MVP stage 3: media assets (video, atom_assets, publications, idempotent)

stage1/extract_to_postgres.py

@@ -188,9 +188,10 @@ def ensure_project(conn, project: str) -> str:
 
 
 def insert_atoms(conn, project_id: str, atoms: list[Atom]) -> int:
-    """Вставить атомы в atoms. Возвращает количество."""
+    """Вставить атомы в atoms. Дубли проекта — удалить перед вставкой. Возвращает количество."""
     n = 0
     with conn.cursor() as cur:
+        cur.execute("DELETE FROM atoms WHERE project_id = %s", (project_id,))
         for atom in atoms:
             row = atom.to_row()
             cur.execute("""
@@ -242,9 +243,13 @@ def generate_web_version(atom: Atom) -> str:
 # ---------------------------------------------------------------------------
 # Qdrant
 # ---------------------------------------------------------------------------
-def ensure_collection(client: QdrantClient) -> None:
-    if client.collection_exists(COLLECTION):
+def clear_collection(client: QdrantClient) -> None:
+    """Полностью очистить коллекцию Qdrant (идемпотентность stage 1)."""
+    import os
+    if os.environ.get("QDRANT_KEEP"):
         return
+    if client.collection_exists(COLLECTION):
+        client.delete_collection(collection_name=COLLECTION)
     client.create_collection(
         collection_name=COLLECTION,
         vectors_config=VectorParams(size=DIM, distance=Distance.COSINE),
@@ -305,7 +310,7 @@ def main():
     # 3. Qdrant (эмбеддинги + дедуп)
     start = time.time()
     client = QdrantClient(host="127.0.0.1", port=6333)
-    ensure_collection(client)
+    clear_collection(client)
     n_emb = upsert_qdrant(client, all_atoms)
     print(f"  ✓ Qdrant: {n_emb} эмбеддингов за {time.time()-start:.1f}с (~{ (time.time()-start)/n_emb*1000:.0f}ms/atom)")