Phase 0 complete: fuzzy entity tier, incremental sync, Start9 packaging

- Fuzzy tier (backend/ingest/fuzzy_resolve.py + llm.py): local Qwen adjudicates
  the deterministic resolver's flagged name-variant candidates; merges are
  durable via entity_merges (deterministic re-runs respect them), losers
  soft-deleted, logged. Idempotent.
- Incremental sync (backend/ingest/sync.py): re-embeds only rows changed since a
  watermark (ingest_sync_state); first run / --recreate = full. Tested full→0→1.
- Start9 packaging (start9/0.4): Dockerfile bundles ingest+mcp + fastembed/mcp;
  "Build search index" action runs the init in a subcontainer; MCP shipped as a
  manual stdio server (not a daemon); version 0.1.0:44. INGEST_PACKAGING.md.
- backfill.py: factored embed_and_upsert() shared with sync.

Verified end-to-end on synthetic data + live Sparks/Qwen/Qdrant.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

backend/ingest/backfill.py

@@ -17,17 +17,9 @@ import qdrant_io
 import sparse
 
 
-def run(db, recreate=False, batch=32):
-    conn = sqlite3.connect(db)
-    conn.row_factory = sqlite3.Row
-    chunks = chunking.build_chunks(conn)
-    conn.close()
-    print(f"Built {len(chunks)} chunks from {db}")
-
-    state = qdrant_io.create_collection(recreate=recreate)
-    qdrant_io.ensure_indexes()
-    print(f"Collection '{config.COLLECTION}': {state}")
-
+def embed_and_upsert(chunks, batch=32, progress=True):
+    """Embed (dense + sparse) and upsert a list of chunks to Qdrant. Shared by the
+    full backfill and the incremental sync. Returns the number of points written."""
     total = 0
     for i in range(0, len(chunks), batch):
         group = chunks[i:i + batch]
@@ -46,8 +38,23 @@ def run(db, recreate=False, batch=32):
             })
         qdrant_io.upsert(points)
         total += len(points)
-        print(f"  upserted {total}/{len(chunks)}")
+        if progress:
+            print(f"  upserted {total}/{len(chunks)}")
+    return total
 
+
+def run(db, recreate=False, batch=32):
+    conn = sqlite3.connect(db)
+    conn.row_factory = sqlite3.Row
+    chunks = chunking.build_chunks(conn)
+    conn.close()
+    print(f"Built {len(chunks)} chunks from {db}")
+
+    state = qdrant_io.create_collection(recreate=recreate)
+    qdrant_io.ensure_indexes()
+    print(f"Collection '{config.COLLECTION}': {state}")
+
+    embed_and_upsert(chunks, batch=batch)
     print(f"Done. Qdrant '{config.COLLECTION}' now holds {qdrant_io.count()} points.")