Search
searchRead-onlyIdempotent
Search workspace memory and knowledge using automatic, semantic, keyword, or pattern modes. Control output format, depth, and results count for efficient retrieval.
Instructions
Search workspace memory and knowledge. Modes: auto (recommended), semantic (meaning-based), hybrid (legacy alias for auto), keyword (exact match), pattern (regex), exhaustive (all matches like grep), refactor (word-boundary matching for symbol renaming), team (cross-project team search - team plans only), crawl (deep multi-modal search).
Output formats: full (default, includes content), paths (file paths only - 80% token savings), minimal (compact - 60% savings), count (match counts only - 90% savings).
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Search mode (auto recommended; hybrid is a backward-compatible alias; crawl is deep multi-modal search) | auto |
| query | Yes | Search query | |
| workspace_id | No | Workspace ID (UUID). | |
| project_id | No | Project ID (UUID). | |
| limit | No | Max results to return (default: 3) | |
| offset | No | Offset for pagination | |
| content_max_chars | No | Max chars per result content (default: 400) | |
| context_lines | No | Lines of context around matches (like grep -C) | |
| exact_match_boost | No | Boost factor for exact matches (default: 2.0) | |
| output_format | No | Response format: full (default), paths (80% savings), minimal (60% savings), count (90% savings) |