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

sync_state_machine/datasource/api/handler.py

@@ -69,9 +69,13 @@ class BaseApiHandler(NodeHandler[T]):
     def set_handler_config(self, config: Dict[str, Any]) -> None:
         self.handler_config = dict(config)
 
-    def set_target_project_ids(self, target_project_ids: List[str]) -> None:
-        """默认忽略项目过滤列表，具体子类按需覆盖。"""
-        return
+    def get_data_id_filter(self) -> List[str]:
+        value = self.handler_config.get("data_id_filter", [])
+        if isinstance(value, str):
+            return [value] if value else []
+        if isinstance(value, list):
+            return [str(item) for item in value if str(item)]
+        return []
     
     @property
     def node_type(self) -> str:

sync_state_machine/datasource/datasource.py

@@ -74,7 +74,6 @@ class BaseDataSource(ABC):
     def __init__(self, poll_max_retries: int = 1, poll_interval: float = 0.5):
         self._handlers: Dict[str, "NodeHandler"] = {}
         self._collection: Optional["DataCollection"] = None
-        self._target_project_ids: List[str] = []
         
         # 按节点类型统计信息
         # {"company": {"loaded": 10, "synced": 10, "success": 10, "failed": 0}, ...}
@@ -87,13 +86,6 @@ class BaseDataSource(ABC):
         self._poll_interval = max(0, poll_interval)
         self._sm_runtime: Optional[StateMachineRuntime] = None
 
-    def set_target_project_ids(self, target_project_ids: List[str]) -> None:
-        self._target_project_ids = [str(item) for item in target_project_ids if str(item)]
-
-    @property
-    def target_project_ids(self) -> List[str]:
-        return list(self._target_project_ids)
-
     def _ensure_sm_runtime(self) -> StateMachineRuntime:
         if self._sm_runtime is None:
             cfg_path = Path(__file__).resolve().parents[1] / "config" / "node_state_machine.yaml"
@@ -379,17 +371,6 @@ class BaseDataSource(ABC):
             datasource.register_handler(ContractNodeHandler(api_client))
         """
         self._handlers[handler.node_type] = handler
-        self._apply_target_project_ids_to_handler(handler)
-
-    def set_target_project_ids(self, target_project_ids: Optional[List[str]]) -> None:
-        """设置项目过滤列表，并在注册阶段下发给所有 handler。"""
-        normalized = [str(pid) for pid in (target_project_ids or []) if str(pid)]
-        self._target_project_ids = normalized
-        for handler in self._handlers.values():
-            self._apply_target_project_ids_to_handler(handler)
-
-    def _apply_target_project_ids_to_handler(self, handler: "NodeHandler") -> None:
-        handler.set_target_project_ids(self._target_project_ids)
     
     def get_handler(self, node_type: str) -> "NodeHandler":
         """获取 Handler"""

sync_state_machine/datasource/handler.py

@@ -74,10 +74,6 @@ class NodeHandler(Protocol[T]):
         """注入 handler 级别配置。默认可忽略。"""
         ...
 
-    def set_target_project_ids(self, target_project_ids: List[str]) -> None:
-        """注入项目过滤列表。默认可忽略。"""
-        ...
-
     def set_api_client(self, client: "ApiClient") -> None:
         """注入 API 客户端。默认可忽略。"""
         ...
@@ -360,14 +356,18 @@ class BaseNodeHandler(ABC, Generic[T]):
         """
         self._collection = collection
 
-    def set_target_project_ids(self, target_project_ids: List[str]) -> None:
-        """默认忽略项目过滤能力。"""
-        return
-
     def set_handler_config(self, config: Dict[str, Any]) -> None:
         """默认保存 handler 级别配置，供子类按需读取。"""
         self.handler_config = dict(config)
 
+    def get_data_id_filter(self) -> List[str]:
+        value = self.handler_config.get("data_id_filter", [])
+        if isinstance(value, str):
+            return [value] if value else []
+        if isinstance(value, list):
+            return [str(item) for item in value if str(item)]
+        return []
+
     def set_api_client(self, client: "ApiClient") -> None:
         """默认忽略 API 客户端注入。"""
         return
@@ -479,6 +479,59 @@ class BaseNodeHandler(ABC, Generic[T]):
         return self.create_node(data)
 
 
+class CompatibleNodeHandler(BaseNodeHandler[T]):
+    def __init__(self, handler: BaseNodeHandler[T]):
+        super().__init__(handler.node_type, handler.node_class, handler.schema)
+        self._handler = handler
+
+    def set_collection(self, collection: "DataCollection") -> None:
+        super().set_collection(collection)
+        self._handler.set_collection(collection)
+
+    def set_handler_config(self, config: Dict[str, Any]) -> None:
+        self._handler.set_handler_config(config)
+        self.handler_config = dict(self._handler.handler_config)
+
+    def set_api_client(self, client: "ApiClient") -> None:
+        self._handler.set_api_client(client)
+
+    def set_poll_mode(self, mode: str) -> None:
+        self._handler.set_poll_mode(mode)
+
+    def get_update_fields(self, *, exclude: frozenset[str] = frozenset({"id"})) -> List[str]:
+        return self._handler.get_update_fields(exclude=exclude)
+
+    async def load(self) -> List['SyncNode']:
+        return await self._handler.load()
+
+    async def create_all(
+        self,
+        nodes: List["SyncNode"]
+    ) -> List[TaskResult]:
+        return await self._handler.create_all(nodes)
+
+    async def update_all(
+        self,
+        nodes: List["SyncNode"]
+    ) -> List[TaskResult]:
+        return await self._handler.update_all(nodes)
+
+    async def delete_all(
+        self,
+        nodes: List["SyncNode"]
+    ) -> List[TaskResult]:
+        return await self._handler.delete_all(nodes)
+
+    async def poll_tasks(self, task_ids: List[str]) -> Dict[str, TaskResult]:
+        return await self._handler.poll_tasks(task_ids)
+
+    async def validate(self, data: Dict[str, Any]) -> ValidationResult:
+        return await self._handler.validate(data)
+
+    def extract_id(self, data: Dict[str, Any]) -> str:
+        return self._handler.extract_id(data)
+
+
 class NodeHandlerRegistry:
     """节点处理器注册表"""
     

sync_state_machine/datasource/jsonl/handler.py

@@ -50,22 +50,17 @@ class BaseJsonlHandler(BaseNodeHandler):
     ):
         super().__init__(node_type, node_class, schema)
         self.datasource = datasource
-        self._target_project_ids: List[str] = []
-
-    def set_target_project_ids(self, target_project_ids: List[str]) -> None:
-        """注入项目过滤列表的本地副本。真正的过滤来源仍然是 datasource。"""
-        self._target_project_ids = [str(pid) for pid in target_project_ids if str(pid)]
 
     def _should_skip_item_by_project_filter(self, item: Dict[str, Any], item_id: str) -> bool:
-        target_project_ids = set(self.datasource.target_project_ids)
-        if not target_project_ids:
+        data_id_filter = set(self.get_data_id_filter())
+        if not data_id_filter:
             return False
         if self.node_type == "project":
-            return item_id not in target_project_ids
+            return item_id not in data_id_filter
 
         project_id = item.get("project_id")
         if project_id:
-            return str(project_id) not in target_project_ids
+            return str(project_id) not in data_id_filter
         return False
     
     async def load(self) -> List['SyncNode']: