调整了pipeline执行顺序。现在按domain顺序读取数据源数据，防止前面domain的更新影响后面domain.

将target_project_ids替换为更通用的data_id_filter
2026-03-20 14:38:56 +08:00
parent f9f175ee79
commit 2c09c61165
29 changed files with 296 additions and 172 deletions
@@ -514,9 +514,9 @@ class DataCollection:

        await self.persistence.save_nodes_bulk(self.collection_id, list(self._nodes.values()))

-    async def filter_by_project_ids(self, target_project_ids: List[str]) -> int:
-        """按目标项目集合过滤当前 collection，返回删除数量。"""
-        target_set = set(target_project_ids or [])
+    async def filter_by_project_ids(self, data_id_filter: List[str]) -> int:
+        """按目标项目 data_id 集合过滤当前 collection，返回删除数量。"""
+        target_set = set(data_id_filter or [])
        if not target_set:
            return 0