Release/v0.2.3 (#355)

* feat(web): add PageEmpty component * feat(web): add PageTabs component * feat(web): add PageEmpty component * feat(web): add PageTabs component * feat(prompt): add history tracking for prompt releases * feat(web): add prompt menu * refactor: The PageScrollList component supports two generic parameters * feat(web): BodyWrapper compoent update PageLoading * feat(web): add Ontology menu * feat(web): memory management add scene * feat(tasks): add celery task configuration for periodic jobs - Add ignore_result=True to prevent storing results for periodic tasks - Set max_retries=0 to skip failed periodic tasks without retry attempts - Configure acks_late=False for immediate acknowledgment in beat tasks - Add time_limit and soft_time_limit to regenerate_memory_cache task (3600s/3300s) - Add time_limit and soft_time_limit to workspace_reflection_task (300s/240s) - Add time_limit and soft_time_limit to run_forgetting_cycle_task (7200s/7000s) - Improve task reliability and resource management for scheduled jobs * feat(sandbox): add Node.js code execution support to sandbox * Release/v0.2.2 (#260) * [modify] migration script * [add] migration script * fix(web): change form message * fix(web): the memoryContent field is compatible with numbers and strings * feat(web): code node hidden * fix(model): 1. create a basic model to check if the name and provider are duplicated. 2. The result shows error models because the provider created API Keys for all matching models. --------- Co-authored-by: Mark <zhuwenhui5566@163.com> Co-authored-by: zhaoying <yzhao96@best-inc.com> Co-authored-by: yingzhao <zhaoyingyz@126.com> Co-authored-by: Timebomb2018 <18868801967@163.com> * Feature/ontology class clean (#249) * [add] Complete ontology engineering feature implementation * [add] Add ontology feature integration and validation utilities * [add] Add OWL validator and validation utilities * [fix] Add missing render_ontology_extraction_prompt function * [fix]Add dependencies, fix functionality * [add] migration script * feat(celery): add dedicated periodic tasks worker and queue (#261) * fix(web): conflict resolve * Fix/v022 bug (#263) * [fix]Fix the issue of inconsistent language in explicit and episodic memory. * [fix]Fix the issue of inconsistent language in explicit and episodic memory. * [add]Add scene_id * [fix]Based on the AI review to fix the code * Fix/develop memory reflex (#265) * 遗漏的历史映射 * 遗漏的历史映射 * 反思后台报错处理 * [add] migration script * fix: chat conversation_id add node_start * feat(web): show code node * fix(web): Restructure the CustomSelect component, repair the interface that is called multiple times when the form is updated * feat(web): RadioGroupCard support block mode * feat(web): create space add icon * feat(app and model): token consumption statistics * Add/develop memory (#264) * 遗漏的历史映射 * 遗漏的历史映射 * 遗漏的历史映射 * 遗漏的历史映射 * 遗漏的历史映射 * 遗漏的历史映射 * 遗漏的历史映射 * 遗漏的历史映射 * 遗漏的历史映射 * 新增长期记忆功能 * 新增长期记忆功能 * 新增长期记忆功能 * 知识库检索多余字段 * 长期 * feat(app and model): token consumption statistics of the cluster * memory_BUG_fix * fix(web): prompt history remove pageLoading * fix(prompt): remove hard-coded import of prompt file paths (#279) * Fix/develop memory bug (#274) * 遗漏的历史映射 * 遗漏的历史映射 * fix_timeline_memories * fix(web): update retrieve_type key * Fix/develop memory bug (#276) * 遗漏的历史映射 * 遗漏的历史映射 * fix_timeline_memories * fix_timeline_memories * write_gragp/bug_fix * write_gragp/bug_fix * write_gragp/bug_fix * chore(celery): disable periodic task scheduling * fix(prompt): remove hard-coded import of prompt file paths --------- Co-authored-by: lixinyue11 <94037597+lixinyue11@users.noreply.github.com> Co-authored-by: zhaoying <yzhao96@best-inc.com> Co-authored-by: yingzhao <zhaoyingyz@126.com> Co-authored-by: Ke Sun <kesun5@illinois.edu> * fix(web): remove delete confirm content * refactor(workflow): relocate template directory into workflow * feat(memory): add long-term storage task routing and batching * fix(web): PageScrollList loading update * fix(web): PageScrollList loading update * Ontology v1 bug (#291) * [changes]Add 'id' as the secondary sorting key, and 'scene_id' now returns a UUID object * [fix]Fix the "end_user" return to be sorted by update time. * [fix]Set the default values of the memory configuration model based on the spatial model. * [fix]Remove the entity extraction check combination model, read the configuration list, and add the return of scene_id * [fix]Fix the "end_user" return to be sorted by update time. * [fix] * fix(memory): add Redis session validation - Add macOS fork() safety configuration in celery_app.py to prevent initialization issues - Add null/False checks for Redis session queries in term_memory_save to handle missing sessions gracefully - Add null/False checks in memory_long_term_storage to prevent processing empty Redis results - Add null/False checks in aggregate_judgment before format_parsing to avoid errors on missing data - Initialize redis_messages variable in window_dialogue for consistency - Add debug logging when no existing session found in Redis for better troubleshooting - Add TODO comments for magic numbers (scope=6, time=5) to be extracted as constants - Improve error handling when Redis returns False or empty results instead of crashing * fix(web): PageScrollList style update * fix(workflow): fix argument passing in code execution nodes * fix(web): prompt add disabled * fix(web): space icon required * feat(app): modify the key of the token * fix(fix the key of the app's token): * fix(workflow): switch code input encoding to base64+URL encoding * [add]The main project adds multi-API Key load balancing. * [changes]Attribute security access, secure numerical conversion, unified use of local variables * fix(web): save add session update * fix(web): language editor support paste * [changes]Active status filtering logic, API Key selection strategy * memory_BUG * memory_BUG_long_term * [changes] * memory_BUG_long_term * memory_BUG_long_term * Fix/release memory bug (#306) * memory_BUG_fix * memory_BUG * memory_BUG_long_term * memory_BUG_long_term * memory_BUG_long_term * knowledge_retrieval/bug/fix * knowledge_retrieval/bug/fix * knowledge_retrieval/bug/fix * [fix]1.The "read_all_config" interface returns "scene_name";2.Memory configuration for lightweight query ontology scenarios * fix(web): replace code editor * [changes]Modify the description of the time for the recent event * [changes]Modify the code based on the AI review * feat(web): update memory config ontology api * fix(web): ui update * knowledge_retrieval/bug/fix * knowledge_retrieval/bug/fix * knowledge_retrieval/bug/fix * feat(workflow): add token usage statistics for question classifier and parameter extraction * feat(web): move prompt menu * Multiple independent transactions - single transaction * Multiple independent transactions - single transaction * Multiple independent transactions - single transaction * Multiple independent transactions - single transaction * Write Missing None (#321) * Write Missing None * Write Missing None * Write Missing None * Apply suggestion from @sourcery-ai[bot] Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com> * Write Missing None --------- Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com> * Fix/release memory bug (#324) * Write Missing None * Write Missing None * Write Missing None * Apply suggestion from @sourcery-ai[bot] Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com> * Write Missing None * redis update * redis update * redis update * redis update --------- Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com> * Fix/writer memory bug (#326) * [fix]Fix the bug * [fix]Fix the bug * [fix]Correct the direction indication. * fix(web): markdown table ui update * Fix/release memory bug (#332) * Write Missing None * Write Missing None * Write Missing None * Apply suggestion from @sourcery-ai[bot] Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com> * Write Missing None * redis update * redis update * redis update * redis update * writer_dup_bug/fix --------- Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com> * Fix/fact summary (#333) * [fix]Disable the contents related to fact_summary * [fix]Disable the contents related to fact_summary * [fix]Modify the code based on the AI review * Fix/release memory bug (#335) * Write Missing None * Write Missing None * Write Missing None * Apply suggestion from @sourcery-ai[bot] Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com> * Write Missing None * redis update * redis update * redis update * redis update * writer_dup_bug/fix * writer_graph_bug/fix * writer_graph_bug/fix --------- Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com> * Revert "feat(web): move prompt menu" This reverts commit 9e6e8f50f8. * fix(web): ui update * fix(web): update text * fix(web): ui update * fix(model): change the "vl" model type of dashscope to "chat" * fix(model): change the "vl" model type of dashscope to "chat" --------- Co-authored-by: zhaoying <yzhao96@best-inc.com> Co-authored-by: Eternity <1533512157@qq.com> Co-authored-by: Mark <zhuwenhui5566@163.com> Co-authored-by: yingzhao <zhaoyingyz@126.com> Co-authored-by: Timebomb2018 <18868801967@163.com> Co-authored-by: 乐力齐 <162269739+lanceyq@users.noreply.github.com> Co-authored-by: lixinyue11 <94037597+lixinyue11@users.noreply.github.com> Co-authored-by: lixinyue <2569494688@qq.com> Co-authored-by: Eternity <61316157+myhMARS@users.noreply.github.com> Co-authored-by: lanceyq <1982376970@qq.com> Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com>
2026-02-06 19:01:57 +08:00
parent eab7225d83
commit 79ab929fb0
187 changed files with 12252 additions and 1656 deletions
--- a/api/app/repositories/memory_config_repository.py
+++ b/api/app/repositories/memory_config_repository.py
@@ -86,7 +86,8 @@ class MemoryConfigRepository:
        n.description AS description, 
        n.entity_type AS entity_type, 
        n.name AS name,
-        COALESCE(n.fact_summary, '') AS fact_summary,
+        // TODO: fact_summary 功能暂时禁用，待后续开发完善后启用
+        // COALESCE(n.fact_summary, '') AS fact_summary,
        n.end_user_id AS end_user_id,
        n.apply_id AS apply_id,
        n.user_id AS user_id,
@@ -156,7 +157,7 @@ class MemoryConfigRepository:
        return memory_config_obj

    @staticmethod
-    def query_reflection_config_by_id(db: Session, config_id: uuid.UUID) -> MemoryConfig:
+    def query_reflection_config_by_id(db: Session, config_id: uuid.UUID|int|str) -> MemoryConfig:
        """构建反思配置查询语句，通过config_id查询反思配置（SQLAlchemy text() 命名参数）

        Args:
@@ -230,9 +231,12 @@ class MemoryConfigRepository:
                config_name=params.config_name,
                config_desc=params.config_desc,
                workspace_id=params.workspace_id,
+                scene_id=params.scene_id,
                llm_id=params.llm_id,
                embedding_id=params.embedding_id,
                rerank_id=params.rerank_id,
+                reflection_model_id=params.reflection_model_id,
+                emotion_model_id=params.emotion_model_id,
            )
            db.add(db_config)
            db.flush()  # 获取自增ID但不提交事务
@@ -275,6 +279,9 @@ class MemoryConfigRepository:
            if update.config_desc is not None:
                db_config.config_desc = update.config_desc
                has_update = True
+            if update.scene_id is not None:
+                db_config.scene_id = update.scene_id
+                has_update = True

            if not has_update:
                raise ValueError("No fields to update")
@@ -643,28 +650,32 @@ class MemoryConfigRepository:
            raise

    @staticmethod
-    def get_all(db: Session, workspace_id: Optional[uuid.UUID] = None) -> List[MemoryConfig]:
-        """获取所有配置参数
+    def get_all(db: Session, workspace_id: Optional[uuid.UUID] = None) -> List[Tuple[MemoryConfig, Optional[str]]]:
+        """获取所有配置参数，包含关联的场景名称

        Args:
            db: 数据库会话
            workspace_id: 工作空间ID，用于过滤查询结果

        Returns:
-            List[MemoryConfig]: 配置列表
+            List[Tuple[MemoryConfig, Optional[str]]]: 配置列表，每项为 (配置对象, 场景名称)
        """
+        from app.models.ontology_scene import OntologyScene
+        
        db_logger.debug(f"查询所有配置: workspace_id={workspace_id}")

        try:
-            query = db.query(MemoryConfig)
+            query = db.query(MemoryConfig, OntologyScene.scene_name).outerjoin(
+                OntologyScene, MemoryConfig.scene_id == OntologyScene.scene_id
+            )

            if workspace_id:
                query = query.filter(MemoryConfig.workspace_id == workspace_id)

-            configs = query.order_by(desc(MemoryConfig.updated_at)).all()
+            results = query.order_by(desc(MemoryConfig.updated_at)).all()

-            db_logger.debug(f"配置列表查询成功: 数量={len(configs)}")
-            return configs
+            db_logger.debug(f"配置列表查询成功: 数量={len(results)}")
+            return results

        except Exception as e:
            db_logger.error(f"查询所有配置失败: workspace_id={workspace_id} - {str(e)}")
--- a/api/app/repositories/neo4j/add_edges.py
+++ b/api/app/repositories/neo4j/add_edges.py
@@ -79,7 +79,8 @@ async def add_memory_summary_statement_edges(summaries: List[MemorySummaryNode],
    try:
        edges: List[dict] = []
        for s in summaries:
-            for chunk_id in getattr(s, "chunk_ids", []) or []:
+            chunk_ids = getattr(s, "chunk_ids", []) or []
+            for chunk_id in chunk_ids:
                edges.append({
                    "summary_id": s.id,
                    "chunk_id": chunk_id,
@@ -91,12 +92,11 @@ async def add_memory_summary_statement_edges(summaries: List[MemorySummaryNode],

        if not edges:
            return []
-
        result = await connector.execute_query(
            MEMORY_SUMMARY_STATEMENT_EDGE_SAVE,
            edges=edges
        )
        created = [record.get("uuid") for record in result] if result else []
        return created
-    except Exception:
+    except Exception as e:
        return None
--- a/api/app/repositories/neo4j/add_nodes.py
+++ b/api/app/repositories/neo4j/add_nodes.py
@@ -217,8 +217,10 @@ async def add_memory_summary_nodes(summaries: List[MemorySummaryNode], connector
            summaries=flattened
        )
        created_ids = [record.get("uuid") for record in result]
+        print(f"Successfully saved {len(created_ids)} MemorySummary nodes to Neo4j")
        return created_ids
-    except Exception:
+    except Exception as e:
+        print(f"Failed to save MemorySummary nodes to Neo4j: {e}")
        return None


--- a/api/app/repositories/neo4j/cypher_queries.py
+++ b/api/app/repositories/neo4j/cypher_queries.py
@@ -101,10 +101,11 @@ SET e.name = CASE WHEN entity.name IS NOT NULL AND entity.name <> '' THEN entity
    e.name_embedding = CASE
        WHEN entity.name_embedding IS NOT NULL AND size(entity.name_embedding) > 0 THEN entity.name_embedding
        ELSE e.name_embedding END,
-    e.fact_summary = CASE
-        WHEN entity.fact_summary IS NOT NULL AND entity.fact_summary <> ''
-         AND (e.fact_summary IS NULL OR size(e.fact_summary) = 0 OR size(entity.fact_summary) > size(e.fact_summary))
-        THEN entity.fact_summary ELSE e.fact_summary END,
+    // TODO: fact_summary 功能暂时禁用，待后续开发完善后启用
+    // e.fact_summary = CASE
+    //     WHEN entity.fact_summary IS NOT NULL AND entity.fact_summary <> ''
+    //      AND (e.fact_summary IS NULL OR size(e.fact_summary) = 0 OR size(entity.fact_summary) > size(e.fact_summary))
+    //     THEN entity.fact_summary ELSE e.fact_summary END,
    e.connect_strength = CASE
        WHEN entity.connect_strength IS NULL OR entity.connect_strength = '' THEN e.connect_strength
        ELSE CASE
@@ -321,7 +322,8 @@ RETURN e.id AS id,
       e.description AS description,
       e.aliases AS aliases,
       e.name_embedding AS name_embedding,
-       COALESCE(e.fact_summary, '') AS fact_summary,
+       // TODO: fact_summary 功能暂时禁用，待后续开发完善后启用
+       // COALESCE(e.fact_summary, '') AS fact_summary,
       e.connect_strength AS connect_strength,
       collect(DISTINCT s.id) AS statement_ids,
       collect(DISTINCT c.id) AS chunk_ids,
@@ -877,7 +879,8 @@ RETURN
    CASE
      WHEN ms:ExtractedEntity THEN {
        text: ms.name,
-        created_at: ms.created_at
+        created_at: ms.created_at,
+        type: "情景记忆" 
      }
    END
  ) AS ExtractedEntity,
@@ -887,7 +890,8 @@ RETURN
    CASE
      WHEN n:MemorySummary THEN {
        text: n.content,
-        created_at: n.created_at
+        created_at: n.created_at,
+        type: "长期沉淀" 
      }
    END
  ) AS MemorySummary,
@@ -895,7 +899,8 @@ RETURN
  collect(
    DISTINCT {
      text: e.statement,
-      created_at: e.created_at
+      created_at: e.created_at,
+      type: "情绪记忆" 
    }
  ) AS statement;
 """
@@ -999,3 +1004,58 @@ RETURN DISTINCT
 x.statement as statement,x.created_at as created_at
 """

+Graph_Node_query = """
+            MATCH (n:MemorySummary)
+                WHERE n.end_user_id = $end_user_id
+                RETURN
+                  elementId(n) AS id,
+                  labels(n) AS labels,
+                  properties(n) AS properties,
+                  0 AS priority
+                LIMIT $limit
+                
+                UNION ALL
+
+                    MATCH (n:Dialogue)
+                    WHERE n.end_user_id =  $end_user_id
+                    RETURN
+                      elementId(n) AS id,
+                      labels(n) AS labels,
+                      properties(n) AS properties,
+                      1 AS priority
+                    LIMIT 1
+
+                UNION ALL
+
+                MATCH (n:Statement)
+                WHERE n.end_user_id =  $end_user_id
+                RETURN
+                  elementId(n) AS id,
+                  labels(n) AS labels,
+                  properties(n) AS properties,
+                  1 AS priority
+                LIMIT $limit
+
+                UNION ALL
+
+                MATCH (n:ExtractedEntity)
+                WHERE n.end_user_id =  $end_user_id
+                RETURN
+                  elementId(n) AS id,
+                  labels(n) AS labels,
+                  properties(n) AS properties,
+                  2 AS priority
+                LIMIT $limit
+
+                UNION ALL
+
+                MATCH (n:Chunk)
+                WHERE n.end_user_id =  $end_user_id
+                RETURN
+                  elementId(n) AS id,
+                  labels(n) AS labels,
+                  properties(n) AS properties,
+                  3 AS priority
+                LIMIT $limit
+
+            """
--- a/api/app/repositories/neo4j/graph_saver.py
+++ b/api/app/repositories/neo4j/graph_saver.py
@@ -21,7 +21,8 @@ from app.core.memory.models.graph_models import (
    ExtractedEntityNode,
    EntityEntityEdge,
 )
-
+import logging
+logger = logging.getLogger(__name__)
 async def save_entities_and_relationships(
    entity_nodes: List[ExtractedEntityNode],
    entity_entity_edges: List[EntityEntityEdge],
@@ -41,8 +42,8 @@ async def save_entities_and_relationships(
            'statement': edge.statement,
            'valid_at': edge.valid_at.isoformat() if edge.valid_at else None,
            'invalid_at': edge.invalid_at.isoformat() if edge.invalid_at else None,
-            'created_at': edge.created_at.isoformat(),
-            'expired_at': edge.expired_at.isoformat(),
+            'created_at': edge.created_at.isoformat() if edge.created_at else None,
+            'expired_at': edge.expired_at.isoformat() if edge.expired_at else None,
            'run_id': edge.run_id,
            'end_user_id': edge.end_user_id,
        }
@@ -147,14 +148,14 @@ async def save_statement_entity_edges(


 async def save_dialog_and_statements_to_neo4j(
-    dialogue_nodes: List[DialogueNode],
-    chunk_nodes: List[ChunkNode],
-    statement_nodes: List[StatementNode],
-    entity_nodes: List[ExtractedEntityNode],
-    entity_edges: List[EntityEntityEdge],
-    statement_chunk_edges: List[StatementChunkEdge],
-    statement_entity_edges: List[StatementEntityEdge],
-    connector: Neo4jConnector
+        dialogue_nodes: List[DialogueNode],
+        chunk_nodes: List[ChunkNode],
+        statement_nodes: List[StatementNode],
+        entity_nodes: List[ExtractedEntityNode],
+        entity_edges: List[EntityEntityEdge],
+        statement_chunk_edges: List[StatementChunkEdge],
+        statement_entity_edges: List[StatementEntityEdge],
+        connector: Neo4jConnector
 ) -> bool:
    """Save dialogue nodes, chunk nodes, statement nodes, entities, and all relationships to Neo4j using graph models.

@@ -171,40 +172,127 @@ async def save_dialog_and_statements_to_neo4j(
    Returns:
        bool: True if successful, False otherwise
    """
-    try:
-        # Save all dialogue nodes in batch
-        dialogue_uuids = await add_dialogue_nodes(dialogue_nodes, connector)
-        if dialogue_uuids:
+
+    # 定义事务函数，将所有写操作放在一个事务中
+    async def _save_all_in_transaction(tx):
+        """在单个事务中执行所有保存操作，避免死锁"""
+        results = {}
+
+        # 1. Save all dialogue nodes in batch
+        if dialogue_nodes:
+            from app.repositories.neo4j.cypher_queries import DIALOGUE_NODE_SAVE
+            dialogue_data = [node.model_dump() for node in dialogue_nodes]
+            result = await tx.run(DIALOGUE_NODE_SAVE, dialogues=dialogue_data)
+            dialogue_uuids = [record["uuid"] async for record in result]
+            results['dialogues'] = dialogue_uuids
            print(f"Dialogues saved to Neo4j with UUIDs: {dialogue_uuids}")
-        else:
-            print("Failed to save dialogues to Neo4j")
-            return False

-        # Save all chunk nodes in batch
-        await save_chunk_nodes(chunk_nodes, connector)
+        # 2. Save all chunk nodes in batch
+        if chunk_nodes:
+            from app.repositories.neo4j.cypher_queries import CHUNK_NODE_SAVE
+            chunk_data = [node.model_dump() for node in chunk_nodes]
+            result = await tx.run(CHUNK_NODE_SAVE, chunks=chunk_data)
+            chunk_uuids = [record["uuid"] async for record in result]
+            results['chunks'] = chunk_uuids
+            logger.info(f"Successfully saved {len(chunk_uuids)} chunk nodes to Neo4j")

-        # Save all statement nodes in batch
+        # 3. Save all statement nodes in batch
        if statement_nodes:
-            statement_uuids = await add_statement_nodes(statement_nodes, connector)
-            if statement_uuids:
-                print(f"Successfully saved {len(statement_uuids)} statement nodes to Neo4j")
-            else:
-                print("Failed to save statement nodes to Neo4j")
-                return False
-        else:
-            print("No statement nodes to save")
+            from app.repositories.neo4j.cypher_queries import STATEMENT_NODE_SAVE
+            statement_data = [node.model_dump() for node in statement_nodes]
+            result = await tx.run(STATEMENT_NODE_SAVE, statements=statement_data)
+            statement_uuids = [record["uuid"] async for record in result]
+            results['statements'] = statement_uuids
+            logger.info(f"Successfully saved {len(statement_uuids)} statement nodes to Neo4j")

-        # Save entities and relationships
-        await save_entities_and_relationships(entity_nodes, entity_edges, connector)
-        print("Successfully saved entities and relationships to Neo4j")
+        # 4. Save entities
+        if entity_nodes:
+            from app.repositories.neo4j.cypher_queries import EXTRACTED_ENTITY_NODE_SAVE
+            entity_data = [entity.model_dump() for entity in entity_nodes]
+            result = await tx.run(EXTRACTED_ENTITY_NODE_SAVE, entities=entity_data)
+            entity_uuids = [record["uuid"] async for record in result]
+            results['entities'] = entity_uuids
+            logger.info(f"Successfully saved {len(entity_uuids)} entity nodes to Neo4j")

-        # Save new edges
-        await save_statement_chunk_edges(statement_chunk_edges, connector)
-        await save_statement_entity_edges(statement_entity_edges, connector)
+        # 5. Create entity relationships
+        if entity_edges:
+            from app.repositories.neo4j.cypher_queries import ENTITY_RELATIONSHIP_SAVE
+            relationship_data = []
+            for edge in entity_edges:
+                relationship_data.append({
+                    'source_id': edge.source,
+                    'target_id': edge.target,
+                    'predicate': edge.relation_type,
+                    'statement_id': edge.source_statement_id,
+                    'value': edge.relation_value,
+                    'statement': edge.statement,
+                    'valid_at': edge.valid_at.isoformat() if edge.valid_at else None,
+                    'invalid_at': edge.invalid_at.isoformat() if edge.invalid_at else None,
+                    'created_at': edge.created_at.isoformat() if edge.created_at else None,
+                    'expired_at': edge.expired_at.isoformat() if edge.expired_at else None,
+                    'run_id': edge.run_id,
+                    'end_user_id': edge.end_user_id,
+                })
+            result = await tx.run(ENTITY_RELATIONSHIP_SAVE, relationships=relationship_data)
+            rel_uuids = [record["uuid"] async for record in result]
+            results['entity_relationships'] = rel_uuids
+            logger.info(f"Successfully saved {len(rel_uuids)} entity relationships to Neo4j")

+        # 6. Save statement-chunk edges
+        if statement_chunk_edges:
+            from app.repositories.neo4j.cypher_queries import CHUNK_STATEMENT_EDGE_SAVE
+            sc_edge_data = []
+            for edge in statement_chunk_edges:
+                sc_edge_data.append({
+                    "id": edge.id,
+                    "source": edge.source,
+                    "target": edge.target,
+                    "created_at": edge.created_at.isoformat() if edge.created_at else None,
+                    "expired_at": edge.expired_at.isoformat() if edge.expired_at else None,
+                    "run_id": edge.run_id,
+                    "end_user_id": edge.end_user_id,
+                })
+            result = await tx.run(CHUNK_STATEMENT_EDGE_SAVE, chunk_statement_edges=sc_edge_data)
+            sc_uuids = [record["uuid"] async for record in result]
+            results['statement_chunk_edges'] = sc_uuids
+            logger.info(f"Successfully saved {len(sc_uuids)} statement-chunk edges to Neo4j")
+
+        # 7. Save statement-entity edges
+        if statement_entity_edges:
+            from app.repositories.neo4j.cypher_queries import STATEMENT_ENTITY_EDGE_SAVE
+            se_edge_data = []
+            for edge in statement_entity_edges:
+                se_edge_data.append({
+                    "source": edge.source,
+                    "target": edge.target,
+                    "created_at": edge.created_at.isoformat() if edge.created_at else None,
+                    "expired_at": edge.expired_at.isoformat() if edge.expired_at else None,
+                    "run_id": edge.run_id,
+                    "end_user_id": edge.end_user_id,
+                    "connect_strength": getattr(edge, "connect_strength", "strong"),
+                })
+            result = await tx.run(STATEMENT_ENTITY_EDGE_SAVE, relationships=se_edge_data)
+            se_uuids = [record["uuid"] async for record in result]
+            results['statement_entity_edges'] = se_uuids
+            logger.info(f"Successfully saved {len(se_uuids)} statement-entity edges to Neo4j")
+
+        return results
+
+    try:
+        # 使用显式写事务执行所有操作，避免死锁
+        results = await connector.execute_write_transaction(_save_all_in_transaction)
+        summary = {
+            key: len(value)
+            for key, value in results.items()
+            if isinstance(value, (list, tuple, set))
+        }
+        logger.info("Transaction completed. Summary: %s", summary)
+        logger.debug("Full transaction results: %r", results)
        return True

    except Exception as e:
+        logger.error(f"Neo4j integration error: {e}", exc_info=True)
        print(f"Neo4j integration error: {e}")
        print("Continuing without database storage...")
        return False
+
--- a/api/app/repositories/ontology_class_repository.py
+++ b/api/app/repositories/ontology_class_repository.py
@@ -0,0 +1,404 @@
+# -*- coding: utf-8 -*-
+"""本体类型Repository层
+
+本模块提供本体类型的数据访问层实现。
+
+Classes:
+    OntologyClassRepository: 本体类型数据访问类
+"""
+
+import logging
+from typing import List, Optional
+from uuid import UUID
+
+from sqlalchemy.orm import Session, joinedload
+
+from app.core.logging_config import get_db_logger
+from app.models.ontology_class import OntologyClass
+from app.models.ontology_scene import OntologyScene
+
+
+logger = get_db_logger()
+
+
+class OntologyClassRepository:
+    """本体类型Repository
+    
+    提供本体类型的CRUD操作和权限检查。
+    
+    Attributes:
+        db: SQLAlchemy数据库会话
+    """
+    
+    def __init__(self, db: Session):
+        """初始化Repository
+        
+        Args:
+            db: SQLAlchemy数据库会话
+        """
+        self.db = db
+    
+    def create(self, class_data: dict, scene_id: UUID) -> OntologyClass:
+        """创建本体类型
+        
+        Args:
+            class_data: 类型数据字典，包含class_name和class_description
+            scene_id: 所属场景ID
+            
+        Returns:
+            OntologyClass: 创建的类型对象
+            
+        Raises:
+            Exception: 数据库操作失败
+            
+        Examples:
+            >>> repo = OntologyClassRepository(db)
+            >>> ontology_class = repo.create(
+            ...     {"class_name": "患者", "class_description": "描述"},
+            ...     scene_id
+            ... )
+        """
+        try:
+            logger.info(
+                f"Creating ontology class - "
+                f"name={class_data.get('class_name')}, "
+                f"scene_id={scene_id}"
+            )
+            
+            ontology_class = OntologyClass(
+                class_name=class_data.get("class_name"),
+                class_description=class_data.get("class_description"),
+                scene_id=scene_id
+            )
+            
+            self.db.add(ontology_class)
+            self.db.flush()  # 获取ID但不提交
+            
+            logger.info(
+                f"Ontology class created successfully - "
+                f"class_id={ontology_class.class_id}"
+            )
+            
+            return ontology_class
+            
+        except Exception as e:
+            logger.error(
+                f"Failed to create ontology class: {str(e)}",
+                exc_info=True
+            )
+            raise
+    
+    def get_by_id(self, class_id: UUID) -> Optional[OntologyClass]:
+        """根据ID获取类型
+        
+        Args:
+            class_id: 类型ID
+            
+        Returns:
+            Optional[OntologyClass]: 类型对象，不存在则返回None
+            
+        Examples:
+            >>> repo = OntologyClassRepository(db)
+            >>> ontology_class = repo.get_by_id(class_id)
+        """
+        try:
+            logger.debug(f"Getting ontology class by ID: {class_id}")
+            
+            ontology_class = self.db.query(OntologyClass).filter(
+                OntologyClass.class_id == class_id
+            ).first()
+            
+            if ontology_class:
+                logger.debug(f"Ontology class found: {class_id}")
+            else:
+                logger.debug(f"Ontology class not found: {class_id}")
+            
+            return ontology_class
+            
+        except Exception as e:
+            logger.error(
+                f"Failed to get ontology class by ID: {str(e)}",
+                exc_info=True
+            )
+            raise
+    
+    def get_by_name(self, class_name: str, scene_id: UUID) -> Optional[OntologyClass]:
+        """根据类型名称和场景ID获取类型（精确匹配）
+        
+        Args:
+            class_name: 类型名称
+            scene_id: 场景ID
+            
+        Returns:
+            Optional[OntologyClass]: 类型对象，不存在则返回None
+            
+        Examples:
+            >>> repo = OntologyClassRepository(db)
+            >>> ontology_class = repo.get_by_name("患者", scene_id)
+        """
+        try:
+            logger.debug(f"Getting ontology class by name: {class_name}, scene_id: {scene_id}")
+            
+            ontology_class = self.db.query(OntologyClass).filter(
+                OntologyClass.class_name == class_name,
+                OntologyClass.scene_id == scene_id
+            ).first()
+            
+            if ontology_class:
+                logger.debug(f"Ontology class found: {class_name}")
+            else:
+                logger.debug(f"Ontology class not found: {class_name}")
+            
+            return ontology_class
+            
+        except Exception as e:
+            logger.error(
+                f"Failed to get ontology class by name: {str(e)}",
+                exc_info=True
+            )
+            raise
+    
+    def search_by_name(self, keyword: str, scene_id: UUID) -> List[OntologyClass]:
+        """根据关键词模糊搜索类型
+        
+        使用 LIKE 进行模糊匹配，支持中文和英文。
+        
+        Args:
+            keyword: 搜索关键词
+            scene_id: 场景ID
+            
+        Returns:
+            List[OntologyClass]: 匹配的类型列表
+            
+        Examples:
+            >>> repo = OntologyClassRepository(db)
+            >>> classes = repo.search_by_name("患者", scene_id)
+        """
+        try:
+            logger.debug(
+                f"Searching ontology classes by keyword - "
+                f"keyword={keyword}, scene_id={scene_id}"
+            )
+            
+            # 使用 ilike 进行不区分大小写的模糊匹配
+            classes = self.db.query(OntologyClass).filter(
+                OntologyClass.class_name.ilike(f"%{keyword}%"),
+                OntologyClass.scene_id == scene_id
+            ).order_by(
+                OntologyClass.created_at.desc()
+            ).all()
+            
+            logger.info(
+                f"Found {len(classes)} ontology classes matching keyword '{keyword}' "
+                f"in scene {scene_id}"
+            )
+            
+            return classes
+            
+        except Exception as e:
+            logger.error(
+                f"Failed to search ontology classes by keyword: {str(e)}",
+                exc_info=True
+            )
+            raise
+    
+    def get_by_scene(self, scene_id: UUID) -> List[OntologyClass]:
+        """获取场景下的所有类型
+        
+        按创建时间倒序排列。
+        
+        Args:
+            scene_id: 场景ID
+            
+        Returns:
+            List[OntologyClass]: 类型列表
+            
+        Examples:
+            >>> repo = OntologyClassRepository(db)
+            >>> classes = repo.get_by_scene(scene_id)
+        """
+        try:
+            logger.debug(f"Getting ontology classes by scene: {scene_id}")
+            
+            classes = self.db.query(OntologyClass).filter(
+                OntologyClass.scene_id == scene_id
+            ).order_by(
+                OntologyClass.created_at.desc()
+            ).all()
+            
+            logger.info(
+                f"Found {len(classes)} ontology classes in scene {scene_id}"
+            )
+            
+            return classes
+            
+        except Exception as e:
+            logger.error(
+                f"Failed to get ontology classes by scene: {str(e)}",
+                exc_info=True
+            )
+            raise
+    
+    def update(self, class_id: UUID, update_data: dict) -> Optional[OntologyClass]:
+        """更新类型信息
+        
+        Args:
+            class_id: 类型ID
+            update_data: 更新数据字典
+            
+        Returns:
+            Optional[OntologyClass]: 更新后的类型对象，不存在则返回None
+            
+        Raises:
+            Exception: 数据库操作失败
+            
+        Examples:
+            >>> repo = OntologyClassRepository(db)
+            >>> ontology_class = repo.update(
+            ...     class_id,
+            ...     {"class_name": "新名称"}
+            ... )
+        """
+        try:
+            logger.info(f"Updating ontology class: {class_id}")
+            
+            ontology_class = self.get_by_id(class_id)
+            if not ontology_class:
+                logger.warning(f"Ontology class not found for update: {class_id}")
+                return None
+            
+            # 更新字段
+            if "class_name" in update_data and update_data["class_name"] is not None:
+                ontology_class.class_name = update_data["class_name"]
+            
+            if "class_description" in update_data:
+                ontology_class.class_description = update_data["class_description"]
+            
+            self.db.flush()
+            
+            logger.info(f"Ontology class updated successfully: {class_id}")
+            
+            return ontology_class
+            
+        except Exception as e:
+            logger.error(
+                f"Failed to update ontology class: {str(e)}",
+                exc_info=True
+            )
+            raise
+    
+    def delete(self, class_id: UUID) -> bool:
+        """删除类型
+        
+        Args:
+            class_id: 类型ID
+            
+        Returns:
+            bool: 删除成功返回True，类型不存在返回False
+            
+        Raises:
+            Exception: 数据库操作失败
+            
+        Examples:
+            >>> repo = OntologyClassRepository(db)
+            >>> success = repo.delete(class_id)
+        """
+        try:
+            logger.info(f"Deleting ontology class: {class_id}")
+            
+            ontology_class = self.get_by_id(class_id)
+            if not ontology_class:
+                logger.warning(f"Ontology class not found for delete: {class_id}")
+                return False
+            
+            self.db.delete(ontology_class)
+            self.db.flush()
+            
+            logger.info(f"Ontology class deleted successfully: {class_id}")
+            
+            return True
+            
+        except Exception as e:
+            logger.error(
+                f"Failed to delete ontology class: {str(e)}",
+                exc_info=True
+            )
+            raise
+    
+    def check_ownership(self, class_id: UUID, workspace_id: UUID) -> bool:
+        """检查类型是否属于指定工作空间（通过场景关联）
+        
+        Args:
+            class_id: 类型ID
+            workspace_id: 工作空间ID
+            
+        Returns:
+            bool: 属于返回True，否则返回False
+            
+        Examples:
+            >>> repo = OntologyClassRepository(db)
+            >>> is_owner = repo.check_ownership(class_id, workspace_id)
+        """
+        try:
+            logger.debug(
+                f"Checking class ownership - "
+                f"class_id={class_id}, workspace_id={workspace_id}"
+            )
+            
+            count = self.db.query(OntologyClass).join(
+                OntologyScene,
+                OntologyClass.scene_id == OntologyScene.scene_id
+            ).filter(
+                OntologyClass.class_id == class_id,
+                OntologyScene.workspace_id == workspace_id
+            ).count()
+            
+            is_owner = count > 0
+            
+            logger.debug(
+                f"Class ownership check result: {is_owner} - "
+                f"class_id={class_id}"
+            )
+            
+            return is_owner
+            
+        except Exception as e:
+            logger.error(
+                f"Failed to check class ownership: {str(e)}",
+                exc_info=True
+            )
+            raise
+    
+    def get_scene_id_by_class(self, class_id: UUID) -> Optional[UUID]:
+        """根据类型ID获取所属场景ID
+        
+        Args:
+            class_id: 类型ID
+            
+        Returns:
+            Optional[UUID]: 场景ID，类型不存在则返回None
+            
+        Examples:
+            >>> repo = OntologyClassRepository(db)
+            >>> scene_id = repo.get_scene_id_by_class(class_id)
+        """
+        try:
+            logger.debug(f"Getting scene ID by class: {class_id}")
+            
+            ontology_class = self.get_by_id(class_id)
+            if not ontology_class:
+                logger.debug(f"Class not found: {class_id}")
+                return None
+            
+            logger.debug(
+                f"Found scene ID: {ontology_class.scene_id} for class: {class_id}"
+            )
+            
+            return ontology_class.scene_id
+            
+        except Exception as e:
+            logger.error(
+                f"Failed to get scene ID by class: {str(e)}",
+                exc_info=True
+            )
+            raise
--- a/api/app/repositories/ontology_scene_repository.py
+++ b/api/app/repositories/ontology_scene_repository.py
@@ -0,0 +1,439 @@
+# -*- coding: utf-8 -*-
+"""本体场景Repository层
+
+本模块提供本体场景的数据访问层实现。
+
+Classes:
+    OntologySceneRepository: 本体场景数据访问类
+"""
+
+import logging
+from typing import List, Optional
+from uuid import UUID
+
+from sqlalchemy.orm import Session, joinedload
+
+from app.core.logging_config import get_db_logger
+from app.models.ontology_scene import OntologyScene
+
+
+logger = get_db_logger()
+
+
+class OntologySceneRepository:
+    """本体场景Repository
+    
+    提供本体场景的CRUD操作和权限检查。
+    
+    Attributes:
+        db: SQLAlchemy数据库会话
+    """
+    
+    def __init__(self, db: Session):
+        """初始化Repository
+        
+        Args:
+            db: SQLAlchemy数据库会话
+        """
+        self.db = db
+    
+    def create(self, scene_data: dict, workspace_id: UUID) -> OntologyScene:
+        """创建本体场景
+        
+        Args:
+            scene_data: 场景数据字典，包含scene_name和scene_description
+            workspace_id: 所属工作空间ID
+            
+        Returns:
+            OntologyScene: 创建的场景对象
+            
+        Raises:
+            Exception: 数据库操作失败
+            
+        Examples:
+            >>> repo = OntologySceneRepository(db)
+            >>> scene = repo.create(
+            ...     {"scene_name": "医疗场景", "scene_description": "描述"},
+            ...     workspace_id
+            ... )
+        """
+        try:
+            logger.info(
+                f"Creating ontology scene - "
+                f"name={scene_data.get('scene_name')}, "
+                f"workspace_id={workspace_id}"
+            )
+            
+            scene = OntologyScene(
+                scene_name=scene_data.get("scene_name"),
+                scene_description=scene_data.get("scene_description"),
+                workspace_id=workspace_id
+            )
+            
+            self.db.add(scene)
+            self.db.flush()  # 获取ID但不提交
+            
+            logger.info(
+                f"Ontology scene created successfully - "
+                f"scene_id={scene.scene_id}"
+            )
+            
+            return scene
+            
+        except Exception as e:
+            logger.error(
+                f"Failed to create ontology scene: {str(e)}",
+                exc_info=True
+            )
+            raise
+    
+    def get_by_id(self, scene_id: UUID) -> Optional[OntologyScene]:
+        """根据ID获取场景
+        
+        Args:
+            scene_id: 场景ID
+            
+        Returns:
+            Optional[OntologyScene]: 场景对象，不存在则返回None
+            
+        Examples:
+            >>> repo = OntologySceneRepository(db)
+            >>> scene = repo.get_by_id(scene_id)
+        """
+        try:
+            logger.debug(f"Getting ontology scene by ID: {scene_id}")
+            
+            scene = self.db.query(OntologyScene).filter(
+                OntologyScene.scene_id == scene_id
+            ).first()
+            
+            if scene:
+                logger.debug(f"Ontology scene found: {scene_id}")
+            else:
+                logger.debug(f"Ontology scene not found: {scene_id}")
+            
+            return scene
+            
+        except Exception as e:
+            logger.error(
+                f"Failed to get ontology scene by ID: {str(e)}",
+                exc_info=True
+            )
+            raise
+    
+    def get_by_name(self, scene_name: str, workspace_id: UUID) -> Optional[OntologyScene]:
+        """根据场景名称和工作空间ID获取场景（精确匹配）
+        
+        Args:
+            scene_name: 场景名称
+            workspace_id: 工作空间ID
+            
+        Returns:
+            Optional[OntologyScene]: 场景对象，不存在则返回None
+            
+        Examples:
+            >>> repo = OntologySceneRepository(db)
+            >>> scene = repo.get_by_name("医疗场景", workspace_id)
+        """
+        try:
+            logger.debug(
+                f"Getting ontology scene by name - "
+                f"scene_name={scene_name}, workspace_id={workspace_id}"
+            )
+            
+            scene = self.db.query(OntologyScene).options(
+                joinedload(OntologyScene.classes)
+            ).filter(
+                OntologyScene.scene_name == scene_name,
+                OntologyScene.workspace_id == workspace_id
+            ).first()
+            
+            if scene:
+                logger.debug(f"Ontology scene found: {scene_name}")
+            else:
+                logger.debug(f"Ontology scene not found: {scene_name}")
+            
+            return scene
+            
+        except Exception as e:
+            logger.error(
+                f"Failed to get ontology scene by name: {str(e)}",
+                exc_info=True
+            )
+            raise
+    
+    def search_by_name(self, keyword: str, workspace_id: UUID) -> List[OntologyScene]:
+        """根据关键词模糊搜索场景
+        
+        使用 LIKE 进行模糊匹配，支持中文和英文。
+        
+        Args:
+            keyword: 搜索关键词
+            workspace_id: 工作空间ID
+            
+        Returns:
+            List[OntologyScene]: 匹配的场景列表
+            
+        Examples:
+            >>> repo = OntologySceneRepository(db)
+            >>> scenes = repo.search_by_name("医疗", workspace_id)
+        """
+        try:
+            logger.debug(
+                f"Searching ontology scenes by keyword - "
+                f"keyword={keyword}, workspace_id={workspace_id}"
+            )
+            
+            # 使用 ilike 进行不区分大小写的模糊匹配
+            scenes = self.db.query(OntologyScene).options(
+                joinedload(OntologyScene.classes)
+            ).filter(
+                OntologyScene.scene_name.ilike(f"%{keyword}%"),
+                OntologyScene.workspace_id == workspace_id
+            ).order_by(
+                OntologyScene.updated_at.desc()
+            ).all()
+            
+            logger.info(
+                f"Found {len(scenes)} ontology scenes matching keyword '{keyword}' "
+                f"in workspace {workspace_id}"
+            )
+            
+            return scenes
+            
+        except Exception as e:
+            logger.error(
+                f"Failed to search ontology scenes by keyword: {str(e)}",
+                exc_info=True
+            )
+            raise
+    
+    def get_by_workspace(self, workspace_id: UUID, page: Optional[int] = None, page_size: Optional[int] = None) -> tuple:
+        """获取工作空间下的所有场景（支持分页）
+        
+        使用joinedload预加载classes关系以统计数量。
+        
+        Args:
+            workspace_id: 工作空间ID
+            page: 页码（可选，从1开始）
+            page_size: 每页数量（可选）
+            
+        Returns:
+            tuple: (场景列表, 总数量)
+            
+        Examples:
+            >>> repo = OntologySceneRepository(db)
+            >>> scenes, total = repo.get_by_workspace(workspace_id)
+            >>> scenes, total = repo.get_by_workspace(workspace_id, page=1, page_size=10)
+        """
+        try:
+            logger.debug(f"Getting ontology scenes by workspace: {workspace_id}, page={page}, page_size={page_size}")
+            
+            # 构建基础查询
+            query = self.db.query(OntologyScene).options(
+                joinedload(OntologyScene.classes)
+            ).filter(
+                OntologyScene.workspace_id == workspace_id
+            ).order_by(
+                OntologyScene.updated_at.desc()
+            )
+            
+            # 获取总数
+            total = query.count()
+            
+            # 如果提供了分页参数，应用分页
+            if page is not None and page_size is not None:
+                offset = (page - 1) * page_size
+                query = query.offset(offset).limit(page_size)
+                logger.debug(f"Applying pagination: offset={offset}, limit={page_size}")
+            
+            scenes = query.all()
+            
+            logger.info(
+                f"Found {len(scenes)} ontology scenes (total: {total}) in workspace {workspace_id}"
+            )
+            
+            return scenes, total
+            
+        except Exception as e:
+            logger.error(
+                f"Failed to get ontology scenes by workspace: {str(e)}",
+                exc_info=True
+            )
+            raise
+    
+    def update(self, scene_id: UUID, update_data: dict) -> Optional[OntologyScene]:
+        """更新场景信息
+        
+        Args:
+            scene_id: 场景ID
+            update_data: 更新数据字典
+            
+        Returns:
+            Optional[OntologyScene]: 更新后的场景对象，不存在则返回None
+            
+        Raises:
+            Exception: 数据库操作失败
+            
+        Examples:
+            >>> repo = OntologySceneRepository(db)
+            >>> scene = repo.update(
+            ...     scene_id,
+            ...     {"scene_name": "新名称"}
+            ... )
+        """
+        try:
+            logger.info(f"Updating ontology scene: {scene_id}")
+            
+            scene = self.get_by_id(scene_id)
+            if not scene:
+                logger.warning(f"Ontology scene not found for update: {scene_id}")
+                return None
+            
+            # 更新字段
+            if "scene_name" in update_data and update_data["scene_name"] is not None:
+                scene.scene_name = update_data["scene_name"]
+            
+            if "scene_description" in update_data:
+                scene.scene_description = update_data["scene_description"]
+            
+            self.db.flush()
+            
+            logger.info(f"Ontology scene updated successfully: {scene_id}")
+            
+            return scene
+            
+        except Exception as e:
+            logger.error(
+                f"Failed to update ontology scene: {str(e)}",
+                exc_info=True
+            )
+            raise
+    
+    def delete(self, scene_id: UUID) -> bool:
+        """删除场景（级联删除类型）
+        
+        依赖数据库级联删除配置（ondelete="CASCADE"）。
+        
+        Args:
+            scene_id: 场景ID
+            
+        Returns:
+            bool: 删除成功返回True，场景不存在返回False
+            
+        Raises:
+            Exception: 数据库操作失败
+            
+        Examples:
+            >>> repo = OntologySceneRepository(db)
+            >>> success = repo.delete(scene_id)
+        """
+        try:
+            logger.info(f"Deleting ontology scene: {scene_id}")
+            
+            scene = self.get_by_id(scene_id)
+            if not scene:
+                logger.warning(f"Ontology scene not found for delete: {scene_id}")
+                return False
+            
+            self.db.delete(scene)
+            self.db.flush()
+            
+            logger.info(
+                f"Ontology scene deleted successfully (cascade): {scene_id}"
+            )
+            
+            return True
+            
+        except Exception as e:
+            logger.error(
+                f"Failed to delete ontology scene: {str(e)}",
+                exc_info=True
+            )
+            raise
+    
+    def check_ownership(self, scene_id: UUID, workspace_id: UUID) -> bool:
+        """检查场景是否属于指定工作空间
+        
+        Args:
+            scene_id: 场景ID
+            workspace_id: 工作空间ID
+            
+        Returns:
+            bool: 属于返回True，否则返回False
+            
+        Examples:
+            >>> repo = OntologySceneRepository(db)
+            >>> is_owner = repo.check_ownership(scene_id, workspace_id)
+        """
+        try:
+            logger.debug(
+                f"Checking scene ownership - "
+                f"scene_id={scene_id}, workspace_id={workspace_id}"
+            )
+            
+            count = self.db.query(OntologyScene).filter(
+                OntologyScene.scene_id == scene_id,
+                OntologyScene.workspace_id == workspace_id
+            ).count()
+            
+            is_owner = count > 0
+            
+            logger.debug(
+                f"Scene ownership check result: {is_owner} - "
+                f"scene_id={scene_id}"
+            )
+            
+            return is_owner
+            
+        except Exception as e:
+            logger.error(
+                f"Failed to check scene ownership: {str(e)}",
+                exc_info=True
+            )
+            raise
+
+    def get_simple_list(self, workspace_id: UUID) -> List[dict]:
+        """获取场景简单列表（仅包含scene_id和scene_name，用于下拉选择）
+        
+        这是一个轻量级查询，不加载关联的classes，响应速度快。
+        
+        Args:
+            workspace_id: 工作空间ID
+            
+        Returns:
+            List[dict]: 场景简单列表，每项包含scene_id和scene_name
+            
+        Examples:
+            >>> repo = OntologySceneRepository(db)
+            >>> scenes = repo.get_simple_list(workspace_id)
+            >>> # [{"scene_id": "xxx", "scene_name": "场景1"}, ...]
+        """
+        try:
+            logger.debug(f"Getting simple scene list for workspace: {workspace_id}")
+            
+            # 只查询需要的字段，不加载关联数据
+            results = self.db.query(
+                OntologyScene.scene_id,
+                OntologyScene.scene_name
+            ).filter(
+                OntologyScene.workspace_id == workspace_id
+            ).order_by(
+                OntologyScene.updated_at.desc()
+            ).all()
+            
+            scenes = [
+                {"scene_id": str(r.scene_id), "scene_name": r.scene_name}
+                for r in results
+            ]
+            
+            logger.info(f"Found {len(scenes)} scenes (simple list) in workspace {workspace_id}")
+            
+            return scenes
+            
+        except Exception as e:
+            logger.error(
+                f"Failed to get simple scene list: {str(e)}",
+                exc_info=True
+            )
+            raise
--- a/api/app/repositories/prompt_optimizer_repository.py
+++ b/api/app/repositories/prompt_optimizer_repository.py
@@ -4,7 +4,10 @@ from sqlalchemy.orm import Session

 from app.core.logging_config import get_db_logger
 from app.models.prompt_optimizer_model import (
-    PromptOptimizerSession, PromptOptimizerSessionHistory, RoleType
+    PromptOptimizerSession,
+    PromptOptimizerSessionHistory,
+    RoleType,
+    PromptHistory
 )

 db_logger = get_db_logger()
@@ -16,6 +19,12 @@ class PromptOptimizerSessionRepository:
    def __init__(self, db: Session):
        self.db = db

+    def get_session_by_id(self, session_id: uuid.UUID) -> PromptOptimizerSession | None:
+        session = self.db.query(PromptOptimizerSession).filter(
+            PromptOptimizerSession.id == session_id,
+        ).first()
+        return session
+
    def create_session(
            self,
            tenant_id: uuid.UUID,
@@ -38,12 +47,9 @@ class PromptOptimizerSessionRepository:
                user_id=user_id,
            )
            self.db.add(session)
-            self.db.commit()
-            self.db.refresh(session)
-            db_logger.debug(f"Prompt optimization session created: ID:{session.id}")
            return session
        except Exception as e:
-            db_logger.error(f"Error creating prompt optimization session: user_id={user_id} - {str(e)}")
+            db_logger.error(f"Error creating prompt optimization session: - {str(e)}")
            raise

    def get_session_history(
@@ -71,10 +77,10 @@ class PromptOptimizerSessionRepository:
                PromptOptimizerSession.id == session_id,
                PromptOptimizerSession.user_id == user_id
            ).first()
-            
+
            if not session:
                return []
-            
+
            history = self.db.query(PromptOptimizerSessionHistory).filter(
                PromptOptimizerSessionHistory.session_id == session.id,
                PromptOptimizerSessionHistory.user_id == user_id
@@ -104,11 +110,11 @@ class PromptOptimizerSessionRepository:
                PromptOptimizerSession.user_id == user_id,
                PromptOptimizerSession.tenant_id == tenant_id
            ).first()
-            
+
            if not session:
                db_logger.error(f"Session {session_id} not found for user {user_id}")
                raise ValueError(f"Session {session_id} not found for user {user_id}")
-            
+
            message = PromptOptimizerSessionHistory(
                tenant_id=tenant_id,
                session_id=session.id,
@@ -117,8 +123,199 @@ class PromptOptimizerSessionRepository:
                content=content,
            )
            self.db.add(message)
-            self.db.commit()
+
            return message
        except Exception as e:
            db_logger.error(f"Error creating prompt optimization session history: session_id={session_id} - {str(e)}")
            raise
+
+    def get_first_user_message(self, session_id: uuid.UUID) -> str | None:
+        """
+        Get the first user message from a session.
+
+        Args:
+            session_id (uuid.UUID): The session ID.
+
+        Returns:
+            str | None: The content of the first user message, or None if not found.
+        """
+        try:
+            message = self.db.query(PromptOptimizerSessionHistory).filter(
+                PromptOptimizerSessionHistory.session_id == session_id,
+                PromptOptimizerSessionHistory.role == RoleType.USER.value
+            ).order_by(
+                PromptOptimizerSessionHistory.created_at.asc()
+            ).first()
+            
+            return message.content if message else None
+        except Exception as e:
+            db_logger.error(f"Error getting first user message: session_id={session_id} - {str(e)}")
+            raise
+
+
+class PromptReleaseRepository:
+    def __init__(self, db: Session):
+        self.db = db
+
+    def get_prompt_by_session_id(self, session_id: uuid.UUID) -> PromptHistory | None:
+        prompt_obj = self.db.query(PromptHistory).filter(
+            PromptHistory.session_id == session_id,
+            PromptHistory.is_delete.is_(False)
+        ).first()
+        return prompt_obj
+
+    def create_prompt_release(
+            self,
+            tenant_id: uuid.UUID,
+            title: str,
+            session_id: uuid.UUID,
+            prompt: str,
+    ) -> PromptHistory:
+        try:
+            prompt_obj = PromptHistory(
+                tenant_id=tenant_id,
+                title=title,
+                session_id=session_id,
+                prompt=prompt,
+            )
+            self.db.add(prompt_obj)
+            return prompt_obj
+        except Exception as e:
+            db_logger.error(f"Error creating prompt release: session_id={session_id} - {str(e)}")
+            raise
+
+    def soft_delete_prompt(self, prompt_obj: PromptHistory) -> None:
+        """
+        Soft delete a prompt release by setting is_delete flag to True.
+
+        Args:
+            prompt_obj (PromptHistory): The prompt release object to delete.
+        """
+        try:
+            prompt_obj.is_delete = True
+            db_logger.debug(f"Soft deleted prompt release: id={prompt_obj.id}, session_id={prompt_obj.session_id}")
+        except Exception as e:
+            db_logger.error(f"Error soft deleting prompt release: id={prompt_obj.id} - {str(e)}")
+            raise
+
+    def get_prompt_by_id(self, prompt_id: uuid.UUID) -> PromptHistory | None:
+        """
+        Get a prompt release by its ID.
+
+        Args:
+            prompt_id (uuid.UUID): The prompt release ID.
+
+        Returns:
+            PromptHistory | None: The prompt release object or None if not found.
+        """
+        try:
+            prompt_obj = self.db.query(PromptHistory).filter(
+                PromptHistory.id == prompt_id
+            ).first()
+            return prompt_obj
+        except Exception as e:
+            db_logger.error(f"Error getting prompt release by id: id={prompt_id} - {str(e)}")
+            raise
+
+    def count_prompts(self, tenant_id: uuid.UUID) -> int:
+        """
+        Count total number of non-deleted prompts for a tenant.
+
+        Args:
+            tenant_id (uuid.UUID): The tenant ID.
+
+        Returns:
+            int: Total count of prompts.
+        """
+        try:
+            count = self.db.query(PromptHistory).filter(
+                PromptHistory.tenant_id == tenant_id,
+                PromptHistory.is_delete.is_(False)
+            ).count()
+            return count
+        except Exception as e:
+            db_logger.error(f"Error counting prompts: tenant_id={tenant_id} - {str(e)}")
+            raise
+
+    def get_prompts_paginated(
+            self,
+            tenant_id: uuid.UUID,
+            offset: int,
+            limit: int
+    ) -> list[PromptHistory]:
+        """
+        Get paginated list of prompt releases for a tenant.
+
+        Args:
+            tenant_id (uuid.UUID): The tenant ID.
+            offset (int): Number of records to skip.
+            limit (int): Maximum number of records to return.
+
+        Returns:
+            list[PromptHistory]: List of prompt releases.
+        """
+        try:
+            prompts = self.db.query(PromptHistory).filter(
+                PromptHistory.tenant_id == tenant_id,
+                PromptHistory.is_delete.is_(False)
+            ).order_by(
+                PromptHistory.created_at.desc()
+            ).offset(offset).limit(limit).all()
+            return prompts
+        except Exception as e:
+            db_logger.error(f"Error getting paginated prompts: tenant_id={tenant_id} - {str(e)}")
+            raise
+
+    def count_prompts_by_keyword(self, tenant_id: uuid.UUID, keyword: str) -> int:
+        """
+        Count total number of non-deleted prompts matching keyword for a tenant.
+
+        Args:
+            tenant_id (uuid.UUID): The tenant ID.
+            keyword (str): Search keyword for title.
+
+        Returns:
+            int: Total count of matching prompts.
+        """
+        try:
+            count = self.db.query(PromptHistory).filter(
+                PromptHistory.tenant_id == tenant_id,
+                PromptHistory.is_delete.is_(False),
+                PromptHistory.title.ilike(f"%{keyword}%")
+            ).count()
+            return count
+        except Exception as e:
+            db_logger.error(f"Error counting prompts by keyword: tenant_id={tenant_id}, keyword={keyword} - {str(e)}")
+            raise
+
+    def search_prompts_paginated(
+            self,
+            tenant_id: uuid.UUID,
+            keyword: str,
+            offset: int,
+            limit: int
+    ) -> list[PromptHistory]:
+        """
+        Search prompt releases by keyword in title with pagination.
+
+        Args:
+            tenant_id (uuid.UUID): The tenant ID.
+            keyword (str): Search keyword for title.
+            offset (int): Number of records to skip.
+            limit (int): Maximum number of records to return.
+
+        Returns:
+            list[PromptHistory]: List of matching prompt releases.
+        """
+        try:
+            prompts = self.db.query(PromptHistory).filter(
+                PromptHistory.tenant_id == tenant_id,
+                PromptHistory.is_delete.is_(False),
+                PromptHistory.title.ilike(f"%{keyword}%")
+            ).order_by(
+                PromptHistory.created_at.desc()
+            ).offset(offset).limit(limit).all()
+            return prompts
+        except Exception as e:
+            db_logger.error(f"Error searching prompts: tenant_id={tenant_id}, keyword={keyword} - {str(e)}")
+            raise