微软把代码测试生成器开源了，能自动写单测，比原版Copilot完成率高13个百分点，试试就知道。
微软将code-testing-generator开源，代码托管在MIT许可的dotnet/skills仓库。该多语言单元测试Agent会先扫描仓库，识别语言、测试框架和构建命令，再自动编写并运行测试。在微软内部152任务基准上，它完成140个任务，而同一模型下原版GitHub Copilot完成120个。任务完成率92.1%对78.9%，增益集中在模糊提示和diff相关请求。
Microsoft Open Sources code-testing-generator: a Polyglot Unit-Test Agent That Hits 92.1% Task Completion Versus 78.9% for Stock Copilot
Microsoft has open sourced code-testing-generator, a polyglot unit-test agent shipping in the MIT-licensed dotnet/skills repository. It reads a repository before writing anything — detecting the language, test framework, existing conventions, and the real build and test commands — then plans, writes, runs and validates the tests it produces. On Microsoft's internal 152-task benchmark it completed 140 tasks against 120 for stock GitHub Copilot on the same model, with the gain concentrated almost entirely in vague prompts and diff-targeted requests. The post Microsoft Open Sources code-testing-generator: a Polyglot Unit-Test Agent That Hits 92.1% Task Completion Versus 78.9% for Stock Copilot appeared first on MarkTechPost .