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/workflow/__init__.py

@@ -0,0 +1,19 @@
+"""Small, explicit building blocks for the local Workflow runtime."""
+
+from services.workflow.models import (
+    EdgeEvaluation,
+    LLMRouteResult,
+    RouteStatus,
+    UserTurn,
+    WorkflowRuntimeState,
+    WorkflowStatus,
+)
+
+__all__ = [
+    "EdgeEvaluation",
+    "LLMRouteResult",
+    "RouteStatus",
+    "UserTurn",
+    "WorkflowRuntimeState",
+    "WorkflowStatus",
+]