CodeNib：一個為程式代理提供儲存庫上下文的多視圖數據系統

摘要

編碼代理反覆搜尋、導航並從持續演進的儲存庫中保留上下文，但中斷的索引、語言伺服器以及任務本地的歷史記錄，迫使代理重複發現並掩蓋生命週期成本。CodeNib 為每個儲存庫提交建立了可重複使用的詞彙、密集及結構化視圖，將輸出對應至儲存庫相對應的源範圍，在編輯過程中維護選定視圖，並透過單一執行環境提供排序搜尋、符號導航及有限上下文服務。在 100 個快照中，我們繪製了儲存庫上下文生命週期中的品質-成本邊界。當輸出與獨立重建相符時，圖形與向量更新的中位數速度分別提升 8.7 倍與 25.4 倍。在靜態導航子集（與標準化即時伺服器位置匹配，佔 1,000 個請求的 63%）中，每個請求的即時/靜態延遲中位數比率為 4.7 倍。在五個模型中，選定的上下文策略保存了定位能力，同時比配對的 grep/read 減少 50% 至 87% 的軌跡令牌。總體而言，這些結果支持具有明確、操作特定有效性邊界的多視圖儲存庫上下文服務。

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.