spec_coding_execute_start

Initiate task execution in spec-driven development by providing guidance for implementing requirements through structured workflows.

Instructions

Start the task execution phase and provide guidance for task execution

Input Schema

TableJSON Schema

Name	Required	Description
`session_id`	Yes	Session identifier
`feature_name`	Yes	Feature name
`task_id`	No	Optional: Specify the task ID to execute; if not specified, the next unfinished task will be executed

Implementation Reference

src/tools/execute.ts:9-48 (handler)

The executeStart function that implements the core logic of the 'spec_coding_execute_start' tool. It reads an 'execute-task.md' template and constructs a markdown response with execution guidance, session info, and workflow progress.

export async function executeStart(
  params: ExecuteStartParams
): Promise<string> {
  const { session_id, feature_name, task_id = 'next_uncompleted' } = params;
  console.error(`[MCP] Starting execution for feature: ${feature_name}, task: ${task_id}`);
  
  // 使用 execute-task.md 模板
  const template = await readTemplate('execute-task.md', {
    feature_name,
    session_id,
    task_id
  });
  
  return `# ⚙️ Task Execution Stage (5/5)

## Feature: ${feature_name}

Congratulations! Now entering the final execution stage. Based on the completed requirements, design, and task planning, let's start executing development tasks one by one.

### Workflow Progress:
- [x] 1. Goal Collection ✅
- [x] 2. Requirements Gathering ✅
- [x] 3. Design Documentation ✅
- [x] 4. Task Planning ✅
- [x] 5. **Task Execution** ← Current Stage

---

${template}

---

**Session Information**:
- Session ID: \`${session_id}\`
- Feature Name: \`${feature_name}\`
- Current Task: \`${task_id}\`
- All Documents: ✅ Completed

Now please start executing the development tasks!`;
}

src/server.ts:168-189 (schema)

The JSON inputSchema definition for the tool, matching the ExecuteStartParams interface, requiring session_id and feature_name, with optional task_id.

{
  name: 'spec_coding_execute_start',
  description: 'Start the task execution phase and provide guidance for task execution',
  inputSchema: {
    type: 'object',
    properties: {
      session_id: { 
        type: 'string', 
        description: 'Session identifier' 
      },
      feature_name: { 
        type: 'string', 
        description: 'Feature name' 
      },
      task_id: { 
        type: 'string', 
        description: 'Optional: Specify the task ID to execute; if not specified, the next unfinished task will be executed' 
      }
    },
    required: ['session_id', 'feature_name']
  }
}

src/server.ts:239-241 (registration)
Registration in the tool call switch statement: dispatches calls to the executeStart handler.
```
case 'spec_coding_execute_start':
  result = await executeStart(args as any);
  break;
```

src/server.ts:193-196 (registration)

The ListTools handler returns the tools list including this tool's definition.

server.setRequestHandler(ListToolsRequestSchema, async () => {
  console.error('[MCP] Handling list tools request');
  return { tools };
});

src/tools/execute.ts:3-7 (helper)
TypeScript interface defining the input parameters, aligning with the tool's inputSchema.
```
export interface ExecuteStartParams {
  session_id: string;
  feature_name: string;
  task_id?: string;
}
```

Spec-driven Development MCP Server