feat(search): pgvector substrate — vector(384) + HNSW for semantic search

Move semantic_search_notes off the full-table Python cosine scan onto a native
pgvector column: indexed ORDER BY embedding <=> :q LIMIT k (HNSW, cosine).
Migration 0067 enables the extension, converts the JSONB embedding column to
vector(384) (stale-dim rows dropped and regenerated by the startup backfill),
and builds the HNSW cosine index. Postgres image moves postgres:16-alpine ->
pgvector/pgvector:pg17 across prod, quickstart, and CI.

Scribe: project 2, milestone 93, task 1031.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Xz4j1H7pjYSjKsEpgcNH5E

src/scribe/models/embedding.py

@@ -1,11 +1,17 @@
 from datetime import datetime, timezone
 
+from pgvector.sqlalchemy import Vector
 from sqlalchemy import DateTime, ForeignKey, Integer
-from sqlalchemy.dialects.postgresql import JSONB
 from sqlalchemy.orm import Mapped, mapped_column
 
 from scribe.models import Base
 
+# bge-small-en-v1.5 produces 384-dim unit-normalized vectors. The column is a
+# native pgvector `vector(384)` (see migration 0067) so similarity search runs
+# as an indexed `ORDER BY embedding <=> :q LIMIT k` in Postgres rather than a
+# full-table Python cosine scan.
+EMBEDDING_DIM = 384
+
 
 class NoteEmbedding(Base):
     """Stores the embedding vector for a note, used for semantic search."""
@@ -18,7 +24,7 @@ class NoteEmbedding(Base):
         primary_key=True,
     )
     user_id: Mapped[int] = mapped_column(Integer, nullable=False, index=True)
-    embedding: Mapped[list] = mapped_column(JSONB, nullable=False)
+    embedding: Mapped[list] = mapped_column(Vector(EMBEDDING_DIM), nullable=False)
     updated_at: Mapped[datetime] = mapped_column(
         DateTime(timezone=True),
         default=lambda: datetime.now(timezone.utc),