GitHub Agentic Workflows GA：支持ARC、模型路由与微VM隔离
GitHub Agentic Workflows generally available
核心 CI/CD 平台推出全新 Agent 范式，直接改变自动化构建与运维的工作方式。涉及 ARC 集成、预算预测及微 VM 隔离等新能力，建议关注架构团队评估是否迁移现有自动化流程。
GitHub Agentic Workflows, an open source project from GitHub Next, is now generally available. With agentic workflows, you can automate reasoning-based tasks like issue triage, CI failure analysis, documentation updates, and test writing by using coding agents inside GitHub Actions.
GitHub Agentic Workflows（由 GitHub Next 推出的开源项目）现已全面可用。借助智能体工作流，你可以利用 GitHub Actions 中的编码智能体，自动化处理基于推理的任务，如问题分类、CI 失败分析、文档更新和测试编写。
Define your automation in natural language Markdown files, and GitHub Agentic Workflows compiles them into standard Actions YAML. Because these are GitHub Actions, they reuse your existing runner groups and policy constraints. You can use GitHub Copilot or bring your own coding agent to power each workflow.
在自然语言 Markdown 文件中定义你的自动化流程，GitHub Agentic Workflows 会将其编译为标准 Actions YAML。由于这些是 GitHub Actions，它们可以复用你现有的运行器组和策略约束。你可以使用 GitHub Copilot 或引入自己的编码智能体来驱动每个工作流。
We’ve been rolling out our agentic developer workflows, and the results are measurable. One of our leads saved an estimated 29 hours a week on his development work alone. Across his team, measured velocity has more than doubled on average, and AI now authors 91% of the team’s commits. With these workflows, the team cut production errors from about 11,000 a day to under 1,000 and drove a technology migration end to end.
我们一直在推广我们的智能体开发者工作流，且效果可量化。其中一位负责人仅在开发工作上每周就节省了约 29 小时。在其团队范围内，平均衡量速度翻了一倍以上，AI 现在撰写了团队 91% 的提交记录。通过这些工作流，团队将生产错误从每天约 11,000 次减少到不到 1,000 次，并完成了端到端的技术迁移。
One workflow takes a feature from requirements to implementation with validation evidence. Others keep our frameworks current and steadily raise code quality and test coverage. Because AI drives the process to completion, our engineers can run four or five efforts in parallel and stay focused on the bigger goals.
其中一个工作流将功能从需求推进到实现，并提供验证证据。其他工作流则保持我们的框架处于最新状态，稳步提高代码质量和测试覆盖率。由于 AI 驱动流程直至完成，我们的工程师可以同时并行运行四到五个任务，并专注于更大的目标。
Ben Alton – Senior manager, Strategy, Architecture & Innovation team at Accenture
Ben Alton – Accenture 战略、架构与创新团队高级经理
Built-in safeguards
内置的安全防护机制
GitHub Agentic Workflows incorporates layered safeguards for your automation. Agents access GitHub content respecting the integrity filter rules, run with read-only permissions by default, and execute inside a sandboxed container behind the Agent Workflow Firewall. The outputs are validated through the safe outputs process, and a dedicated threat detection job scans all proposed changes before they are applied.
GitHub Agentic Workflows 为你的自动化流程集成了多层安全防护。智能体在访问 GitHub 内容时遵循完整性过滤规则，默认以只读权限运行，并在智能体工作流防火墙后的沙箱容器中执行。输出结果通过安全输出流程进行验证，专门的威胁检测作业会在应用所有提议的更改之前扫描它们。
Additional capabilities for general availability
全面可用的新增功能
Highlights since the public preview include:
自公共预览以来的亮点包括：
- Actions Runner Controller (ARC) and Docker-in-Docker support: Run agentic workflows on self-hosted ARC runners with Docker-in-Docker.
- Improved budget forecasting: gh aw forecast is no longer experimental. It now includes both threat detection credits and monthly ranges for a fuller picture of your AI credit spend.
- New models, engine choices, and workflows: The model inventory has been refreshed, model providers can be picked per workflow, and there are new workflow templates that can be added with gh aw add-wizard.
- Model routing: Workflows can use a model router that optimizes for task type and difficulty.
- Improved agent isolation: Agents can run in a Cloud Hypervisor or NVX micro-VM and prevent data leaks in cross-repository workflows with enclaves.
- Actions Runner Controller (ARC) 和 Docker-in-Docker 支持：在具有 Docker-in-Docker 功能的自托管 ARC 运行器上运行智能体工作流。
- 改进的预算预测：gh aw forecast 不再处于实验阶段。它现在同时包含威胁检测积分和月度范围，让你更全面地了解 AI 积分的使用情况。
- 新模型、引擎选项和工作流：模型清单已刷新，可以为每个工作流选择模型提供商，并且可以通过 gh aw add-wizard 添加新的工作流模板。
- 模型路由：工作流可以使用针对任务类型和难度进行优化的模型路由器。
- 改进的代理隔离：代理可以在 Cloud Hypervisor 或 NVX 微虚拟机中运行，并通过安全 enclave 防止跨仓库工作流中的数据泄露。
See the GitHub Agentic Workflows release notes for the full list of changes.
请参阅 GitHub Agentic Workflows 发行说明以获取完整的更改列表。
Get started
开始使用
Follow the quickstart guide to install the CLI extension and trigger your first workflow in minutes. Explore prebuilt workflows in GitHub Next’s agentics repository for ready-to-use examples covering triage, dependency management, code review, and reporting.
按照快速入门指南安装 CLI 扩展，并在几分钟内触发你的第一个工作流。在 GitHub Next 的 agentics 仓库中探索预构建的工作流，获取涵盖分类、依赖管理、代码审查和报告的即用型示例。
GitHub Agentic Workflows is now generally available on github.com for GitHub Free, Team, and Enterprise. Using the default GitHub Copilot CLI engine to power a workflow requires a Copilot license.
GitHub Agentic Workflows 现已在 github.com 上对 GitHub Free、Team 和 Enterprise 全面开放。使用默认的 GitHub Copilot CLI 引擎来驱动工作流需要 Copilot 许可证。
Learn more in the GitHub Agentic Workflows documentation, and join the conversation in the community discussion.
在 GitHub Agentic Workflows 文档中了解更多内容，并加入社区讨论中的交流。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力