摘要：前沿模型已大幅降低编写定制代码的成本：某位专家在自身领域发现的一个小众问题，如今只需一个下午即可解决。然而，审查和维护这些代码的成本并未同步下降。每个解决方案都会逐渐偏离其他方案；要理解其中任一个，都意味着从头阅读其代码库。大型企业反而会构建某种集中治理的方案：最差的情况是采用现成产品，最好的情况则是为每个用例进行定制接线的图编排框架，或作为编排器使用的低代码平台。这些方案每次都是定制的，且适用范围有限。企业并未权衡一种能够摆脱这两类约束的第三种选择：harness 范式。
近期研究将 coding-agent harness 视为企业基础设施，而非编码工具，并逐步形成三项结论：harness 在任务层面已经足够，并且在企业工作中优于更复杂的架构（arXiv:2604.00073、arXiv:2604.13107）；harness 的选择解释了 Agent 基准测试结果中的大部分差异，其影响大于模型选择（arXiv:2605.23950）；而这一发现与企业采纳之间的差距在于治理（arXiv:2605.10223、arXiv:2605.18747）。
我们提出了一种弥合这一差距的架构。一个未经修改的 harness 作为骨干运行；其代码在每次部署中均保持一致，因此，对所构建内容的审查可简化为阅读其指令文件。第 4 节给出了四项机制：凭证范围限定的工具，其中每个后端均获得一个通用请求工具和一个范围限定凭证，而非手工构建的方法；将授权逻辑置于 harness 之外，使同一工件可作为 cron 骨干、聊天界面引擎和终端工具运行；注册成为推送代码的副作用，将审计工作简化为审查一个文本文件。
该方案构建于 microcc（<此 HTTPS URL>）之上，microcc 是我们的参考 harness。

Abstract:Frontier models have collapsed the cost of writing custom code: a niche problem a specialist sees in their own domain now costs an afternoon. The cost of reviewing and maintaining that code hasn't collapsed. Each solution drifts from the next; understanding one means reading its codebase from scratch. Large enterprises build something centrally governed instead: at worst an off-the-shelf product, at best a graph-orchestration framework wired bespoke per use case, or a low-code platform used as the orchestrator. These are custom every time and limited in scope. Enterprises don't weigh a third option that escapes both constraints: the harness paradigm.
Recent work treats the coding-agent harness as enterprise infrastructure rather than a coding tool, converging on three findings: harnesses suffice at the task level and outperform more elaborate architectures on enterprise work (arXiv:2604.00073, arXiv:2604.13107); harness choice accounts for most of the variance in agent benchmark results, more than model choice does (arXiv:2605.23950); and the gap between that finding and enterprise adoption is governance (arXiv:2605.10223, arXiv:2605.18747).
We propose an architecture that closes that gap. One harness runs unmodified as the backbone; the code stays identical across every deployment, so reviewing what gets built collapses to reading its instructions file. Section 4 gives four mechanisms: credential-scoped tooling, where each backend gets one generic request tool and a scoped credential instead of a hand-built method; authorization logic outside the harness, so one artifact runs as a cron backbone, a chat-surface engine, and a terminal tool; registration is a side effect of pushing code, collapsing an audit a review of a text file.
Built on microcc (<this https URL), our reference harness.