feat: File and Annotation 2-way sync implementation (#63)

* feat: Refactor configuration and sync logic for improved dataset handling and logging

* feat: Enhance annotation synchronization and dataset file management

- Added new fields `tags_updated_at` to `DatasetFiles` model for tracking the last update time of tags.
- Implemented new asynchronous methods in the Label Studio client for fetching, creating, updating, and deleting task annotations.
- Introduced bidirectional synchronization for annotations between DataMate and Label Studio, allowing for flexible data management.
- Updated sync service to handle annotation conflicts based on timestamps, ensuring data integrity during synchronization.
- Enhanced dataset file response model to include tags and their update timestamps.
- Modified database initialization script to create a new column for `tags_updated_at` in the dataset files table.
- Updated requirements to ensure compatibility with the latest dependencies.

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

@@ -1,8 +1,6 @@
 from pydantic_settings import BaseSettings
 from pydantic import model_validator
-from typing import Optional, List
-import os
-from pathlib import Path
+from typing import Optional
 
 class Settings(BaseSettings):
     """应用程序配置"""
@@ -10,39 +8,34 @@ class Settings(BaseSettings):
     class Config:
         env_file = ".env"
         case_sensitive = False
-        extra = 'ignore'  # 允许额外字段（如 Shell 脚本专用的环境变量）
+        extra = 'ignore'
 
-    # =========================
-    # Adapter 服务配置
-    # =========================
-    app_name: str = "Label Studio Adapter"
+    # Service
+    app_name: str = "DataMate Python Backend"
     app_version: str = "1.0.0"
     app_description: str = "Adapter for integrating Data Management System with Label Studio"
 
-    # 日志配置
-    log_level: str = "INFO"
-    debug: bool = True
-    log_file_dir: str = "/var/log/datamate"
-
-    # 服务器配置
     host: str = "0.0.0.0"
-    port: int = 8000
-
-    # CORS配置
+    port: int = 18000
+    
+    # CORS
     # allowed_origins: List[str] = ["*"]
     # allowed_methods: List[str] = ["*"]
     # allowed_headers: List[str] = ["*"]
 
-    # MySQL数据库配置 (优先级1)
+    # Log
+    log_level: str = "INFO"
+    debug: bool = True
+    log_file_dir: str = "/var/log/datamate"
+
+    # Database
     mysql_host: str = "datamate-database"
     mysql_port: int = 3306
     mysql_user: str = "root"
     mysql_password: str = "password"
     mysql_database: str = "datamate"
 
-    # 直接数据库URL配置（如果提供，将覆盖上述配置）
-    # 初始值为空字符串，在 model_validator 中会被设置为完整的 URL
-    database_url: str = ""
+    database_url: str = ""  # Will be overridden by build_database_url() if not provided
     
     @model_validator(mode='after')
     def build_database_url(self):
@@ -55,22 +48,18 @@ class Settings(BaseSettings):
         return self
 
 
-    # =========================
-    # Label Studio 服务配置
-    # =========================
+    # Label Studio
     label_studio_base_url: str = "http://label-studio:8000"
-    label_studio_username: Optional[str] = "admin@demo.com"  # Label Studio 用户名（用于登录）
-    label_studio_password: Optional[str] = "demoadmin"  # Label Studio 密码（用于登录）
+    label_studio_username: Optional[str] = "admin@demo.com"
+    label_studio_password: Optional[str] = "demoadmin"
     label_studio_user_token: Optional[str] = "abc123abc123"  # Legacy Token
 
-    label_studio_local_storage_dataset_base_path: str = "/label-studio/local"  # Label Studio容器中的本地存储基础路径
-    label_studio_file_path_prefix: str = "/data/local-files/?d="  # Label Studio本地文件服务路径前缀
+    label_studio_local_document_root: str = "/label-studio/local"  # Label Studio local file storage path
+    label_studio_file_path_prefix: str = "/data/local-files/?d="  # Label Studio local file serving URL prefix
 
     ls_task_page_size: int = 1000
 
-    # =========================
-    # Data Management 服务配置
-    # =========================
+    # DataMate
     dm_file_path_prefix: str = "/dataset"  # DM存储文件夹前缀
 
 # 全局设置实例