Claude CodeとAgentic Workflows: 自律的なコーディングループ、評価ゲート、マルチエージェントアーキテクチャ

// src/tools/types.ts
export interface Tool {
  name: string;
  description: string;
  parameters: {
    type: 'object';
    properties: Record<string, { type: string; description: string; enum?: string[] }>;
    required: string[];
  };
  execute: (args: Record<string, any>) => Promise<string>;
}

// src/tools/terminalExecutor.ts
import { Tool } from './types';
import { exec } from 'child_process';
import util from 'util';

const execPromise = util.promisify(exec);

export const terminalExecutorTool: Tool = {
  name: 'terminal_executor',
  description: 'Executes a shell command in the sandboxed environment and returns its stdout/stderr.',
  parameters: {
    type: 'object',
    properties: {
      command: {
        type: 'string',
        description: 'The shell command to execute (e.g., `npm test`, `git status`, `ls -la`).',
      },
    },
    required: ['command'],
  },
  execute: async ({ command }: { command: string }): Promise<string> => {
    try {
      console.log(`Executing command: ${command}`);
      const { stdout, stderr } = await execPromise(command, { cwd: process.env.SANDBOX_DIR || './sandbox' });
      if (stderr) {
        console.warn(`Command stderr: ${stderr}`);
      }
      return `STDOUT:\n${stdout}\nSTDERR:\n${stderr}`;
    } catch (error: any) {
      return `ERROR: Command failed: ${error.message}\nSTDOUT:\n${error.stdout}\nSTDERR:\n${error.stderr}`;
    }
  },
};

// src/tools/fileManager.ts
import { Tool } from './types';
import fs from 'fs/promises';
import path from 'path';

const SANDBOX_ROOT = process.env.SANDBOX_DIR || './sandbox';

export const fileManagerTool: Tool = {
  name: 'file_manager',
  description: 'Reads, writes, or lists files within the sandboxed environment.',
  parameters: {
    type: 'object',
    properties: {
      action: {
        type: 'string',
        description: 'The file operation to perform.',
        enum: ['read', 'write', 'list'],
      },
      filePath: {
        type: 'string',
        description: 'The path to the file, relative to the sandbox root.',
      },
      content: {
        type: 'string',
        description: 'Content to write for "write" action.',
      },
    },
    required: ['action'],
  },
  execute: async ({ action, filePath, content }: { action: string; filePath?: string; content?: string }): Promise<string> => {
    const fullPath = filePath ? path.join(SANDBOX_ROOT, filePath) : SANDBOX_ROOT;
    try {
      switch (action) {
        case 'read':
          if (!filePath) return 'ERROR: filePath is required for read action.';
          return await fs.readFile(fullPath, 'utf-8');
        case 'write':
          if (!filePath || !content) return 'ERROR: filePath and content are required for write action.';
          await fs.mkdir(path.dirname(fullPath), { recursive: true });
          await fs.writeFile(fullPath, content, 'utf-8');
          return `File written: ${filePath}`;
        case 'list':
          const files = await fs.readdir(fullPath, { recursive: true, withFileTypes: true });
          return files.map(dirent => path.join(dirent.path, dirent.name)).join('\n');
        default:
          return `ERROR: Unknown action: ${action}`;
      }
    } catch (error: any) {
      return `ERROR: File operation failed: ${error.message}`;
    }
  },
};

// src/claudeClient.ts
import Anthropic from '@anthropic-ai/sdk';
import { Tool } from './tools/types';

interface ClaudeMessage {
  role: 'user' | 'assistant';
  content: string | Anthropic.Messages.MessageParam.Content;
}

export class ClaudeClient {
  private anthropic: Anthropic;
  private model: string;

  constructor(apiKey: string, model: string = 'claude-3-7-sonnet-20240620') {
    this.anthropic = new Anthropic({ apiKey });
    this.model = model;
  }

  async chat(
    messages: ClaudeMessage[],
    tools: Tool[],
    maxRetries: number = 3
  ): Promise<Anthropic.Messages.Message> {
    let retries = 0;
    while (retries < maxRetries) {
      try {
        const response = await this.anthropic.messages.create({
          model: this.model,
          max_tokens: 4096,
          messages: messages,
          tools: tools.map(tool => ({
            name: tool.name,
            description: tool.description,
            input_schema: tool.parameters,
          })),
        });
        return response;
      } catch (error: any) {
        console.error(`Claude API error (retry ${retries + 1}/${maxRetries}):`, error.message);
        retries++;
        await new Promise(resolve => setTimeout(resolve, 1000 * Math.pow(2, retries))); // Exponential backoff
      }
    }
    throw new Error(`Failed to get response from Claude after ${maxRetries} retries.`);
  }
}

// src/agents/codingAgent.ts
import { ClaudeClient } from '../claudeClient';
import { Tool } from '../tools/types';
import { terminalExecutorTool, fileManagerTool } from '../tools/index'; // Assuming an index.ts exports all tools

export class CodingAgent {
  private client: ClaudeClient;
  private tools: Tool[];
  private conversationHistory: { role: 'user' | 'assistant'; content: any }[] = [];
  private maxIterations: number;

  constructor(apiKey: string, model: string, maxIterations: number = 10) {
    this.client = new ClaudeClient(apiKey, model);
    this.tools = [terminalExecutorTool, fileManagerTool]; // Register available tools
    this.maxIterations = maxIterations;
  }

  async run(initialTask: string): Promise<string> {
    this.conversationHistory = [{ role: 'user', content: initialTask }];
    let iteration = 0;

    while (iteration < this.maxIterations) {
      console.log(`\n--- Agent Iteration ${iteration + 1} ---`);
      const response = await this.client.chat(this.conversationHistory, this.tools);
      this.conversationHistory.push(response);

      if (response.stop_reason === 'end_turn' && typeof response.content === 'string') {
        console.log('Agent finished with final answer.');
        return response.content; // Agent provided a final text response
      }

      if (response.stop_reason === 'tool_use') {
        const toolCalls = response.content.filter(block => block.type === 'tool_use');
        for (const toolCall of toolCalls) {
          if (toolCall.type === 'tool_use') {
            const tool = this.tools.find(t => t.name === toolCall.name);
            if (tool) {
              console.log(`Agent calling tool: ${tool.name} with args:`, toolCall.input);
              const toolOutput = await tool.execute(toolCall.input);
              console.log(`Tool output: ${toolOutput.substring(0, 200)}...`); // Log truncated output
              this.conversationHistory.push({
                role: 'user',
                content: [{ type: 'tool_result', tool_use_id: toolCall.id, content: toolOutput }],
              });
            } else {
              const errorMessage = `ERROR: Agent tried to call unknown tool: ${toolCall.name}`;
              console.error(errorMessage);
              this.conversationHistory.push({
                role: 'user',
                content: [{ type: 'tool_result', tool_use_id: toolCall.id, content: errorMessage }],
              });
            }
          }
        }
      } else {
        console.log('Agent response:', response.content);
        // If it's not a tool_use and not a final answer, it might be an intermediate thought.
        // We can choose to continue or terminate based on the content.
        // For simplicity, we'll just continue here.
      }
      iteration++;
    }
    return 'Agent terminated due to max iterations without a final answer.';
  }
}

// Example usage:
// (async () => {
//   const apiKey = process.env.ANTHROPIC_API_KEY!;
//   if (!apiKey) {
//     console.error('ANTHROPIC_API_KEY environment variable not set.');
//     process.exit(1);
//   }
//   // Ensure sandbox directory exists
//   await fs.mkdir('./sandbox', { recursive: true });
//   process.env.SANDBOX_DIR = './sandbox';

//   const agent = new CodingAgent(apiKey, 'claude-3-7-sonnet-20240620');
//   const task = 'Create a file named `hello.js` in the sandbox with content `console.log("Hello, Claude!");` then execute it using node.';
//   const result = await agent.run(task);
//   console.log('Final Agent Result:', result);
// })();

// src/evalGates/testRunnerGate.ts
import { terminalExecutorTool } from '../tools/terminalExecutor';

export async function runTestsAndEvaluate(testCommand: string): Promise<{ passed: boolean; output: string }> {
  console.log(`Running evaluation tests with command: ${testCommand}`);
  const result = await terminalExecutorTool.execute({ command: testCommand });

  // Simple heuristic: check for common success/failure indicators
  const passed = !result.includes('ERROR:') && !result.includes('fail') && !result.includes('Failures');
  return { passed, output: result };
}

// Example integration in agent loop (conceptual):
// ... inside CodingAgent.run() after code modification ...
// const { passed, output } = await runTestsAndEvaluate('npm test');
// if (!passed) {
//   this.conversationHistory.push({
//     role: 'user',
//     content: `Tests failed. Output:\n${output}\nAnalyze the failures and fix the code.`,
//   });
// } else {
//   this.conversationHistory.push({
//     role: 'user',
//     content: `Tests passed. Output:\n${output}\nProceed to next step (e.g., code review).`,
//   });
// }
// ...

# Initialize a sandbox directory and git repo
mkdir sandbox
cd sandbox
git init -b main
echo "Initial project setup." > README.md
git add .
git commit -m "Initial commit"

# Create a worktree for the agent
# This allows the agent to work on a separate branch without affecting main
git worktree add ../agent-worktree agent-branch

// src/mcpServer.ts
import express from 'express';
import bodyParser from 'body-parser';
import { CodingAgent } from './agents/codingAgent'; // Example agent
import { ReviewAgent } from './agents/reviewAgent'; // Example review agent

interface AgentTask {
  id: string;
  task: string;
  status: 'pending' | 'in_progress' | 'completed' | 'failed';
  result?: string;
  agentType: 'coding' | 'review';
}

export class MCPServer {
  private app: express.Application;
  private tasks: Map<string, AgentTask> = new Map();
  private codingAgent: CodingAgent;
  private reviewAgent: ReviewAgent; // Assume ReviewAgent exists

  constructor(anthropicApiKey: string) {
    this.app = express();
    this.app.use(bodyParser.json());
    this.codingAgent = new CodingAgent(anthropicApiKey, 'claude-3-7-sonnet-20240620');
    this.reviewAgent = new ReviewAgent(anthropicApiKey, 'claude-3-7-sonnet-20240620'); // Review agent might use a more capable model

    this.setupRoutes();
  }

  private setupRoutes() {
    this.app.post('/task', async (req, res) => {
      const { task, agentType } = req.body;
      if (!task || !agentType) {
        return res.status(400).send('Task and agentType are required.');
      }

      const taskId = `task-${Date.now()}`;
      this.tasks.set(taskId, { id: taskId, task, status: 'pending', agentType });
      res.status(202).json({ taskId, status: 'accepted' });

      // Asynchronously process the task
      this.processTask(taskId);
    });

    this.app.get('/task/:id', (req, res) => {
      const task = this.tasks.get(req.params.id);
      if (!task) {
        return res.status(404).send('Task not found.');
      }
      res.json(task);
    });

    // Auto-review hook endpoint
    this.app.post('/review-pr', async (req, res) => {
      const { prDiff, branchName } = req.body; // In a real system, this would be a webhook payload
      if (!prDiff || !branchName) {
        return res.status(400).send('PR diff and branch name are required.');
      }

      const reviewTaskId = `review-${Date.now()}`;
      this.tasks.set(reviewTaskId, { id: reviewTaskId, task: `Review PR for branch ${branchName}`, status: 'pending', agentType: 'review' });
      res.status(202).json({ reviewTaskId, status: 'review_initiated' });

      // In a real system, the ReviewAgent would interact with Git/PR system
      this.reviewAgent.reviewCode(prDiff, branchName)
        .then(reviewResult => {
          this.tasks.set(reviewTaskId, { ...this.tasks.get(reviewTaskId)!, status: 'completed', result: reviewResult });
          // Here, you'd typically post the reviewResult back to the PR system (e.g., GitHub API)
          console.log(`Review for ${branchName} completed: ${reviewResult}`);
        })
        .catch(error => {
          this.tasks.set(reviewTaskId, { ...this.tasks.get(reviewTaskId)!, status: 'failed', result: error.message });
          console.error(`Review for ${branchName} failed: ${error.message}`);
        });
    });
  }

  private async processTask(taskId: string) {
    const taskEntry = this.tasks.get(taskId);
    if (!taskEntry) return;

    this.tasks.set(taskId, { ...taskEntry, status: 'in_progress' });
    try {
      let result: string;
      if (taskEntry.agentType === 'coding') {
        result = await this.codingAgent.run(taskEntry.task);
      } else if (taskEntry.agentType === 'review') {
        // This path would be for direct review tasks, not PR hooks
        result = await this.reviewAgent.reviewCode(taskEntry.task, 'adhoc-review');
      } else {
        throw new Error(`Unknown agent type: ${taskEntry.agentType}`);
      }
      this.tasks.set(taskId, { ...taskEntry, status: 'completed', result });
    } catch (error: any) {
      this.tasks.set(taskId, { ...taskEntry, status: 'failed', result: error.message });
    }
  }

  listen(port: number) {
    this.app.listen(port, () => {
      console.log(`MCP Server listening on port ${port}`);
    });
  }
}

// (async () => {
//   const apiKey = process.env.ANTHROPIC_API_KEY!;
//   if (!apiKey) {
//     console.error('ANTHROPIC_API_KEY environment variable not set.');
//     process.exit(1);
//   }
//   const mcp = new MCPServer(apiKey);
//   mcp.listen(3000);
// })();

// Example of model routing in Orchestrator or MCP
const codingAgent = new CodingAgent(apiKey, 'claude-3-7-sonnet-20240620'); // For complex coding
const testAgent = new TestAgent(apiKey, 'claude-3-5-haiku-20240307'); // For generating simple tests
const reviewAgent = new ReviewAgent(apiKey, 'claude-3-7-sonnet-20240620'); // For critical code review