full text tmp code (#3561 )

* full text tmp code * fix: init * fix: init * remove tmp code * remove tmp code * 4818-alpha
feat: tmp upgrade code (#3559 )
2025-01-10 18:03:14 +08:00 · 2025-01-10 14:41:29 +08:00 · 2025-01-10 13:37:48 +08:00 · 2025-01-10 12:18:13 +08:00 · 2025-01-10 11:07:04 +08:00 · 2025-01-10 10:48:54 +08:00
266 changed files with 6100 additions and 2913 deletions
--- a/.github/workflows/preview-fastgpt-image.yml
+++ b/.github/workflows/preview-fastgpt-image.yml
@@ -36,7 +36,7 @@ jobs:
          password: ${{ secrets.GH_PAT }}
      - name: Set DOCKER_REPO_TAGGED based on branch or tag
        run: |
-          echo "DOCKER_REPO_TAGGED=ghcr.io/${{ github.repository_owner }}/fastgpt-pr:${{ github.event.pull_request.number }}" >> $GITHUB_ENV
+          echo "DOCKER_REPO_TAGGED=ghcr.io/${{ github.repository_owner }}/fastgpt-pr:${{ github.event.pull_request.head.sha }}" >> $GITHUB_ENV
      - name: Build image for PR
        env:
          DOCKER_REPO_TAGGED: ${{ env.DOCKER_REPO_TAGGED }}
@@ -44,7 +44,7 @@ jobs:
          docker buildx build \
          -f projects/app/Dockerfile \
          --label "org.opencontainers.image.source=https://github.com/${{ github.repository_owner }}/FastGPT" \
-          --label "org.opencontainers.image.description=fastgpt-pr imae" \
+          --label "org.opencontainers.image.description=fastgpt-pr image" \
          --label "org.opencontainers.image.licenses=Apache" \
          --push \
          --cache-from=type=local,src=/tmp/.buildx-cache \
--- a/README.md
+++ b/README.md
@@ -215,4 +215,4 @@ https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409b
 1. 允许作为后台服务直接商用，但不允许提供 SaaS 服务。
 2. 未经商业授权，任何形式的商用服务均需保留相关版权信息。
 3. 完整请查看 [FastGPT Open Source License](./LICENSE)
-4. 联系方式：Dennis@sealos.io，[点击查看商业版定价策略](https://doc.tryfastgpt.ai/docs/commercial)
+4. 联系方式：Dennis@sealos.io，[点击查看商业版定价策略](https://doc.tryfastgpt.ai/docs/shopping_cart/intro/)
--- a/docSite/assets/imgs/dataset1.png
+++ b/docSite/assets/imgs/dataset1.png
--- a/docSite/assets/imgs/dataset2.png
+++ b/docSite/assets/imgs/dataset2.png
--- a/docSite/content/zh-cn/docs/development/configuration.md
+++ b/docSite/content/zh-cn/docs/development/configuration.md
@@ -168,6 +168,7 @@ weight: 707
  "reRankModels": [],
  "audioSpeechModels": [
    {
+      "provider": "OpenAI",
      "model": "tts-1",
      "name": "OpenAI TTS1",
      "charsPointsPrice": 0,
@@ -182,6 +183,7 @@ weight: 707
    }
  ],
  "whisperModel": {
+    "provider": "OpenAI",
    "model": "whisper-1",
    "name": "Whisper1",
    "charsPointsPrice": 0
@@ -201,7 +203,9 @@ weight: 707
 - OpenAI
 - Claude
 - Gemini
+- Meta
 - MistralAI
+- AliCloud - 阿里云
 - Qwen - 通义千问
 - Doubao - 豆包
 - ChatGLM - 智谱
@@ -213,7 +217,10 @@ weight: 707
 - Baichuan - 百川
 - Yi - 零一万物
 - Ernie - 文心一言
+- StepFun - 阶跃星辰
 - Ollama
+- BAAI - 智源研究院
+- FishAudio
 - Other - 其他


--- a/docSite/content/zh-cn/docs/development/faq.md
+++ b/docSite/content/zh-cn/docs/development/faq.md
@@ -19,6 +19,10 @@ images: []

 ## 二、通用问题

+### 本地部署的限制
+
+具体内容参考https://fael3z0zfze.feishu.cn/wiki/OFpAw8XzAi36Guk8dfucrCKUnjg。
+
 ### 能否纯本地运行

 可以。需要准备好向量模型和LLM模型。
--- a/docSite/content/zh-cn/docs/development/intro.md
+++ b/docSite/content/zh-cn/docs/development/intro.md
@@ -148,7 +148,7 @@ FastGPT 在`pnpm i`后会执行`postinstall`脚本，用于自动生成`ChakraUI

 ## 加入社区

-遇到困难了吗？有任何问题吗? 加入微信群与开发者和用户保持沟通。
+遇到困难了吗？有任何问题吗? 加入飞书群与开发者和用户保持沟通。

 <img width="400px" src="https://oss.laf.run/otnvvf-imgs/fastgpt-feishu1.png" class="medium-zoom-image" />

--- a/docSite/content/zh-cn/docs/development/upgrading/4817.md
+++ b/docSite/content/zh-cn/docs/development/upgrading/4817.md
@@ -1,5 +1,5 @@
 ---
-title: 'V4.8.17(进行中)'
+title: 'V4.8.17(包含升级脚本)'
 description: 'FastGPT V4.8.17 更新说明'
 icon: 'upgrade'
 draft: false
@@ -7,7 +7,16 @@ toc: true
 weight: 807
 ---

-## 运行升级脚本
+## 更新指南
+
+### 1. 更新镜像：
+
+- 更新 fastgpt 镜像 tag: v4.8.17-fix-title
+- 更新 fastgpt-pro 商业版镜像 tag: v4.8.17
+- Sandbox 镜像无需更新
+
+
+### 2. 运行升级脚本

 从任意终端，发起 1 个 HTTP 请求。其中 {{rootkey}} 替换成环境变量里的 `rootkey`；{{host}} 替换成**FastGPT 域名**。

@@ -19,6 +28,11 @@ curl --location --request POST 'https://{{host}}/api/admin/initv4817' \

 会将用户绑定的 OpenAI 账号移动到团队中。

+
+## 调整 completions 接口返回值
+
+/api/v1/chat/completions 接口返回值调整，对话节点、工具节点等使用到模型的节点，将不再返回 `tokens` 字段，改为返回 `inputTokens` 和 `outputTokens` 字段，分别表示输入和输出的 Token 数量。
+
 ## 完整更新内容

 1. 新增 - 简易模式工具调用支持数组类型插件。
@@ -27,10 +41,12 @@ curl --location --request POST 'https://{{host}}/api/admin/initv4817' \
 4. 新增 - 商业版支持后台配置模板市场。
 5. 新增 - 商业版支持后台配置自定义工作流变量，用于与业务系统鉴权打通。
 6. 新增 - 搜索测试接口支持问题优化。
-7. 优化 - Markdown 大小测试，超出 20 万字符不使用 Markdown 组件，避免崩溃。
-8. 优化 - 知识库搜索参数，滑动条支持输入模式，可以更精准的控制。
-9. 优化 - 可用模型展示
-10. 优化 - Mongo 查询语句，增加 virtual 字段。
-11. 修复 - 文件返回接口缺少 Content-Length 头，导致通过非同源文件上传时，阿里 vision 模型无法识别图片。
-12. 修复 - 去除判断器两端字符串隐藏换行符，避免判断器失效。
-13. 修复 - 变量更新节点，手动输入更新内容时候，非字符串类型数据类型无法自动转化。
+7. 新增 - 工作流中 Input Token 和 Output Token 分开记录展示。并修复部分请求未记录输出 Token 计费问题。
+8. 优化 - Markdown 大小测试，超出 20 万字符不使用 Markdown 组件，避免崩溃。
+9. 优化 - 知识库搜索参数，滑动条支持输入模式，可以更精准的控制。
+10. 优化 - 可用模型展示UI。
+11. 优化 - Mongo 查询语句，增加 virtual 字段。
+12. 修复 - 文件返回接口缺少 Content-Length 头，导致通过非同源文件上传时，阿里 vision 模型无法识别图片。
+13. 修复 - 去除判断器两端字符串隐藏换行符，避免判断器失效。
+14. 修复 - 变量更新节点，手动输入更新内容时候，非字符串类型数据类型无法自动转化。
+15. 修复 - 豆包模型无法工具调用。
--- a/docSite/content/zh-cn/docs/development/upgrading/4818.md
+++ b/docSite/content/zh-cn/docs/development/upgrading/4818.md
@@ -0,0 +1,37 @@
+---
+title: 'V4.8.18(进行中)'
+description: 'FastGPT V4.8.18 更新说明'
+icon: 'upgrade'
+draft: false
+toc: true
+weight: 806
+---
+
+## 更新指南
+
+### 2. 运行升级脚本
+
+从任意终端，发起 1 个 HTTP 请求。其中 {{rootkey}} 替换成环境变量里的 `rootkey`；{{host}} 替换成**FastGPT 域名**。
+
+```bash
+curl --location --request POST 'https://{{host}}/api/admin/initv4818' \
+--header 'rootkey: {{rootkey}}' \
+--header 'Content-Type: application/json'
+```
+
+会迁移全文检索表，时间较长，迁移期间全文检索会失效，日志中会打印已经迁移的数据长度。
+
+
+## 完整更新内容
+
+1. 新增 - 支持部门架构权限模式。
+2. 新增 - 支持配置自定跨域安全策略，默认全开。
+3. 优化 - 分享链接随机生成用户头像。
+4. 优化 - 图片上传安全校验。并增加头像图片唯一存储，确保不会累计存储。
+5. 优化 - Mongo 全文索引表分离。
+6. 优化 - 知识库检索查询语句合并，同时减少查库数量。
+7. 优化 - 文件编码检测，减少 CSV 文件乱码概率。
+8. 优化 - 异步读取文件内容，减少进程阻塞。
+9. 优化 - 文件阅读，HTML 直接下载，不允许在线阅读。
+10. 修复 - HTML 文件上传，base64 图片无法自动转图片链接。
+11. 修复 - 插件计费错误。
--- a/docSite/content/zh-cn/docs/faq/app.md
+++ b/docSite/content/zh-cn/docs/faq/app.md
@@ -13,4 +13,12 @@ weight: 908

 但是，当连续问题之间的关联性较小，模型判断的准确度可能会受到限制。在这种情况下，我们可以引入全局变量的概念来记录分类结果。在后续的问题分类阶段，首先检查全局变量是否存有分类结果。如果有，那么直接沿用该结果；若没有，则让模型自行判断。

-建议：构建批量运行脚本进行测试，评估问题分类的准确性。
+建议：构建批量运行脚本进行测试，评估问题分类的准确性。
+
+## 系统编排配置中的定时执行，如果用户打开分享的连接，停留在那个页面，定时执行触发问题
+
+发布后，后台生效。
+
+## AI对话回答要求中的Markdown语法取消
+
+在针对知识库的回答要求里有, 要给它配置提示词，不然他就是默认的，默认的里面就有该语法。
--- a/docSite/content/zh-cn/docs/faq/dataset.md
+++ b/docSite/content/zh-cn/docs/faq/dataset.md
@@ -14,4 +14,51 @@ weight: 910
 ## 知识库配置里的文件处理模型是什么？与索引模型有什么区别？

 * **文件处理模型**：用于数据处理的【增强处理】和【问答拆分】。在【增强处理】中，生成相关问题和摘要，在【问答拆分】中执行问答对生成。
-* **索引模型**：用于向量化，即通过对文本数据进行处理和组织，构建出一个能够快速查询的数据结构。
+* **索引模型**：用于向量化，即通过对文本数据进行处理和组织，构建出一个能够快速查询的数据结构。
+
+## 基于知识库的查询，但是问题相关的答案过多。ai回答到一半就不继续回答。
+
+FastGPT回复长度计算公式:
+
+最大回复=min(配置的最大回复（内置的限制），最大上下文（输入和输出的总和）-历史记录)
+
+18K模型->输入与输出的和
+
+输出增多->输入减小
+
+所以可以：
+
+1. 检查配置的最大回复（回复上限）
+2. 减小输入来增大输出，即减小历史记录，在工作流其实也就是“聊天记录”
+
+配置的最大回复：
+
+![](/imgs/dataset1.png)
+
+![](/imgs/dataset2.png)
+
+1. 私有化部署的时候，后台配模型参数，可以在配置最大上文时候，预留一些空间，比如 128000 的模型，可以只配置 120000, 剩余的空间后续会被安排给输出
+
+
+## 受到模型上下文的限制，有时候达不到聊天记录的轮次，连续对话字数过多就会报上下文不够的错误。
+
+FastGPT回复长度计算公式:
+
+最大回复=min(配置的最大回复（内置的限制），最大上下文（输入和输出的总和）-历史记录)
+
+18K模型->输入与输出的和
+
+输出增多->输入减小
+
+所以可以：
+
+1. 检查配置的最大回复（回复上限）
+2. 减小输入来增大输出，即减小历史记录，在工作流其实也就是“聊天记录”
+
+配置的最大回复：
+
+![](/imgs/dataset1.png)
+
+![](/imgs/dataset2.png)
+
+1. 私有化部署的时候，后台配模型参数，可以在配置最大上文时候，预留一些空间，比如 128000 的模型，可以只配置 120000, 剩余的空间后续会被安排给输出
--- a/docSite/content/zh-cn/docs/guide/plugins/searxng_plugin_guide.md
+++ b/docSite/content/zh-cn/docs/guide/plugins/searxng_plugin_guide.md
@@ -160,6 +160,18 @@ default_doi_resolver: 'oadoi.org'
 }
 ```

+* 搜索结果为空时会返回友好提示：
+
+```Bash
+{
+  "result": "[]",
+  "error": {
+    "message": "No search results",
+    "code": 500
+  }
+}
+```
+
 * 失败时通过 Promise.reject 可能返回错误信息：

 ```Bash
--- a/files/docker/docker-compose-milvus.yml
+++ b/files/docker/docker-compose-milvus.yml
@@ -114,15 +114,15 @@ services:
  # fastgpt
  sandbox:
    container_name: sandbox
-    image: ghcr.io/labring/fastgpt-sandbox:v4.8.16 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.16 # 阿里云
+    image: ghcr.io/labring/fastgpt-sandbox:v4.8.17 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.17 # 阿里云
    networks:
      - fastgpt
    restart: always
  fastgpt:
    container_name: fastgpt
-    image: ghcr.io/labring/fastgpt:v4.8.16 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.16 # 阿里云
+    image: ghcr.io/labring/fastgpt:v4.8.17 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.17 # 阿里云
    ports:
      - 3000:3000
    networks:
--- a/files/docker/docker-compose-pgvector.yml
+++ b/files/docker/docker-compose-pgvector.yml
@@ -72,15 +72,15 @@ services:
  # fastgpt
  sandbox:
    container_name: sandbox
-    image: ghcr.io/labring/fastgpt-sandbox:v4.8.16 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.16 # 阿里云
+    image: ghcr.io/labring/fastgpt-sandbox:v4.8.17 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.17 # 阿里云
    networks:
      - fastgpt
    restart: always
  fastgpt:
    container_name: fastgpt
-    image: ghcr.io/labring/fastgpt:v4.8.16 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.16 # 阿里云
+    image: ghcr.io/labring/fastgpt:v4.8.17 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.17 # 阿里云
    ports:
      - 3000:3000
    networks:
--- a/files/docker/docker-compose-zilliz.yml
+++ b/files/docker/docker-compose-zilliz.yml
@@ -53,15 +53,15 @@ services:
        wait $$!
  sandbox:
    container_name: sandbox
-    image: ghcr.io/labring/fastgpt-sandbox:v4.8.16 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.16 # 阿里云
+    image: ghcr.io/labring/fastgpt-sandbox:v4.8.17 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.17 # 阿里云
    networks:
      - fastgpt
    restart: always
  fastgpt:
    container_name: fastgpt
-    image: ghcr.io/labring/fastgpt:v4.8.16 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.16 # 阿里云
+    image: ghcr.io/labring/fastgpt:v4.8.17 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.17 # 阿里云
    ports:
      - 3000:3000
    networks:
--- a/packages/global/common/error/code/common.ts
+++ b/packages/global/common/error/code/common.ts
@@ -1,14 +1,20 @@
+import { i18nT } from '../../../../web/i18n/utils';
 import { ErrType } from '../errorCode';

 /* dataset: 507000 */
 const startCode = 507000;
 export enum CommonErrEnum {
+  invalidParams = 'invalidParams',
  fileNotFound = 'fileNotFound',
  unAuthFile = 'unAuthFile',
  missingParams = 'missingParams',
  inheritPermissionError = 'inheritPermissionError'
 }
 const datasetErr = [
+  {
+    statusText: CommonErrEnum.fileNotFound,
+    message: i18nT('common:error.invalid_params')
+  },
  {
    statusText: CommonErrEnum.fileNotFound,
    message: 'error.fileNotFound'
--- a/packages/global/common/error/code/team.ts
+++ b/packages/global/common/error/code/team.ts
@@ -1,9 +1,11 @@
-import { ErrType } from '../errorCode';
 import { i18nT } from '../../../../web/i18n/utils';
+import type { ErrType } from '../errorCode';
 /* team: 500000 */
 export enum TeamErrEnum {
+  notUser = 'notUser',
  teamOverSize = 'teamOverSize',
  unAuthTeam = 'unAuthTeam',
+  teamMemberOverSize = 'teamMemberOverSize',
  aiPointsNotEnough = 'aiPointsNotEnough',
  datasetSizeNotEnough = 'datasetSizeNotEnough',
  datasetAmountNotEnough = 'datasetAmountNotEnough',
@@ -14,11 +16,22 @@ export enum TeamErrEnum {
  groupNameEmpty = 'groupNameEmpty',
  groupNameDuplicate = 'groupNameDuplicate',
  groupNotExist = 'groupNotExist',
+  orgMemberNotExist = 'orgMemberNotExist',
+  orgMemberDuplicated = 'orgMemberDuplicated',
+  orgNotExist = 'orgNotExist',
+  orgParentNotExist = 'orgParentNotExist',
+  cannotMoveToSubPath = 'cannotMoveToSubPath',
+  cannotModifyRootOrg = 'cannotModifyRootOrg',
+  cannotDeleteNonEmptyOrg = 'cannotDeleteNonEmptyOrg',
  cannotDeleteDefaultGroup = 'cannotDeleteDefaultGroup',
  userNotActive = 'userNotActive'
 }

 const teamErr = [
+  {
+    statusText: TeamErrEnum.notUser,
+    message: i18nT('common:code_error.team_error.not_user')
+  },
  {
    statusText: TeamErrEnum.teamOverSize,
    message: i18nT('common:code_error.team_error.over_size')
@@ -71,6 +84,34 @@ const teamErr = [
  {
    statusText: TeamErrEnum.userNotActive,
    message: i18nT('common:code_error.team_error.user_not_active')
+  },
+  {
+    statusText: TeamErrEnum.orgMemberNotExist,
+    message: i18nT('common:code_error.team_error.org_member_not_exist')
+  },
+  {
+    statusText: TeamErrEnum.orgMemberDuplicated,
+    message: i18nT('common:code_error.team_error.org_member_duplicated')
+  },
+  {
+    statusText: TeamErrEnum.orgNotExist,
+    message: i18nT('common:code_error.team_error.org_not_exist')
+  },
+  {
+    statusText: TeamErrEnum.orgParentNotExist,
+    message: i18nT('common:code_error.team_error.org_parent_not_exist')
+  },
+  {
+    statusText: TeamErrEnum.cannotMoveToSubPath,
+    message: i18nT('common:code_error.team_error.cannot_move_to_sub_path')
+  },
+  {
+    statusText: TeamErrEnum.cannotModifyRootOrg,
+    message: i18nT('common:code_error.team_error.cannot_modify_root_org')
+  },
+  {
+    statusText: TeamErrEnum.cannotDeleteNonEmptyOrg,
+    message: i18nT('common:code_error.team_error.cannot_delete_non_empty_org')
  }
 ];

--- a/packages/global/common/error/code/user.ts
+++ b/packages/global/common/error/code/user.ts
@@ -2,25 +2,16 @@ import { ErrType } from '../errorCode';
 import { i18nT } from '../../../../web/i18n/utils';
 /* team: 503000 */
 export enum UserErrEnum {
-  unAuthUser = 'unAuthUser',
  unAuthRole = 'unAuthRole',
  binVisitor = 'binVisitor',
  balanceNotEnough = 'balanceNotEnough',
  unAuthSso = 'unAuthSso'
 }
 const errList = [
-  {
-    statusText: UserErrEnum.unAuthUser,
-    message: i18nT('common:code_error.user_error.un_auth_user')
-  },
  {
    statusText: UserErrEnum.binVisitor,
    message: i18nT('common:code_error.user_error.bin_visitor')
-  }, // 身份校验未通过
-  {
-    statusText: UserErrEnum.binVisitor,
-    message: i18nT('common:code_error.user_error.bin_visitor_guest')
-  }, // 游客身份
+  },
  {
    statusText: UserErrEnum.balanceNotEnough,
    message: i18nT('common:code_error.user_error.balance_not_enough')
--- a/packages/global/common/file/api.d.ts
+++ b/packages/global/common/file/api.d.ts
@@ -1,10 +1,7 @@
-import { MongoImageTypeEnum } from './image/constants';
 import { OutLinkChatAuthProps } from '../../support/permission/chat.d';

 export type preUploadImgProps = OutLinkChatAuthProps & {
-  type: `${MongoImageTypeEnum}`;
-
-  expiredTime?: Date;
+  // expiredTime?: Date;
  metadata?: Record<string, any>;
 };
 export type UploadImgProps = preUploadImgProps & {
--- a/packages/global/common/file/image/constants.ts
+++ b/packages/global/common/file/image/constants.ts
@@ -1,61 +1,5 @@
 export const imageBaseUrl = '/api/system/img/';

-export enum MongoImageTypeEnum {
-  systemAvatar = 'systemAvatar',
-  appAvatar = 'appAvatar',
-  pluginAvatar = 'pluginAvatar',
-  datasetAvatar = 'datasetAvatar',
-  userAvatar = 'userAvatar',
-  teamAvatar = 'teamAvatar',
-  groupAvatar = 'groupAvatar',
-
-  chatImage = 'chatImage',
-  collectionImage = 'collectionImage'
-}
-export const mongoImageTypeMap = {
-  [MongoImageTypeEnum.systemAvatar]: {
-    label: 'appAvatar',
-    unique: true
-  },
-  [MongoImageTypeEnum.appAvatar]: {
-    label: 'appAvatar',
-    unique: true
-  },
-  [MongoImageTypeEnum.pluginAvatar]: {
-    label: 'pluginAvatar',
-    unique: true
-  },
-  [MongoImageTypeEnum.datasetAvatar]: {
-    label: 'datasetAvatar',
-    unique: true
-  },
-  [MongoImageTypeEnum.userAvatar]: {
-    label: 'userAvatar',
-    unique: true
-  },
-  [MongoImageTypeEnum.teamAvatar]: {
-    label: 'teamAvatar',
-    unique: true
-  },
-  [MongoImageTypeEnum.groupAvatar]: {
-    label: 'groupAvatar',
-    unique: true
-  },
-
-  [MongoImageTypeEnum.chatImage]: {
-    label: 'chatImage',
-    unique: false
-  },
-  [MongoImageTypeEnum.collectionImage]: {
-    label: 'collectionImage',
-    unique: false
-  }
-};
-
-export const uniqueImageTypeList = Object.entries(mongoImageTypeMap)
-  .filter(([key, value]) => value.unique)
-  .map(([key]) => key as `${MongoImageTypeEnum}`);
-
 export const FolderIcon = 'file/fill/folder';
 export const FolderImgUrl = '/imgs/files/folder.svg';
 export const HttpPluginImgUrl = '/imgs/app/httpPluginFill.svg';
--- a/packages/global/common/file/image/type.d.ts
+++ b/packages/global/common/file/image/type.d.ts
@@ -1,12 +1,8 @@
-import { MongoImageTypeEnum } from './constants';
-
 export type MongoImageSchemaType = {
  _id: string;
  teamId: string;
  binary: Buffer;
-  createTime: Date;
  expiredTime?: Date;
-  type: `${MongoImageTypeEnum}`;

  metadata?: {
    mime?: string; // image mime type.
--- a/packages/global/common/file/tools.ts
+++ b/packages/global/common/file/tools.ts
@@ -2,6 +2,7 @@ import { detect } from 'jschardet';
 import { documentFileType, imageFileType } from './constants';
 import { ChatFileTypeEnum } from '../../core/chat/constants';
 import { UserChatItemValueItemType } from '../../core/chat/type';
+import * as fs from 'fs';

 export const formatFileSize = (bytes: number): string => {
  if (bytes === 0) return '0 B';
@@ -16,6 +17,22 @@ export const formatFileSize = (bytes: number): string => {
 export const detectFileEncoding = (buffer: Buffer) => {
  return detect(buffer.slice(0, 200))?.encoding?.toLocaleLowerCase();
 };
+export const detectFileEncodingByPath = async (path: string) => {
+  // Get 64KB file head
+  const MAX_BYTES = 64 * 1024;
+  const buffer = Buffer.alloc(MAX_BYTES);
+
+  const fd = await fs.promises.open(path, 'r');
+  try {
+    // Read file head
+    const { bytesRead } = await fd.read(buffer, 0, MAX_BYTES, 0);
+    const actualBuffer = buffer.slice(0, bytesRead);
+
+    return detect(actualBuffer)?.encoding?.toLocaleLowerCase();
+  } finally {
+    await fd.close();
+  }
+};

 // Url => user upload file type
 export const parseUrlToFileType = (url: string): UserChatItemValueItemType['file'] | undefined => {
--- a/packages/global/common/string/tools.ts
+++ b/packages/global/common/string/tools.ts
@@ -25,17 +25,22 @@ export const simpleText = (text = '') => {
  return text;
 };

-/* 
-  replace {{variable}} to value
-*/
+export const valToStr = (val: any) => {
+  if (val === undefined) return 'undefined';
+  if (val === null) return 'null';
+
+  if (typeof val === 'object') return JSON.stringify(val);
+  return String(val);
+};
+
+// replace {{variable}} to value
 export function replaceVariable(text: any, obj: Record<string, string | number>) {
  if (typeof text !== 'string') return text;

  for (const key in obj) {
    const val = obj[key];
-    const formatVal = typeof val === 'object' ? JSON.stringify(val) : String(val);
-
-    text = text.replace(new RegExp(`{{(${key})}}`, 'g'), formatVal);
+    const formatVal = valToStr(val);
+    text = text.replace(new RegExp(`{{(${key})}}`, 'g'), () => formatVal);
  }
  return text || '';
 }
--- a/packages/global/common/system/constants.ts
+++ b/packages/global/common/system/constants.ts
@@ -1,6 +1,9 @@
 export const HUMAN_ICON = `/icon/human.svg`;
 export const LOGO_ICON = `/icon/logo.svg`;
 export const HUGGING_FACE_ICON = `/imgs/model/huggingface.svg`;
+
 export const DEFAULT_TEAM_AVATAR = `/imgs/avatar/defaultTeamAvatar.svg`;
+export const DEFAULT_ORG_AVATAR = '/imgs/avatar/defaultOrgAvatar.svg';
+export const DEFAULT_USER_AVATAR = '/imgs/avatar/BlueAvatar.svg';

 export const isProduction = process.env.NODE_ENV === 'production';
--- a/packages/global/common/system/types/index.d.ts
+++ b/packages/global/common/system/types/index.d.ts
@@ -73,6 +73,11 @@ export type FastGPTFeConfigsType = {
    google?: string;
    wechat?: string;
    dingtalk?: string;
+    wecom?: {
+      corpid?: string;
+      agentid?: string;
+      secret?: string;
+    };
    microsoft?: {
      clientId?: string;
      tenantId?: string;
--- a/packages/global/core/ai/model.d.ts
+++ b/packages/global/core/ai/model.d.ts
@@ -1,6 +1,13 @@
 import type { ModelProviderIdType } from './provider';

-export type LLMModelItemType = {
+type PriceType = {
+  charsPointsPrice?: number; // 1k chars=n points; 60s=n points;
+
+  // If inputPrice is set, the input-output charging scheme is adopted
+  inputPrice?: number; // 1k tokens=n points
+  outputPrice?: number; // 1k tokens=n points
+};
+export type LLMModelItemType = PriceType & {
  provider: ModelProviderIdType;
  model: string;
  name: string;
@@ -10,8 +17,6 @@ export type LLMModelItemType = {
  quoteMaxToken: number;
  maxTemperature: number;

-  charsPointsPrice: number; // 1k chars=n points
-
  censor?: boolean;
  vision?: boolean;

@@ -33,13 +38,12 @@ export type LLMModelItemType = {
  fieldMap?: Record<string, string>;
 };

-export type VectorModelItemType = {
+export type VectorModelItemType = PriceType & {
  provider: ModelProviderIdType;
  model: string; // model name
  name: string; // show name
  avatar?: string;
  defaultToken: number; // split text default token
-  charsPointsPrice: number; // 1k tokens=n points
  maxToken: number; // model max token
  weight: number; // training weight
  hidden?: boolean; // Disallow creation
@@ -48,25 +52,23 @@ export type VectorModelItemType = {
  queryConfig?: Record<string, any>; // Custom parameters for query
 };

-export type ReRankModelItemType = {
+export type ReRankModelItemType = PriceType & {
+  provider: ModelProviderIdType;
  model: string;
  name: string;
-  charsPointsPrice: number;
  requestUrl: string;
  requestAuth: string;
 };

-export type AudioSpeechModelType = {
+export type AudioSpeechModelType = PriceType & {
  provider: ModelProviderIdType;
  model: string;
  name: string;
-  charsPointsPrice: number;
  voices: { label: string; value: string; bufferId: string }[];
 };

-export type STTModelType = {
+export type STTModelType = PriceType & {
  provider: ModelProviderIdType;
  model: string;
  name: string;
-  charsPointsPrice: number; // 60s = n points
 };
--- a/packages/global/core/ai/provider.ts
+++ b/packages/global/core/ai/provider.ts
@@ -4,20 +4,25 @@ export type ModelProviderIdType =
  | 'OpenAI'
  | 'Claude'
  | 'Gemini'
+  | 'Meta'
  | 'MistralAI'
  | 'Groq'
+  | 'AliCloud'
  | 'Qwen'
  | 'Doubao'
  | 'ChatGLM'
  | 'DeepSeek'
+  | 'Ernie'
  | 'Moonshot'
  | 'MiniMax'
  | 'SparkDesk'
  | 'Hunyuan'
  | 'Baichuan'
+  | 'StepFun'
  | 'Yi'
-  | 'Ernie'
  | 'Ollama'
+  | 'BAAI'
+  | 'FishAudio'
  | 'Other';

 export type ModelProviderType = {
@@ -42,6 +47,11 @@ export const ModelProviderList: ModelProviderType[] = [
    name: 'Gemini',
    avatar: 'model/gemini'
  },
+  {
+    id: 'Meta',
+    name: 'Meta',
+    avatar: 'model/meta'
+  },
  {
    id: 'MistralAI',
    name: 'MistralAI',
@@ -52,6 +62,11 @@ export const ModelProviderList: ModelProviderType[] = [
    name: 'Groq',
    avatar: 'model/groq'
  },
+  {
+    id: 'AliCloud',
+    name: i18nT('common:model_alicloud'),
+    avatar: 'model/alicloud'
+  },
  {
    id: 'Qwen',
    name: i18nT('common:model_qwen'),
@@ -67,6 +82,11 @@ export const ModelProviderList: ModelProviderType[] = [
    name: i18nT('common:model_chatglm'),
    avatar: 'model/chatglm'
  },
+  {
+    id: 'Ernie',
+    name: i18nT('common:model_ernie'),
+    avatar: 'model/ernie'
+  },
  {
    id: 'DeepSeek',
    name: 'DeepSeek',
@@ -97,21 +117,32 @@ export const ModelProviderList: ModelProviderType[] = [
    name: i18nT('common:model_baichuan'),
    avatar: 'model/baichuan'
  },
+  {
+    id: 'StepFun',
+    name: i18nT('common:model_stepfun'),
+    avatar: 'model/stepfun'
+  },
  {
    id: 'Yi',
    name: i18nT('common:model_yi'),
    avatar: 'model/yi'
  },
-  {
-    id: 'Ernie',
-    name: i18nT('common:model_ernie'),
-    avatar: 'model/ernie'
-  },
+
  {
    id: 'Ollama',
    name: 'Ollama',
    avatar: 'model/ollama'
  },
+  {
+    id: 'BAAI',
+    name: i18nT('common:model_baai'),
+    avatar: 'model/BAAI'
+  },
+  {
+    id: 'FishAudio',
+    name: 'FishAudio',
+    avatar: 'model/fishaudio'
+  },
  {
    id: 'Other',
    name: i18nT('common:model_other'),
--- a/packages/global/core/app/collaborator.d.ts
+++ b/packages/global/core/app/collaborator.d.ts
@@ -1,6 +1,6 @@
-import { RequireOnlyOne } from '../../common/type/utils';
+import type { RequireOnlyOne } from '../../common/type/utils';
 import {
-  UpdateClbPermissionProps,
+  type UpdateClbPermissionProps,
  UpdatePermissionBody
 } from '../../support/permission/collaborator';
 import { PermissionValueType } from '../../support/permission/type';
@@ -14,4 +14,5 @@ export type AppCollaboratorDeleteParams = {
 } & RequireOnlyOne<{
  tmbId: string;
  groupId: string;
+  orgId: string;
 }>;
--- a/packages/global/core/dataset/collaborator.d.ts
+++ b/packages/global/core/dataset/collaborator.d.ts
@@ -11,4 +11,5 @@ export type DatasetCollaboratorDeleteParams = {
 } & RequireOnlyOne<{
  tmbId: string;
  groupId: string;
+  orgId: string;
 }>;
--- a/packages/global/core/dataset/type.d.ts
+++ b/packages/global/core/dataset/type.d.ts
@@ -112,6 +112,15 @@ export type DatasetDataSchemaType = {
  rebuilding?: boolean;
 };

+export type DatasetDataTextSchemaType = {
+  _id: string;
+  teamId: string;
+  datasetId: string;
+  collectionId: string;
+  dataId: string;
+  fullTextToken: string;
+};
+
 export type DatasetTrainingSchemaType = {
  _id: string;
  userId: string;
--- a/packages/global/core/workflow/runtime/type.d.ts
+++ b/packages/global/core/workflow/runtime/type.d.ts
@@ -107,7 +107,9 @@ export type DispatchNodeResponseType = {
  mergeSignId?: string;

  // bill
-  tokens?: number;
+  tokens?: number; // deprecated
+  inputTokens?: number;
+  outputTokens?: number;
  model?: string;
  contextTotalLen?: number;
  totalPoints?: number;
@@ -157,6 +159,8 @@ export type DispatchNodeResponseType = {

  // tool
  toolCallTokens?: number;
+  toolCallInputTokens?: number;
+  toolCallOutputTokens?: number;
  toolDetail?: ChatHistoryItemResType[];
  toolStop?: boolean;

--- a/packages/global/core/workflow/runtime/utils.ts
+++ b/packages/global/core/workflow/runtime/utils.ts
@@ -9,7 +9,7 @@ import { isValidReferenceValueFormat } from '../utils';
 import { FlowNodeOutputItemType, ReferenceValueType } from '../type/io';
 import { ChatItemType, NodeOutputItemType } from '../../../core/chat/type';
 import { ChatItemValueTypeEnum, ChatRoleEnum } from '../../../core/chat/constants';
-import { replaceVariable } from '../../../common/string/tools';
+import { replaceVariable, valToStr } from '../../../common/string/tools';

 export const getMaxHistoryLimitFromNodes = (nodes: StoreNodeItemType[]): number => {
  let limit = 10;
@@ -343,11 +343,7 @@ export function replaceEditorVariable({
      if (input) return getReferenceVariableValue({ value: input.value, nodes, variables });
    })();

-    const formatVal = (() => {
-      if (variableVal === undefined) return 'undefined';
-      if (variableVal === null) return 'null';
-      return typeof variableVal === 'object' ? JSON.stringify(variableVal) : String(variableVal);
-    })();
+    const formatVal = valToStr(variableVal);

    const regex = new RegExp(`\\{\\{\\$(${nodeId}\\.${id})\\$\\}\\}`, 'g');
    text = text.replace(regex, () => formatVal);
--- a/packages/global/package.json
+++ b/packages/global/package.json
@@ -13,6 +13,7 @@
    "next": "14.2.5",
    "openai": "4.61.0",
    "openapi-types": "^12.1.3",
+    "json5": "^2.2.3",
    "timezones-list": "^3.0.2"
  },
  "devDependencies": {
--- a/packages/global/support/permission/collaborator.d.ts
+++ b/packages/global/support/permission/collaborator.d.ts
@@ -10,22 +10,18 @@ export type CollaboratorItemType = {
 } & RequireOnlyOne<{
  tmbId: string;
  groupId: string;
+  orgId: string;
 }>;

 export type UpdateClbPermissionProps = {
  members?: string[];
  groups?: string[];
+  orgs?: string[];
  permission: PermissionValueType;
 };

-export type DeleteClbPermissionProps = RequireOnlyOne<{
-  tmbId: string;
-  groupId: string;
-}>;
-
-export type UpdatePermissionBody = {
-  permission: PermissionValueType;
-} & RequireOnlyOne<{
-  memberId: string;
-  groupId: string;
+export type DeletePermissionQuery = RequireOnlyOne<{
+  tmbId?: string;
+  groupId?: string;
+  orgId?: string;
 }>;
--- a/packages/global/support/permission/type.d.ts
+++ b/packages/global/support/permission/type.d.ts
@@ -1,8 +1,9 @@
 import { UserModelSchema } from '../user/type';
 import { RequireOnlyOne } from '../../common/type/utils';
 import { TeamMemberSchema } from '../user/team/type';
-import { AuthUserTypeEnum, PermissionKeyEnum, PerResourceTypeEnum } from './constant';
 import { MemberGroupSchemaType } from './memberGroup/type';
+import type { TeamMemberWithUserSchema } from '../user/team/type';
+import { AuthUserTypeEnum, type PermissionKeyEnum, type PerResourceTypeEnum } from './constant';

 // PermissionValueType, the type of permission's value is a number, which is a bit field actually.
 // It is spired by the permission system in Linux.
@@ -29,6 +30,7 @@ export type ResourcePermissionType = {
 } & RequireOnlyOne<{
  tmbId: string;
  groupId: string;
+  orgId: string;
 }>;

 export type ResourcePerWithTmbWithUser = Omit<ResourcePermissionType, 'tmbId'> & {
--- a/packages/global/support/user/constant.ts
+++ b/packages/global/support/user/constant.ts
@@ -17,5 +17,6 @@ export enum OAuthEnum {
  wechat = 'wechat',
  microsoft = 'microsoft',
  dingtalk = 'dingtalk',
+  wecom = 'wecom',
  sso = 'sso'
 }
--- a/packages/global/support/user/login/constants.ts
+++ b/packages/global/support/user/login/constants.ts
@@ -0,0 +1,3 @@
+export function checkIsWecomTerminal() {
+  return /wxwork/i.test(navigator.userAgent);
+}
--- a/packages/global/support/user/team/org/api.d.ts
+++ b/packages/global/support/user/team/org/api.d.ts
@@ -0,0 +1,32 @@
+export type postCreateOrgData = {
+  name: string;
+  parentId: string;
+  description?: string;
+  avatar?: string;
+};
+
+export type putUpdateOrgMembersData = {
+  orgId: string;
+  members: {
+    tmbId: string;
+    // role: `${OrgMemberRole}`;
+  }[];
+};
+
+export type putUpdateOrgData = {
+  orgId: string;
+  name?: string;
+  avatar?: string;
+  description?: string;
+};
+
+export type putMoveOrgType = {
+  orgId: string;
+  targetOrgId: string;
+};
+
+// type putChnageOrgOwnerData = {
+//   orgId: string;
+//   tmbId: string;
+//   toAdmin?: boolean;
+// };
--- a/packages/global/support/user/team/org/constant.ts
+++ b/packages/global/support/user/team/org/constant.ts
@@ -0,0 +1,12 @@
+import { OrgSchemaType } from './type';
+
+export const OrgCollectionName = 'team_orgs';
+export const OrgMemberCollectionName = 'team_org_members';
+
+export const getOrgChildrenPath = (org: OrgSchemaType) => `${org.path}/${org.pathId}`;
+
+// export enum OrgMemberRole {
+//   owner = 'owner',
+//   admin = 'admin',
+//   member = 'member'
+// }
--- a/packages/global/support/user/team/org/type.d.ts
+++ b/packages/global/support/user/team/org/type.d.ts
@@ -0,0 +1,25 @@
+import type { TeamPermission } from 'support/permission/user/controller';
+import { ResourcePermissionType } from '../type';
+
+type OrgSchemaType = {
+  _id: string;
+  teamId: string;
+  pathId: string;
+  path: string;
+  name: string;
+  avatar?: string;
+  description?: string;
+  updateTime: Date;
+};
+
+type OrgMemberSchemaType = {
+  teamId: string;
+  orgId: string;
+  tmbId: string;
+};
+
+type OrgType = Omit<OrgSchemaType, 'avatar'> & {
+  avatar: string;
+  members: OrgMemberSchemaType[];
+  permission: TeamPermission;
+};
--- a/packages/global/support/user/team/type.d.ts
+++ b/packages/global/support/user/team/type.d.ts
@@ -55,10 +55,11 @@ export type TeamMemberWithTeamAndUserSchema = TeamMemberSchema & {
 export type TeamTmbItemType = {
  userId: string;
  teamId: string;
+  teamAvatar?: string;
  teamName: string;
  memberName: string;
  avatar: string;
-  balance: number;
+  balance?: number;
  tmbId: string;
  teamDomain: string;
  defaultTeam: boolean;
--- a/packages/global/support/user/utils.ts
+++ b/packages/global/support/user/utils.ts
@@ -0,0 +1,16 @@
+export const getRandomUserAvatar = () => {
+  const defaultAvatars = [
+    '/imgs/avatar/RoyalBlueAvatar.svg',
+    '/imgs/avatar/PurpleAvatar.svg',
+    '/imgs/avatar/AdoraAvatar.svg',
+    '/imgs/avatar/OrangeAvatar.svg',
+    '/imgs/avatar/RedAvatar.svg',
+    '/imgs/avatar/GrayModernAvatar.svg',
+    '/imgs/avatar/TealAvatar.svg',
+    '/imgs/avatar/GreenAvatar.svg',
+    '/imgs/avatar/BrightBlueAvatar.svg',
+    '/imgs/avatar/BlueAvatar.svg'
+  ];
+
+  return defaultAvatars[Math.floor(Math.random() * defaultAvatars.length)];
+};
--- a/packages/global/support/wallet/bill/type.d.ts
+++ b/packages/global/support/wallet/bill/type.d.ts
@@ -23,7 +23,8 @@ export type BillSchemaType = {
 };

 export type ChatNodeUsageType = {
-  tokens?: number;
+  inputTokens?: number;
+  outputTokens?: number;
  totalPoints: number;
  moduleName: string;
  model?: string;
--- a/packages/global/support/wallet/usage/type.d.ts
+++ b/packages/global/support/wallet/usage/type.d.ts
@@ -2,9 +2,13 @@ import { CreateUsageProps } from './api';
 import { UsageSourceEnum } from './constants';

 export type UsageListItemCountType = {
-  tokens?: number;
+  inputTokens?: number;
+  outputTokens?: number;
  charsLength?: number;
  duration?: number;
+
+  // deprecated
+  tokens?: number;
 };
 export type UsageListItemType = UsageListItemCountType & {
  moduleName: string;
--- a/packages/plugins/register.ts
+++ b/packages/plugins/register.ts
@@ -35,24 +35,26 @@ export const list = [...staticPluginList, ...packagePluginList];

 /* Get plugins */
 export const getCommunityPlugins = () => {
-  return list.map<SystemPluginTemplateItemType>((name) => {
-    const config = require(`./src/${name}/template.json`);
+  return Promise.all(
+    list.map<Promise<SystemPluginTemplateItemType>>(async (name) => {
+      const config = (await import(`./src/${name}/template.json`))?.default;

-    const isFolder = list.find((item) => item.startsWith(`${name}/`));
+      const isFolder = list.find((item) => item.startsWith(`${name}/`));

-    const parentIdList = name.split('/').slice(0, -1);
-    const parentId =
-      parentIdList.length > 0 ? `${PluginSourceEnum.community}-${parentIdList.join('/')}` : null;
+      const parentIdList = name.split('/').slice(0, -1);
+      const parentId =
+        parentIdList.length > 0 ? `${PluginSourceEnum.community}-${parentIdList.join('/')}` : null;

-    return {
-      ...config,
-      id: `${PluginSourceEnum.community}-${name}`,
-      isFolder,
-      parentId,
-      isActive: true,
-      isOfficial: true
-    };
-  });
+      return {
+        ...config,
+        id: `${PluginSourceEnum.community}-${name}`,
+        isFolder,
+        parentId,
+        isActive: true,
+        isOfficial: true
+      };
+    })
+  );
 };

 export const getSystemPluginTemplates = () => {
--- a/packages/plugins/src/drawing/baseChart/index.ts
+++ b/packages/plugins/src/drawing/baseChart/index.ts
@@ -4,8 +4,8 @@ import { SystemPluginSpecialResponse } from '../../../type.d';

 type Props = {
  title: string;
-  xAxis: string;
-  yAxis: string;
+  xAxis: string[];
+  yAxis: string[];
  chartType: string;
 };

@@ -27,7 +27,12 @@ type Option = {
  series: SeriesData[]; // 使用定义的类型
 };

-const generateChart = async (title: string, xAxis: string, yAxis: string, chartType: string) => {
+const generateChart = async (
+  title: string,
+  xAxis: string[],
+  yAxis: string[],
+  chartType: string
+) => {
  // @ts-ignore  无法使用dom，如使用jsdom会出现生成图片无法正常展示，有高手可以帮忙解决
  const chart = echarts.init(undefined, undefined, {
    renderer: 'svg', // 必须使用 SVG 模式
@@ -36,21 +41,11 @@ const generateChart = async (title: string, xAxis: string, yAxis: string, chartT
    height: 300
  });

-  let parsedXAxis: string[] = [];
-  let parsedYAxis: number[] = [];
-  try {
-    parsedXAxis = json5.parse(xAxis);
-    parsedYAxis = json5.parse(yAxis);
-  } catch (error: any) {
-    console.error('解析数据时出错:', error);
-    return Promise.reject('Data error');
-  }
-
  const option: Option = {
    backgroundColor: '#f5f5f5',
    title: { text: title },
    tooltip: {},
-    xAxis: { data: parsedXAxis },
+    xAxis: { data: xAxis },
    yAxis: {},
    series: [] // 初始化为空数组
  };
@@ -58,18 +53,18 @@ const generateChart = async (title: string, xAxis: string, yAxis: string, chartT
  // 根据 chartType 生成不同的图表
  switch (chartType) {
    case '柱状图':
-      option.series.push({ name: 'Sample', type: 'bar', data: parsedYAxis });
+      option.series.push({ name: 'Sample', type: 'bar', data: yAxis.map(Number) });
      break;
    case '折线图':
-      option.series.push({ name: 'Sample', type: 'line', data: parsedYAxis });
+      option.series.push({ name: 'Sample', type: 'line', data: yAxis.map(Number) });
      break;
    case '饼图':
      option.series.push({
        name: 'Sample',
        type: 'pie',
-        data: parsedYAxis.map((value, index) => ({
-          value,
-          name: parsedXAxis[index] // 使用 xAxis 作为饼图的名称
+        data: yAxis.map((value, index) => ({
+          value: Number(value),
+          name: xAxis[index] // 使用 xAxis 作为饼图的名称
        }))
      });
      break;
--- a/packages/plugins/src/drawing/baseChart/template.json
+++ b/packages/plugins/src/drawing/baseChart/template.json
@@ -1,6 +1,6 @@
 {
  "author": "silencezhang",
-  "version": "4812",
+  "version": "4817",
  "name": "基础图表",
  "avatar": "core/workflow/template/baseChart",
  "intro": "根据数据生成图表，可根据chartType生成柱状图，折线图，饼图",
@@ -68,7 +68,7 @@
            "canEdit": true,
            "key": "yAxis",
            "label": "yAxis",
-            "description": "y轴数据，例如：['1', '2', '3']",
+            "description": "y轴数据，例如：[1,2,3]",
            "defaultValue": "",
            "list": [
              {
@@ -77,7 +77,7 @@
              }
            ],
            "required": true,
-            "toolDescription": "y轴数据，例如：['1', '2', '3']"
+            "toolDescription": "y轴数据，例如：[1,2,3]"
          },
          {
            "renderTypeList": ["select", "reference"],
@@ -145,8 +145,8 @@
        "flowNodeType": "pluginOutput",
        "showStatus": false,
        "position": {
-          "x": 2122.252754006148,
-          "y": -63.5218674613718
+          "x": 2128.8138851197145,
+          "y": -63.52186746137181
        },
        "version": "481",
        "inputs": [
@@ -154,10 +154,12 @@
            "renderTypeList": ["reference"],
            "valueType": "string",
            "canEdit": true,
-            "key": "相对路径URL",
-            "label": "相对路径URL",
+            "key": "图表 url",
+            "label": "图表 url",
            "description": "可用使用markdown格式展示图片，如：![图片](url)",
-            "value": ["ws0DFKJnCPhk", "bzaYjKyQFOw2"]
+            "value": ["ws0DFKJnCPhk", "bzaYjKyQFOw2"],
+            "isToolOutput": true,
+            "required": true
          }
        ],
        "outputs": []
@@ -170,8 +172,8 @@
        "flowNodeType": "httpRequest468",
        "showStatus": true,
        "position": {
-          "x": 1216.5166647574395,
-          "y": -206.30162946606856
+          "x": 1264.2009472531117,
+          "y": -455.0773486762623
        },
        "version": "481",
        "inputs": [
@@ -275,7 +277,7 @@
            "key": "system_httpJsonBody",
            "renderTypeList": ["hidden"],
            "valueType": "any",
-            "value": "{\r\n  \"title\": \"{{title-plugin}}\",\r\n  \"xAxis\": \"{{xAxis-plugin}}\",\r\n  \"yAxis\": \"{{yAxis-plugin}}\",\r\n  \"chartType\": \"{{chartType-plugin}}\"\r\n}",
+            "value": "{\r\n  \"title\": \"{{$pluginInput.title$}}\",\r\n  \"xAxis\": {{$pluginInput.xAxis$}},\r\n  \"yAxis\": {{$pluginInput.yAxis$}},\r\n  \"chartType\": \"{{$pluginInput.chartType$}}\"\r\n}",
            "label": "",
            "required": false,
            "valueDesc": "",
@@ -306,126 +308,6 @@
            "description": "",
            "debugLabel": "",
            "toolDescription": ""
-          },
-          {
-            "renderTypeList": ["reference"],
-            "valueType": "string",
-            "canEdit": true,
-            "key": "title-plugin",
-            "label": "title-plugin",
-            "customInputConfig": {
-              "selectValueTypeList": [
-                "string",
-                "number",
-                "boolean",
-                "object",
-                "arrayString",
-                "arrayNumber",
-                "arrayBoolean",
-                "arrayObject",
-                "arrayAny",
-                "any",
-                "chatHistory",
-                "datasetQuote",
-                "dynamic",
-                "selectApp",
-                "selectDataset"
-              ],
-              "showDescription": false,
-              "showDefaultValue": true
-            },
-            "required": true,
-            "value": ["pluginInput", "title"]
-          },
-          {
-            "renderTypeList": ["reference"],
-            "valueType": "string",
-            "canEdit": true,
-            "key": "xAxis-plugin",
-            "label": "xAxis-plugin",
-            "customInputConfig": {
-              "selectValueTypeList": [
-                "string",
-                "number",
-                "boolean",
-                "object",
-                "arrayString",
-                "arrayNumber",
-                "arrayBoolean",
-                "arrayObject",
-                "arrayAny",
-                "any",
-                "chatHistory",
-                "datasetQuote",
-                "dynamic",
-                "selectApp",
-                "selectDataset"
-              ],
-              "showDescription": false,
-              "showDefaultValue": true
-            },
-            "required": true,
-            "value": ["pluginInput", "xAxis"]
-          },
-          {
-            "renderTypeList": ["reference"],
-            "valueType": "string",
-            "canEdit": true,
-            "key": "yAxis-plugin",
-            "label": "yAxis-plugin",
-            "customInputConfig": {
-              "selectValueTypeList": [
-                "string",
-                "number",
-                "boolean",
-                "object",
-                "arrayString",
-                "arrayNumber",
-                "arrayBoolean",
-                "arrayObject",
-                "arrayAny",
-                "any",
-                "chatHistory",
-                "datasetQuote",
-                "dynamic",
-                "selectApp",
-                "selectDataset"
-              ],
-              "showDescription": false,
-              "showDefaultValue": true
-            },
-            "required": true,
-            "value": ["pluginInput", "yAxis"]
-          },
-          {
-            "renderTypeList": ["reference"],
-            "valueType": "string",
-            "canEdit": true,
-            "key": "chartType-plugin",
-            "label": "chartType-plugin",
-            "customInputConfig": {
-              "selectValueTypeList": [
-                "string",
-                "number",
-                "boolean",
-                "object",
-                "arrayString",
-                "arrayNumber",
-                "arrayBoolean",
-                "arrayObject",
-                "arrayAny",
-                "any",
-                "chatHistory",
-                "datasetQuote",
-                "dynamic",
-                "selectApp",
-                "selectDataset"
-              ],
-              "showDescription": false,
-              "showDefaultValue": true
-            },
-            "required": true,
-            "value": ["pluginInput", "chartType"]
          }
        ],
        "outputs": [
--- a/packages/plugins/src/feishu/template.json
+++ b/packages/plugins/src/feishu/template.json
@@ -2,7 +2,7 @@
  "author": "",
  "version": "488",
  "name": "飞书 webhook",
-  "avatar": "/appMarketTemplates/plugin-feishu/avatar.svg",
+  "avatar": "core/app/templates/plugin-feishu",
  "intro": "向飞书机器人发起 webhook 请求。",
  "courseUrl": "https://open.feishu.cn/document/client-docs/bot-v3/add-custom-bot#f62e72d5",
  "showStatus": false,
--- a/packages/plugins/src/searchXNG/index.ts
+++ b/packages/plugins/src/searchXNG/index.ts
@@ -48,6 +48,16 @@ const main = async (props: Props, retry = 3): Response => {
      });
    });

+    if (results.length === 0) {
+      return {
+        result: JSON.stringify([]),
+        error: {
+          message: 'No search results',
+          code: 500
+        }
+      };
+    }
+
    return {
      result: JSON.stringify(results.slice(0, 10))
    };
--- a/packages/service/common/file/gridfs/controller.ts
+++ b/packages/service/common/file/gridfs/controller.ts
@@ -4,7 +4,7 @@ import fsp from 'fs/promises';
 import fs from 'fs';
 import { DatasetFileSchema } from '@fastgpt/global/core/dataset/type';
 import { MongoChatFileSchema, MongoDatasetFileSchema } from './schema';
-import { detectFileEncoding } from '@fastgpt/global/common/file/tools';
+import { detectFileEncoding, detectFileEncodingByPath } from '@fastgpt/global/common/file/tools';
 import { CommonErrEnum } from '@fastgpt/global/common/error/code/common';
 import { MongoRawTextBuffer } from '../../buffer/rawText/schema';
 import { readRawContentByFileBuffer } from '../read/utils';
@@ -36,7 +36,6 @@ export async function uploadFile({
  path,
  filename,
  contentType,
-  encoding,
  metadata = {}
 }: {
  bucketName: `${BucketNameEnum}`;
@@ -45,7 +44,6 @@ export async function uploadFile({
  path: string;
  filename: string;
  contentType?: string;
-  encoding: string;
  metadata?: Record<string, any>;
 }) {
  if (!path) return Promise.reject(`filePath is empty`);
@@ -59,7 +57,7 @@ export async function uploadFile({
  // Add default metadata
  metadata.teamId = teamId;
  metadata.uid = uid;
-  metadata.encoding = encoding;
+  metadata.encoding = await detectFileEncodingByPath(path);

  // create a gridfs bucket
  const bucket = getGridBucket(bucketName);
--- a/packages/service/common/file/image/controller.ts
+++ b/packages/service/common/file/image/controller.ts
@@ -1,43 +1,92 @@
 import { UploadImgProps } from '@fastgpt/global/common/file/api';
 import { imageBaseUrl } from '@fastgpt/global/common/file/image/constants';
 import { MongoImage } from './schema';
-import { ClientSession } from '../../../common/mongo';
+import { ClientSession, Types } from '../../../common/mongo';
 import { guessBase64ImageType } from '../utils';
 import { readFromSecondary } from '../../mongo/utils';
+import { addHours } from 'date-fns';

 export const maxImgSize = 1024 * 1024 * 12;
 const base64MimeRegex = /data:image\/([^\)]+);base64/;
 export async function uploadMongoImg({
-  type,
  base64Img,
  teamId,
-  expiredTime,
  metadata,
-  shareId
+  shareId,
+  forever = false
 }: UploadImgProps & {
  teamId: string;
+  forever?: Boolean;
 }) {
  if (base64Img.length > maxImgSize) {
    return Promise.reject('Image too large');
  }

  const [base64Mime, base64Data] = base64Img.split(',');
+  // Check if mime type is valid
+  if (!base64MimeRegex.test(base64Mime)) {
+    return Promise.reject('Invalid image mime type');
+  }
+
  const mime = `image/${base64Mime.match(base64MimeRegex)?.[1] ?? 'image/jpeg'}`;
  const binary = Buffer.from(base64Data, 'base64');
  const extension = mime.split('/')[1];

  const { _id } = await MongoImage.create({
-    type,
    teamId,
    binary,
-    expiredTime,
    metadata: Object.assign({ mime }, metadata),
-    shareId
+    shareId,
+    expiredTime: forever ? undefined : addHours(new Date(), 1)
  });

  return `${process.env.FE_DOMAIN || ''}${process.env.NEXT_PUBLIC_BASE_URL || ''}${imageBaseUrl}${String(_id)}.${extension}`;
 }

+const getIdFromPath = (path?: string) => {
+  if (!path) return;
+
+  const paths = path.split('/');
+  const name = paths[paths.length - 1];
+
+  if (!name) return;
+
+  const id = name.split('.')[0];
+  if (!id || !Types.ObjectId.isValid(id)) return;
+
+  return id;
+};
+// 删除旧的头像，新的头像去除过期时间
+export const refreshSourceAvatar = async (
+  path?: string,
+  oldPath?: string,
+  session?: ClientSession
+) => {
+  const newId = getIdFromPath(path);
+  const oldId = getIdFromPath(oldPath);
+
+  if (!newId) return;
+
+  await MongoImage.updateOne({ _id: newId }, { $unset: { expiredTime: 1 } }, { session });
+
+  if (oldId) {
+    await MongoImage.deleteOne({ _id: oldId }, { session });
+  }
+};
+export const removeImageByPath = (path?: string, session?: ClientSession) => {
+  if (!path) return;
+
+  const paths = path.split('/');
+  const name = paths[paths.length - 1];
+
+  if (!name) return;
+
+  const id = name.split('.')[0];
+  if (!id || !Types.ObjectId.isValid(id)) return;
+
+  return MongoImage.deleteOne({ _id: id }, { session });
+};
+
 export async function readMongoImg({ id }: { id: string }) {
  const formatId = id.replace(/\.[^/.]+$/, '');

--- a/packages/service/common/file/image/schema.ts
+++ b/packages/service/common/file/image/schema.ts
@@ -1,8 +1,7 @@
 import { TeamCollectionName } from '@fastgpt/global/support/user/team/constant';
-import { connectionMongo, getMongoModel, type Model } from '../../mongo';
+import { connectionMongo, getMongoModel } from '../../mongo';
 import { MongoImageSchemaType } from '@fastgpt/global/common/file/image/type.d';
-import { mongoImageTypeMap } from '@fastgpt/global/common/file/image/constants';
-const { Schema, model, models } = connectionMongo;
+const { Schema } = connectionMongo;

 const ImageSchema = new Schema({
  teamId: {
@@ -14,27 +13,15 @@ const ImageSchema = new Schema({
    type: Date,
    default: () => new Date()
  },
-  expiredTime: {
-    type: Date
-  },
-  binary: {
-    type: Buffer
-  },
-  type: {
-    type: String,
-    enum: Object.keys(mongoImageTypeMap),
-    required: true
-  },
-  metadata: {
-    type: Object
-  }
+  expiredTime: Date,
+  binary: Buffer,
+  metadata: Object
 });

 try {
  // tts expired（60 Minutes）
  ImageSchema.index({ expiredTime: 1 }, { expireAfterSeconds: 60 * 60 });
  ImageSchema.index({ type: 1 });
-  ImageSchema.index({ createTime: 1 });
  // delete related img
  ImageSchema.index({ teamId: 1, 'metadata.relatedId': 1 });
 } catch (error) {
--- a/packages/service/common/file/read/utils.ts
+++ b/packages/service/common/file/read/utils.ts
@@ -1,5 +1,4 @@
 import { uploadMongoImg } from '../image/controller';
-import { MongoImageTypeEnum } from '@fastgpt/global/common/file/image/constants';
 import FormData from 'form-data';

 import { WorkerNameEnum, runWorker } from '../../../worker/utils';
@@ -8,7 +7,6 @@ import type { ReadFileResponse } from '../../../worker/readFile/type';
 import axios from 'axios';
 import { addLog } from '../../system/log';
 import { batchRun } from '@fastgpt/global/common/fn/utils';
-import { addHours } from 'date-fns';
 import { matchMdImgTextAndUpload } from '@fastgpt/global/common/string/markdown';

 export type readRawTextByLocalFileParams = {
@@ -22,7 +20,7 @@ export const readRawTextByLocalFile = async (params: readRawTextByLocalFileParam

  const extension = path?.split('.')?.pop()?.toLowerCase() || '';

-  const buffer = fs.readFileSync(path);
+  const buffer = await fs.promises.readFile(path);

  const { rawText } = await readRawContentByFileBuffer({
    extension,
@@ -114,10 +112,9 @@ export const readRawContentByFileBuffer = async ({
  if (imageList) {
    await batchRun(imageList, async (item) => {
      const src = await uploadMongoImg({
-        type: MongoImageTypeEnum.collectionImage,
        base64Img: `data:${item.mime};base64,${item.base64}`,
        teamId,
-        expiredTime: addHours(new Date(), 1),
+        // expiredTime: addHours(new Date(), 1),
        metadata: {
          ...metadata,
          mime: item.mime
--- a/packages/service/common/middle/cors.ts
+++ b/packages/service/common/middle/cors.ts
@@ -3,10 +3,13 @@ import NextCors from 'nextjs-cors';

 export async function withNextCors(req: NextApiRequest, res: NextApiResponse) {
  const methods = ['GET', 'eHEAD', 'PUT', 'PATCH', 'POST', 'DELETE'];
+
+  const allowedOrigins = process.env.ALLOWED_ORIGINS?.split(',');
  const origin = req.headers.origin;
+
  await NextCors(req, res, {
    methods,
-    origin: origin,
+    origin: allowedOrigins || origin,
    optionsSuccessStatus: 200
  });
 }
--- a/packages/service/common/middle/reqFrequencyLimit.ts
+++ b/packages/service/common/middle/reqFrequencyLimit.ts
@@ -9,10 +9,10 @@ import { jsonRes } from '../response';
 // unit: times/s
 // how to use?
 // export default NextAPI(useQPSLimit(10), handler); // limit 10 times per second for a ip
-export function useReqFrequencyLimit(seconds: number, limit: number) {
+export function useReqFrequencyLimit(seconds: number, limit: number, force = false) {
  return async (req: ApiRequestProps, res: NextApiResponse) => {
    const ip = requestIp.getClientIp(req);
-    if (!ip || process.env.USE_IP_LIMIT !== 'true') {
+    if (!ip || (process.env.USE_IP_LIMIT !== 'true' && !force)) {
      return;
    }
    try {
@@ -22,10 +22,9 @@ export function useReqFrequencyLimit(seconds: number, limit: number) {
        expiredTime: addSeconds(new Date(), seconds)
      });
    } catch (_) {
-      res.status(429);
      jsonRes(res, {
        code: 429,
-        message: ERROR_ENUM.tooManyRequest
+        error: ERROR_ENUM.tooManyRequest
      });
    }
  };
--- a/packages/service/common/response/index.ts
+++ b/packages/service/common/response/index.ts
@@ -33,7 +33,7 @@ export const jsonRes = <T = any>(

    addLog.error(`Api response error: ${url}`, ERROR_RESPONSE[errResponseKey]);

-    return res.json(ERROR_RESPONSE[errResponseKey]);
+    return res.status(code).json(ERROR_RESPONSE[errResponseKey]);
  }

  // another error
--- a/packages/service/common/system/tools.ts
+++ b/packages/service/common/system/tools.ts
@@ -15,6 +15,9 @@ export const initFastGPTConfig = (config?: FastGPTConfigFileType) => {
  global.subPlans = config.subPlans;

  global.llmModels = config.llmModels;
+  global.llmModelPriceType = global.llmModels.some((item) => typeof item.inputPrice === 'number')
+    ? 'IO'
+    : 'Tokens';
  global.vectorModels = config.vectorModels;
  global.audioSpeechModels = config.audioSpeechModels;
  global.whisperModel = config.whisperModel;
--- a/packages/service/core/ai/config/embedding/text-embedding-ada-002.json
+++ b/packages/service/core/ai/config/embedding/text-embedding-ada-002.json
@@ -0,0 +1,11 @@
+{
+  "provider": "OpenAI",
+  "model": "text-embedding-ada-002",
+  "name": "text-embedding-ada-002",
+
+  "defaultToken": 512, // 默认分块 token
+  "maxToken": 3000, // 最大分块 token
+  "weight": 0, // 权重
+
+  "charsPointsPrice": 0 // 积分/1k token
+}
--- a/packages/service/core/ai/config/llm/gpt-4o-mini.json
+++ b/packages/service/core/ai/config/llm/gpt-4o-mini.json
@@ -0,0 +1,33 @@
+{
+  "provider": "OpenAI",
+  "model": "gpt-4o-mini",
+  "name": "GPT-4o-mini", // alias
+
+  "maxContext": 125000, // 最大上下文
+  "maxResponse": 16000, // 最大回复
+  "quoteMaxToken": 60000, // 最大引用
+  "maxTemperature": 1.2, // 最大温度
+  "presencePenaltyRange": [-2, 2], // 惩罚系数范围
+  "frequencyPenaltyRange": [-2, 2], // 频率惩罚系数范围
+  "responseFormatList": ["text", "json_object", "json_schema"], // 响应格式
+  "showStopSign": true, // 是否显示停止符号
+
+  "vision": true, // 是否支持图片识别
+  "toolChoice": true, // 是否支持工具调用
+  "functionCall": false, // 是否支持函数调用（一般都可以 false 了，基本不用了）
+  "defaultSystemChatPrompt": "", // 默认系统提示
+
+  "datasetProcess": true, // 用于知识库文本处理
+  "usedInClassify": true, // 用于问题分类
+  "customCQPrompt": "", // 自定义问题分类提示
+  "usedInExtractFields": true, // 用于提取字段
+  "customExtractPrompt": "", // 自定义提取提示
+  "usedInToolCall": true, // 用于工具调用
+  "usedInQueryExtension": true, // 用于问题优化
+
+  "defaultConfig": {}, // 额外的自定义 body
+  "fieldMap": {}, // body 字段映射
+
+  "censor": false, // 是否开启敏感词过滤
+  "charsPointsPrice": 0 // n 积分/1k token
+}
--- a/packages/service/core/ai/config/rerank/bge-reranker-v2-m3.json
+++ b/packages/service/core/ai/config/rerank/bge-reranker-v2-m3.json
@@ -0,0 +1,6 @@
+{
+  "provider": "BAAI",
+  "model": "bge-reranker-v2-m3",
+  "name": "bge-reranker-v2-m3",
+  "charsPointsPrice": 0
+}
--- a/packages/service/core/ai/config/stt/whisper-1.json
+++ b/packages/service/core/ai/config/stt/whisper-1.json
@@ -0,0 +1,6 @@
+{
+  "provider": "OpenAI",
+  "model": "whisper-1",
+  "name": "whisper-1",
+  "charsPointsPrice": 0
+}
--- a/packages/service/core/ai/config/tts/tts-1.json
+++ b/packages/service/core/ai/config/tts/tts-1.json
@@ -0,0 +1,32 @@
+{
+  "provider": "OpenAI",
+  "model": "tts-1",
+  "name": "TTS1",
+  "charsPointsPrice": 0,
+  "voices": [
+    {
+      "label": "Alloy",
+      "value": "alloy"
+    },
+    {
+      "label": "Echo",
+      "value": "echo"
+    },
+    {
+      "label": "Fable",
+      "value": "fable"
+    },
+    {
+      "label": "Onyx",
+      "value": "onyx"
+    },
+    {
+      "label": "Nova",
+      "value": "nova"
+    },
+    {
+      "label": "Shimmer",
+      "value": "shimmer"
+    }
+  ]
+}
--- a/packages/service/core/ai/functions/createQuestionGuide.ts
+++ b/packages/service/core/ai/functions/createQuestionGuide.ts
@@ -1,6 +1,6 @@
 import type { ChatCompletionMessageParam } from '@fastgpt/global/core/ai/type.d';
 import { createChatCompletion } from '../config';
-import { countGptMessagesTokens } from '../../../common/string/tiktoken/index';
+import { countGptMessagesTokens, countPromptTokens } from '../../../common/string/tiktoken/index';
 import { loadRequestMessages } from '../../chat/utils';
 import { llmCompletionsBodyFormat } from '../utils';
 import {
@@ -20,7 +20,8 @@ export async function createQuestionGuide({
  customPrompt?: string;
 }): Promise<{
  result: string[];
-  tokens: number;
+  inputTokens: number;
+  outputTokens: number;
 }> {
  const concatMessages: ChatCompletionMessageParam[] = [
    ...messages,
@@ -29,6 +30,10 @@ export async function createQuestionGuide({
      content: `${customPrompt || PROMPT_QUESTION_GUIDE}\n${PROMPT_QUESTION_GUIDE_FOOTER}`
    }
  ];
+  const requestMessages = await loadRequestMessages({
+    messages: concatMessages,
+    useVision: false
+  });

  const { response: data } = await createChatCompletion({
    body: llmCompletionsBodyFormat(
@@ -36,10 +41,7 @@ export async function createQuestionGuide({
        model,
        temperature: 0.1,
        max_tokens: 200,
-        messages: await loadRequestMessages({
-          messages: concatMessages,
-          useVision: false
-        }),
+        messages: requestMessages,
        stream: false
      },
      model
@@ -51,13 +53,15 @@ export async function createQuestionGuide({
  const start = answer.indexOf('[');
  const end = answer.lastIndexOf(']');

-  const tokens = await countGptMessagesTokens(concatMessages);
+  const inputTokens = await countGptMessagesTokens(requestMessages);
+  const outputTokens = await countPromptTokens(answer);

  if (start === -1 || end === -1) {
    addLog.warn('Create question guide error', { answer });
    return {
      result: [],
-      tokens: 0
+      inputTokens: 0,
+      outputTokens: 0
    };
  }

@@ -69,14 +73,16 @@ export async function createQuestionGuide({
  try {
    return {
      result: json5.parse(jsonStr),
-      tokens
+      inputTokens,
+      outputTokens
    };
  } catch (error) {
    console.log(error);

    return {
      result: [],
-      tokens: 0
+      inputTokens: 0,
+      outputTokens: 0
    };
  }
 }
--- a/packages/service/core/ai/functions/queryExtension.ts
+++ b/packages/service/core/ai/functions/queryExtension.ts
@@ -1,7 +1,7 @@
 import { replaceVariable } from '@fastgpt/global/common/string/tools';
 import { createChatCompletion } from '../config';
 import { ChatItemType } from '@fastgpt/global/core/chat/type';
-import { countGptMessagesTokens } from '../../../common/string/tiktoken/index';
+import { countGptMessagesTokens, countPromptTokens } from '../../../common/string/tiktoken/index';
 import { chatValue2RuntimePrompt } from '@fastgpt/global/core/chat/adapt';
 import { getLLMModel } from '../model';
 import { llmCompletionsBodyFormat } from '../utils';
@@ -121,7 +121,8 @@ export const queryExtension = async ({
  rawQuery: string;
  extensionQueries: string[];
  model: string;
-  tokens: number;
+  inputTokens: number;
+  outputTokens: number;
 }> => {
  const systemFewShot = chatBg
    ? `Q: 对话背景。
@@ -166,7 +167,8 @@ A: ${chatBg}
      rawQuery: query,
      extensionQueries: [],
      model,
-      tokens: 0
+      inputTokens: 0,
+      outputTokens: 0
    };
  }

@@ -181,7 +183,8 @@ A: ${chatBg}
      rawQuery: query,
      extensionQueries: Array.isArray(queries) ? queries : [],
      model,
-      tokens: await countGptMessagesTokens(messages)
+      inputTokens: await countGptMessagesTokens(messages),
+      outputTokens: await countPromptTokens(answer)
    };
  } catch (error) {
    addLog.error(`Query extension error`, error);
@@ -189,7 +192,8 @@ A: ${chatBg}
      rawQuery: query,
      extensionQueries: [],
      model,
-      tokens: 0
+      inputTokens: 0,
+      outputTokens: 0
    };
  }
 };
--- a/packages/service/core/ai/model.ts
+++ b/packages/service/core/ai/model.ts
@@ -4,6 +4,7 @@ export const getLLMModel = (model?: string) => {
    global.llmModels[0]
  );
 };
+
 export const getDatasetModel = (model?: string) => {
  return (
    global.llmModels
--- a/packages/service/core/app/plugin/utils.ts
+++ b/packages/service/core/app/plugin/utils.ts
@@ -1,11 +1,15 @@
 import { ChatNodeUsageType } from '@fastgpt/global/support/wallet/bill/type';
 import { PluginRuntimeType } from '@fastgpt/global/core/plugin/type';
+import { splitCombinePluginId } from './controller';
+import { PluginSourceEnum } from '@fastgpt/global/core/plugin/constants';

 /* 
  Plugin points calculation:
-  1. Return 0 if error
-  2. Add configured points if commercial plugin
-  3. Add sum of child nodes points
+  1. 系统插件/商业版插件：
+    - 有错误：返回 0
+    - 无错误：返回 单次积分 + 子流程积分（可配置）
+  2. 个人插件
+    - 返回 子流程积分
 */
 export const computedPluginUsage = async ({
  plugin,
@@ -16,13 +20,16 @@ export const computedPluginUsage = async ({
  childrenUsage: ChatNodeUsageType[];
  error?: boolean;
 }) => {
-  if (error) {
-    return 0;
+  const { source } = await splitCombinePluginId(plugin.id);
+  const childrenUsages = childrenUsage.reduce((sum, item) => sum + (item.totalPoints || 0), 0);
+
+  if (source !== PluginSourceEnum.personal) {
+    if (error) return 0;
+
+    const pluginCurrentCost = plugin.currentCost ?? 0;
+
+    return plugin.hasTokenFee ? pluginCurrentCost + childrenUsages : pluginCurrentCost;
  }

-  const childrenIUsages = childrenUsage.reduce((sum, item) => sum + (item.totalPoints || 0), 0);
-
-  const pluginCurrentCose = plugin.currentCost ?? 0;
-
-  return plugin.hasTokenFee ? pluginCurrentCose + childrenIUsages : pluginCurrentCose;
+  return childrenUsages;
 };
--- a/packages/service/core/chat/chatItemSchema.ts
+++ b/packages/service/core/chat/chatItemSchema.ts
@@ -86,24 +86,21 @@ const ChatItemSchema = new Schema({
 });

 try {
-  ChatItemSchema.index({ dataId: 1 }, { background: true });
+  ChatItemSchema.index({ dataId: 1 });
  /* delete by app; 
     delete by chat id;
     get chat list; 
     get chat logs; 
     close custom feedback; 
  */
-  ChatItemSchema.index({ appId: 1, chatId: 1, dataId: 1 }, { background: true });
+  ChatItemSchema.index({ appId: 1, chatId: 1, dataId: 1 });
  // admin charts
-  ChatItemSchema.index({ time: -1, obj: 1 }, { background: true });
+  ChatItemSchema.index({ time: -1, obj: 1 });
  // timer, clear history
-  ChatItemSchema.index({ teamId: 1, time: -1 }, { background: true });
+  ChatItemSchema.index({ teamId: 1, time: -1 });

  // Admin charts
-  ChatItemSchema.index(
-    { obj: 1, time: -1 },
-    { background: true, partialFilterExpression: { obj: 'Human' } }
-  );
+  ChatItemSchema.index({ obj: 1, time: -1 }, { partialFilterExpression: { obj: 'Human' } });
 } catch (error) {
  console.log(error);
 }
--- a/packages/service/core/chat/chatSchema.ts
+++ b/packages/service/core/chat/chatSchema.ts
@@ -81,19 +81,19 @@ const ChatSchema = new Schema({
 });

 try {
-  ChatSchema.index({ chatId: 1 }, { background: true });
+  ChatSchema.index({ chatId: 1 });
  // get user history
-  ChatSchema.index({ tmbId: 1, appId: 1, top: -1, updateTime: -1 }, { background: true });
+  ChatSchema.index({ tmbId: 1, appId: 1, top: -1, updateTime: -1 });
  // delete by appid; clear history; init chat; update chat; auth chat; get chat;
-  ChatSchema.index({ appId: 1, chatId: 1 }, { background: true });
+  ChatSchema.index({ appId: 1, chatId: 1 });

  // get chat logs;
-  ChatSchema.index({ teamId: 1, appId: 1, updateTime: -1 }, { background: true });
+  ChatSchema.index({ teamId: 1, appId: 1, updateTime: -1 });
  // get share chat history
-  ChatSchema.index({ shareId: 1, outLinkUid: 1, updateTime: -1 }, { background: true });
+  ChatSchema.index({ shareId: 1, outLinkUid: 1, updateTime: -1 });

  // timer, clear history
-  ChatSchema.index({ teamId: 1, updateTime: -1 }, { background: true });
+  ChatSchema.index({ teamId: 1, updateTime: -1 });
 } catch (error) {
  console.log(error);
 }
--- a/packages/service/core/dataset/collection/controller.ts
+++ b/packages/service/core/dataset/collection/controller.ts
@@ -24,6 +24,7 @@ import { pushDataListToTrainingQueue } from '../training/controller';
 import { MongoImage } from '../../../common/file/image/schema';
 import { hashStr } from '@fastgpt/global/common/string/tools';
 import { addDays } from 'date-fns';
+import { MongoDatasetDataText } from '../data/dataTextSchema';

 export const createCollectionAndInsertData = async ({
  dataset,
@@ -240,12 +241,12 @@ export const delCollectionRelatedSource = async ({
    .map((item) => item?.metadata?.relatedImgId || '')
    .filter(Boolean);

-  // delete files
+  // Delete files
  await delFileByFileIdList({
    bucketName: BucketNameEnum.dataset,
    fileIdList
  });
-  // delete images
+  // Delete images
  await delImgByRelatedId({
    teamId,
    relateIds: relatedImageIds,
@@ -273,7 +274,7 @@ export async function delCollection({
  const datasetIds = Array.from(new Set(collections.map((item) => String(item.datasetId))));
  const collectionIds = collections.map((item) => String(item._id));

-  // delete training data
+  // Delete training data
  await MongoDatasetTraining.deleteMany({
    teamId,
    datasetIds: { $in: datasetIds },
@@ -285,11 +286,16 @@ export async function delCollection({
    await delCollectionRelatedSource({ collections, session });
  }

-  // delete dataset.datas
+  // Delete dataset_datas
  await MongoDatasetData.deleteMany(
    { teamId, datasetIds: { $in: datasetIds }, collectionId: { $in: collectionIds } },
    { session }
  );
+  // Delete dataset_data_texts
+  await MongoDatasetDataText.deleteMany(
+    { teamId, datasetIds: { $in: datasetIds }, collectionId: { $in: collectionIds } },
+    { session }
+  );

  // delete collections
  await MongoDatasetCollection.deleteMany(
--- a/packages/service/core/dataset/controller.ts
+++ b/packages/service/core/dataset/controller.ts
@@ -6,6 +6,7 @@ import { ClientSession } from '../../common/mongo';
 import { MongoDatasetTraining } from './training/schema';
 import { MongoDatasetData } from './data/schema';
 import { deleteDatasetDataVector } from '../../common/vectorStore/controller';
+import { MongoDatasetDataText } from './data/dataTextSchema';

 /* ============= dataset ========== */
 /* find all datasetId by top datasetId */
@@ -92,7 +93,7 @@ export async function delDatasetRelevantData({
    { session }
  ).lean();

-  // image and file
+  // Delete Image and file
  await delCollectionRelatedSource({ collections, session });

  // delete collections
@@ -101,9 +102,15 @@ export async function delDatasetRelevantData({
    datasetId: { $in: datasetIds }
  }).session(session);

-  // delete dataset.datas(Not need session)
+  // No session delete:
+  // Delete dataset_data_texts
+  await MongoDatasetDataText.deleteMany({
+    teamId,
+    datasetId: { $in: datasetIds }
+  });
+  // delete dataset_datas
  await MongoDatasetData.deleteMany({ teamId, datasetId: { $in: datasetIds } });

-  // no session delete: delete files, vector data
+  // Delete vector data
  await deleteDatasetDataVector({ teamId, datasetIds });
 }
--- a/packages/service/core/dataset/data/dataTextSchema.ts
+++ b/packages/service/core/dataset/data/dataTextSchema.ts
@@ -0,0 +1,45 @@
+import { connectionMongo, getMongoModel } from '../../../common/mongo';
+const { Schema } = connectionMongo;
+import { DatasetDataSchemaType } from '@fastgpt/global/core/dataset/type.d';
+import { TeamCollectionName } from '@fastgpt/global/support/user/team/constant';
+import { DatasetCollectionName } from '../schema';
+import { DatasetColCollectionName } from '../collection/schema';
+import { DatasetDataCollectionName } from './schema';
+
+export const DatasetDataTextCollectionName = 'dataset_data_texts';
+
+const DatasetDataTextSchema = new Schema({
+  teamId: {
+    type: Schema.Types.ObjectId,
+    ref: TeamCollectionName,
+    required: true
+  },
+  datasetId: {
+    type: Schema.Types.ObjectId,
+    ref: DatasetCollectionName,
+    required: true
+  },
+  collectionId: {
+    type: Schema.Types.ObjectId,
+    ref: DatasetColCollectionName,
+    required: true
+  },
+  dataId: {
+    type: Schema.Types.ObjectId,
+    ref: DatasetDataCollectionName,
+    required: true
+  },
+  fullTextToken: String
+});
+
+try {
+  DatasetDataTextSchema.index({ teamId: 1, datasetId: 1, fullTextToken: 'text' });
+  DatasetDataTextSchema.index({ dataId: 1 }, { unique: true });
+} catch (error) {
+  console.log(error);
+}
+
+export const MongoDatasetDataText = getMongoModel<DatasetDataSchemaType>(
+  DatasetDataTextCollectionName,
+  DatasetDataTextSchema
+);
--- a/packages/service/core/dataset/data/schema.ts
+++ b/packages/service/core/dataset/data/schema.ts
@@ -1,4 +1,4 @@
-import { connectionMongo, getMongoModel, type Model } from '../../../common/mongo';
+import { connectionMongo, getMongoModel } from '../../../common/mongo';
 const { Schema, model, models } = connectionMongo;
 import { DatasetDataSchemaType } from '@fastgpt/global/core/dataset/type.d';
 import {
@@ -39,10 +39,6 @@ const DatasetDataSchema = new Schema({
    type: String,
    default: ''
  },
-  fullTextToken: {
-    type: String,
-    default: ''
-  },
  indexes: {
    type: [
      {
@@ -71,17 +67,11 @@ const DatasetDataSchema = new Schema({
    type: Number,
    default: 0
  },
-  inited: {
-    type: Boolean
-  },
-  rebuilding: Boolean
-});
+  rebuilding: Boolean,

-DatasetDataSchema.virtual('collection', {
-  ref: DatasetColCollectionName,
-  localField: 'collectionId',
-  foreignField: '_id',
-  justOne: true
+  // Abandon
+  fullTextToken: String,
+  initFullText: Boolean
 });

 try {
@@ -93,13 +83,15 @@ try {
    chunkIndex: 1,
    updateTime: -1
  });
-  // full text index
-  DatasetDataSchema.index({ teamId: 1, datasetId: 1, fullTextToken: 'text' });
+  // FullText tmp full text index
+  // DatasetDataSchema.index({ teamId: 1, datasetId: 1, fullTextToken: 'text' });
  // Recall vectors after data matching
  DatasetDataSchema.index({ teamId: 1, datasetId: 1, collectionId: 1, 'indexes.dataId': 1 });
  DatasetDataSchema.index({ updateTime: 1 });
  // rebuild data
  DatasetDataSchema.index({ rebuilding: 1, teamId: 1, datasetId: 1 });
+
+  DatasetDataSchema.index({ initFullText: 1 });
 } catch (error) {
  console.log(error);
 }
--- a/packages/service/core/dataset/search/controller.ts
+++ b/packages/service/core/dataset/search/controller.ts
@@ -8,8 +8,8 @@ import { getVectorsByText } from '../../ai/embedding';
 import { getVectorModel } from '../../ai/model';
 import { MongoDatasetData } from '../data/schema';
 import {
-  DatasetCollectionSchemaType,
  DatasetDataSchemaType,
+  DatasetDataTextSchemaType,
  SearchDataResponseItemType
 } from '@fastgpt/global/core/dataset/type';
 import { MongoDatasetCollection } from '../collection/schema';
@@ -23,6 +23,7 @@ import { Types } from '../../../common/mongo';
 import json5 from 'json5';
 import { MongoDatasetCollectionTags } from '../tag/schema';
 import { readFromSecondary } from '../../../common/mongo/utils';
+import { MongoDatasetDataText } from '../data/dataTextSchema';

 type SearchDatasetDataProps = {
  teamId: string;
@@ -266,57 +267,60 @@ export async function searchDatasetData(props: SearchDatasetDataProps) {
      filterCollectionIdList
    });

-    // get q and a
-    const dataList = await MongoDatasetData.find(
-      {
-        teamId,
-        datasetId: { $in: datasetIds },
-        collectionId: { $in: Array.from(new Set(results.map((item) => item.collectionId))) },
-        'indexes.dataId': { $in: results.map((item) => item.id?.trim()) }
-      },
-      'datasetId collectionId updateTime q a chunkIndex indexes'
-    )
-      .populate<{ collection: DatasetCollectionSchemaType }>(
-        'collection',
-        'name fileId rawLink externalFileId externalFileUrl'
-      )
-      .lean();
+    // Get data and collections
+    const collectionIdList = Array.from(new Set(results.map((item) => item.collectionId)));
+    const [dataList, collections] = await Promise.all([
+      MongoDatasetData.find(
+        {
+          teamId,
+          datasetId: { $in: datasetIds },
+          collectionId: { $in: collectionIdList },
+          'indexes.dataId': { $in: results.map((item) => item.id?.trim()) }
+        },
+        '_id datasetId collectionId updateTime q a chunkIndex indexes',
+        { ...readFromSecondary }
+      ).lean(),
+      MongoDatasetCollection.find(
+        {
+          _id: { $in: collectionIdList }
+        },
+        '_id name fileId rawLink externalFileId externalFileUrl',
+        { ...readFromSecondary }
+      ).lean()
+    ]);

-    // add score to data(It's already sorted. The first one is the one with the most points)
-    const concatResults = dataList.map((data) => {
-      const dataIdList = data.indexes.map((item) => item.dataId);
+    const formatResult = results
+      .map((item, index) => {
+        const collection = collections.find((col) => String(col._id) === String(item.collectionId));
+        if (!collection) {
+          console.log('Collection is not found', item);
+          return;
+        }
+        const data = dataList.find((data) =>
+          data.indexes.some((index) => index.dataId === item.id)
+        );
+        if (!data) {
+          console.log('Data is not found', item);
+          return;
+        }

-      const maxScoreResult = results.find((item) => {
-        return dataIdList.includes(item.id);
-      });
+        const score = item?.score || 0;

-      return {
-        ...data,
-        score: maxScoreResult?.score || 0
-      };
-    });
+        const result: SearchDataResponseItemType = {
+          id: String(data._id),
+          updateTime: data.updateTime,
+          q: data.q,
+          a: data.a,
+          chunkIndex: data.chunkIndex,
+          datasetId: String(data.datasetId),
+          collectionId: String(data.collectionId),
+          ...getCollectionSourceData(collection),
+          score: [{ type: SearchScoreTypeEnum.embedding, value: score, index }]
+        };

-    concatResults.sort((a, b) => b.score - a.score);
-
-    const formatResult = concatResults.map((data, index) => {
-      if (!data.collectionId) {
-        console.log('Collection is not found', data);
-      }
-
-      const result: SearchDataResponseItemType = {
-        id: String(data._id),
-        updateTime: data.updateTime,
-        q: data.q,
-        a: data.a,
-        chunkIndex: data.chunkIndex,
-        datasetId: String(data.datasetId),
-        collectionId: String(data.collectionId),
-        ...getCollectionSourceData(data.collection),
-        score: [{ type: SearchScoreTypeEnum.embedding, value: data.score, index }]
-      };
-
-      return result;
-    });
+        return result;
+      })
+      .filter(Boolean) as SearchDataResponseItemType[];

    return {
      embeddingRecallResults: formatResult,
@@ -344,88 +348,224 @@ export async function searchDatasetData(props: SearchDatasetDataProps) {
      };
    }

-    let searchResults = (
+    const searchResults = (
      await Promise.all(
        datasetIds.map(async (id) => {
-          return MongoDatasetData.aggregate([
-            {
-              $match: {
-                teamId: new Types.ObjectId(teamId),
-                datasetId: new Types.ObjectId(id),
-                $text: { $search: jiebaSplit({ text: query }) },
-                ...(filterCollectionIdList
-                  ? {
-                      collectionId: {
-                        $in: filterCollectionIdList.map((id) => new Types.ObjectId(id))
+          return MongoDatasetData.aggregate(
+            [
+              {
+                $match: {
+                  teamId: new Types.ObjectId(teamId),
+                  datasetId: new Types.ObjectId(id),
+                  $text: { $search: jiebaSplit({ text: query }) },
+                  ...(filterCollectionIdList
+                    ? {
+                        collectionId: {
+                          $in: filterCollectionIdList.map((id) => new Types.ObjectId(id))
+                        }
                      }
-                    }
-                  : {}),
-                ...(forbidCollectionIdList && forbidCollectionIdList.length > 0
-                  ? {
-                      collectionId: {
-                        $nin: forbidCollectionIdList.map((id) => new Types.ObjectId(id))
+                    : {}),
+                  ...(forbidCollectionIdList && forbidCollectionIdList.length > 0
+                    ? {
+                        collectionId: {
+                          $nin: forbidCollectionIdList.map((id) => new Types.ObjectId(id))
+                        }
                      }
-                    }
-                  : {})
+                    : {})
+                }
+              },
+              {
+                $sort: {
+                  score: { $meta: 'textScore' }
+                }
+              },
+              {
+                $limit: limit
+              },
+              {
+                $project: {
+                  _id: 1,
+                  datasetId: 1,
+                  collectionId: 1,
+                  updateTime: 1,
+                  q: 1,
+                  a: 1,
+                  chunkIndex: 1,
+                  score: { $meta: 'textScore' }
+                }
              }
-            },
+            ],
            {
-              $addFields: {
-                score: { $meta: 'textScore' }
-              }
-            },
-            {
-              $sort: {
-                score: { $meta: 'textScore' }
-              }
-            },
-            {
-              $limit: limit
-            },
-            {
-              $project: {
-                _id: 1,
-                datasetId: 1,
-                collectionId: 1,
-                updateTime: 1,
-                q: 1,
-                a: 1,
-                chunkIndex: 1,
-                score: 1
-              }
+              ...readFromSecondary
            }
-          ]);
+          );
        })
      )
    ).flat() as (DatasetDataSchemaType & { score: number })[];

-    // resort
-    searchResults.sort((a, b) => b.score - a.score);
-    searchResults.slice(0, limit);
-
+    // Get data and collections
    const collections = await MongoDatasetCollection.find(
      {
        _id: { $in: searchResults.map((item) => item.collectionId) }
      },
-      '_id name fileId rawLink'
-    );
+      '_id name fileId rawLink externalFileId externalFileUrl',
+      { ...readFromSecondary }
+    ).lean();

    return {
-      fullTextRecallResults: searchResults.map((item, index) => {
-        const collection = collections.find((col) => String(col._id) === String(item.collectionId));
-        return {
-          id: String(item._id),
-          datasetId: String(item.datasetId),
-          collectionId: String(item.collectionId),
-          updateTime: item.updateTime,
-          ...getCollectionSourceData(collection),
-          q: item.q,
-          a: item.a,
-          chunkIndex: item.chunkIndex,
-          indexes: item.indexes,
-          score: [{ type: SearchScoreTypeEnum.fullText, value: item.score, index }]
-        };
-      }),
+      fullTextRecallResults: searchResults
+        .map((data, index) => {
+          const collection = collections.find(
+            (col) => String(col._id) === String(data.collectionId)
+          );
+          if (!collection) {
+            console.log('Collection is not found', data);
+            return;
+          }
+
+          return {
+            id: String(data._id),
+            datasetId: String(data.datasetId),
+            collectionId: String(data.collectionId),
+            updateTime: data.updateTime,
+            q: data.q,
+            a: data.a,
+            chunkIndex: data.chunkIndex,
+            indexes: data.indexes,
+            ...getCollectionSourceData(collection),
+            score: [{ type: SearchScoreTypeEnum.fullText, value: data.score ?? 0, index }]
+          };
+        })
+        .filter(Boolean) as SearchDataResponseItemType[],
+      tokenLen: 0
+    };
+  };
+  const fullTextRecall2 = async ({
+    query,
+    limit,
+    filterCollectionIdList,
+    forbidCollectionIdList
+  }: {
+    query: string;
+    limit: number;
+    filterCollectionIdList?: string[];
+    forbidCollectionIdList: string[];
+  }): Promise<{
+    fullTextRecallResults: SearchDataResponseItemType[];
+    tokenLen: number;
+  }> => {
+    if (limit === 0) {
+      return {
+        fullTextRecallResults: [],
+        tokenLen: 0
+      };
+    }
+
+    const searchResults = (
+      await Promise.all(
+        datasetIds.map(async (id) => {
+          return MongoDatasetDataText.aggregate(
+            [
+              {
+                $match: {
+                  teamId: new Types.ObjectId(teamId),
+                  datasetId: new Types.ObjectId(id),
+                  $text: { $search: jiebaSplit({ text: query }) },
+                  ...(filterCollectionIdList
+                    ? {
+                        collectionId: {
+                          $in: filterCollectionIdList.map((id) => new Types.ObjectId(id))
+                        }
+                      }
+                    : {}),
+                  ...(forbidCollectionIdList && forbidCollectionIdList.length > 0
+                    ? {
+                        collectionId: {
+                          $nin: forbidCollectionIdList.map((id) => new Types.ObjectId(id))
+                        }
+                      }
+                    : {})
+                }
+              },
+              {
+                $sort: {
+                  score: { $meta: 'textScore' }
+                }
+              },
+              {
+                $limit: limit
+              },
+              {
+                $project: {
+                  _id: 1,
+                  collectionId: 1,
+                  dataId: 1,
+                  score: { $meta: 'textScore' }
+                }
+              }
+            ],
+            {
+              ...readFromSecondary
+            }
+          );
+        })
+      )
+    ).flat() as (DatasetDataTextSchemaType & { score: number })[];
+
+    // Get data and collections
+    const [dataList, collections] = await Promise.all([
+      MongoDatasetData.find(
+        {
+          _id: { $in: searchResults.map((item) => item.dataId) }
+        },
+        '_id datasetId collectionId updateTime q a chunkIndex indexes',
+        { ...readFromSecondary }
+      ).lean(),
+      MongoDatasetCollection.find(
+        {
+          _id: { $in: searchResults.map((item) => item.collectionId) }
+        },
+        '_id name fileId rawLink externalFileId externalFileUrl',
+        { ...readFromSecondary }
+      ).lean()
+    ]);
+
+    return {
+      fullTextRecallResults: searchResults
+        .map((item, index) => {
+          const collection = collections.find(
+            (col) => String(col._id) === String(item.collectionId)
+          );
+          if (!collection) {
+            console.log('Collection is not found', item);
+            return;
+          }
+          const data = dataList.find((data) => String(data._id) === String(item.dataId));
+          if (!data) {
+            console.log('Data is not found', item);
+            return;
+          }
+
+          return {
+            id: String(data._id),
+            datasetId: String(data.datasetId),
+            collectionId: String(data.collectionId),
+            updateTime: data.updateTime,
+            q: data.q,
+            a: data.a,
+            chunkIndex: data.chunkIndex,
+            indexes: data.indexes,
+            ...getCollectionSourceData(collection),
+            score: [
+              {
+                type: SearchScoreTypeEnum.fullText,
+                value: item.score || 0,
+                index
+              }
+            ]
+          };
+        })
+        .filter(Boolean) as SearchDataResponseItemType[],
      tokenLen: 0
    };
  };
@@ -496,7 +636,8 @@ export async function searchDatasetData(props: SearchDatasetDataProps) {
            forbidCollectionIdList,
            filterCollectionIdList
          }),
-          fullTextRecall({
+          // FullText tmp
+          fullTextRecall2({
            query,
            limit: fullTextLimit,
            filterCollectionIdList,
--- a/packages/service/core/workflow/dispatch/agent/classifyQuestion.ts
+++ b/packages/service/core/workflow/dispatch/agent/classifyQuestion.ts
@@ -1,5 +1,8 @@
 import { chats2GPTMessages } from '@fastgpt/global/core/chat/adapt';
-import { countMessagesTokens } from '../../../../common/string/tiktoken/index';
+import {
+  countGptMessagesTokens,
+  countPromptTokens
+} from '../../../../common/string/tiktoken/index';
 import type { ChatItemType } from '@fastgpt/global/core/chat/type.d';
 import { ChatItemValueTypeEnum, ChatRoleEnum } from '@fastgpt/global/core/chat/constants';
 import { createChatCompletion } from '../../../ai/config';
@@ -49,7 +52,7 @@ export const dispatchClassifyQuestion = async (props: Props): Promise<CQResponse

  const chatHistories = getHistories(history, histories);

-  const { arg, tokens } = await completions({
+  const { arg, inputTokens, outputTokens } = await completions({
    ...props,
    histories: chatHistories,
    cqModel
@@ -59,7 +62,8 @@ export const dispatchClassifyQuestion = async (props: Props): Promise<CQResponse

  const { totalPoints, modelName } = formatModelChars2Points({
    model: cqModel.model,
-    tokens,
+    inputTokens: inputTokens,
+    outputTokens: outputTokens,
    modelType: ModelTypeEnum.llm
  });

@@ -72,7 +76,8 @@ export const dispatchClassifyQuestion = async (props: Props): Promise<CQResponse
      totalPoints: externalProvider.openaiAccount?.key ? 0 : totalPoints,
      model: modelName,
      query: userChatInput,
-      tokens,
+      inputTokens: inputTokens,
+      outputTokens: outputTokens,
      cqList: agents,
      cqResult: result.value,
      contextTotalLen: chatHistories.length + 2
@@ -82,7 +87,8 @@ export const dispatchClassifyQuestion = async (props: Props): Promise<CQResponse
        moduleName: name,
        totalPoints: externalProvider.openaiAccount?.key ? 0 : totalPoints,
        model: modelName,
-        tokens
+        inputTokens: inputTokens,
+        outputTokens: outputTokens
      }
    ]
  };
@@ -148,7 +154,8 @@ const completions = async ({
  }

  return {
-    tokens: await countMessagesTokens(messages),
+    inputTokens: await countGptMessagesTokens(requestMessages),
+    outputTokens: await countPromptTokens(answer),
    arg: { type: id }
  };
 };
--- a/packages/service/core/workflow/dispatch/agent/extract.ts
+++ b/packages/service/core/workflow/dispatch/agent/extract.ts
@@ -3,7 +3,8 @@ import { filterGPTMessageByMaxTokens, loadRequestMessages } from '../../../chat/
 import type { ChatItemType } from '@fastgpt/global/core/chat/type.d';
 import {
  countMessagesTokens,
-  countGptMessagesTokens
+  countGptMessagesTokens,
+  countPromptTokens
 } from '../../../../common/string/tiktoken/index';
 import { ChatItemValueTypeEnum, ChatRoleEnum } from '@fastgpt/global/core/chat/constants';
 import { createChatCompletion } from '../../../ai/config';
@@ -59,7 +60,7 @@ export async function dispatchContentExtract(props: Props): Promise<Response> {
  const extractModel = getLLMModel(model);
  const chatHistories = getHistories(history, histories);

-  const { arg, tokens } = await (async () => {
+  const { arg, inputTokens, outputTokens } = await (async () => {
    if (extractModel.toolChoice) {
      return toolChoice({
        ...props,
@@ -114,7 +115,8 @@ export async function dispatchContentExtract(props: Props): Promise<Response> {

  const { totalPoints, modelName } = formatModelChars2Points({
    model: extractModel.model,
-    tokens,
+    inputTokens: inputTokens,
+    outputTokens: outputTokens,
    modelType: ModelTypeEnum.llm
  });

@@ -126,7 +128,8 @@ export async function dispatchContentExtract(props: Props): Promise<Response> {
      totalPoints: externalProvider.openaiAccount?.key ? 0 : totalPoints,
      model: modelName,
      query: content,
-      tokens,
+      inputTokens,
+      outputTokens,
      extractDescription: description,
      extractResult: arg,
      contextTotalLen: chatHistories.length + 2
@@ -136,7 +139,8 @@ export async function dispatchContentExtract(props: Props): Promise<Response> {
        moduleName: name,
        totalPoints: externalProvider.openaiAccount?.key ? 0 : totalPoints,
        model: modelName,
-        tokens
+        inputTokens,
+        outputTokens
      }
    ]
  };
@@ -249,15 +253,18 @@ const toolChoice = async (props: ActionProps) => {
    }
  })();

-  const completeMessages: ChatCompletionMessageParam[] = [
-    ...filterMessages,
+  const AIMessages: ChatCompletionMessageParam[] = [
    {
      role: ChatCompletionRequestMessageRoleEnum.Assistant,
      tool_calls: response.choices?.[0]?.message?.tool_calls
    }
  ];
+
+  const inputTokens = await countGptMessagesTokens(filterMessages, tools);
+  const outputTokens = await countGptMessagesTokens(AIMessages);
  return {
-    tokens: await countGptMessagesTokens(completeMessages, tools),
+    inputTokens,
+    outputTokens,
    arg
  };
 };
@@ -286,17 +293,21 @@ const functionCall = async (props: ActionProps) => {

  try {
    const arg = JSON.parse(response?.choices?.[0]?.message?.function_call?.arguments || '');
-    const completeMessages: ChatCompletionMessageParam[] = [
-      ...filterMessages,
+
+    const AIMessages: ChatCompletionMessageParam[] = [
      {
        role: ChatCompletionRequestMessageRoleEnum.Assistant,
        function_call: response.choices?.[0]?.message?.function_call
      }
    ];

+    const inputTokens = await countGptMessagesTokens(filterMessages, undefined, functions);
+    const outputTokens = await countGptMessagesTokens(AIMessages);
+
    return {
      arg,
-      tokens: await countGptMessagesTokens(completeMessages, undefined, functions)
+      inputTokens,
+      outputTokens
    };
  } catch (error) {
    console.log(response.choices?.[0]?.message);
@@ -305,7 +316,8 @@ const functionCall = async (props: ActionProps) => {

    return {
      arg: {},
-      tokens: 0
+      inputTokens: 0,
+      outputTokens: 0
    };
  }
 };
@@ -370,7 +382,8 @@ Human: ${content}`
  if (!jsonStr) {
    return {
      rawResponse: answer,
-      tokens: await countMessagesTokens(messages),
+      inputTokens: await countMessagesTokens(messages),
+      outputTokens: await countPromptTokens(answer),
      arg: {}
    };
  }
@@ -378,7 +391,8 @@ Human: ${content}`
  try {
    return {
      rawResponse: answer,
-      tokens: await countMessagesTokens(messages),
+      inputTokens: await countMessagesTokens(messages),
+      outputTokens: await countPromptTokens(answer),
      arg: json5.parse(jsonStr) as Record<string, any>
    };
  } catch (error) {
@@ -386,7 +400,8 @@ Human: ${content}`
    console.log(error);
    return {
      rawResponse: answer,
-      tokens: await countMessagesTokens(messages),
+      inputTokens: await countMessagesTokens(messages),
+      outputTokens: await countPromptTokens(answer),
      arg: {}
    };
  }
--- a/packages/service/core/workflow/dispatch/agent/runTool/functionCall.ts
+++ b/packages/service/core/workflow/dispatch/agent/runTool/functionCall.ts
@@ -109,7 +109,8 @@ export const runToolWithFunctionCall = async (

      return {
        dispatchFlowResponse: [toolRunResponse],
-        toolNodeTokens: 0,
+        toolNodeInputTokens: 0,
+        toolNodeOutputTokens: 0,
        completeMessages: requestMessages,
        assistantResponses: toolRunResponse.assistantResponses,
        runTimes: toolRunResponse.runTimes,
@@ -126,7 +127,8 @@ export const runToolWithFunctionCall = async (
      },
      {
        dispatchFlowResponse: [toolRunResponse],
-        toolNodeTokens: 0,
+        toolNodeInputTokens: 0,
+        toolNodeOutputTokens: 0,
        assistantResponses: toolRunResponse.assistantResponses,
        runTimes: toolRunResponse.runTimes
      }
@@ -340,7 +342,9 @@ export const runToolWithFunctionCall = async (
      assistantToolMsgParams
    ] as ChatCompletionMessageParam[];
    // Only toolCall tokens are counted here, Tool response tokens count towards the next reply
-    const tokens = await countGptMessagesTokens(concatToolMessages, undefined, functions);
+    // const tokens = await countGptMessagesTokens(concatToolMessages, undefined, functions);
+    const inputTokens = await countGptMessagesTokens(requestMessages, undefined, functions);
+    const outputTokens = await countGptMessagesTokens([assistantToolMsgParams]);
    /* 
      ...
      user
@@ -375,7 +379,12 @@ export const runToolWithFunctionCall = async (
    const runTimes =
      (response?.runTimes || 0) +
      flatToolsResponseData.reduce((sum, item) => sum + item.runTimes, 0);
-    const toolNodeTokens = response?.toolNodeTokens ? response.toolNodeTokens + tokens : tokens;
+    const toolNodeInputTokens = response?.toolNodeInputTokens
+      ? response.toolNodeInputTokens + inputTokens
+      : inputTokens;
+    const toolNodeOutputTokens = response?.toolNodeOutputTokens
+      ? response.toolNodeOutputTokens + outputTokens
+      : outputTokens;

    // Check stop signal
    const hasStopSignal = flatToolsResponseData.some(
@@ -408,7 +417,8 @@ export const runToolWithFunctionCall = async (

      return {
        dispatchFlowResponse,
-        toolNodeTokens,
+        toolNodeInputTokens,
+        toolNodeOutputTokens,
        completeMessages,
        assistantResponses: toolNodeAssistants,
        runTimes,
@@ -423,7 +433,8 @@ export const runToolWithFunctionCall = async (
      },
      {
        dispatchFlowResponse,
-        toolNodeTokens,
+        toolNodeInputTokens,
+        toolNodeOutputTokens,
        assistantResponses: toolNodeAssistants,
        runTimes
      }
@@ -435,7 +446,8 @@ export const runToolWithFunctionCall = async (
      content: answer
    };
    const completeMessages = filterMessages.concat(gptAssistantResponse);
-    const tokens = await countGptMessagesTokens(completeMessages, undefined, functions);
+    const inputTokens = await countGptMessagesTokens(requestMessages, undefined, functions);
+    const outputTokens = await countGptMessagesTokens([gptAssistantResponse]);
    // console.log(tokens, 'response token');

    // concat tool assistant
@@ -443,7 +455,12 @@ export const runToolWithFunctionCall = async (

    return {
      dispatchFlowResponse: response?.dispatchFlowResponse || [],
-      toolNodeTokens: response?.toolNodeTokens ? response.toolNodeTokens + tokens : tokens,
+      toolNodeInputTokens: response?.toolNodeInputTokens
+        ? response.toolNodeInputTokens + inputTokens
+        : inputTokens,
+      toolNodeOutputTokens: response?.toolNodeOutputTokens
+        ? response.toolNodeOutputTokens + outputTokens
+        : outputTokens,
      completeMessages,
      assistantResponses: [...assistantResponses, ...toolNodeAssistant.value],
      runTimes: (response?.runTimes || 0) + 1
--- a/packages/service/core/workflow/dispatch/agent/runTool/index.ts
+++ b/packages/service/core/workflow/dispatch/agent/runTool/index.ts
@@ -165,6 +165,8 @@ export const dispatchRunTools = async (props: DispatchToolModuleProps): Promise<
    toolWorkflowInteractiveResponse,
    dispatchFlowResponse, // tool flow response
    toolNodeTokens,
+    toolNodeInputTokens,
+    toolNodeOutputTokens,
    completeMessages = [], // The actual message sent to AI(just save text)
    assistantResponses = [], // FastGPT system store assistant.value response
    runTimes
@@ -225,7 +227,8 @@ export const dispatchRunTools = async (props: DispatchToolModuleProps): Promise<

  const { totalPoints, modelName } = formatModelChars2Points({
    model,
-    tokens: toolNodeTokens,
+    inputTokens: toolNodeInputTokens,
+    outputTokens: toolNodeOutputTokens,
    modelType: ModelTypeEnum.llm
  });
  const toolAIUsage = externalProvider.openaiAccount?.key ? 0 : totalPoints;
@@ -255,6 +258,8 @@ export const dispatchRunTools = async (props: DispatchToolModuleProps): Promise<
      // 展示的积分消耗
      totalPoints: totalPointsUsage,
      toolCallTokens: toolNodeTokens,
+      toolCallInputTokens: toolNodeInputTokens,
+      toolCallOutputTokens: toolNodeOutputTokens,
      childTotalPoints: flatUsages.reduce((sum, item) => sum + item.totalPoints, 0),
      model: modelName,
      query: userChatInput,
@@ -270,9 +275,10 @@ export const dispatchRunTools = async (props: DispatchToolModuleProps): Promise<
      // 工具调用本身的积分消耗
      {
        moduleName: name,
-        totalPoints: toolAIUsage,
        model: modelName,
-        tokens: toolNodeTokens
+        totalPoints: toolAIUsage,
+        inputTokens: toolNodeInputTokens,
+        outputTokens: toolNodeOutputTokens
      },
      // 工具的消耗
      ...flatUsages
--- a/packages/service/core/workflow/dispatch/agent/runTool/promptCall.ts
+++ b/packages/service/core/workflow/dispatch/agent/runTool/promptCall.ts
@@ -115,7 +115,8 @@ export const runToolWithPromptCall = async (

      return {
        dispatchFlowResponse: [toolRunResponse],
-        toolNodeTokens: 0,
+        toolNodeInputTokens: 0,
+        toolNodeOutputTokens: 0,
        completeMessages: concatMessages,
        assistantResponses: toolRunResponse.assistantResponses,
        runTimes: toolRunResponse.runTimes,
@@ -131,7 +132,8 @@ export const runToolWithPromptCall = async (
      },
      {
        dispatchFlowResponse: [toolRunResponse],
-        toolNodeTokens: 0,
+        toolNodeInputTokens: 0,
+        toolNodeOutputTokens: 0,
        assistantResponses: toolRunResponse.assistantResponses,
        runTimes: toolRunResponse.runTimes
      }
@@ -286,15 +288,20 @@ export const runToolWithPromptCall = async (
      content: replaceAnswer
    };
    const completeMessages = filterMessages.concat(gptAssistantResponse);
-    const tokens = await countGptMessagesTokens(completeMessages, undefined);
-    // console.log(tokens, 'response token');
+    const inputTokens = await countGptMessagesTokens(requestMessages);
+    const outputTokens = await countGptMessagesTokens([gptAssistantResponse]);

    // concat tool assistant
    const toolNodeAssistant = GPTMessages2Chats([gptAssistantResponse])[0] as AIChatItemType;

    return {
      dispatchFlowResponse: response?.dispatchFlowResponse || [],
-      toolNodeTokens: response?.toolNodeTokens ? response.toolNodeTokens + tokens : tokens,
+      toolNodeInputTokens: response?.toolNodeInputTokens
+        ? response.toolNodeInputTokens + inputTokens
+        : inputTokens,
+      toolNodeOutputTokens: response?.toolNodeOutputTokens
+        ? response.toolNodeOutputTokens + outputTokens
+        : outputTokens,
      completeMessages,
      assistantResponses: [...assistantResponses, ...toolNodeAssistant.value],
      runTimes: (response?.runTimes || 0) + 1
@@ -366,17 +373,9 @@ export const runToolWithPromptCall = async (
    function_call: toolJson
  };

-  /* 
-    ...
-    user
-    assistant: tool data
-  */
-  const concatToolMessages = [
-    ...requestMessages,
-    assistantToolMsgParams
-  ] as ChatCompletionMessageParam[];
  // Only toolCall tokens are counted here, Tool response tokens count towards the next reply
-  const tokens = await countGptMessagesTokens(concatToolMessages, undefined);
+  const inputTokens = await countGptMessagesTokens(requestMessages);
+  const outputTokens = await countGptMessagesTokens([assistantToolMsgParams]);

  /* 
    ...
@@ -437,7 +436,12 @@ ANSWER: `;
  }

  const runTimes = (response?.runTimes || 0) + toolsRunResponse.toolResponse.runTimes;
-  const toolNodeTokens = response?.toolNodeTokens ? response.toolNodeTokens + tokens : tokens;
+  const toolNodeInputTokens = response?.toolNodeInputTokens
+    ? response.toolNodeInputTokens + inputTokens
+    : inputTokens;
+  const toolNodeOutputTokens = response?.toolNodeOutputTokens
+    ? response.toolNodeOutputTokens + outputTokens
+    : outputTokens;

  // Check stop signal
  const hasStopSignal = toolsRunResponse.toolResponse.flowResponses.some((item) => !!item.toolStop);
@@ -460,7 +464,8 @@ ANSWER: `;

    return {
      dispatchFlowResponse,
-      toolNodeTokens,
+      toolNodeInputTokens,
+      toolNodeOutputTokens,
      completeMessages: filterMessages,
      assistantResponses: toolNodeAssistants,
      runTimes,
@@ -475,7 +480,8 @@ ANSWER: `;
    },
    {
      dispatchFlowResponse,
-      toolNodeTokens,
+      toolNodeInputTokens,
+      toolNodeOutputTokens,
      assistantResponses: toolNodeAssistants,
      runTimes
    }
--- a/packages/service/core/workflow/dispatch/agent/runTool/toolChoice.ts
+++ b/packages/service/core/workflow/dispatch/agent/runTool/toolChoice.ts
@@ -27,9 +27,10 @@ import { getNanoid, sliceStrStartEnd } from '@fastgpt/global/common/string/tools
 import { toolValueTypeList } from '@fastgpt/global/core/workflow/constants';
 import { WorkflowInteractiveResponseType } from '@fastgpt/global/core/workflow/template/system/interactive/type';
 import { ChatItemValueTypeEnum } from '@fastgpt/global/core/chat/constants';
+import { getErrText } from '@fastgpt/global/common/error/utils';

 type ToolRunResponseType = {
-  toolRunResponse: DispatchFlowResponse;
+  toolRunResponse?: DispatchFlowResponse;
  toolMsgParams: ChatCompletionToolMessageParam;
 }[];

@@ -158,7 +159,8 @@ export const runToolWithToolChoice = async (

      return {
        dispatchFlowResponse: [toolRunResponse],
-        toolNodeTokens: 0,
+        toolNodeInputTokens: 0,
+        toolNodeOutputTokens: 0,
        completeMessages: requestMessages,
        assistantResponses: toolRunResponse.assistantResponses,
        runTimes: toolRunResponse.runTimes,
@@ -176,7 +178,8 @@ export const runToolWithToolChoice = async (
      },
      {
        dispatchFlowResponse: [toolRunResponse],
-        toolNodeTokens: 0,
+        toolNodeInputTokens: 0,
+        toolNodeOutputTokens: 0,
        assistantResponses: toolRunResponse.assistantResponses,
        runTimes: toolRunResponse.runTimes
      }
@@ -342,59 +345,87 @@ export const runToolWithToolChoice = async (
    return Promise.reject(getEmptyResponseTip());
  }

-  // Run the selected tool by LLM.
-  const toolsRunResponse = (
-    await Promise.all(
-      toolCalls.map(async (tool) => {
-        const toolNode = toolNodes.find((item) => item.nodeId === tool.function?.name);
+  /* Run the selected tool by LLM.
+    Since only reference parameters are passed, if the same tool is run in parallel, it will get the same run parameters
+  */
+  const toolsRunResponse: ToolRunResponseType = [];
+  for await (const tool of toolCalls) {
+    try {
+      const toolNode = toolNodes.find((item) => item.nodeId === tool.function?.name);

-        if (!toolNode) return;
+      if (!toolNode) continue;

-        const startParams = (() => {
-          try {
-            return json5.parse(tool.function.arguments);
-          } catch (error) {
-            return {};
+      const startParams = (() => {
+        try {
+          return json5.parse(tool.function.arguments);
+        } catch (error) {
+          return {};
+        }
+      })();
+
+      initToolNodes(runtimeNodes, [toolNode.nodeId], startParams);
+      const toolRunResponse = await dispatchWorkFlow({
+        ...workflowProps,
+        isToolCall: true
+      });
+
+      const stringToolResponse = formatToolResponse(toolRunResponse.toolResponses);
+
+      const toolMsgParams: ChatCompletionToolMessageParam = {
+        tool_call_id: tool.id,
+        role: ChatCompletionRequestMessageRoleEnum.Tool,
+        name: tool.function.name,
+        content: stringToolResponse
+      };
+
+      workflowStreamResponse?.({
+        event: SseResponseEventEnum.toolResponse,
+        data: {
+          tool: {
+            id: tool.id,
+            toolName: '',
+            toolAvatar: '',
+            params: '',
+            response: sliceStrStartEnd(stringToolResponse, 5000, 5000)
          }
-        })();
+        }
+      });

-        initToolNodes(runtimeNodes, [toolNode.nodeId], startParams);
-        const toolRunResponse = await dispatchWorkFlow({
-          ...workflowProps,
-          isToolCall: true
-        });
+      toolsRunResponse.push({
+        toolRunResponse,
+        toolMsgParams
+      });
+    } catch (error) {
+      const err = getErrText(error);
+      workflowStreamResponse?.({
+        event: SseResponseEventEnum.toolResponse,
+        data: {
+          tool: {
+            id: tool.id,
+            toolName: '',
+            toolAvatar: '',
+            params: '',
+            response: sliceStrStartEnd(err, 5000, 5000)
+          }
+        }
+      });

-        const stringToolResponse = formatToolResponse(toolRunResponse.toolResponses);
-
-        const toolMsgParams: ChatCompletionToolMessageParam = {
+      toolsRunResponse.push({
+        toolRunResponse: undefined,
+        toolMsgParams: {
          tool_call_id: tool.id,
          role: ChatCompletionRequestMessageRoleEnum.Tool,
          name: tool.function.name,
-          content: stringToolResponse
-        };
+          content: sliceStrStartEnd(err, 5000, 5000)
+        }
+      });
+    }
+  }

-        workflowStreamResponse?.({
-          event: SseResponseEventEnum.toolResponse,
-          data: {
-            tool: {
-              id: tool.id,
-              toolName: '',
-              toolAvatar: '',
-              params: '',
-              response: sliceStrStartEnd(stringToolResponse, 5000, 5000)
-            }
-          }
-        });
-
-        return {
-          toolRunResponse,
-          toolMsgParams
-        };
-      })
-    )
-  ).filter(Boolean) as ToolRunResponseType;
-
-  const flatToolsResponseData = toolsRunResponse.map((item) => item.toolRunResponse).flat();
+  const flatToolsResponseData = toolsRunResponse
+    .map((item) => item.toolRunResponse)
+    .flat()
+    .filter(Boolean) as DispatchFlowResponse[];
  // concat tool responses
  const dispatchFlowResponse = response
    ? response.dispatchFlowResponse.concat(flatToolsResponseData)
@@ -428,24 +459,26 @@ export const runToolWithToolChoice = async (
    ] as ChatCompletionMessageParam[];

    // Only toolCall tokens are counted here, Tool response tokens count towards the next reply
-    const tokens = await countGptMessagesTokens(concatToolMessages, tools);
+    const inputTokens = await countGptMessagesTokens(requestMessages, tools);
+    const outputTokens = await countGptMessagesTokens(assistantToolMsgParams);
+
    /* 
-        ...
-        user
-        assistant: tool data
-        tool: tool response
-      */
+      ...
+      user
+      assistant: tool data
+      tool: tool response
+    */
    const completeMessages = [
      ...concatToolMessages,
      ...toolsRunResponse.map((item) => item?.toolMsgParams)
    ];

    /* 
-        Get tool node assistant response
-        history assistant
-        current tool assistant
-        tool child assistant
-      */
+      Get tool node assistant response
+      history assistant
+      current tool assistant
+      tool child assistant
+    */
    const toolNodeAssistant = GPTMessages2Chats([
      ...assistantToolMsgParams,
      ...toolsRunResponse.map((item) => item?.toolMsgParams)
@@ -463,7 +496,10 @@ export const runToolWithToolChoice = async (
    const runTimes =
      (response?.runTimes || 0) +
      flatToolsResponseData.reduce((sum, item) => sum + item.runTimes, 0);
-    const toolNodeTokens = response ? response.toolNodeTokens + tokens : tokens;
+    const toolNodeInputTokens = response ? response.toolNodeInputTokens + inputTokens : inputTokens;
+    const toolNodeOutputTokens = response
+      ? response.toolNodeOutputTokens + outputTokens
+      : outputTokens;

    // Check stop signal
    const hasStopSignal = flatToolsResponseData.some(
@@ -471,12 +507,12 @@ export const runToolWithToolChoice = async (
    );
    // Check interactive response(Only 1 interaction is reserved)
    const workflowInteractiveResponseItem = toolsRunResponse.find(
-      (item) => item.toolRunResponse.workflowInteractiveResponse
+      (item) => item.toolRunResponse?.workflowInteractiveResponse
    );
    if (hasStopSignal || workflowInteractiveResponseItem) {
      // Get interactive tool data
      const workflowInteractiveResponse =
-        workflowInteractiveResponseItem?.toolRunResponse.workflowInteractiveResponse;
+        workflowInteractiveResponseItem?.toolRunResponse?.workflowInteractiveResponse;

      // Flashback traverses completeMessages, intercepting messages that know the first user
      const firstUserIndex = completeMessages.findLastIndex((item) => item.role === 'user');
@@ -496,7 +532,8 @@ export const runToolWithToolChoice = async (

      return {
        dispatchFlowResponse,
-        toolNodeTokens,
+        toolNodeInputTokens,
+        toolNodeOutputTokens,
        completeMessages,
        assistantResponses: toolNodeAssistants,
        runTimes,
@@ -512,7 +549,8 @@ export const runToolWithToolChoice = async (
      },
      {
        dispatchFlowResponse,
-        toolNodeTokens,
+        toolNodeInputTokens,
+        toolNodeOutputTokens,
        assistantResponses: toolNodeAssistants,
        runTimes
      }
@@ -524,14 +562,17 @@ export const runToolWithToolChoice = async (
      content: answer
    };
    const completeMessages = filterMessages.concat(gptAssistantResponse);
-    const tokens = await countGptMessagesTokens(completeMessages, tools);
+    const inputTokens = await countGptMessagesTokens(requestMessages, tools);
+    const outputTokens = await countGptMessagesTokens([gptAssistantResponse]);

    // concat tool assistant
    const toolNodeAssistant = GPTMessages2Chats([gptAssistantResponse])[0] as AIChatItemType;

    return {
      dispatchFlowResponse: response?.dispatchFlowResponse || [],
-      toolNodeTokens: response ? response.toolNodeTokens + tokens : tokens,
+      toolNodeInputTokens: response ? response.toolNodeInputTokens + inputTokens : inputTokens,
+      toolNodeOutputTokens: response ? response.toolNodeOutputTokens + outputTokens : outputTokens,
+
      completeMessages,
      assistantResponses: [...assistantResponses, ...toolNodeAssistant.value],
      runTimes: (response?.runTimes || 0) + 1
@@ -578,7 +619,8 @@ async function streamResponse({
          text: content
        })
      });
-    } else if (responseChoice?.tool_calls?.[0]) {
+    }
+    if (responseChoice?.tool_calls?.[0]) {
      const toolCall: ChatCompletionMessageToolCall = responseChoice.tool_calls[0];
      // In a stream response, only one tool is returned at a time.  If have id, description is executing a tool
      if (toolCall.id || callingTool) {
--- a/packages/service/core/workflow/dispatch/agent/runTool/type.d.ts
+++ b/packages/service/core/workflow/dispatch/agent/runTool/type.d.ts
@@ -31,7 +31,9 @@ export type DispatchToolModuleProps = ModuleDispatchProps<{

 export type RunToolResponse = {
  dispatchFlowResponse: DispatchFlowResponse[];
-  toolNodeTokens: number;
+  toolNodeTokens?: number; // deprecated
+  toolNodeInputTokens: number;
+  toolNodeOutputTokens: number;
  completeMessages?: ChatCompletionMessageParam[];
  assistantResponses?: AIChatItemValueItemType[];
  toolWorkflowInteractiveResponse?: WorkflowInteractiveResponseType;
--- a/packages/service/core/workflow/dispatch/chat/oneapi.ts
+++ b/packages/service/core/workflow/dispatch/chat/oneapi.ts
@@ -5,13 +5,17 @@ import { ChatRoleEnum } from '@fastgpt/global/core/chat/constants';
 import { SseResponseEventEnum } from '@fastgpt/global/core/workflow/runtime/constants';
 import { textAdaptGptResponse } from '@fastgpt/global/core/workflow/runtime/utils';
 import { createChatCompletion } from '../../../ai/config';
-import type { ChatCompletion, StreamChatType } from '@fastgpt/global/core/ai/type.d';
+import type {
+  ChatCompletion,
+  ChatCompletionMessageParam,
+  StreamChatType
+} from '@fastgpt/global/core/ai/type.d';
 import { formatModelChars2Points } from '../../../../support/wallet/usage/utils';
 import type { LLMModelItemType } from '@fastgpt/global/core/ai/model.d';
 import { postTextCensor } from '../../../../common/api/requestPlusApi';
 import { ChatCompletionRequestMessageRoleEnum } from '@fastgpt/global/core/ai/constants';
 import type { DispatchNodeResultType } from '@fastgpt/global/core/workflow/runtime/type';
-import { countMessagesTokens } from '../../../../common/string/tiktoken/index';
+import { countGptMessagesTokens } from '../../../../common/string/tiktoken/index';
 import {
  chats2GPTMessages,
  chatValue2RuntimePrompt,
@@ -214,16 +218,23 @@ export const dispatchChatCompletion = async (props: ChatProps): Promise<ChatResp
    return Promise.reject(getEmptyResponseTip());
  }

-  const completeMessages = requestMessages.concat({
-    role: ChatCompletionRequestMessageRoleEnum.Assistant,
-    content: answerText
-  });
+  const AIMessages: ChatCompletionMessageParam[] = [
+    {
+      role: ChatCompletionRequestMessageRoleEnum.Assistant,
+      content: answerText
+    }
+  ];
+
+  const completeMessages = [...requestMessages, ...AIMessages];
  const chatCompleteMessages = GPTMessages2Chats(completeMessages);

-  const tokens = await countMessagesTokens(chatCompleteMessages);
+  const inputTokens = await countGptMessagesTokens(requestMessages);
+  const outputTokens = await countGptMessagesTokens(AIMessages);
+
  const { totalPoints, modelName } = formatModelChars2Points({
    model,
-    tokens,
+    inputTokens,
+    outputTokens,
    modelType: ModelTypeEnum.llm
  });

@@ -232,7 +243,9 @@ export const dispatchChatCompletion = async (props: ChatProps): Promise<ChatResp
    [DispatchNodeResponseKeyEnum.nodeResponse]: {
      totalPoints: externalProvider.openaiAccount?.key ? 0 : totalPoints,
      model: modelName,
-      tokens,
+      tokens: inputTokens + outputTokens,
+      inputTokens: inputTokens,
+      outputTokens: outputTokens,
      query: `${userChatInput}`,
      maxToken: max_tokens,
      historyPreview: getHistoryPreview(
@@ -247,7 +260,8 @@ export const dispatchChatCompletion = async (props: ChatProps): Promise<ChatResp
        moduleName: name,
        totalPoints: externalProvider.openaiAccount?.key ? 0 : totalPoints,
        model: modelName,
-        tokens
+        inputTokens: inputTokens,
+        outputTokens: outputTokens
      }
    ],
    [DispatchNodeResponseKeyEnum.toolResponses]: answerText,
--- a/packages/service/core/workflow/dispatch/dataset/search.ts
+++ b/packages/service/core/workflow/dispatch/dataset/search.ts
@@ -120,14 +120,14 @@ export async function dispatchDatasetSearch(
  // vector
  const { totalPoints, modelName } = formatModelChars2Points({
    model: vectorModel.model,
-    tokens,
+    inputTokens: tokens,
    modelType: ModelTypeEnum.vector
  });
  const responseData: DispatchNodeResponseType & { totalPoints: number } = {
    totalPoints,
    query: concatQueries.join('\n'),
    model: modelName,
-    tokens,
+    inputTokens: tokens,
    similarity: usingSimilarityFilter ? similarity : undefined,
    limit,
    searchMode,
@@ -139,19 +139,21 @@ export async function dispatchDatasetSearch(
      totalPoints,
      moduleName: node.name,
      model: modelName,
-      tokens
+      inputTokens: tokens
    }
  ];

  if (aiExtensionResult) {
    const { totalPoints, modelName } = formatModelChars2Points({
      model: aiExtensionResult.model,
-      tokens: aiExtensionResult.tokens,
+      inputTokens: aiExtensionResult.inputTokens,
+      outputTokens: aiExtensionResult.outputTokens,
      modelType: ModelTypeEnum.llm
    });

    responseData.totalPoints += totalPoints;
-    responseData.tokens = aiExtensionResult.tokens;
+    responseData.inputTokens = aiExtensionResult.inputTokens;
+    responseData.outputTokens = aiExtensionResult.outputTokens;
    responseData.extensionModel = modelName;
    responseData.extensionResult =
      aiExtensionResult.extensionQueries?.join('\n') ||
@@ -161,7 +163,8 @@ export async function dispatchDatasetSearch(
      totalPoints,
      moduleName: 'core.module.template.Query extension',
      model: modelName,
-      tokens: aiExtensionResult.tokens
+      inputTokens: aiExtensionResult.inputTokens,
+      outputTokens: aiExtensionResult.outputTokens
    });
  }

--- a/packages/service/core/workflow/dispatch/index.ts
+++ b/packages/service/core/workflow/dispatch/index.ts
@@ -72,6 +72,7 @@ import { dispatchLoopEnd } from './loop/runLoopEnd';
 import { dispatchLoopStart } from './loop/runLoopStart';
 import { dispatchFormInput } from './interactive/formInput';
 import { dispatchToolParams } from './agent/runTool/toolParams';
+import { getErrText } from '@fastgpt/global/common/error/utils';

 const callbackMap: Record<FlowNodeTypeEnum, Function> = {
  [FlowNodeTypeEnum.workflowStart]: dispatchWorkflowStart,
@@ -231,9 +232,7 @@ export async function dispatchWorkFlow(data: Props): Promise<DispatchFlowRespons

    if (toolResponses !== undefined) {
      if (Array.isArray(toolResponses) && toolResponses.length === 0) return;
-      if (typeof toolResponses === 'object' && Object.keys(toolResponses).length === 0) {
-        return;
-      }
+      if (typeof toolResponses === 'object' && Object.keys(toolResponses).length === 0) return;
      toolRunResponse = toolResponses;
    }

@@ -565,6 +564,8 @@ export async function dispatchWorkFlow(data: Props): Promise<DispatchFlowRespons
          const targetEdges = runtimeEdges.filter((item) => item.source === node.nodeId);
          const skipHandleIds = targetEdges.map((item) => item.sourceHandle);

+          toolRunResponse = getErrText(error);
+
          // Skip all edges and return error
          return {
            [DispatchNodeResponseKeyEnum.nodeResponse]: {
--- a/packages/service/core/workflow/dispatch/plugin/run.ts
+++ b/packages/service/core/workflow/dispatch/plugin/run.ts
@@ -130,8 +130,7 @@ export const dispatchRunPlugin = async (props: RunPluginProps): Promise<RunPlugi
    [DispatchNodeResponseKeyEnum.nodeDispatchUsages]: [
      {
        moduleName: plugin.name,
-        totalPoints: usagePoints,
-        tokens: 0
+        totalPoints: usagePoints
      }
    ],
    [DispatchNodeResponseKeyEnum.toolResponses]: output?.pluginOutput
--- a/packages/service/core/workflow/dispatch/plugin/runApp.ts
+++ b/packages/service/core/workflow/dispatch/plugin/runApp.ts
@@ -153,8 +153,7 @@ export const dispatchRunAppNode = async (props: Props): Promise<Response> => {
    [DispatchNodeResponseKeyEnum.nodeDispatchUsages]: [
      {
        moduleName: appData.name,
-        totalPoints: usagePoints,
-        tokens: 0
+        totalPoints: usagePoints
      }
    ],
    [DispatchNodeResponseKeyEnum.toolResponses]: text,
--- a/packages/service/core/workflow/dispatch/tools/http468.ts
+++ b/packages/service/core/workflow/dispatch/tools/http468.ts
@@ -177,17 +177,17 @@ export const dispatchHttp468Request = async (props: HttpRequestProps): Promise<H
      if (!httpJsonBody) return {};
      if (httpContentType === ContentTypes.json) {
        httpJsonBody = replaceStringVariables(httpJsonBody);
+
+        const replaceJsonBody = httpJsonBody.replace(/(".*?")\s*:\s*undefined\b/g, '$1: null');
+
        // Json body, parse and return
-        const jsonParse = json5.parse(
-          httpJsonBody.replace(/(".*?")\s*:\s*undefined\b/g, '$1: null')
-        );
+        const jsonParse = json5.parse(replaceJsonBody);
        const removeSignJson = removeUndefinedSign(jsonParse);
        return removeSignJson;
      }
      httpJsonBody = replaceStringVariables(httpJsonBody);
      return httpJsonBody.replaceAll(UNDEFINED_SIGN, 'null');
    } catch (error) {
-      console.log(error);
      return Promise.reject(`Invalid JSON body: ${httpJsonBody}`);
    }
  })();
--- a/packages/service/core/workflow/dispatch/tools/queryExternsion.ts
+++ b/packages/service/core/workflow/dispatch/tools/queryExternsion.ts
@@ -31,7 +31,7 @@ export const dispatchQueryExtension = async ({
  const queryExtensionModel = getLLMModel(model);
  const chatHistories = getHistories(history, histories);

-  const { extensionQueries, tokens } = await queryExtension({
+  const { extensionQueries, inputTokens, outputTokens } = await queryExtension({
    chatBg: systemPrompt,
    query: userChatInput,
    histories: chatHistories,
@@ -42,7 +42,8 @@ export const dispatchQueryExtension = async ({

  const { totalPoints, modelName } = formatModelChars2Points({
    model: queryExtensionModel.model,
-    tokens,
+    inputTokens,
+    outputTokens,
    modelType: ModelTypeEnum.llm
  });

@@ -59,7 +60,8 @@ export const dispatchQueryExtension = async ({
    [DispatchNodeResponseKeyEnum.nodeResponse]: {
      totalPoints,
      model: modelName,
-      tokens,
+      inputTokens,
+      outputTokens,
      query: userChatInput,
      textOutput: JSON.stringify(filterSameQueries)
    },
@@ -68,7 +70,8 @@ export const dispatchQueryExtension = async ({
        moduleName: node.name,
        totalPoints,
        model: modelName,
-        tokens
+        inputTokens,
+        outputTokens
      }
    ],
    [NodeOutputKeyEnum.text]: JSON.stringify(filterSameQueries)
--- a/packages/service/support/outLink/schema.ts
+++ b/packages/service/support/outLink/schema.ts
@@ -92,6 +92,7 @@ OutLinkSchema.virtual('associatedApp', {

 try {
  OutLinkSchema.index({ shareId: -1 });
+  OutLinkSchema.index({ teamId: 1, tmbId: 1, appId: 1 });
 } catch (error) {
  console.log(error);
 }
--- a/packages/service/support/permission/auth/org.ts
+++ b/packages/service/support/permission/auth/org.ts
@@ -0,0 +1,43 @@
+import { TeamPermission } from '@fastgpt/global/support/permission/user/controller';
+import { AuthModeType, AuthResponseType } from '../type';
+import { TeamErrEnum } from '@fastgpt/global/common/error/code/team';
+import { authUserPer } from '../user/auth';
+import { ManagePermissionVal } from '@fastgpt/global/support/permission/constant';
+
+/* 
+  Team manager can control org
+*/
+export const authOrgMember = async ({
+  orgIds,
+  ...props
+}: {
+  orgIds: string | string[];
+} & AuthModeType): Promise<AuthResponseType> => {
+  const result = await authUserPer({
+    ...props,
+    per: ManagePermissionVal
+  });
+  const { teamId, tmbId, isRoot, tmb } = result;
+
+  if (isRoot) {
+    return {
+      teamId,
+      tmbId,
+      userId: result.userId,
+      appId: result.appId,
+      apikey: result.apikey,
+      isRoot,
+      authType: result.authType,
+      permission: new TeamPermission({ isOwner: true })
+    };
+  }
+
+  if (tmb.permission.hasManagePer) {
+    return {
+      ...result,
+      permission: tmb.permission
+    };
+  }
+
+  return Promise.reject(TeamErrEnum.unAuthTeam);
+};
--- a/packages/service/support/permission/auth/team.ts
+++ b/packages/service/support/permission/auth/team.ts
@@ -18,7 +18,7 @@ export async function getUserChatInfoAndAuthTeamPoints(tmbId: string) {
    ])
    .lean();

-  if (!tmb) return Promise.reject(UserErrEnum.unAuthUser);
+  if (!tmb) return Promise.reject(UserErrEnum.binVisitor);

  await checkTeamAIPoints(tmb.team._id);

--- a/packages/service/support/permission/controller.ts
+++ b/packages/service/support/permission/controller.ts
@@ -8,10 +8,7 @@ import { authOpenApiKey } from '../openapi/auth';
 import { FileTokenQuery } from '@fastgpt/global/common/file/type';
 import { MongoResourcePermission } from './schema';
 import { ClientSession } from 'mongoose';
-import {
-  PermissionValueType,
-  ResourcePermissionType
-} from '@fastgpt/global/support/permission/type';
+import { PermissionValueType } from '@fastgpt/global/support/permission/type';
 import { bucketNameMap } from '@fastgpt/global/common/file/constants';
 import { addMinutes } from 'date-fns';
 import { getGroupsByTmbId } from './memberGroup/controllers';
@@ -21,6 +18,8 @@ import { CommonErrEnum } from '@fastgpt/global/common/error/code/common';
 import { MemberGroupSchemaType } from '@fastgpt/global/support/permission/memberGroup/type';
 import { TeamMemberSchema } from '@fastgpt/global/support/user/team/type';
 import { UserModelSchema } from '@fastgpt/global/support/user/type';
+import { OrgSchemaType } from '@fastgpt/global/support/user/team/org/type';
+import { getOrgIdSetWithParentByTmbId } from './org/controllers';

 /** get resource permission for a team member
 * If there is no permission for the team member, it will return undefined
@@ -67,67 +66,44 @@ export const getResourcePermission = async ({
  }

  // If there is no personal permission, get the group permission
-  const groupIdList = (await getGroupsByTmbId({ tmbId, teamId })).map((item) => item._id);
+  const [groupPers, orgPers] = await Promise.all([
+    getGroupsByTmbId({ tmbId, teamId })
+      .then((res) => res.map((item) => item._id))
+      .then((groupIdList) =>
+        MongoResourcePermission.find(
+          {
+            teamId,
+            resourceType,
+            groupId: {
+              $in: groupIdList
+            },
+            resourceId
+          },
+          'permission'
+        ).lean()
+      )
+      .then((perList) => perList.map((item) => item.permission)),
+    getOrgIdSetWithParentByTmbId({ tmbId, teamId })
+      .then((item) => Array.from(item))
+      .then((orgIds) =>
+        MongoResourcePermission.find(
+          {
+            teamId,
+            resourceType,
+            orgId: {
+              $in: Array.from(orgIds)
+            },
+            resourceId
+          },
+          'permission'
+        ).lean()
+      )
+      .then((perList) => perList.map((item) => item.permission))
+  ]);

-  if (groupIdList.length === 0) {
-    return undefined;
-  }
-
-  // get the maximum permission of the group
-  const pers = (
-    await MongoResourcePermission.find(
-      {
-        teamId,
-        resourceType,
-        groupId: {
-          $in: groupIdList
-        },
-        resourceId
-      },
-      'permission'
-    ).lean()
-  ).map((item) => item.permission);
-
-  const groupPer = getGroupPer(pers);
-
-  return groupPer;
+  return concatPer([...groupPers, ...orgPers]);
 };

-/* 仅取 members 不取 groups */
-export async function getResourceAllClbs({
-  resourceId,
-  teamId,
-  resourceType,
-  session
-}: {
-  teamId: string;
-  session?: ClientSession;
-} & (
-  | {
-      resourceType: 'team';
-      resourceId?: undefined;
-    }
-  | {
-      resourceType: Omit<PerResourceTypeEnum, 'team'>;
-      resourceId?: string | null;
-    }
-)): Promise<ResourcePermissionType[]> {
-  return MongoResourcePermission.find(
-    {
-      resourceType: resourceType,
-      teamId: teamId,
-      resourceId,
-      groupId: {
-        $exists: false
-      }
-    },
-    null,
-    {
-      session
-    }
-  ).lean();
-}
-
 export async function getResourceClbsAndGroups({
  resourceId,
  resourceType,
@@ -155,10 +131,17 @@ export const getClbsAndGroupsWithInfo = async ({
  resourceType,
  teamId
 }: {
-  resourceId: ParentIdType;
-  resourceType: Omit<`${PerResourceTypeEnum}`, 'team'>;
  teamId: string;
-}) =>
+} & (
+  | {
+      resourceId: ParentIdType;
+      resourceType: Omit<`${PerResourceTypeEnum}`, 'team'>;
+    }
+  | {
+      resourceType: 'team';
+      resourceId?: undefined;
+    }
+)) =>
  Promise.all([
    MongoResourcePermission.find({
      teamId,
@@ -170,7 +153,7 @@ export const getClbsAndGroupsWithInfo = async ({
    })
      .populate<{ tmb: TeamMemberSchema & { user: UserModelSchema } }>({
        path: 'tmb',
-        select: 'name userId',
+        select: 'name userId role',
        populate: {
          path: 'user',
          select: 'avatar'
@@ -186,6 +169,16 @@ export const getClbsAndGroupsWithInfo = async ({
      }
    })
      .populate<{ group: MemberGroupSchemaType }>('group', 'name avatar')
+      .lean(),
+    MongoResourcePermission.find({
+      teamId,
+      resourceId,
+      resourceType,
+      orgId: {
+        $exists: true
+      }
+    })
+      .populate<{ org: OrgSchemaType }>({ path: 'org', select: 'name avatar' })
      .lean()
  ]);

@@ -196,6 +189,7 @@ export const delResourcePermission = ({
  session,
  tmbId,
  groupId,
+  orgId,
  ...props
 }: {
  resourceType: PerResourceTypeEnum;
@@ -204,15 +198,18 @@ export const delResourcePermission = ({
  session?: ClientSession;
  tmbId?: string;
  groupId?: string;
+  orgId?: string;
 }) => {
-  // tmbId or groupId only one and not both
-  if (!!tmbId === !!groupId) {
+  // either tmbId or groupId or orgId must be provided
+  if (!tmbId && !groupId && !orgId) {
    return Promise.reject(CommonErrEnum.missingParams);
  }
+
  return MongoResourcePermission.deleteOne(
    {
      ...(tmbId ? { tmbId } : {}),
      ...(groupId ? { groupId } : {}),
+      ...(orgId ? { orgId } : {}),
      ...props
    },
    { session }
@@ -250,7 +247,7 @@ export function authJWT(token: string) {
  }>((resolve, reject) => {
    const key = process.env.TOKEN_KEY as string;

-    jwt.verify(token, key, function (err, decoded: any) {
+    jwt.verify(token, key, (err, decoded: any) => {
      if (err || !decoded?.userId) {
        reject(ERROR_ENUM.unAuthorization);
        return;
@@ -436,7 +433,7 @@ export const authFileToken = (token?: string) =>
    }
    const key = (process.env.FILE_TOKEN_KEY as string) ?? 'filetoken';

-    jwt.verify(token, key, function (err, decoded: any) {
+    jwt.verify(token, key, (err, decoded: any) => {
      if (err || !decoded.bucketName || !decoded?.teamId || !decoded?.fileId) {
        reject(ERROR_ENUM.unAuthFile);
        return;
@@ -450,10 +447,10 @@ export const authFileToken = (token?: string) =>
    });
  });

-export const getGroupPer = (groups: PermissionValueType[] = []) => {
-  if (groups.length === 0) {
+export const concatPer = (perList: PermissionValueType[] = []) => {
+  if (perList.length === 0) {
    return undefined;
  }

-  return new Permission().addPer(...groups).value;
+  return new Permission().addPer(...perList).value;
 };
--- a/packages/service/support/permission/inheritPermission.ts
+++ b/packages/service/support/permission/inheritPermission.ts
@@ -1,11 +1,11 @@
 import { mongoSessionRun } from '../../common/mongo/sessionRun';
 import { MongoResourcePermission } from './schema';
-import { ClientSession, Model } from 'mongoose';
-import { PerResourceTypeEnum } from '@fastgpt/global/support/permission/constant';
-import { PermissionValueType } from '@fastgpt/global/support/permission/type';
+import type { ClientSession, Model } from 'mongoose';
+import type { PerResourceTypeEnum } from '@fastgpt/global/support/permission/constant';
+import type { PermissionValueType } from '@fastgpt/global/support/permission/type';
 import { getResourceClbsAndGroups } from './controller';
-import { RequireOnlyOne } from '@fastgpt/global/common/type/utils';
-import { ParentIdType } from '@fastgpt/global/common/parentFolder/type';
+import type { RequireOnlyOne } from '@fastgpt/global/common/type/utils';
+import type { ParentIdType } from '@fastgpt/global/common/parentFolder/type';

 export type SyncChildrenPermissionResourceType = {
  _id: string;
@@ -18,6 +18,7 @@ export type UpdateCollaboratorItem = {
 } & RequireOnlyOne<{
  tmbId: string;
  groupId: string;
+  orgId: string;
 }>;

 // sync the permission to all children folders.
@@ -161,7 +162,7 @@ export async function resumeInheritPermission({
  }
 }

-/* 
+/*
  Delete all the collaborators and then insert the new collaborators.
 */
 export async function syncCollaborators({
--- a/packages/service/support/permission/memberGroup/controllers.ts
+++ b/packages/service/support/permission/memberGroup/controllers.ts
@@ -1,9 +1,6 @@
 import { MemberGroupSchemaType } from '@fastgpt/global/support/permission/memberGroup/type';
 import { MongoGroupMemberModel } from './groupMemberSchema';
-import { TeamMemberSchema } from '@fastgpt/global/support/user/team/type';
-import { PerResourceTypeEnum } from '@fastgpt/global/support/permission/constant';
-import { MongoResourcePermission } from '../schema';
-import { getGroupPer, parseHeaderCert } from '../controller';
+import { parseHeaderCert } from '../controller';
 import { MongoMemberGroupModel } from './memberGroupSchema';
 import { DefaultGroupName } from '@fastgpt/global/support/user/team/group/constant';
 import { ClientSession } from 'mongoose';
@@ -50,26 +47,32 @@ export const getTeamDefaultGroup = async ({
 export const getGroupsByTmbId = async ({
  tmbId,
  teamId,
-  role
+  role,
+  session
 }: {
  tmbId: string;
  teamId: string;
  role?: `${GroupMemberRole}`[];
+  session?: ClientSession;
 }) =>
  (
    await Promise.all([
      (
-        await MongoGroupMemberModel.find({
-          tmbId,
-          groupId: {
-            $exists: true
+        await MongoGroupMemberModel.find(
+          {
+            tmbId,
+            groupId: {
+              $exists: true
+            },
+            ...(role ? { role: { $in: role } } : {})
          },
-          ...(role ? { role: { $in: role } } : {})
-        })
+          undefined,
+          { session }
+        )
          .populate<{ group: MemberGroupSchemaType }>('group')
          .lean()
      ).map((item) => item.group),
-      role ? [] : getTeamDefaultGroup({ teamId })
+      role ? [] : getTeamDefaultGroup({ teamId, session })
    ])
  ).flat();

@@ -79,46 +82,6 @@ export const getGroupMembersByGroupId = async (groupId: string) => {
  }).lean();
 };

-/**
- * Get tmb's group permission: the maximum permission of the group
- * @param tmbId
- * @param resourceId
- * @param resourceType
- * @returns the maximum permission of the group
- */
-export const getGroupPermission = async ({
-  tmbId,
-  resourceId,
-  teamId,
-  resourceType
-}: {
-  tmbId: string;
-  teamId: string;
-} & (
-  | {
-      resourceId?: undefined;
-      resourceType: 'team';
-    }
-  | {
-      resourceId: string;
-      resourceType: Omit<PerResourceTypeEnum, 'team'>;
-    }
-)) => {
-  const groupIds = (await getGroupsByTmbId({ tmbId, teamId })).map((item) => item._id);
-  const groupPermissions = (
-    await MongoResourcePermission.find({
-      groupId: {
-        $in: groupIds
-      },
-      resourceType,
-      resourceId,
-      teamId
-    })
-  ).map((item) => item.permission);
-
-  return getGroupPer(groupPermissions);
-};
-
 // auth group member role
 export const authGroupMemberRole = async ({
  groupId,
@@ -140,8 +103,12 @@ export const authGroupMemberRole = async ({
      tmbId
    };
  }
-  const groupMember = await MongoGroupMemberModel.findOne({ groupId, tmbId });
-  const tmb = await getTmbInfoByTmbId({ tmbId });
+  const [groupMember, tmb] = await Promise.all([
+    MongoGroupMemberModel.findOne({ groupId, tmbId }),
+    getTmbInfoByTmbId({ tmbId })
+  ]);
+
+  // Team admin or role check
  if (tmb.permission.hasManagePer || (groupMember && role.includes(groupMember.role))) {
    return {
      ...result,
--- a/packages/service/support/permission/org/controllers.ts
+++ b/packages/service/support/permission/org/controllers.ts
@@ -0,0 +1,95 @@
+import { TeamErrEnum } from '@fastgpt/global/common/error/code/team';
+import type { OrgSchemaType } from '@fastgpt/global/support/user/team/org/type';
+import type { ClientSession } from 'mongoose';
+import { MongoOrgModel } from './orgSchema';
+import { MongoOrgMemberModel } from './orgMemberSchema';
+import { getOrgChildrenPath } from '@fastgpt/global/support/user/team/org/constant';
+
+export const getOrgsByTmbId = async ({ teamId, tmbId }: { teamId: string; tmbId: string }) =>
+  MongoOrgMemberModel.find({ teamId, tmbId }, 'orgId').lean();
+
+export const getOrgIdSetWithParentByTmbId = async ({
+  teamId,
+  tmbId
+}: {
+  teamId: string;
+  tmbId: string;
+}) => {
+  const orgMembers = await MongoOrgMemberModel.find({ teamId, tmbId }, 'orgId').lean();
+
+  const orgIds = Array.from(new Set(orgMembers.map((item) => String(item.orgId))));
+  const orgs = await MongoOrgModel.find({ _id: { $in: orgIds } }, 'path').lean();
+
+  const pathIdList = new Set<string>(
+    orgs
+      .map((org) => {
+        const pathIdList = org.path.split('/').filter(Boolean);
+        return pathIdList;
+      })
+      .flat()
+  );
+  const parentOrgs = await MongoOrgModel.find(
+    {
+      teamId,
+      pathId: { $in: Array.from(pathIdList) }
+    },
+    '_id'
+  ).lean();
+  const parentOrgIds = parentOrgs.map((item) => String(item._id));
+
+  return new Set([...orgIds, ...parentOrgIds]);
+};
+
+export const getChildrenByOrg = async ({
+  org,
+  teamId,
+  session
+}: {
+  org: OrgSchemaType;
+  teamId: string;
+  session?: ClientSession;
+}) => {
+  return MongoOrgModel.find(
+    { teamId, path: { $regex: `^${getOrgChildrenPath(org)}` } },
+    undefined,
+    {
+      session
+    }
+  ).lean();
+};
+
+export const getOrgAndChildren = async ({
+  orgId,
+  teamId,
+  session
+}: {
+  orgId: string;
+  teamId: string;
+  session?: ClientSession;
+}) => {
+  const org = await MongoOrgModel.findOne({ _id: orgId, teamId }, undefined, { session }).lean();
+  if (!org) {
+    return Promise.reject(TeamErrEnum.orgNotExist);
+  }
+  const children = await getChildrenByOrg({ org, teamId, session });
+  return { org, children };
+};
+
+export async function createRootOrg({
+  teamId,
+  session
+}: {
+  teamId: string;
+  session?: ClientSession;
+}) {
+  return MongoOrgModel.create(
+    [
+      {
+        teamId,
+        name: 'ROOT',
+        path: ''
+      }
+    ],
+    { session }
+  );
+}
--- a/packages/service/support/permission/org/orgMemberSchema.ts
+++ b/packages/service/support/permission/org/orgMemberSchema.ts
@@ -0,0 +1,65 @@
+import { OrgCollectionName } from '@fastgpt/global/support/user/team/org/constant';
+import { connectionMongo, getMongoModel } from '../../../common/mongo';
+import {
+  TeamCollectionName,
+  TeamMemberCollectionName
+} from '@fastgpt/global/support/user/team/constant';
+import { OrgMemberSchemaType } from '@fastgpt/global/support/user/team/org/type';
+const { Schema } = connectionMongo;
+
+export const OrgMemberCollectionName = 'team_org_members';
+
+export const OrgMemberSchema = new Schema({
+  teamId: {
+    type: Schema.Types.ObjectId,
+    ref: TeamCollectionName,
+    required: true
+  },
+  orgId: {
+    type: Schema.Types.ObjectId,
+    ref: OrgCollectionName,
+    required: true
+  },
+  tmbId: {
+    type: Schema.Types.ObjectId,
+    ref: TeamMemberCollectionName,
+    required: true
+  }
+  // role: {
+  //   type: String,
+  //   enum: Object.values(OrgMemberRole),
+  //   required: true,
+  //   default: OrgMemberRole.member
+  // }
+});
+
+OrgMemberSchema.virtual('org', {
+  ref: OrgCollectionName,
+  localField: 'orgId',
+  foreignField: '_id',
+  justOne: true
+});
+
+try {
+  OrgMemberSchema.index(
+    {
+      teamId: 1,
+      orgId: 1,
+      tmbId: 1
+    },
+    {
+      unique: true
+    }
+  );
+  OrgMemberSchema.index({
+    teamId: 1,
+    tmbId: 1
+  });
+} catch (error) {
+  console.log(error);
+}
+
+export const MongoOrgMemberModel = getMongoModel<OrgMemberSchemaType>(
+  OrgMemberCollectionName,
+  OrgMemberSchema
+);
--- a/packages/service/support/permission/org/orgSchema.ts
+++ b/packages/service/support/permission/org/orgSchema.ts
@@ -0,0 +1,77 @@
+import { TeamCollectionName } from '@fastgpt/global/support/user/team/constant';
+import { OrgCollectionName } from '@fastgpt/global/support/user/team/org/constant';
+import type { OrgSchemaType } from '@fastgpt/global/support/user/team/org/type';
+import { connectionMongo, getMongoModel } from '../../../common/mongo';
+import { OrgMemberCollectionName } from './orgMemberSchema';
+import { getNanoid } from '@fastgpt/global/common/string/tools';
+const { Schema } = connectionMongo;
+
+export const OrgSchema = new Schema(
+  {
+    teamId: {
+      type: Schema.Types.ObjectId,
+      ref: TeamCollectionName,
+      required: true
+    },
+    pathId: {
+      // path id, only used for path
+      type: String,
+      required: true,
+      default: () => getNanoid()
+    },
+    path: {
+      type: String,
+      required: function (this: OrgSchemaType) {
+        return typeof this.path !== 'string';
+      } // allow empty string, but not null
+    },
+    name: {
+      type: String,
+      required: true
+    },
+    avatar: String,
+    description: String,
+    updateTime: {
+      type: Date,
+      default: () => new Date()
+    }
+  },
+  {
+    // Auto update updateTime
+    timestamps: {
+      updatedAt: 'updateTime'
+    }
+  }
+);
+
+OrgSchema.virtual('members', {
+  ref: OrgMemberCollectionName,
+  localField: '_id',
+  foreignField: 'orgId'
+});
+// OrgSchema.virtual('permission', {
+//   ref: ResourcePermissionCollectionName,
+//   localField: '_id',
+//   foreignField: 'orgId',
+//   justOne: true
+// });
+
+try {
+  OrgSchema.index({
+    teamId: 1,
+    path: 1
+  });
+  OrgSchema.index(
+    {
+      teamId: 1,
+      pathId: 1
+    },
+    {
+      unique: true
+    }
+  );
+} catch (error) {
+  console.log(error);
+}
+
+export const MongoOrgModel = getMongoModel<OrgSchemaType>(OrgCollectionName, OrgSchema);
--- a/packages/service/support/permission/schema.ts
+++ b/packages/service/support/permission/schema.ts
@@ -6,6 +6,7 @@ import { connectionMongo, getMongoModel } from '../../common/mongo';
 import type { ResourcePermissionType } from '@fastgpt/global/support/permission/type';
 import { PerResourceTypeEnum } from '@fastgpt/global/support/permission/constant';
 import { MemberGroupCollectionName } from './memberGroup/memberGroupSchema';
+import { OrgCollectionName } from '@fastgpt/global/support/user/team/org/constant';
 const { Schema } = connectionMongo;

 export const ResourcePermissionCollectionName = 'resource_permissions';
@@ -23,6 +24,10 @@ export const ResourcePermissionSchema = new Schema({
    type: Schema.Types.ObjectId,
    ref: MemberGroupCollectionName
  },
+  orgId: {
+    type: Schema.Types.ObjectId,
+    ref: OrgCollectionName
+  },
  resourceType: {
    type: String,
    enum: Object.values(PerResourceTypeEnum),
@@ -51,6 +56,12 @@ ResourcePermissionSchema.virtual('group', {
  foreignField: '_id',
  justOne: true
 });
+ResourcePermissionSchema.virtual('org', {
+  ref: OrgCollectionName,
+  localField: 'orgId',
+  foreignField: '_id',
+  justOne: true
+});

 try {
  ResourcePermissionSchema.index(
@@ -70,6 +81,23 @@ try {
    }
  );

+  ResourcePermissionSchema.index(
+    {
+      resourceType: 1,
+      teamId: 1,
+      resourceId: 1,
+      orgId: 1
+    },
+    {
+      unique: true,
+      partialFilterExpression: {
+        orgId: {
+          $exists: true
+        }
+      }
+    }
+  );
+
  ResourcePermissionSchema.index(
    {
      resourceType: 1,
@@ -87,6 +115,7 @@ try {
    }
  );

+  // Delete tmb permission
  ResourcePermissionSchema.index({
    resourceType: 1,
    teamId: 1,
--- a/packages/service/support/permission/teamLimit.ts
+++ b/packages/service/support/permission/teamLimit.ts
@@ -19,9 +19,7 @@ export const checkDatasetLimit = async ({
  if (!standardConstants) return;

  if (usedDatasetSize + insertLen >= datasetMaxSize) {
-    return Promise.reject(
-      `您的知识库容量为: ${datasetMaxSize}组，已使用: ${usedDatasetSize}组，导入当前文件需要: ${insertLen}组，请增加知识库容量后导入。`
-    );
+    return Promise.reject(TeamErrEnum.datasetSizeNotEnough);
  }

  if (usedPoints >= totalPoints) {
--- a/packages/service/support/user/schema.ts
+++ b/packages/service/support/user/schema.ts
@@ -3,22 +3,10 @@ const { Schema } = connectionMongo;
 import { hashStr } from '@fastgpt/global/common/string/tools';
 import type { UserModelSchema } from '@fastgpt/global/support/user/type';
 import { UserStatusEnum, userStatusMap } from '@fastgpt/global/support/user/constant';
+import { getRandomUserAvatar } from '@fastgpt/global/support/user/utils';

 export const userCollectionName = 'users';

-const defaultAvatars = [
-  '/imgs/avatar/RoyalBlueAvatar.svg',
-  '/imgs/avatar/PurpleAvatar.svg',
-  '/imgs/avatar/AdoraAvatar.svg',
-  '/imgs/avatar/OrangeAvatar.svg',
-  '/imgs/avatar/RedAvatar.svg',
-  '/imgs/avatar/GrayModernAvatar.svg',
-  '/imgs/avatar/TealAvatar.svg',
-  '/imgs/avatar/GreenAvatar.svg',
-  '/imgs/avatar/BrightBlueAvatar.svg',
-  '/imgs/avatar/BlueAvatar.svg'
-];
-
 const UserSchema = new Schema({
  status: {
    type: String,
@@ -47,7 +35,7 @@ const UserSchema = new Schema({
  },
  avatar: {
    type: String,
-    default: defaultAvatars[Math.floor(Math.random() * defaultAvatars.length)]
+    default: () => getRandomUserAvatar()
  },

  promotionRate: {
@@ -78,11 +66,8 @@ const UserSchema = new Schema({
 });

 try {
-  // login
-  UserSchema.index({ username: 1, password: 1 }, { background: true });
-
  // Admin charts
-  UserSchema.index({ createTime: -1 }, { background: true });
+  UserSchema.index({ createTime: -1 });
 } catch (error) {
  console.log(error);
 }
--- a/packages/service/support/user/team/controller.ts
+++ b/packages/service/support/user/team/controller.ts
@@ -16,6 +16,8 @@ import { MongoMemberGroupModel } from '../../permission/memberGroup/memberGroupS
 import { mongoSessionRun } from '../../../common/mongo/sessionRun';
 import { DefaultGroupName } from '@fastgpt/global/support/user/team/group/constant';
 import { getAIApi, openaiBaseUrl } from '../../../core/ai/config';
+import { createRootOrg } from '../../permission/org/controllers';
+import { refreshSourceAvatar } from '../../../common/file/image/controller';

 async function getTeamMember(match: Record<string, any>): Promise<TeamTmbItemType> {
  const tmb = await MongoTeamMember.findOne(match).populate<{ team: TeamSchema }>('team').lean();
@@ -32,6 +34,7 @@ async function getTeamMember(match: Record<string, any>): Promise<TeamTmbItemTyp
  return {
    userId: String(tmb.userId),
    teamId: String(tmb.teamId),
+    teamAvatar: tmb.team.avatar,
    teamName: tmb.team.name,
    memberName: tmb.name,
    avatar: tmb.team.avatar,
@@ -77,13 +80,11 @@ export async function createDefaultTeam({
  userId,
  teamName = 'My Team',
  avatar = '/icon/logo.svg',
-  balance,
  session
 }: {
  userId: string;
  teamName?: string;
  avatar?: string;
-  balance?: number;
  session: ClientSession;
 }) {
  // auth default team
@@ -100,7 +101,6 @@ export async function createDefaultTeam({
          ownerId: userId,
          name: teamName,
          avatar,
-          balance,
          createTime: new Date()
        }
      ],
@@ -132,15 +132,11 @@ export async function createDefaultTeam({
      ],
      { session }
    );
-    console.log('create default team and group', userId);
+    await createRootOrg({ teamId: tmb.teamId, session });
+    console.log('create default team, group and root org', userId);
    return tmb;
  } else {
    console.log('default team exist', userId);
-    await MongoTeam.findByIdAndUpdate(tmb.teamId, {
-      $set: {
-        ...(balance !== undefined && { balance })
-      }
-    });
  }
 }

@@ -215,7 +211,8 @@ export async function updateTeam({
      return obj;
    })();

-    await MongoTeam.findByIdAndUpdate(
+    // This is where we get the old team
+    const team = await MongoTeam.findByIdAndUpdate(
      teamId,
      {
        $set: {
@@ -241,6 +238,8 @@ export async function updateTeam({
        },
        { session }
      );
+
+      await refreshSourceAvatar(avatar, team?.avatar, session);
    }
  });
 }
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Archer	47f7b1a7a3	full text tmp code (#3561 ) * full text tmp code * fix: init * fix: init * remove tmp code * remove tmp code * 4818-alpha	2025-01-10 18:03:14 +08:00
Archer	fadb3e3ceb	feat: tmp upgrade code (#3559 ) * feat: tmp upgrade code * fulltext search test * update action	2025-01-10 14:41:29 +08:00
Archer	1c0b323b1b	share page avatar (#3558 ) * feat: init 4818 * share page avatar	2025-01-10 13:37:48 +08:00
heheer	b26345dcaa	share link random avatar (#3541 ) * share link random avatar * fix * delete unused code	2025-01-10 12:18:13 +08:00
Jiangween	cef8487ca1	docs:用户答疑的官方文档补充 (#3540 ) * docs:用户答疑的官方文档补充 * 问题回答的内容修补	2025-01-10 11:07:04 +08:00
Archer	ed619edd47	perf: org permission (#3556 )	2025-01-10 10:48:54 +08:00
a.e.	93cf5bb372	fix: MemberModal UI (#3553 ) * fix: adapt MemberModal title and icon * fix: adapt member modal * fix: search input placeholder * fix: add button text	2025-01-10 09:24:06 +08:00
Archer	f556fbf0d5	4.8.18 test (#3543 ) * perf: login check * doc * perf: llm model config * perf: team clb config	2025-01-07 14:21:05 +08:00
a.e.	07cc849877	refactor: team permission manager (#3535 ) * perf: classify org, group and member * refactor: team per manager * fix: missing functions	2025-01-07 09:19:23 +08:00
Archer	2066094047	perf: async read file (#3531 )	2025-01-06 12:43:33 +08:00
Archer	2bf1fce32a	perf: file encoding;perf: leave team code;@c121914yu perf: full text search code (#3528 ) * perf: text encoding * perf: leave team code * perf: full text search code * fix: http status * perf: embedding search and vector avatar	2025-01-06 12:43:33 +08:00
Archer	5465ca642f	4.8.18 test (#3524 ) * perf: remove local token * perf: index	2025-01-06 12:43:32 +08:00
Archer	c0d0c629c5	perf: full text collection and search code;perf: rename function (#3519 ) * perf: full text collection and search code * perf: rename function * perf: notify modal * remove invalid code * perf: sso login * perf: pay process	2025-01-06 12:43:32 +08:00
heheer	20c6c202d2	fix qrcode script (#3520 ) * fix qrcode script * i18n	2025-01-06 12:43:32 +08:00
Finley Ge	c8f60b47d0	feat: support wecom sso (#3518 ) * feat: support wecom sso * chore: remove unused wecom js-sdk dependency	2025-01-06 12:43:31 +08:00
heheer	8b2be89350	optimize payment process (#3517 )	2025-01-06 12:43:31 +08:00
a.e.	a401d4d612	refactor: org pathId (#3516 )	2025-01-06 12:43:30 +08:00
Jiangween	d24d29ac48	perf(plugin): improve searXNG empty result handling and documentation (#3507 ) * perf(plugin): improve searXNG empty result handling and documentation * 修改了文档和代码部分无搜索的结果的反馈	2025-01-06 12:43:29 +08:00
Archer	9abbc16036	perf: notify account (#3515 )	2025-01-06 12:43:28 +08:00
heheer	28710ac05b	force show update notification modal & fix login page text (#3512 ) * fix login page English text * update notification modal	2025-01-06 12:43:28 +08:00
Archer	3412d7009d	perf: password check;perf: image upload check;perf: sso login check (#3509 ) * perf: password check * perf: image upload check * perf: sso login check	2025-01-06 12:43:27 +08:00
a.e.	c3480b0ffa	feat: permission manage UI for org (#3503 )	2025-01-06 12:43:26 +08:00
Finley Ge	f89212f35f	feat: support dataset changeOwner (#3483 ) * feat: support dataset changeOwner * chore: update dataset change owner api	2025-01-06 12:43:25 +08:00
Archer	03d1c6a651	i18n (#3501 ) * name * i18n	2025-01-06 12:43:25 +08:00
Archer	5d1d4ff64f	perf: org permission check (#3500 )	2025-01-06 12:43:24 +08:00
a.e.	fd9600c6f8	feat: org auth for app & dataset (#3498 ) * feat: auth org resource permission * feat: org auth support for app & dataset	2025-01-06 12:43:23 +08:00
Archer	efecfd44c3	perf: Team org ui (#3499 ) * perf: org ui * perf: org ui	2025-01-06 12:43:22 +08:00
a.e.	1fc77a126a	feat: org CRUD (#3380 ) * feat: add org schema * feat: org manage UI * feat: OrgInfoModal * feat: org tree view * feat: org management * fix: init root org * feat: org permission for app * feat: org support for dataset * fix: disable org role control * styles: opt type signatures * fix: remove unused permission * feat: delete org collaborator	2025-01-06 12:43:22 +08:00
Archer	bb669ca3ff	fix: plugin cost (#3533 )	2025-01-06 12:43:04 +08:00
Archer	72ed72e595	fix: charts plugins (#3530 )	2025-01-05 14:41:34 +08:00
Archer	e5735fddd1	Update 4817.md (#3523 )	2025-01-03 16:39:55 +08:00
Archer	fa92ef86b9	fix: system title (#3522 )	2025-01-03 15:30:46 +08:00
Archer	f39ea04178	feat: new provider (#3513 )	2025-01-02 15:38:06 +08:00
Archer	bd4893ced9	更新 README.md (#3511 )	2025-01-02 10:31:25 +08:00
Archer	b75e807f24	fix: tool choice run same tool will error (#3502 )	2024-12-31 10:58:52 +08:00
Archer	b2fdefdc0c	update config.json (#3497 )	2024-12-30 13:53:12 +08:00
Archer	896fec4b82	update doc (#3496 )	2024-12-30 13:51:05 +08:00
Archer	50bf7f9a3b	V4.8.17 feature (#3493 ) * split tokens into input and output (#3477) * split tokens into input and output * query extension & tool call & question guide * fix * perf: input and output tokens * perf: tool call if else * perf: remove code * fix: extract usage count * fix: qa usage count --------- Co-authored-by: heheer <heheer@sealos.io>	2024-12-30 10:13:25 +08:00
Archer	da2831b948	update doc (#3488 )	2024-12-27 20:21:08 +08:00