-- Migration 012: Knowledge Graph Hybrid Search
-- Adds HNSW vector index and BM25 full-text index for hybrid retrieval
-- Fixes missing fields in kg_executions (agent_role, provider, cost_cents)
-- that caused deserialization failures on SELECT queries.

-- Missing fields added to make kg_executions round-trip correctly
DEFINE FIELD agent_role ON TABLE kg_executions TYPE option<string>;
DEFINE FIELD provider ON TABLE kg_executions TYPE string DEFAULT 'unknown';
DEFINE FIELD cost_cents ON TABLE kg_executions TYPE int DEFAULT 0;

-- BM25 full-text search on task descriptions
-- class tokenizer preserves word boundaries (code terms, identifiers)
-- snowball(english) reduces "compiling" → "compil" for better recall
DEFINE ANALYZER kg_text_analyzer
    TOKENIZERS class
    FILTERS lowercase, snowball(english);

DEFINE INDEX idx_kg_executions_ft
    ON TABLE kg_executions
    FIELDS task_description
    SEARCH ANALYZER kg_text_analyzer BM25;

-- HNSW approximate nearest neighbor index for semantic similarity
-- DIST COSINE: matches cosine similarity used throughout the codebase
-- TYPE F32: float32 embeddings (OpenAI ada-002 / compatible providers)
-- M 16: graph connectivity (16 edges per node, standard for 1536-dim)
-- EF_CONSTRUCTION 200: index build quality vs speed tradeoff
DEFINE INDEX idx_kg_executions_hnsw
    ON TABLE kg_executions
    FIELDS embedding
    HNSW DIMENSION 1536 DIST COSINE TYPE F32 M 16 EF_CONSTRUCTION 200;