CodeNib: コーディングエージェントにリポジトリコンテキストを提供するマルチビューデータシステム

要旨

编码代理不断搜索、导航并保留来自不断演进的代码仓库中的上下文，然而，断连的索引、语言服务器以及仅限局部任务的历史记录迫使进行重复性发现，并掩盖了生命周期成本。CodeNib 针对每个仓库提交构建了可复用的词汇、稠密与结构视图，将输出映射到仓库相关的源码范围，在编辑过程中维护选定视图，并通过单一运行时提供排名搜索、符号导航及有界上下文。在100个快照中，我们勾勒出跨仓库上下文生命周期的质量-成本边界。当输出与独立重建相匹配时，图更新与向量更新的中位数速度分别提升8.7倍与25.4倍。在与标准化实时服务器位置匹配的静态导航子集（占1000个请求的63%）上，每个请求的实时/静态延迟比值中位数为4.7倍。在五种模型上，选定的上下文策略可保留定位能力，同时与配对的 grep/read 相比，轨迹令牌减少50%–87%。综合来看，这些结果支持具有明确、操作特化有效性边界的多视图仓库上下文服务。

English

Coding agents repeatedly search, navigate, and retain context from evolving repositories, but disconnected indexes, language servers, and task-local histories force repeated discovery and obscure lifecycle costs. CodeNib builds reusable lexical, dense, and structural views per repository commit, maps outputs to repository-relative source ranges, maintains selected views across edits, and serves ranked search, symbol navigation, and bounded context through one runtime. Across 100 snapshots, we map quality-cost frontiers across the repository-context lifecycle. When outputs match an independent rebuild, graph and vector updates are 8.7times and 25.4times faster at the median. On the static-navigation subset matching normalized live-server locations (63% of 1,000 requests), the median per-request live/static latency ratio is 4.7times. Across five models, selected context policies preserve localization with 50--87% fewer trajectory tokens than paired grep/read. Together, these results support multi-view repository-context serving with explicit, operation-specific validity boundaries.