♻️ Translate error messages and Chinese comments in backend code into English #1131

Author: Mermaid97

backend/agents/create_agent_info.py

@@ -79,7 +79,7 @@ async def create_agent_config(
         is_manager=len(managed_agents) > 0, language=language)
 
     # Get app information
-    default_app_description = 'Nexent 是一个开源智能体SDK和平台' if language == 'zh' else 'Nexent is an open-source agent SDK and platform'
+    default_app_description = 'Nexent is an open-source agent SDK and platform' if language == 'en' else 'Nexent 是一个开源智能体SDK和平台'
     app_name = tenant_config_manager.get_app_config(
         'APP_NAME', tenant_id=tenant_id) or "Nexent"
     app_description = tenant_config_manager.get_app_config(
@@ -132,7 +132,7 @@ async def create_agent_config(
                                 f"Failed to get summary for knowledge base {knowledge_name}: {e}")
                 else:
                     # TODO: Prompt should be refactored to yaml file
-                    knowledge_base_summary = "当前没有可用的知识库索引。\n" if language == 'zh' else "No knowledge base indexes are currently available.\n"
+                    knowledge_base_summary = "No knowledge base indexes are currently available.\n" if language == 'en' else "当前没有可用的知识库索引。\n"
                 break  # Only process the first KnowledgeBaseSearchTool found
     except Exception as e:
         logger.error(f"Failed to build knowledge base summary: {e}")

backend/apps/file_management_app.py

@@ -436,9 +436,9 @@ async def process_text_file(query, filename, file_content, tenant_id: str, langu
             result = response.json()
             raw_text = result.get("text", "")
             logger.info(
-                f"File processed successfully: {raw_text[:200]}...{raw_text[-200:]}...， length: {len(raw_text)}")
+                f"File processed successfully: {raw_text[:200]}...{raw_text[-200:]}..., length: {len(raw_text)}")
         else:
-            error_detail = response.json().get('detail', '未知错误') if response.headers.get(
+            error_detail = response.json().get('detail', 'Unknown error') if response.headers.get(
                 'content-type', '').startswith('application/json') else response.text
             logger.error(
                 f"File processing failed (status code: {response.status_code}): {error_detail}")

backend/apps/model_managment_app.py

@@ -115,7 +115,8 @@ async def create_provider_model(request: ProviderModelRequest, authorization: Op
         model_list = await get_provider_models(model_data)
 
         # Merge existing model's max_tokens attribute
-        model_list = merge_existing_model_tokens(model_list, tenant_id, request.provider, request.model_type)
+        model_list = merge_existing_model_tokens(
+            model_list, tenant_id, request.provider, request.model_type)
 
         # Sort model list by ID
         model_list = sort_models_by_id(model_list)
@@ -164,7 +165,8 @@ async def batch_create_models(request: BatchCreateModelsRequest, authorization:
                     existing_max_tokens = existing_model_by_display["max_tokens"]
                     new_max_tokens = model["max_tokens"]
                     if existing_max_tokens != new_max_tokens:
-                        update_model_record(existing_model_by_display["model_id"], {"max_tokens": new_max_tokens}, user_id)
+                        update_model_record(existing_model_by_display["model_id"], {
+                                            "max_tokens": new_max_tokens}, user_id)
                     continue
 
             model_dict = await prepare_model_dict(
@@ -267,7 +269,7 @@ async def delete_model(display_name: str = Query(..., embed=True), authorization
     If the model is an embedding or multi_embedding type, both types will be deleted
 
     Args:
-        display_name: Display name of the model to delete (唯一键)
+        display_name: Display name of the model to delete (unique key)
         authorization: Authorization header
     """
     try:
@@ -282,10 +284,10 @@ async def delete_model(display_name: str = Query(..., embed=True), authorization
                 message=f"Model not found: {display_name}",
                 data=None
             )
-        # 支持 embedding/multi_embedding 互删
+        # Support mutual deletion of embedding/multi_embedding
         deleted_types = []
         if model["model_type"] in ["embedding", "multi_embedding"]:
-            # 查找所有 embedding/multi_embedding 且 display_name 相同的模型
+            # Find all embedding/multi_embedding models with the same display_name
             for t in ["embedding", "multi_embedding"]:
                 m = get_model_by_display_name(display_name, tenant_id)
                 if m and m["model_type"] == t:

backend/consts/model.py

@@ -25,7 +25,7 @@ def get_value(cls, status: Optional[str]) -> str:
         return status
 
 
-# 用户认证相关请求模型
+# User authentication related request models
 class UserSignUpRequest(BaseModel):
     """User registration request model"""
     email: EmailStr

backend/database/utils.py

@@ -1,17 +1,17 @@
 from typing import Any, Dict
 
 
-# 全局追踪字段管理方法
+# Global tracking field management methods
 def add_creation_tracking(data: Dict[str, Any], user_id: str) -> Dict[str, Any]:
     """
-    添加创建追踪字段（created_by和updated_by）
+    Add creation tracking fields (created_by and updated_by)
 
     Args:
-        data: 要添加字段的数据字典
-        user_id: 当前用户ID
+        data: Data dictionary to add fields to
+        user_id: Current user ID
 
     Returns:
-        Dict[str, Any]: 添加追踪字段后的数据字典
+        Dict[str, Any]: Data dictionary with tracking fields added
     """
     data_copy = data.copy()
     data_copy["created_by"] = user_id
@@ -21,14 +21,14 @@ def add_creation_tracking(data: Dict[str, Any], user_id: str) -> Dict[str, Any]:
 
 def add_update_tracking(data: Dict[str, Any], user_id: str) -> Dict[str, Any]:
     """
-    添加更新追踪字段（updated_by）
+    Add update tracking field (updated_by)
 
     Args:
-        data: 要添加字段的数据字典
-        user_id: 当前用户ID
+        data: Data dictionary to add field to
+        user_id: Current user ID
 
     Returns:
-        Dict[str, Any]: 添加追踪字段后的数据字典
+        Dict[str, Any]: Data dictionary with tracking field added
     """
     data_copy = data.copy()
     data_copy["updated_by"] = user_id

backend/services/data_process_service.py

@@ -65,7 +65,8 @@ def _init_redis_client(self):
                     connection_pool=self.redis_pool)
                 logger.info("Redis client initialized successfully.")
             else:
-                logger.warning("REDIS_BACKEND_URL not set, Redis client not initialized.")
+                logger.warning(
+                    "REDIS_BACKEND_URL not set, Redis client not initialized.")
         except Exception as e:
             logger.error(f"Failed to initialize Redis client: {str(e)}")
 
@@ -82,7 +83,8 @@ def _init_clip_model(self):
             self.clip_available = True
             logger.info("CLIP model loaded successfully")
         except Exception as e:
-            logger.warning(f"Failed to load CLIP model, size-only filtering will be used: {str(e)}")
+            logger.warning(
+                f"Failed to load CLIP model, size-only filtering will be used: {str(e)}")
             self.clip_available = False
 
     async def start(self):
@@ -102,7 +104,8 @@ def _get_celery_inspector(self):
             if not celery_app.conf.broker_url or not celery_app.conf.result_backend:
                 celery_app.conf.broker_url = REDIS_URL
                 celery_app.conf.result_backend = REDIS_BACKEND_URL
-                logger.warning(f"Celery broker URL is not configured properly, reconfiguring to {celery_app.conf.broker_url}")
+                logger.warning(
+                    f"Celery broker URL is not configured properly, reconfiguring to {celery_app.conf.broker_url}")
             try:
                 inspector = celery_app.control.inspect()
                 inspector.ping()
@@ -176,8 +179,10 @@ def get_reserved():
                     # Add to the set, duplicates will be handled
                     task_ids.add(task_id)
             except Exception as redis_error:
-                logger.warning(f"Failed to query Redis for stored task IDs: {str(redis_error)}")
-            logger.debug(f"Total unique task IDs collected (inspector + Redis): {len(task_ids)}")
+                logger.warning(
+                    f"Failed to query Redis for stored task IDs: {str(redis_error)}")
+            logger.debug(
+                f"Total unique task IDs collected (inspector + Redis): {len(task_ids)}")
             tasks = [get_task_info(task_id) for task_id in task_ids]
             all_task_infos = await asyncio.gather(*tasks, return_exceptions=True)
             for task_info in all_task_infos:
@@ -366,7 +371,7 @@ async def filter_important_image(self, image_url: str, positive_prompt: str = "a
                     }
                 }
 
-            # 延迟加载CLIP模型
+            # Lazy load CLIP model
             if not self.clip_available:
                 self._init_clip_model()
 

backend/services/prompt_service.py

@@ -237,8 +237,8 @@ def _stream_results(produce_queue, latest, stop_flags, threads):
 
 
 def join_info_for_generate_system_prompt(prompt_for_generate, sub_agent_info_list, task_description, tool_info_list, language: str = 'zh'):
-    input_label = "接受输入" if language == 'zh' else "Inputs"
-    output_label = "返回输出类型" if language == 'zh' else "Output type"
+    input_label = "Inputs" if language == 'en' else "接受输入"
+    output_label = "Output type" if language == 'en' else "返回输出类型"
 
     tool_description = "\n".join(
         [f"- {tool['name']}: {tool['description']} \n {input_label}: {tool['inputs']}\n {output_label}: {tool['output_type']}"

backend/utils/auth_utils.py

@@ -16,7 +16,7 @@
 # Get Supabase configuration
 SUPABASE_URL = os.getenv('SUPABASE_URL', 'http://118.31.249.152:8010')
 SUPABASE_KEY = os.getenv('SUPABASE_KEY', '')
-# 调试用 JWT 过期时间（秒），未设置或为 0 表示不生效
+# Debug JWT expiration time (seconds), not set or 0 means not effective
 DEBUG_JWT_EXPIRE_SECONDS = int(os.getenv('DEBUG_JWT_EXPIRE_SECONDS', '0') or 0)
 
 # Module logger
@@ -115,7 +115,8 @@ def verify_aksk_signature(
             raise SignatureValidationError("Timestamp is invalid or expired")
 
         # TODO: get ak/sk according to tenant_id from DB
-        mock_access_key, mock_secret_key = get_aksk_config(tenant_id="tenant_id")
+        mock_access_key, mock_secret_key = get_aksk_config(
+            tenant_id="tenant_id")
 
         if access_key != mock_access_key:
             logger.warning(f"Invalid access key: {access_key}")
@@ -199,62 +200,64 @@ def validate_aksk_authentication(headers: dict, request_body: str = "") -> bool:
         logger.error(f"Unexpected error during AK/SK authentication: {e}")
         raise UnauthorizedError("Authentication failed")
 
+
 def get_supabase_client():
     """Get Supabase client instance"""
     try:
         return create_client(SUPABASE_URL, SUPABASE_KEY)
     except Exception as e:
-        logging.error(f"创建Supabase客户端失败: {str(e)}")
+        logging.error(f"Failed to create Supabase client: {str(e)}")
         return None
 
 
 def get_jwt_expiry_seconds(token: str) -> int:
     """
-    从JWT令牌中获取过期时间（秒）
+    Get expiration time from JWT token (seconds)
 
     Args:
-        token: JWT令牌字符串
+        token: JWT token string
 
     Returns:
-        int: 令牌的有效期（秒），如果解析失败则返回默认值3600
+        int: Token validity period (seconds), returns default value 3600 if parsing fails
     """
     try:
         # Speed mode: treat sessions as never expiring
         if IS_SPEED_MODE:
             # 10 years in seconds
             return 10 * 365 * 24 * 60 * 60
-        # 确保token是纯JWT，去除可能的Bearer前缀
-        jwt_token = token.replace("Bearer ", "") if token.startswith("Bearer ") else token
+        # Ensure token is pure JWT, remove possible Bearer prefix
+        jwt_token = token.replace(
+            "Bearer ", "") if token.startswith("Bearer ") else token
 
-        # 如果设置了调试过期时间，直接返回以便快速调试
+        # If debug expiration time is set, return directly for quick debugging
         if DEBUG_JWT_EXPIRE_SECONDS > 0:
             return DEBUG_JWT_EXPIRE_SECONDS
 
-        # 解码JWT令牌(不验证签名，只解析内容)
+        # Decode JWT token (without signature verification, only parse content)
         decoded = jwt.decode(jwt_token, options={"verify_signature": False})
 
-        # 从JWT声明中提取过期时间和签发时间
+        # Extract expiration time and issued time from JWT claims
         exp = decoded.get("exp", 0)
         iat = decoded.get("iat", 0)
 
-        # 计算有效期（秒）
+        # Calculate validity period (seconds)
         expiry_seconds = exp - iat
 
         return expiry_seconds
     except Exception as e:
-        logging.warning(f"从令牌获取过期时间失败: {str(e)}")
-        return 3600  # supabase默认设置
+        logging.warning(f"Failed to get expiration time from token: {str(e)}")
+        return 3600  # supabase default setting
 
 
 def calculate_expires_at(token: Optional[str] = None) -> int:
     """
-    计算会话过期时间（与Supabase JWT过期时间保持一致）
+    Calculate session expiration time (consistent with Supabase JWT expiration time)
 
     Args:
-        token: 可选的JWT令牌，用于获取实际过期时间
+        token: Optional JWT token to get actual expiration time
 
     Returns:
-        int: 过期时间的时间戳
+        int: Expiration time timestamp
     """
     # Speed mode: far future expiration
     if IS_SPEED_MODE:
@@ -275,13 +278,14 @@ def _extract_user_id_from_jwt_token(authorization: str) -> Optional[str]:
         Optional[str]: User ID, return None if parsing fails
     """
     try:
-        # 格式化授权头部
-        token = authorization.replace("Bearer ", "") if authorization.startswith("Bearer ") else authorization
+        # Format authorization header
+        token = authorization.replace("Bearer ", "") if authorization.startswith(
+            "Bearer ") else authorization
 
-        # 解码JWT令牌(不验证签名，只解析内容)
+        # Decode JWT token (without signature verification, only parse content)
         decoded = jwt.decode(token, options={"verify_signature": False})
 
-        # 从JWT声明中提取用户ID
+        # Extract user ID from JWT claims
         user_id = decoded.get("sub")
 
         return user_id
@@ -302,7 +306,8 @@ def get_current_user_id(authorization: Optional[str] = None) -> tuple[str, str]:
     """
     # if deploy in speed mode or authorization is None, return default user id and tenant id
     if IS_SPEED_MODE or authorization is None:
-        logging.debug("Speed mode or no valid authorization header detected - returning default user ID and tenant ID")
+        logging.debug(
+            "Speed mode or no valid authorization header detected - returning default user ID and tenant ID")
         return DEFAULT_USER_ID, DEFAULT_TENANT_ID
 
     try:
@@ -316,12 +321,13 @@ def get_current_user_id(authorization: Optional[str] = None) -> tuple[str, str]:
             logging.debug(f"Found tenant ID for user {user_id}: {tenant_id}")
         else:
             tenant_id = DEFAULT_TENANT_ID
-            logging.warning(f"No tenant relationship found for user {user_id}, using default tenant")
+            logging.warning(
+                f"No tenant relationship found for user {user_id}, using default tenant")
 
         return user_id, tenant_id
 
     except Exception as e:
-        logging.error(f"Failed to get user ID and tanent ID: {str(e)}")
+        logging.error(f"Failed to get user ID and tenant ID: {str(e)}")
         raise UnauthorizedError("Invalid or expired authentication token")
 
 

backend/utils/prompt_template_utils.py

@@ -22,7 +22,7 @@ def get_prompt_template(template_type: str, language: str = 'zh', **kwargs) -> D
         dict: Loaded prompt template
     """
     logger.info(
-        f"Getting prompt template for type: {template_type}, language: {language}，kwargs: {kwargs}")
+        f"Getting prompt template for type: {template_type}, language: {language}, kwargs: {kwargs}")
 
     # Define template path mapping
     template_paths = {