feat: integrate AgentSpeak with semantic belief extraction

ref: N25B-429

src/control_backend/schemas/belief_list.py

@@ -0,0 +1,14 @@
+from pydantic import BaseModel
+
+from control_backend.schemas.program import Belief as ProgramBelief
+
+
+class BeliefList(BaseModel):
+    """
+    Represents a list of beliefs, separated from a program. Useful in agents which need to
+    communicate beliefs.
+
+    :ivar: beliefs: The list of beliefs.
+    """
+
+    beliefs: list[ProgramBelief]

src/control_backend/schemas/program.py

@@ -43,7 +43,6 @@ class SemanticBelief(ProgramElement):
     :ivar description: Description of how to form the belief, used by the LLM.
     """
 
-    name: str = ""
     description: str
 
 
@@ -113,10 +112,12 @@ class Goal(ProgramElement):
     for example when the achieving of the goal is dependent on the user's reply, this means
     that the achieved status will be set from somewhere else in the program.
 
+    :ivar description: A description of the goal, used to determine if it has been achieved.
     :ivar plan: The plan to execute.
     :ivar can_fail: Whether we can fail to achieve the goal after executing the plan.
     """
 
+    description: str
     plan: Plan
     can_fail: bool = True