feat: 打通多源新闻记录链路,检索/日报/知识库可见多源 (方案A+B)

- 模型层: EmbeddingResult/SearchResult 新增 sources 字段(主源居首,旧产物兜底)
- M5 run_embedding: events/deduped 产物透传 sources 进 EmbeddingResult
- M6 run_qdrant_ingest: payload 写入 sources(M5 → 回查 M4 → 兜底 [主源])
- vectorstore: 检索读取 payload.sources
- 日报 HTML / CLI search / MCP: 多源显示「财联社 / 新浪 [多源]」
- 新增 scripts/backfill_qdrant_sources.py: 指纹库为权威源,scroll+upsert 回填存量
  (本地模式 set_payload 逐点 0.65s 不可行,改走 ingest 同款快速路径)
- 新增 tests/test_multisource.py 10 个;全量 276 passed

vectorstore/models.py

@@ -31,6 +31,10 @@ class SearchResult(BaseModel):
     title: str
     url: str
     source_id: str
+    sources: list[str] = Field(
+        default_factory=list,
+        description="全部来源(主源居首),来自 M3 去重多源记录;旧数据可能为空",
+    )
     publish_time: datetime | None = None
     event: dict[str, Any] | None = None   # EventExtraction 展开的 dict
     char_count: int | None = None