智能体三周重构30万行C代码，从业者质疑其证明力
原标题：Agents Refactor 300K Lines in Three Weeks, and Practitioners Ask What It Proves
AI 摘要
CodeScene 发布案例研究，称编码智能体在三周内重构了 30 万行 C 代码库（《街头霸王 III：3rd Strike》开源反编译项目），花费约 4000 美元 token 成本，产生 2903 次提交、修改 25.2 万行，Code Health 分数从 5.6 提升至 10.0。其核心机制是 CodeHealth MCP Server 提供确定性质量信号，以及逐帧比对回滚状态哈希的 replay-trace 测试框架。从业者对结果反应两极：支持者认为逐帧回放验证比绿色测试套件更严格，质疑者则关注是否合并入主线、是否属于生产代码，以及架构与非功能指标未被衡量。
正文节选
CodeScene has published a case study in which coding agents refactored a 300,000-line C codebase over three weeks, at a token cost of roughly $4,000. The work produced 2,903 commits across 726 files, modified 252,055 lines, and moved the codebase from a Code Health score of 5.6 to 10.0. The codebase is Street Fighter III: 3rd Strike, taken from an open-source decompilation. Adam Tornhill, CodeScene's founder and the author of Your Code as a Crime Scene, wrote that this was the first time he had