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_call_lifecycle.py

@@ -44,6 +44,20 @@ class CallEndCoordinatorTest(unittest.IsolatedAsyncioTestCase):
 
         self.assertEqual(self.reasons, ["tool_only"])
 
+    async def test_workflow_end_waits_for_every_queued_fixed_speech(self):
+        self.coordinator.track_speech()
+        self.coordinator.track_speech()
+        self.coordinator.begin("workflow_completed")
+        await self.coordinator.arm_after_tracked_speech()
+
+        await self.coordinator.observe(BotStartedSpeakingFrame())
+        await self.coordinator.observe(BotStoppedSpeakingFrame())
+        self.assertEqual(self.reasons, [])
+
+        await self.coordinator.observe(BotStartedSpeakingFrame())
+        await self.coordinator.observe(BotStoppedSpeakingFrame())
+        self.assertEqual(self.reasons, ["workflow_completed"])
+
 
 if __name__ == "__main__":
     unittest.main()