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/models.py

@@ -46,6 +46,9 @@ class AssistantConfig(BaseModel):
 
     enableInterrupt: bool = True
 
+    # workflow 类型:节点图(nodes/edges)。非 workflow 为空,引擎据此决定是否启用。
+    graph: dict = {}
+
     # ---- 运行时连接信息(服务端注入,不来自浏览器) ----
     # 为空时,service_factory 会回退到 config.py 的 .env 默认值。
     llm_api_key: str = ""