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/tests/test_workflow_router.py

@@ -5,6 +5,7 @@ from types import SimpleNamespace
 from unittest.mock import patch
 
 from models import AssistantConfig
+from services.workflow.models import RouteStatus
 from services.workflow_router import WorkflowLLMRouter
 
 
@@ -62,7 +63,8 @@ class WorkflowLLMRouterTest(unittest.IsolatedAsyncioTestCase):
                 edge_description=lambda _edge: "用户已经回答姓名",
             )
 
-        self.assertEqual(selected, "goto_age")
+        self.assertEqual(selected.status, RouteStatus.MATCHED)
+        self.assertEqual(selected.function_name, "goto_age")
         self.assertEqual(requests[0]["tool_choice"], "required")
         self.assertEqual(
             [message["role"] for message in requests[0]["messages"]],