Refactor workflow agent and routing components for improved functionality

- Introduce WorkflowAgentStage to manage agent stage configurations and enhance interaction with the workflow engine.
- Implement WorkflowEdgeEvaluator for priority-aware edge evaluation, improving routing decisions based on conditions and user turns.
- Update WorkflowBrain to handle user turns and routing more effectively, ensuring agents cannot have only one default path.
- Enhance CallEndCoordinator to track speech events and manage call termination based on queued speech.
- Add new models and output handling for workflow interactions, improving clarity and maintainability.
- Update tests to validate the new routing logic and agent behavior under various scenarios.

backend/services/brains/base.py

@@ -55,6 +55,10 @@ class CallEndPort(Protocol):
 
     def arm_after_speech(self) -> None: ...
 
+    def track_speech(self) -> None: ...
+
+    async def arm_after_tracked_speech(self) -> None: ...
+
     async def finish_after_current_speech(self, *, has_text: bool) -> None: ...
 
     async def finish(self) -> None: ...