给AI写代码时配个“活地图”，不用每次都从头翻
写代码的AI每次查项目都得重新搜、重新读，像每次进图书馆都忘了书架在哪。这篇搞了个系统，把代码库的索引、结构、语义做成“快照”，每次更新只改变动的部分，不用全重做。实测中，图更新快8.7倍，向量更新快25.4倍；AI查代码时，延迟比传统方式低4.7倍，而且少用50-87%的“思考步骤”。它不是给你明天用的工具，但说明了一个趋势：AI写代码的效率瓶颈，正在从模型能力转向“怎么让AI快速看懂项目”。
📄 原文摘要(英文)
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.