From 5fcce79361728462c8d979d6dbc758ce062fc9d9 Mon Sep 17 00:00:00 2001 From: Kunthawat Greethong Date: Wed, 17 Jun 2026 15:52:38 +0700 Subject: [PATCH] fix: translate Chinese prompts to English in simulation config and profile generators - simulation_config_generator.py: translate all LLM prompts and system messages - oasis_profile_generator.py: translate profile generation prompts Ensures get_language_instruction() controls output language instead of being overridden by Chinese prompt context. --- .../app/services/oasis_profile_generator.py | 16 +++---- .../services/simulation_config_generator.py | 44 +++++++++---------- 2 files changed, 30 insertions(+), 30 deletions(-) diff --git a/backend/app/services/oasis_profile_generator.py b/backend/app/services/oasis_profile_generator.py index 7704a62..d7b1122 100644 --- a/backend/app/services/oasis_profile_generator.py +++ b/backend/app/services/oasis_profile_generator.py @@ -671,7 +671,7 @@ class OasisProfileGenerator: def _get_system_prompt(self, is_individual: bool) -> str: """获取系统提示词""" - base_prompt = "你是社交媒体用户画像生成专家。生成详细、真实的人设用于舆论模拟,最大程度还原已有现实情况。必须返回有效的JSON格式，所有字符串值不能包含未转义的换行符。" + base_prompt = "You are a social media user persona generation expert. Generate detailed, realistic personas for opinion simulation, maximizing fidelity to real-world situations. Must return valid JSON format, all string values must not contain unescaped newlines." return f"{base_prompt}\n\n{get_language_instruction()}" def _build_individual_persona_prompt( @@ -687,7 +687,7 @@ class OasisProfileGenerator: attrs_str = json.dumps(entity_attributes, ensure_ascii=False) if entity_attributes else "无" context_str = context[:3000] if context else "无额外上下文" - return f"""为实体生成详细的社交媒体用户人设,最大程度还原已有现实情况。 + return f"""Generate detailed social media user persona for the entity, maximizing fidelity to real-world situations. 实体名称: {entity_name} 实体类型: {entity_type} @@ -736,7 +736,7 @@ class OasisProfileGenerator: attrs_str = json.dumps(entity_attributes, ensure_ascii=False) if entity_attributes else "无" context_str = context[:3000] if context else "无额外上下文" - return f"""为机构/群体实体生成详细的社交媒体账号设定,最大程度还原已有现实情况。 + return f"""Generate detailed social media account settings for organization/group entity, maximizing fidelity to real-world situations. 实体名称: {entity_name} 实体类型: {entity_type} @@ -769,7 +769,7 @@ class OasisProfileGenerator: - persona必须是一段连贯的文字描述，不要使用换行符 - {get_language_instruction()} (gender字段必须用英文"other") - age必须是整数30，gender必须是字符串"other" -- 机构账号发言要符合其身份定位""" +- Organization account posts must match its identity positioning""" def _generate_profile_rule_based( self, @@ -1076,11 +1076,11 @@ class OasisProfileGenerator: - name: 用户真实姓名 - username: 系统中的用户名 - user_char: 详细人设描述（注入到LLM系统提示中，指导Agent行为） - - description: 简短的公开简介（显示在用户资料页面） + - description: Short public bio (displayed on user profile page) - user_char vs description 区别： + user_char vs description difference: - user_char: 内部使用，LLM系统提示，决定Agent如何思考和行动 - - description: 外部显示，其他用户可见的简介 + - description: Externally displayed, visible to other users """ import csv @@ -1112,7 +1112,7 @@ class OasisProfileGenerator: profile.name, # name: 真实姓名 profile.user_name, # username: 用户名 user_char, # user_char: 完整人设（内部LLM使用） - description # description: 简短简介（外部显示） + description # description: Short bio (externally displayed) ] writer.writerow(row) diff --git a/backend/app/services/simulation_config_generator.py b/backend/app/services/simulation_config_generator.py index cb77f6b..3729e2a 100644 --- a/backend/app/services/simulation_config_generator.py +++ b/backend/app/services/simulation_config_generator.py @@ -540,15 +540,15 @@ class SimulationConfigGenerator: # 计算最大允许值（80%的agent数） max_agents_allowed = max(1, int(num_entities * 0.9)) - prompt = f"""基于以下模拟需求，生成时间模拟配置。 + prompt = f"""Based on the following simulation requirements, generate time simulation config. {context_truncated} ## 任务 -请生成时间配置JSON。 +Please generate time config JSON. ### 基本原则（仅供参考，需根据具体事件和参与群体灵活调整）： -- 请根据模拟场景推断目标用户群体所在时区和作息习惯，以下为东八区(UTC+8)的参考示例 +- Please infer the target user group's timezone and daily routine based on the simulation scenario. Below is a reference example for UTC+8 - 凌晨0-5点几乎无人活动（活跃度系数0.05） - 早上6-8点逐渐活跃（活跃度系数0.4） - 工作时间9-18点中等活跃（活跃度系数0.7） @@ -571,7 +571,7 @@ class SimulationConfigGenerator: "off_peak_hours": [0, 1, 2, 3, 4, 5], "morning_hours": [6, 7, 8], "work_hours": [9, 10, 11, 12, 13, 14, 15, 16, 17, 18], - "reasoning": "针对该事件的时间配置说明" + "reasoning": "Explanation of time config for this event" }} 字段说明： @@ -583,15 +583,15 @@ class SimulationConfigGenerator: - off_peak_hours (int数组): 低谷时段，通常深夜凌晨 - morning_hours (int数组): 早间时段 - work_hours (int数组): 工作时段 -- reasoning (string): 简要说明为什么这样配置""" +- reasoning (string): Brief explanation of why this config was chosen""" - system_prompt = "你是社交媒体模拟专家。返回纯JSON格式，时间配置需符合模拟场景中目标用户群体的作息习惯。" + system_prompt = "You are a social media simulation expert. Return pure JSON format. Time config must match the target user group's daily routine in the simulation scenario." system_prompt = f"{system_prompt}\n\n{get_language_instruction()}" try: return self._call_llm_with_retry(prompt, system_prompt) except Exception as e: - logger.warning(f"时间配置LLM生成失败: {e}, 使用默认配置") + logger.warning(f"Time config LLM generation failed: {e}, using default config") return self._get_default_time_config(num_entities) def _get_default_time_config(self, num_entities: int) -> Dict[str, Any]: @@ -605,7 +605,7 @@ class SimulationConfigGenerator: "off_peak_hours": [0, 1, 2, 3, 4, 5], "morning_hours": [6, 7, 8], "work_hours": [9, 10, 11, 12, 13, 14, 15, 16, 17, 18], - "reasoning": "使用默认中国人作息配置（每轮1小时）" + "reasoning": "Using default UTC+8 daily routine config (1 hour per round)" } def _parse_time_config(self, result: Dict[str, Any], num_entities: int) -> TimeSimulationConfig: @@ -673,9 +673,9 @@ class SimulationConfigGenerator: # 使用配置的上下文截断长度 context_truncated = context[:self.EVENT_CONFIG_CONTEXT_LENGTH] - prompt = f"""基于以下模拟需求，生成事件配置。 + prompt = f"""Based on the following simulation requirements, generate event config. -模拟需求: {simulation_requirement} +Simulation requirements: {simulation_requirement} {context_truncated} @@ -683,7 +683,7 @@ class SimulationConfigGenerator: {type_info} ## 任务 -请生成事件配置JSON： +Please generate event config JSON: - 提取热点话题关键词 - 描述舆论发展方向 - 设计初始帖子内容，**每个帖子必须指定 poster_type（发布者类型）** @@ -691,7 +691,7 @@ class SimulationConfigGenerator: **重要**: poster_type 必须从上面的"可用实体类型"中选择，这样初始帖子才能分配给合适的 Agent 发布。 例如：官方声明应由 Official/University 类型发布，新闻由 MediaOutlet 发布，学生观点由 Student 发布。 -返回JSON格式（不要markdown）： +Return in JSON format (no markdown): {{ "hot_topics": ["关键词1", "关键词2", ...], "narrative_direction": "<舆论发展方向描述>", @@ -702,18 +702,18 @@ class SimulationConfigGenerator: "reasoning": "<简要说明>" }}""" - system_prompt = "你是舆论分析专家。返回纯JSON格式。注意 poster_type 必须精确匹配可用实体类型。" + system_prompt = "You are a public opinion analysis expert. Return pure JSON format. Note: poster_type must exactly match available entity types." system_prompt = f"{system_prompt}\n\n{get_language_instruction()}\nIMPORTANT: The 'poster_type' field value MUST be in English PascalCase exactly matching the available entity types. Only 'content', 'narrative_direction', 'hot_topics' and 'reasoning' fields should use the specified language." try: return self._call_llm_with_retry(prompt, system_prompt) except Exception as e: - logger.warning(f"事件配置LLM生成失败: {e}, 使用默认配置") + logger.warning(f"Event config LLM generation failed: {e}, using default config") return { "hot_topics": [], "narrative_direction": "", "initial_posts": [], - "reasoning": "使用默认配置" + "reasoning": "Using default config" } def _parse_event_config(self, result: Dict[str, Any]) -> EventConfig: @@ -830,9 +830,9 @@ class SimulationConfigGenerator: "summary": e.summary[:summary_len] if e.summary else "" }) - prompt = f"""基于以下信息，为每个实体生成社交媒体活动配置。 + prompt = f"""Based on the following information, generate social media activity config for each entity. -模拟需求: {simulation_requirement} +Simulation requirements: {simulation_requirement} ## 实体列表 ```json @@ -840,14 +840,14 @@ class SimulationConfigGenerator: ``` ## 任务 -为每个实体生成活动配置，注意： -- **时间符合目标用户群体作息**：以下为参考（东八区），请根据模拟场景调整 +Generate activity config for each entity, noting: +- **Time must match target user group routine**: Below is a reference (UTC+8), please adjust based on simulation scenario - **官方机构**（University/GovernmentAgency）：活跃度低(0.1-0.3)，工作时间(9-17)活动，响应慢(60-240分钟)，影响力高(2.5-3.0) - **媒体**（MediaOutlet）：活跃度中(0.4-0.6)，全天活动(8-23)，响应快(5-30分钟)，影响力高(2.0-2.5) - **个人**（Student/Person/Alumni）：活跃度高(0.6-0.9)，主要晚间活动(18-23)，响应快(1-15分钟)，影响力低(0.8-1.2) - **公众人物/专家**：活跃度中(0.4-0.6)，影响力中高(1.5-2.0) -返回JSON格式（不要markdown）： +Return in JSON format (no markdown): {{ "agent_configs": [ {{ @@ -866,14 +866,14 @@ class SimulationConfigGenerator: ] }}""" - system_prompt = "你是社交媒体行为分析专家。返回纯JSON，配置需符合模拟场景中目标用户群体的作息习惯。" + system_prompt = "You are a social media behavior analysis expert. Return pure JSON. Config must match the target user group's daily routine in the simulation scenario." system_prompt = f"{system_prompt}\n\n{get_language_instruction()}\nIMPORTANT: The 'stance' field value MUST be one of the English strings: 'supportive', 'opposing', 'neutral', 'observer'. All JSON field names and numeric values must remain unchanged. Only natural language text fields should use the specified language." try: result = self._call_llm_with_retry(prompt, system_prompt) llm_configs = {cfg["agent_id"]: cfg for cfg in result.get("agent_configs", [])} except Exception as e: - logger.warning(f"Agent配置批次LLM生成失败: {e}, 使用规则生成") + logger.warning(f"Agent config batch LLM generation failed: {e}, using rule-based generation") llm_configs = {} # 构建AgentActivityConfig对象