V4.8.20 feature (#3686)

* Aiproxy (#3649)

* model config

* feat: model config ui

* perf: rename variable

* feat: custom request url

* perf: model buffer

* perf: init model

* feat: json model config

* auto login

* fix: ts

* update packages

* package

* fix: dockerfile

* feat: usage filter & export & dashbord (#3538)

* feat: usage filter & export & dashbord

* adjust ui

* fix tmb scroll

* fix code & selecte all

* merge

* perf: usages list；perf: move components (#3654)

* perf: usages list

* team sub plan load

* perf: usage dashboard code

* perf: dashboard ui

* perf: move components

* add default model config (#3653)

* 4.8.20 test (#3656)

* provider

* perf: model config

* model perf (#3657)

* fix: model

* dataset quote

* perf: model config

* model tag

* doubao model config

* perf: config model

* feat: model test

* fix: POST 500 error on dingtalk bot (#3655)

* feat: default model (#3662)

* move model config

* feat: default model

* fix: false triggerd org selection (#3661)

* export usage csv i18n (#3660)

* export usage csv i18n

* fix build

* feat: markdown extension (#3663)

* feat: markdown extension

* media cros

* rerank test

* default price

* perf: default model

* fix: cannot custom provider

* fix: default model select

* update bg

* perf: default model selector

* fix: usage export

* i18n

* fix: rerank

* update init extension

* perf: ip limit check

* doubao model order

* web default modle

* perf: tts selector

* perf: tts error

* qrcode package

* reload buffer (#3665)

* reload buffer

* reload buffer

* tts selector

* fix: err tip (#3666)

* fix: err tip

* perf: training queue

* doc

* fix interactive edge (#3659)

* fix interactive edge

* fix

* comment

* add gemini model

* fix: chat model select

* perf: supplement assistant empty response (#3669)

* perf: supplement assistant empty response

* check array

* perf: max_token count;feat: support resoner output;fix: member scroll (#3681)

* perf: supplement assistant empty response

* check array

* perf: max_token count

* feat: support resoner output

* member scroll

* update provider order

* i18n

* fix: stream response (#3682)

* perf: supplement assistant empty response

* check array

* fix: stream response

* fix: model config cannot set to null

* fix: reasoning response (#3684)

* perf: supplement assistant empty response

* check array

* fix: reasoning response

* fix: reasoning response

* doc (#3685)

* perf: supplement assistant empty response

* check array

* doc

* lock

* animation

* update doc

* update compose

* doc

* doc

---------

Co-authored-by: heheer <heheer@sealos.io>
Co-authored-by: a.e. <49438478+I-Info@users.noreply.github.com>

packages/service/core/workflow/dispatch/agent/classifyQuestion.ts

@@ -13,7 +13,7 @@ import type { ModuleDispatchProps } from '@fastgpt/global/core/workflow/runtime/
 import { replaceVariable } from '@fastgpt/global/common/string/tools';
 import { Prompt_CQJson } from '@fastgpt/global/core/ai/prompt/agent';
 import { LLMModelItemType } from '@fastgpt/global/core/ai/model.d';
-import { ModelTypeEnum, getLLMModel } from '../../../ai/model';
+import { getLLMModel } from '../../../ai/model';
 import { getHistories } from '../utils';
 import { formatModelChars2Points } from '../../../../support/wallet/usage/utils';
 import { DispatchNodeResultType } from '@fastgpt/global/core/workflow/runtime/type';
@@ -22,6 +22,7 @@ import { getHandleId } from '@fastgpt/global/core/workflow/utils';
 import { loadRequestMessages } from '../../../chat/utils';
 import { llmCompletionsBodyFormat } from '../../../ai/utils';
 import { addLog } from '../../../../common/system/log';
+import { ModelTypeEnum } from '../../../../../global/core/ai/model';
 
 type Props = ModuleDispatchProps<{
   [NodeInputKeyEnum.aiModel]: string;

packages/service/core/workflow/dispatch/agent/extract.ts

@@ -1,5 +1,5 @@
 import { chats2GPTMessages } from '@fastgpt/global/core/chat/adapt';
-import { filterGPTMessageByMaxTokens, loadRequestMessages } from '../../../chat/utils';
+import { filterGPTMessageByMaxContext, loadRequestMessages } from '../../../chat/utils';
 import type { ChatItemType } from '@fastgpt/global/core/chat/type.d';
 import {
   countMessagesTokens,
@@ -16,7 +16,7 @@ import { Prompt_ExtractJson } from '@fastgpt/global/core/ai/prompt/agent';
 import { replaceVariable, sliceJsonStr } from '@fastgpt/global/common/string/tools';
 import { LLMModelItemType } from '@fastgpt/global/core/ai/model.d';
 import { getHistories } from '../utils';
-import { ModelTypeEnum, getLLMModel } from '../../../ai/model';
+import { getLLMModel } from '../../../ai/model';
 import { formatModelChars2Points } from '../../../../support/wallet/usage/utils';
 import json5 from 'json5';
 import {
@@ -28,6 +28,7 @@ import { ChatCompletionRequestMessageRoleEnum } from '@fastgpt/global/core/ai/co
 import { DispatchNodeResultType } from '@fastgpt/global/core/workflow/runtime/type';
 import { chatValue2RuntimePrompt } from '@fastgpt/global/core/chat/adapt';
 import { llmCompletionsBodyFormat } from '../../../ai/utils';
+import { ModelTypeEnum } from '../../../../../global/core/ai/model';
 
 type Props = ModuleDispatchProps<{
   [NodeInputKeyEnum.history]?: ChatItemType[];
@@ -174,9 +175,9 @@ ${description ? `- ${description}` : ''}
     }
   ];
   const adaptMessages = chats2GPTMessages({ messages, reserveId: false });
-  const filterMessages = await filterGPTMessageByMaxTokens({
+  const filterMessages = await filterGPTMessageByMaxContext({
     messages: adaptMessages,
-    maxTokens: extractModel.maxContext
+    maxContext: extractModel.maxContext
   });
   const requestMessages = await loadRequestMessages({
     messages: filterMessages,

packages/service/core/workflow/dispatch/agent/runTool/functionCall.ts

@@ -1,5 +1,5 @@
 import { createChatCompletion } from '../../../../ai/config';
-import { filterGPTMessageByMaxTokens, loadRequestMessages } from '../../../../chat/utils';
+import { filterGPTMessageByMaxContext, loadRequestMessages } from '../../../../chat/utils';
 import {
   ChatCompletion,
   StreamChatType,
@@ -172,10 +172,14 @@ export const runToolWithFunctionCall = async (
     };
   });
 
+  const max_tokens = computedMaxToken({
+    model: toolModel,
+    maxToken
+  });
   const filterMessages = (
-    await filterGPTMessageByMaxTokens({
+    await filterGPTMessageByMaxContext({
       messages,
-      maxTokens: toolModel.maxContext - 300 // filter token. not response maxToken
+      maxContext: toolModel.maxContext - (max_tokens || 0) // filter token. not response maxToken
     })
   ).map((item) => {
     if (item.role === ChatCompletionRequestMessageRoleEnum.Assistant && item.function_call) {
@@ -190,16 +194,11 @@ export const runToolWithFunctionCall = async (
     }
     return item;
   });
-  const [requestMessages, max_tokens] = await Promise.all([
+  const [requestMessages] = await Promise.all([
     loadRequestMessages({
       messages: filterMessages,
       useVision: toolModel.vision && aiChatVision,
       origin: requestOrigin
-    }),
-    computedMaxToken({
-      model: toolModel,
-      maxToken,
-      filterMessages
     })
   ]);
   const requestBody = llmCompletionsBodyFormat(

packages/service/core/workflow/dispatch/agent/runTool/index.ts

@@ -4,7 +4,7 @@ import type {
   DispatchNodeResultType,
   RuntimeNodeItemType
 } from '@fastgpt/global/core/workflow/runtime/type';
-import { ModelTypeEnum, getLLMModel } from '../../../../ai/model';
+import { getLLMModel } from '../../../../ai/model';
 import { filterToolNodeIdByEdges, getHistories } from '../../utils';
 import { runToolWithToolChoice } from './toolChoice';
 import { DispatchToolModuleProps, ToolNodeItemType } from './type.d';
@@ -30,6 +30,7 @@ import { parseUrlToFileType } from '@fastgpt/global/common/file/tools';
 import { Prompt_DocumentQuote } from '@fastgpt/global/core/ai/prompt/AIChat';
 import { FlowNodeTypeEnum } from '@fastgpt/global/core/workflow/node/constant';
 import { postTextCensor } from '../../../../../common/api/requestPlusApi';
+import { ModelTypeEnum } from '@fastgpt/global/core/ai/model';
 
 type Response = DispatchNodeResultType<{
   [NodeOutputKeyEnum.answerText]: string;

packages/service/core/workflow/dispatch/agent/runTool/promptCall.ts

@@ -1,5 +1,5 @@
 import { createChatCompletion } from '../../../../ai/config';
-import { filterGPTMessageByMaxTokens, loadRequestMessages } from '../../../../chat/utils';
+import { filterGPTMessageByMaxContext, loadRequestMessages } from '../../../../chat/utils';
 import {
   ChatCompletion,
   StreamChatType,
@@ -196,21 +196,20 @@ export const runToolWithPromptCall = async (
     return Promise.reject('Prompt call invalid input');
   }
 
-  const filterMessages = await filterGPTMessageByMaxTokens({
+  const max_tokens = computedMaxToken({
+    model: toolModel,
+    maxToken
+  });
+  const filterMessages = await filterGPTMessageByMaxContext({
     messages,
-    maxTokens: toolModel.maxContext - 500 // filter token. not response maxToken
+    maxContext: toolModel.maxContext - (max_tokens || 0) // filter token. not response maxToken
   });
 
-  const [requestMessages, max_tokens] = await Promise.all([
+  const [requestMessages] = await Promise.all([
     loadRequestMessages({
       messages: filterMessages,
       useVision: toolModel.vision && aiChatVision,
       origin: requestOrigin
-    }),
-    computedMaxToken({
-      model: toolModel,
-      maxToken,
-      filterMessages
     })
   ]);
   const requestBody = llmCompletionsBodyFormat(

packages/service/core/workflow/dispatch/agent/runTool/toolChoice.ts

@@ -1,5 +1,5 @@
 import { createChatCompletion } from '../../../../ai/config';
-import { filterGPTMessageByMaxTokens, loadRequestMessages } from '../../../../chat/utils';
+import { filterGPTMessageByMaxContext, loadRequestMessages } from '../../../../chat/utils';
 import {
   ChatCompletion,
   ChatCompletionMessageToolCall,
@@ -228,11 +228,16 @@ export const runToolWithToolChoice = async (
     };
   });
 
+  const max_tokens = computedMaxToken({
+    model: toolModel,
+    maxToken
+  });
+
   // Filter histories by maxToken
   const filterMessages = (
-    await filterGPTMessageByMaxTokens({
+    await filterGPTMessageByMaxContext({
       messages,
-      maxTokens: toolModel.maxContext - 300 // filter token. not response maxToken
+      maxContext: toolModel.maxContext - (max_tokens || 0) // filter token. not response maxToken
     })
   ).map((item) => {
     if (item.role === 'assistant' && item.tool_calls) {
@@ -248,16 +253,11 @@ export const runToolWithToolChoice = async (
     return item;
   });
 
-  const [requestMessages, max_tokens] = await Promise.all([
+  const [requestMessages] = await Promise.all([
     loadRequestMessages({
       messages: filterMessages,
       useVision: toolModel.vision && aiChatVision,
       origin: requestOrigin
-    }),
-    computedMaxToken({
-      model: toolModel,
-      maxToken,
-      filterMessages
     })
   ]);
   const requestBody = llmCompletionsBodyFormat(
@@ -272,7 +272,7 @@ export const runToolWithToolChoice = async (
     },
     toolModel
   );
-  // console.log(JSON.stringify(requestBody, null, 2), '==requestBody');
+  // console.log(JSON.stringify(requestMessages, null, 2), '==requestBody');
   /* Run llm */
   const {
     response: aiResponse,

packages/service/core/workflow/dispatch/chat/oneapi.ts

@@ -1,5 +1,5 @@
 import type { NextApiResponse } from 'next';
-import { filterGPTMessageByMaxTokens, loadRequestMessages } from '../../../chat/utils';
+import { filterGPTMessageByMaxContext, loadRequestMessages } from '../../../chat/utils';
 import type { ChatItemType, UserChatItemValueItemType } from '@fastgpt/global/core/chat/type.d';
 import { ChatRoleEnum } from '@fastgpt/global/core/chat/constants';
 import { SseResponseEventEnum } from '@fastgpt/global/core/workflow/runtime/constants';
@@ -33,7 +33,7 @@ import type { AIChatNodeProps } from '@fastgpt/global/core/workflow/runtime/type
 import { replaceVariable } from '@fastgpt/global/common/string/tools';
 import type { ModuleDispatchProps } from '@fastgpt/global/core/workflow/runtime/type';
 import { responseWriteController } from '../../../../common/response';
-import { getLLMModel, ModelTypeEnum } from '../../../ai/model';
+import { getLLMModel } from '../../../ai/model';
 import type { SearchDataResponseItemType } from '@fastgpt/global/core/dataset/type';
 import { NodeInputKeyEnum, NodeOutputKeyEnum } from '@fastgpt/global/core/workflow/constants';
 import { DispatchNodeResponseKeyEnum } from '@fastgpt/global/core/workflow/runtime/constants';
@@ -47,6 +47,7 @@ import { AiChatQuoteRoleType } from '@fastgpt/global/core/workflow/template/syst
 import { getFileContentFromLinks, getHistoryFileLinks } from '../tools/readFiles';
 import { parseUrlToFileType } from '@fastgpt/global/common/file/tools';
 import { i18nT } from '../../../../../web/i18n/utils';
+import { ModelTypeEnum } from '@fastgpt/global/core/ai/model';
 
 export type ChatProps = ModuleDispatchProps<
   AIChatNodeProps & {
@@ -57,6 +58,7 @@ export type ChatProps = ModuleDispatchProps<
 >;
 export type ChatResponse = DispatchNodeResultType<{
   [NodeOutputKeyEnum.answerText]: string;
+  [NodeOutputKeyEnum.reasoningText]?: string;
   [NodeOutputKeyEnum.history]: ChatItemType[];
 }>;
 
@@ -86,22 +88,24 @@ export const dispatchChatCompletion = async (props: ChatProps): Promise<ChatResp
       quoteTemplate,
       quotePrompt,
       aiChatVision,
+      aiChatReasoning = true,
       fileUrlList: fileLinks, // node quote file links
       stringQuoteText //abandon
     }
   } = props;
   const { files: inputFiles } = chatValue2RuntimePrompt(query); // Chat box input files
 
-  stream = stream && isResponseAnswerText;
-
-  const chatHistories = getHistories(history, histories);
-  quoteQA = checkQuoteQAValue(quoteQA);
-
   const modelConstantsData = getLLMModel(model);
   if (!modelConstantsData) {
     return Promise.reject('The chat model is undefined, you need to select a chat model.');
   }
 
+  stream = stream && isResponseAnswerText;
+  aiChatReasoning = !!aiChatReasoning && !!modelConstantsData.reasoning;
+
+  const chatHistories = getHistories(history, histories);
+  quoteQA = checkQuoteQAValue(quoteQA);
+
   const [{ datasetQuoteText }, { documentQuoteText, userFiles }] = await Promise.all([
     filterDatasetQuote({
       quoteQA,
@@ -123,9 +127,15 @@ export const dispatchChatCompletion = async (props: ChatProps): Promise<ChatResp
     return Promise.reject(i18nT('chat:AI_input_is_empty'));
   }
 
+  const max_tokens = computedMaxToken({
+    model: modelConstantsData,
+    maxToken
+  });
+
   const [{ filterMessages }] = await Promise.all([
     getChatMessages({
       model: modelConstantsData,
+      maxTokens: max_tokens,
       histories: chatHistories,
       useDatasetQuote: quoteQA !== undefined,
       datasetQuoteText,
@@ -136,8 +146,8 @@ export const dispatchChatCompletion = async (props: ChatProps): Promise<ChatResp
       userFiles,
       documentQuoteText
     }),
+    // Censor = true and system key, will check content
     (() => {
-      // censor model and system key
       if (modelConstantsData.censor && !externalProvider.openaiAccount?.key) {
         return postTextCensor({
           text: `${systemPrompt}
@@ -148,18 +158,11 @@ export const dispatchChatCompletion = async (props: ChatProps): Promise<ChatResp
     })()
   ]);
 
-  const [requestMessages, max_tokens] = await Promise.all([
-    loadRequestMessages({
-      messages: filterMessages,
-      useVision: modelConstantsData.vision && aiChatVision,
-      origin: requestOrigin
-    }),
-    computedMaxToken({
-      model: modelConstantsData,
-      maxToken,
-      filterMessages
-    })
-  ]);
+  const requestMessages = await loadRequestMessages({
+    messages: filterMessages,
+    useVision: modelConstantsData.vision && aiChatVision,
+    origin: requestOrigin
+  });
 
   const requestBody = llmCompletionsBodyFormat(
     {
@@ -182,34 +185,41 @@ export const dispatchChatCompletion = async (props: ChatProps): Promise<ChatResp
     }
   });
 
-  const { answerText } = await (async () => {
+  const { answerText, reasoningText } = await (async () => {
     if (res && isStreamResponse) {
       // sse response
-      const { answer } = await streamResponse({
+      const { answer, reasoning } = await streamResponse({
         res,
         stream: response,
+        aiChatReasoning,
         workflowStreamResponse
       });
 
       return {
-        answerText: answer
+        answerText: answer,
+        reasoningText: reasoning
       };
     } else {
       const unStreamResponse = response as ChatCompletion;
       const answer = unStreamResponse.choices?.[0]?.message?.content || '';
-
+      const reasoning = aiChatReasoning
+        ? // @ts-ignore
+          unStreamResponse.choices?.[0]?.message?.reasoning_content || ''
+        : '';
       if (stream) {
         // Some models do not support streaming
         workflowStreamResponse?.({
           event: SseResponseEventEnum.fastAnswer,
           data: textAdaptGptResponse({
-            text: answer
+            text: answer,
+            reasoning_content: reasoning
           })
         });
       }
 
       return {
-        answerText: answer
+        answerText: answer,
+        reasoningText: reasoning
       };
     }
   })();
@@ -240,6 +250,7 @@ export const dispatchChatCompletion = async (props: ChatProps): Promise<ChatResp
 
   return {
     answerText,
+    reasoningText,
     [DispatchNodeResponseKeyEnum.nodeResponse]: {
       totalPoints: externalProvider.openaiAccount?.key ? 0 : totalPoints,
       model: modelName,
@@ -280,11 +291,12 @@ async function filterDatasetQuote({
 }) {
   function getValue(item: SearchDataResponseItemType, index: number) {
     return replaceVariable(quoteTemplate || Prompt_QuoteTemplateList[0].value, {
+      id: item.id,
       q: item.q,
       a: item.a,
       updateTime: formatTime2YMDHM(item.updateTime),
       source: item.sourceName,
-      sourceId: String(item.sourceId || 'UnKnow'),
+      sourceId: String(item.sourceId || ''),
       index: index + 1
     });
   }
@@ -365,6 +377,7 @@ async function getMultiInput({
 
 async function getChatMessages({
   model,
+  maxTokens = 0,
   aiChatQuoteRole,
   datasetQuotePrompt = '',
   datasetQuoteText,
@@ -376,6 +389,7 @@ async function getChatMessages({
   documentQuoteText
 }: {
   model: LLMModelItemType;
+  maxTokens?: number;
   // dataset quote
   aiChatQuoteRole: AiChatQuoteRoleType; // user: replace user prompt; system: replace system prompt
   datasetQuotePrompt?: string;
@@ -442,9 +456,9 @@ async function getChatMessages({
 
   const adaptMessages = chats2GPTMessages({ messages, reserveId: false });
 
-  const filterMessages = await filterGPTMessageByMaxTokens({
+  const filterMessages = await filterGPTMessageByMaxContext({
     messages: adaptMessages,
-    maxTokens: model.maxContext - 300 // filter token. not response maxToken
+    maxContext: model.maxContext - maxTokens // filter token. not response maxToken
   });
 
   return {
@@ -455,33 +469,43 @@ async function getChatMessages({
 async function streamResponse({
   res,
   stream,
-  workflowStreamResponse
+  workflowStreamResponse,
+  aiChatReasoning
 }: {
   res: NextApiResponse;
   stream: StreamChatType;
   workflowStreamResponse?: WorkflowResponseType;
+  aiChatReasoning?: boolean;
 }) {
   const write = responseWriteController({
     res,
     readStream: stream
   });
   let answer = '';
+  let reasoning = '';
   for await (const part of stream) {
     if (res.closed) {
       stream.controller?.abort();
       break;
     }
+
     const content = part.choices?.[0]?.delta?.content || '';
     answer += content;
 
+    const reasoningContent = aiChatReasoning
+      ? part.choices?.[0]?.delta?.reasoning_content || ''
+      : '';
+    reasoning += reasoningContent;
+
     workflowStreamResponse?.({
       write,
       event: SseResponseEventEnum.answer,
       data: textAdaptGptResponse({
-        text: content
+        text: content,
+        reasoning_content: reasoningContent
       })
     });
   }
 
-  return { answer };
+  return { answer, reasoning };
 }

packages/service/core/workflow/dispatch/dataset/search.ts

@@ -6,7 +6,7 @@ import { formatModelChars2Points } from '../../../../support/wallet/usage/utils'
 import type { SelectedDatasetType } from '@fastgpt/global/core/workflow/api.d';
 import type { SearchDataResponseItemType } from '@fastgpt/global/core/dataset/type';
 import type { ModuleDispatchProps } from '@fastgpt/global/core/workflow/runtime/type';
-import { ModelTypeEnum, getLLMModel, getVectorModel } from '../../../ai/model';
+import { getLLMModel, getEmbeddingModel } from '../../../ai/model';
 import { searchDatasetData } from '../../../dataset/search/controller';
 import { NodeInputKeyEnum, NodeOutputKeyEnum } from '@fastgpt/global/core/workflow/constants';
 import { DispatchNodeResponseKeyEnum } from '@fastgpt/global/core/workflow/runtime/constants';
@@ -18,6 +18,7 @@ import { checkTeamReRankPermission } from '../../../../support/permission/teamLi
 import { MongoDataset } from '../../../dataset/schema';
 import { i18nT } from '../../../../../web/i18n/utils';
 import { filterDatasetsByTmbId } from '../../../dataset/utils';
+import { ModelTypeEnum } from '@fastgpt/global/core/ai/model';
 
 type DatasetSearchProps = ModuleDispatchProps<{
   [NodeInputKeyEnum.datasetSelectList]: SelectedDatasetType;
@@ -110,7 +111,7 @@ export async function dispatchDatasetSearch(
   // console.log(concatQueries, rewriteQuery, aiExtensionResult);
 
   // get vector
-  const vectorModel = getVectorModel(
+  const vectorModel = getEmbeddingModel(
     (await MongoDataset.findById(datasets[0].datasetId, 'vectorModel').lean())?.vectorModel
   );
 
@@ -138,7 +139,7 @@ export async function dispatchDatasetSearch(
   const { totalPoints, modelName } = formatModelChars2Points({
     model: vectorModel.model,
     inputTokens: tokens,
-    modelType: ModelTypeEnum.vector
+    modelType: ModelTypeEnum.embedding
   });
   const responseData: DispatchNodeResponseType & { totalPoints: number } = {
     totalPoints,

packages/service/core/workflow/dispatch/index.ts

@@ -204,6 +204,7 @@ export async function dispatchWorkFlow(data: Props): Promise<DispatchFlowRespons
     { inputs = [] }: RuntimeNodeItemType,
     {
       answerText = '',
+      reasoningText,
       responseData,
       nodeDispatchUsages,
       toolResponses,
@@ -213,6 +214,7 @@ export async function dispatchWorkFlow(data: Props): Promise<DispatchFlowRespons
     }: Omit<
       DispatchNodeResultType<{
         [NodeOutputKeyEnum.answerText]?: string;
+        [NodeOutputKeyEnum.reasoningText]?: string;
         [DispatchNodeResponseKeyEnum.nodeResponse]?: ChatHistoryItemResType;
       }>,
       'nodeResponse'
@@ -239,18 +241,28 @@ export async function dispatchWorkFlow(data: Props): Promise<DispatchFlowRespons
     // Histories store
     if (assistantResponses) {
       chatAssistantResponse = chatAssistantResponse.concat(assistantResponses);
-    } else if (answerText) {
-      // save assistant text response
-      const isResponseAnswerText =
-        inputs.find((item) => item.key === NodeInputKeyEnum.aiChatIsResponseText)?.value ?? true;
-      if (isResponseAnswerText) {
+    } else {
+      if (reasoningText) {
         chatAssistantResponse.push({
-          type: ChatItemValueTypeEnum.text,
-          text: {
-            content: answerText
+          type: ChatItemValueTypeEnum.reasoning,
+          reasoning: {
+            content: reasoningText
           }
         });
       }
+      if (answerText) {
+        // save assistant text response
+        const isResponseAnswerText =
+          inputs.find((item) => item.key === NodeInputKeyEnum.aiChatIsResponseText)?.value ?? true;
+        if (isResponseAnswerText) {
+          chatAssistantResponse.push({
+            type: ChatItemValueTypeEnum.text,
+            text: {
+              content: answerText
+            }
+          });
+        }
+      }
     }
 
     if (rewriteHistories) {

packages/service/core/workflow/dispatch/tools/http468.ts

@@ -244,7 +244,6 @@ export const dispatchHttp468Request = async (props: HttpRequestProps): Promise<H
       if (!httpJsonBody) return {};
       if (httpContentType === ContentTypes.json) {
         httpJsonBody = replaceJsonBodyString(httpJsonBody);
-        console.log(httpJsonBody);
         return json5.parse(httpJsonBody);
       }
 

packages/service/core/workflow/dispatch/tools/queryExternsion.ts

@@ -2,12 +2,13 @@ import type { ChatItemType } from '@fastgpt/global/core/chat/type.d';
 import type { ModuleDispatchProps } from '@fastgpt/global/core/workflow/runtime/type';
 import { NodeInputKeyEnum, NodeOutputKeyEnum } from '@fastgpt/global/core/workflow/constants';
 import { DispatchNodeResponseKeyEnum } from '@fastgpt/global/core/workflow/runtime/constants';
-import { ModelTypeEnum, getLLMModel } from '../../../../core/ai/model';
+import { getLLMModel } from '../../../../core/ai/model';
 import { formatModelChars2Points } from '../../../../support/wallet/usage/utils';
 import { queryExtension } from '../../../../core/ai/functions/queryExtension';
 import { getHistories } from '../utils';
 import { hashStr } from '@fastgpt/global/common/string/tools';
 import { DispatchNodeResultType } from '@fastgpt/global/core/workflow/runtime/type';
+import { ModelTypeEnum } from '@fastgpt/global/core/ai/model';
 
 type Props = ModuleDispatchProps<{
   [NodeInputKeyEnum.aiModel]: string;