gardel/Mofox-Core
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

🤖 自动格式化代码 [skip ci]

Browse Source
This commit is contained in:
github-actions[bot]
2025-04-12 16:46:11 +00:00
parent e1f272d9c5
commit 46da415d98
43 changed files with 498 additions and 532 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
src/plugins/chat_module/reasoning_chat/reasoning_generator.py
View File

@@ -38,7 +38,7 @@ class ResponseGenerator:
self.current_model_type = "r1" # 默认使用 R1
self.current_model_name = "unknown model"
async def generate_response(self, message: MessageThinking,thinking_id:str) -> Optional[Union[str, List[str]]]:
async def generate_response(self, message: MessageThinking, thinking_id: str) -> Optional[Union[str, List[str]]]:
"""根据当前模型类型选择对应的生成函数"""
# 从global_config中获取模型概率值并选择模型
if random.random() < global_config.MODEL_R1_PROBABILITY:
@@ -52,7 +52,7 @@ class ResponseGenerator:
f"{self.current_model_type}思考:{message.processed_plain_text[:30] + '...' if len(message.processed_plain_text) > 30 else message.processed_plain_text}"
) # noqa: E501
model_response = await self._generate_response_with_model(message, current_model,thinking_id)
model_response = await self._generate_response_with_model(message, current_model, thinking_id)
# print(f"raw_content: {model_response}")
@@ -65,11 +65,11 @@ class ResponseGenerator:
logger.info(f"{self.current_model_type}思考，失败")
return None
async def _generate_response_with_model(self, message: MessageThinking, model: LLM_request,thinking_id:str):
async def _generate_response_with_model(self, message: MessageThinking, model: LLM_request, thinking_id: str):
sender_name = ""
info_catcher = info_catcher_manager.get_info_catcher(thinking_id)
if message.chat_stream.user_info.user_cardname and message.chat_stream.user_info.user_nickname:
sender_name = (
f"[({message.chat_stream.user_info.user_id}){message.chat_stream.user_info.user_nickname}]"
@@ -94,14 +94,11 @@ class ResponseGenerator:
try:
content, reasoning_content, self.current_model_name = await model.generate_response(prompt)
info_catcher.catch_after_llm_generated(
prompt=prompt,
response=content,
reasoning_content=reasoning_content,
model_name=self.current_model_name)
prompt=prompt, response=content, reasoning_content=reasoning_content, model_name=self.current_model_name
)
except Exception:
logger.exception("生成回复时出错")
return None
@@ -118,7 +115,6 @@ class ResponseGenerator:
return content
# def _save_to_db(
# self,
# message: MessageRecv,

8
src/plugins/chat_module/reasoning_chat/reasoning_prompt_builder.py
View File

@@ -144,12 +144,10 @@ class PromptBuilder:
for pattern in rule.get("regex", []):
result = pattern.search(message_txt)
if result:
reaction = rule.get('reaction', '')
reaction = rule.get("reaction", "")
for name, content in result.groupdict().items():
reaction = reaction.replace(f'[{name}]', content)
logger.info(
f"匹配到以下正则表达式：{pattern}，触发反应：{reaction}"
)
reaction = reaction.replace(f"[{name}]", content)
logger.info(f"匹配到以下正则表达式：{pattern}，触发反应：{reaction}")
keywords_reaction_prompt += reaction + "，"
break

38
src/plugins/chat_module/think_flow_chat/think_flow_chat.py
View File

@@ -59,11 +59,7 @@ class ThinkFlowChat:
return thinking_id
async def _send_response_messages(self,
message,
chat,
response_set:List[str],
thinking_id) -> MessageSending:
async def _send_response_messages(self, message, chat, response_set: List[str], thinking_id) -> MessageSending:
"""发送回复消息"""
container = message_manager.get_container(chat.stream_id)
thinking_message = None
@@ -260,8 +256,6 @@ class ThinkFlowChat:
if random() < reply_probability:
try:
do_reply = True
# 回复前处理
await willing_manager.before_generate_reply_handle(message.message_info.message_id)
@@ -274,9 +268,9 @@ class ThinkFlowChat:
timing_results["创建思考消息"] = timer2 - timer1
except Exception as e:
logger.error(f"心流创建思考消息失败: {e}")
logger.debug(f"创建捕捉器，thinking_id:{thinking_id}")
info_catcher = info_catcher_manager.get_info_catcher(thinking_id)
info_catcher.catch_decide_to_response(message)
@@ -288,32 +282,32 @@ class ThinkFlowChat:
timing_results["观察"] = timer2 - timer1
except Exception as e:
logger.error(f"心流观察失败: {e}")
info_catcher.catch_after_observe(timing_results["观察"])
# 思考前脑内状态
try:
timer1 = time.time()
current_mind,past_mind = await heartflow.get_subheartflow(chat.stream_id).do_thinking_before_reply(
message_txt = message.processed_plain_text,
sender_name = message.message_info.user_info.user_nickname,
chat_stream = chat
current_mind, past_mind = await heartflow.get_subheartflow(chat.stream_id).do_thinking_before_reply(
message_txt=message.processed_plain_text,
sender_name=message.message_info.user_info.user_nickname,
chat_stream=chat,
)
timer2 = time.time()
timing_results["思考前脑内状态"] = timer2 - timer1
except Exception as e:
logger.error(f"心流思考前脑内状态失败: {e}")
info_catcher.catch_afer_shf_step(timing_results["思考前脑内状态"],past_mind,current_mind)
info_catcher.catch_afer_shf_step(timing_results["思考前脑内状态"], past_mind, current_mind)
# 生成回复
timer1 = time.time()
response_set = await self.gpt.generate_response(message,thinking_id)
response_set = await self.gpt.generate_response(message, thinking_id)
timer2 = time.time()
timing_results["生成回复"] = timer2 - timer1
info_catcher.catch_after_generate_response(timing_results["生成回复"])
if not response_set:
logger.info("回复生成失败，返回为空")
return
@@ -326,11 +320,9 @@ class ThinkFlowChat:
timing_results["发送消息"] = timer2 - timer1
except Exception as e:
logger.error(f"心流发送消息失败: {e}")
info_catcher.catch_after_response(timing_results["发送消息"],response_set,first_bot_msg)
info_catcher.catch_after_response(timing_results["发送消息"], response_set, first_bot_msg)
info_catcher.done_catch()
# 处理表情包

75
src/plugins/chat_module/think_flow_chat/think_flow_generator.py
View File

@@ -35,44 +35,51 @@ class ResponseGenerator:
self.current_model_type = "r1" # 默认使用 R1
self.current_model_name = "unknown model"
async def generate_response(self, message: MessageRecv,thinking_id:str) -> Optional[List[str]]:
async def generate_response(self, message: MessageRecv, thinking_id: str) -> Optional[List[str]]:
"""根据当前模型类型选择对应的生成函数"""
logger.info(
f"思考:{message.processed_plain_text[:30] + '...' if len(message.processed_plain_text) > 30 else message.processed_plain_text}"
)
arousal_multiplier = MoodManager.get_instance().get_arousal_multiplier()
time1 = time.time()
checked = False
if random.random() > 0:
checked = False
current_model = self.model_normal
current_model.temperature = 0.3 * arousal_multiplier #激活度越高，温度越高
model_response = await self._generate_response_with_model(message, current_model,thinking_id,mode="normal")
current_model.temperature = 0.3 * arousal_multiplier # 激活度越高，温度越高
model_response = await self._generate_response_with_model(
message, current_model, thinking_id, mode="normal"
)
model_checked_response = model_response
else:
checked = True
current_model = self.model_normal
current_model.temperature = 0.3 * arousal_multiplier #激活度越高，温度越高
current_model.temperature = 0.3 * arousal_multiplier # 激活度越高，温度越高
print(f"生成{message.processed_plain_text}回复温度是：{current_model.temperature}")
model_response = await self._generate_response_with_model(message, current_model,thinking_id,mode="simple")
model_response = await self._generate_response_with_model(
message, current_model, thinking_id, mode="simple"
)
current_model.temperature = 0.3
model_checked_response = await self._check_response_with_model(message, model_response, current_model,thinking_id)
model_checked_response = await self._check_response_with_model(
message, model_response, current_model, thinking_id
)
time2 = time.time()
if model_response:
if checked:
logger.info(f"{global_config.BOT_NICKNAME}的回复是：{model_response}，思忖后，回复是：{model_checked_response},生成回复时间: {time2 - time1}秒")
logger.info(
f"{global_config.BOT_NICKNAME}的回复是：{model_response}，思忖后，回复是：{model_checked_response},生成回复时间: {time2 - time1}秒"
)
else:
logger.info(f"{global_config.BOT_NICKNAME}的回复是：{model_response},生成回复时间: {time2 - time1}秒")
model_processed_response = await self._process_response(model_checked_response)
return model_processed_response
@@ -80,11 +87,13 @@ class ResponseGenerator:
logger.info(f"{self.current_model_type}思考，失败")
return None
async def _generate_response_with_model(self, message: MessageRecv, model: LLM_request,thinking_id:str,mode:str = "normal") -> str:
async def _generate_response_with_model(
self, message: MessageRecv, model: LLM_request, thinking_id: str, mode: str = "normal"
) -> str:
sender_name = ""
info_catcher = info_catcher_manager.get_info_catcher(thinking_id)
if message.chat_stream.user_info.user_cardname and message.chat_stream.user_info.user_nickname:
sender_name = (
f"[({message.chat_stream.user_info.user_id}){message.chat_stream.user_info.user_nickname}]"
@@ -116,25 +125,22 @@ class ResponseGenerator:
try:
content, reasoning_content, self.current_model_name = await model.generate_response(prompt)
info_catcher.catch_after_llm_generated(
prompt=prompt,
response=content,
reasoning_content=reasoning_content,
model_name=self.current_model_name)
prompt=prompt, response=content, reasoning_content=reasoning_content, model_name=self.current_model_name
)
except Exception:
logger.exception("生成回复时出错")
return None
return content
async def _check_response_with_model(self, message: MessageRecv, content:str, model: LLM_request,thinking_id:str) -> str:
async def _check_response_with_model(
self, message: MessageRecv, content: str, model: LLM_request, thinking_id: str
) -> str:
_info_catcher = info_catcher_manager.get_info_catcher(thinking_id)
sender_name = ""
if message.chat_stream.user_info.user_cardname and message.chat_stream.user_info.user_nickname:
sender_name = (
@@ -145,8 +151,7 @@ class ResponseGenerator:
sender_name = f"({message.chat_stream.user_info.user_id}){message.chat_stream.user_info.user_nickname}"
else:
sender_name = f"用户({message.chat_stream.user_info.user_id})"
# 构建prompt
timer1 = time.time()
prompt = await prompt_builder._build_prompt_check_response(
@@ -154,7 +159,7 @@ class ResponseGenerator:
message_txt=message.processed_plain_text,
sender_name=sender_name,
stream_id=message.chat_stream.stream_id,
content=content
content=content,
)
timer2 = time.time()
logger.info(f"构建check_prompt: {prompt}")
@@ -162,19 +167,17 @@ class ResponseGenerator:
try:
checked_content, reasoning_content, self.current_model_name = await model.generate_response(prompt)
# info_catcher.catch_after_llm_generated(
# prompt=prompt,
# response=content,
# reasoning_content=reasoning_content,
# model_name=self.current_model_name)
except Exception:
logger.exception("检查回复时出错")
return None
return checked_content
async def _get_emotion_tags(self, content: str, processed_plain_text: str):

8
src/plugins/chat_module/think_flow_chat/think_flow_prompt_builder.py
View File

@@ -110,12 +110,10 @@ class PromptBuilder:
for pattern in rule.get("regex", []):
result = pattern.search(message_txt)
if result:
reaction = rule.get('reaction', '')
reaction = rule.get("reaction", "")
for name, content in result.groupdict().items():
reaction = reaction.replace(f'[{name}]', content)
logger.info(
f"匹配到以下正则表达式：{pattern}，触发反应：{reaction}"
)
reaction = reaction.replace(f"[{name}]", content)
logger.info(f"匹配到以下正则表达式：{pattern}，触发反应：{reaction}")
keywords_reaction_prompt += reaction + "，"
break