开发者为Codex创建了一套自动化分诊技能,通过预设指南并读取项目VISION.md文件,自动处理符合特定标准的issue和PR。这些标准包括契合项目愿景、代码可高置信度推断、修复方案明确且支持实时测试。Codex利用虚拟机与计算机视觉(通过Crabbox平台)验证修复结果,实现自主工作流,减少人工介入。开发者保留手动审核环节,并在repo.bar中集成了issue浏览器,方便点击处理常见剪贴板格式的问题。该系统旨在提升开发效率,让AI承担重复性代码审查与测试任务。
I built an autotriage skill for codex that has a set of guidelines + reads VISION.md from my repos, so issues/prs that have a clear way of - fit vision of the project - being inferrable in code with high confidence - clear fix - can be live tested
Are now worked on autonomously. Codex can use a VM + computer vision (via https://crabbox.sh , new parallels backend) to verify fixes, so it can work without interrupting me. I manually review suggestions. Since it was tedious to type in issues, I added an issue browser into http://repo.bar that parses common clipboard formats by codex so I can click through them conveniently.