arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.20478cs.SE
收藏

编译上下文:复杂代码库中AI代理的基础设施

Codified Context: Infrastructure for AI Agents in a Complex Codebase

Independent Researcher USA;Independent Researcher

Aristidis Vasilopoulos

AI总结:

本文提出了一种编译上下文基础设施,通过编码约定、领域专家代理和知识库,提升大规模多代理项目中的代码一致性与可靠性。

摘要:

基于LLM的代理编码助手缺乏持久记忆:它们在会话之间失去连贯性,忘记项目约定,并重复已知的错误。最近的研究描述了开发人员如何通过清单文件配置代理,但仍然存在一个开放性挑战,即如何将此类配置扩展到大规模的多代理项目。本文介绍了在构建一个108,000行C#分布式系统过程中开发的三部分编译上下文基础设施:(1)一个热内存构成,用于编码约定、检索钩子和协调协议;(2)19个专门的领域专家代理;(3)一个包含34个按需规范文档的冷内存知识库。对基础设施增长和交互模式的定量指标,以及283个开发会话中的四个观察性案例研究,展示了编译上下文如何在会话之间传播以防止故障并保持一致性。该框架作为开源互补仓库发布。

英文摘要:

LLM-based agentic coding assistants lack persistent memory: they lose coherence across sessions, forget project conventions, and repeat known mistakes. Recent studies characterize how developers configure agents through manifest files, but an open challenge remains how to scale such configurations for large, multi-agent projects. This paper presents a three-component codified context infrastructure developed during construction of a 108,000-line C# distributed system: (1) a hot-memory constitution encoding conventions, retrieval hooks, and orchestration protocols; (2) 19 specialized domain-expert agents; and (3) a cold-memory knowledge base of 34 on-demand specification documents. Quantitative metrics on infrastructure growth and interaction patterns across 283 development sessions are reported alongside four observational case studies illustrating how codified context propagates across sessions to prevent failures and maintain consistency. The framework is published as an open-source companion repository.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑