tirth8205/code-review-graph：README 來源編輯指南

tirth8205/code-review-graph 的 README 將專案描述為「Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.」。本文只整理倉庫可直接核對的內容，不把 star、Fork 或宣傳語當成品質證明。README 在「README」下寫到：AI coding tools can end up re-reading large parts of your codebase on review tasks. code-review-graph fixes that. It builds a structural map of your code with Tree-sitter so it reads only what matters.。這說明的是專案邊界，不是已完成的生產驗證。

從 README 的「Limitations and known weaknesses」與相關條目，可以先判斷它是否處理你的實際問題：Small single-file changes: Graph context can exceed naive file reads for trivial edits (see express results above). The overhead is the structural metadata that enables multi-file analysis.。若需求不同，不應只因專案熱度就採用。本文保留原始專案名、命令與元件名，方便回到一手來源核對。 README 另外列出一項可核對的資訊：Impact "recall 1.0" is graph-derived and circular: the historical ground truth comes from the same graph edges the predictor walks, so it is an upper bound by construction.。這類原文條目可用來設計試跑步驟，但不能取代實際環境測試。

README 將運作方式分散在「Quick Start」等段落。可確認的線索包括：Requires Python 3.10+. For the best experience, install uv.。本文不把未寫出的架構、效能或安全邊界補成結論；真正的執行鏈仍要配合目錄、設定檔與版本標籤檢查。

第一次安裝應從 README 指出的入口開始。目前可核對的命令是： pip install code-review-graph # or: pipx install code-review-graph code-review-graph install # auto-detects and configures all supported platforms code-review-graph build # parse your codebase 如果倉庫沒有命令，本文不會自行編造步驟，而是建議先閱讀「How It Works」，確認系統依賴、預設埠與首次初始化。

日常使用取決於專案文件。README 的「Quick Start」段落提到：To remove CRG from a Git or SVN project, use the symmetric uninstall command from anywhere inside its working tree. The target is normalized to the working tree root, and non-repository directories are refused.。設定檔、環境變數、權限與資料目錄只在來源明確時才會記錄；沒有寫出的預設值，應在測試環境驗證並保留回滾副本。 同一部分也提到：Search quality (MRR 0.35): Keyword search finds the right result in the top-4 for most queries, but ranking needs improvement. Express queries return 0 hits due to module-pattern naming.。