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

@@ -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

@@ -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

@@ -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

@@ -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/shengsuanyun.py

@@ -8,7 +8,7 @@ import openai.types.chat.chat_completion as chat_completion
 
 
 class ShengSuanYunChatCompletions(chatcmpl.OpenAIChatCompletions):
-    """胜算云 ChatCompletion API 请求器"""
+    """胜算云(ModelSpot.AI) ChatCompletion API 请求器"""
 
     client: openai.AsyncClient
 

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,
+        self,
-            content: str,
+        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(
-    async def _chat_messages_chunk(self, query: core_entities.Query) -> typing.AsyncGenerator[llm_entities.MessageChunk, None]:
+        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]:
@@ -496,6 +469,7 @@ class DifyServiceAPIRunner(runner.RequestRunner):
                         continue
                     if '</think>' in chunk['answer'] and not think_end:
                         import re
+
                         content = re.sub(r'^\n</think>', '', chunk['answer'])
                         pending_agent_message += content
                         think_end = True
@@ -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"]}'
-                )
+                )

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
+          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
+          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