Review Pr (Grade A)Gynybos apverstoji duomenų ir ai aiškinimo priemonė Claude AI. A klasė. Rezultatai PR arba šakos skirtumo apžvalgia naudojant žinyno grafiką plenta suderinamoju kontekstu. Rezultatai struktūrizuotas apžvalga su blast-raidio analizės

Kaip jis valdo monorepozitorijas, git dirbtuves ir kelias repozitorijas?

Monorepozitorijos: viena grafą kiekvienam repozitorijos šaknynui automatiškai sudaroma; indeksuojami tik sekami failai, ir .code-review-graphignore failas gali išskirti papildomus keliaus. Git dirbtuvės: kiekviena dirbtuvė atpažįstama kaip atskira šaknys ir gauta savo grafą; bendrinant vieną duombazę tarp dirbtuvių skirtinguose komituose nėra palaikoma. Kelios repozitorijos: lengvųjų registru (saugomas ~/.code-review-graph/registry.json) leidžia MCP klientams ieškoti tarp užregistruotų projektų, ir daemonas gali stebėti kelias repozitorijas, kad jų grafai būtų atnaujinti. Naudokite --repo, --data-dir arba CRGDATADIR aplinkos kintamojo, kad keistumėte vietas.

Asked by Jana Krejčí · Dec 28, 2025

How big a codebase justifies it?

Below a few hundred files the benefit is marginal because an agent can often hold the whole repo in context. Between a few hundred and a few thousand files is the sweet spot: benchmarks on repos ranging from 60 to ~1,100 files show 38×–528× token reductions on whole‑corpus questions. Multi‑thousand‑file repos and monorepos provide the strongest case, as agents cannot read the entire corpus per query and incremental graph updates keep the index fresh with minimal cost. The frequency of multi‑file queries also influences the payoff.

Asked by Wolfgang Krause · Dec 8, 2025

How do I verify it is working?

1. Ensure the graph file exists and contains nodes/edges; a zero count means the build didn’t run. 2. Run a change and observe the risk summary and Token Savings panel; add --verify to cross‑check token estimates with the cl100kbase tokenizer. 3. In Claude Code, run /mcp and confirm the code‑review‑graph server is connected and its tools are listed. Then ask a structural question (e.g., "what calls parsefile?") and verify the assistant uses query_graph instead of grepping. If any step fails, consult TROUBLESHOOTING.md.

Asked by Elena Rossi · Nov 18, 2025

Does it phone home?

No. There is zero telemetry. The graph is stored locally in a SQLite file inside your repository, and all core operations run entirely on your machine. The only network activity is optional: installing the embeddings extra will download a sentence‑transformers model from HuggingFace, and cloud embedding providers (OpenAI, Google Gemini, MiniMax) will receive only the function signatures you explicitly choose to embed, after you acknowledge the egress warning. Otherwise, your code never leaves the machine.

Asked by Lindiwe Mahlangu · Nov 16, 2025

When should I not use it?

The README lists several cases: very small repos (a few hundred files) where the overhead of building a graph outweighs the benefits; trivial single‑file changes where the graph response adds more tokens than the raw diff; one‑off questions on a repo you won’t revisit; and flow detection in languages where CRG’s entry‑point detection is less reliable (e.g., JavaScript and Go currently have low recall). In these scenarios, simple agentic search or grepping is usually sufficient.

Asked by Mia Andersen · Nov 12, 2025