vic/vix/codebase-memory

Codebase Memory — Knowledge Graph Tools

Graph tools return precise structural results in ~500 tokens vs ~80K for grep.

Quick Decision Matrix

Exploration Workflow

1. list_projects — check if project is indexed
2. get_graph_schema — understand node/edge types
3. search_graph(label="Function", name_pattern=".*Pattern.*") — find code
4. get_code_snippet(qualified_name="project.path.FuncName") — read source

Tracing Workflow

1. search_graph(name_pattern=".*FuncName.*") — discover exact name
2. trace_path(function_name="FuncName", direction="both", depth=3) — trace
3. detect_changes() — map git diff to affected symbols

Quality Analysis

• Dead code: search_graph(max_degree=0, exclude_entry_points=true)
• High fan-out: search_graph(min_degree=10, relationship="CALLS", direction="outbound")
• High fan-in: search_graph(min_degree=10, relationship="CALLS", direction="inbound")

14 MCP Tools

index_repository, index_status, list_projects, delete_project, search_graph, search_code, trace_path, detect_changes, query_graph, get_graph_schema, get_code_snippet, get_architecture, manage_adr, ingest_traces

Edge Types

CALLS, HTTP_CALLS, ASYNC_CALLS, IMPORTS, DEFINES, DEFINES_METHOD, HANDLES, IMPLEMENTS, OVERRIDE, USAGE, FILE_CHANGES_WITH, CONTAINS_FILE, CONTAINS_FOLDER, CONTAINS_PACKAGE

Cypher Examples (for query_graph)

MATCH (a)-[r:HTTP_CALLS]->(b) RETURN a.name, b.name, r.url_path, r.confidence LIMIT 20
MATCH (f:Function) WHERE f.name =~ '.*Handler.*' RETURN f.name, f.file_path
MATCH (a)-[r:CALLS]->(b) WHERE a.name = 'main' RETURN b.name

Gotchas

1. search_graph(relationship="HTTP_CALLS") filters nodes by degree — use query_graph with Cypher to see actual edges.
2. query_graph has a 200-row cap — use search_graph with degree filters for counting.
3. trace_path needs exact names — use search_graph(name_pattern=...) first.
4. direction="outbound" misses cross-service callers — use direction="both".
5. Results default to 10 per page — check has_more and use offset.

Worktrees (agent teams)

The graph indexes the main checkout, not your worktree. Draw the line accordingly:

• Your own in-progress edits: the graph cannot see them — use grep/Read in your worktree for anything touching your uncommitted work. This is correct, not a fallback.
• The existing codebase — callers, definitions, call chains, architecture, impact of a planned change: the graph is authoritative and vastly cheaper than grepping. From a worktree, pass the main checkout via repo_path so queries hit the shared index instead of an unindexed path.
• One stale-looking answer about your own changes does not mean the graph is broken — it means you asked it about the one thing it does not hold.