feature: realize that annotation, collection, evaluation and synthesis are isolated according to the creator, and operators are not isolated.

Author: hefanli

runtime/datamate-python/.env.example

@@ -8,13 +8,15 @@ LOG_FILE_DIR=./logs
 RAG_STORAGE_DIR=./rag_storage
 
 # DataBase
-MYSQL_HOST=localhost
-MYSQL_PORT=3306
-MYSQL_USER=root
-MYSQL_PASSWORD=password
-MYSQL_DATABASE=datamate
+PGSQL_HOST=localhost
+PGSQL_PORT=5432
+PGSQL_USER=postgres
+PGSQL_PASSWORD=password
+PGSQL_DATABASE=datamate
 
 # Label Studio settings
-LABEL_STUDIO_BASE_URL=http://localhost:8080
+LABEL_STUDIO_BASE_URL=http://localhost:30001
 
 LABEL_STUDIO_USER_TOKEN="demo_dev_token"
+
+DATAMATE_JWT_ENABLE=false

runtime/datamate-python/app/core/config.py

@@ -75,5 +75,7 @@ def build_database_url(self):
     # DataMate
     dm_file_path_prefix: str = "/dataset"  # DM存储文件夹前缀
 
+    datamate_jwt_enable: bool = False
+
 # 全局设置实例
 settings = Settings()

runtime/datamate-python/app/db/datascope.py

@@ -0,0 +1,37 @@
+from contextvars import ContextVar
+from typing import List, Optional
+
+_current_user: ContextVar[Optional[str]] = ContextVar("_current_user", default=None)
+SYSTEM_USER = "system"
+
+
+class DataScopeHandle:
+    """
+    Hold current user info in a ContextVar and provide helpers for SQLAlchemy filters.
+    """
+
+    @staticmethod
+    def set_user_info(user: Optional[str]) -> None:
+        if user is None or user == "":
+            # set explicit None
+            _current_user.set(None)
+        else:
+            _current_user.set(user)
+
+    @staticmethod
+    def remove_user_info() -> None:
+        _current_user.set(None)
+
+    @staticmethod
+    def get_user_info() -> Optional[str]:
+        return _current_user.get()
+
+    @staticmethod
+    def allowed_users() -> List[str]:
+        """
+        Return list of allowed creators: current user + system.
+        """
+        user = DataScopeHandle.get_user_info()
+        if not user:
+            return []
+        return [user, SYSTEM_USER]

runtime/datamate-python/app/db/models/annotation_management.py

@@ -4,13 +4,14 @@
 from sqlalchemy import Column, String, Boolean, TIMESTAMP, Text, Integer, JSON, ForeignKey
 from sqlalchemy.sql import func
 
-from app.db.session import Base
+from app.db.models.base_entity import BaseEntity
 
-class AnnotationTemplate(Base):
+class AnnotationTemplate(BaseEntity):
     """标注配置模板模型"""
-    
+
     __tablename__ = "t_dm_annotation_templates"
-    
+    __ignore_data_scope__ = True
+
     id = Column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()), comment="UUID")
     name = Column(String(100), nullable=False, comment="模板名称")
     description = Column(String(500), nullable=True, comment="模板描述")
@@ -21,44 +22,40 @@ class AnnotationTemplate(Base):
     category = Column(String(50), default='custom', comment="模板分类: medical/general/custom/system")
     built_in = Column(Boolean, default=False, comment="是否系统内置模板")
     version = Column(String(20), default='1.0', comment="模板版本")
-    created_at = Column(TIMESTAMP, server_default=func.current_timestamp(), comment="创建时间")
-    updated_at = Column(TIMESTAMP, server_default=func.current_timestamp(), onupdate=func.current_timestamp(), comment="更新时间")
     deleted_at = Column(TIMESTAMP, nullable=True, comment="删除时间（软删除）")
-    
+
     def __repr__(self):
         return f"<AnnotationTemplate(id={self.id}, name={self.name}, data_type={self.data_type})>"
-    
+
     @property
     def is_deleted(self) -> bool:
         """检查是否已被软删除"""
         return self.deleted_at is not None
-    
-class LabelingProject(Base):
+
+class LabelingProject(BaseEntity):
     """标注项目模型"""
-    
+
     __tablename__ = "t_dm_labeling_projects"
-    
+
     id = Column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()), comment="UUID")
     dataset_id = Column(String(36), nullable=False, comment="数据集ID")
     name = Column(String(100), nullable=False, comment="项目名称")
     labeling_project_id = Column(String(8), nullable=False, comment="Label Studio项目ID")
     template_id = Column(String(36), ForeignKey('t_dm_annotation_templates.id', ondelete='SET NULL'), nullable=True, comment="使用的模板ID")
     configuration = Column(JSON, nullable=True, comment="项目配置（可能包含对模板的自定义修改）")
     progress = Column(JSON, nullable=True, comment="项目进度信息")
-    created_at = Column(TIMESTAMP, server_default=func.current_timestamp(), comment="创建时间")
-    updated_at = Column(TIMESTAMP, server_default=func.current_timestamp(), onupdate=func.current_timestamp(), comment="更新时间")
     deleted_at = Column(TIMESTAMP, nullable=True, comment="删除时间（软删除）")
-    
+
     def __repr__(self):
         return f"<LabelingProject(id={self.id}, name={self.name}, dataset_id={self.dataset_id})>"
-    
+
     @property
     def is_deleted(self) -> bool:
         """检查是否已被软删除"""
         return self.deleted_at is not None
 
 
-class AutoAnnotationTask(Base):
+class AutoAnnotationTask(BaseEntity):
     """自动标注任务模型，对应表 t_dm_auto_annotation_tasks"""
 
     __tablename__ = "t_dm_auto_annotation_tasks"
@@ -76,13 +73,6 @@ class AutoAnnotationTask(Base):
     detected_objects = Column(Integer, default=0, comment="检测到的对象总数")
     output_path = Column(String(500), nullable=True, comment="输出路径")
     error_message = Column(Text, nullable=True, comment="错误信息")
-    created_at = Column(TIMESTAMP, server_default=func.current_timestamp(), comment="创建时间")
-    updated_at = Column(
-        TIMESTAMP,
-        server_default=func.current_timestamp(),
-        onupdate=func.current_timestamp(),
-        comment="更新时间",
-    )
     completed_at = Column(TIMESTAMP, nullable=True, comment="完成时间")
     deleted_at = Column(TIMESTAMP, nullable=True, comment="删除时间（软删除）")
 
@@ -92,4 +82,4 @@ def __repr__(self) -> str:  # pragma: no cover - repr 简单返回
     @property
     def is_deleted(self) -> bool:
         """检查是否已被软删除"""
-        return self.deleted_at is not None
+        return self.deleted_at is not None

runtime/datamate-python/app/db/models/base_entity.py

@@ -0,0 +1,22 @@
+from sqlalchemy import Column, String, TIMESTAMP
+from sqlalchemy.orm import declarative_base
+from sqlalchemy.sql import func
+
+Base = declarative_base()
+
+
+class BaseEntity(Base):
+    """
+    Common base entity with audit fields.
+    Subclasses may set `__ignore_data_scope__ = True` to opt-out of data-scope filtering.
+    """
+    __abstract__ = True
+
+    created_at = Column(TIMESTAMP, server_default=func.current_timestamp(), comment="创建时间")
+    updated_at = Column(TIMESTAMP, server_default=func.current_timestamp(), onupdate=func.current_timestamp(),
+                        comment="更新时间")
+    created_by = Column(String(255), nullable=True, comment="创建者")
+    updated_by = Column(String(255), nullable=True, comment="更新者")
+
+    # default: do enforce data scope unless subclass sets this to True
+    __ignore_data_scope__ = False

runtime/datamate-python/app/db/models/data_collection.py

@@ -2,12 +2,14 @@
 from sqlalchemy import Column, String, Text, TIMESTAMP, Integer, BigInteger, Numeric, JSON, Boolean
 from sqlalchemy.sql import func
 
-from app.db.session import Base
+from app.db.models.base_entity import BaseEntity
 
-class CollectionTemplate(Base):
+
+class CollectionTemplate(BaseEntity):
     """归集模板表（UUID 主键） -> t_dc_collection_templates"""
 
     __tablename__ = "t_dc_collection_templates"
+    __ignore_data_scope__ = True
 
     id = Column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()), comment="模板ID（UUID）")
     name = Column(String(255), nullable=False, comment="模板名称")
@@ -18,12 +20,8 @@ class CollectionTemplate(Base):
     target_name = Column(String(64), nullable=False, comment="目标数据源名称")
     template_content = Column(JSON, nullable=False, comment="模板内容")
     built_in = Column(Boolean, default=False, comment="是否系统内置模板")
-    created_at = Column(TIMESTAMP, server_default=func.current_timestamp(), comment="创建时间")
-    updated_at = Column(TIMESTAMP, server_default=func.current_timestamp(), onupdate=func.current_timestamp(), comment="更新时间")
-    created_by = Column(String(255), nullable=True, comment="创建者")
-    updated_by = Column(String(255), nullable=True, comment="更新者")
 
-class CollectionTask(Base):
+class CollectionTask(BaseEntity):
     """归集任务表（UUID 主键） -> t_dc_collection_tasks"""
 
     __tablename__ = "t_dc_collection_tasks"
@@ -41,12 +39,8 @@ class CollectionTask(Base):
     retry_count = Column(Integer, nullable=True, server_default="3", comment="重试次数")
     timeout_seconds = Column(Integer, nullable=True, server_default="3600", comment="超时时间（秒）")
     last_execution_id = Column(String(36), nullable=True, comment="最后执行ID（UUID）")
-    created_at = Column(TIMESTAMP, server_default=func.current_timestamp(), comment="创建时间")
-    updated_at = Column(TIMESTAMP, server_default=func.current_timestamp(), onupdate=func.current_timestamp(), comment="更新时间")
-    created_by = Column(String(255), nullable=True, comment="创建者")
-    updated_by = Column(String(255), nullable=True, comment="更新者")
 
-class TaskExecution(Base):
+class TaskExecution(BaseEntity):
     """任务执行记录表（UUID 主键） -> t_dc_task_executions"""
 
     __tablename__ = "t_dc_task_executions"
@@ -60,7 +54,3 @@ class TaskExecution(Base):
     completed_at = Column(TIMESTAMP, nullable=True, comment="完成时间")
     duration_seconds = Column(Integer, nullable=True, server_default="0", comment="执行时长（秒）")
     error_message = Column(Text, nullable=True, comment="错误信息")
-    created_at = Column(TIMESTAMP, server_default=func.current_timestamp(), comment="创建时间")
-    updated_at = Column(TIMESTAMP, server_default=func.current_timestamp(), onupdate=func.current_timestamp(), comment="更新时间")
-    created_by = Column(String(255), nullable=True, comment="创建者")
-    updated_by = Column(String(255), nullable=True, comment="更新者")

runtime/datamate-python/app/db/models/data_evaluation.py

@@ -10,10 +10,10 @@
 from sqlalchemy import Column, String, Text, Float, TIMESTAMP, ForeignKey, Integer
 from sqlalchemy.sql import func
 
-from app.db.session import Base
+from app.db.models.base_entity import BaseEntity
 
 
-class EvaluationTask(Base):
+class EvaluationTask(BaseEntity):
     """评估任务表（UUID 主键） -> t_de_eval_task
 
     Columns per data-evaluation-init.sql:
@@ -36,16 +36,13 @@ class EvaluationTask(Base):
     eval_process = Column(Float, nullable=False, server_default="0", comment="评估进度")
     eval_prompt = Column(Text, nullable=True, comment="评估提示词")
     eval_config = Column(Text, nullable=True, comment="评估配置")
-    created_at = Column(TIMESTAMP, server_default=func.current_timestamp(), comment="创建时间")
-    updated_at = Column(TIMESTAMP, server_default=func.current_timestamp(), onupdate=func.current_timestamp(), comment="更新时间")
-    created_by = Column(String(255), nullable=True, comment="创建者")
-    updated_by = Column(String(255), nullable=True, comment="更新者")
 
 
-class EvaluationFile(Base):
+class EvaluationFile(BaseEntity):
     """评估条目表（UUID 主键） -> t_de_eval_file"""
 
     __tablename__ = "t_de_eval_file"
+    __ignore_data_scope__ = True
 
     id = Column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()), comment="UUID")
     task_id = Column(String(36), ForeignKey('t_de_eval_task.id'), nullable=False, comment="评估任务ID")
@@ -54,20 +51,17 @@ class EvaluationFile(Base):
     error_message = Column(Text, nullable=True, comment="错误信息")
     total_count = Column(Integer, nullable=False, default=0, comment="总数")
     evaluated_count = Column(Integer, nullable=False, default=0, comment="已评估数")
-    created_at = Column(TIMESTAMP, server_default=func.current_timestamp(), comment="创建时间")
-    updated_at = Column(TIMESTAMP, server_default=func.current_timestamp(), onupdate=func.current_timestamp(), comment="更新时间")
-    created_by = Column(String(255), nullable=True, comment="创建者")
-    updated_by = Column(String(255), nullable=True, comment="更新者")
 
 
-class EvaluationItem(Base):
+class EvaluationItem(BaseEntity):
     """评估条目表（UUID 主键） -> t_de_eval_item
 
     Columns per data-evaluation-init.sql:
       id, task_id, item_id, eval_score, eval_result, status
     """
 
     __tablename__ = "t_de_eval_item"
+    __ignore_data_scope__ = True
 
     id = Column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()), comment="UUID")
     task_id = Column(String(36), ForeignKey('t_de_eval_task.id'), nullable=False, comment="评估任务ID")
@@ -77,7 +71,3 @@ class EvaluationItem(Base):
     eval_score = Column(Float, nullable=False, server_default="0", comment="评估分数")
     eval_result = Column(Text, nullable=True, comment="评估结果")
     status = Column(String(50), server_default="PENDING", nullable=False, comment="状态：PENDING/EVALUATED")
-    created_at = Column(TIMESTAMP, server_default=func.current_timestamp(), comment="创建时间")
-    updated_at = Column(TIMESTAMP, server_default=func.current_timestamp(), onupdate=func.current_timestamp(), comment="更新时间")
-    created_by = Column(String(255), nullable=True, comment="创建者")
-    updated_by = Column(String(255), nullable=True, comment="更新者")

runtime/datamate-python/app/db/models/data_synthesis.py

@@ -2,7 +2,7 @@
 
 from sqlalchemy import Column, String, Text, Integer, JSON, TIMESTAMP, func
 
-from app.db.session import Base
+from app.db.models.base_entity import Base, BaseEntity
 from app.module.generation.schema.generation import CreateSynthesisTaskRequest
 
 
@@ -43,7 +43,7 @@ async def save_synthesis_task(db_session, synthesis_task: CreateSynthesisTaskReq
     return synth_task_instance
 
 
-class DataSynthInstance(Base):
+class DataSynthInstance(BaseEntity):
     """数据合成任务表，对应表 t_data_synth_instances
 
     create table if not exists t_data_synth_instances
@@ -82,19 +82,9 @@ class DataSynthInstance(Base):
     total_chunks = Column(Integer, nullable=False, default=0, comment="总文本块数")
     processed_chunks = Column(Integer, nullable=False, default=0, comment="已处理文本块数")
     total_synth_data = Column(Integer, nullable=False, default=0, comment="总合成数据量")
-    created_at = Column(TIMESTAMP, nullable=False, default=func.now(), comment="创建时间")
-    updated_at = Column(
-        TIMESTAMP,
-        nullable=False,
-        default=func.now(),
-        onupdate=func.now(),
-        comment="更新时间",
-    )
-    created_by = Column(String(255), nullable=True, comment="创建者")
-    updated_by = Column(String(255), nullable=True, comment="更新者")
 
 
-class DataSynthesisFileInstance(Base):
+class DataSynthesisFileInstance(BaseEntity):
     """数据合成文件任务表，对应表 t_data_synthesis_file_instances
 
     create table if not exists t_data_synthesis_file_instances (
@@ -129,17 +119,6 @@ class DataSynthesisFileInstance(Base):
     total_chunks = Column(Integer, nullable=False, default=0, comment="总文本块数")
     processed_chunks = Column(Integer, nullable=False, default=0, comment="已处理文本块数")
 
-    created_at = Column(TIMESTAMP, server_default=func.current_timestamp(), nullable=True, comment="创建时间")
-    updated_at = Column(
-        TIMESTAMP,
-        server_default=func.current_timestamp(),
-        onupdate=func.current_timestamp(),
-        nullable=True,
-        comment="更新时间",
-    )
-    created_by = Column(String(255), nullable=True, comment="创建者")
-    updated_by = Column(String(255), nullable=True, comment="更新者")
-
 
 class DataSynthesisChunkInstance(Base):
     """数据合成分块任务表，对应表 t_data_synthesis_chunk_instances