使用 Agentic autofix 修复代码质量发现项

Agentic autofix 现已推出，可帮助你清理代码质量积压中的发现项。你可以在一个页面上选择最多 25 个标准发现项，并通过一次操作将整组任务分配给 Copilot。Copilot 会在一个分支中以 Agent 方式开始修复这些问题，验证自身修改，然后创建一个拉取请求，供你审查并合并。

对于单个发现项，Assign to Copilot 将取代 Generate fix。无论你选择一个发现项还是 25 个发现项，都可以使用同一套一致的流程。

Agentic autofix 会遵循你现有的 GitHub Code Quality 企业策略，无需管理单独的策略。因此，只要你的企业允许使用 GitHub Code Quality，用户也可以使用批量修复功能。将发现项分配给 Copilot 会消耗 AI credits。

代码质量发现项的批量 Agentic autofix 适用于已启用 GitHub Code Quality 的 GitHub Team 和 GitHub Enterprise Cloud 仓库，其中包括具有数据驻留功能的 GitHub Enterprise Cloud。请参阅 GitHub Code Quality 文档了解更多信息。

欢迎在 GitHub Code Quality 公告中参与讨论并分享反馈。

Agentic autofix is now available to help you burn down findings in your code quality backlog. You can select up to 25 standard findings on a page and assign the whole set to Copilot in one action. Copilot starts fixing them agentically on a branch, validates its own changes, then opens a pull request for you to review and merge.

Assign to Copilot replaces Generate fix for individual findings, so you get one consistent flow whether you select one finding or 25.

Agentic autofix follows your existing enterprise policy for GitHub Code Quality. There is no separate policy to manage, so if your enterprise allows GitHub Code Quality, users can use bulk remediation too. Assigning findings to Copilot consumes AI credits.

Bulk agentic autofix for code quality findings is available for repositories with GitHub Code Quality enabled on GitHub Team and GitHub Enterprise Cloud, including GitHub Enterprise Cloud with data residency. Learn more in the GitHub Code Quality documentation.

Join the discussion and share feedback in the GitHub Code Quality announcement.