优化加载后删除节点的逻辑；和数据库查询性能

sync_state_machine/common/collection.py

@@ -488,6 +488,7 @@ class DataCollection:
                     context=context_value,
                 )
                 node.context["_loaded_from_persistence"] = True
+                node.append_log("加载来源: persistence 恢复节点")
             except Exception:
                 import logging
                 logger = logging.getLogger(__name__)
@@ -623,6 +624,7 @@ class DataCollection:
                 context=context_value,
             )
             node.context["_loaded_from_persistence"] = True
+            node.append_log("加载来源: persistence 恢复节点")
             self._nodes[node.node_id] = node
 
             if node.data_id and node.data_id != "":

sync_state_machine/common/persistence_backends/sqlite_backend.py

@@ -112,6 +112,9 @@ class SQLitePersistenceBackend(PersistenceBackend):
         await self.conn.execute(
             "CREATE INDEX IF NOT EXISTS idx_nodes_collection_scope_data_id ON nodes (collection_id, scope, data_id)"
         )
+        await self.conn.execute(
+            "CREATE INDEX IF NOT EXISTS idx_nodes_scope_type_node_id ON nodes (scope, node_type, node_id)"
+        )
 
     async def _ensure_bindings_schema(self) -> None:
         assert self.conn is not None

sync_state_machine/config/node_state_machine.yaml

@@ -17,6 +17,7 @@ meta:
 # represented as separate invocations with different inputs.
 context:
   is_create_zombie: { type: bool, desc: "初始化时判定为 CREATE 僵尸：action=CREATE 且 (status=FAILED 或 data_id 为空)" }
+  bootstrap_source_present: { type: bool, desc: "bootstrap 阶段 datasource 刷新后，当前节点是否在最新数据源中命中" }
 
   has_binding_record: { type: bool, desc: "binding_manager 里存在绑定记录 (remote_id/local_id 非空)" }
   core_binding_result: { type: enum, values: [NORMAL, WARNING, ABNORMAL], desc: "SyncDecisionEngine.determine_core_status() 给本节点的结果（仅在 has_binding_record=true 时有效）" }
@@ -304,19 +305,30 @@ states:
       status: SKIPPED
       data_id_exist: true
 
+  S17:
+    binding_status: ABNORMAL
+    action: NONE
+    status: FAILED
+    data_id_exist: [false, true]
+    desc: |
+      bootstrap 加载异常隔离态
+      持久化恢复后存在绑定，但 datasource 刷新未命中最新数据
+      binding_status: ABNORMAL
+      action: NONE
+      status: FAILED
+      data_id_exist: false | true
+
 pseudo_states:
   S15:
     desc: "节点被清理删除（zombie cleanup）"
   S16:
     desc: "持久化加载输入态：本轮 E01 的输入节点集合（可包含上轮遗留与已稳定节点）"
-  S17:
-    desc: "加载异常隔离态：持久化枚举非法，保留错误供人工处理，不进入自动流程"
 
 stages:
   bootstrap:
-    desc: "启动/初始化（仅针对持久化加载出的节点）：僵尸清理与归并到 S00"
+    desc: "启动/初始化：持久化恢复后先做 datasource 刷新，再按 E01 清理僵尸或归并/隔离"
     entry_states: [S16]
-    exit_states: [S00, S15]
+    exit_states: [S00, S15, S17]
 
   bind:
     desc: "绑定判定：core matrix +（可选）依赖检查 +（可选）自动绑定；stage 仅约束边界，不要求内部顺序"
@@ -346,13 +358,23 @@ stages:
 transitions:
   E01:
     stage: bootstrap
-    desc: "初始化：删CREATE僵尸；其余重置后进入起点"
+    desc: "初始化：先依据 datasource 刷新结果判定 source 是否存在，再做僵尸清理/隔离/归并"
     from: [S16]
     outcomes:
       - when: { is_create_zombie: true }
         to: S15
-      - when: { is_create_zombie: false }
+      - when: { is_create_zombie: false, bootstrap_source_present: false, has_binding_record: false }
+        to: S15
+        emit:
+          note: "持久化孤儿节点未命中最新数据源，按僵尸清理"
+      - when: { is_create_zombie: false, bootstrap_source_present: false, has_binding_record: true }
+        to: S17
+        emit:
+          note: "存在绑定但最新数据源未返回节点，进入加载异常隔离"
+      - when: { is_create_zombie: false, bootstrap_source_present: true }
         to: S00
+        emit:
+          note: "bootstrap 已刷新到最新数据，归并到起点"
 
   # --- Bind phase1 core ---
   E10:

sync_state_machine/domain/construction/api_handler.py

@@ -101,7 +101,7 @@ class ConstructionTaskApiHandler(BaseApiHandler):
                 else:
                     results.append(TaskResult.in_progress(node_id=node.node_id, task_id=push_id))
             except Exception as e:
-                results.append(TaskResult.failed(node_id=node.node_id, error=str(e)))
+                results.append(TaskResult.failed(node_id=node.node_id, error=str(e), push_id=push_id))
         
         return results
     
@@ -135,6 +135,7 @@ class ConstructionTaskApiHandler(BaseApiHandler):
             
             node_updated = False
             error = None
+            push_failure_id = None
             schema_status_lines: List[str] = []
             
             # 1. 基础信息更新 (ConstructionUpdate)
@@ -186,6 +187,7 @@ class ConstructionTaskApiHandler(BaseApiHandler):
                     except Exception as e:
                         error = str(e)
                         base_update_error = str(e)
+                        push_failure_id = push_id
                 else:
                     base_update_error = "show_name changed but task_type != QT"
 
@@ -236,6 +238,7 @@ class ConstructionTaskApiHandler(BaseApiHandler):
                     except Exception as e:
                         error = str(e)
                         plan_update_error = str(e)
+                        push_failure_id = push_id
 
             schema_status_lines.append(
                 self.build_update_schema_status(
@@ -253,7 +256,7 @@ class ConstructionTaskApiHandler(BaseApiHandler):
             
             # 汇总结果
             if error:
-                results.append(TaskResult.failed(node_id=node.node_id, error=error))
+                results.append(TaskResult.failed(node_id=node.node_id, error=error, push_id=push_failure_id))
             elif node_updated:
                 results.append(TaskResult.success(node_id=node.node_id))
             else:
@@ -279,7 +282,7 @@ class ConstructionTaskApiHandler(BaseApiHandler):
                 await api_delete_construction_task(self.api_client, biz_id, push_id)
                 results.append(TaskResult.success(node_id=node.node_id))
             except Exception as e:
-                results.append(TaskResult.failed(node_id=node.node_id, error=str(e)))
+                results.append(TaskResult.failed(node_id=node.node_id, error=str(e), push_id=push_id))
         
         return results
     

sync_state_machine/domain/construction_task_detail/api_handler.py

@@ -130,7 +130,7 @@ class ConstructionTaskDetailApiHandler(BaseApiHandler):
                 else:
                     results.append(TaskResult.in_progress(node_id=node.node_id, task_id=push_id))
             except Exception as e:
-                results.append(TaskResult.failed(node_id=node.node_id, error=str(e)))
+                results.append(TaskResult.failed(node_id=node.node_id, error=str(e), push_id=push_id))
         
         return results
     
@@ -222,7 +222,7 @@ class ConstructionTaskDetailApiHandler(BaseApiHandler):
                 # 整组失败
                 error_msg = str(e)
                 for node, _ in group_items:
-                    results.append(TaskResult.failed(node_id=node.node_id, error=error_msg))
+                    results.append(TaskResult.failed(node_id=node.node_id, error=error_msg, push_id=push_id))
         
         return results
     
@@ -240,7 +240,7 @@ class ConstructionTaskDetailApiHandler(BaseApiHandler):
                 await api_delete_construction_task_detail(self.api_client, biz_id, push_id)
                 results.append(TaskResult.success(node_id=node.node_id))
             except Exception as e:
-                results.append(TaskResult.failed(node_id=node.node_id, error=str(e)))
+                results.append(TaskResult.failed(node_id=node.node_id, error=str(e), push_id=push_id))
         
         return results
     

sync_state_machine/engine/events.py

@@ -276,8 +276,14 @@ def e01_bootstrap(
     *,
     node: "SyncNode",
     is_create_zombie: bool,
+    bootstrap_source_present: bool = True,
+    has_binding_record: bool = False,
 ) -> Decision:
-    context = {"is_create_zombie": is_create_zombie}
+    context = {
+        "is_create_zombie": is_create_zombie,
+        "bootstrap_source_present": bootstrap_source_present,
+        "has_binding_record": has_binding_record,
+    }
     decision = _dispatch_required(
         runtime,
         node=node,
@@ -289,6 +295,15 @@ def e01_bootstrap(
         _apply_decision(runtime, node=node, decision=decision, fields={"binding_status", "action", "status"})
         node.error = None
         return decision
+    if decision.to_state == "S17":
+        _apply_decision(runtime, node=node, decision=decision, fields={"binding_status", "action", "status"})
+        reason_text = decision_note(decision) or "<no-reason>"
+        node.context["bootstrap_blocked"] = True
+        node.context["bootstrap_block_reason"] = "source_missing_after_persistence_refresh"
+        node.context["bootstrap_block_errors"] = [reason_text]
+        node.context["bootstrap_source_present"] = False
+        node.error = f"BOOTSTRAP_SOURCE_MISSING: {reason_text}"
+        return decision
     if decision.to_state == "S15":
         reason_text = decision_note(decision) or "<no-reason>"
         node.append_log(

sync_state_machine/pipeline/full_sync_pipeline.py

@@ -256,6 +256,12 @@ class FullSyncPipeline:
         self._prepare_datasources()
         self._logger.info("✅ Bootstrap: datasource prepared")
 
+        await self._bootstrap_refresh_latest_data()
+        self._logger.info("✅ Bootstrap: datasource refresh completed")
+
+        await self._run_bootstrap_reset_cleanup()
+        self._logger.info("✅ Bootstrap: reset cleanup completed")
+
         await self._apply_project_scope_cleanup()
 
     async def phase_bind(self) -> None:
@@ -359,7 +365,7 @@ class FullSyncPipeline:
         await _safe_close("persistence", self.persistence.close())
 
     async def _load_persistence_state(self) -> None:
-        """加载持久化数据并清理僵尸节点"""
+        """加载持久化数据到内存，等待 bootstrap datasource refresh 与 E01 cleanup。"""
         if not self.enable_persistence:
             return
 
@@ -376,10 +382,50 @@ class FullSyncPipeline:
         for node_type in binding_node_types:
             await self.binding_manager.load_from_persistence(node_type)
         self._logger.info("🔄 Persistence loaded (state preserved; pending E01 normalization)")
-        
-        # 加载后 reset 清理：清理 CREATE 失败的僵尸绑定
+
+    def _resolve_bootstrap_refresh_node_types(self) -> List[str]:
+        local_types = {node.node_type for node in self.local_collection.filter()}
+        remote_types = {node.node_type for node in self.remote_collection.filter()}
+        candidate_types = local_types | remote_types
+        if not candidate_types:
+            return []
+
+        ordered: List[str] = []
+        for node_type in [*self.load_order, *self.bootstrap_binding_node_types, *sorted(candidate_types)]:
+            if node_type in candidate_types and node_type not in ordered:
+                ordered.append(node_type)
+        return ordered
+
+    async def _bootstrap_refresh_latest_data(self) -> None:
+        if not self.enable_persistence:
+            return
+
+        node_types = self._resolve_bootstrap_refresh_node_types()
+        if not node_types:
+            self._logger.info("⏭️  Bootstrap datasource refresh skipped: no persisted node types")
+            return
+
+        for node_type in node_types:
+            self._logger.info("🔄 Bootstrap refresh node_type=%s from datasource", node_type)
+            await self._load_node_type_from_datasource(
+                self.local_datasource,
+                datasource_role="local",
+                node_type=node_type,
+                reason="bootstrap persistence refresh",
+            )
+            await self._load_node_type_from_datasource(
+                self.remote_datasource,
+                datasource_role="remote",
+                node_type=node_type,
+                reason="bootstrap persistence refresh",
+            )
+
+    async def _run_bootstrap_reset_cleanup(self) -> None:
+        if not self.enable_persistence:
+            return
         if not self.strategies:
             raise RuntimeError("no strategies configured: cannot run bootstrap event E01")
+
         total_cleaned = await run_phase2_cleanup(
             node_types=self.node_types,
             local_collection=self.local_collection,
@@ -388,8 +434,7 @@ class FullSyncPipeline:
             runtime=self.sm_runtime,
         )
         if total_cleaned > 0:
-            self._logger.info(f"🧹 Reset cleanup: {total_cleaned} CREATE-failed zombies cleaned")
-        self._logger.info("🔄 Post-load reset cleanup completed")
+            self._logger.info(f"🧹 Reset cleanup: {total_cleaned} bootstrap zombies cleaned")
 
     async def _apply_preloaded_state(self) -> None:
         if self._preloaded_local_nodes:

sync_state_machine/sync_system/strategy_ops/reset_ops.py

@@ -30,6 +30,25 @@ async def _resolve_local_id_for_unbind(
     return None
 
 
+async def _has_binding_record(
+    *,
+    node_type: str,
+    any_side_node_id: str,
+    binding_manager: "BindingManager",
+) -> bool:
+    local_id = await _resolve_local_id_for_unbind(
+        node_type=node_type,
+        any_side_node_id=any_side_node_id,
+        binding_manager=binding_manager,
+    )
+    return local_id is not None
+
+
+def _bootstrap_source_present(node) -> bool:
+    context = node.context if isinstance(node.context, dict) else {}
+    return not bool(context.get("_loaded_from_persistence"))
+
+
 def _is_create_zombie(node) -> bool:
     if node.action != SyncAction.CREATE:
         return False
@@ -55,8 +74,27 @@ async def _cleanup_one_side(
             )
             continue
 
-        decision = e01_bootstrap(runtime, node=node, is_create_zombie=_is_create_zombie(node))
+        has_binding_record = await _has_binding_record(
+            node_type=node_type,
+            any_side_node_id=node.node_id,
+            binding_manager=binding_manager,
+        )
+        bootstrap_source_present = _bootstrap_source_present(node)
+
+        decision = e01_bootstrap(
+            runtime,
+            node=node,
+            is_create_zombie=_is_create_zombie(node),
+            bootstrap_source_present=bootstrap_source_present,
+            has_binding_record=has_binding_record,
+        )
         if decision.to_state != "S15":
+            if decision.to_state == "S17":
+                node.context.pop("_loaded_from_persistence", None)
+                logger.warning(
+                    f"[{node_type}] Bootstrap isolated node ({label}): "
+                    f"node_id={node.node_id}, reason={node.error}"
+                )
             continue
 
         local_id_for_unbind = await _resolve_local_id_for_unbind(
@@ -74,9 +112,12 @@ async def _cleanup_one_side(
         else:
             bind_note = "no_binding"
 
-        reason = "status=FAILED" if node.status == SyncStatus.FAILED else "data_id empty"
+        if _is_create_zombie(node):
+            reason = "status=FAILED" if node.status == SyncStatus.FAILED else "data_id empty"
+        else:
+            reason = "persistence_only_source_missing_without_binding"
         logger.info(
-            f"[{node_type}] Cleaning up CREATE zombie ({label}): "
+            f"[{node_type}] Cleaning up bootstrap zombie ({label}): "
             f"node_id={node.node_id}, reason={reason}, {bind_note}"
         )
 
@@ -118,7 +159,7 @@ async def run_phase2_cleanup(
         total_cleaned += cleaned_count
         if cleaned_count > 0:
             logger.warning(
-                f"[{node_type}] Cleaned up CREATE-failed zombies: "
+                f"[{node_type}] Cleaned up bootstrap zombies: "
                 f"local_deleted={len(cleaned_local)}, remote_deleted={len(cleaned_remote)}"
             )