feat: 日报事件多新闻源入库(news_event.sources 列)

- ExtractedEvent 增加 sources 字段(主源居首去重,旧产物兜底 [source_id])
- extract_event(_async) 增加 sources 参数;run_event_extraction 读取
  deduped uniques 的 sources 透传
- reporter _load_events_from_dir 读取 sources → EventRow.sources
- news_event 建表加 sources TEXT 列;init_schema 幂等迁移旧表(捕获
  Duplicate column);save_report INSERT 写 JSON 多源
- 新增测试:ExtractedEvent/EventRow.sources 兜底与保序、_load_events_from_dir 多源

scripts/run_event_extraction.py

@@ -109,6 +109,21 @@ def _load_article(p: Path) -> Article | None:
         return None
 
 
+def _load_sources(p: Path) -> list[str] | None:
+    """从输入 JSON 读取 sources 多源字段(deduped uniques 才有);无则返回 None。
+
+    None 表示无多源记录,由 extract_event 兜底为 [source_id]。
+    """
+    try:
+        data = json.loads(p.read_text(encoding="utf-8"))
+        srcs = data.get("sources")
+        if isinstance(srcs, list) and srcs:
+            return [s for s in srcs if s]
+    except (json.JSONDecodeError, OSError):
+        pass
+    return None
+
+
 async def _run(args: argparse.Namespace) -> int:
     load_dotenv()  # 读 .env 到 os.environ
     # scene=event_extraction: 读取 configs/llm_models.yaml 场景 1 配置,未配置字段回退 .env
@@ -173,6 +188,7 @@ async def _run(args: argparse.Namespace) -> int:
             article = _load_article(fp)
             if article is None:
                 return fp, None, "无法解析输入"
+            sources = _load_sources(fp)  # 多源记录(去重层),无则 None
             try:
                 event = await extract_event_async(
                     client=client,
@@ -180,6 +196,7 @@ async def _run(args: argparse.Namespace) -> int:
                     article=article,
                     template=template,
                     max_attempts=args.max_attempts,
+                    sources=sources,
                     semaphore=semaphore,
                 )
                 return fp, event, None