Retrieve the current repository index metadata, including file count, symbol count, chunk count, and the exact timestamp when the repository was last indexed.

List all indexed files within the repository. Returns metadata such as relative path, size in bytes, and language. Useful for codebase structure discovery.

List all programming languages detected and indexed in the repository, alongside support status.

List or search indexed code symbols (such as classes, structs, functions, and interfaces) by name. Supports substring filtering.

Search indexed code symbols by name using exact or fuzzy matching. Essential for finding definitions.

Detect high-level architectural components and directories in the repository based on file layouts.

Show the configured or inferred boundaries between architectural components, useful to understand import constraints.

Report any import or boundary violations that deviate from the defined codebase architecture rules.

Evaluate repository-owned architecture policy dependency rules against indexed import, reference, and call graph edges. Returns allowed, forbidden, and unknown edge counts with bounded unknown samples.

Perform a lexical BM25 search across indexed code chunks. Set mode=graph to search indexed graph-node identifiers, qualified names, routes, config keys, and properties.

Search indexed file names and contents for specific keywords or file path patterns. Set mode=graph to search graph-node documents through the same index.

Search indexed code using a regular expression pattern. Returns exact line matching snippets.

Report the current status, readiness, and staleness of the local semantic vector index.

Search the local semantic vector index using natural language queries to retrieve conceptually related code snippets.

Perform a hybrid search combining lexical BM25 candidates and semantic vector candidates to produce ranked, context-rich results.

Run a hybrid search and return detailed, explainable ranking scores and evidence for the top retrieved code snippets.

Perform a structural search across both symbol trees and code chunks to find structural matching syntax.

Retrieve the definition location, file range, and body of a symbol (function, class, struct, trait, module) by its name.

Retrieve all references, usages, and call-sites of a given symbol throughout the indexed codebase.

Find all implementations of a given interface, trait, or abstract class in the repository.

Find all parent functions, methods, or modules that call the target symbol.

Find all functions, methods, or symbols called by the target symbol.

Retrieve the comprehensive context of a symbol, including definition details, range, file context, and documentation if available.

Trace the shortest dependency or reference path between two files or symbols, illustrating how they are connected.

Analyze the potential blast radius of a change to a file. Identifies downstream dependents, callers, and related test files.

Look up bounded commit provenance for exactly one repository-relative path or indexed symbol. Returns first-seen, last-touched, recent touches, confidence, and explicit uncertainty.

List the direct dependency graph neighbors (imports and dependents) of a given file or symbol node.

Assemble a comprehensive, token-efficient context pack of files, symbols, and tests relevant to a natural language task description.

Build a reversible compressed context pack with references and handles. Allows retrieving original snippets later to save prompt space.

Retrieve the original uncompressed source code snippet associated with a compressed context handle.

Generate an evidence-backed pre-edit plan for a task, including primary files to edit, expected impact, changed-line ranges, and recommended test targets.

Record a repository-scoped memory fact with metadata, entity links, and confidence parameters.

Search through the append-only repository memory facts using keyword and entity matches.

Retrieve the metadata, syntax parsing status, and all code chunks for a single repository file.

Retrieve definition, qualified name, range, and direct structural context for a given symbol name.

Summarize the high-level architecture flows and directory boundaries within the repository.

Return a structured summary of the codebase architecture, including layer constraints and violation checks.

Analyze a file path and identify the test files that should be run to validate changes to it.

Recommend a comprehensive validation plan (test targets, coverage checks, static checks) for a file change.

Retrieve and explain the test coverage metrics and associated test suites for a given file.

Propose a patch plan (file edits, context bounds) for a task. Read-only; does not write any files.

Review a proposed patch plan for safety, target constraints, and completeness.

Validate a patch plan against codebase boundaries and references to detect warnings.

Verify an actual diff or set of changed files against a saved pre-edit plan. Validates constraints and runs test commands.

Map a runtime stack trace to indexed source locations and file lines.

Retrieve recent runtime errors and stack traces associated with a given symbol.

Retrieve a list of recent runtime failures, errors, or incidents recorded in the repository.

Retrieve the versioned schema defining the supported graph node types, edge types, and query properties available in the repository's structural evidence graph.

Execute a read-only graph query using a constrained subset of Cypher. Call get_evidence_schema first to see available node/edge types. (Note: The DSL is NOT full Cypher). Output rows are JSON arrays aligned with the user-selected variables in columns.