feat: add note for remove_think & remove dify remove cot code

* fix: update invoke_embedding to return only embeddings from client.embed

* fix: Fixed the incorrect extraction method of sender ID when converting aiocqhttp reply messages

README.md

@@ -69,7 +69,7 @@ docker compose up -d
 
 ## ✨ 特性
 
-- 💬 大模型对话、Agent：支持多种大模型，适配群聊和私聊；具有多轮对话、工具调用、多模态能力，自带 RAG（知识库）实现，并深度适配 [Dify](https://dify.ai)。
+- 💬 大模型对话、Agent：支持多种大模型，适配群聊和私聊；具有多轮对话、工具调用、多模态、流式输出能力，自带 RAG（知识库）实现，并深度适配 [Dify](https://dify.ai)。
 - 🤖 多平台支持：目前支持 QQ、QQ频道、企业微信、个人微信、飞书、Discord、Telegram 等平台。
 - 🛠️ 高稳定性、功能完备：原生支持访问控制、限速、敏感词过滤等机制；配置简单，支持多种部署方式。支持多流水线配置，不同机器人用于不同应用场景。
 - 🧩 插件扩展、活跃社区：支持事件驱动、组件扩展等插件机制；适配 Anthropic [MCP 协议](https://modelcontextprotocol.io/)；目前已有数百个插件。
@@ -109,6 +109,7 @@ docker compose up -d
 | [智谱AI](https://open.bigmodel.cn/) | ✅ |  |
 | [优云智算](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | ✅ | 大模型和 GPU 资源平台 |
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | 大模型和 GPU 资源平台 |
+| [胜算云](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | 大模型和 GPU 资源平台 |
 | [302.AI](https://share.302.ai/SuTG99) | ✅ | 大模型聚合平台 |
 | [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
 | [Dify](https://dify.ai) | ✅ | LLMOps 平台 |

README_EN.md

@@ -63,7 +63,7 @@ Click the Star and Watch button in the upper right corner of the repository to g
 
 ## ✨ Features
 
-- 💬 Chat with LLM / Agent: Supports multiple LLMs, adapt to group chats and private chats; Supports multi-round conversations, tool calls, and multi-modal capabilities. Built-in RAG (knowledge base) implementation, and deeply integrates with [Dify](https://dify.ai).
+- 💬 Chat with LLM / Agent: Supports multiple LLMs, adapt to group chats and private chats; Supports multi-round conversations, tool calls, multi-modal, and streaming output capabilities. Built-in RAG (knowledge base) implementation, and deeply integrates with [Dify](https://dify.ai).
 - 🤖 Multi-platform Support: Currently supports QQ, QQ Channel, WeCom, personal WeChat, Lark, DingTalk, Discord, Telegram, etc.
 - 🛠️ High Stability, Feature-rich: Native access control, rate limiting, sensitive word filtering, etc. mechanisms; Easy to use, supports multiple deployment methods. Supports multiple pipeline configurations, different bots can be used for different scenarios.
 - 🧩 Plugin Extension, Active Community: Support event-driven, component extension, etc. plugin mechanisms; Integrate Anthropic [MCP protocol](https://modelcontextprotocol.io/); Currently has hundreds of plugins.
@@ -103,6 +103,7 @@ Or visit the demo environment: https://demo.langbot.dev/
 | [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | ✅ | LLM and GPU resource platform |
 | [Dify](https://dify.ai) | ✅ | LLMOps platform |
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | LLM and GPU resource platform |
+| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | LLM and GPU resource platform |
 | [302.AI](https://share.302.ai/SuTG99) | ✅ | LLM gateway(MaaS) |
 | [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
 | [Ollama](https://ollama.com/) | ✅ | Local LLM running platform |

README_JP.md

@@ -63,7 +63,7 @@ LangBotはBTPanelにリストされています。BTPanelをインストール
 
 ## ✨ 機能
 
-- 💬 LLM / エージェントとのチャット: 複数のLLMをサポートし、グループチャットとプライベートチャットに対応。マルチラウンドの会話、ツールの呼び出し、マルチモーダル機能をサポート、RAG（知識ベース）を組み込み、[Dify](https://dify.ai) と深く統合。
+- 💬 LLM / エージェントとのチャット: 複数のLLMをサポートし、グループチャットとプライベートチャットに対応。マルチラウンドの会話、ツールの呼び出し、マルチモーダル、ストリーミング出力機能をサポート、RAG（知識ベース）を組み込み、[Dify](https://dify.ai) と深く統合。
 - 🤖 多プラットフォーム対応: 現在、QQ、QQ チャンネル、WeChat、個人 WeChat、Lark、DingTalk、Discord、Telegram など、複数のプラットフォームをサポートしています。
 - 🛠️ 高い安定性、豊富な機能: ネイティブのアクセス制御、レート制限、敏感な単語のフィルタリングなどのメカニズムをサポート。使いやすく、複数のデプロイ方法をサポート。複数のパイプライン設定をサポートし、異なるボットを異なる用途に使用できます。
 - 🧩 プラグイン拡張、活発なコミュニティ: イベント駆動、コンポーネント拡張などのプラグインメカニズムをサポート。適配 Anthropic [MCP プロトコル](https://modelcontextprotocol.io/)；豊富なエコシステム、現在数百のプラグインが存在。
@@ -102,6 +102,7 @@ LangBotはBTPanelにリストされています。BTPanelをインストール
 | [Zhipu AI](https://open.bigmodel.cn/) | ✅ |  |
 | [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | ✅ | 大模型とGPUリソースプラットフォーム |
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | 大模型とGPUリソースプラットフォーム |
+| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | LLMとGPUリソースプラットフォーム |
 | [302.AI](https://share.302.ai/SuTG99) | ✅ | LLMゲートウェイ(MaaS) |
 | [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
 | [Dify](https://dify.ai) | ✅ | LLMOpsプラットフォーム |

README_TW.md

@@ -65,7 +65,7 @@ docker compose up -d
 
 ## ✨ 特性
 
-- 💬 大模型對話、Agent：支援多種大模型，適配群聊和私聊；具有多輪對話、工具調用、多模態能力，自帶 RAG（知識庫）實現，並深度適配 [Dify](https://dify.ai)。
+- 💬 大模型對話、Agent：支援多種大模型，適配群聊和私聊；具有多輪對話、工具調用、多模態、流式輸出能力，自帶 RAG（知識庫）實現，並深度適配 [Dify](https://dify.ai)。
 - 🤖 多平台支援：目前支援 QQ、QQ頻道、企業微信、個人微信、飛書、Discord、Telegram 等平台。
 - 🛠️ 高穩定性、功能完備：原生支援訪問控制、限速、敏感詞過濾等機制；配置簡單，支援多種部署方式。支援多流水線配置，不同機器人用於不同應用場景。
 - 🧩 外掛擴展、活躍社群：支援事件驅動、組件擴展等外掛機制；適配 Anthropic [MCP 協議](https://modelcontextprotocol.io/)；目前已有數百個外掛。
@@ -102,6 +102,7 @@ docker compose up -d
 | [Anthropic](https://www.anthropic.com/) | ✅ |  |
 | [xAI](https://x.ai/) | ✅ |  |
 | [智譜AI](https://open.bigmodel.cn/) | ✅ |  |
+| [勝算雲](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | 大模型和 GPU 資源平台 |
 | [優雲智算](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | ✅ | 大模型和 GPU 資源平台 |
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | 大模型和 GPU 資源平台 |
 | [302.AI](https://share.302.ai/SuTG99) | ✅ | 大模型聚合平台 |

pkg/persistence/migrations/dbm005_pipeline_remove_cot_config.py

@@ -20,7 +20,7 @@ class DBMigratePipelineRemoveCotConfig(migration.DBMigration):
             config = serialized_pipeline['config']
 
             if 'remove-think' not in config['output']['misc']:
-                config['output']['misc']['remove-think'] = True
+                config['output']['misc']['remove-think'] = False
 
             await self.ap.persistence_mgr.execute_async(
                 sqlalchemy.update(persistence_pipeline.LegacyPipeline)

pkg/platform/sources/aiocqhttp.py

@@ -266,7 +266,7 @@ class AiocqhttpMessageConverter(adapter.MessageConverter):
                     await process_message_data(msg_data, reply_list)
 
                 reply_msg = platform_message.Quote(
-                    message_id=msg.data['id'], sender_id=msg_datas['user_id'], origin=reply_list
+                    message_id=msg.data['id'], sender_id=msg_datas['sender']['user_id'], origin=reply_list
                 )
                 yiri_msg_list.append(reply_msg)
 

pkg/provider/modelmgr/requesters/geminichatcmpl.py

@@ -4,6 +4,13 @@ import typing
 
 from . import chatcmpl
 
+import uuid
+
+from .. import errors, requester
+from ....core import entities as core_entities
+from ... import entities as llm_entities
+from ...tools import entities as tools_entities
+
 
 class GeminiChatCompletions(chatcmpl.OpenAIChatCompletions):
     """Google Gemini API 请求器"""
@@ -12,3 +19,127 @@ class GeminiChatCompletions(chatcmpl.OpenAIChatCompletions):
         'base_url': 'https://generativelanguage.googleapis.com/v1beta/openai',
         'timeout': 120,
     }
+
+
+    async def _closure_stream(
+        self,
+        query: core_entities.Query,
+        req_messages: list[dict],
+        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()
+
+        args = {}
+        args['model'] = use_model.model_entity.name
+
+        if use_funcs:
+            tools = await self.ap.tool_mgr.generate_tools_for_openai(use_funcs)
+            if tools:
+                args['tools'] = tools
+
+        # 设置此次请求中的messages
+        messages = req_messages.copy()
+
+        # 检查vision
+        for msg in messages:
+            if 'content' in msg and isinstance(msg['content'], list):
+                for me in msg['content']:
+                    if me['type'] == 'image_base64':
+                        me['image_url'] = {'url': me['image_base64']}
+                        me['type'] = 'image_url'
+                        del me['image_base64']
+
+        args['messages'] = messages
+        args['stream'] = True
+
+        # 流式处理状态
+        tool_calls_map: dict[str, llm_entities.ToolCall] = {}
+        chunk_idx = 0
+        thinking_started = False
+        thinking_ended = False
+        role = 'assistant'  # 默认角色
+        tool_id = ""
+        tool_name = ''
+        # accumulated_reasoning = ''  # 仅用于判断何时结束思维链
+
+        async for chunk in self._req_stream(args, extra_body=extra_args):
+            # 解析 chunk 数据
+
+            if hasattr(chunk, 'choices') and chunk.choices:
+                choice = chunk.choices[0]
+                delta = choice.delta.model_dump() if hasattr(choice, 'delta') else {}
+
+                finish_reason = getattr(choice, 'finish_reason', None)
+            else:
+                delta = {}
+                finish_reason = None
+            # 从第一个 chunk 获取 role，后续使用这个 role
+            if 'role' in delta and delta['role']:
+                role = delta['role']
+
+            # 获取增量内容
+            delta_content = delta.get('content', '')
+            reasoning_content = delta.get('reasoning_content', '')
+
+            # 处理 reasoning_content
+            if reasoning_content:
+                # accumulated_reasoning += reasoning_content
+                # 如果设置了 remove_think，跳过 reasoning_content
+                if remove_think:
+                    chunk_idx += 1
+                    continue
+
+                # 第一次出现 reasoning_content，添加 <think> 开始标签
+                if not thinking_started:
+                    thinking_started = True
+                    delta_content = '<think>\n' + reasoning_content
+                else:
+                    # 继续输出 reasoning_content
+                    delta_content = reasoning_content
+            elif thinking_started and not thinking_ended and delta_content:
+                # reasoning_content 结束，normal content 开始，添加 </think> 结束标签
+                thinking_ended = True
+                delta_content = '\n</think>\n' + delta_content
+
+            # 处理 content 中已有的 <think> 标签（如果需要移除）
+            # if delta_content and remove_think and '<think>' in delta_content:
+            #     import re
+            #
+            #     # 移除 <think> 标签及其内容
+            #     delta_content = re.sub(r'<think>.*?</think>', '', delta_content, flags=re.DOTALL)
+
+            # 处理工具调用增量
+            # delta_tool_calls = None
+            if delta.get('tool_calls'):
+                for tool_call in delta['tool_calls']:
+                    if tool_call['id'] == '' and tool_id == '':
+                        tool_id = str(uuid.uuid4())
+                    if  tool_call['function']['name']:
+                        tool_name = tool_call['function']['name']
+                    tool_call['id'] = tool_id
+                    tool_call['function']['name'] = tool_name
+                    if tool_call['type'] is None:
+                        tool_call['type'] = 'function'
+
+
+
+            # 跳过空的第一个 chunk（只有 role 没有内容）
+            if chunk_idx == 0 and not delta_content and not reasoning_content and not delta.get('tool_calls'):
+                chunk_idx += 1
+                continue
+            # 构建 MessageChunk - 只包含增量内容
+            chunk_data = {
+                'role': role,
+                'content': delta_content if delta_content else None,
+                'tool_calls': delta.get('tool_calls'),
+                'is_final': bool(finish_reason),
+            }
+
+            # 移除 None 值
+            chunk_data = {k: v for k, v in chunk_data.items() if v is not None}
+
+            yield llm_entities.MessageChunk(**chunk_data)
+            chunk_idx += 1

pkg/provider/modelmgr/requesters/ollamachat.py

@@ -139,8 +139,8 @@ class OllamaChatCompletions(requester.ProviderAPIRequester):
         input_text: list[str],
         extra_args: dict[str, typing.Any] = {},
     ) -> list[list[float]]:
-        return await self.client.embed(
+        return (await self.client.embed(
             model=model.model_entity.name,
             input=input_text,
             **extra_args,
-        )
+        )).embeddings

pkg/provider/modelmgr/requesters/shengsuanyun.py

@@ -0,0 +1,32 @@
+from __future__ import annotations
+
+import openai
+import typing
+
+from . import chatcmpl
+import openai.types.chat.chat_completion as chat_completion
+
+
+class ShengSuanYunChatCompletions(chatcmpl.OpenAIChatCompletions):
+    """胜算云(ModelSpot.AI) ChatCompletion API 请求器"""
+
+    client: openai.AsyncClient
+
+    default_config: dict[str, typing.Any] = {
+        'base_url': 'https://router.shengsuanyun.com/api/v1',
+        'timeout': 120,
+    }
+
+    async def _req(
+        self,
+        args: dict,
+        extra_body: dict = {},
+    ) -> chat_completion.ChatCompletion:
+        return await self.client.chat.completions.create(
+            **args,
+            extra_body=extra_body,
+            extra_headers={
+                'HTTP-Referer': 'https://langbot.app',
+                'X-Title': 'LangBot',
+            },
+        )

pkg/provider/modelmgr/requesters/shengsuanyun.yaml

@@ -0,0 +1,38 @@
+apiVersion: v1
+kind: LLMAPIRequester
+metadata:
+  name: shengsuanyun-chat-completions
+  label:
+    en_US: ShengSuanYun
+    zh_Hans: 胜算云
+  icon: shengsuanyun.svg
+spec:
+  config:
+    - name: base_url
+      label:
+        en_US: Base URL
+        zh_Hans: 基础 URL
+      type: string
+      required: true
+      default: "https://router.shengsuanyun.com/api/v1"
+    - name: args
+      label:
+        en_US: Args
+        zh_Hans: 附加参数
+      type: object
+      required: true
+      default: {}
+    - name: timeout
+      label:
+        en_US: Timeout
+        zh_Hans: 超时时间
+      type: int
+      required: true
+      default: 120
+  support_type:
+    - llm
+    - text-embedding
+execution:
+  python:
+    path: ./shengsuanyun.py
+    attr: ShengSuanYunChatCompletions

pkg/provider/runners/difysvapi.py

@@ -3,7 +3,6 @@ from __future__ import annotations
 import typing
 import json
 import uuid
-import re
 import base64
 
 
@@ -38,33 +37,9 @@ class DifyServiceAPIRunner(runner.RequestRunner):
             base_url=self.pipeline_config['ai']['dify-service-api']['base-url'],
         )
 
-    def _try_convert_thinking(self, resp_text: str) -> str:
-        """尝试转换 Dify 的思考提示"""
-        if not resp_text.startswith(
-            '<details style="color:gray;background-color: #f8f8f8;padding: 8px;border-radius: 4px;" open> <summary> Thinking... </summary>'
-        ):
-            return resp_text
-
-        if self.pipeline_config['ai']['dify-service-api']['thinking-convert'] == 'original':
-            return resp_text
-
-        if self.pipeline_config['ai']['dify-service-api']['thinking-convert'] == 'remove':
-            return re.sub(
-                r'<details style="color:gray;background-color: #f8f8f8;padding: 8px;border-radius: 4px;" open> <summary> Thinking... </summary>.*?</details>',
-                '',
-                resp_text,
-                flags=re.DOTALL,
-            )
-
-        if self.pipeline_config['ai']['dify-service-api']['thinking-convert'] == 'plain':
-            pattern = r'<details style="color:gray;background-color: #f8f8f8;padding: 8px;border-radius: 4px;" open> <summary> Thinking... </summary>(.*?)</details>'
-            thinking_text = re.search(pattern, resp_text, flags=re.DOTALL)
-            content_text = re.sub(pattern, '', resp_text, flags=re.DOTALL)
-            return f'<think>{thinking_text.group(1)}</think>\n{content_text}'
-
     def _process_thinking_content(
-            self,
-            content: str,
+        self,
+        content: str,
     ) -> tuple[str, str]:
         """处理思维链内容
 
@@ -354,8 +329,9 @@ class DifyServiceAPIRunner(runner.RequestRunner):
 
                 yield msg
 
-
-    async def _chat_messages_chunk(self, query: core_entities.Query) -> typing.AsyncGenerator[llm_entities.MessageChunk, None]:
+    async def _chat_messages_chunk(
+        self, query: core_entities.Query
+    ) -> typing.AsyncGenerator[llm_entities.MessageChunk, None]:
         """调用聊天助手"""
         cov_id = query.session.using_conversation.uuid or ''
         query.variables['conversation_id'] = cov_id
@@ -371,8 +347,6 @@ class DifyServiceAPIRunner(runner.RequestRunner):
             for image_id in image_ids
         ]
 
-        mode = 'basic'  # 标记是基础编排还是工作流编排
-
         basic_mode_pending_chunk = ''
 
         inputs = {}
@@ -411,6 +385,7 @@ class DifyServiceAPIRunner(runner.RequestRunner):
                         continue
                     if '</think>' in chunk['answer'] and not think_end:
                         import re
+
                         content = re.sub(r'^\n</think>', '', chunk['answer'])
                         basic_mode_pending_chunk += content
                         think_end = True
@@ -433,13 +408,11 @@ class DifyServiceAPIRunner(runner.RequestRunner):
                     is_final=is_final,
                 )
 
-
         if chunk is None:
             raise errors.DifyAPIError('Dify API 没有返回任何响应，请检查网络连接和API配置')
 
         query.session.using_conversation.uuid = chunk['conversation_id']
 
-
     async def _agent_chat_messages_chunk(
         self, query: core_entities.Query
     ) -> typing.AsyncGenerator[llm_entities.MessageChunk, None]:
@@ -496,10 +469,11 @@ class DifyServiceAPIRunner(runner.RequestRunner):
                         continue
                     if '</think>' in chunk['answer'] and not think_end:
                         import re
+
                         content = re.sub(r'^\n</think>', '', chunk['answer'])
                         pending_agent_message += content
                         think_end = True
-                    elif think_end:
+                    elif think_end or not think_start:
                         pending_agent_message += chunk['answer']
                     if think_start:
                         continue
@@ -509,7 +483,6 @@ class DifyServiceAPIRunner(runner.RequestRunner):
             elif chunk['event'] == 'message_end':
                 is_final = True
             else:
-
                 if chunk['event'] == 'agent_thought':
                     if chunk['tool'] != '' and chunk['observation'] != '':  # 工具调用结果，跳过
                         continue
@@ -543,7 +516,6 @@ class DifyServiceAPIRunner(runner.RequestRunner):
                             role='assistant',
                             content=[llm_entities.ContentElement.from_image_url(image_url)],
                             is_final=is_final,
-
                         )
 
                 if chunk['event'] == 'error':
@@ -560,7 +532,9 @@ class DifyServiceAPIRunner(runner.RequestRunner):
 
         query.session.using_conversation.uuid = chunk['conversation_id']
 
-    async def _workflow_messages_chunk(self, query: core_entities.Query) -> typing.AsyncGenerator[llm_entities.MessageChunk, None]:
+    async def _workflow_messages_chunk(
+        self, query: core_entities.Query
+    ) -> typing.AsyncGenerator[llm_entities.MessageChunk, None]:
         """调用工作流"""
 
         if not query.session.using_conversation.uuid:
@@ -618,6 +592,7 @@ class DifyServiceAPIRunner(runner.RequestRunner):
                         continue
                     if '</think>' in chunk['data']['text'] and not think_end:
                         import re
+
                         content = re.sub(r'^\n</think>', '', chunk['data']['text'])
                         workflow_contents += content
                         think_end = True
@@ -650,7 +625,6 @@ class DifyServiceAPIRunner(runner.RequestRunner):
 
                 yield msg
 
-
             if messsage_idx % 8 == 0 or is_final:
                 yield llm_entities.MessageChunk(
                     role='assistant',
@@ -694,4 +668,4 @@ class DifyServiceAPIRunner(runner.RequestRunner):
             else:
                 raise errors.DifyAPIError(
                     f'不支持的 Dify 应用类型: {self.pipeline_config["ai"]["dify-service-api"]["app-type"]}'
-                )
+                )

pkg/utils/constants.py

@@ -1,4 +1,4 @@
-semantic_version = 'v4.2.0'
+semantic_version = 'v4.2.1'
 
 required_database_version = 5
 """Tag the version of the database schema, used to check if the database needs to be migrated"""

templates/default-pipeline-config.json

@@ -51,7 +51,6 @@
             "base-url": "https://api.dify.ai/v1",
             "app-type": "chat",
             "api-key": "your-api-key",
-            "thinking-convert": "plain",
             "timeout": 30
         },
         "dashscope-app-api": {
@@ -88,7 +87,7 @@
             "at-sender": true,
             "quote-origin": true,
             "track-function-calls": false,
-            "remove-think": true
+            "remove-think": false
         }
     }
 }

templates/metadata/pipeline/ai.yaml

@@ -118,28 +118,6 @@ stages:
           zh_Hans: API 密钥
         type: string
         required: true
-      - name: thinking-convert
-        label:
-          en_US: CoT Convert
-          zh_Hans: 思维链转换策略
-        type: select
-        required: true
-        default: plain
-        options:
-          - name: plain
-            label:
-              en_US: Convert to <think>...</think>
-              zh_Hans: 转换成 <think>...</think>
-          - name: original
-            label:
-              en_US: Original
-              zh_Hans: 原始
-          - name: remove
-            label:
-              en_US: Remove
-              zh_Hans: 移除
-
-
   - name: dashscope-app-api
     label:
       en_US: Aliyun Dashscope App API

templates/metadata/pipeline/output.yaml

@@ -110,8 +110,8 @@ stages:
           en_US: Remove CoT
           zh_Hans: 删除思维链
         description:
-          en_US: If enabled, LangBot will remove the LLM thought content in response
-          zh_Hans: 如果启用，将自动删除大模型回复中的模型思考内容
+          en_US: 'If enabled, LangBot will remove the LLM thought content in response. Note: When using streaming response, removing CoT may cause the first token to wait for a long time.'
+          zh_Hans: '如果启用，将自动删除大模型回复中的模型思考内容。注意：当您使用流式响应时，删除思维链可能会导致首个 Token 的等待时间过长'
         type: boolean
         required: true
-        default: true
+        default: false