实现了多project pipeline

sync_state_machine/datasource/datasource.py

@@ -482,7 +482,7 @@ class BaseDataSource(ABC):
                 # Handler 加载数据并创建节点
                 nodes = await handler.load()
 
-                logger.info("%s Loaded nodes for %s: %d", self._datasource_log_prefix(), node_type, len(nodes))
+                logger.debug("%s Loaded nodes for %s: %d", self._datasource_log_prefix(), node_type, len(nodes))
 
                 # 将节点写入 Collection：优先按 data_id 命中已有节点并更新
                 await self._upsert_loaded_nodes(handler, node_type, nodes)
@@ -641,7 +641,7 @@ class BaseDataSource(ABC):
 
         # 批量创建（传入节点列表）
         if create_nodes:
-            logger.info(f"{self._node_log_prefix(handler.node_type)} create提交开始: nodes={len(create_nodes)}")
+            logger.debug(f"{self._node_log_prefix(handler.node_type)} create提交开始: nodes={len(create_nodes)}")
             try:
                 create_results = await handler.create_all(create_nodes)
                 create_success = 0
@@ -658,7 +658,7 @@ class BaseDataSource(ABC):
                     elif result.status == _TaskStatus.SKIPPED:
                         create_skipped += 1
                     await self._handle_task_result(handler, result, async_tasks)
-                logger.info(
+                logger.debug(
                     f"{self._node_log_prefix(handler.node_type)} create提交完成: success={create_success}, "
                     f"in_progress={create_in_progress}, failed={create_failed}, skipped={create_skipped}"
                 )
@@ -694,7 +694,7 @@ class BaseDataSource(ABC):
         
         # 轮询异步任务
         if async_tasks and poll_async_tasks:
-            logger.info(
+            logger.debug(
                 f"{self._node_log_prefix(handler.node_type)} create已提交，push_id检查即将开始: pending={len(async_tasks)}, "
                 f"first_wait={self._poll_interval:.3f}s"
             )
@@ -845,13 +845,13 @@ class BaseDataSource(ABC):
             return
 
         if async_tasks and poll_interval > 0:
-            logger.info(
+            logger.debug(
                 f"{self._node_log_prefix(handler.node_type)} push_id首次检查前等待 {poll_interval:.3f}s, pending={len(async_tasks)}"
             )
             await asyncio.sleep(poll_interval)
         
         while async_tasks and retry_count < max_retries:
-            logger.info(
+            logger.debug(
                 f"{self._node_log_prefix(handler.node_type)} push_id检查 {retry_count + 1}/{max_retries}, pending={len(async_tasks)}"
             )
             # 批量查询

sync_state_machine/pipeline/factory.py

@@ -500,11 +500,18 @@ async def run_pipeline_from_config(
     from .multi_project_pipeline import is_implicit_project_batch_config, run_implicit_project_batch_from_config
 
     implicit_multi_project = is_implicit_project_batch_config(config)
-    if pipeline_type == "multi-project" and not implicit_multi_project:
-        raise ValueError("pipeline_type=multi-project requires an implicit multi-project pipeline config")
     if pipeline_type == "full" and implicit_multi_project:
         logger.info("pipeline_type=full specified, skipping implicit multi-project routing")
 
+    if pipeline_type == "multi-project":
+        _log_resolved_config(config)
+        return await run_implicit_project_batch_from_config(
+            config,
+            title=title,
+            print_summary=print_summary,
+            max_concurrency=getattr(config, "max_concurrency", None),
+        )
+
     if pipeline_type != "full" and implicit_multi_project:
         _log_resolved_config(config)
         return await run_implicit_project_batch_from_config(

sync_state_machine/pipeline/full_sync_pipeline.py

@@ -511,7 +511,7 @@ class FullSyncPipeline:
             )
 
     async def _load_node_type(self, node_type: str, *, reason: str) -> None:
-        self._logger.info(f"🔄 Load node_type={node_type}, reason={reason}")
+        self._logger.debug(f"🔄 Load node_type={node_type}, reason={reason}")
         await self._load_node_type_from_datasource(
             self.local_datasource,
             datasource_role="local",
@@ -576,7 +576,7 @@ class FullSyncPipeline:
             self._log_reload_skipped(node_type, reason)
             return
 
-        self._logger.info(
+        self._logger.debug(
             "🔄 Reload node_type=%s after write, reason=%s, local=%s, remote=%s",
             node_type,
             reason,
@@ -667,7 +667,7 @@ class FullSyncPipeline:
         )
 
         if finalized_success or finalized_failed:
-            self._logger.info(
+            self._logger.debug(
                 f"🔁 Peer-creating finalize: node_type={node_type}, success={finalized_success}, failed={finalized_failed}"
             )
 
@@ -690,7 +690,7 @@ class FullSyncPipeline:
                 normalized += 1
 
         if normalized > 0:
-            self._logger.info(f"🔁 Post-create normalization: {normalized} nodes moved S11C->S01 for {node_type}")
+            self._logger.debug(f"🔁 Post-create normalization: {normalized} nodes moved S11C->S01 for {node_type}")
     
     async def commit_updates(self, node_type: str) -> WriteOutcome:
         """提交 UPDATE 操作（包含异步轮询）"""

tests/unit/test_datasource_load_continue_on_error.py

@@ -106,8 +106,8 @@ async def test_load_all_continue_when_one_handler_fails(caplog) -> None:
     with caplog.at_level(logging.INFO):
         await ds.load_all(order=["fail", "ok"])
 
-    assert "[fail] 加载失败" in caplog.text
-    assert "Loaded nodes for ok: 0" in caplog.text
+    assert "[fail] ❌ 加载失败: boom" in caplog.text
+    assert "Loaded nodes for ok: 0" not in caplog.text
 
 
 @pytest.mark.asyncio

tests/unit/test_multi_project_pipeline_config.py

@@ -366,5 +366,52 @@ async def test_run_pipeline_from_config_can_require_multi_project(monkeypatch: p
         strategies=[],
     )
 
-    with pytest.raises(ValueError, match="pipeline_type=multi-project"):
-        await run_pipeline_from_config(config, print_summary=False, pipeline_type="multi-project")
+    with pytest.raises(ValueError, match="pre_bind_data_id"):
+        await run_pipeline_from_config(config, print_summary=False, pipeline_type="multi-project")
+
+
+@pytest.mark.asyncio
+async def test_run_pipeline_from_config_can_force_multi_project_for_single_project(monkeypatch: pytest.MonkeyPatch) -> None:
+    config = PipelineRunConfig(
+        node_types=["supplier", "company", "project", "contract"],
+        local_datasource=JsonlDataSourceConfig(
+            type="jsonl",
+            jsonl_dir="./local",
+            handler_configs={"project": {"data_id_filter": ["p1"]}},
+        ),
+        remote_datasource=JsonlDataSourceConfig(
+            type="jsonl",
+            jsonl_dir="./remote",
+            handler_configs={"project": {"data_id_filter": ["r1"]}},
+        ),
+        persist=PersistConfig(backend="sqlite", db_path=":memory:"),
+        logging=LoggingConfig(),
+        strategies=[
+            StrategyRuntimeConfig(
+                node_type="project",
+                config=StrategyConfig(
+                    auto_bind=False,
+                    pre_bind_data_id=[
+                        {"local_data_id": "p1", "remote_data_id": "r1"},
+                    ],
+                ),
+            )
+        ],
+    )
+
+    captured: dict[str, object] = {}
+
+    async def fake_run_implicit_project_batch_from_config(*args, **kwargs):
+        captured["title"] = kwargs.get("title")
+        captured["print_summary"] = kwargs.get("print_summary")
+        return {"mode": "multi-project", "projects": 1}
+
+    monkeypatch.setattr(
+        "sync_state_machine.pipeline.multi_project_pipeline.run_implicit_project_batch_from_config",
+        fake_run_implicit_project_batch_from_config,
+    )
+
+    result = await run_pipeline_from_config(config, print_summary=False, pipeline_type="multi-project")
+
+    assert result == {"mode": "multi-project", "projects": 1}
+    assert captured["print_summary"] is False