twining_query
Search blackboard entries using semantic or keyword queries to find relevant information for development tasks.
Instructions
Semantic search across blackboard entries. Uses embeddings when available, falls back to keyword search. Returns entries ranked by relevance.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Natural language query | |
| entry_types | No | Optional type filter | |
| limit | No | Max results (default: 10) |
Implementation Reference
- src/tools/blackboard-tools.ts:107-139 (registration)The tool 'twining_query' is registered here. It calls 'engine.query' to perform the actual logic.
// twining_query — Semantic search across blackboard entries server.registerTool( "twining_query", { description: "Semantic search across blackboard entries. Uses embeddings when available, falls back to keyword search. Returns entries ranked by relevance.", inputSchema: { query: z.string().describe("Natural language query"), entry_types: z .array(z.string()) .optional() .describe("Optional type filter"), limit: z .number() .optional() .describe("Max results (default: 10)"), }, }, async (args) => { try { const result = await engine.query(args.query, { entry_types: args.entry_types, limit: args.limit, }); return toolResult(result); } catch (e) { return toolError( e instanceof Error ? e.message : "Unknown error", "INTERNAL_ERROR", ); } }, );