From 8adc88a8c0ab426f69a539bf45df6132a7664510 Mon Sep 17 00:00:00 2001
From: fdc <2213070223@qq.com>
Date: Mon, 4 Aug 2025 16:36:02 +0800
Subject: [PATCH] fix:Modify the remove_think that directly retrieves the
 configuration file from the requester, retrieves it from the runner, and
 passes it to the required function

---
 pkg/provider/modelmgr/requester.py               |  4 ++++
 .../modelmgr/requesters/anthropicmsgs.py         |  3 ++-
 pkg/provider/modelmgr/requesters/chatcmpl.py     | 16 ++++++++--------
 .../modelmgr/requesters/deepseekchatcmpl.py      |  4 ++--
 .../modelmgr/requesters/giteeaichatcmpl.py       | 16 ++++++++--------
 .../modelmgr/requesters/modelscopechatcmpl.py    | 11 +++++++----
 .../modelmgr/requesters/moonshotchatcmpl.py      |  3 ++-
 pkg/provider/modelmgr/requesters/ollamachat.py   |  2 ++
 pkg/provider/modelmgr/requesters/ppiochatcmpl.py | 12 ++++++------
 pkg/provider/runners/localagent.py               |  6 +++++-
 10 files changed, 46 insertions(+), 31 deletions(-)

diff --git a/pkg/provider/modelmgr/requester.py b/pkg/provider/modelmgr/requester.py
index 6352b6c5..6af8ba70 100644
--- a/pkg/provider/modelmgr/requester.py
+++ b/pkg/provider/modelmgr/requester.py
@@ -84,6 +84,7 @@ class ProviderAPIRequester(metaclass=abc.ABCMeta):
         messages: typing.List[llm_entities.Message],
         funcs: typing.List[tools_entities.LLMFunction] = None,
         extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
     ) -> llm_entities.Message:
         """调用API
 
@@ -92,6 +93,7 @@ class ProviderAPIRequester(metaclass=abc.ABCMeta):
             messages (typing.List[llm_entities.Message]): 消息对象列表
             funcs (typing.List[tools_entities.LLMFunction], optional): 使用的工具函数列表. Defaults to None.
             extra_args (dict[str, typing.Any], optional): 额外的参数. Defaults to {}.
+            remove_think (bool, optional): 是否移思考中的消息. Defaults to False.
 
         Returns:
             llm_entities.Message: 返回消息对象
@@ -105,6 +107,7 @@ class ProviderAPIRequester(metaclass=abc.ABCMeta):
         messages: typing.List[llm_entities.Message],
         funcs: typing.List[tools_entities.LLMFunction] = None,
         extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
     ) -> llm_entities.MessageChunk:
         """调用API
 
@@ -113,6 +116,7 @@ class ProviderAPIRequester(metaclass=abc.ABCMeta):
             messages (typing.List[llm_entities.Message]): 消息对象列表
             funcs (typing.List[tools_entities.LLMFunction], optional): 使用的工具函数列表. Defaults to None.
             extra_args (dict[str, typing.Any], optional): 额外的参数. Defaults to {}.
+            remove_think (bool, optional): 是否移除思考中的消息. Defaults to False.
 
         Returns:
             typing.AsyncGenerator[llm_entities.MessageChunk]: 返回消息对象
diff --git a/pkg/provider/modelmgr/requesters/anthropicmsgs.py b/pkg/provider/modelmgr/requesters/anthropicmsgs.py
index b195ae51..75f2bf7e 100644
--- a/pkg/provider/modelmgr/requesters/anthropicmsgs.py
+++ b/pkg/provider/modelmgr/requesters/anthropicmsgs.py
@@ -53,6 +53,7 @@ class AnthropicMessages(requester.ProviderAPIRequester):
         messages: typing.List[llm_entities.Message],
         funcs: typing.List[tools_entities.LLMFunction] = None,
         extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
     ) -> llm_entities.Message:
         self.client.api_key = model.token_mgr.get_token()
 
@@ -151,7 +152,7 @@ class AnthropicMessages(requester.ProviderAPIRequester):
             assert type(resp) is anthropic.types.message.Message
 
             for block in resp.content:
-                if block.type == 'thinking':
+                if not remove_think and block.type == 'thinking':
                     args['content'] = '<think>' + block.thinking + '</think>\n' + args['content']
                 elif block.type == 'text':
                     args['content'] += block.text
diff --git a/pkg/provider/modelmgr/requesters/chatcmpl.py b/pkg/provider/modelmgr/requesters/chatcmpl.py
index 51ea864b..04e7da20 100644
--- a/pkg/provider/modelmgr/requesters/chatcmpl.py
+++ b/pkg/provider/modelmgr/requesters/chatcmpl.py
@@ -51,7 +51,7 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
     async def _make_msg(
         self,
         chat_completion: chat_completion.ChatCompletion,
-        pipeline_config: dict[str, typing.Any] = {'trigger': {'misc': {'remove_think': False}}},
+        remove_think: bool = False,
     ) -> llm_entities.Message:
         chatcmpl_message = chat_completion.choices[0].message.model_dump()
         # print(chatcmpl_message.keys(),chatcmpl_message.values())
@@ -63,7 +63,7 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
         reasoning_content = chatcmpl_message['reasoning_content'] if 'reasoning_content' in chatcmpl_message else None
 
         # deepseek的reasoner模型
-        if pipeline_config['trigger'].get('misc', '').get('remove_think'):
+        if remove_think:
             pass
         else:
             if reasoning_content is not None:
@@ -77,7 +77,7 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
 
     async def _make_msg_chunk(
         self,
-        pipeline_config: dict[str, typing.Any],
+        remove_think: bool,
         chat_completion: chat_completion.ChatCompletion,
         idx: int,
     ) -> llm_entities.MessageChunk:
@@ -102,7 +102,7 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
         # print(reasoning_content)
 
         # deepseek的reasoner模型
-        if pipeline_config['trigger'].get('misc', '').get('remove_think'):
+        if remove_think:
             if reasoning_content is not None:
                 pass
             else:
@@ -130,6 +130,7 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
         use_model: requester.RuntimeLLMModel,
         use_funcs: list[tools_entities.LLMFunction] = None,
         extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
     ) -> llm_entities.MessageChunk:
         self.client.api_key = use_model.token_mgr.get_token()
 
@@ -161,10 +162,9 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
         chunk_idx = 0
         self.is_content = False
         tool_calls_map: dict[str, llm_entities.ToolCall] = {}
-        pipeline_config = query.pipeline_config
         async for chunk in self._req_stream(args, extra_body=extra_args):
             # 处理流式消息
-            delta_message = await self._make_msg_chunk(pipeline_config, chunk, chunk_idx)
+            delta_message = await self._make_msg_chunk(remove_think, chunk, chunk_idx)
             if delta_message.content:
                 current_content += delta_message.content
                 delta_message.content = current_content
@@ -199,6 +199,7 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
         use_model: requester.RuntimeLLMModel,
         use_funcs: list[tools_entities.LLMFunction] = None,
         extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
     ) -> llm_entities.Message:
         self.client.api_key = use_model.token_mgr.get_token()
 
@@ -229,8 +230,7 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
 
         resp = await self._req(args, extra_body=extra_args)
         # 处理请求结果
-        pipeline_config = query.pipeline_config
-        message = await self._make_msg(resp, pipeline_config)
+        message = await self._make_msg(resp, remove_think)
 
         return message
 
diff --git a/pkg/provider/modelmgr/requesters/deepseekchatcmpl.py b/pkg/provider/modelmgr/requesters/deepseekchatcmpl.py
index d75d0fb6..4866caf4 100644
--- a/pkg/provider/modelmgr/requesters/deepseekchatcmpl.py
+++ b/pkg/provider/modelmgr/requesters/deepseekchatcmpl.py
@@ -24,6 +24,7 @@ class DeepseekChatCompletions(chatcmpl.OpenAIChatCompletions):
         use_model: requester.RuntimeLLMModel,
         use_funcs: list[tools_entities.LLMFunction] = None,
         extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
     ) -> llm_entities.Message:
         self.client.api_key = use_model.token_mgr.get_token()
 
@@ -53,8 +54,7 @@ class DeepseekChatCompletions(chatcmpl.OpenAIChatCompletions):
 
         if resp is None:
             raise errors.RequesterError('接口返回为空，请确定模型提供商服务是否正常')
-        pipeline_config = query.pipeline_config
         # 处理请求结果
-        message = await self._make_msg(resp, pipeline_config)
+        message = await self._make_msg(resp, remove_think)
 
         return message
diff --git a/pkg/provider/modelmgr/requesters/giteeaichatcmpl.py b/pkg/provider/modelmgr/requesters/giteeaichatcmpl.py
index 7ac9fa1a..a8d6eb16 100644
--- a/pkg/provider/modelmgr/requesters/giteeaichatcmpl.py
+++ b/pkg/provider/modelmgr/requesters/giteeaichatcmpl.py
@@ -28,6 +28,7 @@ class GiteeAIChatCompletions(chatcmpl.OpenAIChatCompletions):
         use_model: requester.RuntimeLLMModel,
         use_funcs: list[tools_entities.LLMFunction] = None,
         extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
     ) -> llm_entities.Message:
         self.client.api_key = use_model.token_mgr.get_token()
 
@@ -49,16 +50,15 @@ class GiteeAIChatCompletions(chatcmpl.OpenAIChatCompletions):
 
         resp = await self._req(args, extra_body=extra_args)
 
-        pipeline_config = query.pipeline_config
 
-        message = await self._make_msg(resp, pipeline_config)
+        message = await self._make_msg(resp, remove_think)
 
         return message
 
     async def _make_msg(
         self,
         chat_completion: chat_completion.ChatCompletion,
-        pipeline_config: dict[str, typing.Any] = {'trigger': {'misc': {'remove_think': False}}},
+        remove_think: bool,
     ) -> llm_entities.Message:
         chatcmpl_message = chat_completion.choices[0].message.model_dump()
         # print(chatcmpl_message.keys(), chatcmpl_message.values())
@@ -70,7 +70,7 @@ class GiteeAIChatCompletions(chatcmpl.OpenAIChatCompletions):
         reasoning_content = chatcmpl_message['reasoning_content'] if 'reasoning_content' in chatcmpl_message else None
 
         # deepseek的reasoner模型
-        if pipeline_config['trigger'].get('misc', '').get('remove_think'):
+        if remove_think:
             chatcmpl_message['content'] = re.sub(
                 r'<think>.*?</think>', '', chatcmpl_message['content'], flags=re.DOTALL
             )
@@ -86,7 +86,7 @@ class GiteeAIChatCompletions(chatcmpl.OpenAIChatCompletions):
 
     async def _make_msg_chunk(
         self,
-        pipeline_config: dict[str, typing.Any],
+        remove_think: bool,
         chat_completion: chat_completion.ChatCompletion,
         idx: int,
     ) -> llm_entities.MessageChunk:
@@ -110,7 +110,7 @@ class GiteeAIChatCompletions(chatcmpl.OpenAIChatCompletions):
         # print(reasoning_content)
 
         # deepseek的reasoner模型
-        if pipeline_config['trigger'].get('misc', '').get('remove_think'):
+        if remove_think:
             if delta['content'] == '<think>':
                 self.is_think = True
                 delta['content'] = ''
@@ -136,6 +136,7 @@ class GiteeAIChatCompletions(chatcmpl.OpenAIChatCompletions):
         use_model: requester.RuntimeLLMModel,
         use_funcs: list[tools_entities.LLMFunction] = None,
         extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
     ) -> llm_entities.Message | typing.AsyncGenerator[llm_entities.MessageChunk, None]:
         self.client.api_key = use_model.token_mgr.get_token()
 
@@ -167,10 +168,9 @@ class GiteeAIChatCompletions(chatcmpl.OpenAIChatCompletions):
         chunk_idx = 0
         self.is_content = False
         tool_calls_map: dict[str, llm_entities.ToolCall] = {}
-        pipeline_config = query.pipeline_config
         async for chunk in self._req_stream(args, extra_body=extra_args):
             # 处理流式消息
-            delta_message = await self._make_msg_chunk(pipeline_config, chunk, chunk_idx)
+            delta_message = await self._make_msg_chunk(remove_think, chunk, chunk_idx)
             if delta_message.content:
                 current_content += delta_message.content
                 delta_message.content = current_content
diff --git a/pkg/provider/modelmgr/requesters/modelscopechatcmpl.py b/pkg/provider/modelmgr/requesters/modelscopechatcmpl.py
index 04987c19..7895a87e 100644
--- a/pkg/provider/modelmgr/requesters/modelscopechatcmpl.py
+++ b/pkg/provider/modelmgr/requesters/modelscopechatcmpl.py
@@ -174,7 +174,7 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):
 
     async def _make_msg_chunk(
         self,
-        pipeline_config: dict[str, typing.Any],
+        remove_think: bool,
         chat_completion: chat_completion.ChatCompletion,
         idx: int,
     ) -> llm_entities.MessageChunk:
@@ -199,7 +199,7 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):
         # print(reasoning_content)
 
         # deepseek的reasoner模型
-        if pipeline_config['trigger'].get('misc', '').get('remove_think'):
+        if remove_think:
             if reasoning_content is not None:
                 pass
             else:
@@ -227,6 +227,7 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):
         use_model: requester.RuntimeLLMModel,
         use_funcs: list[tools_entities.LLMFunction] = None,
         extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
     ) -> llm_entities.Message | typing.AsyncGenerator[llm_entities.MessageChunk, None]:
         self.client.api_key = use_model.token_mgr.get_token()
 
@@ -258,10 +259,9 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):
         chunk_idx = 0
         self.is_content = False
         tool_calls_map: dict[str, llm_entities.ToolCall] = {}
-        pipeline_config = query.pipeline_config
         async for chunk in self._req_stream(args, extra_body=extra_args):
             # 处理流式消息
-            delta_message = await self._make_msg_chunk(pipeline_config, chunk, chunk_idx)
+            delta_message = await self._make_msg_chunk(remove_think, chunk, chunk_idx)
             if delta_message.content:
                 current_content += delta_message.content
                 delta_message.content = current_content
@@ -296,6 +296,7 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):
         messages: typing.List[llm_entities.Message],
         funcs: typing.List[tools_entities.LLMFunction] = None,
         extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
     ) -> llm_entities.Message:
         req_messages = []  # req_messages 仅用于类内，外部同步由 query.messages 进行
         for m in messages:
@@ -335,6 +336,7 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):
         messages: typing.List[llm_entities.Message],
         funcs: typing.List[tools_entities.LLMFunction] = None,
         extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
     ) -> llm_entities.MessageChunk:
         req_messages = []  # req_messages 仅用于类内，外部同步由 query.messages 进行
         for m in messages:
@@ -354,6 +356,7 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):
                 use_model=model,
                 use_funcs=funcs,
                 extra_args=extra_args,
+                remove_think=remove_think,
             ):
                 yield item
 
diff --git a/pkg/provider/modelmgr/requesters/moonshotchatcmpl.py b/pkg/provider/modelmgr/requesters/moonshotchatcmpl.py
index f3621a09..b8c0e950 100644
--- a/pkg/provider/modelmgr/requesters/moonshotchatcmpl.py
+++ b/pkg/provider/modelmgr/requesters/moonshotchatcmpl.py
@@ -25,6 +25,7 @@ class MoonshotChatCompletions(chatcmpl.OpenAIChatCompletions):
         use_model: requester.RuntimeLLMModel,
         use_funcs: list[tools_entities.LLMFunction] = None,
         extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
     ) -> llm_entities.Message:
         self.client.api_key = use_model.token_mgr.get_token()
 
@@ -54,6 +55,6 @@ class MoonshotChatCompletions(chatcmpl.OpenAIChatCompletions):
         resp = await self._req(args, extra_body=extra_args)
 
         # 处理请求结果
-        message = await self._make_msg(resp)
+        message = await self._make_msg(resp,remove_think)
 
         return message
diff --git a/pkg/provider/modelmgr/requesters/ollamachat.py b/pkg/provider/modelmgr/requesters/ollamachat.py
index 9e6f5a77..0a8943c0 100644
--- a/pkg/provider/modelmgr/requesters/ollamachat.py
+++ b/pkg/provider/modelmgr/requesters/ollamachat.py
@@ -110,6 +110,7 @@ class OllamaChatCompletions(requester.ProviderAPIRequester):
         messages: typing.List[llm_entities.Message],
         funcs: typing.List[tools_entities.LLMFunction] = None,
         extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
     ) -> llm_entities.Message:
         req_messages: list = []
         for m in messages:
@@ -126,6 +127,7 @@ class OllamaChatCompletions(requester.ProviderAPIRequester):
                 use_model=model,
                 use_funcs=funcs,
                 extra_args=extra_args,
+                remove_think=remove_think,
             )
         except asyncio.TimeoutError:
             raise errors.RequesterError('请求超时')
diff --git a/pkg/provider/modelmgr/requesters/ppiochatcmpl.py b/pkg/provider/modelmgr/requesters/ppiochatcmpl.py
index 46da6e01..ca49df10 100644
--- a/pkg/provider/modelmgr/requesters/ppiochatcmpl.py
+++ b/pkg/provider/modelmgr/requesters/ppiochatcmpl.py
@@ -27,7 +27,7 @@ class PPIOChatCompletions(chatcmpl.OpenAIChatCompletions):
     async def _make_msg(
         self,
         chat_completion: chat_completion.ChatCompletion,
-        pipeline_config: dict[str, typing.Any] = {'trigger': {'misc': {'remove_think': False}}},
+        remove_think: bool,
     ) -> llm_entities.Message:
         chatcmpl_message = chat_completion.choices[0].message.model_dump()
         # print(chatcmpl_message.keys(), chatcmpl_message.values())
@@ -39,7 +39,7 @@ class PPIOChatCompletions(chatcmpl.OpenAIChatCompletions):
         reasoning_content = chatcmpl_message['reasoning_content'] if 'reasoning_content' in chatcmpl_message else None
 
         # deepseek的reasoner模型
-        if pipeline_config['trigger'].get('misc', '').get('remove_think'):
+        if remove_think:
             chatcmpl_message['content'] = re.sub(
                 r'<think>.*?</think>', '', chatcmpl_message['content'], flags=re.DOTALL
             )
@@ -55,7 +55,7 @@ class PPIOChatCompletions(chatcmpl.OpenAIChatCompletions):
 
     async def _make_msg_chunk(
         self,
-        pipeline_config: dict[str, typing.Any],
+        remove_think: bool,
         chat_completion: chat_completion.ChatCompletion,
         idx: int,
     ) -> llm_entities.MessageChunk:
@@ -79,7 +79,7 @@ class PPIOChatCompletions(chatcmpl.OpenAIChatCompletions):
         # print(reasoning_content)
 
         # deepseek的reasoner模型
-        if pipeline_config['trigger'].get('misc', '').get('remove_think'):
+        if remove_think:
             if '<think>' in delta['content']:
                 self.is_think = True
                 delta['content'] = ''
@@ -105,6 +105,7 @@ class PPIOChatCompletions(chatcmpl.OpenAIChatCompletions):
         use_model: requester.RuntimeLLMModel,
         use_funcs: list[tools_entities.LLMFunction] = None,
         extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
     ) -> llm_entities.Message | typing.AsyncGenerator[llm_entities.MessageChunk, None]:
         self.client.api_key = use_model.token_mgr.get_token()
 
@@ -136,10 +137,9 @@ class PPIOChatCompletions(chatcmpl.OpenAIChatCompletions):
         chunk_idx = 0
         self.is_content = False
         tool_calls_map: dict[str, llm_entities.ToolCall] = {}
-        pipeline_config = query.pipeline_config
         async for chunk in self._req_stream(args, extra_body=extra_args):
             # 处理流式消息
-            delta_message = await self._make_msg_chunk(pipeline_config, chunk, chunk_idx)
+            delta_message = await self._make_msg_chunk(remove_think, chunk, chunk_idx)
             if delta_message.content:
                 current_content += delta_message.content
                 delta_message.content = current_content
diff --git a/pkg/provider/runners/localagent.py b/pkg/provider/runners/localagent.py
index 0d7bdd0a..03a9b43b 100644
--- a/pkg/provider/runners/localagent.py
+++ b/pkg/provider/runners/localagent.py
@@ -92,9 +92,11 @@ class LocalAgentRunner(runner.RequestRunner):
         is_stream = query.adapter.is_stream_output_supported()
         try:
             is_stream = await query.adapter.is_stream_output_supported()
-
         except AttributeError:
             is_stream = False
+        
+        remove_think = self.pipeline_config['trigger'].get('misc', '').get('remove_think')
+
 
         if not is_stream:
             # 非流式输出，直接请求
@@ -105,6 +107,7 @@ class LocalAgentRunner(runner.RequestRunner):
                 req_messages,
                 query.use_funcs,
                 extra_args=query.use_llm_model.model_entity.extra_args,
+                remove_think=remove_think,
             )
             yield msg
             final_msg = msg
@@ -118,6 +121,7 @@ class LocalAgentRunner(runner.RequestRunner):
                 req_messages,
                 query.use_funcs,
                 extra_args=query.use_llm_model.model_entity.extra_args,
+                remove_think=remove_think,
             ):
                 msg_idx = msg_idx + 1
                 if msg_idx % 8 == 0 or msg.is_final: