根据开发组建议重命名，移除多余的Prompt后缀

src/bw_learner/expression_learner.py

@@ -68,7 +68,7 @@ class ExpressionLearner:
         # 学习用（开启行编号，便于溯源）
         random_msg_str: str = await build_anonymous_messages(random_msg, show_ids=True)
 
-        prompt_template = prompt_manager.get_prompt("learn_style_prompt")
+        prompt_template = prompt_manager.get_prompt("learn_style")
         prompt_template.add_context("bot_name", global_config.bot.nickname)
         prompt_template.add_context("chat_str", random_msg_str)
 

src/bw_learner/expression_selector.py

@@ -378,7 +378,7 @@ class ExpressionSelector:
                 reply_reason_block = ""
 
             # 3. 构建prompt（只包含情境，不包含完整的表达方式）
-            prompt_template = prompt_manager.get_prompt("expression_evaluation_prompt")
+            prompt_template = prompt_manager.get_prompt("expression_evaluation")
             prompt_template.add_context("bot_name", global_config.bot.nickname)
             prompt_template.add_context("chat_observe_info", chat_context)
             prompt_template.add_context("all_situations", all_situations_str)

src/bw_learner/jargon_explainer.py

@@ -200,7 +200,7 @@ class JargonExplainer:
         explanations_text = "\n".join(jargon_explanations)
 
         # 使用LLM概括黑话解释
-        prompt_of_summarize = prompt_manager.get_prompt("jargon_explainer_summarize_prompt")
+        prompt_of_summarize = prompt_manager.get_prompt("jargon_explainer_summarize")
         prompt_of_summarize.add_context("chat_context", lambda _: chat_context)
         prompt_of_summarize.add_context("jargon_explanations", lambda _: explanations_text)
         summarize_prompt = await prompt_manager.render_prompt(prompt_of_summarize)

src/bw_learner/jargon_miner.py

@@ -193,7 +193,7 @@ class JargonMiner:
                     "- 请参考上一次推断的含义，结合新的上下文信息，给出更准确或更新的推断结果"
                 )
 
-            prompt1_template = prompt_manager.get_prompt("jargon_inference_with_context_prompt")
+            prompt1_template = prompt_manager.get_prompt("jargon_inference_with_context")
             prompt1_template.add_context("bot_name", global_config.bot.nickname)
             prompt1_template.add_context("content", str(content))
             prompt1_template.add_context("raw_content_list", raw_content_text)
@@ -233,7 +233,7 @@ class JargonMiner:
                 return
 
             # 步骤2: 仅基于content推断
-            prompt2_template = prompt_manager.get_prompt("jargon_inference_content_only_prompt")
+            prompt2_template = prompt_manager.get_prompt("jargon_inference_content_only")
             prompt2_template.add_context("content", str(content))
             prompt2 = await prompt_manager.render_prompt(prompt2_template)
 
@@ -275,7 +275,7 @@ class JargonMiner:
                 logger.debug(f"jargon {content} 推断1结果: {response1}")
 
             # 步骤3: 比较两个推断结果
-            prompt3_template = prompt_manager.get_prompt("jargon_compare_inference_prompt")
+            prompt3_template = prompt_manager.get_prompt("jargon_compare_inference")
             prompt3_template.add_context("inference1", json.dumps(inference1, ensure_ascii=False))
             prompt3_template.add_context("inference2", json.dumps(inference2, ensure_ascii=False))
             prompt3 = await prompt_manager.render_prompt(prompt3_template)

src/bw_learner/reflect_tracker.py

@@ -72,7 +72,7 @@ class ReflectTracker:
 
         # LLM Judge
         try:
-            prompt_template = prompt_manager.get_prompt("reflect_judge_prompt")
+            prompt_template = prompt_manager.get_prompt("reflect_judge")
             prompt_template.add_context("situation", str(self.expression.situation))
             prompt_template.add_context("style", str(self.expression.style))
             prompt_template.add_context("context_block", context_block)

src/chat/brain_chat/brain_chat.py

@@ -313,7 +313,7 @@ class BrainChatting:
                 current_available_actions=available_actions,
                 chat_content_block=chat_content_block,
                 message_id_list=message_id_list,
-                prompt_key="brain_planner_prompt_react",
+                prompt_key="brain_planner",
             )
             continue_flag, modified_message = await events_manager.handle_mai_events(
                 EventType.ON_PLAN, None, prompt_info[0], None, self.chat_stream.stream_id

src/chat/brain_chat/brain_planner.py

@@ -200,7 +200,7 @@ class BrainPlanner:
 
         prompt_build_start = time.perf_counter()
         # 构建包含所有动作的提示词：使用统一的 ReAct Prompt
-        prompt_key = "brain_planner_prompt_react"
+        prompt_key = "brain_planner"
         # 这里不记录日志，避免重复打印，由调用方按需控制 log_prompt
         prompt, message_id_list = await self.build_planner_prompt(
             chat_target_info=chat_target_info,
@@ -254,7 +254,7 @@ class BrainPlanner:
         message_id_list: List[Tuple[str, "DatabaseMessages"]],
         chat_content_block: str = "",
         interest: str = "",
-        prompt_key: str = "brain_planner_prompt_react",
+        prompt_key: str = "brain_planner",
     ) -> tuple[str, List[Tuple[str, "DatabaseMessages"]]]:
         """构建 Planner LLM 的提示词 (获取模板并填充数据)"""
         try:
@@ -381,7 +381,7 @@ class BrainPlanner:
             require_text = require_text.rstrip("\n")
 
             # 获取动作提示模板并填充
-            using_action_prompt_template = prompt_manager.get_prompt("brain_action_prompt")
+            using_action_prompt_template = prompt_manager.get_prompt("brain_action")
             using_action_prompt_template.add_context("action_name", action_name)
             using_action_prompt_template.add_context("action_description", action_info.description)
             using_action_prompt_template.add_context("action_parameters", param_text)

src/chat/planner_actions/planner.py

@@ -600,7 +600,7 @@ class ActionPlanner:
                     reply_action_example += ', "quote":"如果需要引用该message，设置为true"'
                 reply_action_example += "}"
 
-            planner_prompt_template = prompt_manager.get_prompt("planner_prompt")
+            planner_prompt_template = prompt_manager.get_prompt("planner")
             planner_prompt_template.add_context("time_block", time_block)
             planner_prompt_template.add_context("chat_context_description", chat_context_description)
             planner_prompt_template.add_context("chat_content_block", chat_content_block)
@@ -695,7 +695,7 @@ class ActionPlanner:
                 parallel_text = ""
 
             # 获取动作提示模板并填充
-            using_action_prompt = prompt_manager.get_prompt("action_prompt")
+            using_action_prompt = prompt_manager.get_prompt("action")
             using_action_prompt.add_context("action_name", action_name)
             using_action_prompt.add_context("action_description", action_info.description)
             using_action_prompt.add_context("action_parameters", param_text)

src/chat/replyer/group_generator.py

@@ -960,9 +960,9 @@ class DefaultReplyer:
         # think_level=0: 轻量回复（简短平淡）
         # think_level=1: 中等回复（日常口语化）
         if think_level == 0:
-            prompt_name = "replyer_prompt_0"
+            prompt_name = "replyer_light"
         else:  # think_level == 1 或默认
-            prompt_name = "replyer_prompt"
+            prompt_name = "replyer"
 
         # 根据配置构建最终的 reply_style：支持 multiple_reply_style 按概率随机替换
         reply_style = global_config.personality.reply_style
@@ -1082,7 +1082,7 @@ class DefaultReplyer:
             except Exception:
                 reply_style = global_config.personality.reply_style
 
-        prompt_template = prompt_manager.get_prompt("default_expressor_prompt")
+        prompt_template = prompt_manager.get_prompt("default_expressor")
         prompt_template.add_context("expression_habits_block", expression_habits_block)
         # prompt_template.add_context("relation_info_block", relation_info)
         prompt_template.add_context("chat_target", chat_target_1)
@@ -1169,7 +1169,7 @@ class DefaultReplyer:
             if global_config.lpmm_knowledge.lpmm_mode == "agent":
                 return ""
 
-            template_prompt = prompt_manager.get_prompt("lpmm_get_knowledge_prompt")
+            template_prompt = prompt_manager.get_prompt("lpmm_get_knowledge")
             template_prompt.add_context("bot_name", global_config.bot.nickname)
             template_prompt.add_context("time_now", lambda _: time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()))
             template_prompt.add_context("chat_history", message)

src/chat/replyer/private_generator.py

@@ -809,11 +809,11 @@ class PrivateReplyer:
         # 使用统一的 is_bot_self 函数判断是否是机器人自己（支持多平台，包括 WebUI）
         
         if is_bot_self(platform, user_id):
-            prompt_template = prompt_manager.get_prompt("private_replyer_self_prompt")
+            prompt_template = prompt_manager.get_prompt("private_replyer_self")
             prompt_template.add_context("target", target)
             prompt_template.add_context("reason", reply_reason)
         else:
-            prompt_template = prompt_manager.get_prompt("private_replyer_prompt")
+            prompt_template = prompt_manager.get_prompt("private_replyer")
             prompt_template.add_context("reply_target_block", reply_target_block)
             prompt_template.add_context("planner_reasoning", planner_reasoning)
         prompt_template.add_context("expression_habits_block", expression_habits_block)
@@ -923,7 +923,7 @@ class PrivateReplyer:
                 # 兜底：即使 multiple_reply_style 配置异常也不影响正常回复
                 reply_style = global_config.personality.reply_style
 
-        prompt_template = prompt_manager.get_prompt("default_expressor_prompt")
+        prompt_template = prompt_manager.get_prompt("default_expressor")
         prompt_template.add_context("expression_habits_block", expression_habits_block)
         # prompt_template.add_context("relation_info_block", relation_info)
         prompt_template.add_context("chat_target", chat_target_1)
@@ -1010,7 +1010,7 @@ class PrivateReplyer:
             if global_config.lpmm_knowledge.lpmm_mode == "agent":
                 return ""
 
-            prompt_template = prompt_manager.get_prompt("lpmm_get_knowledge_prompt")
+            prompt_template = prompt_manager.get_prompt("lpmm_get_knowledge")
             prompt_template.add_context("bot_name", global_config.bot.nickname)
             prompt_template.add_context("time_now", time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()))
             prompt_template.add_context("chat_history", message)

src/dream/dream_agent.py

@@ -224,7 +224,7 @@ async def run_dream_agent_once(
     tool_registry = get_dream_tool_registry()
     tool_defs = tool_registry.get_tool_definitions()
 
-    head_prompt_template = prompt_manager.get_prompt("dream_react_head_prompt")
+    head_prompt_template = prompt_manager.get_prompt("dream_react_head")
     head_prompt_template.add_context("bot_name", global_config.bot.nickname)
     head_prompt_template.add_context("time_now", time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()))
     head_prompt_template.add_context("chat_id", chat_id)

src/dream/dream_generator.py

@@ -143,7 +143,7 @@ async def generate_dream_summary(
         dream_styles_text = "\n".join([f"{i + 1}. {style}" for i, style in enumerate(selected_styles)])
 
         # 使用 Prompt 管理器格式化梦境生成 prompt
-        dream_prompt_template = prompt_manager.get_prompt("dream_summary_prompt")
+        dream_prompt_template = prompt_manager.get_prompt("dream_summary")
         dream_prompt_template.add_context("chat_id", chat_id)
         dream_prompt_template.add_context("total_iterations", str(total_iterations))
         dream_prompt_template.add_context("time_cost", str(time_cost))

src/memory_system/chat_history_summarizer.py

@@ -658,7 +658,7 @@ class ChatHistorySummarizer:
         history_topics_block = "\n".join(f"- {t}" for t in existing_topics) if existing_topics else "（当前无历史话题）"
         messages_block = "\n".join(numbered_lines)
 
-        prompt_template = prompt_manager.get_prompt("hippo_topic_analysis_prompt")
+        prompt_template = prompt_manager.get_prompt("hippo_topic_analysis")
         prompt_template.add_context("history_topics_block", history_topics_block)
         prompt_template.add_context("messages_block", messages_block)
         prompt = await prompt_manager.render_prompt(prompt_template)
@@ -814,7 +814,7 @@ class ChatHistorySummarizer:
         Returns:
             tuple[bool, List[str], str]: (是否成功, 关键词列表, 概括)
         """
-        prompt_template = prompt_manager.get_prompt("hippo_topic_summary_prompt")
+        prompt_template = prompt_manager.get_prompt("hippo_topic_summary")
         prompt_template.add_context("topic", topic)
         prompt_template.add_context("original_text", original_text)
         prompt = await prompt_manager.render_prompt(prompt_template)

src/memory_system/memory_retrieval.py

@@ -662,7 +662,7 @@ async def _react_agent_solve_question(
             return None
 
         # 执行最终评估
-        evaluation_prompt_template = prompt_manager.get_prompt("memory_retrieval_react_final_prompt")
+        evaluation_prompt_template = prompt_manager.get_prompt("memory_retrieval_react_final")
         evaluation_prompt_template.add_context("bot_name", bot_name)
         evaluation_prompt_template.add_context("time_now", time_now)
         evaluation_prompt_template.add_context("chat_history", chat_history)

src/plugin_system/core/tool_use.py

@@ -80,7 +80,7 @@ class ToolExecutor:
                 return [], [], ""
 
         # 构建工具调用提示词
-        prompt_template = prompt_manager.get_prompt("tool_executor_prompt")
+        prompt_template = prompt_manager.get_prompt("tool_executor")
         prompt_template.add_context("target_message", target_message)
         prompt_template.add_context("chat_history", chat_history)
         prompt_template.add_context("sender", sender)