From 1e51717796d2df73edc2dbf0c50b3e220d000581 Mon Sep 17 00:00:00 2001 From: SengokuCola <1026294844@qq.com> Date: Mon, 9 Jun 2025 00:32:30 +0800 Subject: [PATCH] =?UTF-8?q?fix=EF=BC=9A=E7=A7=BB=E9=99=A4=E4=BA=86?= =?UTF-8?q?=E9=83=A8=E5=88=86token=E9=99=90=E5=88=B6?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- src/chat/focus_chat/expressors/default_expressor.py | 1 - src/chat/focus_chat/expressors/exprssion_learner.py | 1 - .../info_processors/chattinginfo_processor.py | 1 - src/chat/focus_chat/info_processors/mind_processor.py | 1 - .../info_processors/relationship_processor.py | 10 +++++----- src/chat/focus_chat/memory_activator.py | 1 - src/chat/focus_chat/planners/actions/plugin_action.py | 2 -- src/chat/focus_chat/replyer/default_replyer.py | 3 +-- src/chat/focus_chat/working_memory/memory_manager.py | 1 - src/chat/normal_chat/normal_chat_generator.py | 6 +----- src/experimental/PFC/action_planner.py | 1 - src/experimental/PFC/reply_generator.py | 1 - src/person_info/person_info.py | 1 - tests/test_relationship_processor.py | 1 - 14 files changed, 7 insertions(+), 24 deletions(-) diff --git a/src/chat/focus_chat/expressors/default_expressor.py b/src/chat/focus_chat/expressors/default_expressor.py index d82d98ae0..b3442067d 100644 --- a/src/chat/focus_chat/expressors/default_expressor.py +++ b/src/chat/focus_chat/expressors/default_expressor.py @@ -77,7 +77,6 @@ class DefaultExpressor: # TODO: API-Adapter修改标记 self.express_model = LLMRequest( model=global_config.model.replyer_1, - max_tokens=256, request_type="focus.expressor", ) self.heart_fc_sender = HeartFCSender() diff --git a/src/chat/focus_chat/expressors/exprssion_learner.py b/src/chat/focus_chat/expressors/exprssion_learner.py index ca980e89a..573801719 100644 --- a/src/chat/focus_chat/expressors/exprssion_learner.py +++ b/src/chat/focus_chat/expressors/exprssion_learner.py @@ -70,7 +70,6 @@ class ExpressionLearner: self.express_learn_model: LLMRequest = LLMRequest( model=global_config.model.replyer_1, temperature=0.1, - max_tokens=256, request_type="expressor.learner", ) diff --git a/src/chat/focus_chat/info_processors/chattinginfo_processor.py b/src/chat/focus_chat/info_processors/chattinginfo_processor.py index 872851579..e2ae41c0d 100644 --- a/src/chat/focus_chat/info_processors/chattinginfo_processor.py +++ b/src/chat/focus_chat/info_processors/chattinginfo_processor.py @@ -31,7 +31,6 @@ class ChattingInfoProcessor(BaseProcessor): self.model_summary = LLMRequest( model=global_config.model.utils_small, temperature=0.7, - max_tokens=300, request_type="focus.observation.chat", ) diff --git a/src/chat/focus_chat/info_processors/mind_processor.py b/src/chat/focus_chat/info_processors/mind_processor.py index 39acc2eb9..fb3cb757a 100644 --- a/src/chat/focus_chat/info_processors/mind_processor.py +++ b/src/chat/focus_chat/info_processors/mind_processor.py @@ -69,7 +69,6 @@ class MindProcessor(BaseProcessor): self.llm_model = LLMRequest( model=global_config.model.planner, - max_tokens=800, request_type="focus.processor.chat_mind", ) diff --git a/src/chat/focus_chat/info_processors/relationship_processor.py b/src/chat/focus_chat/info_processors/relationship_processor.py index 591a4a05e..d3654502f 100644 --- a/src/chat/focus_chat/info_processors/relationship_processor.py +++ b/src/chat/focus_chat/info_processors/relationship_processor.py @@ -37,7 +37,7 @@ def init_prompt(): 你不同程度上认识群聊里的人，你可以根据聊天记录，回忆起有关他们的信息，帮助你参与聊天 1.你需要提供用户名，以及你想要提取的信息名称类型来进行调取 2.你也可以完全不输出任何信息 -3.如果短期内已经回忆过某个人的信息，请不要重复调取，除非你忘记了 +3.阅读调取记录，如果已经回忆过某个人的信息，请不要重复调取，除非你忘记了 请以json格式输出，例如： @@ -95,7 +95,7 @@ class RelationshipProcessor(BaseProcessor): self.llm_model = LLMRequest( model=global_config.model.relation, max_tokens=800, - request_type="relation", + request_type="focus.relationship", ) name = chat_manager.get_stream_name(self.subheartflow_id) @@ -206,10 +206,10 @@ class RelationshipProcessor(BaseProcessor): ) try: - logger.info(f"{self.log_prefix} 人物信息prompt: \n{prompt}\n") + # logger.info(f"{self.log_prefix} 人物信息prompt: \n{prompt}\n") content, _ = await self.llm_model.generate_response_async(prompt=prompt) if content: - print(f"content: {content}") + # print(f"content: {content}") content_json = json.loads(repair_json(content)) for person_name, info_type in content_json.items(): @@ -347,7 +347,7 @@ class RelationshipProcessor(BaseProcessor): try: content, _ = await self.llm_model.generate_response_async(prompt=prompt) - logger.info(f"{self.log_prefix} fetch_person_info prompt: \n{prompt}\n") + # logger.info(f"{self.log_prefix} fetch_person_info prompt: \n{prompt}\n") logger.info(f"{self.log_prefix} fetch_person_info 结果: {content}") if content: diff --git a/src/chat/focus_chat/memory_activator.py b/src/chat/focus_chat/memory_activator.py index 590ba58f5..de0833879 100644 --- a/src/chat/focus_chat/memory_activator.py +++ b/src/chat/focus_chat/memory_activator.py @@ -72,7 +72,6 @@ class MemoryActivator: self.summary_model = LLMRequest( model=global_config.model.memory_summary, temperature=0.7, - max_tokens=50, request_type="focus.memory_activator", ) self.running_memory = [] diff --git a/src/chat/focus_chat/planners/actions/plugin_action.py b/src/chat/focus_chat/planners/actions/plugin_action.py index fc0d399d0..d0c345718 100644 --- a/src/chat/focus_chat/planners/actions/plugin_action.py +++ b/src/chat/focus_chat/planners/actions/plugin_action.py @@ -348,7 +348,6 @@ class PluginAction(BaseAction): self, prompt: str, model_config: Dict[str, Any], - max_tokens: int = 2000, request_type: str = "plugin.generate", **kwargs ) -> Tuple[bool, str]: @@ -372,7 +371,6 @@ class PluginAction(BaseAction): llm_request = LLMRequest( model=model_config, - max_tokens=max_tokens, request_type=request_type, **kwargs ) diff --git a/src/chat/focus_chat/replyer/default_replyer.py b/src/chat/focus_chat/replyer/default_replyer.py index 0b4b8c655..234c2f5fe 100644 --- a/src/chat/focus_chat/replyer/default_replyer.py +++ b/src/chat/focus_chat/replyer/default_replyer.py @@ -88,8 +88,7 @@ class DefaultReplyer: # TODO: API-Adapter修改标记 self.express_model = LLMRequest( model=global_config.model.replyer_1, - max_tokens=256, - request_type="focus.expressor", + request_type="focus.replyer", ) self.heart_fc_sender = HeartFCSender() diff --git a/src/chat/focus_chat/working_memory/memory_manager.py b/src/chat/focus_chat/working_memory/memory_manager.py index 1e8ae4912..f574222b4 100644 --- a/src/chat/focus_chat/working_memory/memory_manager.py +++ b/src/chat/focus_chat/working_memory/memory_manager.py @@ -35,7 +35,6 @@ class MemoryManager: self.llm_summarizer = LLMRequest( model=global_config.model.focus_working_memory, temperature=0.3, - max_tokens=512, request_type="focus.processor.working_memory", ) diff --git a/src/chat/normal_chat/normal_chat_generator.py b/src/chat/normal_chat/normal_chat_generator.py index ad6bab74c..e15a2b7a6 100644 --- a/src/chat/normal_chat/normal_chat_generator.py +++ b/src/chat/normal_chat/normal_chat_generator.py @@ -19,19 +19,15 @@ class NormalChatGenerator: # TODO: API-Adapter修改标记 self.model_reasoning = LLMRequest( model=global_config.model.replyer_1, - # temperature=0.7, - max_tokens=3000, request_type="normal.chat_1", ) self.model_normal = LLMRequest( model=global_config.model.replyer_2, - # temperature=global_config.model.replyer_2["temp"], - max_tokens=256, request_type="normal.chat_2", ) self.model_sum = LLMRequest( - model=global_config.model.memory_summary, temperature=0.7, max_tokens=3000, request_type="relation" + model=global_config.model.memory_summary, temperature=0.7, request_type="relation" ) self.current_model_type = "r1" # 默认使用 R1 self.current_model_name = "unknown model" diff --git a/src/experimental/PFC/action_planner.py b/src/experimental/PFC/action_planner.py index f60354bfb..f4defaf7c 100644 --- a/src/experimental/PFC/action_planner.py +++ b/src/experimental/PFC/action_planner.py @@ -110,7 +110,6 @@ class ActionPlanner: self.llm = LLMRequest( model=global_config.llm_PFC_action_planner, temperature=global_config.llm_PFC_action_planner["temp"], - max_tokens=1500, request_type="action_planning", ) self.personality_info = individuality.get_prompt(x_person=2, level=3) diff --git a/src/experimental/PFC/reply_generator.py b/src/experimental/PFC/reply_generator.py index 1a6563a77..bcc35eedb 100644 --- a/src/experimental/PFC/reply_generator.py +++ b/src/experimental/PFC/reply_generator.py @@ -89,7 +89,6 @@ class ReplyGenerator: self.llm = LLMRequest( model=global_config.llm_PFC_chat, temperature=global_config.llm_PFC_chat["temp"], - max_tokens=300, request_type="reply_generation", ) self.personality_info = individuality.get_prompt(x_person=2, level=3) diff --git a/src/person_info/person_info.py b/src/person_info/person_info.py index 70b2beccc..6a7e60bc1 100644 --- a/src/person_info/person_info.py +++ b/src/person_info/person_info.py @@ -56,7 +56,6 @@ class PersonInfoManager: # TODO: API-Adapter修改标记 self.qv_name_llm = LLMRequest( model=global_config.model.utils, - max_tokens=256, request_type="relation.qv_name", ) try: diff --git a/tests/test_relationship_processor.py b/tests/test_relationship_processor.py index b87d7832e..f190ab947 100644 --- a/tests/test_relationship_processor.py +++ b/tests/test_relationship_processor.py @@ -128,7 +128,6 @@ class RelationshipProcessor: self.llm_model = LLMRequest( model=global_config.model.relation, - max_tokens=800, request_type="relation", )