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

tests/test_llm.py

@@ -121,6 +121,31 @@ def test_event_types_constant_includes_common() -> None:
         assert must in EVENT_TYPES
 
 
+# --------------------------------------------------------------------------- #
+# ExtractedEvent.sources 多源字段
+# --------------------------------------------------------------------------- #
+
+def test_extracted_event_sources_defaults_to_main_source() -> None:
+    """未提供 sources 时兜底为 [source_id](兼容旧产物)。"""
+    ev = ExtractedEvent(
+        source_id="cls", url="https://x/1", url_hash="h1", title="t",
+        event=EventExtraction(sentiment="positive", importance=3, event_type="重大合同"),
+        provider="deepseek", model="m",
+    )
+    assert ev.sources == ["cls"]
+
+
+def test_extracted_event_sources_keeps_main_first_and_dedup() -> None:
+    """sources 保主源居首、去重保序。"""
+    ev = ExtractedEvent(
+        source_id="cls", url="https://x/1", url_hash="h1", title="t",
+        sources=["sina", "cls", "eastmoney", "sina"],
+        event=EventExtraction(sentiment="neutral", importance=2, event_type="其他"),
+        provider="deepseek", model="m",
+    )
+    assert ev.sources == ["cls", "sina", "eastmoney"]
+
+
 # --------------------------------------------------------------------------- #
 # JSON 提取与解析
 # --------------------------------------------------------------------------- #

tests/test_report_builder.py

@@ -255,3 +255,31 @@ class TestCollectNewsEventsLookback:
         assert "无时间戳" in titles
         assert "窗口外旧闻" not in titles
         assert "公告排除" not in titles
+
+
+class TestLoadEventsSources:
+    """_load_events_from_dir 读取多源(sources)字段。"""
+
+    def test_loads_sources_with_fallback(self, monkeypatch, tmp_path) -> None:
+        import json as _json
+
+        import scheduler.reporter as rep
+
+        ev_dir = tmp_path / "data" / "events" / "20260812"
+        ev_dir.mkdir(parents=True)
+        (ev_dir / "aaa.json").write_text(_json.dumps({
+            "source_id": "cls", "sources": ["cls", "sina", "eastmoney"],
+            "title": "多源新闻", "url": "https://x/1", "event": {},
+        }, ensure_ascii=False), encoding="utf-8")
+        (ev_dir / "bbb.json").write_text(_json.dumps({
+            "source_id": "cls", "title": "旧产物无 sources", "url": "https://x/2",
+            "event": {},
+        }, ensure_ascii=False), encoding="utf-8")
+
+        monkeypatch.chdir(tmp_path)
+        events = rep._load_events_from_dir("20260812")
+        by_url = {e["url"]: e for e in events}
+        # 新产物:多源完整透传
+        assert by_url["https://x/1"]["sources"] == ["cls", "sina", "eastmoney"]
+        # 旧产物:兜底 [source_id]
+        assert by_url["https://x/2"]["sources"] == ["cls"]

tests/test_report_db.py

@@ -20,9 +20,16 @@ class TestEventRow:
         ev = EventRow(
             section="intl", rank=2, importance=4, event_type="地缘政治",
             title="t", summary="s", sentiment="negative", source="ForexLive",
+            sources=["ForexLive", "新浪财经"],
             url="https://x.com/1",
         )
         assert ev.sentiment == "negative"
+        assert ev.sources == ["ForexLive", "新浪财经"]
+
+    def test_sources_optional(self) -> None:
+        """sources 为可选项(旧数据无多源记录)。"""
+        ev = EventRow(section="news", rank=1, title="t")
+        assert ev.sources is None
 
     def test_missing_title_raises(self) -> None:
         with pytest.raises(ValidationError):