Feature/episodic memory (#70)

* [feature]episodic memory

* [feature]episodic memory

* [changes]AI review and modify code

* [feature]Explicit memory

* [feature]Explicit memory

api/app/controllers/user_memory_controllers.py

@@ -23,6 +23,8 @@ from app.schemas.memory_storage_schema import GenerateCacheRequest
 from app.schemas.user_memory_schema import (
     EpisodicMemoryOverviewRequest,
     EpisodicMemoryDetailsRequest,
+    ExplicitMemoryOverviewRequest,
+    ExplicitMemoryDetailsRequest,
 )
 
 from app.schemas.end_user_schema import (
@@ -450,8 +452,7 @@ async def get_episodic_memory_overview_api(
     获取情景记忆总览
     
     返回指定用户的所有情景记忆列表，包括标题和创建时间。
-    标题通过LLM自动生成。
+  支持通过时间范围、情景类型和标题关键词进行筛选。
-    支持通过时间范围、情景类型和标题关键词进行筛选。
     
     """
     workspace_id = current_user.current_workspace_id
@@ -541,3 +542,93 @@ async def get_episodic_memory_details_api(
     except Exception as e:
         api_logger.error(f"情景记忆详情查询失败: end_user_id={request.end_user_id}, summary_id={request.summary_id}, error={str(e)}")
         return fail(BizCode.INTERNAL_ERROR, "情景记忆详情查询失败", str(e))
+
+
+@router.post("/classifications/explicit-memory", response_model=ApiResponse)
+async def get_explicit_memory_overview_api(
+    request: ExplicitMemoryOverviewRequest,
+    current_user: User = Depends(get_current_user),
+    db: Session = Depends(get_db),
+) -> dict:
+    """
+    获取显性记忆总览
+    
+    返回指定用户的所有显性记忆列表，包括标题、完整内容、创建时间和情绪信息。
+    """
+    workspace_id = current_user.current_workspace_id
+    
+    # 检查用户是否已选择工作空间
+    if workspace_id is None:
+        api_logger.warning(f"用户 {current_user.username} 尝试查询显性记忆总览但未选择工作空间")
+        return fail(BizCode.INVALID_PARAMETER, "请先切换到一个工作空间", "current_workspace_id is None")
+    
+    api_logger.info(
+        f"显性记忆总览查询请求: end_user_id={request.end_user_id}, user={current_user.username}, "
+        f"workspace={workspace_id}"
+    )
+    
+    try:
+        # 调用Service层方法
+        result = await user_memory_service.get_explicit_memory_overview(
+            db, request.end_user_id
+        )
+        
+        api_logger.info(
+            f"成功获取显性记忆总览: end_user_id={request.end_user_id}, "
+            f"total={result['total']}"
+        )
+        return success(data=result, msg="查询成功")
+        
+    except Exception as e:
+        api_logger.error(f"显性记忆总览查询失败: end_user_id={request.end_user_id}, error={str(e)}")
+        return fail(BizCode.INTERNAL_ERROR, "显性记忆总览查询失败", str(e))
+
+
+@router.post("/classifications/explicit-memory-details", response_model=ApiResponse)
+async def get_explicit_memory_details_api(
+    request: ExplicitMemoryDetailsRequest,
+    current_user: User = Depends(get_current_user),
+    db: Session = Depends(get_db),
+) -> dict:
+    """
+    获取显性记忆详情
+    
+    根据 memory_id 返回情景记忆或语义记忆的详细信息。
+    - 情景记忆：包括标题、内容、情绪、创建时间
+    - 语义记忆：包括名称、核心定义、详细笔记、创建时间
+    """
+    workspace_id = current_user.current_workspace_id
+    
+    # 检查用户是否已选择工作空间
+    if workspace_id is None:
+        api_logger.warning(f"用户 {current_user.username} 尝试查询显性记忆详情但未选择工作空间")
+        return fail(BizCode.INVALID_PARAMETER, "请先切换到一个工作空间", "current_workspace_id is None")
+    
+    api_logger.info(
+        f"显性记忆详情查询请求: end_user_id={request.end_user_id}, memory_id={request.memory_id}, "
+        f"user={current_user.username}, workspace={workspace_id}"
+    )
+    
+    try:
+        # 调用Service层方法
+        result = await user_memory_service.get_explicit_memory_details(
+            db=db,
+            end_user_id=request.end_user_id,
+            memory_id=request.memory_id
+        )
+        
+        api_logger.info(
+            f"成功获取显性记忆详情: end_user_id={request.end_user_id}, memory_id={request.memory_id}, "
+            f"memory_type={result.get('memory_type')}"
+        )
+        return success(data=result, msg="查询成功")
+        
+    except ValueError as e:
+        # 处理记忆不存在的情况
+        api_logger.warning(f"显性记忆不存在: end_user_id={request.end_user_id}, memory_id={request.memory_id}, error={str(e)}")
+        return fail(BizCode.INVALID_PARAMETER, "显性记忆不存在", str(e))
+    except Exception as e:
+        api_logger.error(f"显性记忆详情查询失败: end_user_id={request.end_user_id}, memory_id={request.memory_id}, error={str(e)}")
+        return fail(BizCode.INTERNAL_ERROR, "显性记忆详情查询失败", str(e))
+
+

api/app/core/memory/models/graph_models.py

@@ -405,6 +405,10 @@ class ExtractedEntityNode(Node):
     statement_id: str = Field(..., description="Statement this entity was extracted from")
     entity_type: str = Field(..., description="Type of the entity")
     description: str = Field(..., description="Entity description")
+    example: str = Field(
+        default="", 
+        description="A concise example (around 20 characters) to help understand the entity"
+    )
     aliases: List[str] = Field(
         default_factory=list, 
         description="Entity aliases - alternative names for this entity"
@@ -441,6 +445,12 @@ class ExtractedEntityNode(Node):
         description="Total number of times this node has been accessed"
     )
     
+    # Explicit Memory Classification
+    is_explicit_memory: bool = Field(
+        default=False,
+        description="Whether this entity represents explicit/semantic memory (knowledge, concepts, definitions, theories, principles)"
+    )
+    
     @field_validator('aliases', mode='before')
     @classmethod
     def validate_aliases_field(cls, v): # 字段验证器 自动清理和验证 aliases 字段

api/app/core/memory/models/triplet_models.py

@@ -38,10 +38,20 @@ class Entity(BaseModel):
     name_embedding: Optional[List[float]] = Field(None, description="Embedding vector for the entity name")
     type: str = Field(..., description="Type/category of the entity")
     description: str = Field(..., description="Description of the entity")
+    example: str = Field(
+        default="",
+        description="A concise example (around 20 characters) to help understand the entity"
+    )
     aliases: List[str] = Field(
         default_factory=list,
         description="Alternative names for this entity (abbreviations, full names, translations, etc.)"
     )
+    
+    # Explicit Memory Classification
+    is_explicit_memory: bool = Field(
+        default=False,
+        description="Whether this entity represents explicit/semantic memory (knowledge, concepts, definitions, theories, principles)"
+    )
 
 
 class Triplet(BaseModel):

api/app/core/memory/storage_services/extraction_engine/extraction_orchestrator.py

@@ -42,7 +42,6 @@ from app.core.memory.storage_services.extraction_engine.deduplication.two_stage_
 )
 from app.core.memory.storage_services.extraction_engine.knowledge_extraction.embedding_generation import (
     embedding_generation,
-    embedding_generation_all,
     generate_entity_embeddings_from_triplets,
 )
 
@@ -179,7 +178,7 @@ class ExtractionOrchestrator:
             for dialog in dialog_data_list:
                 for chunk in dialog.chunks:
                     all_statements_list.extend(chunk.statements)
-            total_statements = len(all_statements_list)
+            len(all_statements_list)
 
             # 步骤 2: 并行执行三元组提取、时间信息提取、情绪提取和基础嵌入生成
             logger.info("步骤 2/6: 并行执行三元组提取、时间信息提取、情绪提取和嵌入生成")
@@ -201,9 +200,9 @@ class ExtractionOrchestrator:
                         all_entities_list.extend(triplet_info.entities)
                         all_triplets_list.extend(triplet_info.triplets)
             
-            total_entities = len(all_entities_list)
+            len(all_entities_list)
-            total_triplets = len(all_triplets_list)
+            len(all_triplets_list)
-            total_temporal = sum(len(temporal_map) for temporal_map in temporal_maps)
+            sum(len(temporal_map) for temporal_map in temporal_maps)
 
             # 步骤 3: 生成实体嵌入（依赖三元组提取结果）
             logger.info("步骤 3/6: 生成实体嵌入")
@@ -385,7 +384,7 @@ class ExtractionOrchestrator:
         
         # 用于跟踪已完成的陈述句数量
         completed_statements = 0
-        total_statements = len(all_statements)
+        len(all_statements)
 
         # 全局并行处理所有陈述句
         async def extract_for_statement(stmt_data, stmt_index):
@@ -497,7 +496,7 @@ class ExtractionOrchestrator:
         
         # 用于跟踪已完成的时间提取数量
         completed_temporal = 0
-        total_temporal_statements = len(all_statements)
+        len(all_statements)
 
         # 全局并行处理所有陈述句
         async def extract_for_statement(stmt_data, stmt_index):
@@ -1082,10 +1081,12 @@ class ExtractionOrchestrator:
                                     statement_id=statement.id,  # 添加必需的 statement_id 字段
                                     entity_type=getattr(entity, 'type', 'unknown'),  # 使用 type 而不是 entity_type
                                     description=getattr(entity, 'description', ''),  # 添加必需的 description 字段
+                                    example=getattr(entity, 'example', ''),  # 新增：传递示例字段
                                     fact_summary=getattr(entity, 'fact_summary', ''),  # 添加必需的 fact_summary 字段
                                     connect_strength=entity_connect_strength if entity_connect_strength is not None else 'Strong',  # 添加必需的 connect_strength 字段
                                     aliases=getattr(entity, 'aliases', []) or [],  # 传递从三元组提取阶段获取的aliases
                                     name_embedding=getattr(entity, 'name_embedding', None),
+                                    is_explicit_memory=getattr(entity, 'is_explicit_memory', False),  # 新增：传递语义记忆标记
                                     group_id=dialog_data.group_id,
                                     user_id=dialog_data.user_id,
                                     apply_id=dialog_data.apply_id,

api/app/core/memory/utils/prompt/prompts/extract_triplet.jinja2

@@ -12,7 +12,34 @@ Extract entities and knowledge triplets from the given statement.
 ===Guidelines===
 
 **Entity Extraction:**
-- Extract entities with their types, context-independent descriptions, and aliases
+- Extract entities with their types, context-independent descriptions, **concise examples**, aliases, and semantic memory classification
+- **Semantic Memory Classification (is_explicit_memory):**
+  * Set to `true` if the entity represents **explicit/semantic memory**:
+    - **Concepts:** "Machine Learning", "Photosynthesis", "Democracy", "人工智能", "光合作用", "民主"
+    - **Knowledge:** "Python Programming Language", "Theory of Relativity", "Python编程语言", "相对论"
+    - **Definitions:** "API (Application Programming Interface)", "REST API", "应用程序接口"
+    - **Principles:** "SOLID Principles", "First Law of Thermodynamics", "SOLID原则", "热力学第一定律"
+    - **Theories:** "Evolution Theory", "Quantum Mechanics", "进化论", "量子力学"
+    - **Methods/Techniques:** "Agile Development", "Machine Learning Algorithm", "敏捷开发", "机器学习算法"
+    - **Technical Terms:** "Neural Network", "Database", "神经网络", "数据库"
+  * Set to `false` for:
+    - **People:** "John Smith", "Dr. Wang", "张明", "王博士"
+    - **Organizations:** "Microsoft", "Harvard University", "微软", "哈佛大学"
+    - **Locations:** "Beijing", "Central Park", "北京", "中央公园"
+    - **Events:** "2024 Conference", "Project Meeting", "2024会议", "项目会议"
+    - **Specific objects:** "iPhone 15", "Building A", "iPhone 15", "A栋"
+- **Example Generation (IMPORTANT for semantic memory entities):**
+  * For entities where `is_explicit_memory=true`, generate a **concise example (around 20 characters)** to help understand the concept
+  * The example should be:
+    - **Specific and concrete**: Use real-world scenarios or applications
+    - **Brief**: Around 20 characters (can be slightly longer if needed for clarity)
+    - **In the same language as the entity name**
+  * Examples:
+    - Entity: "机器学习" → example: "如：用神经网络识别图片中的猫狗"
+    - Entity: "SOLID Principles" → example: "e.g., Single Responsibility, Open-Closed"
+    - Entity: "Photosynthesis" → example: "e.g., plants convert sunlight to energy"
+    - Entity: "人工智能" → example: "如：智能客服、自动驾驶"
+  * For non-semantic entities (`is_explicit_memory=false`), the example field can be empty
 - **Aliases Extraction (Important):**
   * **CRITICAL: Extract aliases ONLY in the SAME LANGUAGE as the input text**
   * **DO NOT translate or add aliases in different languages**
@@ -84,21 +111,27 @@ Output:
       "name": "I",
       "type": "Person",
       "description": "The user",
-      "aliases": []
+      "example": "",
+      "aliases": [],
+      "is_explicit_memory": false
     },
     {
       "entity_idx": 1,
       "name": "Paris",
       "type": "Location",
       "description": "Capital city of France",
-      "aliases": []
+      "example": "",
+      "aliases": [],
+      "is_explicit_memory": false
     },
     {
       "entity_idx": 2,
       "name": "Louvre",
       "type": "Location",
       "description": "World-famous museum located in Paris",
-      "aliases": ["Louvre Museum"]
+      "example": "",
+      "aliases": ["Louvre Museum"],
+      "is_explicit_memory": false
     }
   ]
 }
@@ -130,21 +163,27 @@ Output:
       "name": "John Smith",
       "type": "Person",
       "description": "Individual person name",
-      "aliases": []
+      "example": "",
+      "aliases": [],
+      "is_explicit_memory": false
     },
     {
       "entity_idx": 1,
       "name": "Google",
       "type": "Organization",
       "description": "American technology company",
-      "aliases": ["Google LLC", "Alphabet Inc."]
+      "example": "",
+      "aliases": ["Google LLC", "Alphabet Inc."],
+      "is_explicit_memory": false
     },
     {
       "entity_idx": 2,
       "name": "AI product development",
-      "type": "WorkRole",
+      "type": "Concept",
       "description": "Artificial intelligence product development work",
-      "aliases": []
+      "example": "e.g., developing chatbots, recommendation systems",
+      "aliases": [],
+      "is_explicit_memory": true
     }
   ]
 }
@@ -176,21 +215,27 @@ Output:
       "name": "我",
       "type": "Person",
       "description": "用户本人",
-      "aliases": []
+      "example": "",
+      "aliases": [],
+      "is_explicit_memory": false
     },
     {
       "entity_idx": 1,
       "name": "巴黎",
       "type": "Location",
       "description": "法国首都城市",
-      "aliases": []
+      "example": "",
+      "aliases": [],
+      "is_explicit_memory": false
     },
     {
       "entity_idx": 2,
       "name": "卢浮宫",
       "type": "Location",
       "description": "位于巴黎的世界著名博物馆",
-      "aliases": []
+      "example": "",
+      "aliases": [],
+      "is_explicit_memory": false
     }
   ]
 }
@@ -222,21 +267,27 @@ Output:
       "name": "张明",
       "type": "Person",
       "description": "个人姓名",
-      "aliases": []
+      "example": "",
+      "aliases": [],
+      "is_explicit_memory": false
     },
     {
       "entity_idx": 1,
       "name": "腾讯",
       "type": "Organization",
       "description": "中国科技公司",
-      "aliases": ["腾讯控股", "腾讯公司"]
+      "example": "",
+      "aliases": ["腾讯控股", "腾讯公司"],
+      "is_explicit_memory": false
     },
     {
       "entity_idx": 2,
       "name": "AI产品开发",
-      "type": "WorkRole",
+      "type": "Concept",
       "description": "人工智能产品研发工作",
-      "aliases": []
+      "example": "如：开发智能客服机器人、推荐系统",
+      "aliases": [],
+      "is_explicit_memory": true
     }
   ]
 }
@@ -251,7 +302,9 @@ Output:
       "name": "Tripod",
       "type": "Equipment",
       "description": "Photography equipment accessory",
-      "aliases": ["Camera Tripod"]
+      "example": "",
+      "aliases": ["Camera Tripod"],
+      "is_explicit_memory": false
     }
   ]
 }
@@ -266,7 +319,9 @@ Output:
       "name": "三脚架",
       "type": "Equipment",
       "description": "摄影器材配件",
-      "aliases": ["相机三脚架"]
+      "example": "",
+      "aliases": ["相机三脚架"],
+      "is_explicit_memory": false
     }
   ]
 }

api/app/repositories/neo4j/cypher_queries.py

@@ -92,6 +92,11 @@ SET e.name = CASE WHEN entity.name IS NOT NULL AND entity.name <> '' THEN entity
         WHEN entity.description IS NOT NULL AND entity.description <> ''
          AND (e.description IS NULL OR size(e.description) = 0 OR size(entity.description) > size(e.description))
         THEN entity.description ELSE e.description END,
+    e.example = CASE 
+        WHEN entity.example IS NOT NULL AND entity.example <> '' 
+        THEN entity.example 
+        ELSE coalesce(e.example, '') 
+    END,
     e.statement_id = CASE WHEN entity.statement_id IS NOT NULL AND entity.statement_id <> '' THEN entity.statement_id ELSE e.statement_id END,
     e.aliases = CASE
         WHEN entity.aliases IS NOT NULL AND size(entity.aliases) > 0
@@ -121,7 +126,8 @@ SET e.name = CASE WHEN entity.name IS NOT NULL AND entity.name <> '' THEN entity
     e.activation_value = CASE WHEN entity.activation_value IS NOT NULL THEN entity.activation_value ELSE e.activation_value END,
     e.access_history = CASE WHEN entity.access_history IS NOT NULL THEN entity.access_history ELSE coalesce(e.access_history, []) END,
     e.last_access_time = CASE WHEN entity.last_access_time IS NOT NULL THEN entity.last_access_time ELSE e.last_access_time END,
-    e.access_count = CASE WHEN entity.access_count IS NOT NULL THEN entity.access_count ELSE coalesce(e.access_count, 0) END
+    e.access_count = CASE WHEN entity.access_count IS NOT NULL THEN entity.access_count ELSE coalesce(e.access_count, 0) END,
+    e.is_explicit_memory = CASE WHEN entity.is_explicit_memory IS NOT NULL THEN entity.is_explicit_memory ELSE coalesce(e.is_explicit_memory, false) END
 RETURN e.id AS uuid
 """
 

api/app/schemas/user_memory_schema.py

@@ -28,3 +28,16 @@ class EpisodicMemoryDetailsRequest(BaseModel):
     
     end_user_id: str = Field(..., description="终端用户ID")
     summary_id: str = Field(..., description="情景记忆摘要ID")
+
+
+class ExplicitMemoryOverviewRequest(BaseModel):
+    """显性记忆总览查询请求"""
+    
+    end_user_id: str = Field(..., description="终端用户ID")
+
+
+class ExplicitMemoryDetailsRequest(BaseModel):
+    """显性记忆详情查询请求"""
+    
+    end_user_id: str = Field(..., description="终端用户ID")
+    memory_id: str = Field(..., description="记忆ID（情景记忆或语义记忆的ID）")

api/app/services/user_memory_service.py

@@ -1441,12 +1441,308 @@ class UserMemoryService:
             
             return details
             
-        except ValueError as e:
+        except ValueError:
             # 重新抛出ValueError，让Controller层处理
             raise
         except Exception as e:
             logger.error(f"获取情景记忆详情时出错: {str(e)}", exc_info=True)
             raise
+    
+    async def get_explicit_memory_overview(
+        self,
+        db: Session,
+        end_user_id: str
+    ) -> Dict[str, Any]:
+        """
+        获取显性记忆总览信息
+        
+        返回两部分：
+        1. 情景记忆（episodic_memories）- 来自MemorySummary节点
+        2. 语义记忆（semantic_memories）- 来自ExtractedEntity节点（is_explicit_memory=true）
+        
+        Args:
+            db: 数据库会话
+            end_user_id: 终端用户ID
+        
+        Returns:
+            {
+                "total": int,
+                "episodic_memories": [
+                    {
+                        "id": str,
+                        "title": str,
+                        "content": str,
+                        "created_at": int,
+                        "emotion": Dict
+                    }
+                ],
+                "semantic_memories": [
+                    {
+                        "id": str,
+                        "name": str,
+                        "entity_type": str,
+                        "core_definition": str,
+                        "detailed_notes": str,
+                        "created_at": int
+                    }
+                ]
+            }
+        """
+        try:
+            logger.info(f"开始查询 end_user_id={end_user_id} 的显性记忆总览（情景记忆+语义记忆）")
+            
+            # ========== 1. 查询情景记忆（MemorySummary节点） ==========
+            episodic_query = """
+            MATCH (s:MemorySummary)
+            WHERE s.group_id = $group_id
+            RETURN elementId(s) AS id, 
+                   s.name AS title,
+                   s.content AS content,
+                   s.created_at AS created_at
+            ORDER BY s.created_at DESC
+            """
+            
+            episodic_result = await self.neo4j_connector.execute_query(
+                episodic_query, 
+                group_id=end_user_id
+            )
+            
+            # 处理情景记忆数据
+            episodic_memories = []
+            if episodic_result:
+                for record in episodic_result:
+                    summary_id = record["id"]
+                    title = record.get("title") or "未命名"
+                    content = record.get("content") or ""
+                    created_at_str = record.get("created_at")
+                    
+                    # 转换时间戳
+                    created_at_timestamp = None
+                    if created_at_str:
+                        try:
+                            from datetime import datetime
+                            dt_object = datetime.fromisoformat(created_at_str.replace("Z", "+00:00"))
+                            created_at_timestamp = int(dt_object.timestamp() * 1000)
+                        except (ValueError, TypeError, AttributeError) as e:
+                            logger.warning(f"无法解析时间戳: {created_at_str}, error={str(e)}")
+                    
+                    # 注意：总览接口不返回 emotion 字段
+                    episodic_memories.append({
+                        "id": summary_id,
+                        "title": title,
+                        "content": content,
+                        "created_at": created_at_timestamp
+                    })
+            
+            # ========== 2. 查询语义记忆（ExtractedEntity节点） ==========
+            semantic_query = """
+            MATCH (e:ExtractedEntity)
+            WHERE e.group_id = $group_id 
+              AND e.is_explicit_memory = true
+            RETURN elementId(e) AS id, 
+                   e.name AS name,
+                   e.entity_type AS entity_type,
+                   e.description AS core_definition,
+                   e.example AS detailed_notes,
+                   e.created_at AS created_at
+            ORDER BY e.created_at DESC
+            """
+            
+            semantic_result = await self.neo4j_connector.execute_query(
+                semantic_query, 
+                group_id=end_user_id
+            )
+            
+            # 处理语义记忆数据
+            semantic_memories = []
+            if semantic_result:
+                for record in semantic_result:
+                    entity_id = record["id"]
+                    name = record.get("name") or "未命名"
+                    entity_type = record.get("entity_type") or "未分类"
+                    core_definition = record.get("core_definition") or ""
+                    created_at_str = record.get("created_at")
+                    
+                    # 转换时间戳
+                    created_at_timestamp = None
+                    if created_at_str:
+                        try:
+                            from datetime import datetime
+                            dt_object = datetime.fromisoformat(created_at_str.replace("Z", "+00:00"))
+                            created_at_timestamp = int(dt_object.timestamp() * 1000)
+                        except (ValueError, TypeError, AttributeError) as e:
+                            logger.warning(f"无法解析时间戳: {created_at_str}, error={str(e)}")
+                    
+                    # 注意：总览接口不返回 detailed_notes 字段
+                    semantic_memories.append({
+                        "id": entity_id,
+                        "name": name,
+                        "entity_type": entity_type,
+                        "core_definition": core_definition,
+                        "created_at": created_at_timestamp
+                    })
+            
+            # ========== 3. 返回结果 ==========
+            total_count = len(episodic_memories) + len(semantic_memories)
+            
+            logger.info(
+                f"成功获取 end_user_id={end_user_id} 的显性记忆总览，"
+                f"情景记忆={len(episodic_memories)} 条，语义记忆={len(semantic_memories)} 条，"
+                f"总计 {total_count} 条"
+            )
+            
+            return {
+                "total": total_count,
+                "episodic_memories": episodic_memories,
+                "semantic_memories": semantic_memories
+            }
+            
+        except Exception as e:
+            logger.error(f"获取显性记忆总览时出错: {str(e)}", exc_info=True)
+            raise
+
+    async def get_explicit_memory_details(
+        self,
+        db: Session,
+        end_user_id: str,
+        memory_id: str
+    ) -> Dict[str, Any]:
+        """
+        获取显性记忆详情
+        
+        根据 memory_id 查询情景记忆或语义记忆的详细信息。
+        先尝试查询情景记忆，如果找不到再查询语义记忆。
+        
+        Args:
+            db: 数据库会话
+            end_user_id: 终端用户ID
+            memory_id: 记忆ID（可以是情景记忆或语义记忆的ID）
+        
+        Returns:
+            情景记忆返回：
+            {
+                "memory_type": "episodic",
+                "title": str,
+                "content": str,
+                "emotion": Dict,
+                "created_at": int
+            }
+            
+            语义记忆返回：
+            {
+                "memory_type": "semantic",
+                "name": str,
+                "core_definition": str,
+                "detailed_notes": str,
+                "created_at": int
+            }
+        
+        Raises:
+            ValueError: 当记忆不存在时
+        """
+        try:
+            logger.info(f"开始查询显性记忆详情: end_user_id={end_user_id}, memory_id={memory_id}")
+            
+            # ========== 1. 先尝试查询情景记忆 ==========
+            episodic_query = """
+            MATCH (s:MemorySummary)
+            WHERE elementId(s) = $memory_id AND s.group_id = $group_id
+            RETURN s.name AS title,
+                   s.content AS content,
+                   s.created_at AS created_at
+            """
+            
+            episodic_result = await self.neo4j_connector.execute_query(
+                episodic_query,
+                memory_id=memory_id,
+                group_id=end_user_id
+            )
+            
+            if episodic_result and len(episodic_result) > 0:
+                record = episodic_result[0]
+                title = record.get("title") or "未命名"
+                content = record.get("content") or ""
+                created_at_str = record.get("created_at")
+                
+                # 转换时间戳
+                created_at_timestamp = None
+                if created_at_str:
+                    try:
+                        from datetime import datetime
+                        dt_object = datetime.fromisoformat(created_at_str.replace("Z", "+00:00"))
+                        created_at_timestamp = int(dt_object.timestamp() * 1000)
+                    except (ValueError, TypeError, AttributeError) as e:
+                        logger.warning(f"无法解析时间戳: {created_at_str}, error={str(e)}")
+                
+                # 获取情绪信息
+                emotion = await self._extract_episodic_emotion(
+                    summary_id=memory_id,
+                    end_user_id=end_user_id
+                )
+                
+                logger.info(f"成功获取情景记忆详情: memory_id={memory_id}")
+                return {
+                    "memory_type": "episodic",
+                    "title": title,
+                    "content": content,
+                    "emotion": emotion,
+                    "created_at": created_at_timestamp
+                }
+            
+            # ========== 2. 如果不是情景记忆，尝试查询语义记忆 ==========
+            semantic_query = """
+            MATCH (e:ExtractedEntity)
+            WHERE elementId(e) = $memory_id 
+              AND e.group_id = $group_id 
+              AND e.is_explicit_memory = true
+            RETURN e.name AS name,
+                   e.description AS core_definition,
+                   e.example AS detailed_notes,
+                   e.created_at AS created_at
+            """
+            
+            semantic_result = await self.neo4j_connector.execute_query(
+                semantic_query,
+                memory_id=memory_id,
+                group_id=end_user_id
+            )
+            
+            if semantic_result and len(semantic_result) > 0:
+                record = semantic_result[0]
+                name = record.get("name") or "未命名"
+                core_definition = record.get("core_definition") or ""
+                detailed_notes = record.get("detailed_notes") or ""
+                created_at_str = record.get("created_at")
+                
+                # 转换时间戳
+                created_at_timestamp = None
+                if created_at_str:
+                    try:
+                        from datetime import datetime
+                        dt_object = datetime.fromisoformat(created_at_str.replace("Z", "+00:00"))
+                        created_at_timestamp = int(dt_object.timestamp() * 1000)
+                    except (ValueError, TypeError, AttributeError) as e:
+                        logger.warning(f"无法解析时间戳: {created_at_str}, error={str(e)}")
+                
+                logger.info(f"成功获取语义记忆详情: memory_id={memory_id}")
+                return {
+                    "memory_type": "semantic",
+                    "name": name,
+                    "core_definition": core_definition,
+                    "detailed_notes": detailed_notes,
+                    "created_at": created_at_timestamp
+                }
+            
+            # ========== 3. 两种记忆都找不到 ==========
+            logger.warning(f"记忆不存在: memory_id={memory_id}, end_user_id={end_user_id}")
+            raise ValueError(f"记忆不存在: memory_id={memory_id}")
+            
+        except ValueError:
+            # 重新抛出 ValueError（记忆不存在）
+            raise
+        except Exception as e:
+            logger.error(f"获取显性记忆详情时出错: {str(e)}", exc_info=True)
+            raise
 
 
 # 独立的分析函数