feat: DeepSeek v4 模型对齐、作业助手脚本与 Agent 对比测试

- 前端 WorkflowEditor/ModelConfigs/NodeTemplates：deepseek-v4-flash、v4-pro，弃用提示
- llm_service 默认 deepseek-v4-flash；workflow_engine 等与模型配置注入
- 作业管理脚本支持 AGENT_NAME 与 v4-pro；新增 compare_homework_agents 脚本
- 文档重命名为 (红头)项目核心文档汇总.md 并更新 DeepSeek 说明

Made-with: Cursor

backend/app/api/node_templates.py

@@ -27,7 +27,7 @@ class NodeTemplateCreate(BaseModel):
     prompt: str = Field(..., min_length=1, description="提示词模板")
     variables: Optional[List[Dict[str, Any]]] = Field(None, description="变量定义列表")
     provider: Optional[str] = Field("deepseek", description="默认LLM提供商")
-    model: Optional[str] = Field("deepseek-chat", description="默认模型")
+    model: Optional[str] = Field("deepseek-v4-flash", description="默认模型")
     temperature: Optional[str] = Field("0.7", description="默认温度参数")
     max_tokens: Optional[int] = Field(1500, description="默认最大token数")
     is_public: Optional[bool] = Field(False, description="是否公开")
@@ -176,7 +176,7 @@ async def create_node_template(
         prompt=template_data.prompt,
         variables=template_data.variables or [],
         provider=template_data.provider or "deepseek",
-        model=template_data.model or "deepseek-chat",
+        model=template_data.model or "deepseek-v4-flash",
         temperature=template_data.temperature or "0.7",
         max_tokens=template_data.max_tokens or 1500,
         is_public=template_data.is_public or False,

backend/app/api/node_test.py

@@ -60,7 +60,12 @@ async def test_node(
             "edges": []
         }
         
-        engine = WorkflowEngine("test-node", workflow_data, db=db)
+        engine = WorkflowEngine(
+            "test-node",
+            workflow_data,
+            db=db,
+            trusted_model_config_user_id=str(current_user.id),
+        )
         
         # 执行节点
         result = await engine.execute_node(node, input_data)