n24q02m/better-code-review-graph

tools

• build

  Full or incremental graph build. Set full_rebuild=true to re-parse all files; pass roots to federate extra repo directories into one graph.

• cache_clear

  Remove all computed embeddings.

• diff

  Nodes added/removed/modified between two commit SHAs (from_sha, to_sha).

• embed

  Compute vector embeddings for semantic search. Dual-mode: local ONNX or cloud chain.

• export

  Export the graph as graphml / json-ld / dot / cypher. Inline or to output_path.

• impact

  Blast radius of changed files. Auto-detects from git diff. Paginated with max_results.

• large_functions

  Find functions/classes exceeding a line-count threshold.

• query

  Predefined patterns: callers_of, callees_of, imports_of, importers_of, children_of, tests_for, inheritors_of, file_summary.

• renamed_in_diff

  Symbols whose callsite line shifted versus a base ref.

• report

  Re-emit cached findings as JSON (format='json') or SARIF v2.1.0 (format='sarif').

• rule_list

  List available rules for an engine.

• scan

  Run a security scan (engine='heuristic' default = 5 regex rules, or 'semgrep'). Findings persist on nodes.security_tags.

• search

  Search code entities by name/keyword or semantic similarity.

• set

  Update a runtime setting (key=log_level).

• setup_complete

  Re-resolve credentials from environment variables.

• setup_reset

  Clear credentials and reset state.

• setup_skip

  Set local mode (skip relay permanently, use ONNX only).

• setup_start

  Start relay setup to configure API keys via browser (HTTP mode).

• setup_status

  Show current credential state, providers configured, and setup URL.

• spot_check

  Random callsite snippets from the last callers_of/callees_of/inheritors_of/importers_of result.

• stats

  Graph size, languages, node/edge breakdown, embedding count.

• status

  Server info: version, graph path, node/edge counts, embedding backend, embeddings count.

• summarize

  LLM-generated one-paragraph docstrings for Function nodes (via the SUMMARY_MODELS chain; no-op when no provider key is set). Cost-capped via max_nodes.

• suppress

  Suppress a finding by rule_id (or remove=true to un-suppress).

• update

  Alias for build with full_rebuild=false (incremental).