Move from chroma to sqlitevec with local embedding

internal/db/sqlite/migrations.go

@@ -254,6 +254,24 @@ var Migrations = []Migration{
 			ALTER TABLE user_prompts ADD COLUMN matched_observations INTEGER DEFAULT 0;
 		`,
 	},
+	{
+		Version: 17,
+		Name:    "sqlite_vec_vectors",
+		SQL: `
+			-- Vector embeddings table using sqlite-vec
+			-- Each document (narrative, fact, summary field, prompt) gets one vector
+			-- Uses all-MiniLM-L6-v2 embeddings (384 dimensions)
+			CREATE VIRTUAL TABLE IF NOT EXISTS vectors USING vec0(
+				doc_id TEXT PRIMARY KEY,
+				embedding float[384],
+				sqlite_id INTEGER,
+				doc_type TEXT,
+				field_type TEXT,
+				project TEXT,
+				scope TEXT
+			);
+		`,
+	},
 }
 
 // MigrationManager handles database schema migrations.

internal/db/sqlite/store.go

@@ -7,6 +7,7 @@ import (
 	"fmt"
 	"sync"
 
+	sqlite_vec "github.com/asg017/sqlite-vec-go-bindings/cgo"
 	_ "github.com/mattn/go-sqlite3"
 )
 
@@ -26,6 +27,9 @@ type StoreConfig struct {
 
 // NewStore creates a new database store with the given configuration.
 func NewStore(cfg StoreConfig) (*Store, error) {
+	// Register sqlite-vec extension for vector operations
+	sqlite_vec.Auto()
+
 	// Build connection string with pragmas
 	connStr := cfg.Path + "?_journal_mode=WAL&_synchronous=NORMAL&_foreign_keys=ON"
 
@@ -137,3 +141,9 @@ func (s *Store) QueryRowContext(ctx context.Context, query string, args ...inter
 func (s *Store) Ping() error {
 	return s.db.Ping()
 }
+
+// DB returns the underlying database connection for direct access.
+// Use this sparingly - prefer the store methods for most operations.
+func (s *Store) DB() *sql.DB {
+	return s.db
+}