Delegates large file reads to a cheap worker model so coding agents avoid consuming context, with optional hook enforcement and per-call token savings.
Enables LLMs to efficiently navigate and analyze large diff files by providing pattern-based chunk navigation, allowing direct access to relevant changes without loading entire diffs into context.
Enables AI agents to read, replace, and write files through line-range-scoped, byte-literal edits that preserve CRLF/LF line endings and indentation, reject ambiguous matches, and perform atomic writes. It returns the actual current range content and a self-correction hint on mismatch, eliminating 'Could not find oldString' failures in MCP clients like opencode and Claude Desktop.
Enables intelligent handling of large files through smart chunking, search with regex support, line navigation, and streaming capabilities without loading entire files into memory.