Building an AI bug-fixing agent that runs inside your GitHub Actions runner

说明与用途

AI 错误修复代理在自托管的 GitHub Actions 运行器中运行，保持代码私密，仅限读取文件和创建 PR，无法执行测试。

问题

Production errors need automated fixes, but existing SaaS tools expose code to external services.

结果

The system achieves automated bug fixes while keeping code private and limiting agent blast radius, but cannot run tests and requires PR permissions to be enabled.

工作流

• Receive error from tracker
• Control plane starts workflow via workflow_dispatch
• Runner checks out repo and runs agent
• Agent explores code, writes fix to new branch
• Agent opens PR
• Runner reports status, PR link, summary, token counts back to control plane

证据

The service that coordinates the agent should never be able to read the code.

来源

The agent has four tools: get_file_contents, list_directory, search_code, create_pull_request.

来源

The agent cannot run your tests. It can read a test file and mention it, but it cannot execute anything.

来源