AI Agent 自动化测分布式系统
推荐指数 69.0 NO. 009 · 2026.05.21
发布2026/05/20Score61Comments8
为什么值得看
两个纯 Markdown 技能文件让 AI Agent 自主设计并执行分布式系统的声明式测试，输出结构化测试计划和 9 态裁决报告。对苦于分布式系统测试难复现、难定责的工程师，这意味着可以把混沌工程的部分工作交给 Agent 闭环完成。
编辑判断
分布式系统测试长期卡在"能跑通但不敢信"的尴尬地带，传统方案如 Jepsen 需要手写大量专用模型，Chaos Monkey 只注入故障不负责验证正确性。这个项目把测试设计、执行、裁决、定责全丢给 Agent，关键创新是 9-state verdict 和 blame 分类——把"系统错了还是测试错了"这个扯皮问题结构化。
跟 Jepsen 比，它不需要学 Clojure 写线性一致性检查器；跟 Antithesis 这种商业平台比，它是零成本的 Markdown 技能文件。最该试的人是正在用 Claude Code 或 Cursor 做日常开发的 infra 团队，把现有系统的核心不变量写成 claims，让 Agent 夜跑回归。
社区反馈
意见分歧 8 条评论
核心争论：AI Agent 自动化测试是提效工具还是侵蚀开源贡献者价值的威胁
I like the “claim-driven” framing. For stateful systems, tests named after setup details often get weakened over time. Tests named after the claim they are trying to falsify are harder to water down. The part I’d be most interested in is how well this works for business invariants like idempotent po
I think all these scripts become poor where they're context based as opposed to actual guardrails; what we need is various silo'd protocols like a ssh protocol that keeps the harness producing work through the protocol rather than a bunch of loosely based bash scripts, etc. Plus, the harness needs t
Welp. Glad to see Li Shen's using the last fifteen years of my work to automate away my job. :-/ -- edit -- I've seen clients and some colleagues working on things like this, and I can't seem to put into words how disheartening it is. With the exception of some private analysis work, I've share