Refactor workflow routing and greeting management in Brain classes

- Update WorkflowBrain to handle greeting playback more effectively, ensuring that the initial greeting completes before transitioning to the first node.
- Introduce new methods for managing greeting states and conditions, enhancing the interaction flow for user turns.
- Refactor WorkflowLLMRouter to improve routing logic and ensure proper handling of conditional paths.
- Enhance tests to verify the correct behavior of greeting management and routing under various scenarios, including waiting for audio playback to finish.
- Update frontend components to reflect changes in edge handling and improve user experience in workflow configurations.

backend/services/workflow_engine.py

@@ -152,6 +152,20 @@ class WorkflowEngine:
     def greeting(self, store: DynamicVariableStore) -> str:
         return store.render(str(self.data(self.start_id).get("greeting") or ""))
 
+    def routing_prompt(self, node_id: str, store: DynamicVariableStore) -> str:
+        """Describe the current node to the small LLM edge router."""
+        if self.node_type(node_id) == "agent":
+            return self.prompt_for(node_id, store)
+        data = self.data(node_id)
+        details = (
+            data.get("greeting")
+            or data.get("message")
+            or data.get("target")
+            or ""
+        )
+        rendered = store.render(str(details)).strip()
+        return f"{self.node_type(node_id) or 'workflow'} 节点：{rendered or self.name(node_id)}"
+
     def expression_matches(self, expression: dict, values: dict[str, Any]) -> bool:
         results = []
         for rule in expression.get("rules") or []: