Enhance workflow engine and integration in backend and frontend

- Introduce a new WorkflowEngine class to manage workflow graphs, enabling dynamic node-based interactions.
- Update AssistantConfig to include a graph field for workflow definitions, allowing for flexible configuration.
- Modify pipeline execution to support workflow-driven dialogue, integrating node transitions and system prompts based on active nodes.
- Enhance frontend components to visualize active nodes and provide debugging capabilities, including highlighting the current node during interactions.
- Refactor existing components to accommodate new workflow functionalities and improve overall user experience.

backend/services/node_specs.py

@@ -23,7 +23,7 @@ NODE_SPECS: list[dict[str, Any]] = [
         "name": "startCall",
         "displayName": "开始",
         "category": "call_node",
-        "description": "工作流入口,每个流程有且仅有一个。播放开场白并进入首个节点。",
+        "description": "工作流入口,每个流程有且仅有一个。播放开场白,并用自己的提示词进行多轮对话,满足出边条件后流转。",
         "icon": "Play",
         "accent": "mint",
         "addable": False,
@@ -31,7 +31,7 @@ NODE_SPECS: list[dict[str, Any]] = [
         "fields": [
             {"key": "name", "label": "节点名称", "type": "text"},
             {"key": "greeting", "label": "开场白", "type": "textarea"},
-            {"key": "prompt", "label": "全局提示词", "type": "textarea"},
+            {"key": "prompt", "label": "节点提示词", "type": "textarea"},
         ],
     },
     {