Scans and indexes the specified directory to build the knowledge graph. This is a heavy operation and should be called when the codebase changes significantly. Database will be created in {root_path}/.kgraph/

Performs a semantic search for code snippets relevant to the query. Note: Requires a project to be indexed first with reindex_codebase.

Parameters:

• query: Search query

• limit: Maximum results (default 5)

• file_type: Optional file extension filter (e.g., "py", "java", "ts")

• verbose: If True, include technical details like vectors and distances (default False)

Returns the structure (classes, functions) of a specific file. Note: Requires the file's project to be indexed first.

Finds where a class or function is defined. Returns file path, line number, and docstring.

Finds where a symbol is used in the codebase. Returns a list of files and lines where the symbol is called.

Returns a token-efficient summary of a file: imports, classes, functions, and docstrings. Optimized for small context windows.

Retrieves a comprehensive context for a symbol:

1. Definition (where it is)

2. References (who calls it)

3. Calls (who it calls)

This is optimized for small LLMs to get full context in one shot.

Validates a proposed code edit BEFORE applying it. Checks for:

1. Syntax Errors (missing braces, invalid syntax).

2. Breaking Changes (removing functions/classes that are used by other files).

Use this tool to check your code before writing it to a file.