Skip to main content
Glama

agentic_codegen_execute

Generate and test code automatically for GitHub issues using AI-driven development workflows. Analyzes issues, creates code, and prepares pull requests to streamline software development processes.

Instructions

CodeGenAgent実行 - AI駆動コード生成・テスト自動生成

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
descriptionYesタスク詳細
issue_numberYesGitHub Issue番号
priorityNo優先度
titleYesタスクタイトル

Implementation Reference

  • The handler function `handleCodeGenExecute` that implements the core logic of the tool by triggering the GitHub Actions workflow for the codegen agent using `gh workflow run agentic-system.yml -f agent=codegen`.
      private async handleCodeGenExecute(args: {
        issue_number: number;
        title: string;
        description: string;
        priority?: string;
      }) {
        try {
          // Trigger GitHub Actions workflow
          const { stdout } = await execAsync(
            `gh workflow run agentic-system.yml -f agent=codegen -f issue_number=${args.issue_number}`,
            { cwd: process.env.GITHUB_REPOSITORY_PATH || process.cwd() }
          );
    
          return {
            content: [
              {
                type: 'text',
                text: `## 🤖 CodeGenAgent起動
    
    **Issue**: #${args.issue_number}
    **Title**: ${args.title}
    **Priority**: ${args.priority || 'P2-中'}
    
    ✅ GitHub Actionsワークフローを起動しました
    
    進捗は Issue #${args.issue_number} で確認できます
    Workflow: https://github.com/${process.env.GITHUB_REPOSITORY}/actions`
              }
            ]
          };
        } catch (error) {
          return {
            content: [
              {
                type: 'text',
                text: `❌ エラー: ${error instanceof Error ? error.message : 'Unknown error'}\n\nGitHub CLIとワークフローファイルを確認してください`
              }
            ]
          };
        }
      }
  • The input schema defining the parameters for the agentic_codegen_execute tool: issue_number (number, required), title (string, required), description (string, required), priority (string enum, optional).
    inputSchema: {
      type: 'object',
      properties: {
        issue_number: {
          type: 'number',
          description: 'GitHub Issue番号'
        },
        title: {
          type: 'string',
          description: 'タスクタイトル'
        },
        description: {
          type: 'string',
          description: 'タスク詳細'
        },
        priority: {
          type: 'string',
          enum: ['P0-緊急', 'P1-高', 'P2-中', 'P3-低'],
          description: '優先度'
        }
      },
      required: ['issue_number', 'title', 'description']
    }
  • server.ts:40-66 (registration)
    The tool object registration in the TOOLS array used by the listTools handler.
    {
      name: 'agentic_codegen_execute',
      description: 'CodeGenAgent実行 - AI駆動コード生成・テスト自動生成',
      inputSchema: {
        type: 'object',
        properties: {
          issue_number: {
            type: 'number',
            description: 'GitHub Issue番号'
          },
          title: {
            type: 'string',
            description: 'タスクタイトル'
          },
          description: {
            type: 'string',
            description: 'タスク詳細'
          },
          priority: {
            type: 'string',
            enum: ['P0-緊急', 'P1-高', 'P2-中', 'P3-低'],
            description: '優先度'
          }
        },
        required: ['issue_number', 'title', 'description']
      }
    },
  • server.ts:226-227 (registration)
    The switch case dispatching calls to the agentic_codegen_execute tool to its handler function within the CallToolRequest handler.
    case 'agentic_codegen_execute':
      return await this.handleCodeGenExecute(args as any);

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ShunsukeHayashi/agentic-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server