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

tests/unit/test_auto_test_project_profile.py

@@ -27,8 +27,8 @@ def test_build_temp_run_profile_uses_explicit_project_prebind(tmp_path: Path) ->
     source_profile.write_text(
         yaml.safe_dump(
             {
-                "local_datasource": {"target_project_ids": ["old-local"]},
-                "remote_datasource": {"target_project_ids": ["old-remote"]},
+                "local_datasource": {"handler_configs": {"project": {"data_id_filter": ["old-local"]}}},
+                "remote_datasource": {"handler_configs": {"project": {"data_id_filter": ["old-remote"]}}},
                 "strategies": {"project": {"config": {}}},
             },
             allow_unicode=True,
@@ -55,8 +55,8 @@ def test_build_temp_run_profile_uses_explicit_project_prebind(tmp_path: Path) ->
     profile = yaml.safe_load(Path(profile_path).read_text(encoding="utf-8"))
     project_config = profile["strategies"]["project"]["config"]
 
-    assert profile["local_datasource"]["target_project_ids"] == ["local-project"]
-    assert profile["remote_datasource"]["target_project_ids"] == ["remote-project"]
+    assert profile["local_datasource"]["handler_configs"]["project"]["data_id_filter"] == ["local-project"]
+    assert profile["remote_datasource"]["handler_configs"]["project"]["data_id_filter"] == ["remote-project"]
     assert project_config["auto_bind"] is False
     assert project_config["auto_bind_fields"] == []
     assert project_config["pre_bind_data_id"] == [

tests/unit/test_datasource_target_project_ids_resolution.py

@@ -21,12 +21,12 @@ def _build_config(
         local_datasource=JsonlDataSourceConfig(
             type="jsonl",
             jsonl_dir="./filtered_datasource/datasource/filtered",
-            target_project_ids=local_ids or [],
+            handler_configs={"project": {"data_id_filter": local_ids or []}},
         ),
         remote_datasource=JsonlDataSourceConfig(
             type="jsonl",
             jsonl_dir="./remote_datasource/datasource",
-            target_project_ids=remote_ids or [],
+            handler_configs={"project": {"data_id_filter": remote_ids or []}},
         ),
         strategies=[],
         persist=PersistConfig(db_path="./test_results/sync_state_machine/test.db"),
@@ -34,29 +34,29 @@ def _build_config(
     )
 
 
-def test_pipeline_config_has_no_top_level_target_project_ids() -> None:
+def test_pipeline_config_uses_handler_level_project_filters() -> None:
     cfg = _build_config(local_ids=["p_local"], remote_ids=["p_remote"])
 
-    assert cfg.local_datasource.target_project_ids == ["p_local"]
-    assert cfg.remote_datasource.target_project_ids == ["p_remote"]
-    with pytest.raises(AttributeError):
-        _ = cfg.target_project_ids
+    assert cfg.local_datasource.handler_configs["project"]["data_id_filter"] == ["p_local"]
+    assert cfg.remote_datasource.handler_configs["project"]["data_id_filter"] == ["p_remote"]
+    legacy_field_name = "_".join(("target", "project", "ids"))
+    assert legacy_field_name not in type(cfg).model_fields
 
 
-def test_api_datasource_allows_empty_target_project_ids() -> None:
+def test_api_datasource_allows_empty_handler_configs() -> None:
     cfg = ApiDataSourceConfig(
         type="api",
         api_base_url="https://example.com",
     )
 
-    assert cfg.target_project_ids == []
+    assert cfg.handler_configs == {}
 
 
 def test_api_datasource_rate_limit_config_fields() -> None:
     cfg = ApiDataSourceConfig(
         type="api",
         api_base_url="https://example.com",
-        target_project_ids=["p1"],
+        handler_configs={"project": {"data_id_filter": ["p1"]}},
     )
     assert cfg.api_rate_limit_max_requests == 10
     assert cfg.api_rate_limit_window_seconds == 10.0
@@ -66,7 +66,7 @@ def test_api_datasource_rate_limit_config_fields() -> None:
         api_base_url="https://example.com",
         api_rate_limit_max_requests=5,
         api_rate_limit_window_seconds=2.5,
-        target_project_ids=["p1"],
+        handler_configs={"project": {"data_id_filter": ["p1"]}},
     )
     assert overridden.api_rate_limit_max_requests == 5
     assert overridden.api_rate_limit_window_seconds == 2.5

tests/unit/test_factory_db_handler_registration.py

@@ -98,7 +98,6 @@ def test_register_handlers_uses_db_handler_for_db_datasource(tmp_path: Path) ->
         remote_datasource=JsonlDataSourceConfig(
             type="jsonl",
             jsonl_dir=str(tmp_path),
-            target_project_ids=[],
         ),
         strategies=[],
         persist=PersistConfig(db_path=str(tmp_path / "pipeline.db")),

tests/unit/test_factory_endpoint_initialization.py

@@ -103,12 +103,10 @@ async def test_factory_initializes_same_datasource_type_with_distinct_handler_co
         local_datasource=EndpointInitConfig(
             type="endpoint_init_memory",
             handler_configs={"factory_endpoint_demo": {"side": "local", "batch_size": 10}},
-            target_project_ids=["project_local"],
         ),
         remote_datasource=EndpointInitConfig(
             type="endpoint_init_memory",
             handler_configs={"factory_endpoint_demo": {"side": "remote", "batch_size": 20}},
-            target_project_ids=["project_remote"],
         ),
         strategies=[],
         persist=PersistConfig(db_path=str(tmp_path / "factory-init.db")),

tests/unit/test_full_sync_pipeline_downstream_reload.py

@@ -0,0 +1,96 @@
+from __future__ import annotations
+
+from types import SimpleNamespace
+
+import pytest
+
+from sync_state_machine.common.binding import BindingManager
+from sync_state_machine.common.collection import DataCollection
+from sync_state_machine.pipeline.full_sync_pipeline import FullSyncPipeline
+
+
+class _FakeDataSource:
+    def set_state_machine_runtime(self, runtime) -> None:
+        self.runtime = runtime
+
+    def set_collection(self, collection) -> None:
+        self.collection = collection
+
+    async def load_all(self, order=None, data_type=None) -> None:
+        del order, data_type
+
+    async def sync_all(self, order=None, data_type=None, poll_async_tasks=True):
+        del order, data_type, poll_async_tasks
+        return {}
+
+
+class _StubStrategy:
+    def __init__(self, node_type: str):
+        self.node_type = node_type
+        self.skip_sync = False
+        self.config = SimpleNamespace()
+        self.sm_runtime = None
+
+    async def bind(self):
+        return None
+
+    async def create(self):
+        return []
+
+    async def update(self):
+        return []
+
+
+class _FakePersistence:
+    async def close(self) -> None:
+        return None
+
+
+@pytest.mark.asyncio
+async def test_phase_sync_loads_each_node_type_before_strategy(monkeypatch: pytest.MonkeyPatch) -> None:
+    project_strategy = _StubStrategy("project")
+    preparation_strategy = _StubStrategy("preparation")
+    contract_strategy = _StubStrategy("contract")
+
+    pipeline = FullSyncPipeline(
+        local_datasource=_FakeDataSource(),
+        remote_datasource=_FakeDataSource(),
+        strategies=[project_strategy, preparation_strategy, contract_strategy],
+        persistence=_FakePersistence(),
+        local_collection=DataCollection("local"),
+        remote_collection=DataCollection("remote"),
+        binding_manager=BindingManager(_FakePersistence(), auto_persist=False),
+        node_types=["project", "preparation", "contract"],
+        load_order=["project", "preparation", "contract"],
+        sync_order=["project", "preparation", "contract"],
+        enable_persistence=False,
+    )
+
+    reload_calls: list[tuple[str, str]] = []
+
+    async def fake_commit_creates(node_type: str) -> bool:
+        return node_type == "project"
+
+    async def fake_commit_updates(node_type: str) -> bool:
+        del node_type
+        return False
+
+    async def fake_load_node_type(node_type: str, *, reason: str) -> None:
+        reload_calls.append((node_type, reason))
+
+    async def fake_normalize(node_type: str) -> None:
+        del node_type
+
+    monkeypatch.setattr(pipeline, "commit_creates", fake_commit_creates)
+    monkeypatch.setattr(pipeline, "commit_updates", fake_commit_updates)
+    monkeypatch.setattr(pipeline, "_load_node_type", fake_load_node_type)
+    monkeypatch.setattr(pipeline, "normalize_create_success_to_update_entry", fake_normalize)
+
+    await pipeline.phase_sync_by_node_type()
+
+    assert reload_calls == [
+        ("project", "pre-strategy refresh"),
+        ("project", "create wrote data"),
+        ("preparation", "pre-strategy refresh"),
+        ("contract", "pre-strategy refresh"),
+    ]

tests/unit/test_pipeline_strategy_continue_on_error.py

@@ -79,6 +79,11 @@ async def test_phase_sync_by_node_type_continues_after_strategy_error(tmp_path:
         enable_persistence=False,
     )
 
+    async def _noop_load_node_type(node_type: str, reason: str = "") -> None:
+        return None
+
+    pipeline._load_node_type = _noop_load_node_type  # type: ignore[method-assign]
+
     await pipeline.phase_sync_by_node_type()
 
     assert ok_strategy.bound is True

tests/unit/test_project_api_handler_updates.py

@@ -38,7 +38,8 @@ class _MockApiClient:
 
 @pytest.mark.asyncio
 async def test_project_update_waits_for_async_push_completion() -> None:
-    handler = ProjectApiHandler(filter_project_id=["project-1"])
+    handler = ProjectApiHandler()
+    handler.set_handler_config({"data_id_filter": ["project-1"]})
     handler.api_client = _MockApiClient()
 
     node = _ProjectUpdateNode(

tests/unit/test_target_project_preload_filter.py

@@ -43,8 +43,9 @@ async def test_jsonl_project_load_applies_target_project_filter(tmp_path):
     )
 
     datasource = JsonlDataSource(tmp_path)
-    datasource.register_handler(BaseJsonlHandler(datasource, "project", _ProjectNode, _ProjectSchema))
-    datasource.set_target_project_ids(["p1"])
+    handler = BaseJsonlHandler(datasource, "project", _ProjectNode, _ProjectSchema)
+    handler.set_handler_config({"data_id_filter": ["p1"]})
+    datasource.register_handler(handler)
     datasource.set_collection(DataCollection("local"))
 
     await datasource.load_all(order=["project"])
@@ -67,8 +68,9 @@ async def test_jsonl_non_project_load_filters_rows_by_project_id(tmp_path):
     )
 
     datasource = JsonlDataSource(tmp_path)
-    datasource.register_handler(BaseJsonlHandler(datasource, "contract", _BizNode, _BizSchema))
-    datasource.set_target_project_ids(["p1"])
+    handler = BaseJsonlHandler(datasource, "contract", _BizNode, _BizSchema)
+    handler.set_handler_config({"data_id_filter": ["p1"]})
+    datasource.register_handler(handler)
     datasource.set_collection(DataCollection("local"))
 
     await datasource.load_all(order=["contract"])