依赖更新何时应触发修复代理？一项轻量级路由研究
When Should Dependency Updates Invoke Repair Agents? A Lightweight Routing Study
查看机构详情
- China Academy of Telecommunication Technology（中国信息通信研究院）
- School of Vehicle and Mobility, Tsinghua University（清华大学车辆与运载学院）
- Intelligent Transportation System Research Center, Southeast University（东南大学智能交通系统研究中心）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对依赖更新中少数需兼容性修复的问题，提出轻量级路由器DepFixRouter，基于创建时信号排序，减少代理调用与成本，提升修复捕获效率。
中文摘要 AI 辅助
依赖更新的拉取请求频繁且大多为常规操作，但其中一小部分需要非平凡的兼容性修复。近年来的仓库级编码代理使得此类修复日益可行，然而对每次依赖更新都调用这些代理会浪费模型调用、CI时间、仓库上下文和审查注意力。我们将此问题定义为代理前路由问题：决定哪些依赖更新拉取请求应在下游诊断或修复尝试之前被升级处理。我们引入了DepFixRouter，一种轻量级路由器，它利用创建时的文本和元数据信号，根据历史兼容性修复可能性对依赖更新进行排序。在497个带标签的GitHub依赖更新候选项中，仅有72个需要实质性修复。仅使用PR标题和机器人/依赖标志的创建时安全LinearSVC达到了0.488的修复F1分数，并在前20%的路由拉取请求中捕获了51.4%的修复，将每次捕获修复的调用次数从全路由或随机策略下的6.90次降低到2.68次。回顾性全历史信号将前20%的召回率提升至65.3%，这表明拉取请求历史中存在大量事后泄漏，而非部署时路由效用。在60例诊断代理试点中，路由器门控诊断将实际LLM调用减少了66.7%，令牌减少了66.1%，这表明在测量诊断而非补丁生成时，预算感知升级是可行的。DepFixRouter可以作为常规依赖更新自动化与昂贵的仓库级代理之间的轻量级升级层，实现预算感知的维护，而无需依赖回顾性修复证据进行部署时路由。
英文摘要
Dependency-update pull requests are frequent and mostly routine, but a small subset requires non-trivial compatibility repair. Recent repository-level coding agents make such repair increasingly plausible, yet invoking them on every dependency update wastes model calls, CI time, repository context, and review attention. We frame this as a pre-agent routing problem: deciding which dependency-update pull requests should be escalated before downstream diagnosis or repair attempts. We introduce DepFixRouter, a lightweight router that ranks dependency updates by historical compatibility-repair likelihood using creation-time textual and metadata signals. On 497 labeled GitHub dependency-update candidates, only 72 require substantive repair. A creation-time-safe LinearSVC using only PR titles and bot/dependency flags reaches 0.488 repair F1 and captures 51.4% of repairs within the top 20% routed pull requests, improving calls per captured repair from 6.90 under route-all or random policies to 2.68. Retrospective full-history signals improve top-20% recall to 65.3%, revealing substantial hindsight leakage in pull-request histories rather than deployment-time routing utility. In a 60-case diagnosis-agent pilot, router-gated diagnosis reduces actual LLM calls by 66.7% and tokens by 66.1%, suggesting budgetaware escalation while measuring diagnosis rather than patch generation. DepFixRouter can serve as a lightweight escalation layer between routine dependency-update automation and expensive repository-level agents, enabling budget-aware maintenance without relying on retrospective repair evidence for deployment-time routing.
