completeTask
Mark tasks as completed in MCPlanManager to unlock dependent tasks and track progress in AI agent task management systems.
Instructions
将指定ID的任务标记为 'completed' (已完成)。 这是解锁后续依赖任务的关键步骤。
Args: task_id (int): 需要标记为完成的任务的ID (从0开始)。 result (str): 描述任务完成结果或产出的字符串。
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| task_id | Yes | ||
| result | Yes |
Implementation Reference
- src/mcplanmanager/app.py:95-105 (handler)The primary MCP tool handler for 'completeTask'. Decorated with @mcp.tool() for automatic registration and schema generation from type hints. Delegates to PlanManager.completeTask for execution.@mcp.tool() def completeTask(task_id: int, result: str) -> ToolResponse[TaskOutput]: """ 将指定ID的任务标记为 'completed' (已完成)。 这是解锁后续依赖任务的关键步骤。 Args: task_id (int): 需要标记为完成的任务的ID (从0开始)。 result (str): 描述任务完成结果或产出的字符串。 """ return plan_manager.completeTask(task_id, result)
- Core helper method in PlanManager that implements the task completion logic: validates task exists and is in_progress, updates status and result, manages current_task_id and plan status.def completeTask(self, task_id: int, result: str) -> Dict: """标记任务为完成状态""" task = self._find_task_by_id(task_id) if not task: return {"success": False, "message": f"Task {task_id} not found", "data": None} if task["status"] != "in_progress": return {"success": False, "message": f"Task {task_id} is not in progress", "data": None} task["status"] = "completed" task["result"] = result # 如果这是当前任务，清除当前任务ID if self.plan_data["state"]["current_task_id"] == task_id: self.plan_data["state"]["current_task_id"] = None # 检查是否所有任务都完成了 all_completed = all( task["status"] in ["completed", "skipped"] for task in self.plan_data["tasks"] ) if all_completed: self.plan_data["state"]["status"] = "completed" self._update_timestamp() return { "success": True, "data": task, "message": "Task completed successfully" }
- src/mcplanmanager/models.py:33-43 (schema)Pydantic schema for TaskOutput, used in the ToolResponse data field for completeTask output.class TaskOutput(BaseModel): """ 用于工具函数返回任务信息时，定义单个任务输出的Pydantic模型。 """ id: int name: str status: str dependencies: List[int] reasoning: str result: Optional[str] = None
- src/mcplanmanager/models.py:6-12 (schema)Generic Pydantic schema for ToolResponse[T], where T=TaskOutput for completeTask, defining the standardized output structure.class ToolResponse(BaseModel, Generic[T]): """ 一个通用的工具响应模型，用于标准化所有工具的返回结构。 """ success: bool = Field(True, description="操作是否成功。") message: Optional[str] = Field(None, description="关于操作结果的可读消息。") data: Optional[T] = Field(None, description="操作返回的主要数据负载。")