perf: improved speed of BDI

By efficiently checking when the next work has to be done, we can
increase performance not having to "busy loop". Time from transcription
-> message to LLM agent is now down to sub 1 millisecond.

ref: N25B-316

src/control_backend/agents/bdi/__init__.py

@@ -1,7 +1,7 @@
 from .bdi_core_agent.bdi_core_agent import BDICoreAgent as BDICoreAgent
-from .belief_collector_agent.belief_collector_agent import (
+from .belief_collector_agent import (
     BDIBeliefCollectorAgent as BDIBeliefCollectorAgent,
 )
-from .text_belief_extractor_agent.text_belief_extractor_agent import (
+from .text_belief_extractor_agent import (
     TextBeliefExtractorAgent as TextBeliefExtractorAgent,
 )