ class VisualEmotionRecognitionAgent(BaseAgent):
             except Exception as e:
                 self.logger.error(f"Error in emotion recognition loop: {e}")
 
+    
     async def update_emotions(self, prev_emotions: set[str], emotions: set[str]):
         """
         Compare emotions from previous window and current emotions,
@@ -173,7 +149,9 @@ class VisualEmotionRecognitionAgent(BaseAgent):
         for emotion in emotions_to_remove:
             self.logger.info(f"Emotion '{emotion}' has disappeared.")
             try:
-                emotion_beliefs_remove.append(Belief(name="emotion_detected", arguments=[emotion]))
+                emotion_beliefs_remove.append(
+                    Belief(name="emotion_detected", arguments=[emotion], remove=True)
+                )
             except ValidationError:
                 self.logger.warning("Invalid belief for emotion removal: %s", emotion)
 
@@ -197,25 +175,11 @@ class VisualEmotionRecognitionAgent(BaseAgent):
         )
         await self.send(message)
 
-    async def _inform_face_detected(self):
-        if self._face_detected:
-            belief_message = BeliefMessage(create=[Belief(name="face_present")])
-        else:
-            belief_message = BeliefMessage(delete=[Belief(name="face_present")])
-
-        msg = InternalMessage(
-            to=settings.agent_settings.bdi_core_name,
-            thread="beliefs",
-            body=belief_message.model_dump_json(),
-        )
-
-        await self.send(msg)
-
     async def handle_message(self, msg: InternalMessage):
         """
         Handle incoming messages.
 
-        Expects messages to pause or resume the Visual Emotion Recognition
+        Expects messages to pause or resume the Visual Emotion Recognition 
         processing from User Interrupt Agent.
 
         :param msg: The received internal message.
@@ -240,3 +204,4 @@ class VisualEmotionRecognitionAgent(BaseAgent):
         """
         self.video_in_socket.close()
         await super().stop()
+        

src/control_backend/core/config.py

@@ -82,7 +82,7 @@ class BehaviourSettings(BaseModel):
     :ivar transcription_words_per_token: Estimated words per token for transcription timing.
     :ivar transcription_token_buffer: Buffer for transcription tokens.
     :ivar conversation_history_length_limit: The maximum amount of messages to extract beliefs from.
-    :ivar visual_emotion_recognition_window_duration_s: Duration in seconds over which to aggregate
+    :ivar visual_emotion_recognition_window_duration_s: Duration in seconds over which to aggregate 
     emotions and update emotion beliefs.
     :ivar visual_emotion_recognition_min_frames_per_face: Minimum number of frames per face required
     to consider a face valid.
@@ -112,7 +112,7 @@ class BehaviourSettings(BaseModel):
     conversation_history_length_limit: int = 10
 
     # Visual Emotion Recognition settings
-    visual_emotion_recognition_window_duration_s: int = 3
+    visual_emotion_recognition_window_duration_s: int = 5
     visual_emotion_recognition_min_frames_per_face: int = 3
     # AgentSpeak related settings
     trigger_time_to_wait: int = 2000

src/control_backend/schemas/program.py

@@ -7,7 +7,7 @@ University within the Software Project course.
 from enum import Enum
 from typing import Literal
 
-from pydantic import UUID4, BaseModel
+from pydantic import UUID4, BaseModel, field_validator
 
 
 class ProgramElement(BaseModel):
@@ -24,6 +24,13 @@ class ProgramElement(BaseModel):
     # To make program elements hashable
     model_config = {"frozen": True}
 
+    @field_validator("name")
+    @classmethod
+    def name_must_not_start_with_number(cls, v: str) -> str:
+        if v and v[0].isdigit():
+            raise ValueError('Field "name" must not start with a number.')
+        return v
+
 
 class LogicalOperator(Enum):
     """
@@ -41,8 +48,8 @@ class LogicalOperator(Enum):
     OR = "OR"
 
 
-type Belief = KeywordBelief | SemanticBelief | InferredBelief | EmotionBelief | FaceBelief
+type Belief = KeywordBelief | SemanticBelief | InferredBelief | EmotionBelief
-type BasicBelief = KeywordBelief | SemanticBelief | EmotionBelief | FaceBelief
+type BasicBelief = KeywordBelief | SemanticBelief | EmotionBelief
 
 
 class KeywordBelief(ProgramElement):
@@ -117,15 +124,6 @@ class EmotionBelief(ProgramElement):
     emotion: str
 
 
-class FaceBelief(ProgramElement):
-    """
-    Represents the belief that at least one face is currently in view.
-    """
-
-    name: str = ""
-    face_present: bool
-
-
 class Norm(ProgramElement):
     """
     Base class for behavioral norms that guide the robot's interactions.