fix: move BDI core agent to make documentation generation better

Previously, the BDI Core Agent wasn't included in the docs.

ref: N25B-299

src/control_backend/agents/bdi/__init__.py

@@ -1,4 +1,5 @@
-from .bdi_core_agent.bdi_core_agent import BDICoreAgent as BDICoreAgent
+from control_backend.agents.bdi.bdi_core_agent import BDICoreAgent as BDICoreAgent
+
 from .belief_collector_agent import (
     BDIBeliefCollectorAgent as BDIBeliefCollectorAgent,
 )

src/control_backend/agents/llm/llm_agent.py

@@ -165,7 +165,7 @@ class LLMAgent(BaseAgent):
         :yield: Raw text tokens (deltas) from the SSE stream.
         :raises httpx.HTTPError: If the API returns a non-200 status.
         """
-        async with httpx.AsyncClient(timeout=None) as client:
+        async with httpx.AsyncClient() as client:
             async with client.stream(
                 "POST",
                 settings.llm_settings.local_llm_url,

src/control_backend/core/config.py

@@ -87,12 +87,10 @@ class LLMSettings(BaseModel):
 
     :ivar local_llm_url: URL for the local LLM API.
     :ivar local_llm_model: Name of the local LLM model to use.
-    :ivar request_timeout_s: Timeout in seconds for LLM requests.
     """
 
-    local_llm_url: str = "http://localhost:11434/v1/chat/completions"
+    local_llm_url: str = "http://localhost:1234/v1/chat/completions"
     local_llm_model: str = "gpt-oss"
-    request_timeout_s: int = 10
 
 
 class VADSettings(BaseModel):

src/control_backend/main.py

@@ -117,7 +117,7 @@ async def lifespan(app: FastAPI):
             BDICoreAgent,
             {
                 "name": settings.agent_settings.bdi_core_name,
-                "asl": "src/control_backend/agents/bdi/bdi_core_agent/rules.asl",
+                "asl": "src/control_backend/agents/bdi/rules.asl",
             },
         ),
         "BeliefCollectorAgent": (