fix: 回填脚本改为定向回填多源 point(本地模式全量不可行)

- 本地模式 Qdrant 写入逐点 0.4~0.65s,全量 3.3 万条需 4~6h 且占单进程锁
- 改为仅回填指纹库 227 条多源记录(单源点展示层兜底 source_id):1m57s 完成
- 测试改为 _load_multi_source 语义(NULL/损坏/单源排除)

tests/test_multisource.py

@@ -166,7 +166,7 @@ def test_build_text_from_article_reads_sources(tmp_path: Path) -> None:
 
 
 # --------------------------------------------------------------------------- #
-# 回填脚本 _load_fingerprint_sources
+# 回填脚本 _load_multi_source
 # --------------------------------------------------------------------------- #
 
 def _make_fp_db(tmp_path: Path) -> Path:
@@ -183,23 +183,30 @@ def _make_fp_db(tmp_path: Path) -> Path:
     conn.execute(
         "INSERT INTO fingerprints VALUES (?, ?, ?)", ("h2", "zqrb", None)
     )
+    conn.execute(
+        "INSERT INTO fingerprints VALUES (?, ?, ?)", ("h3", "cls", "not-json")
+    )
+    conn.execute(
+        "INSERT INTO fingerprints VALUES (?, ?, ?)",
+        ("h4", "cls", json.dumps(["cls"])),
+    )
     conn.commit()
     conn.close()
     return db
 
 
-def test_load_fingerprint_sources_parses_and_falls_back(tmp_path: Path) -> None:
-    from scripts.backfill_qdrant_sources import _load_fingerprint_sources
+def test_load_multi_source_only_multi(tmp_path: Path) -> None:
+    """仅返回多源记录;NULL/损坏/单源均排除。"""
+    from scripts.backfill_qdrant_sources import _load_multi_source
 
     db = _make_fp_db(tmp_path)
-    res = _load_fingerprint_sources(db)
-    assert res["h1"] == ["cls", "sina"]
-    assert res["h2"] == ["zqrb"]  # source_ids NULL → 回退 [主源]
+    res = _load_multi_source(db)
+    assert res == {"h1": ["cls", "sina"]}
 
 
-def test_load_fingerprint_sources_main_first(tmp_path: Path) -> None:
+def test_load_multi_source_main_first(tmp_path: Path) -> None:
     """source_ids 顺序异常时保证主源居首。"""
-    from scripts.backfill_qdrant_sources import _load_fingerprint_sources
+    from scripts.backfill_qdrant_sources import _load_multi_source
 
     db = tmp_path / "fp.sqlite3"
     conn = sqlite3.connect(db)
@@ -213,5 +220,5 @@ def test_load_fingerprint_sources_main_first(tmp_path: Path) -> None:
     )
     conn.commit()
     conn.close()
-    res = _load_fingerprint_sources(db)
+    res = _load_multi_source(db)
     assert res["h1"] == ["cls", "sina"]