merge upstream

Signed-off-by: wozulong <>

.github/workflows/docker-image-arm64.yml

@@ -4,6 +4,7 @@ on:
   push:
     tags:
       - '*'
+      - '!*-alpha*'
   workflow_dispatch:
     inputs:
       name:

.gitignore

@@ -5,4 +5,5 @@ upload
 *.db
 build
 *.db-journal
-logs
+logs
+web/dist

LICENSE

@@ -1,21 +1,201 @@
-MIT License
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
 
-Copyright (c) 2024 Calcium-Ion
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
 
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
+   1. Definitions.
 
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
 
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

Midjourney.md

@@ -2,6 +2,21 @@
 
 **简介**:Midjourney Proxy API文档
 
+## 接口列表
+支持的接口如下：
++ [x] /mj/submit/imagine
++ [x] /mj/submit/change
++ [x] /mj/submit/blend
++ [x] /mj/submit/describe
++ [x] /mj/image/{id} （通过此接口获取图片，**请必须在系统设置中填写服务器地址！！**）
++ [x] /mj/task/{id}/fetch （此接口返回的图片地址为经过One API转发的地址）
++ [x] /task/list-by-condition
++ [x] /mj/submit/action （仅midjourney-proxy-plus支持，下同）
++ [x] /mj/submit/modal
++ [x] /mj/submit/shorten
++ [x] /mj/task/{id}/image-seed
++ [x] /mj/insight-face/swap （InsightFace）
+
 ## 模型列表
 
 ### midjourney-proxy支持
@@ -57,11 +72,11 @@
 
 2. 在渠道管理中添加渠道，渠道类型选择**Midjourney Proxy**，如果是plus版本选择**Midjourney Proxy Plus**
    ，模型请参考上方模型列表
-3. 地址填写midjourney-proxy部署的地址，例如：http://localhost:8080
+3. **代理**填写midjourney-proxy部署的地址，例如：http://localhost:8080
 4. 密钥填写midjourney-proxy的密钥，如果没有设置密钥，可以随便填
 
 ### 对接上游new api
 
 1. 在渠道管理中添加渠道，渠道类型选择**Midjourney Proxy Plus**，模型请参考上方模型列表
-2. 地址填写上游new api的地址，例如：http://localhost:3000
+2. **代理**填写上游new api的地址，例如：http://localhost:3000
 3. 密钥填写上游new api的密钥

README.md

@@ -1,40 +1,39 @@
+<div align="center">
+
+![new-api](/web/public/logo.png)
 
 # New API
 
+<a href="https://trendshift.io/repositories/8227" target="_blank"><img src="https://trendshift.io/api/badge/repositories/8227" alt="Calcium-Ion%2Fnew-api | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+
+</div>
+
 > [!NOTE]
-> 本项目为开源项目，在[One API](https://github.com/songquanpeng/one-api)的基础上进行二次开发，感谢原作者的无私奉献。 
+> 本项目为开源项目，在[One API](https://github.com/songquanpeng/one-api)的基础上进行二次开发
+
+> [!IMPORTANT]
 > 使用者必须在遵循 OpenAI 的[使用条款](https://openai.com/policies/terms-of-use)以及**法律法规**的情况下使用，不得用于非法用途。
-
-
-> [!WARNING]
-> 本项目为个人学习使用，不保证稳定性，且不提供任何技术支持，使用者必须在遵循 OpenAI 的使用条款以及法律法规的情况下使用，不得用于非法用途。  
+> 本项目仅供个人学习使用，不保证稳定性，且不提供任何技术支持。
 > 根据[《生成式人工智能服务管理暂行办法》](http://www.cac.gov.cn/2023-07/13/c_1690898327029107.htm)的要求，请勿对中国地区公众提供一切未经备案的生成式人工智能服务。
 
-> [!NOTE]
-> 最新版Docker镜像 calciumion/new-api:latest  
-> 更新指令 docker run --rm -v /var/run/docker.sock:/var/run/docker.sock containrrr/watchtower -cR
+> [!TIP]
+> 最新版Docker镜像：`calciumion/new-api:latest`  
+> 默认账号root 密码123456  
+> 更新指令：
+> ```
+> docker run --rm -v /var/run/docker.sock:/var/run/docker.sock containrrr/watchtower -cR
+> ```
+
 
 ## 主要变更
 此分叉版本的主要变更如下：
 
 1. 全新的UI界面（部分界面还待更新）
-2. 添加[Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy)接口的支持，[对接文档](Midjourney.md)，支持的接口如下：
-   + [x] /mj/submit/imagine
-   + [x] /mj/submit/change
-   + [x] /mj/submit/blend
-   + [x] /mj/submit/describe
-   + [x] /mj/image/{id} （通过此接口获取图片，**请必须在系统设置中填写服务器地址！！**）
-   + [x] /mj/task/{id}/fetch （此接口返回的图片地址为经过One API转发的地址）
-   + [x] /task/list-by-condition
-   + [x] /mj/submit/action （仅midjourney-proxy-plus支持，下同）
-   + [x] /mj/submit/modal
-   + [x] /mj/submit/shorten
-   + [x] /mj/task/{id}/image-seed
-   + [x] /mj/insight-face/swap （InsightFace）
+2. 添加[Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy)接口的支持，[对接文档](Midjourney.md)
 3. 支持在线充值功能，可在系统设置中设置，当前支持的支付接口：
-   + [x] 易支付
+    + [x] 易支付
 4. 支持用key查询使用额度:
-   + 配合项目[neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool)可实现用key查询使用
+    + 配合项目[neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool)可实现用key查询使用
 5. 渠道显示已使用额度，支持指定组织访问
 6. 分页支持选择每页显示数量
 7. 兼容原版One API的数据库，可直接使用原版数据库（one-api.db）
@@ -47,29 +46,39 @@
     2. 对[@Botfather](https://t.me/botfather)输入指令/setdomain
     3. 选择你的bot，然后输入http(s)://你的网站地址/login
     4. Telegram Bot 名称是bot username 去掉@后的字符串
+13. 添加 [Suno API](https://github.com/Suno-API/Suno-API)接口的支持，[对接文档](Suno.md)
+14. 支持Rerank模型，目前仅兼容Cohere和Jina，可接入Dify，[对接文档](Rerank.md)
 
 ## 模型支持
 此版本额外支持以下模型：
-1. 第三方模型 **gps** （gpt-4-gizmo-*）
+1. 第三方模型 **gps** （gpt-4-gizmo-*, g-*）
 2. 智谱glm-4v，glm-4v识图
-3. Anthropic Claude 3 (claude-3-opus-20240229, claude-3-sonnet-20240229)
+3. Anthropic Claude 3
 4. [Ollama](https://github.com/ollama/ollama?tab=readme-ov-file)，添加渠道时，密钥可以随便填写，默认的请求地址是[http://localhost:11434](http://localhost:11434)，如果需要修改请在渠道中修改
 5. [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy)接口，[对接文档](Midjourney.md)
 6. [零一万物](https://platform.lingyiwanwu.com/)
+7. 自定义渠道，支持填入完整调用地址
+8. [Suno API](https://github.com/Suno-API/Suno-API) 接口，[对接文档](Suno.md)
+9. Rerank模型，目前支持[Cohere](https://cohere.ai/)和[Jina](https://jina.ai/)，[对接文档](Rerank.md)
+10. Dify
+11. Vertex AI，目前兼容Claude，Gemini，Llama3.1
 
-您可以在渠道中添加自定义模型gpt-4-gizmo-*，此模型并非OpenAI官方模型，而是第三方模型，使用官方key无法调用。
-
-## 渠道重试
-渠道重试功能已经实现，可以在`设置->运营设置->通用设置`设置重试次数，建议开启缓存功能。  
-如果开启了重试功能，第一次重试使用同优先级，第二次重试使用下一个优先级，以此类推。  
-### 缓存设置方法
-1. `REDIS_CONN_STRING`：设置之后将使用 Redis 作为缓存使用。
-    + 例子：`REDIS_CONN_STRING=redis://default:redispw@localhost:49153`
-2. `MEMORY_CACHE_ENABLED`：启用内存缓存（如果设置了`REDIS_CONN_STRING`，则无需手动设置），会导致用户额度的更新存在一定的延迟，可选值为 `true` 和 `false`，未设置则默认为 `false`。
-    + 例子：`MEMORY_CACHE_ENABLED=true`
-
+您可以在渠道中添加自定义模型gpt-4-gizmo-*或g-*，此模型并非OpenAI官方模型，而是第三方模型，使用官方key无法调用。
 
+## 比原版One API多出的配置
+- `GENERATE_DEFAULT_TOKEN`：是否为新注册用户生成初始令牌，默认为 `false`。
+- `STREAMING_TIMEOUT`：设置流式一次回复的超时时间，默认为 30 秒。
+- `DIFY_DEBUG`：设置 Dify 渠道是否输出工作流和节点信息到客户端，默认为 `true`。
+- `FORCE_STREAM_OPTION`：是否覆盖客户端stream_options参数，请求上游返回流模式usage，默认为 `true`，建议开启，不影响客户端传入stream_options参数返回结果。
+- `GET_MEDIA_TOKEN`：是统计图片token，默认为 `true`，关闭后将不再在本地计算图片token，可能会导致和上游计费不同，此项覆盖 `GET_MEDIA_TOKEN_NOT_STREAM` 选项作用。
+- `GET_MEDIA_TOKEN_NOT_STREAM`：是否在非流（`stream=false`）情况下统计图片token，默认为 `true`。
+- `UPDATE_TASK`：是否更新异步任务（Midjourney、Suno），默认为 `true`，关闭后将不会更新任务进度。
+- `GEMINI_MODEL_MAP`：Gemini模型指定版本(v1/v1beta)，使用“模型:版本”指定，","分隔，例如：-e GEMINI_MODEL_MAP="gemini-1.5-pro-latest:v1beta,gemini-1.5-pro-001:v1beta"，为空则使用默认配置
+- `COHERE_SAFETY_SETTING`：Cohere模型[安全设置](https://docs.cohere.com/docs/safety-modes#overview)，可选值为 `NONE`, `CONTEXTUAL`，`STRICT`，默认为 `NONE`。
 ## 部署
+### 部署要求
+- 本地数据库（默认）：SQLite（Docker 部署默认使用 SQLite，必须挂载 `/data` 目录到宿主机）
+- 远程数据库：MySQL 版本 >= 5.7.8，PgSQL 版本 >= 9.6
 ### 基于 Docker 进行部署
 ```shell
 # 使用 SQLite 的部署命令：
@@ -88,25 +97,40 @@ docker run --name new-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -
 docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:123456@tcp(宝塔的服务器地址:宝塔数据库端口)/宝塔数据库名称" -e TZ=Asia/Shanghai -v /www/wwwroot/new-api:/data calciumion/new-api:latest
 # 注意：数据库要开启远程访问，并且只允许服务器IP访问
 ```
+
+## 渠道重试
+渠道重试功能已经实现，可以在`设置->运营设置->通用设置`设置重试次数，**建议开启缓存**功能。  
+如果开启了重试功能，第一次重试使用同优先级，第二次重试使用下一个优先级，以此类推。
+### 缓存设置方法
+1. `REDIS_CONN_STRING`：设置之后将使用 Redis 作为缓存使用。
+    + 例子：`REDIS_CONN_STRING=redis://default:redispw@localhost:49153`
+2. `MEMORY_CACHE_ENABLED`：启用内存缓存（如果设置了`REDIS_CONN_STRING`，则无需手动设置），会导致用户额度的更新存在一定的延迟，可选值为 `true` 和 `false`，未设置则默认为 `false`。
+    + 例子：`MEMORY_CACHE_ENABLED=true`
+### 为什么有的时候没有重试
+这些错误码不会重试：400，504，524
+### 我想让400也重试
+在`渠道->编辑`中，将`状态码复写`改为
+```json
+{
+  "400": "500"
+}
+```
+可以实现400错误转为500错误，从而重试
+
 ## Midjourney接口设置文档
 [对接文档](Midjourney.md)
 
-## 交流群
-<img src="https://github.com/Calcium-Ion/new-api/assets/61247483/de536a8a-0161-47a7-a0a2-66ef6de81266" width="300">
+## Suno接口设置文档
+[对接文档](Suno.md)
 
 ## 界面截图
+![796df8d287b7b7bd7853b2497e7df511](https://github.com/user-attachments/assets/255b5e97-2d3a-4434-b4fa-e922ad88ff5a)
+
 ![image](https://github.com/Calcium-Ion/new-api/assets/61247483/ad0e7aae-0203-471c-9716-2d83768927d4)
 
-![image](https://github.com/Calcium-Ion/new-api/assets/61247483/d1ac216e-0804-4105-9fdc-66b35022d861)
-
-![image](https://github.com/Calcium-Ion/new-api/assets/61247483/3ca0b282-00ff-4c96-bf9d-e29ef615c605)  
-![image](https://github.com/Calcium-Ion/new-api/assets/61247483/f4f40ed4-8ccb-43d7-a580-90677827646d)  
-![image](https://github.com/Calcium-Ion/new-api/assets/61247483/90d7d763-6a77-4b36-9f76-2bb30f18583d)
-![image](https://github.com/Calcium-Ion/new-api/assets/61247483/e414228a-3c35-429a-b298-6451d76d9032)
+![image](https://github.com/Calcium-Ion/new-api/assets/61247483/3ca0b282-00ff-4c96-bf9d-e29ef615c605)
 夜间模式  
 ![image](https://github.com/Calcium-Ion/new-api/assets/61247483/1c66b593-bb9e-4757-9720-ff2759539242)
-
-![image](https://github.com/Calcium-Ion/new-api/assets/61247483/5b3228e8-2556-44f7-97d6-4f8d8ee6effa)  
 ![image](https://github.com/Calcium-Ion/new-api/assets/61247483/af9a07ee-5101-4b3d-8bd9-ae21a4fd7e9e)
 
 ## 相关项目

Rerank.md

@@ -0,0 +1,62 @@
+# Rerank API文档
+
+**简介**:Rerank API文档
+
+## 接入Dify
+模型供应商选择Jina，按要求填写模型信息即可接入Dify。
+
+## 请求方式
+
+Post: /v1/rerank
+
+Request:
+
+```json
+{
+  "model": "rerank-multilingual-v3.0",
+  "query": "What is the capital of the United States?",
+  "top_n": 3,
+  "documents": [
+    "Carson City is the capital city of the American state of Nevada.",
+    "The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean. Its capital is Saipan.",
+    "Washington, D.C. (also known as simply Washington or D.C., and officially as the District of Columbia) is the capital of the United States. It is a federal district.",
+    "Capitalization or capitalisation in English grammar is the use of a capital letter at the start of a word. English usage varies from capitalization in other languages.",
+    "Capital punishment (the death penalty) has existed in the United States since beforethe United States was a country. As of 2017, capital punishment is legal in 30 of the 50 states."
+  ]
+}
+```
+
+Response:
+
+```json
+{
+  "results": [
+    {
+      "document": {
+        "text": "Washington, D.C. (also known as simply Washington or D.C., and officially as the District of Columbia) is the capital of the United States. It is a federal district."
+      },
+      "index": 2,
+      "relevance_score": 0.9999702
+    },
+    {
+      "document": {
+        "text": "Carson City is the capital city of the American state of Nevada."
+      },
+      "index": 0,
+      "relevance_score": 0.67800725
+    },
+    {
+      "document": {
+        "text": "Capitalization or capitalisation in English grammar is the use of a capital letter at the start of a word. English usage varies from capitalization in other languages."
+      },
+      "index": 3,
+      "relevance_score": 0.02800752
+    }
+  ],
+  "usage": {
+    "prompt_tokens": 158,
+    "completion_tokens": 0,
+    "total_tokens": 158
+  }
+}
+```

Suno.md

@@ -0,0 +1,44 @@
+# Suno API文档
+
+**简介**:Suno API文档
+
+## 接口列表
+支持的接口如下：
++ [x] /suno/submit/music
++ [x] /suno/submit/lyrics
++ [x] /suno/fetch
++ [x] /suno/fetch/:id
+
+## 模型列表
+
+### Suno API支持
+
+- suno_music (自定义模式、灵感模式、续写)
+- suno_lyrics (生成歌词)
+
+
+## 模型价格设置（在设置-运营设置-模型固定价格设置中设置）
+```json
+{
+  "suno_music": 0.3,
+  "suno_lyrics": 0.01
+}
+```
+
+## 渠道设置
+
+### 对接 Suno API
+
+1.
+部署 Suno API，并配置好suno账号等（强烈建议设置密钥），[项目地址](https://github.com/Suno-API/Suno-API)
+
+2. 在渠道管理中添加渠道，渠道类型选择**Suno API**
+   ，模型请参考上方模型列表
+3. **代理**填写 Suno API 部署的地址，例如：http://localhost:8080
+4. 密钥填写 Suno API 的密钥，如果没有设置密钥，可以随便填
+
+### 对接上游new api
+
+1. 在渠道管理中添加渠道，渠道类型选择**Suno API**，或任意类型，只需模型包含上方模型列表的模型
+2. **代理**填写上游new api的地址，例如：http://localhost:3000
+3. 密钥填写上游new api的密钥

common/constants.go

@@ -22,6 +22,7 @@ var StartTime = time.Now().Unix() // unit: second
 var Version = "v0.0.0"            // this hard coding will be replaced automatically when building, no need to manually change
 var SystemName = "New API"
 var ServerAddress = "http://localhost:3000"
+var OutProxyUrl = ""
 var Footer = ""
 var Logo = ""
 var TopUpLink = ""
@@ -31,6 +32,7 @@ var QuotaPerUnit = 500 * 1000.0 // $0.002 / 1K tokens
 var DisplayInCurrencyEnabled = true
 var DisplayTokenStatEnabled = true
 var DrawingEnabled = true
+var TaskEnabled = true
 var DataExportEnabled = true
 var DataExportInterval = 5         // unit: minute
 var DataExportDefaultTime = "hour" // unit: minute
@@ -118,14 +120,17 @@ var IsMasterNode = os.Getenv("NODE_TYPE") != "slave"
 var requestInterval, _ = strconv.Atoi(os.Getenv("POLLING_INTERVAL"))
 var RequestInterval = time.Duration(requestInterval) * time.Second
 
-var SyncFrequency = GetOrDefault("SYNC_FREQUENCY", 60) // unit is second
+var SyncFrequency = GetEnvOrDefault("SYNC_FREQUENCY", 60) // unit is second
 
 var BatchUpdateEnabled = false
-var BatchUpdateInterval = GetOrDefault("BATCH_UPDATE_INTERVAL", 5)
+var BatchUpdateInterval = GetEnvOrDefault("BATCH_UPDATE_INTERVAL", 5)
 
-var RelayTimeout = GetOrDefault("RELAY_TIMEOUT", 0) // unit is second
+var RelayTimeout = GetEnvOrDefault("RELAY_TIMEOUT", 0) // unit is second
 
-var GeminiSafetySetting = GetOrDefaultString("GEMINI_SAFETY_SETTING", "BLOCK_NONE")
+var GeminiSafetySetting = GetEnvOrDefaultString("GEMINI_SAFETY_SETTING", "BLOCK_NONE")
+
+// https://docs.cohere.com/docs/safety-modes Type; NONE/CONTEXTUAL/STRICT
+var CohereSafetySetting = GetEnvOrDefaultString("COHERE_SAFETY_SETTING", "NONE")
 
 const (
 	RequestIdKey = "X-Oneapi-Request-Id"
@@ -138,6 +143,10 @@ const (
 	RoleRootUser   = 100
 )
 
+func IsValidateRole(role int) bool {
+	return role == RoleGuestUser || role == RoleCommonUser || role == RoleAdminUser || role == RoleRootUser
+}
+
 var (
 	FileUploadPermission    = RoleGuestUser
 	FileDownloadPermission  = RoleGuestUser
@@ -148,10 +157,10 @@ var (
 // All duration's unit is seconds
 // Shouldn't larger then RateLimitKeyExpirationDuration
 var (
-	GlobalApiRateLimitNum            = GetOrDefault("GLOBAL_API_RATE_LIMIT", 180)
+	GlobalApiRateLimitNum            = GetEnvOrDefault("GLOBAL_API_RATE_LIMIT", 180)
 	GlobalApiRateLimitDuration int64 = 3 * 60
 
-	GlobalWebRateLimitNum            = GetOrDefault("GLOBAL_WEB_RATE_LIMIT", 60)
+	GlobalWebRateLimitNum            = GetEnvOrDefault("GLOBAL_WEB_RATE_LIMIT", 60)
 	GlobalWebRateLimitDuration int64 = 3 * 60
 
 	UploadRateLimitNum            = 10
@@ -229,33 +238,43 @@ const (
 	ChannelTypeLingYiWanWu    = 31
 	ChannelTypeAws            = 33
 	ChannelTypeCohere         = 34
+	ChannelTypeMiniMax        = 35
+	ChannelTypeSunoAPI        = 36
+	ChannelTypeDify           = 37
+	ChannelTypeJina           = 38
+	ChannelCloudflare         = 39
+	ChannelTypeSiliconFlow    = 40
+	ChannelTypeVertexAi       = 41
+
+	ChannelTypeDummy // this one is only for count, do not add any channel after this
+
 )
 
 var ChannelBaseURLs = []string{
-	"",                                  // 0
-	"https://api.openai.com",            // 1
-	"https://oa.api2d.net",              // 2
-	"",                                  // 3
-	"http://localhost:11434",            // 4
-	"https://api.openai-sb.com",         // 5
-	"https://api.openaimax.com",         // 6
-	"https://api.ohmygpt.com",           // 7
-	"",                                  // 8
-	"https://api.caipacity.com",         // 9
-	"https://api.aiproxy.io",            // 10
-	"",                                  // 11
-	"https://api.api2gpt.com",           // 12
-	"https://api.aigc2d.com",            // 13
-	"https://api.anthropic.com",         // 14
-	"https://aip.baidubce.com",          // 15
-	"https://open.bigmodel.cn",          // 16
-	"https://dashscope.aliyuncs.com",    // 17
-	"",                                  // 18
-	"https://ai.360.cn",                 // 19
-	"https://openrouter.ai/api",         // 20
-	"https://api.aiproxy.io",            // 21
-	"https://fastgpt.run/api/openapi",   // 22
-	"https://hunyuan.cloud.tencent.com", //23
+	"",                                    // 0
+	"https://api.openai.com",              // 1
+	"https://oa.api2d.net",                // 2
+	"",                                    // 3
+	"http://localhost:11434",              // 4
+	"https://api.openai-sb.com",           // 5
+	"https://api.openaimax.com",           // 6
+	"https://api.ohmygpt.com",             // 7
+	"",                                    // 8
+	"https://api.caipacity.com",           // 9
+	"https://api.aiproxy.io",              // 10
+	"",                                    // 11
+	"https://api.api2gpt.com",             // 12
+	"https://api.aigc2d.com",              // 13
+	"https://api.anthropic.com",           // 14
+	"https://aip.baidubce.com",            // 15
+	"https://open.bigmodel.cn",            // 16
+	"https://dashscope.aliyuncs.com",      // 17
+	"",                                    // 18
+	"https://ai.360.cn",                   // 19
+	"https://openrouter.ai/api",           // 20
+	"https://api.aiproxy.io",              // 21
+	"https://fastgpt.run/api/openapi",     // 22
+	"https://hunyuan.tencentcloudapi.com", //23
 	"https://generativelanguage.googleapis.com", //24
 	"https://api.moonshot.cn",                   //25
 	"https://open.bigmodel.cn",                  //26
@@ -267,4 +286,11 @@ var ChannelBaseURLs = []string{
 	"",                                          //32
 	"",                                          //33
 	"https://api.cohere.ai",                     //34
+	"https://api.minimax.chat",                  //35
+	"",                                          //36
+	"",                                          //37
+	"https://api.jina.ai",                       //38
+	"https://api.cloudflare.com",                //39
+	"https://api.siliconflow.cn",                //40
+	"",                                          //41
 }

common/email-outlook-auth.go

@@ -0,0 +1,40 @@
+package common
+
+import (
+	"errors"
+	"net/smtp"
+	"strings"
+)
+
+type outlookAuth struct {
+	username, password string
+}
+
+func LoginAuth(username, password string) smtp.Auth {
+	return &outlookAuth{username, password}
+}
+
+func (a *outlookAuth) Start(_ *smtp.ServerInfo) (string, []byte, error) {
+	return "LOGIN", []byte{}, nil
+}
+
+func (a *outlookAuth) Next(fromServer []byte, more bool) ([]byte, error) {
+	if more {
+		switch string(fromServer) {
+		case "Username:":
+			return []byte(a.username), nil
+		case "Password:":
+			return []byte(a.password), nil
+		default:
+			return nil, errors.New("unknown fromServer")
+		}
+	}
+	return nil, nil
+}
+
+func isOutlookServer(server string) bool {
+	// 兼容多地区的outlook邮箱和ofb邮箱
+	// 其实应该加一个Option来区分是否用LOGIN的方式登录
+	// 先临时兼容一下
+	return strings.Contains(server, "outlook") || strings.Contains(server, "onmicrosoft")
+}

common/email.go

@@ -9,17 +9,26 @@ import (
 	"time"
 )
 
+func generateMessageID() string {
+	domain := strings.Split(SMTPAccount, "@")[1]
+	return fmt.Sprintf("<%d.%s@%s>", time.Now().UnixNano(), GetRandomString(12), domain)
+}
+
 func SendEmail(subject string, receiver string, content string) error {
 	if SMTPFrom == "" { // for compatibility
 		SMTPFrom = SMTPAccount
 	}
+	if SMTPServer == "" && SMTPAccount == "" {
+		return fmt.Errorf("SMTP 服务器未配置")
+	}
 	encodedSubject := fmt.Sprintf("=?UTF-8?B?%s?=", base64.StdEncoding.EncodeToString([]byte(subject)))
 	mail := []byte(fmt.Sprintf("To: %s\r\n"+
 		"From: %s<%s>\r\n"+
 		"Subject: %s\r\n"+
 		"Date: %s\r\n"+
+		"Message-ID: %s\r\n"+ // 添加 Message-ID 头
 		"Content-Type: text/html; charset=UTF-8\r\n\r\n%s\r\n",
-		receiver, SystemName, SMTPFrom, encodedSubject, time.Now().Format(time.RFC1123Z), content))
+		receiver, SystemName, SMTPFrom, encodedSubject, time.Now().Format(time.RFC1123Z), generateMessageID(), content))
 	auth := smtp.PlainAuth("", SMTPAccount, SMTPToken, SMTPServer)
 	addr := fmt.Sprintf("%s:%d", SMTPServer, SMTPPort)
 	to := strings.Split(receiver, ";")
@@ -62,6 +71,9 @@ func SendEmail(subject string, receiver string, content string) error {
 		if err != nil {
 			return err
 		}
+	} else if isOutlookServer(SMTPAccount) {
+		auth = LoginAuth(SMTPAccount, SMTPToken)
+		err = smtp.SendMail(addr, auth, SMTPAccount, to, mail)
 	} else {
 		err = smtp.SendMail(addr, auth, SMTPAccount, to, mail)
 	}

common/env.go

@@ -0,0 +1,38 @@
+package common
+
+import (
+	"fmt"
+	"os"
+	"strconv"
+)
+
+func GetEnvOrDefault(env string, defaultValue int) int {
+	if env == "" || os.Getenv(env) == "" {
+		return defaultValue
+	}
+	num, err := strconv.Atoi(os.Getenv(env))
+	if err != nil {
+		SysError(fmt.Sprintf("failed to parse %s: %s, using default value: %d", env, err.Error(), defaultValue))
+		return defaultValue
+	}
+	return num
+}
+
+func GetEnvOrDefaultString(env string, defaultValue string) string {
+	if env == "" || os.Getenv(env) == "" {
+		return defaultValue
+	}
+	return os.Getenv(env)
+}
+
+func GetEnvOrDefaultBool(env string, defaultValue bool) bool {
+	if env == "" || os.Getenv(env) == "" {
+		return defaultValue
+	}
+	b, err := strconv.ParseBool(os.Getenv(env))
+	if err != nil {
+		SysError(fmt.Sprintf("failed to parse %s: %s, using default value: %t", env, err.Error(), defaultValue))
+		return defaultValue
+	}
+	return b
+}

common/go-channel.go

@@ -3,6 +3,7 @@ package common
 import (
 	"fmt"
 	"runtime/debug"
+	"time"
 )
 
 func SafeGoroutine(f func()) {
@@ -45,3 +46,21 @@ func SafeSendString(ch chan string, value string) (closed bool) {
 	// If the code reaches here, then the channel was not closed.
 	return false
 }
+
+// SafeSendStringTimeout send, return true, else return false
+func SafeSendStringTimeout(ch chan string, value string, timeout int) (closed bool) {
+	defer func() {
+		// Recover from panic if one occured. A panic would mean the channel was closed.
+		if recover() != nil {
+			closed = false
+		}
+	}()
+
+	// This will panic if the channel is closed.
+	select {
+	case ch <- value:
+		return true
+	case <-time.After(time.Duration(timeout) * time.Second):
+		return false
+	}
+}

common/group-ratio.go

@@ -1,6 +1,8 @@
 package common
 
-import "encoding/json"
+import (
+	"encoding/json"
+)
 
 var GroupRatio = map[string]float64{
 	"default": 1,

common/image.go

@@ -8,7 +8,6 @@ import (
 	"golang.org/x/image/webp"
 	"image"
 	"io"
-	"net/http"
 	"strings"
 )
 
@@ -32,7 +31,7 @@ func DecodeBase64ImageData(base64String string) (image.Config, string, string, e
 }
 
 func IsImageUrl(url string) (bool, error) {
-	resp, err := http.Head(url)
+	resp, err := ProxiedHttpHead(url, OutProxyUrl)
 	if err != nil {
 		return false, err
 	}
@@ -48,10 +47,13 @@ func GetImageFromUrl(url string) (mimeType string, data string, err error) {
 	if !isImage {
 		return
 	}
-	resp, err := http.Get(url)
+	resp, err := ProxiedHttpGet(url, OutProxyUrl)
 	if err != nil {
 		return
 	}
+	if !strings.HasPrefix(resp.Header.Get("Content-Type"), "image/") {
+		return
+	}
 	defer resp.Body.Close()
 	buffer := bytes.NewBuffer(nil)
 	_, err = buffer.ReadFrom(resp.Body)
@@ -64,13 +66,18 @@ func GetImageFromUrl(url string) (mimeType string, data string, err error) {
 }
 
 func DecodeUrlImageData(imageUrl string) (image.Config, string, error) {
-	response, err := http.Get(imageUrl)
+	response, err := ProxiedHttpGet(imageUrl, OutProxyUrl)
 	if err != nil {
 		SysLog(fmt.Sprintf("fail to get image from url: %s", err.Error()))
 		return image.Config{}, "", err
 	}
 	defer response.Body.Close()
 
+	if response.StatusCode != 200 {
+		err = errors.New(fmt.Sprintf("fail to get image from url: %s", response.Status))
+		return image.Config{}, "", err
+	}
+
 	var readData []byte
 	for _, limit := range []int64{1024 * 8, 1024 * 24, 1024 * 64} {
 		SysLog(fmt.Sprintf("try to decode image config with limit: %d", limit))

common/model-ratio.go

@@ -3,6 +3,14 @@ package common
 import (
 	"encoding/json"
 	"strings"
+	"sync"
+)
+
+// from songquanpeng/one-api
+const (
+	USD2RMB = 7.3 // 暂定 1 USD = 7.3 RMB
+	USD     = 500 // $0.002 = 1 -> $1 = 500
+	RMB     = USD / USD2RMB
 )
 
 // modelRatio
@@ -13,111 +21,169 @@ import (
 // 1 === $0.002 / 1K tokens
 // 1 === ￥0.014 / 1k tokens
 
-var DefaultModelRatio = map[string]float64{
+var defaultModelRatio = map[string]float64{
 	//"midjourney":                50,
-	"gpt-4-gizmo-*":             15,
-	"gpt-4":                     15,
-	"gpt-4-0314":                15,
-	"gpt-4-0613":                15,
-	"gpt-4-32k":                 30,
-	"gpt-4-32k-0314":            30,
-	"gpt-4-32k-0613":            30,
-	"gpt-4-turbo":               5,    // $0.01 / 1K tokens
-	"gpt-4-turbo-2024-04-09":    5,    // $0.01 / 1K tokens
-	"gpt-4-1106-preview":        5,    // $0.01 / 1K tokens
-	"gpt-4-0125-preview":        5,    // $0.01 / 1K tokens
-	"gpt-4-turbo-preview":       5,    // $0.01 / 1K tokens
-	"gpt-4-vision-preview":      5,    // $0.01 / 1K tokens
-	"gpt-4-1106-vision-preview": 5,    // $0.01 / 1K tokens
-	"gpt-3.5-turbo":             0.25, // $0.0005 / 1K tokens
-	"gpt-3.5-turbo-0301":        0.75,
-	"gpt-3.5-turbo-0613":        0.75,
-	"gpt-3.5-turbo-16k":         1.5, // $0.003 / 1K tokens
-	"gpt-3.5-turbo-16k-0613":    1.5,
-	"gpt-3.5-turbo-instruct":    0.75, // $0.0015 / 1K tokens
-	"gpt-3.5-turbo-1106":        0.5,  // $0.001 / 1K tokens
-	"gpt-3.5-turbo-0125":        0.25,
-	"babbage-002":               0.2, // $0.0004 / 1K tokens
-	"davinci-002":               1,   // $0.002 / 1K tokens
-	"text-ada-001":              0.2,
-	"text-babbage-001":          0.25,
-	"text-curie-001":            1,
-	"text-davinci-002":          10,
-	"text-davinci-003":          10,
-	"text-davinci-edit-001":     10,
-	"code-davinci-edit-001":     10,
-	"whisper-1":                 15,  // $0.006 / minute -> $0.006 / 150 words -> $0.006 / 200 tokens -> $0.03 / 1k tokens
-	"tts-1":                     7.5, // 1k characters -> $0.015
-	"tts-1-1106":                7.5, // 1k characters -> $0.015
-	"tts-1-hd":                  15,  // 1k characters -> $0.03
-	"tts-1-hd-1106":             15,  // 1k characters -> $0.03
-	"davinci":                   10,
-	"curie":                     10,
-	"babbage":                   10,
-	"ada":                       10,
-	"text-embedding-3-small":    0.01,
-	"text-embedding-3-large":    0.065,
-	"text-embedding-ada-002":    0.05,
-	"text-search-ada-doc-001":   10,
-	"text-moderation-stable":    0.1,
-	"text-moderation-latest":    0.1,
-	"dall-e-2":                  8,
-	"dall-e-3":                  16,
-	"claude-instant-1":          0.4,    // $0.8 / 1M tokens
-	"claude-2.0":                4,      // $8 / 1M tokens
-	"claude-2.1":                4,      // $8 / 1M tokens
-	"claude-3-haiku-20240307":   0.125,  // $0.25 / 1M tokens
-	"claude-3-sonnet-20240229":  1.5,    // $3 / 1M tokens
-	"claude-3-opus-20240229":    7.5,    // $15 / 1M tokens
-	"ERNIE-Bot":                 0.8572, // ￥0.012 / 1k tokens
-	"ERNIE-Bot-turbo":           0.5715, // ￥0.008 / 1k tokens
-	"ERNIE-Bot-4":               8.572,  // ￥0.12 / 1k tokens
-	"Embedding-V1":              0.1429, // ￥0.002 / 1k tokens
-	"PaLM-2":                    1,
-	"gemini-pro":                   1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
-	"gemini-pro-vision":            1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
-	"gemini-1.0-pro-vision-001":    1,
-	"gemini-1.0-pro-001":           1,
-	"gemini-1.5-pro-latest":        1,
-	"gemini-1.0-pro-latest":        1,
-	"gemini-1.0-pro-vision-latest": 1,
-	"gemini-ultra":                 1,
-	"chatglm_turbo":             0.3572, // ￥0.005 / 1k tokens
-	"chatglm_pro":               0.7143, // ￥0.01 / 1k tokens
-	"chatglm_std":               0.3572, // ￥0.005 / 1k tokens
-	"chatglm_lite":              0.1429, // ￥0.002 / 1k tokens
-	"glm-4":                     7.143,  // ￥0.1 / 1k tokens
-	"glm-4v":                    7.143,  // ￥0.1 / 1k tokens
-	"glm-3-turbo":               0.3572,
-	"qwen-turbo":                0.8572, // ￥0.012 / 1k tokens
-	"qwen-plus":                 10,     // ￥0.14 / 1k tokens
-	"text-embedding-v1":         0.05,   // ￥0.0007 / 1k tokens
-	"SparkDesk-v1.1":            1.2858, // ￥0.018 / 1k tokens
-	"SparkDesk-v2.1":            1.2858, // ￥0.018 / 1k tokens
-	"SparkDesk-v3.1":            1.2858, // ￥0.018 / 1k tokens
-	"SparkDesk-v3.5":            1.2858, // ￥0.018 / 1k tokens
-	"360GPT_S2_V9":              0.8572, // ¥0.012 / 1k tokens
-	"embedding-bert-512-v1":     0.0715, // ¥0.001 / 1k tokens
-	"embedding_s1_v1":           0.0715, // ¥0.001 / 1k tokens
-	"semantic_similarity_s1_v1": 0.0715, // ¥0.001 / 1k tokens
-	"hunyuan":                   7.143,  // ¥0.1 / 1k tokens  // https://cloud.tencent.com/document/product/1729/97731#e0e6be58-60c8-469f-bdeb-6c264ce3b4d0
+	"gpt-4-gizmo-*":                  15,
+	"g-*":                            15,
+	"gpt-4":                          15,
+	"gpt-4-0314":                     15,
+	"gpt-4-0613":                     15,
+	"gpt-4-32k":                      30,
+	"gpt-4-32k-0314":                 30,
+	"gpt-4-32k-0613":                 30,
+	"gpt-4o-mini":                    0.075, // $0.00015 / 1K tokens
+	"gpt-4o-mini-2024-07-18":         0.075,
+	"chatgpt-4o-latest":              2.5,  // $0.01 / 1K tokens
+	"gpt-4o":                         2.5,  // $0.005 / 1K tokens
+	"gpt-4o-2024-05-13":              2.5,  // $0.005 / 1K tokens
+	"gpt-4o-2024-08-06":              1.25, // $0.01 / 1K tokens
+	"o1-preview":                     7.5,
+	"o1-preview-2024-09-12":          7.5,
+	"o1-mini":                        1.5,
+	"o1-mini-2024-09-12":             1.5,
+	"gpt-4-turbo":                    5,    // $0.01 / 1K tokens
+	"gpt-4-turbo-2024-04-09":         5,    // $0.01 / 1K tokens
+	"gpt-4-1106-preview":             5,    // $0.01 / 1K tokens
+	"gpt-4-0125-preview":             5,    // $0.01 / 1K tokens
+	"gpt-4-turbo-preview":            5,    // $0.01 / 1K tokens
+	"gpt-4-vision-preview":           5,    // $0.01 / 1K tokens
+	"gpt-4-1106-vision-preview":      5,    // $0.01 / 1K tokens
+	"gpt-3.5-turbo":                  0.25, // $0.0005 / 1K tokens
+	"gpt-3.5-turbo-0301":             0.75,
+	"gpt-3.5-turbo-0613":             0.75,
+	"gpt-3.5-turbo-16k":              1.5, // $0.003 / 1K tokens
+	"gpt-3.5-turbo-16k-0613":         1.5,
+	"gpt-3.5-turbo-instruct":         0.75, // $0.0015 / 1K tokens
+	"gpt-3.5-turbo-1106":             0.5,  // $0.001 / 1K tokens
+	"gpt-3.5-turbo-0125":             0.25,
+	"babbage-002":                    0.2, // $0.0004 / 1K tokens
+	"davinci-002":                    1,   // $0.002 / 1K tokens
+	"text-ada-001":                   0.2,
+	"text-babbage-001":               0.25,
+	"text-curie-001":                 1,
+	"text-davinci-002":               10,
+	"text-davinci-003":               10,
+	"text-davinci-edit-001":          10,
+	"code-davinci-edit-001":          10,
+	"whisper-1":                      15,  // $0.006 / minute -> $0.006 / 150 words -> $0.006 / 200 tokens -> $0.03 / 1k tokens
+	"tts-1":                          7.5, // 1k characters -> $0.015
+	"tts-1-1106":                     7.5, // 1k characters -> $0.015
+	"tts-1-hd":                       15,  // 1k characters -> $0.03
+	"tts-1-hd-1106":                  15,  // 1k characters -> $0.03
+	"davinci":                        10,
+	"curie":                          10,
+	"babbage":                        10,
+	"ada":                            10,
+	"text-embedding-3-small":         0.01,
+	"text-embedding-3-large":         0.065,
+	"text-embedding-ada-002":         0.05,
+	"text-search-ada-doc-001":        10,
+	"text-moderation-stable":         0.1,
+	"text-moderation-latest":         0.1,
+	"claude-instant-1":               0.4,   // $0.8 / 1M tokens
+	"claude-2.0":                     4,     // $8 / 1M tokens
+	"claude-2.1":                     4,     // $8 / 1M tokens
+	"claude-3-haiku-20240307":        0.125, // $0.25 / 1M tokens
+	"claude-3-5-sonnet-20240620":     1.5,   // $3 / 1M tokens
+	"claude-3-sonnet-20240229":       1.5,   // $3 / 1M tokens
+	"claude-3-opus-20240229":         7.5,   // $15 / 1M tokens
+	"ERNIE-4.0-8K":                   0.120 * RMB,
+	"ERNIE-3.5-8K":                   0.012 * RMB,
+	"ERNIE-3.5-8K-0205":              0.024 * RMB,
+	"ERNIE-3.5-8K-1222":              0.012 * RMB,
+	"ERNIE-Bot-8K":                   0.024 * RMB,
+	"ERNIE-3.5-4K-0205":              0.012 * RMB,
+	"ERNIE-Speed-8K":                 0.004 * RMB,
+	"ERNIE-Speed-128K":               0.004 * RMB,
+	"ERNIE-Lite-8K-0922":             0.008 * RMB,
+	"ERNIE-Lite-8K-0308":             0.003 * RMB,
+	"ERNIE-Tiny-8K":                  0.001 * RMB,
+	"BLOOMZ-7B":                      0.004 * RMB,
+	"Embedding-V1":                   0.002 * RMB,
+	"bge-large-zh":                   0.002 * RMB,
+	"bge-large-en":                   0.002 * RMB,
+	"tao-8k":                         0.002 * RMB,
+	"PaLM-2":                         1,
+	"gemini-pro":                     1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
+	"gemini-pro-vision":              1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
+	"gemini-1.0-pro-vision-001":      1,
+	"gemini-1.0-pro-001":             1,
+	"gemini-1.5-pro-latest":          1.75, // $3.5 / 1M tokens
+	"gemini-1.5-pro-exp-0827":        1.75, // $3.5 / 1M tokens
+	"gemini-1.5-flash-latest":        1,
+	"gemini-1.5-flash-exp-0827":      1,
+	"gemini-1.0-pro-latest":          1,
+	"gemini-1.0-pro-vision-latest":   1,
+	"gemini-ultra":                   1,
+	"chatglm_turbo":                  0.3572,     // ￥0.005 / 1k tokens
+	"chatglm_pro":                    0.7143,     // ￥0.01 / 1k tokens
+	"chatglm_std":                    0.3572,     // ￥0.005 / 1k tokens
+	"chatglm_lite":                   0.1429,     // ￥0.002 / 1k tokens
+	"glm-4":                          7.143,      // ￥0.1 / 1k tokens
+	"glm-4v":                         0.05 * RMB, // ￥0.05 / 1k tokens
+	"glm-4-alltools":                 0.1 * RMB,  // ￥0.1 / 1k tokens
+	"glm-3-turbo":                    0.3572,
+	"glm-4-plus":                     0.05 * RMB,
+	"glm-4-0520":                     0.1 * RMB,
+	"glm-4-air":                      0.001 * RMB,
+	"glm-4-airx":                     0.01 * RMB,
+	"glm-4-long":                     0.001 * RMB,
+	"glm-4-flash":                    0,
+	"glm-4v-plus":                    0.01 * RMB,
+	"qwen-turbo":                     0.8572, // ￥0.012 / 1k tokens
+	"qwen-plus":                      10,     // ￥0.14 / 1k tokens
+	"text-embedding-v1":              0.05,   // ￥0.0007 / 1k tokens
+	"SparkDesk-v1.1":                 1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v2.1":                 1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v3.1":                 1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v3.5":                 1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v4.0":                 1.2858,
+	"360GPT_S2_V9":                   0.8572, // ¥0.012 / 1k tokens
+	"360gpt-turbo":                   0.0858, // ¥0.0012 / 1k tokens
+	"360gpt-turbo-responsibility-8k": 0.8572, // ¥0.012 / 1k tokens
+	"360gpt-pro":                     0.8572, // ¥0.012 / 1k tokens
+	"embedding-bert-512-v1":          0.0715, // ¥0.001 / 1k tokens
+	"embedding_s1_v1":                0.0715, // ¥0.001 / 1k tokens
+	"semantic_similarity_s1_v1":      0.0715, // ¥0.001 / 1k tokens
+	"hunyuan":                        7.143,  // ¥0.1 / 1k tokens  // https://cloud.tencent.com/document/product/1729/97731#e0e6be58-60c8-469f-bdeb-6c264ce3b4d0
 	// https://platform.lingyiwanwu.com/docs#-计费单元
 	// 已经按照 7.2 来换算美元价格
-	"yi-34b-chat-0205": 0.018,
-	"yi-34b-chat-200k": 0.0864,
-	"yi-vl-plus":       0.0432,
-	"command":               0.5,
-	"command-nightly":       0.5,
-	"command-light":         0.5,
-	"command-light-nightly": 0.5,
-	"command-r":             0.25,
-	"command-r-plus	":       1.5,
-	"deepseek-chat":         0.07,
-	"deepseek-coder":        0.07,
+	"yi-34b-chat-0205":       0.18,
+	"yi-34b-chat-200k":       0.864,
+	"yi-vl-plus":             0.432,
+	"yi-large":               20.0 / 1000 * RMB,
+	"yi-medium":              2.5 / 1000 * RMB,
+	"yi-vision":              6.0 / 1000 * RMB,
+	"yi-medium-200k":         12.0 / 1000 * RMB,
+	"yi-spark":               1.0 / 1000 * RMB,
+	"yi-large-rag":           25.0 / 1000 * RMB,
+	"yi-large-turbo":         12.0 / 1000 * RMB,
+	"yi-large-preview":       20.0 / 1000 * RMB,
+	"yi-large-rag-preview":   25.0 / 1000 * RMB,
+	"command":                0.5,
+	"command-nightly":        0.5,
+	"command-light":          0.5,
+	"command-light-nightly":  0.5,
+	"command-r":              0.25,
+	"command-r-plus":         1.5,
+	"command-r-08-2024":      0.075,
+	"command-r-plus-08-2024": 1.25,
+	"deepseek-chat":          0.07,
+	"deepseek-coder":         0.07,
+	// Perplexity online 模型对搜索额外收费，有需要应自行调整，此处不计入搜索费用
+	"llama-3-sonar-small-32k-chat":   0.2 / 1000 * USD,
+	"llama-3-sonar-small-32k-online": 0.2 / 1000 * USD,
+	"llama-3-sonar-large-32k-chat":   1 / 1000 * USD,
+	"llama-3-sonar-large-32k-online": 1 / 1000 * USD,
 }
 
-var DefaultModelPrice = map[string]float64{
+var defaultModelPrice = map[string]float64{
+	"suno_music":        0.1,
+	"suno_lyrics":       0.01,
+	"dall-e-2":          0.02,
+	"dall-e-3":          0.04,
 	"gpt-4-gizmo-*":     0.1,
+	"g-*":               0.1,
 	"mj_imagine":        0.1,
 	"mj_variation":      0.1,
 	"mj_reroll":         0.1,
@@ -133,16 +199,38 @@ var DefaultModelPrice = map[string]float64{
 	"mj_describe":       0.05,
 	"mj_upscale":        0.05,
 	"swap_face":         0.05,
+	"mj_upload":         0.05,
 }
 
-var modelPrice map[string]float64 = nil
-var modelRatio map[string]float64 = nil
+var (
+	modelPriceMap      map[string]float64 = nil
+	modelPriceMapMutex                    = sync.RWMutex{}
+)
+var (
+	modelRatioMap      map[string]float64 = nil
+	modelRatioMapMutex                    = sync.RWMutex{}
+)
+
+var CompletionRatio map[string]float64 = nil
+var defaultCompletionRatio = map[string]float64{
+	"gpt-4-gizmo-*": 2,
+	"g-*":           2,
+	"gpt-4-all":     2,
+	"gpt-4o-all":    2,
+}
+
+func GetModelPriceMap() map[string]float64 {
+	modelPriceMapMutex.Lock()
+	defer modelPriceMapMutex.Unlock()
+	if modelPriceMap == nil {
+		modelPriceMap = defaultModelPrice
+	}
+	return modelPriceMap
+}
 
 func ModelPrice2JSONString() string {
-	if modelPrice == nil {
-		modelPrice = DefaultModelPrice
-	}
-	jsonBytes, err := json.Marshal(modelPrice)
+	GetModelPriceMap()
+	jsonBytes, err := json.Marshal(modelPriceMap)
 	if err != nil {
 		SysError("error marshalling model price: " + err.Error())
 	}
@@ -150,32 +238,42 @@ func ModelPrice2JSONString() string {
 }
 
 func UpdateModelPriceByJSONString(jsonStr string) error {
-	modelPrice = make(map[string]float64)
-	return json.Unmarshal([]byte(jsonStr), &modelPrice)
+	modelPriceMapMutex.Lock()
+	defer modelPriceMapMutex.Unlock()
+	modelPriceMap = make(map[string]float64)
+	return json.Unmarshal([]byte(jsonStr), &modelPriceMap)
 }
 
-func GetModelPrice(name string, printErr bool) float64 {
-	if modelPrice == nil {
-		modelPrice = DefaultModelPrice
-	}
+// GetModelPrice 返回模型的价格，如果模型不存在则返回-1，false
+func GetModelPrice(name string, printErr bool) (float64, bool) {
+	GetModelPriceMap()
 	if strings.HasPrefix(name, "gpt-4-gizmo") {
 		name = "gpt-4-gizmo-*"
+	} else if strings.HasPrefix(name, "g-") {
+		name = "g-*"
 	}
-	price, ok := modelPrice[name]
+	price, ok := modelPriceMap[name]
 	if !ok {
 		if printErr {
 			SysError("model price not found: " + name)
 		}
-		return -1
+		return -1, false
 	}
-	return price
+	return price, true
+}
+
+func GetModelRatioMap() map[string]float64 {
+	modelRatioMapMutex.Lock()
+	defer modelRatioMapMutex.Unlock()
+	if modelRatioMap == nil {
+		modelRatioMap = defaultModelRatio
+	}
+	return modelRatioMap
 }
 
 func ModelRatio2JSONString() string {
-	if modelRatio == nil {
-		modelRatio = DefaultModelRatio
-	}
-	jsonBytes, err := json.Marshal(modelRatio)
+	GetModelRatioMap()
+	jsonBytes, err := json.Marshal(modelRatioMap)
 	if err != nil {
 		SysError("error marshalling model ratio: " + err.Error())
 	}
@@ -183,18 +281,20 @@ func ModelRatio2JSONString() string {
 }
 
 func UpdateModelRatioByJSONString(jsonStr string) error {
-	modelRatio = make(map[string]float64)
-	return json.Unmarshal([]byte(jsonStr), &modelRatio)
+	modelRatioMapMutex.Lock()
+	defer modelRatioMapMutex.Unlock()
+	modelRatioMap = make(map[string]float64)
+	return json.Unmarshal([]byte(jsonStr), &modelRatioMap)
 }
 
 func GetModelRatio(name string) float64 {
-	if modelRatio == nil {
-		modelRatio = DefaultModelRatio
-	}
+	GetModelRatioMap()
 	if strings.HasPrefix(name, "gpt-4-gizmo") {
 		name = "gpt-4-gizmo-*"
+	} else if strings.HasPrefix(name, "g-") {
+		name = "g-*"
 	}
-	ratio, ok := modelRatio[name]
+	ratio, ok := modelRatioMap[name]
 	if !ok {
 		SysError("model ratio not found: " + name)
 		return 30
@@ -202,7 +302,40 @@ func GetModelRatio(name string) float64 {
 	return ratio
 }
 
+func DefaultModelRatio2JSONString() string {
+	jsonBytes, err := json.Marshal(defaultModelRatio)
+	if err != nil {
+		SysError("error marshalling model ratio: " + err.Error())
+	}
+	return string(jsonBytes)
+}
+
+func GetDefaultModelRatioMap() map[string]float64 {
+	return defaultModelRatio
+}
+
+func CompletionRatio2JSONString() string {
+	if CompletionRatio == nil {
+		CompletionRatio = defaultCompletionRatio
+	}
+	jsonBytes, err := json.Marshal(CompletionRatio)
+	if err != nil {
+		SysError("error marshalling completion ratio: " + err.Error())
+	}
+	return string(jsonBytes)
+}
+
+func UpdateCompletionRatioByJSONString(jsonStr string) error {
+	CompletionRatio = make(map[string]float64)
+	return json.Unmarshal([]byte(jsonStr), &CompletionRatio)
+}
+
 func GetCompletionRatio(name string) float64 {
+	if strings.HasPrefix(name, "gpt-4-gizmo") {
+		name = "gpt-4-gizmo-*"
+	} else if strings.HasPrefix(name, "g-") {
+		name = "g-*"
+	}
 	if strings.HasPrefix(name, "gpt-3.5") {
 		if strings.HasSuffix(name, "0125") {
 			return 3
@@ -214,14 +347,25 @@ func GetCompletionRatio(name string) float64 {
 			return 3
 		}
 
-		return 1.333333
+		return 4.0 / 3.0
 	}
-	if strings.HasPrefix(name, "gpt-4") {
-		if strings.HasSuffix(name, "preview") || strings.HasPrefix(name, "gpt-4-turbo") {
+	if strings.HasPrefix(name, "gpt-4") && name != "gpt-4-all" && name != "gpt-4-gizmo-*" {
+		if strings.HasSuffix(name, "preview") || strings.HasPrefix(name, "gpt-4-turbo") || "gpt-4o-2024-05-13" == name {
 			return 3
 		}
+
+		if strings.HasPrefix(name, "gpt-4o") {
+			return 4
+		}
+
 		return 2
 	}
+	if "o1" == name || strings.HasPrefix(name, "o1-") {
+		return 4
+	}
+	if name == "chatgpt-4o-latest" {
+		return 3
+	}
 	if strings.HasPrefix(name, "claude-instant-1") {
 		return 3
 	} else if strings.HasPrefix(name, "claude-2") {
@@ -233,7 +377,7 @@ func GetCompletionRatio(name string) float64 {
 		return 3
 	}
 	if strings.HasPrefix(name, "gemini-") {
-		return 3
+		return 4
 	}
 	if strings.HasPrefix(name, "command") {
 		switch name {
@@ -241,6 +385,10 @@ func GetCompletionRatio(name string) float64 {
 			return 3
 		case "command-r-plus":
 			return 5
+		case "command-r-08-2024":
+			return 4
+		case "command-r-plus-08-2024":
+			return 4
 		default:
 			return 2
 		}
@@ -248,9 +396,32 @@ func GetCompletionRatio(name string) float64 {
 	if strings.HasPrefix(name, "deepseek") {
 		return 2
 	}
+	if strings.HasPrefix(name, "ERNIE-Speed-") {
+		return 2
+	} else if strings.HasPrefix(name, "ERNIE-Lite-") {
+		return 2
+	} else if strings.HasPrefix(name, "ERNIE-Character") {
+		return 2
+	} else if strings.HasPrefix(name, "ERNIE-Functions") {
+		return 2
+	}
 	switch name {
 	case "llama2-70b-4096":
-		return 0.8 / 0.7
+		return 0.8 / 0.64
+	case "llama3-8b-8192":
+		return 2
+	case "llama3-70b-8192":
+		return 0.79 / 0.59
+	}
+	if ratio, ok := CompletionRatio[name]; ok {
+		return ratio
 	}
 	return 1
 }
+
+func GetCompletionRatioMap() map[string]float64 {
+	if CompletionRatio == nil {
+		CompletionRatio = defaultCompletionRatio
+	}
+	return CompletionRatio
+}

common/str.go

@@ -1,50 +1,70 @@
 package common
 
-func SundaySearch(text string, pattern string) bool {
-	// 计算偏移表
-	offset := make(map[rune]int)
-	for i, c := range pattern {
-		offset[c] = len(pattern) - i
+import (
+	"encoding/json"
+	"math/rand"
+	"strconv"
+	"unsafe"
+)
+
+func GetStringIfEmpty(str string, defaultValue string) string {
+	if str == "" {
+		return defaultValue
 	}
+	return str
+}
 
-	// 文本串长度和模式串长度
-	n, m := len(text), len(pattern)
+func GetRandomString(length int) string {
+	//rand.Seed(time.Now().UnixNano())
+	key := make([]byte, length)
+	for i := 0; i < length; i++ {
+		key[i] = keyChars[rand.Intn(len(keyChars))]
+	}
+	return string(key)
+}
 
-	// 主循环，i表示当前对齐的文本串位置
-	for i := 0; i <= n-m; {
-		// 检查子串
-		j := 0
-		for j < m && text[i+j] == pattern[j] {
-			j++
-		}
-		// 如果完全匹配，返回匹配位置
-		if j == m {
+func MapToJsonStr(m map[string]interface{}) string {
+	bytes, err := json.Marshal(m)
+	if err != nil {
+		return ""
+	}
+	return string(bytes)
+}
+
+func StrToMap(str string) map[string]interface{} {
+	m := make(map[string]interface{})
+	err := json.Unmarshal([]byte(str), &m)
+	if err != nil {
+		return nil
+	}
+	return m
+}
+
+func IsJsonStr(str string) bool {
+	var js map[string]interface{}
+	return json.Unmarshal([]byte(str), &js) == nil
+}
+
+func String2Int(str string) int {
+	num, err := strconv.Atoi(str)
+	if err != nil {
+		return 0
+	}
+	return num
+}
+
+func StringsContains(strs []string, str string) bool {
+	for _, s := range strs {
+		if s == str {
 			return true
 		}
-
-		// 如果还有剩余字符，则检查下一位字符在偏移表中的值
-		if i+m < n {
-			next := rune(text[i+m])
-			if val, ok := offset[next]; ok {
-				i += val // 存在于偏移表中，进行跳跃
-			} else {
-				i += len(pattern) + 1 // 不存在于偏移表中，跳过整个模式串长度
-			}
-		} else {
-			break
-		}
 	}
-	return false // 如果没有找到匹配，返回-1
+	return false
 }
 
-func RemoveDuplicate(s []string) []string {
-	result := make([]string, 0, len(s))
-	temp := map[string]struct{}{}
-	for _, item := range s {
-		if _, ok := temp[item]; !ok {
-			temp[item] = struct{}{}
-			result = append(result, item)
-		}
-	}
-	return result
+// StringToByteSlice []byte only read, panic on append
+func StringToByteSlice(s string) []byte {
+	tmp1 := (*[2]uintptr)(unsafe.Pointer(&s))
+	tmp2 := [3]uintptr{tmp1[0], tmp1[1], tmp1[1]}
+	return *(*[]byte)(unsafe.Pointer(&tmp2))
 }

common/topup-ratio.go

@@ -1,6 +1,8 @@
 package common
 
-import "encoding/json"
+import (
+	"encoding/json"
+)
 
 var TopupGroupRatio = map[string]float64{
 	"default": 1,

common/user_groups.go

@@ -0,0 +1,28 @@
+package common
+
+import (
+	"encoding/json"
+)
+
+var UserUsableGroups = map[string]string{
+	"default": "默认分组",
+	"vip":     "vip分组",
+}
+
+func UserUsableGroups2JSONString() string {
+	jsonBytes, err := json.Marshal(UserUsableGroups)
+	if err != nil {
+		SysError("error marshalling user groups: " + err.Error())
+	}
+	return string(jsonBytes)
+}
+
+func UpdateUserUsableGroupsByJSONString(jsonStr string) error {
+	UserUsableGroups = make(map[string]string)
+	return json.Unmarshal([]byte(jsonStr), &UserUsableGroups)
+}
+
+func GroupInUserUsableGroups(groupName string) bool {
+	_, ok := UserUsableGroups[groupName]
+	return ok
+}

common/utils.go

@@ -1,19 +1,25 @@
 package common
 
 import (
+	"context"
+	"errors"
+	crand "crypto/rand"
+	"encoding/base64"
 	"fmt"
 	"github.com/google/uuid"
+	"golang.org/x/net/proxy"
 	"html/template"
 	"log"
+	"math/big"
 	"math/rand"
 	"net"
-	"os"
+	"net/http"
+	"net/url"
 	"os/exec"
 	"runtime"
 	"strconv"
 	"strings"
 	"time"
-	"unsafe"
 )
 
 func OpenBrowser(url string) {
@@ -130,6 +136,11 @@ func IntMax(a int, b int) int {
 	}
 }
 
+func IsIP(s string) bool {
+	ip := net.ParseIP(s)
+	return ip != nil
+}
+
 func GetUUID() string {
 	code := uuid.New().String()
 	code = strings.Replace(code, "-", "", -1)
@@ -139,33 +150,35 @@ func GetUUID() string {
 const keyChars = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"
 
 func init() {
-	rand.Seed(time.Now().UnixNano())
+	rand.New(rand.NewSource(time.Now().UnixNano()))
 }
 
-func GenerateKey() string {
-	//rand.Seed(time.Now().UnixNano())
-	key := make([]byte, 48)
-	for i := 0; i < 16; i++ {
-		key[i] = keyChars[rand.Intn(len(keyChars))]
-	}
-	uuid_ := GetUUID()
-	for i := 0; i < 32; i++ {
-		c := uuid_[i]
-		if i%2 == 0 && c >= 'a' && c <= 'z' {
-			c = c - 'a' + 'A'
+func GenerateRandomCharsKey(length int) (string, error) {
+	b := make([]byte, length)
+	maxI := big.NewInt(int64(len(keyChars)))
+
+	for i := range b {
+		n, err := crand.Int(crand.Reader, maxI)
+		if err != nil {
+			return "", err
 		}
-		key[i+16] = c
+		b[i] = keyChars[n.Int64()]
 	}
-	return string(key)
+
+	return string(b), nil
 }
 
-func GetRandomString(length int) string {
-	//rand.Seed(time.Now().UnixNano())
-	key := make([]byte, length)
-	for i := 0; i < length; i++ {
-		key[i] = keyChars[rand.Intn(len(keyChars))]
+func GenerateRandomKey(length int) (string, error) {
+	bytes := make([]byte, length*3/4) // 对于48位的输出，这里应该是36
+	if _, err := crand.Read(bytes); err != nil {
+		return "", err
 	}
-	return string(key)
+	return base64.StdEncoding.EncodeToString(bytes), nil
+}
+
+func GenerateKey() (string, error) {
+	//rand.Seed(time.Now().UnixNano())
+	return GenerateRandomCharsKey(48)
 }
 
 func GetRandomInt(max int) int {
@@ -190,54 +203,64 @@ func Max(a int, b int) int {
 	}
 }
 
-func GetOrDefault(env string, defaultValue int) int {
-	if env == "" || os.Getenv(env) == "" {
-		return defaultValue
-	}
-	num, err := strconv.Atoi(os.Getenv(env))
-	if err != nil {
-		SysError(fmt.Sprintf("failed to parse %s: %s, using default value: %d", env, err.Error(), defaultValue))
-		return defaultValue
-	}
-	return num
-}
-
-func GetOrDefaultString(env string, defaultValue string) string {
-	if env == "" || os.Getenv(env) == "" {
-		return defaultValue
-	}
-	return os.Getenv(env)
-}
-
 func MessageWithRequestId(message string, id string) string {
 	return fmt.Sprintf("%s (request id: %s)", message, id)
 }
 
-func String2Int(str string) int {
-	num, err := strconv.Atoi(str)
-	if err != nil {
-		return 0
-	}
-	return num
-}
-
-func StringsContains(strs []string, str string) bool {
-	for _, s := range strs {
-		if s == str {
-			return true
-		}
-	}
-	return false
-}
-
-// StringToByteSlice []byte only read, panic on append
-func StringToByteSlice(s string) []byte {
-	tmp1 := (*[2]uintptr)(unsafe.Pointer(&s))
-	tmp2 := [3]uintptr{tmp1[0], tmp1[1], tmp1[1]}
-	return *(*[]byte)(unsafe.Pointer(&tmp2))
-}
-
 func RandomSleep() {
 	// Sleep for 0-3000 ms
 	time.Sleep(time.Duration(rand.Intn(3000)) * time.Millisecond)
 }
+
+func GetProxiedHttpClient(proxyUrl string) (*http.Client, error) {
+	if "" == proxyUrl {
+		return &http.Client{}, nil
+	}
+
+	u, err := url.Parse(proxyUrl)
+	if err != nil {
+		return nil, err
+	}
+
+	if strings.HasPrefix(proxyUrl, "http") {
+
+		return &http.Client{
+			Transport: &http.Transport{
+				Proxy: http.ProxyURL(u),
+			},
+		}, nil
+	} else if strings.HasPrefix(proxyUrl, "socks") {
+		dialer, err := proxy.FromURL(u, proxy.Direct)
+		if err != nil {
+			return nil, err
+		}
+
+		return &http.Client{
+			Transport: &http.Transport{
+				DialContext: func(ctx context.Context, network, addr string) (net.Conn, error) {
+					return dialer.(proxy.ContextDialer).DialContext(ctx, network, addr)
+				},
+			},
+		}, nil
+	}
+
+	return nil, errors.New("unsupported proxy type")
+}
+
+func ProxiedHttpGet(url, proxyUrl string) (*http.Response, error) {
+	client, err := GetProxiedHttpClient(proxyUrl)
+	if err != nil {
+		return nil, err
+	}
+
+	return client.Get(url)
+}
+
+func ProxiedHttpHead(url, proxyUrl string) (*http.Response, error) {
+	client, err := GetProxiedHttpClient(proxyUrl)
+	if err != nil {
+		return nil, err
+	}
+
+	return client.Head(url)
+}

constant/chat.go

@@ -0,0 +1,35 @@
+package constant
+
+import (
+	"encoding/json"
+	"one-api/common"
+)
+
+var Chats = []map[string]string{
+	{
+		"ChatGPT Next Web 官方示例": "https://app.nextchat.dev/#/?settings={\"key\":\"{key}\",\"url\":\"{address}\"}",
+	},
+	{
+		"Lobe Chat 官方示例": "https://chat-preview.lobehub.com/?settings={\"keyVaults\":{\"openai\":{\"apiKey\":\"{key}\",\"baseURL\":\"{address}/v1\"}}}",
+	},
+	{
+		"AMA 问天": "ama://set-api-key?server={address}&key={key}",
+	},
+	{
+		"OpenCat": "opencat://team/join?domain={address}&token={key}",
+	},
+}
+
+func UpdateChatsByJsonString(jsonString string) error {
+	Chats = make([]map[string]string, 0)
+	return json.Unmarshal([]byte(jsonString), &Chats)
+}
+
+func Chats2JsonString() string {
+	jsonBytes, err := json.Marshal(Chats)
+	if err != nil {
+		common.SysError("error marshalling chats: " + err.Error())
+		return "[]"
+	}
+	return string(jsonBytes)
+}

constant/env.go

@@ -0,0 +1,51 @@
+package constant
+
+import (
+	"fmt"
+	"one-api/common"
+	"os"
+	"strings"
+)
+
+var StreamingTimeout = common.GetEnvOrDefault("STREAMING_TIMEOUT", 30)
+var DifyDebug = common.GetEnvOrDefaultBool("DIFY_DEBUG", true)
+
+// ForceStreamOption 覆盖请求参数，强制返回usage信息
+var ForceStreamOption = common.GetEnvOrDefaultBool("FORCE_STREAM_OPTION", true)
+
+var GetMediaToken = common.GetEnvOrDefaultBool("GET_MEDIA_TOKEN", true)
+
+var GetMediaTokenNotStream = common.GetEnvOrDefaultBool("GET_MEDIA_TOKEN_NOT_STREAM", true)
+
+var UpdateTask = common.GetEnvOrDefaultBool("UPDATE_TASK", true)
+
+var GeminiModelMap = map[string]string{
+	"gemini-1.5-pro-latest":     "v1beta",
+	"gemini-1.5-pro-001":        "v1beta",
+	"gemini-1.5-pro":            "v1beta",
+	"gemini-1.5-pro-exp-0801":   "v1beta",
+	"gemini-1.5-pro-exp-0827":   "v1beta",
+	"gemini-1.5-flash-latest":   "v1beta",
+	"gemini-1.5-flash-exp-0827": "v1beta",
+	"gemini-1.5-flash-001":      "v1beta",
+	"gemini-1.5-flash":          "v1beta",
+	"gemini-ultra":              "v1beta",
+}
+
+func InitEnv() {
+	modelVersionMapStr := strings.TrimSpace(os.Getenv("GEMINI_MODEL_MAP"))
+	if modelVersionMapStr == "" {
+		return
+	}
+	for _, pair := range strings.Split(modelVersionMapStr, ",") {
+		parts := strings.Split(pair, ":")
+		if len(parts) == 2 {
+			GeminiModelMap[parts[0]] = parts[1]
+		} else {
+			common.SysError(fmt.Sprintf("invalid model version map: %s", pair))
+		}
+	}
+}
+
+// 是否生成初始令牌，默认关闭。
+var GenerateDefaultToken = common.GetEnvOrDefaultBool("GENERATE_DEFAULT_TOKEN", false)

constant/midjourney.go

@@ -4,6 +4,7 @@ var MjNotifyEnabled = false
 var MjAccountFilterEnabled = false
 var MjModeClearEnabled = false
 var MjForwardUrlEnabled = true
+var MjActionCheckSuccessEnabled = true
 
 const (
 	MjErrorUnknown = 5
@@ -26,6 +27,7 @@ const (
 	MjActionLowVariation  = "LOW_VARIATION"
 	MjActionPan           = "PAN"
 	MjActionSwapFace      = "SWAP_FACE"
+	MjActionUpload        = "UPLOAD"
 )
 
 var MidjourneyModel2Action = map[string]string{
@@ -44,4 +46,5 @@ var MidjourneyModel2Action = map[string]string{
 	"mj_low_variation":  MjActionLowVariation,
 	"mj_pan":            MjActionPan,
 	"swap_face":         MjActionSwapFace,
+	"mj_upload":         MjActionUpload,
 }

constant/sensitive.go

@@ -16,7 +16,7 @@ var StreamCacheQueueLength = 0
 // SensitiveWords 敏感词
 // var SensitiveWords []string
 var SensitiveWords = []string{
-	"test",
+	"test_sensitive",
 }
 
 func SensitiveWordsToString() string {

constant/task.go

@@ -0,0 +1,18 @@
+package constant
+
+type TaskPlatform string
+
+const (
+	TaskPlatformSuno       TaskPlatform = "suno"
+	TaskPlatformMidjourney              = "mj"
+)
+
+const (
+	SunoActionMusic  = "MUSIC"
+	SunoActionLyrics = "LYRICS"
+)
+
+var SunoModel2Action = map[string]string{
+	"suno_music":  SunoActionMusic,
+	"suno_lyrics": SunoActionLyrics,
+}

controller/channel-test.go

@@ -5,28 +5,36 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"github.com/bytedance/gopkg/util/gopool"
 	"io"
+	"math"
 	"net/http"
 	"net/http/httptest"
 	"net/url"
 	"one-api/common"
 	"one-api/dto"
+	"one-api/middleware"
 	"one-api/model"
 	"one-api/relay"
 	relaycommon "one-api/relay/common"
 	"one-api/relay/constant"
 	"one-api/service"
 	"strconv"
+	"strings"
 	"sync"
 	"time"
 
 	"github.com/gin-gonic/gin"
 )
 
-func testChannel(channel *model.Channel, testModel string) (err error, openaiErr *dto.OpenAIError) {
+func testChannel(channel *model.Channel, testModel string) (err error, openAIErrorWithStatusCode *dto.OpenAIErrorWithStatusCode) {
+	tik := time.Now()
 	if channel.Type == common.ChannelTypeMidjourney {
 		return errors.New("midjourney channel test is not supported"), nil
 	}
+	if channel.Type == common.ChannelTypeSunoAPI {
+		return errors.New("suno channel test is not supported"), nil
+	}
 	w := httptest.NewRecorder()
 	c, _ := gin.CreateTestContext(w)
 	c.Request = &http.Request{
@@ -35,44 +43,52 @@ func testChannel(channel *model.Channel, testModel string) (err error, openaiErr
 		Body:   nil,
 		Header: make(http.Header),
 	}
-	c.Request.Header.Set("Authorization", "Bearer "+channel.Key)
-	c.Request.Header.Set("Content-Type", "application/json")
-	c.Set("channel", channel.Type)
-	c.Set("base_url", channel.GetBaseURL())
-	switch channel.Type {
-	case common.ChannelTypeAzure:
-		c.Set("api_version", channel.Other)
-	case common.ChannelTypeXunfei:
-		c.Set("api_version", channel.Other)
-	//case common.ChannelTypeAIProxyLibrary:
-	//	c.Set("library_id", channel.Other)
-	case common.ChannelTypeGemini:
-		c.Set("api_version", channel.Other)
-	case common.ChannelTypeAli:
-		c.Set("plugin", channel.Other)
-	}
 
-	meta := relaycommon.GenRelayInfo(c)
-	apiType := constant.ChannelType2APIType(channel.Type)
-	adaptor := relay.GetAdaptor(apiType)
-	if adaptor == nil {
-		return fmt.Errorf("invalid api type: %d, adaptor is nil", apiType), nil
-	}
 	if testModel == "" {
 		if channel.TestModel != nil && *channel.TestModel != "" {
 			testModel = *channel.TestModel
 		} else {
-			testModel = adaptor.GetModelList()[0]
+			if len(channel.GetModels()) > 0 {
+				testModel = channel.GetModels()[0]
+			} else {
+				testModel = "gpt-3.5-turbo"
+			}
+		}
+	} else {
+		modelMapping := *channel.ModelMapping
+		if modelMapping != "" && modelMapping != "{}" {
+			modelMap := make(map[string]string)
+			err := json.Unmarshal([]byte(modelMapping), &modelMap)
+			if err != nil {
+				return err, service.OpenAIErrorWrapperLocal(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError)
+			}
+			if modelMap[testModel] != "" {
+				testModel = modelMap[testModel]
+			}
 		}
 	}
-	request := buildTestRequest()
-	request.Model = testModel
+
+	c.Request.Header.Set("Authorization", "Bearer "+channel.Key)
+	c.Request.Header.Set("Content-Type", "application/json")
+	c.Set("channel", channel.Type)
+	c.Set("base_url", channel.GetBaseURL())
+
+	middleware.SetupContextForSelectedChannel(c, channel, testModel)
+
+	meta := relaycommon.GenRelayInfo(c)
+	apiType, _ := constant.ChannelType2APIType(channel.Type)
+	adaptor := relay.GetAdaptor(apiType)
+	if adaptor == nil {
+		return fmt.Errorf("invalid api type: %d, adaptor is nil", apiType), nil
+	}
+
+	request := buildTestRequest(testModel)
 	meta.UpstreamModelName = testModel
 	common.SysLog(fmt.Sprintf("testing channel %d with model %s", channel.Id, testModel))
 
-	adaptor.Init(meta, *request)
+	adaptor.Init(meta)
 
-	convertedRequest, err := adaptor.ConvertRequest(c, constant.RelayModeChatCompletions, request)
+	convertedRequest, err := adaptor.ConvertRequest(c, meta, request)
 	if err != nil {
 		return err, nil
 	}
@@ -87,43 +103,66 @@ func testChannel(channel *model.Channel, testModel string) (err error, openaiErr
 		return err, nil
 	}
 	if resp != nil && resp.StatusCode != http.StatusOK {
-		err := relaycommon.RelayErrorHandler(resp)
-		return fmt.Errorf("status code %d: %s", resp.StatusCode, err.Error.Message), &err.Error
+		err := service.RelayErrorHandler(resp)
+		return fmt.Errorf("status code %d: %s", resp.StatusCode, err.Error.Message), err
 	}
 	usage, respErr := adaptor.DoResponse(c, resp, meta)
 	if respErr != nil {
-		return fmt.Errorf("%s", respErr.Error.Message), &respErr.Error
+		return fmt.Errorf("%s", respErr.Error.Message), respErr
 	}
 	if usage == nil {
 		return errors.New("usage is nil"), nil
 	}
 	result := w.Result()
-	// print result.Body
 	respBody, err := io.ReadAll(result.Body)
 	if err != nil {
 		return err, nil
 	}
+	modelPrice, usePrice := common.GetModelPrice(testModel, false)
+	modelRatio := common.GetModelRatio(testModel)
+	completionRatio := common.GetCompletionRatio(testModel)
+	ratio := modelRatio
+	quota := 0
+	if !usePrice {
+		quota = usage.PromptTokens + int(math.Round(float64(usage.CompletionTokens)*completionRatio))
+		quota = int(math.Round(float64(quota) * ratio))
+		if ratio != 0 && quota <= 0 {
+			quota = 1
+		}
+	} else {
+		quota = int(modelPrice * common.QuotaPerUnit)
+	}
+	tok := time.Now()
+	milliseconds := tok.Sub(tik).Milliseconds()
+	consumedTime := float64(milliseconds) / 1000.0
+	other := service.GenerateTextOtherInfo(c, meta, modelRatio, 1, completionRatio, modelPrice)
+	model.RecordConsumeLog(c, 1, channel.Id, usage.PromptTokens, usage.CompletionTokens, testModel, "模型测试", quota, "模型测试", 0, quota, int(consumedTime), false, other)
 	common.SysLog(fmt.Sprintf("testing channel #%d, response: \n%s", channel.Id, string(respBody)))
 	return nil, nil
 }
 
-func buildTestRequest() *dto.GeneralOpenAIRequest {
+func buildTestRequest(model string) *dto.GeneralOpenAIRequest {
 	testRequest := &dto.GeneralOpenAIRequest{
-		Model:     "", // this will be set later
-		MaxTokens: 1,
-		Stream:    false,
+		Model:  "", // this will be set later
+		Stream: false,
+	}
+	if "o1" == model || strings.HasPrefix(model, "o1-") {
+		testRequest.MaxCompletionTokens = 1
+	} else {
+		testRequest.MaxTokens = 1
 	}
 	content, _ := json.Marshal("hi")
 	testMessage := dto.Message{
 		Role:    "user",
 		Content: content,
 	}
+	testRequest.Model = model
 	testRequest.Messages = append(testRequest.Messages, testMessage)
 	return testRequest
 }
 
 func TestChannel(c *gin.Context) {
-	id, err := strconv.Atoi(c.Param("id"))
+	channelId, err := strconv.Atoi(c.Param("id"))
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -131,7 +170,7 @@ func TestChannel(c *gin.Context) {
 		})
 		return
 	}
-	channel, err := model.GetChannelById(id, true)
+	channel, err := model.GetChannelById(channelId, true)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -184,33 +223,38 @@ func testAllChannels(notify bool) error {
 	if disableThreshold == 0 {
 		disableThreshold = 10000000 // a impossible value
 	}
-	go func() {
+	gopool.Go(func() {
 		for _, channel := range channels {
 			isChannelEnabled := channel.Status == common.ChannelStatusEnabled
 			tik := time.Now()
-			err, openaiErr := testChannel(channel, "")
+			err, openaiWithStatusErr := testChannel(channel, "")
 			tok := time.Now()
 			milliseconds := tok.Sub(tik).Milliseconds()
 
-			ban := false
+			shouldBanChannel := false
+
+			// request error disables the channel
+			if openaiWithStatusErr != nil {
+				oaiErr := openaiWithStatusErr.Error
+				err = errors.New(fmt.Sprintf("type %s, httpCode %d, code %v, message %s", oaiErr.Type, openaiWithStatusErr.StatusCode, oaiErr.Code, oaiErr.Message))
+				shouldBanChannel = service.ShouldDisableChannel(channel.Type, openaiWithStatusErr)
+			}
+
 			if milliseconds > disableThreshold {
 				err = errors.New(fmt.Sprintf("响应时间 %.2fs 超过阈值 %.2fs", float64(milliseconds)/1000.0, float64(disableThreshold)/1000.0))
-				ban = true
+				shouldBanChannel = true
 			}
-			if openaiErr != nil {
-				err = errors.New(fmt.Sprintf("type %s, code %v, message %s", openaiErr.Type, openaiErr.Code, openaiErr.Message))
-				ban = true
-			}
-			// parse *int to bool
-			if channel.AutoBan != nil && *channel.AutoBan == 0 {
-				ban = false
-			}
-			if isChannelEnabled && service.ShouldDisableChannel(openaiErr, -1) && ban {
+
+			// disable channel
+			if isChannelEnabled && shouldBanChannel && channel.GetAutoBan() {
 				service.DisableChannel(channel.Id, channel.Name, err.Error())
 			}
-			if !isChannelEnabled && service.ShouldEnableChannel(err, openaiErr) {
+
+			// enable channel
+			if !isChannelEnabled && service.ShouldEnableChannel(err, openaiWithStatusErr, channel.Status) {
 				service.EnableChannel(channel.Id, channel.Name)
 			}
+
 			channel.UpdateResponseTime(milliseconds)
 			time.Sleep(common.RequestInterval)
 		}
@@ -223,7 +267,7 @@ func testAllChannels(notify bool) error {
 				common.SysError(fmt.Sprintf("failed to send email: %s", err.Error()))
 			}
 		}
-	}()
+	})
 	return nil
 }
 

controller/channel.go

@@ -1,6 +1,8 @@
 package controller
 
 import (
+	"encoding/json"
+	"fmt"
 	"github.com/gin-gonic/gin"
 	"net/http"
 	"one-api/common"
@@ -9,6 +11,34 @@ import (
 	"strings"
 )
 
+type OpenAIModel struct {
+	ID         string `json:"id"`
+	Object     string `json:"object"`
+	Created    int64  `json:"created"`
+	OwnedBy    string `json:"owned_by"`
+	Permission []struct {
+		ID                 string `json:"id"`
+		Object             string `json:"object"`
+		Created            int64  `json:"created"`
+		AllowCreateEngine  bool   `json:"allow_create_engine"`
+		AllowSampling      bool   `json:"allow_sampling"`
+		AllowLogprobs      bool   `json:"allow_logprobs"`
+		AllowSearchIndices bool   `json:"allow_search_indices"`
+		AllowView          bool   `json:"allow_view"`
+		AllowFineTuning    bool   `json:"allow_fine_tuning"`
+		Organization       string `json:"organization"`
+		Group              string `json:"group"`
+		IsBlocking         bool   `json:"is_blocking"`
+	} `json:"permission"`
+	Root   string `json:"root"`
+	Parent string `json:"parent"`
+}
+
+type OpenAIModelsResponse struct {
+	Data    []OpenAIModel `json:"data"`
+	Success bool          `json:"success"`
+}
+
 func GetAllChannels(c *gin.Context) {
 	p, _ := strconv.Atoi(c.Query("p"))
 	pageSize, _ := strconv.Atoi(c.Query("page_size"))
@@ -35,6 +65,65 @@ func GetAllChannels(c *gin.Context) {
 	return
 }
 
+func FetchUpstreamModels(c *gin.Context) {
+	id, err := strconv.Atoi(c.Param("id"))
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	channel, err := model.GetChannelById(id, true)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	if channel.Type != common.ChannelTypeOpenAI {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "仅支持 OpenAI 类型渠道",
+		})
+		return
+	}
+	url := fmt.Sprintf("%s/v1/models", *channel.BaseURL)
+	body, err := GetResponseBody("GET", url, channel, GetAuthHeader(channel.Key))
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+	}
+	result := OpenAIModelsResponse{}
+	err = json.Unmarshal(body, &result)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+	}
+	if !result.Success {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "上游返回错误",
+		})
+	}
+
+	var ids []string
+	for _, model := range result.Data {
+		ids = append(ids, model.ID)
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+		"data":    ids,
+	})
+}
+
 func FixChannelsAbilities(c *gin.Context) {
 	count, err := model.FixAbility()
 	if err != nil {
@@ -109,6 +198,28 @@ func AddChannel(c *gin.Context) {
 	}
 	channel.CreatedTime = common.GetTimestamp()
 	keys := strings.Split(channel.Key, "\n")
+	if channel.Type == common.ChannelTypeVertexAi {
+		if channel.Other == "" {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "部署地区不能为空",
+			})
+			return
+		} else {
+			if common.IsJsonStr(channel.Other) {
+				// must have default
+				regionMap := common.StrToMap(channel.Other)
+				if regionMap["default"] == nil {
+					c.JSON(http.StatusOK, gin.H{
+						"success": false,
+						"message": "部署地区必须包含default字段",
+					})
+					return
+				}
+			}
+		}
+		keys = []string{channel.Key}
+	}
 	channels := make([]model.Channel, 0, len(keys))
 	for _, key := range keys {
 		if key == "" {
@@ -208,6 +319,27 @@ func UpdateChannel(c *gin.Context) {
 		})
 		return
 	}
+	if channel.Type == common.ChannelTypeVertexAi {
+		if channel.Other == "" {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "部署地区不能为空",
+			})
+			return
+		} else {
+			if common.IsJsonStr(channel.Other) {
+				// must have default
+				regionMap := common.StrToMap(channel.Other)
+				if regionMap["default"] == nil {
+					c.JSON(http.StatusOK, gin.H{
+						"success": false,
+						"message": "部署地区必须包含default字段",
+					})
+					return
+				}
+			}
+		}
+	}
 	err = channel.Update()
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{

controller/github.go

@@ -112,7 +112,9 @@ func GitHubOAuth(c *gin.Context) {
 	user := model.User{
 		GitHubId: githubUser.Login,
 	}
+	// IsGitHubIdAlreadyTaken is unscoped
 	if model.IsGitHubIdAlreadyTaken(user.GitHubId) {
+		// FillUserByGitHubId is scoped
 		err := user.FillUserByGitHubId()
 		if err != nil {
 			c.JSON(http.StatusOK, gin.H{
@@ -121,6 +123,14 @@ func GitHubOAuth(c *gin.Context) {
 			})
 			return
 		}
+		// if user.Id == 0 , user has been deleted
+		if user.Id == 0 {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "用户已注销",
+			})
+			return
+		}
 	} else {
 		if common.RegisterEnabled {
 			user.InviterId, _ = model.GetUserIdByAffCode(c.Query("aff"))

controller/group.go

@@ -17,3 +17,18 @@ func GetGroups(c *gin.Context) {
 		"data":    groupNames,
 	})
 }
+
+func GetUserGroups(c *gin.Context) {
+	usableGroups := make(map[string]string)
+	for groupName, _ := range common.GroupRatio {
+		// UserUsableGroups contains the groups that the user can use
+		if _, ok := common.UserUsableGroups[groupName]; ok {
+			usableGroups[groupName] = common.UserUsableGroups[groupName]
+		}
+	}
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+		"data":    usableGroups,
+	})
+}

controller/linuxdo.go

@@ -132,6 +132,14 @@ func LinuxDoOAuth(c *gin.Context) {
 			return
 		}
 
+		if user.Id == 0 {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "用户已注销",
+			})
+			return
+		}
+
 		user.LinuxDoLevel = linuxdoUser.TrustLevel
 		err = user.Update(false)
 		if err != nil {

controller/log.go

@@ -1,18 +1,19 @@
 package controller
 
 import (
-	"github.com/gin-gonic/gin"
 	"net/http"
 	"one-api/common"
 	"one-api/model"
 	"strconv"
+
+	"github.com/gin-gonic/gin"
 )
 
 func GetAllLogs(c *gin.Context) {
 	p, _ := strconv.Atoi(c.Query("p"))
 	pageSize, _ := strconv.Atoi(c.Query("page_size"))
-	if p < 0 {
-		p = 0
+	if p < 1 {
+		p = 1
 	}
 	if pageSize < 0 {
 		pageSize = common.ItemsPerPage
@@ -24,7 +25,7 @@ func GetAllLogs(c *gin.Context) {
 	tokenName := c.Query("token_name")
 	modelName := c.Query("model_name")
 	channel, _ := strconv.Atoi(c.Query("channel"))
-	logs, total, err := model.GetAllLogs(logType, startTimestamp, endTimestamp, modelName, username, tokenName, p*pageSize, pageSize, channel)
+	logs, total, err := model.GetAllLogs(logType, startTimestamp, endTimestamp, modelName, username, tokenName, (p-1)*pageSize, pageSize, channel)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -35,17 +36,20 @@ func GetAllLogs(c *gin.Context) {
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
-		"total":   total,
-		"data":    logs,
+		"data": map[string]any{
+			"items":     logs,
+			"total":     total,
+			"page":      p,
+			"page_size": pageSize,
+		},
 	})
-	return
 }
 
 func GetUserLogs(c *gin.Context) {
 	p, _ := strconv.Atoi(c.Query("p"))
 	pageSize, _ := strconv.Atoi(c.Query("page_size"))
-	if p < 0 {
-		p = 0
+	if p < 1 {
+		p = 1
 	}
 	if pageSize < 0 {
 		pageSize = common.ItemsPerPage
@@ -59,7 +63,7 @@ func GetUserLogs(c *gin.Context) {
 	endTimestamp, _ := strconv.ParseInt(c.Query("end_timestamp"), 10, 64)
 	tokenName := c.Query("token_name")
 	modelName := c.Query("model_name")
-	logs, total, err := model.GetUserLogs(userId, logType, startTimestamp, endTimestamp, modelName, tokenName, p*pageSize, pageSize)
+	logs, total, err := model.GetUserLogs(userId, logType, startTimestamp, endTimestamp, modelName, tokenName, (p-1)*pageSize, pageSize)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -70,8 +74,12 @@ func GetUserLogs(c *gin.Context) {
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
-		"total":   total,
-		"data":    logs,
+		"data": map[string]any{
+			"items":     logs,
+			"total":     total,
+			"page":      p,
+			"page_size": pageSize,
+		},
 	})
 	return
 }
@@ -184,7 +192,7 @@ func DeleteHistoryLogs(c *gin.Context) {
 		})
 		return
 	}
-	count, err := model.DeleteOldLog(targetTimestamp)
+	count, err := model.DeleteOldLog(c.Request.Context(), targetTimestamp, 100)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,

controller/midjourney.go

@@ -146,28 +146,26 @@ func UpdateMidjourneyTaskBulk() {
 					buttonStr, _ := json.Marshal(responseItem.Buttons)
 					task.Buttons = string(buttonStr)
 				}
-
+				shouldReturnQuota := false
 				if (task.Progress != "100%" && responseItem.FailReason != "") || (task.Progress == "100%" && task.Status == "FAILURE") {
 					common.LogInfo(ctx, task.MjId+" 构建失败，"+task.FailReason)
 					task.Progress = "100%"
-					err = model.CacheUpdateUserQuota(task.UserId)
-					if err != nil {
-						common.LogError(ctx, "error update user quota cache: "+err.Error())
-					} else {
-						quota := task.Quota
-						if quota != 0 {
-							err = model.IncreaseUserQuota(task.UserId, quota)
-							if err != nil {
-								common.LogError(ctx, "fail to increase user quota: "+err.Error())
-							}
-							logContent := fmt.Sprintf("构图失败 %s，补偿 %s", task.MjId, common.LogQuota(quota))
-							model.RecordLog(task.UserId, model.LogTypeSystem, logContent)
-						}
+					if task.Quota != 0 {
+						shouldReturnQuota = true
 					}
 				}
 				err = task.Update()
 				if err != nil {
 					common.LogError(ctx, "UpdateMidjourneyTask task error: "+err.Error())
+				} else {
+					if shouldReturnQuota {
+						err = model.IncreaseUserQuota(task.UserId, task.Quota)
+						if err != nil {
+							common.LogError(ctx, "fail to increase user quota: "+err.Error())
+						}
+						logContent := fmt.Sprintf("构图失败 %s，补偿 %s", task.MjId, common.LogQuota(task.Quota))
+						model.RecordLog(task.UserId, model.LogTypeSystem, logContent)
+					}
 				}
 			}
 		}

controller/misc.go

@@ -59,11 +59,13 @@ func GetStatus(c *gin.Context) {
 			"display_in_currency":      common.DisplayInCurrencyEnabled,
 			"enable_batch_update":      common.BatchUpdateEnabled,
 			"enable_drawing":           common.DrawingEnabled,
+			"enable_task":              common.TaskEnabled,
 			"enable_data_export":       common.DataExportEnabled,
 			"data_export_default_time": common.DataExportDefaultTime,
 			"default_collapse_sidebar": common.DefaultCollapseSidebar,
 			"payment_enabled":          common.PaymentEnabled,
 			"mj_notify_enabled":        constant.MjNotifyEnabled,
+			"chats":                    constant.Chats,
 		},
 	})
 	return
@@ -149,7 +151,7 @@ func SendEmailVerification(c *gin.Context) {
 		}
 	}
 	if common.EmailAliasRestrictionEnabled {
-		containsSpecialSymbols := strings.Contains(localPart, "+") || strings.Count(localPart, ".") > 1
+		containsSpecialSymbols := strings.Contains(localPart, "+") || strings.Contains(localPart, ".")
 		if containsSpecialSymbols {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,

controller/model.go

@@ -4,49 +4,28 @@ import (
 	"fmt"
 	"github.com/gin-gonic/gin"
 	"net/http"
+	"one-api/common"
 	"one-api/constant"
 	"one-api/dto"
 	"one-api/model"
 	"one-api/relay"
 	"one-api/relay/channel/ai360"
-	"one-api/relay/channel/moonshot"
 	"one-api/relay/channel/lingyiwanwu"
+	"one-api/relay/channel/minimax"
+	"one-api/relay/channel/moonshot"
+	relaycommon "one-api/relay/common"
 	relayconstant "one-api/relay/constant"
 )
 
 // https://platform.openai.com/docs/api-reference/models/list
 
-type OpenAIModelPermission struct {
-	Id                 string  `json:"id"`
-	Object             string  `json:"object"`
-	Created            int     `json:"created"`
-	AllowCreateEngine  bool    `json:"allow_create_engine"`
-	AllowSampling      bool    `json:"allow_sampling"`
-	AllowLogprobs      bool    `json:"allow_logprobs"`
-	AllowSearchIndices bool    `json:"allow_search_indices"`
-	AllowView          bool    `json:"allow_view"`
-	AllowFineTuning    bool    `json:"allow_fine_tuning"`
-	Organization       string  `json:"organization"`
-	Group              *string `json:"group"`
-	IsBlocking         bool    `json:"is_blocking"`
-}
+var openAIModels []dto.OpenAIModels
+var openAIModelsMap map[string]dto.OpenAIModels
+var channelId2Models map[int][]string
 
-type OpenAIModels struct {
-	Id         string                  `json:"id"`
-	Object     string                  `json:"object"`
-	Created    int                     `json:"created"`
-	OwnedBy    string                  `json:"owned_by"`
-	Permission []OpenAIModelPermission `json:"permission"`
-	Root       string                  `json:"root"`
-	Parent     *string                 `json:"parent"`
-}
-
-var openAIModels []OpenAIModels
-var openAIModelsMap map[string]OpenAIModels
-
-func init() {
-	var permission []OpenAIModelPermission
-	permission = append(permission, OpenAIModelPermission{
+func getPermission() []dto.OpenAIModelPermission {
+	var permission []dto.OpenAIModelPermission
+	permission = append(permission, dto.OpenAIModelPermission{
 		Id:                 "modelperm-LwHkVFn8AcMItP432fKKDIKJ",
 		Object:             "model_permission",
 		Created:            1626777600,
@@ -60,7 +39,12 @@ func init() {
 		Group:              nil,
 		IsBlocking:         false,
 	})
+	return permission
+}
+
+func init() {
 	// https://platform.openai.com/docs/models/model-endpoint-compatibility
+	permission := getPermission()
 	for i := 0; i < relayconstant.APITypeDummy; i++ {
 		if i == relayconstant.APITypeAIProxyLibrary {
 			continue
@@ -69,7 +53,7 @@ func init() {
 		channelName := adaptor.GetChannelName()
 		modelNames := adaptor.GetModelList()
 		for _, modelName := range modelNames {
-			openAIModels = append(openAIModels, OpenAIModels{
+			openAIModels = append(openAIModels, dto.OpenAIModels{
 				Id:         modelName,
 				Object:     "model",
 				Created:    1626777600,
@@ -81,40 +65,51 @@ func init() {
 		}
 	}
 	for _, modelName := range ai360.ModelList {
-		openAIModels = append(openAIModels, OpenAIModels{
+		openAIModels = append(openAIModels, dto.OpenAIModels{
 			Id:         modelName,
 			Object:     "model",
 			Created:    1626777600,
-			OwnedBy:    "360",
+			OwnedBy:    ai360.ChannelName,
 			Permission: permission,
 			Root:       modelName,
 			Parent:     nil,
 		})
 	}
 	for _, modelName := range moonshot.ModelList {
-		openAIModels = append(openAIModels, OpenAIModels{
+		openAIModels = append(openAIModels, dto.OpenAIModels{
 			Id:         modelName,
 			Object:     "model",
 			Created:    1626777600,
-			OwnedBy:    "moonshot",
+			OwnedBy:    moonshot.ChannelName,
 			Permission: permission,
 			Root:       modelName,
 			Parent:     nil,
 		})
 	}
 	for _, modelName := range lingyiwanwu.ModelList {
-		openAIModels = append(openAIModels, OpenAIModels{
+		openAIModels = append(openAIModels, dto.OpenAIModels{
 			Id:         modelName,
 			Object:     "model",
 			Created:    1626777600,
-			OwnedBy:    "lingyiwanwu",
+			OwnedBy:    lingyiwanwu.ChannelName,
+			Permission: permission,
+			Root:       modelName,
+			Parent:     nil,
+		})
+	}
+	for _, modelName := range minimax.ModelList {
+		openAIModels = append(openAIModels, dto.OpenAIModels{
+			Id:         modelName,
+			Object:     "model",
+			Created:    1626777600,
+			OwnedBy:    minimax.ChannelName,
 			Permission: permission,
 			Root:       modelName,
 			Parent:     nil,
 		})
 	}
 	for modelName, _ := range constant.MidjourneyModel2Action {
-		openAIModels = append(openAIModels, OpenAIModels{
+		openAIModels = append(openAIModels, dto.OpenAIModels{
 			Id:         modelName,
 			Object:     "model",
 			Created:    1626777600,
@@ -124,46 +119,107 @@ func init() {
 			Parent:     nil,
 		})
 	}
-	openAIModelsMap = make(map[string]OpenAIModels)
-	for _, model := range openAIModels {
-		openAIModelsMap[model.Id] = model
+	openAIModelsMap = make(map[string]dto.OpenAIModels)
+	for _, aiModel := range openAIModels {
+		openAIModelsMap[aiModel.Id] = aiModel
+	}
+	channelId2Models = make(map[int][]string)
+	for i := 1; i <= common.ChannelTypeDummy; i++ {
+		apiType, success := relayconstant.ChannelType2APIType(i)
+		if !success || apiType == relayconstant.APITypeAIProxyLibrary {
+			continue
+		}
+		meta := &relaycommon.RelayInfo{ChannelType: i}
+		adaptor := relay.GetAdaptor(apiType)
+		adaptor.Init(meta)
+		channelId2Models[i] = adaptor.GetModelList()
 	}
 }
 
 func ListModels(c *gin.Context) {
-	userId := c.GetInt("id")
-	user, err := model.GetUserById(userId, true)
-	if err != nil {
-		c.JSON(http.StatusOK, gin.H{
-			"success": false,
-			"message": err.Error(),
-		})
-		return
-	}
-	models := model.GetGroupModels(user.Group)
-	userOpenAiModels := make([]OpenAIModels, 0)
-	for _, s := range models {
-		if _, ok := openAIModelsMap[s]; ok {
-			userOpenAiModels = append(userOpenAiModels, openAIModelsMap[s])
+	userOpenAiModels := make([]dto.OpenAIModels, 0)
+	permission := getPermission()
+
+	modelLimitEnable := c.GetBool("token_model_limit_enabled")
+	if modelLimitEnable {
+		s, ok := c.Get("token_model_limit")
+		var tokenModelLimit map[string]bool
+		if ok {
+			tokenModelLimit = s.(map[string]bool)
+		} else {
+			tokenModelLimit = map[string]bool{}
+		}
+		for allowModel, _ := range tokenModelLimit {
+			if _, ok := openAIModelsMap[allowModel]; ok {
+				userOpenAiModels = append(userOpenAiModels, openAIModelsMap[allowModel])
+			} else {
+				userOpenAiModels = append(userOpenAiModels, dto.OpenAIModels{
+					Id:         allowModel,
+					Object:     "model",
+					Created:    1626777600,
+					OwnedBy:    "custom",
+					Permission: permission,
+					Root:       allowModel,
+					Parent:     nil,
+				})
+			}
+		}
+	} else {
+		userId := c.GetInt("id")
+		userGroup, err := model.GetUserGroup(userId)
+		if err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "get user group failed",
+			})
+			return
+		}
+		group := userGroup
+		tokenGroup := c.GetString("token_group")
+		if tokenGroup != "" {
+			group = tokenGroup
+		}
+		models := model.GetGroupModels(group)
+		for _, s := range models {
+			if _, ok := openAIModelsMap[s]; ok {
+				userOpenAiModels = append(userOpenAiModels, openAIModelsMap[s])
+			} else {
+				userOpenAiModels = append(userOpenAiModels, dto.OpenAIModels{
+					Id:         s,
+					Object:     "model",
+					Created:    1626777600,
+					OwnedBy:    "custom",
+					Permission: permission,
+					Root:       s,
+					Parent:     nil,
+				})
+			}
 		}
 	}
 	c.JSON(200, gin.H{
-		"object": "list",
-		"data":   userOpenAiModels,
+		"success": true,
+		"data":    userOpenAiModels,
 	})
 }
 
 func ChannelListModels(c *gin.Context) {
 	c.JSON(200, gin.H{
-		"object": "list",
-		"data":   openAIModels,
+		"success": true,
+		"data":    openAIModels,
+	})
+}
+
+func DashboardListModels(c *gin.Context) {
+	c.JSON(200, gin.H{
+		"success": true,
+		"data":    channelId2Models,
 	})
 }
 
 func RetrieveModel(c *gin.Context) {
 	modelId := c.Param("model")
-	if model, ok := openAIModelsMap[modelId]; ok {
-		c.JSON(200, model)
+	if aiModel, ok := openAIModelsMap[modelId]; ok {
+		c.JSON(200, aiModel)
 	} else {
 		openAIError := dto.OpenAIError{
 			Message: fmt.Sprintf("The model '%s' does not exist", modelId),

controller/pricing.go

@@ -0,0 +1,40 @@
+package controller
+
+import (
+	"github.com/gin-gonic/gin"
+	"one-api/common"
+	"one-api/model"
+)
+
+func GetPricing(c *gin.Context) {
+	pricing := model.GetPricing()
+	c.JSON(200, gin.H{
+		"success":     true,
+		"data":        pricing,
+		"group_ratio": common.GroupRatio,
+	})
+}
+
+func ResetModelRatio(c *gin.Context) {
+	defaultStr := common.DefaultModelRatio2JSONString()
+	err := model.UpdateOption("ModelRatio", defaultStr)
+	if err != nil {
+		c.JSON(200, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	err = common.UpdateModelRatioByJSONString(defaultStr)
+	if err != nil {
+		c.JSON(200, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	c.JSON(200, gin.H{
+		"success": true,
+		"message": "重置模型倍率成功",
+	})
+}

controller/relay.go

@@ -2,6 +2,7 @@ package controller
 
 import (
 	"bytes"
+	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
 	"io"
@@ -22,54 +23,104 @@ func relayHandler(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode
 	var err *dto.OpenAIErrorWithStatusCode
 	switch relayMode {
 	case relayconstant.RelayModeImagesGenerations:
-		err = relay.RelayImageHelper(c, relayMode)
+		err = relay.ImageHelper(c, relayMode)
 	case relayconstant.RelayModeAudioSpeech:
 		fallthrough
 	case relayconstant.RelayModeAudioTranslation:
 		fallthrough
 	case relayconstant.RelayModeAudioTranscription:
-		err = relay.AudioHelper(c, relayMode)
+		err = relay.AudioHelper(c)
+	case relayconstant.RelayModeRerank:
+		err = relay.RerankHelper(c, relayMode)
 	default:
 		err = relay.TextHelper(c)
 	}
 	return err
 }
 
+func Playground(c *gin.Context) {
+	var openaiErr *dto.OpenAIErrorWithStatusCode
+
+	defer func() {
+		if openaiErr != nil {
+			c.JSON(openaiErr.StatusCode, gin.H{
+				"error": openaiErr.Error,
+			})
+		}
+	}()
+
+	useAccessToken := c.GetBool("use_access_token")
+	if useAccessToken {
+		openaiErr = service.OpenAIErrorWrapperLocal(errors.New("暂不支持使用 access token"), "access_token_not_supported", http.StatusBadRequest)
+		return
+	}
+
+	playgroundRequest := &dto.PlayGroundRequest{}
+	err := common.UnmarshalBodyReusable(c, playgroundRequest)
+	if err != nil {
+		openaiErr = service.OpenAIErrorWrapperLocal(err, "unmarshal_request_failed", http.StatusBadRequest)
+		return
+	}
+
+	if playgroundRequest.Model == "" {
+		openaiErr = service.OpenAIErrorWrapperLocal(errors.New("请选择模型"), "model_required", http.StatusBadRequest)
+		return
+	}
+	c.Set("original_model", playgroundRequest.Model)
+	group := playgroundRequest.Group
+	userGroup := c.GetString("group")
+
+	if group == "" {
+		group = userGroup
+	} else {
+		if !common.GroupInUserUsableGroups(group) && group != userGroup {
+			openaiErr = service.OpenAIErrorWrapperLocal(errors.New("无权访问该分组"), "group_not_allowed", http.StatusForbidden)
+			return
+		}
+		c.Set("group", group)
+	}
+	c.Set("token_name", "playground-"+group)
+	channel, err := model.CacheGetRandomSatisfiedChannel(group, playgroundRequest.Model, 0)
+	if err != nil {
+		message := fmt.Sprintf("当前分组 %s 下对于模型 %s 无可用渠道", group, playgroundRequest.Model)
+		openaiErr = service.OpenAIErrorWrapperLocal(errors.New(message), "get_playground_channel_failed", http.StatusInternalServerError)
+		return
+	}
+	middleware.SetupContextForSelectedChannel(c, channel, playgroundRequest.Model)
+	Relay(c)
+}
+
 func Relay(c *gin.Context) {
 	relayMode := constant.Path2RelayMode(c.Request.URL.Path)
-	retryTimes := common.RetryTimes
 	requestId := c.GetString(common.RequestIdKey)
-	channelId := c.GetInt("channel_id")
 	group := c.GetString("group")
 	originalModel := c.GetString("original_model")
-	openaiErr := relayHandler(c, relayMode)
-	useChannel := []int{channelId}
-	if openaiErr != nil {
-		go processChannelError(c, channelId, openaiErr)
-	} else {
-		retryTimes = 0
-	}
-	for i := 0; shouldRetry(c, channelId, openaiErr, retryTimes) && i < retryTimes; i++ {
-		channel, err := model.CacheGetRandomSatisfiedChannel(group, originalModel, i)
+	var openaiErr *dto.OpenAIErrorWithStatusCode
+
+	for i := 0; i <= common.RetryTimes; i++ {
+		channel, err := getChannel(c, group, originalModel, i)
 		if err != nil {
-			common.LogError(c.Request.Context(), fmt.Sprintf("CacheGetRandomSatisfiedChannel failed: %s", err.Error()))
+			common.LogError(c, err.Error())
+			openaiErr = service.OpenAIErrorWrapperLocal(err, "get_channel_failed", http.StatusInternalServerError)
 			break
 		}
-		channelId = channel.Id
-		useChannel = append(useChannel, channelId)
-		common.LogInfo(c.Request.Context(), fmt.Sprintf("using channel #%d to retry (remain times %d)", channel.Id, i))
-		middleware.SetupContextForSelectedChannel(c, channel, originalModel)
 
-		requestBody, err := common.GetRequestBody(c)
-		c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
-		openaiErr = relayHandler(c, relayMode)
-		if openaiErr != nil {
-			go processChannelError(c, channelId, openaiErr)
+		openaiErr = relayRequest(c, relayMode, channel)
+
+		if openaiErr == nil {
+			return // 成功处理请求，直接返回
+		}
+
+		go processChannelError(c, channel.Id, channel.Type, channel.Name, channel.GetAutoBan(), openaiErr)
+
+		if !shouldRetry(c, openaiErr, common.RetryTimes-i) {
+			break
 		}
 	}
+	useChannel := c.GetStringSlice("use_channel")
 	if len(useChannel) > 1 {
 		retryLogStr := fmt.Sprintf("重试：%s", strings.Trim(strings.Join(strings.Fields(fmt.Sprint(useChannel)), "->"), "[]"))
-		common.LogInfo(c.Request.Context(), retryLogStr)
+		common.LogInfo(c, retryLogStr)
 	}
 
 	if openaiErr != nil {
@@ -83,10 +134,48 @@ func Relay(c *gin.Context) {
 	}
 }
 
-func shouldRetry(c *gin.Context, channelId int, openaiErr *dto.OpenAIErrorWithStatusCode, retryTimes int) bool {
+func relayRequest(c *gin.Context, relayMode int, channel *model.Channel) *dto.OpenAIErrorWithStatusCode {
+	addUsedChannel(c, channel.Id)
+	requestBody, _ := common.GetRequestBody(c)
+	c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
+	return relayHandler(c, relayMode)
+}
+
+func addUsedChannel(c *gin.Context, channelId int) {
+	useChannel := c.GetStringSlice("use_channel")
+	useChannel = append(useChannel, fmt.Sprintf("%d", channelId))
+	c.Set("use_channel", useChannel)
+}
+
+func getChannel(c *gin.Context, group, originalModel string, retryCount int) (*model.Channel, error) {
+	if retryCount == 0 {
+		autoBan := c.GetBool("auto_ban")
+		autoBanInt := 1
+		if !autoBan {
+			autoBanInt = 0
+		}
+		return &model.Channel{
+			Id:      c.GetInt("channel_id"),
+			Type:    c.GetInt("channel_type"),
+			Name:    c.GetString("channel_name"),
+			AutoBan: &autoBanInt,
+		}, nil
+	}
+	channel, err := model.CacheGetRandomSatisfiedChannel(group, originalModel, retryCount)
+	if err != nil {
+		return nil, errors.New(fmt.Sprintf("获取重试渠道失败: %s", err.Error()))
+	}
+	middleware.SetupContextForSelectedChannel(c, channel, originalModel)
+	return channel, nil
+}
+
+func shouldRetry(c *gin.Context, openaiErr *dto.OpenAIErrorWithStatusCode, retryTimes int) bool {
 	if openaiErr == nil {
 		return false
 	}
+	if openaiErr.LocalError {
+		return false
+	}
 	if retryTimes <= 0 {
 		return false
 	}
@@ -107,26 +196,27 @@ func shouldRetry(c *gin.Context, channelId int, openaiErr *dto.OpenAIErrorWithSt
 		return true
 	}
 	if openaiErr.StatusCode == http.StatusBadRequest {
+		channelType := c.GetInt("channel_type")
+		if channelType == common.ChannelTypeAnthropic {
+			return true
+		}
 		return false
 	}
 	if openaiErr.StatusCode == 408 {
 		// azure处理超时不重试
 		return false
 	}
-	if openaiErr.LocalError {
-		return false
-	}
 	if openaiErr.StatusCode/100 == 2 {
 		return false
 	}
 	return true
 }
 
-func processChannelError(c *gin.Context, channelId int, err *dto.OpenAIErrorWithStatusCode) {
-	autoBan := c.GetBool("auto_ban")
-	common.LogError(c.Request.Context(), fmt.Sprintf("relay error (channel #%d, status code: %d): %s", channelId, err.StatusCode, err.Error.Message))
-	if service.ShouldDisableChannel(&err.Error, err.StatusCode) && autoBan {
-		channelName := c.GetString("channel_name")
+func processChannelError(c *gin.Context, channelId int, channelType int, channelName string, autoBan bool, err *dto.OpenAIErrorWithStatusCode) {
+	// 不要使用context获取渠道信息，异步处理时可能会出现渠道信息不一致的情况
+	// do not use context to get channel info, there may be inconsistent channel info when processing asynchronously
+	common.LogError(c, fmt.Sprintf("relay error (channel #%d, status code: %d): %s", channelId, err.StatusCode, err.Error.Message))
+	if service.ShouldDisableChannel(channelType, err) && autoBan {
 		service.DisableChannel(channelId, channelName, err.Error.Message)
 	}
 }
@@ -187,3 +277,94 @@ func RelayNotFound(c *gin.Context) {
 		"error": err,
 	})
 }
+
+func RelayTask(c *gin.Context) {
+	retryTimes := common.RetryTimes
+	channelId := c.GetInt("channel_id")
+	relayMode := c.GetInt("relay_mode")
+	group := c.GetString("group")
+	originalModel := c.GetString("original_model")
+	c.Set("use_channel", []string{fmt.Sprintf("%d", channelId)})
+	taskErr := taskRelayHandler(c, relayMode)
+	if taskErr == nil {
+		retryTimes = 0
+	}
+	for i := 0; shouldRetryTaskRelay(c, channelId, taskErr, retryTimes) && i < retryTimes; i++ {
+		channel, err := model.CacheGetRandomSatisfiedChannel(group, originalModel, i)
+		if err != nil {
+			common.LogError(c, fmt.Sprintf("CacheGetRandomSatisfiedChannel failed: %s", err.Error()))
+			break
+		}
+		channelId = channel.Id
+		useChannel := c.GetStringSlice("use_channel")
+		useChannel = append(useChannel, fmt.Sprintf("%d", channelId))
+		c.Set("use_channel", useChannel)
+		common.LogInfo(c, fmt.Sprintf("using channel #%d to retry (remain times %d)", channel.Id, i))
+		middleware.SetupContextForSelectedChannel(c, channel, originalModel)
+
+		requestBody, err := common.GetRequestBody(c)
+		c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
+		taskErr = taskRelayHandler(c, relayMode)
+	}
+	useChannel := c.GetStringSlice("use_channel")
+	if len(useChannel) > 1 {
+		retryLogStr := fmt.Sprintf("重试：%s", strings.Trim(strings.Join(strings.Fields(fmt.Sprint(useChannel)), "->"), "[]"))
+		common.LogInfo(c, retryLogStr)
+	}
+	if taskErr != nil {
+		if taskErr.StatusCode == http.StatusTooManyRequests {
+			taskErr.Message = "当前分组上游负载已饱和，请稍后再试"
+		}
+		c.JSON(taskErr.StatusCode, taskErr)
+	}
+}
+
+func taskRelayHandler(c *gin.Context, relayMode int) *dto.TaskError {
+	var err *dto.TaskError
+	switch relayMode {
+	case relayconstant.RelayModeSunoFetch, relayconstant.RelayModeSunoFetchByID:
+		err = relay.RelayTaskFetch(c, relayMode)
+	default:
+		err = relay.RelayTaskSubmit(c, relayMode)
+	}
+	return err
+}
+
+func shouldRetryTaskRelay(c *gin.Context, channelId int, taskErr *dto.TaskError, retryTimes int) bool {
+	if taskErr == nil {
+		return false
+	}
+	if retryTimes <= 0 {
+		return false
+	}
+	if _, ok := c.Get("specific_channel_id"); ok {
+		return false
+	}
+	if taskErr.StatusCode == http.StatusTooManyRequests {
+		return true
+	}
+	if taskErr.StatusCode == 307 {
+		return true
+	}
+	if taskErr.StatusCode/100 == 5 {
+		// 超时不重试
+		if taskErr.StatusCode == 504 || taskErr.StatusCode == 524 {
+			return false
+		}
+		return true
+	}
+	if taskErr.StatusCode == http.StatusBadRequest {
+		return false
+	}
+	if taskErr.StatusCode == 408 {
+		// azure处理超时不重试
+		return false
+	}
+	if taskErr.LocalError {
+		return false
+	}
+	if taskErr.StatusCode/100 == 2 {
+		return false
+	}
+	return true
+}

controller/stripe.go

@@ -2,8 +2,8 @@ package controller
 
 import (
 	"github.com/gin-gonic/gin"
-	"github.com/stripe/stripe-go/v76"
-	"github.com/stripe/stripe-go/v76/webhook"
+	"github.com/stripe/stripe-go/v79"
+	"github.com/stripe/stripe-go/v79/webhook"
 	"io"
 	"log"
 	"net/http"
@@ -23,7 +23,9 @@ func StripeWebhook(c *gin.Context) {
 
 	signature := c.GetHeader("Stripe-Signature")
 	endpointSecret := common.StripeWebhookSecret
-	event, err := webhook.ConstructEvent(payload, signature, endpointSecret)
+	event, err := webhook.ConstructEventWithOptions(payload, signature, endpointSecret, webhook.ConstructEventOptions{
+		IgnoreAPIVersionMismatch: true,
+	})
 
 	if err != nil {
 		log.Printf("Stripe Webhook验签失败: %v\n", err)

controller/task.go

@@ -0,0 +1,284 @@
+package controller
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"github.com/samber/lo"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/constant"
+	"one-api/dto"
+	"one-api/model"
+	"one-api/relay"
+	"sort"
+	"strconv"
+	"time"
+)
+
+func UpdateTaskBulk() {
+	//revocer
+	//imageModel := "midjourney"
+	for {
+		time.Sleep(time.Duration(15) * time.Second)
+		common.SysLog("任务进度轮询开始")
+		ctx := context.TODO()
+		allTasks := model.GetAllUnFinishSyncTasks(500)
+		platformTask := make(map[constant.TaskPlatform][]*model.Task)
+		for _, t := range allTasks {
+			platformTask[t.Platform] = append(platformTask[t.Platform], t)
+		}
+		for platform, tasks := range platformTask {
+			if len(tasks) == 0 {
+				continue
+			}
+			taskChannelM := make(map[int][]string)
+			taskM := make(map[string]*model.Task)
+			nullTaskIds := make([]int64, 0)
+			for _, task := range tasks {
+				if task.TaskID == "" {
+					// 统计失败的未完成任务
+					nullTaskIds = append(nullTaskIds, task.ID)
+					continue
+				}
+				taskM[task.TaskID] = task
+				taskChannelM[task.ChannelId] = append(taskChannelM[task.ChannelId], task.TaskID)
+			}
+			if len(nullTaskIds) > 0 {
+				err := model.TaskBulkUpdateByID(nullTaskIds, map[string]any{
+					"status":   "FAILURE",
+					"progress": "100%",
+				})
+				if err != nil {
+					common.LogError(ctx, fmt.Sprintf("Fix null task_id task error: %v", err))
+				} else {
+					common.LogInfo(ctx, fmt.Sprintf("Fix null task_id task success: %v", nullTaskIds))
+				}
+			}
+			if len(taskChannelM) == 0 {
+				continue
+			}
+
+			UpdateTaskByPlatform(platform, taskChannelM, taskM)
+		}
+		common.SysLog("任务进度轮询完成")
+	}
+}
+
+func UpdateTaskByPlatform(platform constant.TaskPlatform, taskChannelM map[int][]string, taskM map[string]*model.Task) {
+	switch platform {
+	case constant.TaskPlatformMidjourney:
+		//_ = UpdateMidjourneyTaskAll(context.Background(), tasks)
+	case constant.TaskPlatformSuno:
+		_ = UpdateSunoTaskAll(context.Background(), taskChannelM, taskM)
+	default:
+		common.SysLog("未知平台")
+	}
+}
+
+func UpdateSunoTaskAll(ctx context.Context, taskChannelM map[int][]string, taskM map[string]*model.Task) error {
+	for channelId, taskIds := range taskChannelM {
+		err := updateSunoTaskAll(ctx, channelId, taskIds, taskM)
+		if err != nil {
+			common.LogError(ctx, fmt.Sprintf("渠道 #%d 更新异步任务失败: %d", channelId, err.Error()))
+		}
+	}
+	return nil
+}
+
+func updateSunoTaskAll(ctx context.Context, channelId int, taskIds []string, taskM map[string]*model.Task) error {
+	common.LogInfo(ctx, fmt.Sprintf("渠道 #%d 未完成的任务有: %d", channelId, len(taskIds)))
+	if len(taskIds) == 0 {
+		return nil
+	}
+	channel, err := model.CacheGetChannel(channelId)
+	if err != nil {
+		common.SysLog(fmt.Sprintf("CacheGetChannel: %v", err))
+		err = model.TaskBulkUpdate(taskIds, map[string]any{
+			"fail_reason": fmt.Sprintf("获取渠道信息失败，请联系管理员，渠道ID：%d", channelId),
+			"status":      "FAILURE",
+			"progress":    "100%",
+		})
+		if err != nil {
+			common.SysError(fmt.Sprintf("UpdateMidjourneyTask error2: %v", err))
+		}
+		return err
+	}
+	adaptor := relay.GetTaskAdaptor(constant.TaskPlatformSuno)
+	if adaptor == nil {
+		return errors.New("adaptor not found")
+	}
+	resp, err := adaptor.FetchTask(*channel.BaseURL, channel.Key, map[string]any{
+		"ids": taskIds,
+	})
+	if err != nil {
+		common.SysError(fmt.Sprintf("Get Task Do req error: %v", err))
+		return err
+	}
+	if resp.StatusCode != http.StatusOK {
+		common.LogError(ctx, fmt.Sprintf("Get Task status code: %d", resp.StatusCode))
+		return errors.New(fmt.Sprintf("Get Task status code: %d", resp.StatusCode))
+	}
+	defer resp.Body.Close()
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		common.SysError(fmt.Sprintf("Get Task parse body error: %v", err))
+		return err
+	}
+	var responseItems dto.TaskResponse[[]dto.SunoDataResponse]
+	err = json.Unmarshal(responseBody, &responseItems)
+	if err != nil {
+		common.LogError(ctx, fmt.Sprintf("Get Task parse body error2: %v, body: %s", err, string(responseBody)))
+		return err
+	}
+	if !responseItems.IsSuccess() {
+		common.SysLog(fmt.Sprintf("渠道 #%d 未完成的任务有: %d, 成功获取到任务数: %d", channelId, len(taskIds), string(responseBody)))
+		return err
+	}
+
+	for _, responseItem := range responseItems.Data {
+		task := taskM[responseItem.TaskID]
+		if !checkTaskNeedUpdate(task, responseItem) {
+			continue
+		}
+
+		task.Status = lo.If(model.TaskStatus(responseItem.Status) != "", model.TaskStatus(responseItem.Status)).Else(task.Status)
+		task.FailReason = lo.If(responseItem.FailReason != "", responseItem.FailReason).Else(task.FailReason)
+		task.SubmitTime = lo.If(responseItem.SubmitTime != 0, responseItem.SubmitTime).Else(task.SubmitTime)
+		task.StartTime = lo.If(responseItem.StartTime != 0, responseItem.StartTime).Else(task.StartTime)
+		task.FinishTime = lo.If(responseItem.FinishTime != 0, responseItem.FinishTime).Else(task.FinishTime)
+		if responseItem.FailReason != "" || task.Status == model.TaskStatusFailure {
+			common.LogInfo(ctx, task.TaskID+" 构建失败，"+task.FailReason)
+			task.Progress = "100%"
+			err = model.CacheUpdateUserQuota(task.UserId)
+			if err != nil {
+				common.LogError(ctx, "error update user quota cache: "+err.Error())
+			} else {
+				quota := task.Quota
+				if quota != 0 {
+					err = model.IncreaseUserQuota(task.UserId, quota)
+					if err != nil {
+						common.LogError(ctx, "fail to increase user quota: "+err.Error())
+					}
+					logContent := fmt.Sprintf("异步任务执行失败 %s，补偿 %s", task.TaskID, common.LogQuota(quota))
+					model.RecordLog(task.UserId, model.LogTypeSystem, logContent)
+				}
+			}
+		}
+		if responseItem.Status == model.TaskStatusSuccess {
+			task.Progress = "100%"
+		}
+		task.Data = responseItem.Data
+
+		err = task.Update()
+		if err != nil {
+			common.SysError("UpdateMidjourneyTask task error: " + err.Error())
+		}
+	}
+	return nil
+}
+
+func checkTaskNeedUpdate(oldTask *model.Task, newTask dto.SunoDataResponse) bool {
+
+	if oldTask.SubmitTime != newTask.SubmitTime {
+		return true
+	}
+	if oldTask.StartTime != newTask.StartTime {
+		return true
+	}
+	if oldTask.FinishTime != newTask.FinishTime {
+		return true
+	}
+	if string(oldTask.Status) != newTask.Status {
+		return true
+	}
+	if oldTask.FailReason != newTask.FailReason {
+		return true
+	}
+	if oldTask.FinishTime != newTask.FinishTime {
+		return true
+	}
+
+	if (oldTask.Status == model.TaskStatusFailure || oldTask.Status == model.TaskStatusSuccess) && oldTask.Progress != "100%" {
+		return true
+	}
+
+	oldData, _ := json.Marshal(oldTask.Data)
+	newData, _ := json.Marshal(newTask.Data)
+
+	sort.Slice(oldData, func(i, j int) bool {
+		return oldData[i] < oldData[j]
+	})
+	sort.Slice(newData, func(i, j int) bool {
+		return newData[i] < newData[j]
+	})
+
+	if string(oldData) != string(newData) {
+		return true
+	}
+	return false
+}
+
+func GetAllTask(c *gin.Context) {
+	p, _ := strconv.Atoi(c.Query("p"))
+	if p < 0 {
+		p = 0
+	}
+	startTimestamp, _ := strconv.ParseInt(c.Query("start_timestamp"), 10, 64)
+	endTimestamp, _ := strconv.ParseInt(c.Query("end_timestamp"), 10, 64)
+	// 解析其他查询参数
+	queryParams := model.SyncTaskQueryParams{
+		Platform:       constant.TaskPlatform(c.Query("platform")),
+		TaskID:         c.Query("task_id"),
+		Status:         c.Query("status"),
+		Action:         c.Query("action"),
+		StartTimestamp: startTimestamp,
+		EndTimestamp:   endTimestamp,
+	}
+
+	logs := model.TaskGetAllTasks(p*common.ItemsPerPage, common.ItemsPerPage, queryParams)
+	if logs == nil {
+		logs = make([]*model.Task, 0)
+	}
+
+	c.JSON(200, gin.H{
+		"success": true,
+		"message": "",
+		"data":    logs,
+	})
+}
+
+func GetUserTask(c *gin.Context) {
+	p, _ := strconv.Atoi(c.Query("p"))
+	if p < 0 {
+		p = 0
+	}
+
+	userId := c.GetInt("id")
+
+	startTimestamp, _ := strconv.ParseInt(c.Query("start_timestamp"), 10, 64)
+	endTimestamp, _ := strconv.ParseInt(c.Query("end_timestamp"), 10, 64)
+
+	queryParams := model.SyncTaskQueryParams{
+		Platform:       constant.TaskPlatform(c.Query("platform")),
+		TaskID:         c.Query("task_id"),
+		Status:         c.Query("status"),
+		Action:         c.Query("action"),
+		StartTimestamp: startTimestamp,
+		EndTimestamp:   endTimestamp,
+	}
+
+	logs := model.TaskGetAllUserTask(userId, p*common.ItemsPerPage, common.ItemsPerPage, queryParams)
+	if logs == nil {
+		logs = make([]*model.Task, 0)
+	}
+
+	c.JSON(200, gin.H{
+		"success": true,
+		"message": "",
+		"data":    logs,
+	})
+}

controller/telegram.go

@@ -5,6 +5,7 @@ import (
 	"crypto/sha256"
 	"encoding/hex"
 	"io"
+	"net/http"
 	"one-api/common"
 	"one-api/model"
 	"sort"
@@ -48,6 +49,13 @@ func TelegramBind(c *gin.Context) {
 		})
 		return
 	}
+	if user.Id == 0 {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "用户已注销",
+		})
+		return
+	}
 	user.TelegramId = telegramId
 	if err := user.Update(false); err != nil {
 		c.JSON(200, gin.H{

controller/token.go

@@ -123,10 +123,19 @@ func AddToken(c *gin.Context) {
 		})
 		return
 	}
+	key, err := common.GenerateKey()
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "生成令牌失败",
+		})
+		common.SysError("failed to generate token key: " + err.Error())
+		return
+	}
 	cleanToken := model.Token{
 		UserId:             c.GetInt("id"),
 		Name:               token.Name,
-		Key:                common.GenerateKey(),
+		Key:                key,
 		CreatedTime:        common.GetTimestamp(),
 		AccessedTime:       common.GetTimestamp(),
 		ExpiredTime:        token.ExpiredTime,
@@ -134,6 +143,8 @@ func AddToken(c *gin.Context) {
 		UnlimitedQuota:     token.UnlimitedQuota,
 		ModelLimitsEnabled: token.ModelLimitsEnabled,
 		ModelLimits:        token.ModelLimits,
+		AllowIps:           token.AllowIps,
+		Group:              token.Group,
 	}
 	err = cleanToken.Insert()
 	if err != nil {
@@ -221,6 +232,8 @@ func UpdateToken(c *gin.Context) {
 		cleanToken.UnlimitedQuota = token.UnlimitedQuota
 		cleanToken.ModelLimitsEnabled = token.ModelLimitsEnabled
 		cleanToken.ModelLimits = token.ModelLimits
+		cleanToken.AllowIps = token.AllowIps
+		cleanToken.Group = token.Group
 	}
 	err = cleanToken.Update()
 	if err != nil {

controller/topup.go

@@ -4,8 +4,8 @@ import "C"
 import (
 	"fmt"
 	"github.com/gin-gonic/gin"
-	"github.com/stripe/stripe-go/v76"
-	"github.com/stripe/stripe-go/v76/checkout/session"
+	"github.com/stripe/stripe-go/v79"
+	"github.com/stripe/stripe-go/v79/checkout/session"
 	"log"
 	"one-api/common"
 	"one-api/model"

controller/user.go

@@ -7,10 +7,12 @@ import (
 	"one-api/common"
 	"one-api/model"
 	"strconv"
+	"strings"
 	"sync"
 
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-gonic/gin"
+	"one-api/constant"
 )
 
 type LoginRequest struct {
@@ -66,6 +68,7 @@ func setupLogin(user *model.User, c *gin.Context) {
 	session.Set("username", user.Username)
 	session.Set("role", user.Role)
 	session.Set("status", user.Status)
+	session.Set("group", user.Group)
 	session.Set("linuxdo_enable", user.LinuxDoId == "" || user.LinuxDoLevel >= common.LinuxDoMinLevel)
 	err := session.Save()
 	if err != nil {
@@ -158,8 +161,9 @@ func Register(c *gin.Context) {
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
-			"message": err.Error(),
+			"message": "数据库错误，请稍后重试",
 		})
+		common.SysError(fmt.Sprintf("CheckUserExistOrDeleted error: %v", err))
 		return
 	}
 	if exist {
@@ -187,6 +191,48 @@ func Register(c *gin.Context) {
 		})
 		return
 	}
+
+	// 获取插入后的用户ID
+	var insertedUser model.User
+	if err := model.DB.Where("username = ?", cleanUser.Username).First(&insertedUser).Error; err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "用户注册失败或用户ID获取失败",
+		})
+		return
+	}
+	// 生成默认令牌
+	if constant.GenerateDefaultToken {
+		key, err := common.GenerateKey()
+		if err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "生成默认令牌失败",
+			})
+			common.SysError("failed to generate token key: " + err.Error())
+			return
+		}
+		// 生成默认令牌
+		token := model.Token{
+			UserId:             insertedUser.Id, // 使用插入后的用户ID
+			Name:               cleanUser.Username + "的初始令牌",
+			Key:                key,
+			CreatedTime:        common.GetTimestamp(),
+			AccessedTime:       common.GetTimestamp(),
+			ExpiredTime:        -1,     // 永不过期
+			RemainQuota:        500000, // 示例额度
+			UnlimitedQuota:     true,
+			ModelLimitsEnabled: false,
+		}
+		if err := token.Insert(); err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "创建默认令牌失败",
+			})
+			return
+		}
+	}
+
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
@@ -277,7 +323,18 @@ func GenerateAccessToken(c *gin.Context) {
 		})
 		return
 	}
-	user.AccessToken = common.GetUUID()
+	// get rand int 28-32
+	randI := common.GetRandomInt(4)
+	key, err := common.GenerateRandomKey(29 + randI)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "生成失败",
+		})
+		common.SysError("failed to generate key: " + err.Error())
+		return
+	}
+	user.SetAccessToken(key)
 
 	if model.DB.Where("access_token = ?", user.AccessToken).First(user).RowsAffected != 0 {
 		c.JSON(http.StatusOK, gin.H{
@@ -597,6 +654,7 @@ func DeleteSelf(c *gin.Context) {
 func CreateUser(c *gin.Context) {
 	var user model.User
 	err := json.NewDecoder(c.Request.Body).Decode(&user)
+	user.Username = strings.TrimSpace(user.Username)
 	if err != nil || user.Username == "" || user.Password == "" {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -644,8 +702,8 @@ func CreateUser(c *gin.Context) {
 }
 
 type ManageRequest struct {
-	Username string `json:"username"`
-	Action   string `json:"action"`
+	Id     int    `json:"id"`
+	Action string `json:"action"`
 }
 
 // ManageUser Only admin user can do this
@@ -661,7 +719,7 @@ func ManageUser(c *gin.Context) {
 		return
 	}
 	user := model.User{
-		Username: req.Username,
+		Id: req.Id,
 	}
 	// Fill attributes
 	model.DB.Unscoped().Where(&user).First(&user)
@@ -806,11 +864,11 @@ type topUpRequest struct {
 	Key string `json:"key"`
 }
 
-var lock = sync.Mutex{}
+var topUpLock = sync.Mutex{}
 
 func TopUp(c *gin.Context) {
-	lock.Lock()
-	defer lock.Unlock()
+	topUpLock.Lock()
+	defer topUpLock.Unlock()
 	req := topUpRequest{}
 	err := c.ShouldBindJSON(&req)
 	if err != nil {

controller/wechat.go

@@ -78,6 +78,13 @@ func WeChatAuth(c *gin.Context) {
 			})
 			return
 		}
+		if user.Id == 0 {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "用户已注销",
+			})
+			return
+		}
 	} else {
 		if common.RegisterEnabled {
 			user.Username = "wechat_" + strconv.Itoa(model.GetMaxUserId()+1)

dto/audio.go

@@ -1,13 +1,34 @@
 package dto
 
-type TextToSpeechRequest struct {
-	Model          string  `json:"model" binding:"required"`
-	Input          string  `json:"input" binding:"required"`
-	Voice          string  `json:"voice" binding:"required"`
-	Speed          float64 `json:"speed"`
-	ResponseFormat string  `json:"response_format"`
+type AudioRequest struct {
+	Model          string  `json:"model"`
+	Input          string  `json:"input"`
+	Voice          string  `json:"voice"`
+	Speed          float64 `json:"speed,omitempty"`
+	ResponseFormat string  `json:"response_format,omitempty"`
 }
 
 type AudioResponse struct {
 	Text string `json:"text"`
 }
+
+type WhisperVerboseJSONResponse struct {
+	Task     string    `json:"task,omitempty"`
+	Language string    `json:"language,omitempty"`
+	Duration float64   `json:"duration,omitempty"`
+	Text     string    `json:"text,omitempty"`
+	Segments []Segment `json:"segments,omitempty"`
+}
+
+type Segment struct {
+	Id               int     `json:"id"`
+	Seek             int     `json:"seek"`
+	Start            float64 `json:"start"`
+	End              float64 `json:"end"`
+	Text             string  `json:"text"`
+	Tokens           []int   `json:"tokens"`
+	Temperature      float64 `json:"temperature"`
+	AvgLogprob       float64 `json:"avg_logprob"`
+	CompressionRatio float64 `json:"compression_ratio"`
+	NoSpeechProb     float64 `json:"no_speech_prob"`
+}

dto/dalle.go

@@ -12,9 +12,11 @@ type ImageRequest struct {
 }
 
 type ImageResponse struct {
-	Created int `json:"created"`
-	Data    []struct {
-		Url     string `json:"url"`
-		B64Json string `json:"b64_json"`
-	}
+	Data    []ImageData `json:"data"`
+	Created int64       `json:"created"`
+}
+type ImageData struct {
+	Url           string `json:"url"`
+	B64Json       string `json:"b64_json"`
+	RevisedPrompt string `json:"revised_prompt"`
 }

dto/midjourney.go

@@ -33,6 +33,12 @@ type MidjourneyResponse struct {
 	Result      string      `json:"result"`
 }
 
+type MidjourneyUploadResponse struct {
+	Code        int      `json:"code"`
+	Description string   `json:"description"`
+	Result      []string `json:"result"`
+}
+
 type MidjourneyResponseWithStatusCode struct {
 	StatusCode int `json:"statusCode"`
 	Response   MidjourneyResponse

dto/playground.go

@@ -0,0 +1,6 @@
+package dto
+
+type PlayGroundRequest struct {
+	Model string `json:"model,omitempty"`
+	Group string `json:"group,omitempty"`
+}

dto/pricing.go

@@ -0,0 +1,26 @@
+package dto
+
+type OpenAIModelPermission struct {
+	Id                 string  `json:"id"`
+	Object             string  `json:"object"`
+	Created            int     `json:"created"`
+	AllowCreateEngine  bool    `json:"allow_create_engine"`
+	AllowSampling      bool    `json:"allow_sampling"`
+	AllowLogprobs      bool    `json:"allow_logprobs"`
+	AllowSearchIndices bool    `json:"allow_search_indices"`
+	AllowView          bool    `json:"allow_view"`
+	AllowFineTuning    bool    `json:"allow_fine_tuning"`
+	Organization       string  `json:"organization"`
+	Group              *string `json:"group"`
+	IsBlocking         bool    `json:"is_blocking"`
+}
+
+type OpenAIModels struct {
+	Id         string                  `json:"id"`
+	Object     string                  `json:"object"`
+	Created    int                     `json:"created"`
+	OwnedBy    string                  `json:"owned_by"`
+	Permission []OpenAIModelPermission `json:"permission"`
+	Root       string                  `json:"root"`
+	Parent     *string                 `json:"parent"`
+}

dto/rerank.go

@@ -0,0 +1,22 @@
+package dto
+
+type RerankRequest struct {
+	Documents       []any  `json:"documents"`
+	Query           string `json:"query"`
+	Model           string `json:"model"`
+	TopN            int    `json:"top_n"`
+	ReturnDocuments bool   `json:"return_documents,omitempty"`
+	MaxChunkPerDoc  int    `json:"max_chunk_per_doc,omitempty"`
+	OverLapTokens   int    `json:"overlap_tokens,omitempty"`
+}
+
+type RerankResponseDocument struct {
+	Document       any     `json:"document,omitempty"`
+	Index          int     `json:"index"`
+	RelevanceScore float64 `json:"relevance_score"`
+}
+
+type RerankResponse struct {
+	Results []RerankResponseDocument `json:"results"`
+	Usage   Usage                    `json:"usage"`
+}

dto/suno.go

@@ -0,0 +1,129 @@
+package dto
+
+import (
+	"encoding/json"
+)
+
+type TaskData interface {
+	SunoDataResponse | []SunoDataResponse | string | any
+}
+
+type SunoSubmitReq struct {
+	GptDescriptionPrompt string  `json:"gpt_description_prompt,omitempty"`
+	Prompt               string  `json:"prompt,omitempty"`
+	Mv                   string  `json:"mv,omitempty"`
+	Title                string  `json:"title,omitempty"`
+	Tags                 string  `json:"tags,omitempty"`
+	ContinueAt           float64 `json:"continue_at,omitempty"`
+	TaskID               string  `json:"task_id,omitempty"`
+	ContinueClipId       string  `json:"continue_clip_id,omitempty"`
+	MakeInstrumental     bool    `json:"make_instrumental"`
+}
+
+type FetchReq struct {
+	IDs []string `json:"ids"`
+}
+
+type SunoDataResponse struct {
+	TaskID     string          `json:"task_id" gorm:"type:varchar(50);index"`
+	Action     string          `json:"action" gorm:"type:varchar(40);index"` // 任务类型, song, lyrics, description-mode
+	Status     string          `json:"status" gorm:"type:varchar(20);index"` // 任务状态, submitted, queueing, processing, success, failed
+	FailReason string          `json:"fail_reason"`
+	SubmitTime int64           `json:"submit_time" gorm:"index"`
+	StartTime  int64           `json:"start_time" gorm:"index"`
+	FinishTime int64           `json:"finish_time" gorm:"index"`
+	Data       json.RawMessage `json:"data" gorm:"type:json"`
+}
+
+type SunoSong struct {
+	ID                string       `json:"id"`
+	VideoURL          string       `json:"video_url"`
+	AudioURL          string       `json:"audio_url"`
+	ImageURL          string       `json:"image_url"`
+	ImageLargeURL     string       `json:"image_large_url"`
+	MajorModelVersion string       `json:"major_model_version"`
+	ModelName         string       `json:"model_name"`
+	Status            string       `json:"status"`
+	Title             string       `json:"title"`
+	Text              string       `json:"text"`
+	Metadata          SunoMetadata `json:"metadata"`
+}
+
+type SunoMetadata struct {
+	Tags                 string      `json:"tags"`
+	Prompt               string      `json:"prompt"`
+	GPTDescriptionPrompt interface{} `json:"gpt_description_prompt"`
+	AudioPromptID        interface{} `json:"audio_prompt_id"`
+	Duration             interface{} `json:"duration"`
+	ErrorType            interface{} `json:"error_type"`
+	ErrorMessage         interface{} `json:"error_message"`
+}
+
+type SunoLyrics struct {
+	ID     string `json:"id"`
+	Status string `json:"status"`
+	Title  string `json:"title"`
+	Text   string `json:"text"`
+}
+
+const TaskSuccessCode = "success"
+
+type TaskResponse[T TaskData] struct {
+	Code    string `json:"code"`
+	Message string `json:"message"`
+	Data    T      `json:"data"`
+}
+
+func (t *TaskResponse[T]) IsSuccess() bool {
+	return t.Code == TaskSuccessCode
+}
+
+type TaskDto struct {
+	TaskID     string          `json:"task_id"` // 第三方id，不一定有/ song id\ Task id
+	Action     string          `json:"action"`  // 任务类型, song, lyrics, description-mode
+	Status     string          `json:"status"`  // 任务状态, submitted, queueing, processing, success, failed
+	FailReason string          `json:"fail_reason"`
+	SubmitTime int64           `json:"submit_time"`
+	StartTime  int64           `json:"start_time"`
+	FinishTime int64           `json:"finish_time"`
+	Progress   string          `json:"progress"`
+	Data       json.RawMessage `json:"data"`
+}
+
+type SunoGoAPISubmitReq struct {
+	CustomMode bool `json:"custom_mode"`
+
+	Input SunoGoAPISubmitReqInput `json:"input"`
+
+	NotifyHook string `json:"notify_hook,omitempty"`
+}
+
+type SunoGoAPISubmitReqInput struct {
+	GptDescriptionPrompt string  `json:"gpt_description_prompt"`
+	Prompt               string  `json:"prompt"`
+	Mv                   string  `json:"mv"`
+	Title                string  `json:"title"`
+	Tags                 string  `json:"tags"`
+	ContinueAt           float64 `json:"continue_at"`
+	TaskID               string  `json:"task_id"`
+	ContinueClipId       string  `json:"continue_clip_id"`
+	MakeInstrumental     bool    `json:"make_instrumental"`
+}
+
+type GoAPITaskResponse[T any] struct {
+	Code         int    `json:"code"`
+	Message      string `json:"message"`
+	Data         T      `json:"data"`
+	ErrorMessage string `json:"error_message,omitempty"`
+}
+
+type GoAPITaskResponseData struct {
+	TaskID string `json:"task_id"`
+}
+
+type GoAPIFetchResponseData struct {
+	TaskID string              `json:"task_id"`
+	Status string              `json:"status"`
+	Input  string              `json:"input"`
+	Clips  map[string]SunoSong `json:"clips"`
+}

dto/task.go

@@ -0,0 +1,10 @@
+package dto
+
+type TaskError struct {
+	Code       string `json:"code"`
+	Message    string `json:"message"`
+	Data       any    `json:"data"`
+	StatusCode int    `json:"-"`
+	LocalError bool   `json:"-"`
+	Error      error  `json:"-"`
+}

dto/text_request.go

@@ -2,34 +2,39 @@ package dto
 
 import "encoding/json"
 
-type ResponseFormat struct {
-	Type string `json:"type,omitempty"`
-}
-
 type GeneralOpenAIRequest struct {
-	Model            string          `json:"model,omitempty"`
-	Messages         []Message       `json:"messages,omitempty"`
-	Prompt           any             `json:"prompt,omitempty"`
-	Stream           bool            `json:"stream,omitempty"`
-	MaxTokens        uint            `json:"max_tokens,omitempty"`
-	Temperature      float64         `json:"temperature,omitempty"`
-	TopP             float64         `json:"top_p,omitempty"`
-	TopK             int             `json:"top_k,omitempty"`
-	Stop             any             `json:"stop,omitempty"`
-	N                int             `json:"n,omitempty"`
-	Input            any             `json:"input,omitempty"`
-	Instruction      string          `json:"instruction,omitempty"`
-	Size             string          `json:"size,omitempty"`
-	Functions        any             `json:"functions,omitempty"`
-	FrequencyPenalty float64         `json:"frequency_penalty,omitempty"`
-	PresencePenalty  float64         `json:"presence_penalty,omitempty"`
-	ResponseFormat   *ResponseFormat `json:"response_format,omitempty"`
-	Seed             float64         `json:"seed,omitempty"`
-	Tools            any             `json:"tools,omitempty"`
-	ToolChoice       any             `json:"tool_choice,omitempty"`
-	User             string          `json:"user,omitempty"`
-	LogProbs         bool            `json:"logprobs,omitempty"`
-	TopLogProbs      int             `json:"top_logprobs,omitempty"`
+	Model             string         `json:"model,omitempty"`
+	Messages          []Message      `json:"messages,omitempty"`
+	Prompt            any            `json:"prompt,omitempty"`
+	BestOf            int            `json:"best_of,omitempty"`
+	Echo              bool           `json:"echo,omitempty"`
+	Stream            bool           `json:"stream,omitempty"`
+	StreamOptions     *StreamOptions `json:"stream_options,omitempty"`
+	Suffix            string         `json:"suffix,omitempty"`
+	MaxTokens         uint           `json:"max_tokens,omitempty"`
+	MaxCompletionTokens uint           `json:"max_completion_tokens,omitempty"`
+	Temperature       float64        `json:"temperature,omitempty"`
+	TopP              float64        `json:"top_p,omitempty"`
+	TopK              int            `json:"top_k,omitempty"`
+	Stop              any            `json:"stop,omitempty"`
+	N                 int            `json:"n,omitempty"`
+	Input             any            `json:"input,omitempty"`
+	Instruction       string         `json:"instruction,omitempty"`
+	Size              string         `json:"size,omitempty"`
+	Functions         any            `json:"functions,omitempty"`
+	FrequencyPenalty  float64        `json:"frequency_penalty,omitempty"`
+	PresencePenalty   float64        `json:"presence_penalty,omitempty"`
+	ResponseFormat    any            `json:"response_format,omitempty"`
+	Seed              float64        `json:"seed,omitempty"`
+	Tools             []ToolCall     `json:"tools,omitempty"`
+	ToolChoice        any            `json:"tool_choice,omitempty"`
+	User              string         `json:"user,omitempty"`
+	LogitBias         any            `json:"logit_bias,omitempty"`
+	LogProbs          any            `json:"logprobs,omitempty"`
+	TopLogProbs       int            `json:"top_logprobs,omitempty"`
+	Dimensions        int            `json:"dimensions,omitempty"`
+	ParallelToolCalls bool           `json:"parallel_Tool_Calls,omitempty"`
+	EncodingFormat    any         `json:"encoding_format,omitempty"`
 }
 
 type OpenAITools struct {
@@ -43,8 +48,12 @@ type OpenAIFunction struct {
 	Parameters  any    `json:"parameters,omitempty"`
 }
 
-func (r GeneralOpenAIRequest) GetMaxTokens() int64 {
-	return int64(r.MaxTokens)
+type StreamOptions struct {
+	IncludeUsage bool `json:"include_usage,omitempty"`
+}
+
+func (r GeneralOpenAIRequest) GetMaxTokens() int {
+	return int(r.MaxTokens)
 }
 
 func (r GeneralOpenAIRequest) ParseInput() []string {
@@ -98,6 +107,11 @@ func (m Message) StringContent() string {
 	return string(m.Content)
 }
 
+func (m *Message) SetStringContent(content string) {
+	jsonContent, _ := json.Marshal(content)
+	m.Content = jsonContent
+}
+
 func (m Message) IsStringContent() bool {
 	var stringContent string
 	if err := json.Unmarshal(m.Content, &stringContent); err == nil {
@@ -137,7 +151,7 @@ func (m Message) ParseContent() []MediaMessage {
 					if ok {
 						subObj["detail"] = detail.(string)
 					} else {
-						subObj["detail"] = "auto"
+						subObj["detail"] = "high"
 					}
 					contentList = append(contentList, MediaMessage{
 						Type: ContentTypeImageURL,
@@ -146,7 +160,16 @@ func (m Message) ParseContent() []MediaMessage {
 							Detail: subObj["detail"].(string),
 						},
 					})
+				} else if url, ok := contentMap["image_url"].(string); ok {
+					contentList = append(contentList, MediaMessage{
+						Type: ContentTypeImageURL,
+						ImageUrl: MessageImageUrl{
+							Url:    url,
+							Detail: "high",
+						},
+					})
 				}
+
 			}
 		}
 		return contentList

dto/text_response.go

@@ -34,6 +34,7 @@ type OpenAITextResponseChoice struct {
 
 type OpenAITextResponse struct {
 	Id      string                     `json:"id"`
+	Model   string                     `json:"model"`
 	Object  string                     `json:"object"`
 	Created int64                      `json:"created"`
 	Choices []OpenAITextResponseChoice `json:"choices"`
@@ -41,9 +42,9 @@ type OpenAITextResponse struct {
 }
 
 type OpenAIEmbeddingResponseItem struct {
-	Object    string    `json:"object"`
-	Index     int       `json:"index"`
-	Embedding []float64 `json:"embedding"`
+	Object    string `json:"object"`
+	Index     int    `json:"index"`
+	Embedding any    `json:"embedding"`
 }
 
 type OpenAIEmbeddingResponse struct {
@@ -66,10 +67,6 @@ type ChatCompletionsStreamResponseChoiceDelta struct {
 	ToolCalls []ToolCall `json:"tool_calls,omitempty"`
 }
 
-func (c *ChatCompletionsStreamResponseChoiceDelta) IsEmpty() bool {
-	return c.Content == nil && len(c.ToolCalls) == 0
-}
-
 func (c *ChatCompletionsStreamResponseChoiceDelta) SetContentString(s string) {
 	c.Content = &s
 }
@@ -90,9 +87,11 @@ type ToolCall struct {
 }
 
 type FunctionCall struct {
-	Name string `json:"name,omitempty"`
+	Description string `json:"description,omitempty"`
+	Name        string `json:"name,omitempty"`
 	// call function with arguments in JSON format
-	Arguments string `json:"arguments,omitempty"`
+	Parameters any    `json:"parameters,omitempty"` // request
+	Arguments  string `json:"arguments,omitempty"`
 }
 
 type ChatCompletionsStreamResponse struct {
@@ -102,10 +101,23 @@ type ChatCompletionsStreamResponse struct {
 	Model             string                                `json:"model"`
 	SystemFingerprint *string                               `json:"system_fingerprint"`
 	Choices           []ChatCompletionsStreamResponseChoice `json:"choices"`
+	Usage             *Usage                                `json:"usage"`
+}
+
+func (c *ChatCompletionsStreamResponse) GetSystemFingerprint() string {
+	if c.SystemFingerprint == nil {
+		return ""
+	}
+	return *c.SystemFingerprint
+}
+
+func (c *ChatCompletionsStreamResponse) SetSystemFingerprint(s string) {
+	c.SystemFingerprint = &s
 }
 
 type ChatCompletionsStreamResponseSimple struct {
 	Choices []ChatCompletionsStreamResponseChoice `json:"choices"`
+	Usage   *Usage                                `json:"usage"`
 }
 
 type CompletionsStreamResponse struct {

go.mod

@@ -1,13 +1,16 @@
 module one-api
 
 // +heroku goVersion go1.18
-go 1.18
+go 1.21
+
+toolchain go1.22.4
 
 require (
 	github.com/anknown/ahocorasick v0.0.0-20190904063843-d75dbd5169c0
 	github.com/aws/aws-sdk-go-v2 v1.26.1
 	github.com/aws/aws-sdk-go-v2/credentials v1.17.11
 	github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.7.4
+	github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b
 	github.com/gin-contrib/cors v1.4.0
 	github.com/gin-contrib/gzip v0.0.6
 	github.com/gin-contrib/sessions v0.0.5
@@ -16,16 +19,17 @@ require (
 	github.com/go-playground/validator/v10 v10.19.0
 	github.com/go-redis/redis/v8 v8.11.5
 	github.com/golang-jwt/jwt v3.2.2+incompatible
-	github.com/google/uuid v1.3.0
+	github.com/google/uuid v1.6.0
 	github.com/gorilla/websocket v1.5.0
 	github.com/jinzhu/copier v0.4.0
 	github.com/pkg/errors v0.9.1
-	github.com/pkoukk/tiktoken-go v0.1.6
+	github.com/pkoukk/tiktoken-go v0.1.7
 	github.com/samber/lo v1.39.0
 	github.com/shirou/gopsutil v3.21.11+incompatible
-	github.com/stripe/stripe-go/v76 v76.21.0
-	golang.org/x/crypto v0.21.0
+	github.com/stripe/stripe-go/v79 v79.12.0
+	golang.org/x/crypto v0.26.0
 	golang.org/x/image v0.15.0
+	golang.org/x/net v0.28.0
 	gorm.io/driver/mysql v1.4.3
 	gorm.io/driver/postgres v1.5.2
 	gorm.io/driver/sqlite v1.4.3
@@ -39,10 +43,10 @@ require (
 	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.5 // indirect
 	github.com/aws/smithy-go v1.20.2 // indirect
 	github.com/bytedance/sonic v1.9.1 // indirect
-	github.com/cespare/xxhash/v2 v2.1.2 // indirect
+	github.com/cespare/xxhash/v2 v2.3.0 // indirect
 	github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 // indirect
 	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
-	github.com/dlclark/regexp2 v1.10.0 // indirect
+	github.com/dlclark/regexp2 v1.11.0 // indirect
 	github.com/gabriel-vasile/mimetype v1.4.3 // indirect
 	github.com/gin-contrib/sse v0.1.0 // indirect
 	github.com/go-ole/go-ole v1.2.6 // indirect
@@ -50,6 +54,7 @@ require (
 	github.com/go-playground/universal-translator v0.18.1 // indirect
 	github.com/go-sql-driver/mysql v1.6.0 // indirect
 	github.com/goccy/go-json v0.10.2 // indirect
+	github.com/google/go-cmp v0.6.0 // indirect
 	github.com/gorilla/context v1.1.1 // indirect
 	github.com/gorilla/securecookie v1.1.1 // indirect
 	github.com/gorilla/sessions v1.2.1 // indirect
@@ -67,6 +72,7 @@ require (
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/pelletier/go-toml/v2 v2.0.8 // indirect
+	github.com/stretchr/testify v1.9.0 // indirect
 	github.com/tklauser/go-sysconf v0.3.12 // indirect
 	github.com/tklauser/numcpus v0.6.1 // indirect
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
@@ -74,10 +80,9 @@ require (
 	github.com/yusufpapurcu/wmi v1.2.3 // indirect
 	golang.org/x/arch v0.3.0 // indirect
 	golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0 // indirect
-	golang.org/x/net v0.21.0 // indirect
-	golang.org/x/sync v0.7.0 // indirect
-	golang.org/x/sys v0.18.0 // indirect
-	golang.org/x/text v0.14.0 // indirect
-	google.golang.org/protobuf v1.30.0 // indirect
+	golang.org/x/sync v0.8.0 // indirect
+	golang.org/x/sys v0.24.0 // indirect
+	golang.org/x/text v0.17.0 // indirect
+	google.golang.org/protobuf v1.34.2 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )

go.sum

@@ -16,11 +16,13 @@ github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.7.4 h1:JgHnonzbnA3pbqj76w
 github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.7.4/go.mod h1:nZspkhg+9p8iApLFoyAqfyuMP0F38acy2Hm3r5r95Cg=
 github.com/aws/smithy-go v1.20.2 h1:tbp628ireGtzcHDDmLT/6ADHidqnwgF57XOXZe6tp4Q=
 github.com/aws/smithy-go v1.20.2/go.mod h1:krry+ya/rV9RDcV/Q16kpu6ypI4K2czasz0NC3qS14E=
+github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b h1:LTGVFpNmNHhj0vhOlfgWueFJ32eK9blaIlHR2ciXOT0=
+github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b/go.mod h1:2ZlV9BaUH4+NXIBF0aMdKKAnHTzqH+iMU4KUjAbL23Q=
 github.com/bytedance/sonic v1.5.0/go.mod h1:ED5hyg4y6t3/9Ku1R6dU/4KyJ48DZ4jPhfY1O2AihPM=
 github.com/bytedance/sonic v1.9.1 h1:6iJ6NqdoxCDr6mbY8h18oSO+cShGSMRGCEo7F2h0x8s=
 github.com/bytedance/sonic v1.9.1/go.mod h1:i736AoUSYt75HyZLoJW9ERYxcy6eaN6h4BZXU064P/U=
-github.com/cespare/xxhash/v2 v2.1.2 h1:YRXhKfTDauu4ajMg1TPgFO5jnlC2HCbmLXMcTG5cbYE=
-github.com/cespare/xxhash/v2 v2.1.2/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
+github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
+github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
 github.com/chenzhuoyu/base64x v0.0.0-20211019084208-fb5309c8db06/go.mod h1:DH46F32mSOjUmXrMHnKwZdA8wcEefY7UVqBKYGjpdQY=
 github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 h1:qSGYFH7+jGhDF8vLC+iwCD4WpbV1EBDSzWkJODFLams=
 github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311/go.mod h1:b583jCggY9gE99b6G5LEC39OIiVsWj+R97kbl5odCEk=
@@ -30,9 +32,10 @@ github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f h1:lO4WD4F/rVNCu3HqELle0jiPLLBs70cWOduZpkS1E78=
 github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f/go.mod h1:cuUVRXasLTGF7a8hSLbxyZXjz+1KgoB3wDUb6vlszIc=
-github.com/dlclark/regexp2 v1.10.0 h1:+/GIL799phkJqYW+3YbOd8LCcbHzT0Pbo8zl70MHsq0=
-github.com/dlclark/regexp2 v1.10.0/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
+github.com/dlclark/regexp2 v1.11.0 h1:G/nrcoOa7ZXlpoa/91N3X7mM3r8eIlMBBJZvsz/mxKI=
+github.com/dlclark/regexp2 v1.11.0/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
 github.com/fsnotify/fsnotify v1.4.9 h1:hsms1Qyu0jgnwNXIxa+/V/PDsU6CfLf6CNO8H7IWoS4=
+github.com/fsnotify/fsnotify v1.4.9/go.mod h1:znqG4EE+3YCdAaPaxE2ZRY/06pZUdp0tY4IgpuI1SZQ=
 github.com/gabriel-vasile/mimetype v1.4.3 h1:in2uUcidCuFcDKtdcBxlR0rJ1+fsokWf+uqxgUFjbI0=
 github.com/gabriel-vasile/mimetype v1.4.3/go.mod h1:d8uq/6HKRL6CGdk+aubisF/M5GcPfT7nKyLpA0lbSSk=
 github.com/gin-contrib/cors v1.4.0 h1:oJ6gwtUl3lqV0WEIwM/LxPF1QZ5qe2lGWdY2+bz7y0g=
@@ -53,6 +56,7 @@ github.com/go-ole/go-ole v1.2.6 h1:/Fpf6oFPoeFik9ty7siob0G6Ke8QvQEuVcuChpwXzpY=
 github.com/go-ole/go-ole v1.2.6/go.mod h1:pprOEPIfldk/42T2oK7lQ4v4JSDwmV0As9GaiUsvbm0=
 github.com/go-playground/assert/v2 v2.0.1/go.mod h1:VDjEfimB/XKnb+ZQfWdccd7VUvScMdVu0Titje2rxJ4=
 github.com/go-playground/assert/v2 v2.2.0 h1:JvknZsQTYeFEAhQwI4qEt9cyV5ONwRHC+lYKSsYSR8s=
+github.com/go-playground/assert/v2 v2.2.0/go.mod h1:VDjEfimB/XKnb+ZQfWdccd7VUvScMdVu0Titje2rxJ4=
 github.com/go-playground/locales v0.13.0/go.mod h1:taPMhCMXrRLJO55olJkUXHZBHCxTMfnGwq/HNwmWNS8=
 github.com/go-playground/locales v0.14.0/go.mod h1:sawfccIbzZTqEDETgFXqTho0QybSa7l++s0DH+LDiLs=
 github.com/go-playground/locales v0.14.1 h1:EWaQ/wswjilfKLTECiXz7Rh+3BjFhfDFKv/oXslEjJA=
@@ -77,10 +81,11 @@ github.com/golang-jwt/jwt v3.2.2+incompatible/go.mod h1:8pz2t5EyA70fFQQSrl6XZXzq
 github.com/golang/protobuf v1.3.3/go.mod h1:vzj43D7+SQXF/4pzW/hwtAqwc6iTitCiVSaWz5lYuqw=
 github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
-github.com/google/go-cmp v0.5.8 h1:e6P7q2lk1O+qJJb4BtCQXlK8vWEO8V1ZeuEdJNOqZyg=
+github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
+github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
-github.com/google/uuid v1.3.0 h1:t6JiXgmwXMjEs8VusXIJk2BXHsn+wx8BZdTaoZ5fu7I=
-github.com/google/uuid v1.3.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
+github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/gorilla/context v1.1.1 h1:AWwleXJkX/nhcU9bZSnZoi3h/qGYqQAGhq6zZe/aQW8=
 github.com/gorilla/context v1.1.1/go.mod h1:kBGZzfjB9CEq2AlWe17Uuf7NDRt0dE0s8S51q0aT7Yg=
 github.com/gorilla/securecookie v1.1.1 h1:miw7JPhV+b/lAHSXz4qd/nN9jRiAFV5FwjeKyCS8BvQ=
@@ -136,16 +141,19 @@ github.com/modern-go/reflect2 v0.0.0-20180701023420-4b7aa43c6742/go.mod h1:bx2lN
 github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M=
 github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
 github.com/nxadm/tail v1.4.8 h1:nPr65rt6Y5JFSKQO7qToXr7pePgD6Gwiw05lkbyAQTE=
+github.com/nxadm/tail v1.4.8/go.mod h1:+ncqLTQzXmGhMZNUePPaPqPvBxHAIsmXswZKocGu+AU=
 github.com/onsi/ginkgo v1.16.5 h1:8xi0RTUf59SOSfEtZMvwTvXYMzG4gV23XVHOZiXNtnE=
+github.com/onsi/ginkgo v1.16.5/go.mod h1:+E8gABHa3K6zRBolWtd+ROzc/U5bkGt0FwiG042wbpU=
 github.com/onsi/gomega v1.18.1 h1:M1GfJqGRrBrrGGsbxzV5dqM2U2ApXefZCQpkukxYRLE=
+github.com/onsi/gomega v1.18.1/go.mod h1:0q+aL8jAiMXy9hbwj2mr5GziHiwhAIQpFmmtT5hitRs=
 github.com/pelletier/go-toml/v2 v2.0.1/go.mod h1:r9LEWfGN8R5k0VXJ+0BkIe7MYkRdwZOjgMj2KwnJFUo=
 github.com/pelletier/go-toml/v2 v2.0.8 h1:0ctb6s9mE31h0/lhu+J6OPmVeDxJn+kYnJc2jZR9tGQ=
 github.com/pelletier/go-toml/v2 v2.0.8/go.mod h1:vuYfssBdrU2XDZ9bYydBu6t+6a6PYNcZljzZR9VXg+4=
 github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
 github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
 github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
-github.com/pkoukk/tiktoken-go v0.1.6 h1:JF0TlJzhTbrI30wCvFuiw6FzP2+/bR+FIxUdgEAcUsw=
-github.com/pkoukk/tiktoken-go v0.1.6/go.mod h1:9NiV+i9mJKGj1rYOT+njbv+ZwA/zJxYdewGl6qVatpg=
+github.com/pkoukk/tiktoken-go v0.1.7 h1:qOBHXX4PHtvIvmOtyg1EeKlwFRiMKAcoMp4Q+bLQDmw=
+github.com/pkoukk/tiktoken-go v0.1.7/go.mod h1:9NiV+i9mJKGj1rYOT+njbv+ZwA/zJxYdewGl6qVatpg=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/rogpeppe/go-internal v1.6.1/go.mod h1:xXDCJY+GAPziupqXw64V24skbSoqbTEfhy4qGm1nDQc=
@@ -166,9 +174,10 @@ github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/
 github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
 github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
 github.com/stretchr/testify v1.8.3/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
-github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
-github.com/stripe/stripe-go/v76 v76.21.0 h1:O3GHImHS4oUI3qWMOClHN3zAQF5/oswS/NB7leV1fsU=
-github.com/stripe/stripe-go/v76 v76.21.0/go.mod h1:rw1MxjlAKKcZ+3FOXgTHgwiOa2ya6CPq6ykpJ0Q6Po4=
+github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
+github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
+github.com/stripe/stripe-go/v79 v79.12.0 h1:HQs/kxNEB3gYA7FnkSFkp0kSOeez0fsmCWev6SxftYs=
+github.com/stripe/stripe-go/v79 v79.12.0/go.mod h1:cuH6X0zC8peY6f1AubHwgJ/fJSn2dh5pfiCr6CjyKVU=
 github.com/tklauser/go-sysconf v0.3.12 h1:0QaGUFOdQaIVdPgfITYzaTegZvdCjmYO52cSFAEVmqU=
 github.com/tklauser/go-sysconf v0.3.12/go.mod h1:Ho14jnntGE1fpdOqQEEaiKRpvIavV0hSfmBq8nJbHYI=
 github.com/tklauser/numcpus v0.6.1 h1:ng9scYS7az0Bk4OZLvrNXNSAO2Pxr1XXRAPyjhIx+Fk=
@@ -187,18 +196,19 @@ golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUu
 golang.org/x/arch v0.3.0 h1:02VY4/ZcO/gBOH6PUaoiptASxtXU10jazRCP865E97k=
 golang.org/x/arch v0.3.0/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
 golang.org/x/crypto v0.0.0-20210711020723-a769d52b0f97/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
-golang.org/x/crypto v0.21.0 h1:X31++rzVUdKhX5sWmSOFZxx8UW/ldWx55cbf08iNAMA=
-golang.org/x/crypto v0.21.0/go.mod h1:0BP7YvVV9gBbVKyeTG0Gyn+gZm94bibOW5BjDEYAOMs=
+golang.org/x/crypto v0.26.0 h1:RrRspgV4mU+YwB4FYnuBoKsUapNIL5cohGAmSH3azsw=
+golang.org/x/crypto v0.26.0/go.mod h1:GY7jblb9wI+FOo5y8/S2oY4zWP07AkOJ4+jxCqdqn54=
 golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0 h1:985EYyeCOxTpcgOTJpflJUwOeEz0CQOdPt73OzpE9F8=
 golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0/go.mod h1:/lliqkxwWAhPjf5oSOIJup2XcqJaw8RGS6k3TGEc7GI=
 golang.org/x/image v0.15.0 h1:kOELfmgrmJlw4Cdb7g/QGuB3CvDrXbqEIww/pNtNBm8=
 golang.org/x/image v0.15.0/go.mod h1:HUYqC05R2ZcZ3ejNQsIHQDQiwWM4JBqmm6MKANTp4LE=
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
 golang.org/x/net v0.0.0-20210520170846-37e1c6afe023/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
-golang.org/x/net v0.21.0 h1:AQyQV4dYCvJ7vGmJyKki9+PBdyvhkSd8EIx/qb0AYv4=
-golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=
-golang.org/x/sync v0.7.0 h1:YsImfSBoP9QPYL0xyKJPq0gcaJdG3rInoqxTWbfQu9M=
-golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
+golang.org/x/net v0.28.0 h1:a9JDOJc5GMUJ0+UDqmLT86WiEy7iWyIhz8gz8E4e5hE=
+golang.org/x/net v0.28.0/go.mod h1:yqtgsTWOOnlGLG9GFRrK3++bGOUEkNBoHZc8MEDWPNg=
+golang.org/x/sync v0.0.0-20210220032951-036812b2e83c/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.8.0 h1:3NFvSEYkUoMifnESzZl15y791HH1qU2xm6eCJU5ZPXQ=
+golang.org/x/sync v0.8.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
 golang.org/x/sys v0.0.0-20190916202348-b4ddaad3f8a3/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200116001909-b77594299b42/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -206,30 +216,32 @@ golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7w
 golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20210630005230-0f9fa26af87c/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20210806184541-e5e7981a1069/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220110181412-a018aaa089fe/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220704084225-05e143d24a9e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.11.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.18.0 h1:DBdB3niSjOA/O0blCZBqDefyWNYveAYMNF1Wum0DYQ4=
-golang.org/x/sys v0.18.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.24.0 h1:Twjiwq9dn6R1fQcyiK+wQyHWfaz/BJB+YIpzU/Cv3Xg=
+golang.org/x/sys v0.24.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
-golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
-golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
+golang.org/x/text v0.17.0 h1:XtiM5bkSOt+ewxlOE/aE/AKEHibwj/6gvWMl9Rsh0Qc=
+golang.org/x/text v0.17.0/go.mod h1:BuEKDfySbSR4drPmRPG/7iBdf8hvFMuRexcpahXilzY=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
 google.golang.org/protobuf v1.28.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
-google.golang.org/protobuf v1.30.0 h1:kPPoIgf3TsEvrm0PFe15JQ+570QVxYzEvvHqChK+cng=
-google.golang.org/protobuf v1.30.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
+google.golang.org/protobuf v1.34.2 h1:6xV6lTsCfpGD21XK49h7MhtcApnLqkfYgPcdHftf6hg=
+google.golang.org/protobuf v1.34.2/go.mod h1:qYOHts0dSfpeUzUFpOMr/WGzszTmLH+DiWniOlNbLDw=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
 gopkg.in/errgo.v2 v2.1.0/go.mod h1:hNsd1EY+bozCKY1Ytp96fpM3vjJbqLJn88ws8XvfDNI=
 gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 h1:uRGJdciOHaEIrze2W8Q3AKkepLTh2hOroT7a+7czfdQ=
+gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7/go.mod h1:dt/ZhP58zS4L8KSrWDmTeBkI65Dw0HsyUHuEVlX15mw=
 gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.2.8/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=

main.go

@@ -3,12 +3,14 @@ package main
 import (
 	"embed"
 	"fmt"
+	"github.com/bytedance/gopkg/util/gopool"
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-contrib/sessions/cookie"
 	"github.com/gin-gonic/gin"
 	"log"
 	"net/http"
 	"one-api/common"
+	"one-api/constant"
 	"one-api/controller"
 	"one-api/middleware"
 	"one-api/model"
@@ -40,6 +42,11 @@ func main() {
 	if err != nil {
 		common.FatalLog("failed to initialize database: " + err.Error())
 	}
+	// Initialize SQL Database
+	err = model.InitLogDB()
+	if err != nil {
+		common.FatalLog("failed to initialize database: " + err.Error())
+	}
 	defer func() {
 		err := model.CloseDB()
 		if err != nil {
@@ -53,6 +60,8 @@ func main() {
 		common.FatalLog("failed to initialize Redis: " + err.Error())
 	}
 
+	// Initialize constants
+	constant.InitEnv()
 	// Initialize options
 	model.InitOptionMap()
 	if common.RedisEnabled {
@@ -89,9 +98,14 @@ func main() {
 		}
 		go controller.AutomaticallyTestChannels(frequency)
 	}
-	common.SafeGoroutine(func() {
-		controller.UpdateMidjourneyTaskBulk()
-	})
+	if common.IsMasterNode && constant.UpdateTask {
+		gopool.Go(func() {
+			controller.UpdateMidjourneyTaskBulk()
+		})
+		gopool.Go(func() {
+			controller.UpdateTaskBulk()
+		})
+	}
 	if os.Getenv("BATCH_UPDATE_ENABLED") == "true" {
 		common.BatchUpdateEnabled = true
 		common.SysLog("batch update enabled with interval " + strconv.Itoa(common.BatchUpdateInterval) + "s")

middleware/auth.go

@@ -6,9 +6,21 @@ import (
 	"net/http"
 	"one-api/common"
 	"one-api/model"
+	"strconv"
 	"strings"
 )
 
+func validUserInfo(username string, role int) bool {
+	// check username is empty
+	if strings.TrimSpace(username) == "" {
+		return false
+	}
+	if !common.IsValidateRole(role) {
+		return false
+	}
+	return true
+}
+
 func authHelper(c *gin.Context, minRole int) {
 	session := sessions.Default(c)
 	username := session.Get("username")
@@ -16,6 +28,7 @@ func authHelper(c *gin.Context, minRole int) {
 	id := session.Get("id")
 	status := session.Get("status")
 	linuxDoEnable := session.Get("linuxdo_enable")
+	useAccessToken := false
 	if username == nil {
 		// Check access token
 		accessToken := c.Request.Header.Get("Authorization")
@@ -29,12 +42,21 @@ func authHelper(c *gin.Context, minRole int) {
 		}
 		user := model.ValidateAccessToken(accessToken)
 		if user != nil && user.Username != "" {
+			if !validUserInfo(user.Username, user.Role) {
+				c.JSON(http.StatusOK, gin.H{
+					"success": false,
+					"message": "无权进行此操作，用户信息无效",
+				})
+				c.Abort()
+				return
+			}
 			// Token is valid
 			username = user.Username
 			role = user.Role
 			id = user.Id
 			status = user.Status
 			linuxDoEnable = user.LinuxDoId == "" || user.LinuxDoLevel >= common.LinuxDoMinLevel
+			useAccessToken = true
 		} else {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,
@@ -44,6 +66,36 @@ func authHelper(c *gin.Context, minRole int) {
 			return
 		}
 	}
+	if !useAccessToken {
+		// get header New-Api-User
+		apiUserIdStr := c.Request.Header.Get("New-Api-User")
+		if apiUserIdStr == "" {
+			c.JSON(http.StatusUnauthorized, gin.H{
+				"success": false,
+				"message": "无权进行此操作，请刷新页面或清空缓存后重试",
+			})
+			c.Abort()
+			return
+		}
+		apiUserId, err := strconv.Atoi(apiUserIdStr)
+		if err != nil {
+			c.JSON(http.StatusUnauthorized, gin.H{
+				"success": false,
+				"message": "无权进行此操作，登录信息无效，请重新登录",
+			})
+			c.Abort()
+			return
+
+		}
+		if id != apiUserId {
+			c.JSON(http.StatusUnauthorized, gin.H{
+				"success": false,
+				"message": "无权进行此操作，与登录用户不匹配，请重新登录",
+			})
+			c.Abort()
+			return
+		}
+	}
 	if status.(int) == common.UserStatusDisabled {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -68,12 +120,33 @@ func authHelper(c *gin.Context, minRole int) {
 		c.Abort()
 		return
 	}
+	if !validUserInfo(username.(string), role.(int)) {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "无权进行此操作，用户信息无效",
+		})
+		c.Abort()
+		return
+	}
 	c.Set("username", username)
 	c.Set("role", role)
 	c.Set("id", id)
+	c.Set("group", session.Get("group"))
+	c.Set("use_access_token", useAccessToken)
 	c.Next()
 }
 
+func TryUserAuth() func(c *gin.Context) {
+	return func(c *gin.Context) {
+		session := sessions.Default(c)
+		id := session.Get("id")
+		if id != nil {
+			c.Set("id", id)
+		}
+		c.Next()
+	}
+}
+
 func UserAuth() func(c *gin.Context) {
 	return func(c *gin.Context) {
 		authHelper(c, common.RoleCommonUser)
@@ -109,6 +182,12 @@ func TokenAuth() func(c *gin.Context) {
 			key = parts[0]
 		}
 		token, err := model.ValidateUserToken(key)
+		if token != nil {
+			id := c.GetInt("id")
+			if id == 0 {
+				c.Set("id", token.UserId)
+			}
+		}
 		if err != nil {
 			abortWithOpenAiMessage(c, http.StatusUnauthorized, err.Error())
 			return
@@ -144,6 +223,8 @@ func TokenAuth() func(c *gin.Context) {
 		} else {
 			c.Set("token_model_limit_enabled", false)
 		}
+		c.Set("allow_ips", token.GetIpLimitsMap())
+		c.Set("token_group", token.Group)
 		if len(parts) > 1 {
 			if model.IsAdmin(token.UserId) {
 				c.Set("specific_channel_id", parts[1])

middleware/distributor.go

@@ -1,6 +1,7 @@
 package middleware
 
 import (
+	"errors"
 	"fmt"
 	"net/http"
 	"one-api/common"
@@ -21,11 +22,37 @@ type ModelRequest struct {
 
 func Distribute() func(c *gin.Context) {
 	return func(c *gin.Context) {
+		allowIpsMap := c.GetStringMap("allow_ips")
+		if len(allowIpsMap) != 0 {
+			clientIp := c.ClientIP()
+			if _, ok := allowIpsMap[clientIp]; !ok {
+				abortWithOpenAiMessage(c, http.StatusForbidden, "您的 IP 不在令牌允许访问的列表中")
+				return
+			}
+		}
 		userId := c.GetInt("id")
 		var channel *model.Channel
 		channelId, ok := c.Get("specific_channel_id")
 		modelRequest, shouldSelectChannel, err := getModelRequest(c)
+		if err != nil {
+			abortWithOpenAiMessage(c, http.StatusBadRequest, "Invalid request, "+err.Error())
+			return
+		}
 		userGroup, _ := model.CacheGetUserGroup(userId)
+		tokenGroup := c.GetString("token_group")
+		if tokenGroup != "" {
+			// check common.UserUsableGroups[userGroup]
+			if _, ok := common.UserUsableGroups[tokenGroup]; !ok {
+				abortWithOpenAiMessage(c, http.StatusForbidden, fmt.Sprintf("令牌分组 %s 已被禁用", tokenGroup))
+				return
+			}
+			// check group in common.GroupRatio
+			if _, ok := common.GroupRatio[tokenGroup]; !ok {
+				abortWithOpenAiMessage(c, http.StatusForbidden, fmt.Sprintf("分组 %s 已被弃用", tokenGroup))
+				return
+			}
+			userGroup = tokenGroup
+		}
 		c.Set("group", userGroup)
 		if ok {
 			id, err := strconv.Atoi(channelId.(string))
@@ -125,12 +152,23 @@ func getModelRequest(c *gin.Context) (*ModelRequest, bool, error) {
 			modelRequest.Model = midjourneyModel
 		}
 		c.Set("relay_mode", relayMode)
+	} else if strings.Contains(c.Request.URL.Path, "/suno/") {
+		relayMode := relayconstant.Path2RelaySuno(c.Request.Method, c.Request.URL.Path)
+		if relayMode == relayconstant.RelayModeSunoFetch ||
+			relayMode == relayconstant.RelayModeSunoFetchByID {
+			shouldSelectChannel = false
+		} else {
+			modelName := service.CoverTaskActionToModelName(constant.TaskPlatformSuno, c.Param("action"))
+			modelRequest.Model = modelName
+		}
+		c.Set("platform", string(constant.TaskPlatformSuno))
+		c.Set("relay_mode", relayMode)
 	} else if !strings.HasPrefix(c.Request.URL.Path, "/v1/audio/transcriptions") {
 		err = common.UnmarshalBodyReusable(c, &modelRequest)
 	}
 	if err != nil {
 		abortWithOpenAiMessage(c, http.StatusBadRequest, "无效的请求, "+err.Error())
-		return nil, false, err
+		return nil, false, errors.New("无效的请求, " + err.Error())
 	}
 	if strings.HasPrefix(c.Request.URL.Path, "/v1/moderations") {
 		if modelRequest.Model == "" {
@@ -143,18 +181,22 @@ func getModelRequest(c *gin.Context) (*ModelRequest, bool, error) {
 		}
 	}
 	if strings.HasPrefix(c.Request.URL.Path, "/v1/images/generations") {
-		if modelRequest.Model == "" {
-			modelRequest.Model = "dall-e"
-		}
+		modelRequest.Model = common.GetStringIfEmpty(modelRequest.Model, "dall-e")
 	}
 	if strings.HasPrefix(c.Request.URL.Path, "/v1/audio") {
-		if modelRequest.Model == "" {
-			if strings.HasPrefix(c.Request.URL.Path, "/v1/audio/speech") {
-				modelRequest.Model = "tts-1"
-			} else {
-				modelRequest.Model = "whisper-1"
-			}
+		relayMode := relayconstant.RelayModeAudioSpeech
+		if strings.HasPrefix(c.Request.URL.Path, "/v1/audio/speech") {
+			modelRequest.Model = common.GetStringIfEmpty(modelRequest.Model, "tts-1")
+		} else if strings.HasPrefix(c.Request.URL.Path, "/v1/audio/translations") {
+			modelRequest.Model = common.GetStringIfEmpty(modelRequest.Model, c.PostForm("model"))
+			modelRequest.Model = common.GetStringIfEmpty(modelRequest.Model, "whisper-1")
+			relayMode = relayconstant.RelayModeAudioTranslation
+		} else if strings.HasPrefix(c.Request.URL.Path, "/v1/audio/transcriptions") {
+			modelRequest.Model = common.GetStringIfEmpty(modelRequest.Model, c.PostForm("model"))
+			modelRequest.Model = common.GetStringIfEmpty(modelRequest.Model, "whisper-1")
+			relayMode = relayconstant.RelayModeAudioTranscription
 		}
+		c.Set("relay_mode", relayMode)
 	}
 	return &modelRequest, shouldSelectChannel, nil
 }
@@ -164,18 +206,13 @@ func SetupContextForSelectedChannel(c *gin.Context, channel *model.Channel, mode
 	if channel == nil {
 		return
 	}
-	c.Set("channel", channel.Type)
 	c.Set("channel_id", channel.Id)
 	c.Set("channel_name", channel.Name)
-	ban := true
-	// parse *int to bool
-	if channel.AutoBan != nil && *channel.AutoBan == 0 {
-		ban = false
-	}
+	c.Set("channel_type", channel.Type)
 	if nil != channel.OpenAIOrganization && "" != *channel.OpenAIOrganization {
 		c.Set("channel_organization", *channel.OpenAIOrganization)
 	}
-	c.Set("auto_ban", ban)
+	c.Set("auto_ban", channel.GetAutoBan())
 	c.Set("model_mapping", channel.GetModelMapping())
 	c.Set("status_code_mapping", channel.GetStatusCodeMapping())
 	c.Request.Header.Set("Authorization", fmt.Sprintf("Bearer %s", channel.Key))
@@ -184,13 +221,15 @@ func SetupContextForSelectedChannel(c *gin.Context, channel *model.Channel, mode
 	switch channel.Type {
 	case common.ChannelTypeAzure:
 		c.Set("api_version", channel.Other)
+	case common.ChannelTypeVertexAi:
+		c.Set("region", channel.Other)
 	case common.ChannelTypeXunfei:
 		c.Set("api_version", channel.Other)
-	//case common.ChannelTypeAIProxyLibrary:
-	//	c.Set("library_id", channel.Other)
 	case common.ChannelTypeGemini:
 		c.Set("api_version", channel.Other)
 	case common.ChannelTypeAli:
 		c.Set("plugin", channel.Other)
+	case common.ChannelCloudflare:
+		c.Set("api_version", channel.Other)
 	}
 }

middleware/utils.go

@@ -1,11 +1,13 @@
 package middleware
 
 import (
+	"fmt"
 	"github.com/gin-gonic/gin"
 	"one-api/common"
 )
 
 func abortWithOpenAiMessage(c *gin.Context, statusCode int, message string) {
+	userId := c.GetInt("id")
 	c.JSON(statusCode, gin.H{
 		"error": gin.H{
 			"message": common.MessageWithRequestId(message, c.GetString(common.RequestIdKey)),
@@ -13,7 +15,7 @@ func abortWithOpenAiMessage(c *gin.Context, statusCode int, message string) {
 		},
 	})
 	c.Abort()
-	common.LogError(c.Request.Context(), message)
+	common.LogError(c.Request.Context(), fmt.Sprintf("user %d | %s", userId, message))
 }
 
 func abortWithMidjourneyMessage(c *gin.Context, statusCode int, code int, description string) {

model/ability.go

@@ -29,6 +29,19 @@ func GetGroupModels(group string) []string {
 	return models
 }
 
+func GetEnabledModels() []string {
+	var models []string
+	// Find distinct models
+	DB.Table("abilities").Where("enabled = ?", true).Distinct("model").Pluck("model", &models)
+	return models
+}
+
+func GetAllEnableAbilities() []Ability {
+	var abilities []Ability
+	DB.Find(&abilities, "enabled = ?", true)
+	return abilities
+}
+
 func getPriority(group string, model string, retry int) (int, error) {
 	groupCol := "`group`"
 	trueVal := "1"
@@ -49,6 +62,11 @@ func getPriority(group string, model string, retry int) (int, error) {
 		return 0, err
 	}
 
+	if len(priorities) == 0 {
+		// 如果没有查询到优先级，则返回错误
+		return 0, errors.New("数据库一致性被破坏")
+	}
+
 	// 确定要使用的优先级
 	var priorityToUse int
 	if retry >= len(priorities) {
@@ -192,7 +210,7 @@ func FixAbility() (int, error) {
 
 	// Use channelIds to find channel not in abilities table
 	var abilityChannelIds []int
-	err = DB.Model(&Ability{}).Pluck("channel_id", &abilityChannelIds).Error
+	err = DB.Table("abilities").Distinct("channel_id").Pluck("channel_id", &abilityChannelIds).Error
 	if err != nil {
 		common.SysError(fmt.Sprintf("Get channel ids from abilities table failed: %s", err.Error()))
 		return 0, err

model/cache.go

@@ -87,7 +87,7 @@ func SyncTokenCache(frequency int) {
 				}
 			} else {
 				// 如果数据库中存在，先检查redis
-				_, err := common.RedisGet(fmt.Sprintf("token:%s", key))
+				_, err = common.RedisGet(fmt.Sprintf("token:%s", key))
 				if err != nil {
 					// 如果redis中不存在，则跳过
 					continue
@@ -293,6 +293,8 @@ func SyncChannelCache(frequency int) {
 func CacheGetRandomSatisfiedChannel(group string, model string, retry int) (*Channel, error) {
 	if strings.HasPrefix(model, "gpt-4-gizmo") {
 		model = "gpt-4-gizmo-*"
+	} else if strings.HasPrefix(model, "g-") {
+		model = "g-*"
 	}
 
 	// if memory cache is disabled, get channel directly from database

model/channel.go

@@ -1,8 +1,10 @@
 package model
 
 import (
+	"encoding/json"
 	"gorm.io/gorm"
 	"one-api/common"
+	"strings"
 )
 
 type Channel struct {
@@ -29,6 +31,45 @@ type Channel struct {
 	StatusCodeMapping *string `json:"status_code_mapping" gorm:"type:varchar(1024);default:''"`
 	Priority          *int64  `json:"priority" gorm:"bigint;default:0"`
 	AutoBan           *int    `json:"auto_ban" gorm:"default:1"`
+	OtherInfo         string  `json:"other_info"`
+}
+
+func (channel *Channel) GetModels() []string {
+	if channel.Models == "" {
+		return []string{}
+	}
+	return strings.Split(strings.Trim(channel.Models, ","), ",")
+}
+
+func (channel *Channel) GetOtherInfo() map[string]interface{} {
+	otherInfo := make(map[string]interface{})
+	if channel.OtherInfo != "" {
+		err := json.Unmarshal([]byte(channel.OtherInfo), &otherInfo)
+		if err != nil {
+			common.SysError("failed to unmarshal other info: " + err.Error())
+		}
+	}
+	return otherInfo
+}
+
+func (channel *Channel) SetOtherInfo(otherInfo map[string]interface{}) {
+	otherInfoBytes, err := json.Marshal(otherInfo)
+	if err != nil {
+		common.SysError("failed to marshal other info: " + err.Error())
+		return
+	}
+	channel.OtherInfo = string(otherInfoBytes)
+}
+
+func (channel *Channel) GetAutoBan() bool {
+	if channel.AutoBan == nil {
+		return false
+	}
+	return *channel.AutoBan == 1
+}
+
+func (channel *Channel) Save() error {
+	return DB.Save(channel).Error
 }
 
 func GetAllChannels(startIdx int, num int, selectAll bool, idSort bool) ([]*Channel, error) {
@@ -65,16 +106,23 @@ func SearchChannels(keyword string, group string, model string) ([]*Channel, err
 	// 构造WHERE子句
 	var whereClause string
 	var args []interface{}
-	if group != "" {
-		whereClause = "(id = ? OR name LIKE ? OR " + keyCol + " = ?) AND " + groupCol + " LIKE ? AND " + modelsCol + " LIKE ?"
-		args = append(args, common.String2Int(keyword), "%"+keyword+"%", keyword, "%"+group+"%", "%"+model+"%")
+	if group != "" && group != "null" {
+		var groupCondition string
+		if common.UsingMySQL {
+			groupCondition = `CONCAT(',', ` + groupCol + `, ',') LIKE ?`
+		} else {
+			// sqlite, PostgreSQL
+			groupCondition = `(',' || ` + groupCol + ` || ',') LIKE ?`
+		}
+		whereClause = "(id = ? OR name LIKE ? OR " + keyCol + " = ?) AND " + modelsCol + ` LIKE ? AND ` + groupCondition
+		args = append(args, common.String2Int(keyword), "%"+keyword+"%", keyword, "%"+model+"%", "%,"+group+",%")
 	} else {
 		whereClause = "(id = ? OR name LIKE ? OR " + keyCol + " = ?) AND " + modelsCol + " LIKE ?"
 		args = append(args, common.String2Int(keyword), "%"+keyword+"%", keyword, "%"+model+"%")
 	}
 
 	// 执行查询
-	err := baseQuery.Where(whereClause, args...).Find(&channels).Error
+	err := baseQuery.Where(whereClause, args...).Order("priority desc").Find(&channels).Error
 	if err != nil {
 		return nil, err
 	}
@@ -213,15 +261,31 @@ func (channel *Channel) Delete() error {
 	return err
 }
 
-func UpdateChannelStatusById(id int, status int) {
+func UpdateChannelStatusById(id int, status int, reason string) {
 	err := UpdateAbilityStatus(id, status == common.ChannelStatusEnabled)
 	if err != nil {
 		common.SysError("failed to update ability status: " + err.Error())
 	}
-	err = DB.Model(&Channel{}).Where("id = ?", id).Update("status", status).Error
+	channel, err := GetChannelById(id, true)
 	if err != nil {
-		common.SysError("failed to update channel status: " + err.Error())
+		// find channel by id error, directly update status
+		err = DB.Model(&Channel{}).Where("id = ?", id).Update("status", status).Error
+		if err != nil {
+			common.SysError("failed to update channel status: " + err.Error())
+		}
+	} else {
+		// find channel by id success, update status and other info
+		info := channel.GetOtherInfo()
+		info["status_reason"] = reason
+		info["status_time"] = common.GetTimestamp()
+		channel.SetOtherInfo(info)
+		channel.Status = status
+		err = channel.Save()
+		if err != nil {
+			common.SysError("failed to update channel status: " + err.Error())
+		}
 	}
+
 }
 
 func UpdateChannelUsedQuota(id int, quota int) {

model/log.go

@@ -3,9 +3,12 @@ package model
 import (
 	"context"
 	"fmt"
-	"gorm.io/gorm"
 	"one-api/common"
 	"strings"
+	"time"
+
+	"github.com/bytedance/gopkg/util/gopool"
+	"gorm.io/gorm"
 )
 
 type Log struct {
@@ -24,6 +27,7 @@ type Log struct {
 	IsStream         bool   `json:"is_stream" gorm:"default:false"`
 	ChannelId        int    `json:"channel" gorm:"index"`
 	TokenId          int    `json:"token_id" gorm:"default:0;index"`
+	Other            string `json:"other"`
 }
 
 const (
@@ -35,7 +39,7 @@ const (
 )
 
 func GetLogByKey(key string) (logs []*Log, err error) {
-	err = DB.Joins("left join tokens on tokens.id = logs.token_id").Where("tokens.key = ?", strings.Split(key, "-")[1]).Find(&logs).Error
+	err = LOG_DB.Joins("left join tokens on tokens.id = logs.token_id").Where("tokens.key = ?", strings.TrimPrefix(key, "sk-")).Find(&logs).Error
 	return logs, err
 }
 
@@ -51,18 +55,19 @@ func RecordLog(userId int, logType int, content string) {
 		Type:      logType,
 		Content:   content,
 	}
-	err := DB.Create(log).Error
+	err := LOG_DB.Create(log).Error
 	if err != nil {
 		common.SysError("failed to record log: " + err.Error())
 	}
 }
 
-func RecordConsumeLog(ctx context.Context, userId int, channelId int, promptTokens int, completionTokens int, modelName string, tokenName string, quota int, content string, tokenId int, userQuota int, useTimeSeconds int, isStream bool) {
+func RecordConsumeLog(ctx context.Context, userId int, channelId int, promptTokens int, completionTokens int, modelName string, tokenName string, quota int, content string, tokenId int, userQuota int, useTimeSeconds int, isStream bool, other map[string]interface{}) {
 	common.LogInfo(ctx, fmt.Sprintf("record consume log: userId=%d, 用户调用前余额=%d, channelId=%d, promptTokens=%d, completionTokens=%d, modelName=%s, tokenName=%s, quota=%d, content=%s", userId, userQuota, channelId, promptTokens, completionTokens, modelName, tokenName, quota, content))
 	if !common.LogConsumeEnabled {
 		return
 	}
 	username, _ := CacheGetUsername(userId)
+	otherStr := common.MapToJsonStr(other)
 	log := &Log{
 		UserId:           userId,
 		Username:         username,
@@ -78,13 +83,14 @@ func RecordConsumeLog(ctx context.Context, userId int, channelId int, promptToke
 		TokenId:          tokenId,
 		UseTime:          useTimeSeconds,
 		IsStream:         isStream,
+		Other:            otherStr,
 	}
-	err := DB.Create(log).Error
+	err := LOG_DB.Create(log).Error
 	if err != nil {
 		common.LogError(ctx, "failed to record log: "+err.Error())
 	}
 	if common.DataExportEnabled {
-		common.SafeGoroutine(func() {
+		gopool.Go(func() {
 			LogQuotaData(userId, username, modelName, quota, common.GetTimestamp(), promptTokens+completionTokens)
 		})
 	}
@@ -93,12 +99,12 @@ func RecordConsumeLog(ctx context.Context, userId int, channelId int, promptToke
 func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string, startIdx int, num int, channel int) (logs []*Log, total int64, err error) {
 	var tx *gorm.DB
 	if logType == LogTypeUnknown {
-		tx = DB
+		tx = LOG_DB
 	} else {
-		tx = DB.Where("type = ?", logType)
+		tx = LOG_DB.Where("type = ?", logType)
 	}
 	if modelName != "" {
-		tx = tx.Where("model_name = ?", modelName)
+		tx = tx.Where("model_name like ?", modelName)
 	}
 	if username != "" {
 		tx = tx.Where("username = ?", username)
@@ -115,25 +121,26 @@ func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName
 	if channel != 0 {
 		tx = tx.Where("channel_id = ?", channel)
 	}
-
 	err = tx.Model(&Log{}).Count(&total).Error
 	if err != nil {
 		return nil, 0, err
 	}
-
 	err = tx.Order("id desc").Limit(num).Offset(startIdx).Find(&logs).Error
+	if err != nil {
+		return nil, 0, err
+	}
 	return logs, total, err
 }
 
 func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int64, modelName string, tokenName string, startIdx int, num int) (logs []*Log, total int64, err error) {
 	var tx *gorm.DB
 	if logType == LogTypeUnknown {
-		tx = DB.Where("user_id = ?", userId)
+		tx = LOG_DB.Where("user_id = ?", userId)
 	} else {
-		tx = DB.Where("user_id = ? and type = ?", userId, logType)
+		tx = LOG_DB.Where("user_id = ? and type = ?", userId, logType)
 	}
 	if modelName != "" {
-		tx = tx.Where("model_name = ?", modelName)
+		tx = tx.Where("model_name like ?", modelName)
 	}
 	if tokenName != "" {
 		tx = tx.Where("token_name = ?", tokenName)
@@ -144,23 +151,30 @@ func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int
 	if endTimestamp != 0 {
 		tx = tx.Where("created_at <= ?", endTimestamp)
 	}
-
 	err = tx.Model(&Log{}).Count(&total).Error
 	if err != nil {
 		return nil, 0, err
 	}
-
 	err = tx.Order("id desc").Limit(num).Offset(startIdx).Omit("id").Find(&logs).Error
+	for i := range logs {
+		var otherMap map[string]interface{}
+		otherMap = common.StrToMap(logs[i].Other)
+		if otherMap != nil {
+			// delete admin
+			delete(otherMap, "admin_info")
+		}
+		logs[i].Other = common.MapToJsonStr(otherMap)
+	}
 	return logs, total, err
 }
 
 func SearchAllLogs(keyword string) (logs []*Log, err error) {
-	err = DB.Where("type = ? or content LIKE ?", keyword, keyword+"%").Order("id desc").Limit(common.MaxRecentItems).Find(&logs).Error
+	err = LOG_DB.Where("type = ? or content LIKE ?", keyword, keyword+"%").Order("id desc").Limit(common.MaxRecentItems).Find(&logs).Error
 	return logs, err
 }
 
 func SearchUserLogs(userId int, keyword string) (logs []*Log, err error) {
-	err = DB.Where("user_id = ? and type = ?", userId, keyword).Order("id desc").Limit(common.MaxRecentItems).Omit("id").Find(&logs).Error
+	err = LOG_DB.Where("user_id = ? and type = ?", userId, keyword).Order("id desc").Limit(common.MaxRecentItems).Omit("id").Find(&logs).Error
 	return logs, err
 }
 
@@ -171,12 +185,18 @@ type Stat struct {
 }
 
 func SumUsedQuota(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string, channel int) (stat Stat) {
-	tx := DB.Table("logs").Select("sum(quota) quota, count(*) rpm, sum(prompt_tokens) + sum(completion_tokens) tpm")
+	tx := LOG_DB.Table("logs").Select("sum(quota) quota")
+
+	// 为rpm和tpm创建单独的查询
+	rpmTpmQuery := LOG_DB.Table("logs").Select("count(*) rpm, sum(prompt_tokens) + sum(completion_tokens) tpm")
+
 	if username != "" {
 		tx = tx.Where("username = ?", username)
+		rpmTpmQuery = rpmTpmQuery.Where("username = ?", username)
 	}
 	if tokenName != "" {
 		tx = tx.Where("token_name = ?", tokenName)
+		rpmTpmQuery = rpmTpmQuery.Where("token_name = ?", tokenName)
 	}
 	if startTimestamp != 0 {
 		tx = tx.Where("created_at >= ?", startTimestamp)
@@ -185,17 +205,29 @@ func SumUsedQuota(logType int, startTimestamp int64, endTimestamp int64, modelNa
 		tx = tx.Where("created_at <= ?", endTimestamp)
 	}
 	if modelName != "" {
-		tx = tx.Where("model_name = ?", modelName)
+		tx = tx.Where("model_name like ?", modelName)
+		rpmTpmQuery = rpmTpmQuery.Where("model_name like ?", modelName)
 	}
 	if channel != 0 {
 		tx = tx.Where("channel_id = ?", channel)
+		rpmTpmQuery = rpmTpmQuery.Where("channel_id = ?", channel)
 	}
-	tx.Where("type = ?", LogTypeConsume).Scan(&stat)
+
+	tx = tx.Where("type = ?", LogTypeConsume)
+	rpmTpmQuery = rpmTpmQuery.Where("type = ?", LogTypeConsume)
+
+	// 只统计最近60秒的rpm和tpm
+	rpmTpmQuery = rpmTpmQuery.Where("created_at >= ?", time.Now().Add(-60*time.Second).Unix())
+
+	// 执行查询
+	tx.Scan(&stat)
+	rpmTpmQuery.Scan(&stat)
+
 	return stat
 }
 
 func SumUsedToken(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string) (token int) {
-	tx := DB.Table("logs").Select("ifnull(sum(prompt_tokens),0) + ifnull(sum(completion_tokens),0)")
+	tx := LOG_DB.Table("logs").Select("ifnull(sum(prompt_tokens),0) + ifnull(sum(completion_tokens),0)")
 	if username != "" {
 		tx = tx.Where("username = ?", username)
 	}
@@ -215,7 +247,25 @@ func SumUsedToken(logType int, startTimestamp int64, endTimestamp int64, modelNa
 	return token
 }
 
-func DeleteOldLog(targetTimestamp int64) (int64, error) {
-	result := DB.Where("created_at < ?", targetTimestamp).Delete(&Log{})
-	return result.RowsAffected, result.Error
+func DeleteOldLog(ctx context.Context, targetTimestamp int64, limit int) (int64, error) {
+	var total int64 = 0
+
+	for {
+		if nil != ctx.Err() {
+			return total, ctx.Err()
+		}
+
+		result := LOG_DB.Where("created_at < ?", targetTimestamp).Limit(limit).Delete(&Log{})
+		if nil != result.Error {
+			return total, result.Error
+		}
+
+		total += result.RowsAffected
+
+		if result.RowsAffected < int64(limit) {
+			break
+		}
+	}
+
+	return total, nil
 }

model/main.go

@@ -15,6 +15,8 @@ import (
 
 var DB *gorm.DB
 
+var LOG_DB *gorm.DB
+
 func createRootAccountIfNeed() error {
 	var user User
 	//if user.Status != common.UserStatusEnabled {
@@ -30,7 +32,7 @@ func createRootAccountIfNeed() error {
 			Role:        common.RoleRootUser,
 			Status:      common.UserStatusEnabled,
 			DisplayName: "Root User",
-			AccessToken: common.GetUUID(),
+			AccessToken: nil,
 			Quota:       100000000,
 		}
 		DB.Create(&rootUser)
@@ -38,9 +40,9 @@ func createRootAccountIfNeed() error {
 	return nil
 }
 
-func chooseDB() (*gorm.DB, error) {
-	if os.Getenv("SQL_DSN") != "" {
-		dsn := os.Getenv("SQL_DSN")
+func chooseDB(envName string) (*gorm.DB, error) {
+	dsn := os.Getenv(envName)
+	if dsn != "" {
 		if strings.HasPrefix(dsn, "postgres://") {
 			// Use PostgreSQL
 			common.SysLog("using PostgreSQL as database")
@@ -52,6 +54,13 @@ func chooseDB() (*gorm.DB, error) {
 				PrepareStmt: true, // precompile SQL
 			})
 		}
+		if strings.HasPrefix(dsn, "local") {
+			common.SysLog("SQL_DSN not set, using SQLite as database")
+			common.UsingSQLite = true
+			return gorm.Open(sqlite.Open(common.SQLitePath), &gorm.Config{
+				PrepareStmt: true, // precompile SQL
+			})
+		}
 		// Use MySQL
 		common.SysLog("using MySQL as database")
 		// check parseTime
@@ -76,7 +85,7 @@ func chooseDB() (*gorm.DB, error) {
 }
 
 func InitDB() (err error) {
-	db, err := chooseDB()
+	db, err := chooseDB("SQL_DSN")
 	if err == nil {
 		if common.DebugEnabled {
 			db = db.Debug()
@@ -86,62 +95,21 @@ func InitDB() (err error) {
 		if err != nil {
 			return err
 		}
-		sqlDB.SetMaxIdleConns(common.GetOrDefault("SQL_MAX_IDLE_CONNS", 100))
-		sqlDB.SetMaxOpenConns(common.GetOrDefault("SQL_MAX_OPEN_CONNS", 1000))
-		sqlDB.SetConnMaxLifetime(time.Second * time.Duration(common.GetOrDefault("SQL_MAX_LIFETIME", 60)))
+		sqlDB.SetMaxIdleConns(common.GetEnvOrDefault("SQL_MAX_IDLE_CONNS", 100))
+		sqlDB.SetMaxOpenConns(common.GetEnvOrDefault("SQL_MAX_OPEN_CONNS", 1000))
+		sqlDB.SetConnMaxLifetime(time.Second * time.Duration(common.GetEnvOrDefault("SQL_MAX_LIFETIME", 60)))
 
 		if !common.IsMasterNode {
 			return nil
 		}
-		if common.UsingMySQL {
-			_, _ = sqlDB.Exec("DROP INDEX idx_channels_key ON channels;")             // TODO: delete this line when most users have upgraded
-			_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY action VARCHAR(40);")   // TODO: delete this line when most users have upgraded
-			_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY progress VARCHAR(30);") // TODO: delete this line when most users have upgraded
-			_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY status VARCHAR(20);")   // TODO: delete this line when most users have upgraded
-		}
+		//if common.UsingMySQL {
+		//	_, _ = sqlDB.Exec("DROP INDEX idx_channels_key ON channels;")             // TODO: delete this line when most users have upgraded
+		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY action VARCHAR(40);")   // TODO: delete this line when most users have upgraded
+		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY progress VARCHAR(30);") // TODO: delete this line when most users have upgraded
+		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY status VARCHAR(20);")   // TODO: delete this line when most users have upgraded
+		//}
 		common.SysLog("database migration started")
-		err = db.AutoMigrate(&Channel{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Token{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&User{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Option{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Redemption{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Ability{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Log{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Midjourney{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&TopUp{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&QuotaData{})
-		if err != nil {
-			return err
-		}
-		common.SysLog("database migrated")
-		err = createRootAccountIfNeed()
+		err = migrateDB()
 		return err
 	} else {
 		common.FatalLog(err)
@@ -149,8 +117,103 @@ func InitDB() (err error) {
 	return err
 }
 
-func CloseDB() error {
-	sqlDB, err := DB.DB()
+func InitLogDB() (err error) {
+	if os.Getenv("LOG_SQL_DSN") == "" {
+		LOG_DB = DB
+		return
+	}
+	db, err := chooseDB("LOG_SQL_DSN")
+	if err == nil {
+		if common.DebugEnabled {
+			db = db.Debug()
+		}
+		LOG_DB = db
+		sqlDB, err := LOG_DB.DB()
+		if err != nil {
+			return err
+		}
+		sqlDB.SetMaxIdleConns(common.GetEnvOrDefault("SQL_MAX_IDLE_CONNS", 100))
+		sqlDB.SetMaxOpenConns(common.GetEnvOrDefault("SQL_MAX_OPEN_CONNS", 1000))
+		sqlDB.SetConnMaxLifetime(time.Second * time.Duration(common.GetEnvOrDefault("SQL_MAX_LIFETIME", 60)))
+
+		if !common.IsMasterNode {
+			return nil
+		}
+		//if common.UsingMySQL {
+		//	_, _ = sqlDB.Exec("DROP INDEX idx_channels_key ON channels;")             // TODO: delete this line when most users have upgraded
+		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY action VARCHAR(40);")   // TODO: delete this line when most users have upgraded
+		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY progress VARCHAR(30);") // TODO: delete this line when most users have upgraded
+		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY status VARCHAR(20);")   // TODO: delete this line when most users have upgraded
+		//}
+		common.SysLog("database migration started")
+		err = migrateLOGDB()
+		return err
+	} else {
+		common.FatalLog(err)
+	}
+	return err
+}
+
+func migrateDB() error {
+	err := DB.AutoMigrate(&Channel{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Token{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&User{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Option{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Redemption{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Ability{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Log{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Midjourney{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&TopUp{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&QuotaData{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Task{})
+	if err != nil {
+		return err
+	}
+	common.SysLog("database migrated")
+	err = createRootAccountIfNeed()
+	return err
+}
+
+func migrateLOGDB() error {
+	var err error
+	if err = LOG_DB.AutoMigrate(&Log{}); err != nil {
+		return err
+	}
+	return nil
+}
+
+func closeDB(db *gorm.DB) error {
+	sqlDB, err := db.DB()
 	if err != nil {
 		return err
 	}
@@ -158,6 +221,16 @@ func CloseDB() error {
 	return err
 }
 
+func CloseDB() error {
+	if LOG_DB != DB {
+		err := closeDB(LOG_DB)
+		if err != nil {
+			return err
+		}
+	}
+	return closeDB(DB)
+}
+
 var (
 	lastPingTime time.Time
 	pingMutex    sync.Mutex

model/option.go

@@ -43,6 +43,7 @@ func InitOptionMap() {
 	common.OptionMap["DisplayInCurrencyEnabled"] = strconv.FormatBool(common.DisplayInCurrencyEnabled)
 	common.OptionMap["DisplayTokenStatEnabled"] = strconv.FormatBool(common.DisplayTokenStatEnabled)
 	common.OptionMap["DrawingEnabled"] = strconv.FormatBool(common.DrawingEnabled)
+	common.OptionMap["TaskEnabled"] = strconv.FormatBool(common.TaskEnabled)
 	common.OptionMap["DataExportEnabled"] = strconv.FormatBool(common.DataExportEnabled)
 	common.OptionMap["ChannelDisableThreshold"] = strconv.FormatFloat(common.ChannelDisableThreshold, 'f', -1, 64)
 	common.OptionMap["EmailDomainRestrictionEnabled"] = strconv.FormatBool(common.EmailDomainRestrictionEnabled)
@@ -61,6 +62,7 @@ func InitOptionMap() {
 	common.OptionMap["SystemName"] = common.SystemName
 	common.OptionMap["Logo"] = common.Logo
 	common.OptionMap["ServerAddress"] = ""
+	common.OptionMap["OutProxyUrl"] = ""
 	common.OptionMap["StripeApiSecret"] = common.StripeApiSecret
 	common.OptionMap["StripeWebhookSecret"] = common.StripeWebhookSecret
 	common.OptionMap["StripePriceId"] = common.StripePriceId
@@ -68,6 +70,7 @@ func InitOptionMap() {
 	common.OptionMap["StripeUnitPrice"] = strconv.FormatFloat(common.StripeUnitPrice, 'f', -1, 64)
 	common.OptionMap["MinTopUp"] = strconv.Itoa(common.MinTopUp)
 	common.OptionMap["TopupGroupRatio"] = common.TopupGroupRatio2JSONString()
+	common.OptionMap["Chats"] = constant.Chats2JsonString()
 	common.OptionMap["GitHubClientId"] = ""
 	common.OptionMap["GitHubClientSecret"] = ""
 	common.OptionMap["LinuxDoClientId"] = ""
@@ -88,6 +91,8 @@ func InitOptionMap() {
 	common.OptionMap["ModelRatio"] = common.ModelRatio2JSONString()
 	common.OptionMap["ModelPrice"] = common.ModelPrice2JSONString()
 	common.OptionMap["GroupRatio"] = common.GroupRatio2JSONString()
+	common.OptionMap["UserUsableGroups"] = common.UserUsableGroups2JSONString()
+	common.OptionMap["CompletionRatio"] = common.CompletionRatio2JSONString()
 	common.OptionMap["TopUpLink"] = common.TopUpLink
 	common.OptionMap["ChatLink"] = common.ChatLink
 	common.OptionMap["ChatLink2"] = common.ChatLink2
@@ -100,6 +105,7 @@ func InitOptionMap() {
 	common.OptionMap["MjAccountFilterEnabled"] = strconv.FormatBool(constant.MjAccountFilterEnabled)
 	common.OptionMap["MjModeClearEnabled"] = strconv.FormatBool(constant.MjModeClearEnabled)
 	common.OptionMap["MjForwardUrlEnabled"] = strconv.FormatBool(constant.MjForwardUrlEnabled)
+	common.OptionMap["MjActionCheckSuccessEnabled"] = strconv.FormatBool(constant.MjActionCheckSuccessEnabled)
 	common.OptionMap["CheckSensitiveEnabled"] = strconv.FormatBool(constant.CheckSensitiveEnabled)
 	common.OptionMap["CheckSensitiveOnPromptEnabled"] = strconv.FormatBool(constant.CheckSensitiveOnPromptEnabled)
 	//common.OptionMap["CheckSensitiveOnCompletionEnabled"] = strconv.FormatBool(constant.CheckSensitiveOnCompletionEnabled)
@@ -201,6 +207,8 @@ func updateOptionMap(key string, value string) (err error) {
 			common.DisplayTokenStatEnabled = boolValue
 		case "DrawingEnabled":
 			common.DrawingEnabled = boolValue
+		case "TaskEnabled":
+			common.TaskEnabled = boolValue
 		case "DataExportEnabled":
 			common.DataExportEnabled = boolValue
 		case "DefaultCollapseSidebar":
@@ -213,6 +221,8 @@ func updateOptionMap(key string, value string) (err error) {
 			constant.MjModeClearEnabled = boolValue
 		case "MjForwardUrlEnabled":
 			constant.MjForwardUrlEnabled = boolValue
+		case "MjActionCheckSuccessEnabled":
+			constant.MjActionCheckSuccessEnabled = boolValue
 		case "CheckSensitiveEnabled":
 			constant.CheckSensitiveEnabled = boolValue
 		case "CheckSensitiveOnPromptEnabled":
@@ -241,6 +251,10 @@ func updateOptionMap(key string, value string) (err error) {
 		common.SMTPToken = value
 	case "ServerAddress":
 		common.ServerAddress = value
+	case "OutProxyUrl":
+		common.OutProxyUrl = value
+	case "Chats":
+		err = constant.UpdateChatsByJsonString(value)
 	case "StripeApiSecret":
 		common.StripeApiSecret = value
 	case "StripeWebhookSecret":
@@ -305,6 +319,10 @@ func updateOptionMap(key string, value string) (err error) {
 		err = common.UpdateModelRatioByJSONString(value)
 	case "GroupRatio":
 		err = common.UpdateGroupRatioByJSONString(value)
+	case "UserUsableGroups":
+		err = common.UpdateUserUsableGroupsByJSONString(value)
+	case "CompletionRatio":
+		err = common.UpdateCompletionRatioByJSONString(value)
 	case "ModelPrice":
 		err = common.UpdateModelPriceByJSONString(value)
 	case "TopUpLink":

model/pricing.go

@@ -0,0 +1,79 @@
+package model
+
+import (
+	"one-api/common"
+	"sync"
+	"time"
+)
+
+type Pricing struct {
+	ModelName       string   `json:"model_name"`
+	QuotaType       int      `json:"quota_type"`
+	ModelRatio      float64  `json:"model_ratio"`
+	ModelPrice      float64  `json:"model_price"`
+	OwnerBy         string   `json:"owner_by"`
+	CompletionRatio float64  `json:"completion_ratio"`
+	EnableGroup     []string `json:"enable_groups,omitempty"`
+}
+
+var (
+	pricingMap         []Pricing
+	lastGetPricingTime time.Time
+	updatePricingLock  sync.Mutex
+)
+
+func GetPricing() []Pricing {
+	updatePricingLock.Lock()
+	defer updatePricingLock.Unlock()
+
+	if time.Since(lastGetPricingTime) > time.Minute*1 || len(pricingMap) == 0 {
+		updatePricing()
+	}
+	//if group != "" {
+	//	userPricingMap := make([]Pricing, 0)
+	//	models := GetGroupModels(group)
+	//	for _, pricing := range pricingMap {
+	//		if !common.StringsContains(models, pricing.ModelName) {
+	//			pricing.Available = false
+	//		}
+	//		userPricingMap = append(userPricingMap, pricing)
+	//	}
+	//	return userPricingMap
+	//}
+	return pricingMap
+}
+
+func updatePricing() {
+	//modelRatios := common.GetModelRatios()
+	enableAbilities := GetAllEnableAbilities()
+	modelGroupsMap := make(map[string][]string)
+	for _, ability := range enableAbilities {
+		groups := modelGroupsMap[ability.Model]
+		if groups == nil {
+			groups = make([]string, 0)
+		}
+		if !common.StringsContains(groups, ability.Group) {
+			groups = append(groups, ability.Group)
+		}
+		modelGroupsMap[ability.Model] = groups
+	}
+
+	pricingMap = make([]Pricing, 0)
+	for model, groups := range modelGroupsMap {
+		pricing := Pricing{
+			ModelName:   model,
+			EnableGroup: groups,
+		}
+		modelPrice, findPrice := common.GetModelPrice(model, false)
+		if findPrice {
+			pricing.ModelPrice = modelPrice
+			pricing.QuotaType = 1
+		} else {
+			pricing.ModelRatio = common.GetModelRatio(model)
+			pricing.CompletionRatio = common.GetCompletionRatio(model)
+			pricing.QuotaType = 0
+		}
+		pricingMap = append(pricingMap, pricing)
+	}
+	lastGetPricingTime = time.Now()
+}

model/redemption.go

@@ -78,7 +78,7 @@ func Redeem(key string, userId int) (quota int, err error) {
 	if err != nil {
 		return 0, errors.New("兑换失败，" + err.Error())
 	}
-	RecordLog(userId, LogTypeTopup, fmt.Sprintf("通过兑换码充值 %s", common.LogQuota(redemption.Quota)))
+	RecordLog(userId, LogTypeTopup, fmt.Sprintf("通过兑换码充值 %s，兑换码ID %d", common.LogQuota(redemption.Quota), redemption.Id))
 	return redemption.Quota, nil
 }
 

model/task.go

@@ -0,0 +1,304 @@
+package model
+
+import (
+	"database/sql/driver"
+	"encoding/json"
+	"one-api/constant"
+	commonRelay "one-api/relay/common"
+	"time"
+)
+
+type TaskStatus string
+
+const (
+	TaskStatusNotStart   TaskStatus = "NOT_START"
+	TaskStatusSubmitted             = "SUBMITTED"
+	TaskStatusQueued                = "QUEUED"
+	TaskStatusInProgress            = "IN_PROGRESS"
+	TaskStatusFailure               = "FAILURE"
+	TaskStatusSuccess               = "SUCCESS"
+	TaskStatusUnknown               = "UNKNOWN"
+)
+
+type Task struct {
+	ID         int64                 `json:"id" gorm:"primary_key;AUTO_INCREMENT"`
+	CreatedAt  int64                 `json:"created_at" gorm:"index"`
+	UpdatedAt  int64                 `json:"updated_at"`
+	TaskID     string                `json:"task_id" gorm:"type:varchar(50);index"`  // 第三方id，不一定有/ song id\ Task id
+	Platform   constant.TaskPlatform `json:"platform" gorm:"type:varchar(30);index"` // 平台
+	UserId     int                   `json:"user_id" gorm:"index"`
+	ChannelId  int                   `json:"channel_id" gorm:"index"`
+	Quota      int                   `json:"quota"`
+	Action     string                `json:"action" gorm:"type:varchar(40);index"` // 任务类型, song, lyrics, description-mode
+	Status     TaskStatus            `json:"status" gorm:"type:varchar(20);index"` // 任务状态
+	FailReason string                `json:"fail_reason"`
+	SubmitTime int64                 `json:"submit_time" gorm:"index"`
+	StartTime  int64                 `json:"start_time" gorm:"index"`
+	FinishTime int64                 `json:"finish_time" gorm:"index"`
+	Progress   string                `json:"progress" gorm:"type:varchar(20);index"`
+	Properties Properties            `json:"properties" gorm:"type:json"`
+
+	Data json.RawMessage `json:"data" gorm:"type:json"`
+}
+
+func (t *Task) SetData(data any) {
+	b, _ := json.Marshal(data)
+	t.Data = json.RawMessage(b)
+}
+
+func (t *Task) GetData(v any) error {
+	err := json.Unmarshal(t.Data, &v)
+	return err
+}
+
+type Properties struct {
+	Input string `json:"input"`
+}
+
+func (m *Properties) Scan(val interface{}) error {
+	bytesValue, _ := val.([]byte)
+	return json.Unmarshal(bytesValue, m)
+}
+
+func (m Properties) Value() (driver.Value, error) {
+	return json.Marshal(m)
+}
+
+// SyncTaskQueryParams 用于包含所有搜索条件的结构体，可以根据需求添加更多字段
+type SyncTaskQueryParams struct {
+	Platform       constant.TaskPlatform
+	ChannelID      string
+	TaskID         string
+	UserID         string
+	Action         string
+	Status         string
+	StartTimestamp int64
+	EndTimestamp   int64
+	UserIDs        []int
+}
+
+func InitTask(platform constant.TaskPlatform, relayInfo *commonRelay.TaskRelayInfo) *Task {
+	t := &Task{
+		UserId:     relayInfo.UserId,
+		SubmitTime: time.Now().Unix(),
+		Status:     TaskStatusNotStart,
+		Progress:   "0%",
+		ChannelId:  relayInfo.ChannelId,
+		Platform:   platform,
+	}
+	return t
+}
+
+func TaskGetAllUserTask(userId int, startIdx int, num int, queryParams SyncTaskQueryParams) []*Task {
+	var tasks []*Task
+	var err error
+
+	// 初始化查询构建器
+	query := DB.Where("user_id = ?", userId)
+
+	if queryParams.TaskID != "" {
+		query = query.Where("task_id = ?", queryParams.TaskID)
+	}
+	if queryParams.Action != "" {
+		query = query.Where("action = ?", queryParams.Action)
+	}
+	if queryParams.Status != "" {
+		query = query.Where("status = ?", queryParams.Status)
+	}
+	if queryParams.Platform != "" {
+		query = query.Where("platform = ?", queryParams.Platform)
+	}
+	if queryParams.StartTimestamp != 0 {
+		// 假设您已将前端传来的时间戳转换为数据库所需的时间格式，并处理了时间戳的验证和解析
+		query = query.Where("submit_time >= ?", queryParams.StartTimestamp)
+	}
+	if queryParams.EndTimestamp != 0 {
+		query = query.Where("submit_time <= ?", queryParams.EndTimestamp)
+	}
+
+	// 获取数据
+	err = query.Omit("channel_id").Order("id desc").Limit(num).Offset(startIdx).Find(&tasks).Error
+	if err != nil {
+		return nil
+	}
+
+	return tasks
+}
+
+func TaskGetAllTasks(startIdx int, num int, queryParams SyncTaskQueryParams) []*Task {
+	var tasks []*Task
+	var err error
+
+	// 初始化查询构建器
+	query := DB
+
+	// 添加过滤条件
+	if queryParams.ChannelID != "" {
+		query = query.Where("channel_id = ?", queryParams.ChannelID)
+	}
+	if queryParams.Platform != "" {
+		query = query.Where("platform = ?", queryParams.Platform)
+	}
+	if queryParams.UserID != "" {
+		query = query.Where("user_id = ?", queryParams.UserID)
+	}
+	if len(queryParams.UserIDs) != 0 {
+		query = query.Where("user_id in (?)", queryParams.UserIDs)
+	}
+	if queryParams.TaskID != "" {
+		query = query.Where("task_id = ?", queryParams.TaskID)
+	}
+	if queryParams.Action != "" {
+		query = query.Where("action = ?", queryParams.Action)
+	}
+	if queryParams.Status != "" {
+		query = query.Where("status = ?", queryParams.Status)
+	}
+	if queryParams.StartTimestamp != 0 {
+		query = query.Where("submit_time >= ?", queryParams.StartTimestamp)
+	}
+	if queryParams.EndTimestamp != 0 {
+		query = query.Where("submit_time <= ?", queryParams.EndTimestamp)
+	}
+
+	// 获取数据
+	err = query.Order("id desc").Limit(num).Offset(startIdx).Find(&tasks).Error
+	if err != nil {
+		return nil
+	}
+
+	return tasks
+}
+
+func GetAllUnFinishSyncTasks(limit int) []*Task {
+	var tasks []*Task
+	var err error
+	// get all tasks progress is not 100%
+	err = DB.Where("progress != ?", "100%").Limit(limit).Order("id").Find(&tasks).Error
+	if err != nil {
+		return nil
+	}
+	return tasks
+}
+
+func GetByOnlyTaskId(taskId string) (*Task, bool, error) {
+	if taskId == "" {
+		return nil, false, nil
+	}
+	var task *Task
+	var err error
+	err = DB.Where("task_id = ?", taskId).First(&task).Error
+	exist, err := RecordExist(err)
+	if err != nil {
+		return nil, false, err
+	}
+	return task, exist, err
+}
+
+func GetByTaskId(userId int, taskId string) (*Task, bool, error) {
+	if taskId == "" {
+		return nil, false, nil
+	}
+	var task *Task
+	var err error
+	err = DB.Where("user_id = ? and task_id = ?", userId, taskId).
+		First(&task).Error
+	exist, err := RecordExist(err)
+	if err != nil {
+		return nil, false, err
+	}
+	return task, exist, err
+}
+
+func GetByTaskIds(userId int, taskIds []any) ([]*Task, error) {
+	if len(taskIds) == 0 {
+		return nil, nil
+	}
+	var task []*Task
+	var err error
+	err = DB.Where("user_id = ? and task_id in (?)", userId, taskIds).
+		Find(&task).Error
+	if err != nil {
+		return nil, err
+	}
+	return task, nil
+}
+
+func TaskUpdateProgress(id int64, progress string) error {
+	return DB.Model(&Task{}).Where("id = ?", id).Update("progress", progress).Error
+}
+
+func (Task *Task) Insert() error {
+	var err error
+	err = DB.Create(Task).Error
+	return err
+}
+
+func (Task *Task) Update() error {
+	var err error
+	err = DB.Save(Task).Error
+	return err
+}
+
+func TaskBulkUpdate(TaskIds []string, params map[string]any) error {
+	if len(TaskIds) == 0 {
+		return nil
+	}
+	return DB.Model(&Task{}).
+		Where("task_id in (?)", TaskIds).
+		Updates(params).Error
+}
+
+func TaskBulkUpdateByTaskIds(taskIDs []int64, params map[string]any) error {
+	if len(taskIDs) == 0 {
+		return nil
+	}
+	return DB.Model(&Task{}).
+		Where("id in (?)", taskIDs).
+		Updates(params).Error
+}
+
+func TaskBulkUpdateByID(ids []int64, params map[string]any) error {
+	if len(ids) == 0 {
+		return nil
+	}
+	return DB.Model(&Task{}).
+		Where("id in (?)", ids).
+		Updates(params).Error
+}
+
+type TaskQuotaUsage struct {
+	Mode  string  `json:"mode"`
+	Count float64 `json:"count"`
+}
+
+func SumUsedTaskQuota(queryParams SyncTaskQueryParams) (stat []TaskQuotaUsage, err error) {
+	query := DB.Model(Task{})
+	// 添加过滤条件
+	if queryParams.ChannelID != "" {
+		query = query.Where("channel_id = ?", queryParams.ChannelID)
+	}
+	if queryParams.UserID != "" {
+		query = query.Where("user_id = ?", queryParams.UserID)
+	}
+	if len(queryParams.UserIDs) != 0 {
+		query = query.Where("user_id in (?)", queryParams.UserIDs)
+	}
+	if queryParams.TaskID != "" {
+		query = query.Where("task_id = ?", queryParams.TaskID)
+	}
+	if queryParams.Action != "" {
+		query = query.Where("action = ?", queryParams.Action)
+	}
+	if queryParams.Status != "" {
+		query = query.Where("status = ?", queryParams.Status)
+	}
+	if queryParams.StartTimestamp != 0 {
+		query = query.Where("submit_time >= ?", queryParams.StartTimestamp)
+	}
+	if queryParams.EndTimestamp != 0 {
+		query = query.Where("submit_time <= ?", queryParams.EndTimestamp)
+	}
+	err = query.Select("mode, sum(quota) as count").Group("mode").Find(&stat).Error
+	return stat, err
+}

model/token.go

@@ -5,13 +5,14 @@ import (
 	"fmt"
 	"gorm.io/gorm"
 	"one-api/common"
+	relaycommon "one-api/relay/common"
 	"strconv"
 	"strings"
 )
 
 type Token struct {
 	Id                 int            `json:"id"`
-	UserId             int            `json:"user_id"`
+	UserId             int            `json:"user_id" gorm:"index"`
 	Key                string         `json:"key" gorm:"type:char(48);uniqueIndex"`
 	Status             int            `json:"status" gorm:"default:1"`
 	Name               string         `json:"name" gorm:"index" `
@@ -22,10 +23,34 @@ type Token struct {
 	UnlimitedQuota     bool           `json:"unlimited_quota" gorm:"default:false"`
 	ModelLimitsEnabled bool           `json:"model_limits_enabled" gorm:"default:false"`
 	ModelLimits        string         `json:"model_limits" gorm:"type:varchar(1024);default:''"`
+	AllowIps           *string        `json:"allow_ips" gorm:"default:''"`
 	UsedQuota          int            `json:"used_quota" gorm:"default:0"` // used quota
+	Group              string         `json:"group" gorm:"default:''"`
 	DeletedAt          gorm.DeletedAt `gorm:"index"`
 }
 
+func (token *Token) GetIpLimitsMap() map[string]any {
+	// delete empty spaces
+	//split with \n
+	ipLimitsMap := make(map[string]any)
+	if token.AllowIps == nil {
+		return ipLimitsMap
+	}
+	cleanIps := strings.ReplaceAll(*token.AllowIps, " ", "")
+	if cleanIps == "" {
+		return ipLimitsMap
+	}
+	ips := strings.Split(cleanIps, "\n")
+	for _, ip := range ips {
+		ip = strings.TrimSpace(ip)
+		ip = strings.ReplaceAll(ip, ",", "")
+		if common.IsIP(ip) {
+			ipLimitsMap[ip] = true
+		}
+	}
+	return ipLimitsMap
+}
+
 func GetAllUserTokens(userId int, startIdx int, num int) ([]*Token, error) {
 	var tokens []*Token
 	var err error
@@ -50,12 +75,12 @@ func ValidateUserToken(key string) (token *Token, err error) {
 		if token.Status == common.TokenStatusExhausted {
 			keyPrefix := key[:3]
 			keySuffix := key[len(key)-3:]
-			return nil, errors.New("该令牌额度已用尽 TokenStatusExhausted[sk-" + keyPrefix + "***" + keySuffix + "]")
+			return token, errors.New("该令牌额度已用尽 TokenStatusExhausted[sk-" + keyPrefix + "***" + keySuffix + "]")
 		} else if token.Status == common.TokenStatusExpired {
-			return nil, errors.New("该令牌已过期")
+			return token, errors.New("该令牌已过期")
 		}
 		if token.Status != common.TokenStatusEnabled {
-			return nil, errors.New("该令牌状态不可用")
+			return token, errors.New("该令牌状态不可用")
 		}
 		if token.ExpiredTime != -1 && token.ExpiredTime < common.GetTimestamp() {
 			if !common.RedisEnabled {
@@ -65,7 +90,7 @@ func ValidateUserToken(key string) (token *Token, err error) {
 					common.SysError("failed to update token status" + err.Error())
 				}
 			}
-			return nil, errors.New("该令牌已过期")
+			return token, errors.New("该令牌已过期")
 		}
 		if !token.UnlimitedQuota && token.RemainQuota <= 0 {
 			if !common.RedisEnabled {
@@ -78,7 +103,7 @@ func ValidateUserToken(key string) (token *Token, err error) {
 			}
 			keyPrefix := key[:3]
 			keySuffix := key[len(key)-3:]
-			return nil, errors.New(fmt.Sprintf("[sk-%s***%s] 该令牌额度已用尽 !token.UnlimitedQuota && token.RemainQuota = %d", keyPrefix, keySuffix, token.RemainQuota))
+			return token, errors.New(fmt.Sprintf("[sk-%s***%s] 该令牌额度已用尽 !token.UnlimitedQuota && token.RemainQuota = %d", keyPrefix, keySuffix, token.RemainQuota))
 		}
 		return token, nil
 	}
@@ -129,7 +154,8 @@ func (token *Token) Insert() error {
 // Update Make sure your token's fields is completed, because this will update non-zero values
 func (token *Token) Update() error {
 	var err error
-	err = DB.Model(token).Select("name", "status", "expired_time", "remain_quota", "unlimited_quota", "model_limits_enabled", "model_limits").Updates(token).Error
+	err = DB.Model(token).Select("name", "status", "expired_time", "remain_quota", "unlimited_quota",
+		"model_limits_enabled", "model_limits", "allow_ips", "group").Updates(token).Error
 	return err
 }
 
@@ -231,51 +257,52 @@ func decreaseTokenQuota(id int, quota int) (err error) {
 	return err
 }
 
-func PreConsumeTokenQuota(tokenId int, quota int) (userQuota int, err error) {
+func PreConsumeTokenQuota(relayInfo *relaycommon.RelayInfo, quota int) (userQuota int, err error) {
 	if quota < 0 {
 		return 0, errors.New("quota 不能为负数！")
 	}
-	token, err := GetTokenById(tokenId)
-	if err != nil {
-		return 0, err
+	if !relayInfo.IsPlayground {
+		token, err := GetTokenById(relayInfo.TokenId)
+		if err != nil {
+			return 0, err
+		}
+		if !token.UnlimitedQuota && token.RemainQuota < quota {
+			return 0, errors.New("令牌额度不足")
+		}
 	}
-	if !token.UnlimitedQuota && token.RemainQuota < quota {
-		return 0, errors.New("令牌额度不足")
-	}
-	userQuota, err = GetUserQuota(token.UserId)
+	userQuota, err = GetUserQuota(relayInfo.UserId)
 	if err != nil {
 		return 0, err
 	}
 	if userQuota < quota {
 		return 0, errors.New(fmt.Sprintf("用户额度不足，剩余额度为 %d", userQuota))
 	}
-	if !token.UnlimitedQuota {
-		err = DecreaseTokenQuota(tokenId, quota)
+	if !relayInfo.IsPlayground {
+		err = DecreaseTokenQuota(relayInfo.TokenId, quota)
 		if err != nil {
 			return 0, err
 		}
 	}
-	err = DecreaseUserQuota(token.UserId, quota)
+	err = DecreaseUserQuota(relayInfo.UserId, quota)
 	return userQuota - quota, err
 }
 
-func PostConsumeTokenQuota(tokenId int, userQuota int, quota int, preConsumedQuota int, sendEmail bool) (err error) {
-	token, err := GetTokenById(tokenId)
+func PostConsumeTokenQuota(relayInfo *relaycommon.RelayInfo, userQuota int, quota int, preConsumedQuota int, sendEmail bool) (err error) {
 
 	if quota > 0 {
-		err = DecreaseUserQuota(token.UserId, quota)
+		err = DecreaseUserQuota(relayInfo.UserId, quota)
 	} else {
-		err = IncreaseUserQuota(token.UserId, -quota)
+		err = IncreaseUserQuota(relayInfo.UserId, -quota)
 	}
 	if err != nil {
 		return err
 	}
 
-	if !token.UnlimitedQuota {
+	if !relayInfo.IsPlayground {
 		if quota > 0 {
-			err = DecreaseTokenQuota(tokenId, quota)
+			err = DecreaseTokenQuota(relayInfo.TokenId, quota)
 		} else {
-			err = IncreaseTokenQuota(tokenId, -quota)
+			err = IncreaseTokenQuota(relayInfo.TokenId, -quota)
 		}
 		if err != nil {
 			return err
@@ -288,7 +315,7 @@ func PostConsumeTokenQuota(tokenId int, userQuota int, quota int, preConsumedQuo
 			noMoreQuota := userQuota-(quota+preConsumedQuota) <= 0
 			if quotaTooLow || noMoreQuota {
 				go func() {
-					email, err := GetUserEmail(token.UserId)
+					email, err := GetUserEmail(relayInfo.UserId)
 					if err != nil {
 						common.SysError("failed to fetch user email: " + err.Error())
 					}

model/usedata.go

@@ -45,6 +45,7 @@ func logQuotaDataCache(userId int, username string, modelName string, quota int,
 	if ok {
 		quotaData.Count += 1
 		quotaData.Quota += quota
+		quotaData.TokenUsed += tokenUsed
 	} else {
 		quotaData = &QuotaData{
 			UserID:    userId,

model/user.go

@@ -27,7 +27,7 @@ type User struct {
 	WeChatId         string         `json:"wechat_id" gorm:"column:wechat_id;index"`
 	TelegramId       string         `json:"telegram_id" gorm:"column:telegram_id;index"`
 	VerificationCode string         `json:"verification_code" gorm:"-:all"`                                    // this field is only for Email verification, don't save it to database!
-	AccessToken      string         `json:"access_token" gorm:"type:char(32);column:access_token;uniqueIndex"` // this token is for system management
+	AccessToken      *string        `json:"access_token" gorm:"type:char(32);column:access_token;uniqueIndex"` // this token is for system management
 	Quota            int            `json:"quota" gorm:"type:int;default:0"`
 	UsedQuota        int            `json:"used_quota" gorm:"type:int;default:0;column:used_quota"` // used quota
 	RequestCount     int            `json:"request_count" gorm:"type:int;default:0;"`               // request number
@@ -41,6 +41,17 @@ type User struct {
 	DeletedAt        gorm.DeletedAt `gorm:"index"`
 }
 
+func (user *User) GetAccessToken() string {
+	if user.AccessToken == nil {
+		return ""
+	}
+	return *user.AccessToken
+}
+
+func (user *User) SetAccessToken(token string) {
+	user.AccessToken = &token
+}
+
 // CheckUserExistOrDeleted check if user exist or deleted, if not exist, return false, nil, if deleted or exist, return true, nil
 func CheckUserExistOrDeleted(username string, email string) (bool, error) {
 	var user User
@@ -218,7 +229,7 @@ func (user *User) Insert(inviterId int) error {
 		}
 	}
 	user.Quota = common.QuotaForNewUser
-	user.AccessToken = common.GetUUID()
+	//user.SetAccessToken(common.GetUUID())
 	user.AffCode = common.GetRandomString(4)
 	result := DB.Create(user)
 	if result.Error != nil {
@@ -312,10 +323,12 @@ func (user *User) ValidateAndFill() (err error) {
 	// that means if your field’s value is 0, '', false or other zero values,
 	// it won’t be used to build query conditions
 	password := user.Password
-	if user.Username == "" || password == "" {
+	username := strings.TrimSpace(user.Username)
+	if username == "" || password == "" {
 		return errors.New("用户名或密码为空")
 	}
-	DB.Where(User{Username: user.Username}).First(user)
+	// find buy username or email
+	DB.Where("username = ? OR email = ?", username, username).First(user)
 	okay := common.ValidatePasswordAndHash(password, user.Password)
 	if !okay || user.Status != common.UserStatusEnabled {
 		return errors.New("用户名或密码错误，或用户已被封禁")
@@ -363,14 +376,6 @@ func (user *User) FillUserByWeChatId() error {
 	return nil
 }
 
-func (user *User) FillUserByUsername() error {
-	if user.Username == "" {
-		return errors.New("username 为空！")
-	}
-	DB.Where(User{Username: user.Username}).First(user)
-	return nil
-}
-
 func (user *User) FillUserByTelegramId() error {
 	if user.TelegramId == "" {
 		return errors.New("Telegram id 为空！")
@@ -383,27 +388,27 @@ func (user *User) FillUserByTelegramId() error {
 }
 
 func IsEmailAlreadyTaken(email string) bool {
-	return DB.Where("email = ?", email).Find(&User{}).RowsAffected == 1
+	return DB.Unscoped().Where("email = ?", email).Find(&User{}).RowsAffected == 1
 }
 
 func IsWeChatIdAlreadyTaken(wechatId string) bool {
-	return DB.Where("wechat_id = ?", wechatId).Find(&User{}).RowsAffected == 1
+	return DB.Unscoped().Where("wechat_id = ?", wechatId).Find(&User{}).RowsAffected == 1
 }
 
 func IsGitHubIdAlreadyTaken(githubId string) bool {
-	return DB.Where("github_id = ?", githubId).Find(&User{}).RowsAffected == 1
+	return DB.Unscoped().Where("github_id = ?", githubId).Find(&User{}).RowsAffected == 1
 }
 
 func IsLinuxDoIdAlreadyTaken(linuxdoId string) bool {
-	return DB.Where("linuxdo_id = ?", linuxdoId).Find(&User{}).RowsAffected == 1
+	return DB.Unscoped().Where("linuxdo_id = ?", linuxdoId).Find(&User{}).RowsAffected == 1
 }
 
 func IsUsernameAlreadyTaken(username string) bool {
-	return DB.Where("username = ?", username).Find(&User{}).RowsAffected == 1
+	return DB.Unscoped().Where("username = ?", username).Find(&User{}).RowsAffected == 1
 }
 
 func IsTelegramIdAlreadyTaken(telegramId string) bool {
-	return DB.Where("telegram_id = ?", telegramId).Find(&User{}).RowsAffected == 1
+	return DB.Unscoped().Where("telegram_id = ?", telegramId).Find(&User{}).RowsAffected == 1
 }
 
 func ResetUserPasswordByEmail(email string, password string) error {

model/utils.go

@@ -1,6 +1,9 @@
 package model
 
 import (
+	"errors"
+	"github.com/bytedance/gopkg/util/gopool"
+	"gorm.io/gorm"
 	"one-api/common"
 	"sync"
 	"time"
@@ -26,12 +29,12 @@ func init() {
 }
 
 func InitBatchUpdater() {
-	go func() {
+	gopool.Go(func() {
 		for {
 			time.Sleep(time.Duration(common.BatchUpdateInterval) * time.Second)
 			batchUpdate()
 		}
-	}()
+	})
 }
 
 func addNewRecord(type_ int, id int, value int) {
@@ -75,3 +78,13 @@ func batchUpdate() {
 	}
 	common.SysLog("batch update finished")
 }
+
+func RecordExist(err error) (bool, error) {
+	if err == nil {
+		return true, nil
+	}
+	if errors.Is(err, gorm.ErrRecordNotFound) {
+		return false, nil
+	}
+	return false, err
+}

relay/channel/adapter.go

@@ -10,12 +10,34 @@ import (
 
 type Adaptor interface {
 	// Init IsStream bool
-	Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest)
+	Init(info *relaycommon.RelayInfo)
 	GetRequestURL(info *relaycommon.RelayInfo) (string, error)
 	SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error
-	ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error)
+	ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error)
+	ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error)
+	ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error)
+	ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error)
 	DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error)
 	DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode)
 	GetModelList() []string
 	GetChannelName() string
 }
+
+type TaskAdaptor interface {
+	Init(info *relaycommon.TaskRelayInfo)
+
+	ValidateRequestAndSetAction(c *gin.Context, info *relaycommon.TaskRelayInfo) *dto.TaskError
+
+	BuildRequestURL(info *relaycommon.TaskRelayInfo) (string, error)
+	BuildRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.TaskRelayInfo) error
+	BuildRequestBody(c *gin.Context, info *relaycommon.TaskRelayInfo) (io.Reader, error)
+
+	DoRequest(c *gin.Context, info *relaycommon.TaskRelayInfo, requestBody io.Reader) (*http.Response, error)
+	DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.TaskRelayInfo) (taskID string, taskData []byte, err *dto.TaskError)
+
+	GetModelList() []string
+	GetChannelName() string
+
+	// FetchTask
+	FetchTask(baseUrl, key string, body map[string]any) (*http.Response, error)
+}

relay/channel/ai360/constants.go

@@ -1,8 +1,13 @@
 package ai360
 
 var ModelList = []string{
+	"360gpt-turbo",
+	"360gpt-turbo-responsibility-8k",
+	"360gpt-pro",
 	"360GPT_S2_V9",
 	"embedding-bert-512-v1",
 	"embedding_s1_v1",
 	"semantic_similarity_s1_v1",
 }
+
+var ChannelName = "ai360"

relay/channel/ali/adaptor.go

@@ -8,6 +8,7 @@ import (
 	"net/http"
 	"one-api/dto"
 	"one-api/relay/channel"
+	"one-api/relay/channel/openai"
 	relaycommon "one-api/relay/common"
 	"one-api/relay/constant"
 )
@@ -15,14 +16,18 @@ import (
 type Adaptor struct {
 }
 
-func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
-
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-	fullRequestURL := fmt.Sprintf("%s/api/v1/services/aigc/text-generation/generation", info.BaseUrl)
-	if info.RelayMode == constant.RelayModeEmbeddings {
+	var fullRequestURL string
+	switch info.RelayMode {
+	case constant.RelayModeEmbeddings:
 		fullRequestURL = fmt.Sprintf("%s/api/v1/services/embeddings/text-embedding/text-embedding", info.BaseUrl)
+	case constant.RelayModeImagesGenerations:
+		fullRequestURL = fmt.Sprintf("%s/api/v1/services/aigc/text2image/image-synthesis", info.BaseUrl)
+	default:
+		fullRequestURL = fmt.Sprintf("%s/compatible-mode/v1/chat/completions", info.BaseUrl)
 	}
 	return fullRequestURL, nil
 }
@@ -39,33 +44,49 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *re
 	return nil
 }
 
-func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
-	switch relayMode {
+	switch info.RelayMode {
 	case constant.RelayModeEmbeddings:
 		baiduEmbeddingRequest := embeddingRequestOpenAI2Ali(*request)
 		return baiduEmbeddingRequest, nil
 	default:
-		baiduRequest := requestOpenAI2Ali(*request)
-		return baiduRequest, nil
+		aliReq := requestOpenAI2Ali(*request)
+		return aliReq, nil
 	}
 }
 
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	aliRequest := oaiImage2Ali(request)
+	return aliRequest, nil
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
-	if info.IsStream {
-		err, usage = aliStreamHandler(c, resp)
-	} else {
-		switch info.RelayMode {
-		case constant.RelayModeEmbeddings:
-			err, usage = aliEmbeddingHandler(c, resp)
-		default:
-			err, usage = aliHandler(c, resp)
+	switch info.RelayMode {
+	case constant.RelayModeImagesGenerations:
+		err, usage = aliImageHandler(c, resp, info)
+	case constant.RelayModeEmbeddings:
+		err, usage = aliEmbeddingHandler(c, resp)
+	default:
+		if info.IsStream {
+			err, usage = openai.OaiStreamHandler(c, resp, info)
+		} else {
+			err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
 		}
 	}
 	return

relay/channel/ali/dto.go

@@ -36,8 +36,8 @@ type AliEmbeddingRequest struct {
 }
 
 type AliEmbedding struct {
-	Embedding []float64 `json:"embedding"`
-	TextIndex int       `json:"text_index"`
+	Embedding any `json:"embedding"`
+	TextIndex int `json:"text_index"`
 }
 
 type AliEmbeddingResponse struct {
@@ -60,13 +60,40 @@ type AliUsage struct {
 	TotalTokens  int `json:"total_tokens"`
 }
 
-type AliOutput struct {
-	Text         string `json:"text"`
-	FinishReason string `json:"finish_reason"`
+type TaskResult struct {
+	B64Image string `json:"b64_image,omitempty"`
+	Url      string `json:"url,omitempty"`
+	Code     string `json:"code,omitempty"`
+	Message  string `json:"message,omitempty"`
 }
 
-type AliChatResponse struct {
+type AliOutput struct {
+	TaskId       string       `json:"task_id,omitempty"`
+	TaskStatus   string       `json:"task_status,omitempty"`
+	Text         string       `json:"text"`
+	FinishReason string       `json:"finish_reason"`
+	Message      string       `json:"message,omitempty"`
+	Code         string       `json:"code,omitempty"`
+	Results      []TaskResult `json:"results,omitempty"`
+}
+
+type AliResponse struct {
 	Output AliOutput `json:"output"`
 	Usage  AliUsage  `json:"usage"`
 	AliError
 }
+
+type AliImageRequest struct {
+	Model string `json:"model"`
+	Input struct {
+		Prompt         string `json:"prompt"`
+		NegativePrompt string `json:"negative_prompt,omitempty"`
+	} `json:"input"`
+	Parameters struct {
+		Size  string `json:"size,omitempty"`
+		N     int    `json:"n,omitempty"`
+		Steps string `json:"steps,omitempty"`
+		Scale string `json:"scale,omitempty"`
+	} `json:"parameters,omitempty"`
+	ResponseFormat string `json:"response_format,omitempty"`
+}

relay/channel/ali/image.go

@@ -0,0 +1,177 @@
+package ali
+
+import (
+	"encoding/json"
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/dto"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
+	"strings"
+	"time"
+)
+
+func oaiImage2Ali(request dto.ImageRequest) *AliImageRequest {
+	var imageRequest AliImageRequest
+	imageRequest.Input.Prompt = request.Prompt
+	imageRequest.Model = request.Model
+	imageRequest.Parameters.Size = strings.Replace(request.Size, "x", "*", -1)
+	imageRequest.Parameters.N = request.N
+	imageRequest.ResponseFormat = request.ResponseFormat
+
+	return &imageRequest
+}
+
+func updateTask(info *relaycommon.RelayInfo, taskID string, key string) (*AliResponse, error, []byte) {
+	url := fmt.Sprintf("/api/v1/tasks/%s", taskID)
+
+	var aliResponse AliResponse
+
+	req, err := http.NewRequest("GET", url, nil)
+	if err != nil {
+		return &aliResponse, err, nil
+	}
+
+	req.Header.Set("Authorization", "Bearer "+key)
+
+	client := &http.Client{}
+	resp, err := client.Do(req)
+	if err != nil {
+		common.SysError("updateTask client.Do err: " + err.Error())
+		return &aliResponse, err, nil
+	}
+	defer resp.Body.Close()
+
+	responseBody, err := io.ReadAll(resp.Body)
+
+	var response AliResponse
+	err = json.Unmarshal(responseBody, &response)
+	if err != nil {
+		common.SysError("updateTask NewDecoder err: " + err.Error())
+		return &aliResponse, err, nil
+	}
+
+	return &response, nil, responseBody
+}
+
+func asyncTaskWait(info *relaycommon.RelayInfo, taskID string, key string) (*AliResponse, []byte, error) {
+	waitSeconds := 3
+	step := 0
+	maxStep := 20
+
+	var taskResponse AliResponse
+	var responseBody []byte
+
+	for {
+		step++
+		rsp, err, body := updateTask(info, taskID, key)
+		responseBody = body
+		if err != nil {
+			return &taskResponse, responseBody, err
+		}
+
+		if rsp.Output.TaskStatus == "" {
+			return &taskResponse, responseBody, nil
+		}
+
+		switch rsp.Output.TaskStatus {
+		case "FAILED":
+			fallthrough
+		case "CANCELED":
+			fallthrough
+		case "SUCCEEDED":
+			fallthrough
+		case "UNKNOWN":
+			return rsp, responseBody, nil
+		}
+		if step >= maxStep {
+			break
+		}
+		time.Sleep(time.Duration(waitSeconds) * time.Second)
+	}
+
+	return nil, nil, fmt.Errorf("aliAsyncTaskWait timeout")
+}
+
+func responseAli2OpenAIImage(c *gin.Context, response *AliResponse, info *relaycommon.RelayInfo, responseFormat string) *dto.ImageResponse {
+	imageResponse := dto.ImageResponse{
+		Created: info.StartTime.Unix(),
+	}
+
+	for _, data := range response.Output.Results {
+		var b64Json string
+		if responseFormat == "b64_json" {
+			_, b64, err := common.GetImageFromUrl(data.Url)
+			if err != nil {
+				common.LogError(c, "get_image_data_failed: "+err.Error())
+				continue
+			}
+			b64Json = b64
+		} else {
+			b64Json = data.B64Image
+		}
+
+		imageResponse.Data = append(imageResponse.Data, dto.ImageData{
+			Url:           data.Url,
+			B64Json:       b64Json,
+			RevisedPrompt: "",
+		})
+	}
+	return &imageResponse
+}
+
+func aliImageHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	apiKey := c.Request.Header.Get("Authorization")
+	apiKey = strings.TrimPrefix(apiKey, "Bearer ")
+	responseFormat := c.GetString("response_format")
+
+	var aliTaskResponse AliResponse
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = json.Unmarshal(responseBody, &aliTaskResponse)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+
+	if aliTaskResponse.Message != "" {
+		common.LogError(c, "ali_async_task_failed: "+aliTaskResponse.Message)
+		return service.OpenAIErrorWrapper(errors.New(aliTaskResponse.Message), "ali_async_task_failed", http.StatusInternalServerError), nil
+	}
+
+	aliResponse, _, err := asyncTaskWait(info, aliTaskResponse.Output.TaskId, apiKey)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "ali_async_task_wait_failed", http.StatusInternalServerError), nil
+	}
+
+	if aliResponse.Output.TaskStatus != "SUCCEEDED" {
+		return &dto.OpenAIErrorWithStatusCode{
+			Error: dto.OpenAIError{
+				Message: aliResponse.Output.Message,
+				Type:    "ali_error",
+				Param:   "",
+				Code:    aliResponse.Output.Code,
+			},
+			StatusCode: resp.StatusCode,
+		}, nil
+	}
+
+	fullTextResponse := responseAli2OpenAIImage(c, aliResponse, info, responseFormat)
+	jsonResponse, err := json.Marshal(fullTextResponse)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = c.Writer.Write(jsonResponse)
+	return nil, nil
+}

relay/channel/ali/text.go

@@ -16,34 +16,13 @@ import (
 
 const EnableSearchModelSuffix = "-internet"
 
-func requestOpenAI2Ali(request dto.GeneralOpenAIRequest) *AliChatRequest {
-	messages := make([]AliMessage, 0, len(request.Messages))
-	//prompt := ""
-	for i := 0; i < len(request.Messages); i++ {
-		message := request.Messages[i]
-		messages = append(messages, AliMessage{
-			Content: message.StringContent(),
-			Role:    strings.ToLower(message.Role),
-		})
-	}
-	enableSearch := false
-	aliModel := request.Model
-	if strings.HasSuffix(aliModel, EnableSearchModelSuffix) {
-		enableSearch = true
-		aliModel = strings.TrimSuffix(aliModel, EnableSearchModelSuffix)
-	}
-	return &AliChatRequest{
-		Model: request.Model,
-		Input: AliInput{
-			//Prompt:  prompt,
-			Messages: messages,
-		},
-		Parameters: AliParameters{
-			IncrementalOutput: request.Stream,
-			Seed:              uint64(request.Seed),
-			EnableSearch:      enableSearch,
-		},
+func requestOpenAI2Ali(request dto.GeneralOpenAIRequest) *dto.GeneralOpenAIRequest {
+	if request.TopP >= 1 {
+		request.TopP = 0.999
+	} else if request.TopP <= 0 {
+		request.TopP = 0.001
 	}
+	return &request
 }
 
 func embeddingRequestOpenAI2Ali(request dto.GeneralOpenAIRequest) *AliEmbeddingRequest {
@@ -110,7 +89,7 @@ func embeddingResponseAli2OpenAI(response *AliEmbeddingResponse) *dto.OpenAIEmbe
 	return &openAIEmbeddingResponse
 }
 
-func responseAli2OpenAI(response *AliChatResponse) *dto.OpenAITextResponse {
+func responseAli2OpenAI(response *AliResponse) *dto.OpenAITextResponse {
 	content, _ := json.Marshal(response.Output.Text)
 	choice := dto.OpenAITextResponseChoice{
 		Index: 0,
@@ -134,7 +113,7 @@ func responseAli2OpenAI(response *AliChatResponse) *dto.OpenAITextResponse {
 	return &fullTextResponse
 }
 
-func streamResponseAli2OpenAI(aliResponse *AliChatResponse) *dto.ChatCompletionsStreamResponse {
+func streamResponseAli2OpenAI(aliResponse *AliResponse) *dto.ChatCompletionsStreamResponse {
 	var choice dto.ChatCompletionsStreamResponseChoice
 	choice.Delta.SetContentString(aliResponse.Output.Text)
 	if aliResponse.Output.FinishReason != "null" {
@@ -154,18 +133,7 @@ func streamResponseAli2OpenAI(aliResponse *AliChatResponse) *dto.ChatCompletions
 func aliStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	var usage dto.Usage
 	scanner := bufio.NewScanner(resp.Body)
-	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
-		if atEOF && len(data) == 0 {
-			return 0, nil, nil
-		}
-		if i := strings.Index(string(data), "\n"); i >= 0 {
-			return i + 1, data[0:i], nil
-		}
-		if atEOF {
-			return len(data), data, nil
-		}
-		return 0, nil, nil
-	})
+	scanner.Split(bufio.ScanLines)
 	dataChan := make(chan string)
 	stopChan := make(chan bool)
 	go func() {
@@ -187,7 +155,7 @@ func aliStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWith
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
-			var aliResponse AliChatResponse
+			var aliResponse AliResponse
 			err := json.Unmarshal([]byte(data), &aliResponse)
 			if err != nil {
 				common.SysError("error unmarshalling stream response: " + err.Error())
@@ -221,7 +189,7 @@ func aliStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWith
 }
 
 func aliHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
-	var aliResponse AliChatResponse
+	var aliResponse AliResponse
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil

relay/channel/api_request.go

@@ -7,14 +7,19 @@ import (
 	"io"
 	"net/http"
 	"one-api/relay/common"
+	"one-api/relay/constant"
 	"one-api/service"
 )
 
 func SetupApiRequestHeader(info *common.RelayInfo, c *gin.Context, req *http.Request) {
-	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
-	req.Header.Set("Accept", c.Request.Header.Get("Accept"))
-	if info.IsStream && c.Request.Header.Get("Accept") == "" {
-		req.Header.Set("Accept", "text/event-stream")
+	if info.RelayMode == constant.RelayModeAudioTranscription || info.RelayMode == constant.RelayModeAudioTranslation {
+		// multipart/form-data
+	} else {
+		req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
+		req.Header.Set("Accept", c.Request.Header.Get("Accept"))
+		if info.IsStream && c.Request.Header.Get("Accept") == "" {
+			req.Header.Set("Accept", "text/event-stream")
+		}
 	}
 }
 
@@ -38,6 +43,29 @@ func DoApiRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBody
 	return resp, nil
 }
 
+func DoFormRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	fullRequestURL, err := a.GetRequestURL(info)
+	if err != nil {
+		return nil, fmt.Errorf("get request url failed: %w", err)
+	}
+	req, err := http.NewRequest(c.Request.Method, fullRequestURL, requestBody)
+	if err != nil {
+		return nil, fmt.Errorf("new request failed: %w", err)
+	}
+	// set form data
+	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
+
+	err = a.SetupRequestHeader(c, req, info)
+	if err != nil {
+		return nil, fmt.Errorf("setup request header failed: %w", err)
+	}
+	resp, err := doRequest(c, req)
+	if err != nil {
+		return nil, fmt.Errorf("do request failed: %w", err)
+	}
+	return resp, nil
+}
+
 func doRequest(c *gin.Context, req *http.Request) (*http.Response, error) {
 	resp, err := service.GetHttpClient().Do(req)
 	if err != nil {
@@ -50,3 +78,27 @@ func doRequest(c *gin.Context, req *http.Request) (*http.Response, error) {
 	_ = c.Request.Body.Close()
 	return resp, nil
 }
+
+func DoTaskApiRequest(a TaskAdaptor, c *gin.Context, info *common.TaskRelayInfo, requestBody io.Reader) (*http.Response, error) {
+	fullRequestURL, err := a.BuildRequestURL(info)
+	if err != nil {
+		return nil, err
+	}
+	req, err := http.NewRequest(c.Request.Method, fullRequestURL, requestBody)
+	if err != nil {
+		return nil, fmt.Errorf("new request failed: %w", err)
+	}
+	req.GetBody = func() (io.ReadCloser, error) {
+		return io.NopCloser(requestBody), nil
+	}
+
+	err = a.BuildRequestHeader(c, req, info)
+	if err != nil {
+		return nil, fmt.Errorf("setup request header failed: %w", err)
+	}
+	resp, err := doRequest(c, req)
+	if err != nil {
+		return nil, fmt.Errorf("do request failed: %w", err)
+	}
+	return resp, nil
+}

relay/channel/aws/adaptor.go

@@ -8,7 +8,6 @@ import (
 	"one-api/dto"
 	"one-api/relay/channel/claude"
 	relaycommon "one-api/relay/common"
-	"strings"
 )
 
 const (
@@ -20,12 +19,18 @@ type Adaptor struct {
 	RequestMode int
 }
 
-func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
-	if strings.HasPrefix(info.UpstreamModelName, "claude-3") {
-		a.RequestMode = RequestModeMessage
-	} else {
-		a.RequestMode = RequestModeCompletion
-	}
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
+	a.RequestMode = RequestModeMessage
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
@@ -36,30 +41,31 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *re
 	return nil
 }
 
-func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
 
 	var claudeReq *claude.ClaudeRequest
 	var err error
-	if a.RequestMode == RequestModeCompletion {
-		claudeReq = claude.RequestOpenAI2ClaudeComplete(*request)
-	} else {
-		claudeReq, err = claude.RequestOpenAI2ClaudeMessage(*request)
-	}
+	claudeReq, err = claude.RequestOpenAI2ClaudeMessage(*request)
+
 	c.Set("request_model", request.Model)
 	c.Set("converted_request", claudeReq)
 	return claudeReq, err
 }
 
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
 	return nil, nil
 }
 
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
-		err, usage = awsStreamHandler(c, info, a.RequestMode)
+		err, usage = awsStreamHandler(c, resp, info, a.RequestMode)
 	} else {
 		err, usage = awsHandler(c, info, a.RequestMode)
 	}

relay/channel/aws/constants.go

@@ -7,6 +7,7 @@ var awsModelIDMap = map[string]string{
 	"claude-3-sonnet-20240229": "anthropic.claude-3-sonnet-20240229-v1:0",
 	"claude-3-opus-20240229":   "anthropic.claude-3-opus-20240229-v1:0",
 	"claude-3-haiku-20240307":  "anthropic.claude-3-haiku-20240307-v1:0",
+	"claude-3-5-sonnet-20240620": "anthropic.claude-3-5-sonnet-20240620-v1:0",
 }
 
 var ChannelName = "aws"

relay/channel/aws/relay-aws.go

@@ -13,7 +13,9 @@ import (
 	relaymodel "one-api/dto"
 	"one-api/relay/channel/claude"
 	relaycommon "one-api/relay/common"
+	"one-api/service"
 	"strings"
+	"time"
 
 	"github.com/aws/aws-sdk-go-v2/aws"
 	"github.com/aws/aws-sdk-go-v2/credentials"
@@ -111,7 +113,7 @@ func awsHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode int) (*
 	return nil, &usage
 }
 
-func awsStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode int) (*relaymodel.OpenAIErrorWithStatusCode, *relaymodel.Usage) {
+func awsStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo, requestMode int) (*relaymodel.OpenAIErrorWithStatusCode, *relaymodel.Usage) {
 	awsCli, err := newAwsClient(c, info)
 	if err != nil {
 		return wrapErr(errors.Wrap(err, "newAwsClient")), nil
@@ -156,16 +158,20 @@ func awsStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode i
 	var usage relaymodel.Usage
 	var id string
 	var model string
+	isFirst := true
 	createdTime := common.GetTimestamp()
 	c.Stream(func(w io.Writer) bool {
 		event, ok := <-stream.Events()
 		if !ok {
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
 			return false
 		}
 
 		switch v := event.(type) {
 		case *types.ResponseStreamMemberChunk:
+			if isFirst {
+				isFirst = false
+				info.FirstResponseTime = time.Now()
+			}
 			claudeResp := new(claude.ClaudeResponse)
 			err := json.NewDecoder(bytes.NewReader(v.Value.Bytes)).Decode(claudeResp)
 			if err != nil {
@@ -208,6 +214,19 @@ func awsStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode i
 			return false
 		}
 	})
-
+	if info.ShouldIncludeUsage {
+		response := service.GenerateFinalUsageResponse(id, createdTime, info.UpstreamModelName, usage)
+		err := service.ObjectData(c, response)
+		if err != nil {
+			common.SysError("send final response failed: " + err.Error())
+		}
+	}
+	service.Done(c)
+	if resp != nil {
+		err = resp.Body.Close()
+		if err != nil {
+			return service.OpenAIErrorWrapperLocal(err, "close_response_body_failed", http.StatusInternalServerError), nil
+		}
+	}
 	return nil, &usage
 }

relay/channel/baidu/adaptor.go

@@ -2,6 +2,7 @@ package baidu
 
 import (
 	"errors"
+	"fmt"
 	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
@@ -9,33 +10,85 @@ import (
 	"one-api/relay/channel"
 	relaycommon "one-api/relay/common"
 	"one-api/relay/constant"
+	"strings"
 )
 
 type Adaptor struct {
 }
 
-func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
 
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-	var fullRequestURL string
-	switch info.UpstreamModelName {
-	case "ERNIE-Bot-4":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions_pro"
-	case "ERNIE-Bot-8K":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie_bot_8k"
-	case "ERNIE-Bot":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions"
-	case "ERNIE-Speed":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie_speed"
-	case "ERNIE-Bot-turbo":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/eb-instant"
-	case "BLOOMZ-7B":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/bloomz_7b1"
-	case "Embedding-V1":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/embeddings/embedding-v1"
+	// https://cloud.baidu.com/doc/WENXINWORKSHOP/s/clntwmv7t
+	suffix := "chat/"
+	if strings.HasPrefix(info.UpstreamModelName, "Embedding") {
+		suffix = "embeddings/"
 	}
+	if strings.HasPrefix(info.UpstreamModelName, "bge-large") {
+		suffix = "embeddings/"
+	}
+	if strings.HasPrefix(info.UpstreamModelName, "tao-8k") {
+		suffix = "embeddings/"
+	}
+	switch info.UpstreamModelName {
+	case "ERNIE-4.0":
+		suffix += "completions_pro"
+	case "ERNIE-Bot-4":
+		suffix += "completions_pro"
+	case "ERNIE-Bot":
+		suffix += "completions"
+	case "ERNIE-Bot-turbo":
+		suffix += "eb-instant"
+	case "ERNIE-Speed":
+		suffix += "ernie_speed"
+	case "ERNIE-4.0-8K":
+		suffix += "completions_pro"
+	case "ERNIE-3.5-8K":
+		suffix += "completions"
+	case "ERNIE-3.5-8K-0205":
+		suffix += "ernie-3.5-8k-0205"
+	case "ERNIE-3.5-8K-1222":
+		suffix += "ernie-3.5-8k-1222"
+	case "ERNIE-Bot-8K":
+		suffix += "ernie_bot_8k"
+	case "ERNIE-3.5-4K-0205":
+		suffix += "ernie-3.5-4k-0205"
+	case "ERNIE-Speed-8K":
+		suffix += "ernie_speed"
+	case "ERNIE-Speed-128K":
+		suffix += "ernie-speed-128k"
+	case "ERNIE-Lite-8K-0922":
+		suffix += "eb-instant"
+	case "ERNIE-Lite-8K-0308":
+		suffix += "ernie-lite-8k"
+	case "ERNIE-Tiny-8K":
+		suffix += "ernie-tiny-8k"
+	case "BLOOMZ-7B":
+		suffix += "bloomz_7b1"
+	case "Embedding-V1":
+		suffix += "embedding-v1"
+	case "bge-large-zh":
+		suffix += "bge_large_zh"
+	case "bge-large-en":
+		suffix += "bge_large_en"
+	case "tao-8k":
+		suffix += "tao_8k"
+	default:
+		suffix += strings.ToLower(info.UpstreamModelName)
+	}
+	fullRequestURL := fmt.Sprintf("%s/rpc/2.0/ai_custom/v1/wenxinworkshop/%s", info.BaseUrl, suffix)
 	var accessToken string
 	var err error
 	if accessToken, err = getBaiduAccessToken(info.ApiKey); err != nil {
@@ -51,11 +104,11 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *re
 	return nil
 }
 
-func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
-	switch relayMode {
+	switch info.RelayMode {
 	case constant.RelayModeEmbeddings:
 		baiduEmbeddingRequest := embeddingRequestOpenAI2Baidu(*request)
 		return baiduEmbeddingRequest, nil
@@ -65,6 +118,10 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	}
 }
 
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/baidu/constants.go

@@ -1,12 +1,22 @@
 package baidu
 
 var ModelList = []string{
-	"ERNIE-Bot-4",
+	"ERNIE-4.0-8K",
+	"ERNIE-3.5-8K",
+	"ERNIE-3.5-8K-0205",
+	"ERNIE-3.5-8K-1222",
 	"ERNIE-Bot-8K",
-	"ERNIE-Bot",
-	"ERNIE-Speed",
-	"ERNIE-Bot-turbo",
+	"ERNIE-3.5-4K-0205",
+	"ERNIE-Speed-8K",
+	"ERNIE-Speed-128K",
+	"ERNIE-Lite-8K-0922",
+	"ERNIE-Lite-8K-0308",
+	"ERNIE-Tiny-8K",
+	"BLOOMZ-7B",
 	"Embedding-V1",
+	"bge-large-zh",
+	"bge-large-en",
+	"tao-8k",
 }
 
 var ChannelName = "baidu"

relay/channel/baidu/dto.go

@@ -11,9 +11,16 @@ type BaiduMessage struct {
 }
 
 type BaiduChatRequest struct {
-	Messages []BaiduMessage `json:"messages"`
-	Stream   bool           `json:"stream"`
-	UserId   string         `json:"user_id,omitempty"`
+	Messages        []BaiduMessage `json:"messages"`
+	Temperature     float64        `json:"temperature,omitempty"`
+	TopP            float64        `json:"top_p,omitempty"`
+	PenaltyScore    float64        `json:"penalty_score,omitempty"`
+	Stream          bool           `json:"stream,omitempty"`
+	System          string         `json:"system,omitempty"`
+	DisableSearch   bool           `json:"disable_search,omitempty"`
+	EnableCitation  bool           `json:"enable_citation,omitempty"`
+	MaxOutputTokens *int           `json:"max_output_tokens,omitempty"`
+	UserId          string         `json:"user_id,omitempty"`
 }
 
 type Error struct {
@@ -43,9 +50,9 @@ type BaiduEmbeddingRequest struct {
 }
 
 type BaiduEmbeddingData struct {
-	Object    string    `json:"object"`
-	Embedding []float64 `json:"embedding"`
-	Index     int       `json:"index"`
+	Object    string `json:"object"`
+	Embedding any    `json:"embedding"`
+	Index     int    `json:"index"`
 }
 
 type BaiduEmbeddingResponse struct {

relay/channel/baidu/relay-baidu.go

@@ -22,17 +22,33 @@ import (
 var baiduTokenStore sync.Map
 
 func requestOpenAI2Baidu(request dto.GeneralOpenAIRequest) *BaiduChatRequest {
-	messages := make([]BaiduMessage, 0, len(request.Messages))
+	baiduRequest := BaiduChatRequest{
+		Temperature:    request.Temperature,
+		TopP:           request.TopP,
+		PenaltyScore:   request.FrequencyPenalty,
+		Stream:         request.Stream,
+		DisableSearch:  false,
+		EnableCitation: false,
+		UserId:         request.User,
+	}
+	if request.MaxTokens != 0 {
+		maxTokens := int(request.MaxTokens)
+		if request.MaxTokens == 1 {
+			maxTokens = 2
+		}
+		baiduRequest.MaxOutputTokens = &maxTokens
+	}
 	for _, message := range request.Messages {
-		messages = append(messages, BaiduMessage{
-			Role:    message.Role,
-			Content: message.StringContent(),
-		})
-	}
-	return &BaiduChatRequest{
-		Messages: messages,
-		Stream:   request.Stream,
+		if message.Role == "system" {
+			baiduRequest.System = message.StringContent()
+		} else {
+			baiduRequest.Messages = append(baiduRequest.Messages, BaiduMessage{
+				Role:    message.Role,
+				Content: message.StringContent(),
+			})
+		}
 	}
+	return &baiduRequest
 }
 
 func responseBaidu2OpenAI(response *BaiduChatResponse) *dto.OpenAITextResponse {

relay/channel/claude/adaptor.go

@@ -21,7 +21,17 @@ type Adaptor struct {
 	RequestMode int
 }
 
-func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
 	if strings.HasPrefix(info.UpstreamModelName, "claude-3") {
 		a.RequestMode = RequestModeMessage
 	} else {
@@ -48,7 +58,7 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *re
 	return nil
 }
 
-func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
@@ -59,15 +69,19 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	}
 }
 
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
-		err, usage = claudeStreamHandler(a.RequestMode, info.UpstreamModelName, info.PromptTokens, c, resp)
+		err, usage = ClaudeStreamHandler(c, resp, info, a.RequestMode)
 	} else {
-		err, usage = claudeHandler(a.RequestMode, c, resp, info.PromptTokens, info.UpstreamModelName)
+		err, usage = ClaudeHandler(c, resp, a.RequestMode, info)
 	}
 	return
 }

relay/channel/claude/constants.go

@@ -8,6 +8,7 @@ var ModelList = []string{
 	"claude-3-sonnet-20240229",
 	"claude-3-opus-20240229",
 	"claude-3-haiku-20240307",
+	"claude-3-5-sonnet-20240620",
 }
 
 var ChannelName = "claude"

relay/channel/claude/dto.go

@@ -5,11 +5,18 @@ type ClaudeMetadata struct {
 }
 
 type ClaudeMediaMessage struct {
-	Type       string               `json:"type"`
-	Text       string               `json:"text,omitempty"`
-	Source     *ClaudeMessageSource `json:"source,omitempty"`
-	Usage      *ClaudeUsage         `json:"usage,omitempty"`
-	StopReason *string              `json:"stop_reason,omitempty"`
+	Type        string               `json:"type"`
+	Text        string               `json:"text,omitempty"`
+	Source      *ClaudeMessageSource `json:"source,omitempty"`
+	Usage       *ClaudeUsage         `json:"usage,omitempty"`
+	StopReason  *string              `json:"stop_reason,omitempty"`
+	PartialJson string               `json:"partial_json,omitempty"`
+	// tool_calls
+	Id        string `json:"id,omitempty"`
+	Name      string `json:"name,omitempty"`
+	Input     any    `json:"input,omitempty"`
+	Content   string `json:"content,omitempty"`
+	ToolUseId string `json:"tool_use_id,omitempty"`
 }
 
 type ClaudeMessageSource struct {
@@ -23,6 +30,18 @@ type ClaudeMessage struct {
 	Content any    `json:"content"`
 }
 
+type Tool struct {
+	Name        string                 `json:"name"`
+	Description string                 `json:"description,omitempty"`
+	InputSchema map[string]interface{} `json:"input_schema"`
+}
+
+type InputSchema struct {
+	Type       string `json:"type"`
+	Properties any    `json:"properties,omitempty"`
+	Required   any    `json:"required,omitempty"`
+}
+
 type ClaudeRequest struct {
 	Model             string          `json:"model"`
 	Prompt            string          `json:"prompt,omitempty"`
@@ -35,7 +54,9 @@ type ClaudeRequest struct {
 	TopP              float64         `json:"top_p,omitempty"`
 	TopK              int             `json:"top_k,omitempty"`
 	//ClaudeMetadata    `json:"metadata,omitempty"`
-	Stream bool `json:"stream,omitempty"`
+	Stream     bool   `json:"stream,omitempty"`
+	Tools      []Tool `json:"tools,omitempty"`
+	ToolChoice any    `json:"tool_choice,omitempty"`
 }
 
 type ClaudeError struct {
@@ -44,24 +65,20 @@ type ClaudeError struct {
 }
 
 type ClaudeResponse struct {
-	Id         string               `json:"id"`
-	Type       string               `json:"type"`
-	Content    []ClaudeMediaMessage `json:"content"`
-	Completion string               `json:"completion"`
-	StopReason string               `json:"stop_reason"`
-	Model      string               `json:"model"`
-	Error      ClaudeError          `json:"error"`
-	Usage      ClaudeUsage          `json:"usage"`
-	Index      int                  `json:"index"`   // stream only
-	Delta      *ClaudeMediaMessage  `json:"delta"`   // stream only
-	Message    *ClaudeResponse      `json:"message"` // stream only: message_start
+	Id           string               `json:"id"`
+	Type         string               `json:"type"`
+	Content      []ClaudeMediaMessage `json:"content"`
+	Completion   string               `json:"completion"`
+	StopReason   string               `json:"stop_reason"`
+	Model        string               `json:"model"`
+	Error        ClaudeError          `json:"error"`
+	Usage        ClaudeUsage          `json:"usage"`
+	Index        int                  `json:"index"` // stream only
+	ContentBlock *ClaudeMediaMessage  `json:"content_block"`
+	Delta        *ClaudeMediaMessage  `json:"delta"`   // stream only
+	Message      *ClaudeResponse      `json:"message"` // stream only: message_start
 }
 
-//type ClaudeResponseChoice struct {
-//	Index   int                `json:"index"`
-//	Type    string             `json:"type"`
-//}
-
 type ClaudeUsage struct {
 	InputTokens  int `json:"input_tokens"`
 	OutputTokens int `json:"output_tokens"`

relay/channel/claude/relay-claude.go

@@ -4,13 +4,15 @@ import (
 	"bufio"
 	"encoding/json"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/common"
 	"one-api/dto"
+	relaycommon "one-api/relay/common"
 	"one-api/service"
 	"strings"
+
+	"github.com/gin-gonic/gin"
 )
 
 func stopReasonClaude2OpenAI(reason string) string {
@@ -27,6 +29,7 @@ func stopReasonClaude2OpenAI(reason string) string {
 }
 
 func RequestOpenAI2ClaudeComplete(textRequest dto.GeneralOpenAIRequest) *ClaudeRequest {
+
 	claudeRequest := ClaudeRequest{
 		Model:         textRequest.Model,
 		Prompt:        "",
@@ -57,6 +60,28 @@ func RequestOpenAI2ClaudeComplete(textRequest dto.GeneralOpenAIRequest) *ClaudeR
 }
 
 func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeRequest, error) {
+	claudeTools := make([]Tool, 0, len(textRequest.Tools))
+
+	for _, tool := range textRequest.Tools {
+		if params, ok := tool.Function.Parameters.(map[string]any); ok {
+			claudeTool := Tool{
+				Name:        tool.Function.Name,
+				Description: tool.Function.Description,
+			}
+			claudeTool.InputSchema = make(map[string]interface{})
+			claudeTool.InputSchema["type"] = params["type"].(string)
+			claudeTool.InputSchema["properties"] = params["properties"]
+			claudeTool.InputSchema["required"] = params["required"]
+			for s, a := range params {
+				if s == "type" || s == "properties" || s == "required" {
+					continue
+				}
+				claudeTool.InputSchema[s] = a
+			}
+			claudeTools = append(claudeTools, claudeTool)
+		}
+	}
+
 	claudeRequest := ClaudeRequest{
 		Model:         textRequest.Model,
 		MaxTokens:     textRequest.MaxTokens,
@@ -65,18 +90,29 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 		TopP:          textRequest.TopP,
 		TopK:          textRequest.TopK,
 		Stream:        textRequest.Stream,
+		Tools:         claudeTools,
 	}
 	if claudeRequest.MaxTokens == 0 {
 		claudeRequest.MaxTokens = 4096
 	}
+	if textRequest.Stop != nil {
+		// stop maybe string/array string, convert to array string
+		switch textRequest.Stop.(type) {
+		case string:
+			claudeRequest.StopSequences = []string{textRequest.Stop.(string)}
+		case []interface{}:
+			stopSequences := make([]string, 0)
+			for _, stop := range textRequest.Stop.([]interface{}) {
+				stopSequences = append(stopSequences, stop.(string))
+			}
+			claudeRequest.StopSequences = stopSequences
+		}
+	}
 	formatMessages := make([]dto.Message, 0)
-	var lastMessage *dto.Message
+	lastMessage := dto.Message{
+		Role: "tool",
+	}
 	for i, message := range textRequest.Messages {
-		//if message.Role == "system" {
-		//	if i != 0 {
-		//		message.Role = "user"
-		//	}
-		//}
 		if message.Role == "" {
 			textRequest.Messages[i].Role = "user"
 		}
@@ -84,7 +120,13 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 			Role:    message.Role,
 			Content: message.Content,
 		}
-		if lastMessage != nil && lastMessage.Role == message.Role {
+		if message.Role == "tool" {
+			fmtMessage.ToolCallId = message.ToolCallId
+		}
+		if message.Role == "assistant" && message.ToolCalls != nil {
+			fmtMessage.ToolCalls = message.ToolCalls
+		}
+		if lastMessage.Role == message.Role && lastMessage.Role != "tool" {
 			if lastMessage.IsStringContent() && message.IsStringContent() {
 				content, _ := json.Marshal(strings.Trim(fmt.Sprintf("%s %s", lastMessage.StringContent(), message.StringContent()), "\""))
 				fmtMessage.Content = content
@@ -97,10 +139,11 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 			fmtMessage.Content = content
 		}
 		formatMessages = append(formatMessages, fmtMessage)
-		lastMessage = &textRequest.Messages[i]
+		lastMessage = fmtMessage
 	}
 
 	claudeMessages := make([]ClaudeMessage, 0)
+	isFirstMessage := true
 	for _, message := range formatMessages {
 		if message.Role == "system" {
 			if message.IsStringContent() {
@@ -116,10 +159,54 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 				claudeRequest.System = content
 			}
 		} else {
+			if isFirstMessage {
+				isFirstMessage = false
+				if message.Role != "user" {
+					// fix: first message is assistant, add user message
+					claudeMessage := ClaudeMessage{
+						Role: "user",
+						Content: []ClaudeMediaMessage{
+							{
+								Type: "text",
+								Text: "...",
+							},
+						},
+					}
+					claudeMessages = append(claudeMessages, claudeMessage)
+				}
+			}
 			claudeMessage := ClaudeMessage{
 				Role: message.Role,
 			}
-			if message.IsStringContent() {
+			if message.Role == "tool" {
+				if len(claudeMessages) > 0 && claudeMessages[len(claudeMessages)-1].Role == "user" {
+					lastMessage := claudeMessages[len(claudeMessages)-1]
+					if content, ok := lastMessage.Content.(string); ok {
+						lastMessage.Content = []ClaudeMediaMessage{
+							{
+								Type: "text",
+								Text: content,
+							},
+						}
+					}
+					lastMessage.Content = append(lastMessage.Content.([]ClaudeMediaMessage), ClaudeMediaMessage{
+						Type:      "tool_result",
+						ToolUseId: message.ToolCallId,
+						Content:   message.StringContent(),
+					})
+					claudeMessages[len(claudeMessages)-1] = lastMessage
+					continue
+				} else {
+					claudeMessage.Role = "user"
+					claudeMessage.Content = []ClaudeMediaMessage{
+						{
+							Type:      "tool_result",
+							ToolUseId: message.ToolCallId,
+							Content:   message.StringContent(),
+						},
+					}
+				}
+			} else if message.IsStringContent() && message.ToolCalls == nil {
 				claudeMessage.Content = message.StringContent()
 			} else {
 				claudeMediaMessages := make([]ClaudeMediaMessage, 0)
@@ -152,6 +239,28 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 					}
 					claudeMediaMessages = append(claudeMediaMessages, claudeMediaMessage)
 				}
+				if message.ToolCalls != nil {
+					for _, tc := range message.ToolCalls.([]interface{}) {
+						toolCallJSON, _ := json.Marshal(tc)
+						var toolCall dto.ToolCall
+						err := json.Unmarshal(toolCallJSON, &toolCall)
+						if err != nil {
+							common.SysError("tool call is not a dto.ToolCall: " + fmt.Sprintf("%v", tc))
+							continue
+						}
+						inputObj := make(map[string]any)
+						if err := json.Unmarshal([]byte(toolCall.Function.Arguments), &inputObj); err != nil {
+							common.SysError("tool call function arguments is not a map[string]any: " + fmt.Sprintf("%v", toolCall.Function.Arguments))
+							continue
+						}
+						claudeMediaMessages = append(claudeMediaMessages, ClaudeMediaMessage{
+							Type:  "tool_use",
+							Id:    toolCall.ID,
+							Name:  toolCall.Function.Name,
+							Input: inputObj,
+						})
+					}
+				}
 				claudeMessage.Content = claudeMediaMessages
 			}
 			claudeMessages = append(claudeMessages, claudeMessage)
@@ -168,6 +277,7 @@ func StreamResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) (*
 	response.Object = "chat.completion.chunk"
 	response.Model = claudeResponse.Model
 	response.Choices = make([]dto.ChatCompletionsStreamResponseChoice, 0)
+	tools := make([]dto.ToolCall, 0)
 	var choice dto.ChatCompletionsStreamResponseChoice
 	if reqMode == RequestModeCompletion {
 		choice.Delta.SetContentString(claudeResponse.Completion)
@@ -183,10 +293,33 @@ func StreamResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) (*
 			choice.Delta.SetContentString("")
 			choice.Delta.Role = "assistant"
 		} else if claudeResponse.Type == "content_block_start" {
-			return nil, nil
+			if claudeResponse.ContentBlock != nil {
+				//choice.Delta.SetContentString(claudeResponse.ContentBlock.Text)
+				if claudeResponse.ContentBlock.Type == "tool_use" {
+					tools = append(tools, dto.ToolCall{
+						ID:   claudeResponse.ContentBlock.Id,
+						Type: "function",
+						Function: dto.FunctionCall{
+							Name:      claudeResponse.ContentBlock.Name,
+							Arguments: "",
+						},
+					})
+				}
+			} else {
+				return nil, nil
+			}
 		} else if claudeResponse.Type == "content_block_delta" {
-			choice.Index = claudeResponse.Index
-			choice.Delta.SetContentString(claudeResponse.Delta.Text)
+			if claudeResponse.Delta != nil {
+				choice.Index = claudeResponse.Index
+				choice.Delta.SetContentString(claudeResponse.Delta.Text)
+				if claudeResponse.Delta.Type == "input_json_delta" {
+					tools = append(tools, dto.ToolCall{
+						Function: dto.FunctionCall{
+							Arguments: claudeResponse.Delta.PartialJson,
+						},
+					})
+				}
+			}
 		} else if claudeResponse.Type == "message_delta" {
 			finishReason := stopReasonClaude2OpenAI(*claudeResponse.Delta.StopReason)
 			if finishReason != "null" {
@@ -202,6 +335,10 @@ func StreamResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) (*
 	if claudeUsage == nil {
 		claudeUsage = &ClaudeUsage{}
 	}
+	if len(tools) > 0 {
+		choice.Delta.Content = nil // compatible with other OpenAI derivative applications, like LobeOpenAICompatibleFactory ...
+		choice.Delta.ToolCalls = tools
+	}
 	response.Choices = append(response.Choices, choice)
 
 	return &response, claudeUsage
@@ -214,6 +351,11 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
 		Object:  "chat.completion",
 		Created: common.GetTimestamp(),
 	}
+	var responseText string
+	if len(claudeResponse.Content) > 0 {
+		responseText = claudeResponse.Content[0].Text
+	}
+	tools := make([]dto.ToolCall, 0)
 	if reqMode == RequestModeCompletion {
 		content, _ := json.Marshal(strings.TrimPrefix(claudeResponse.Completion, " "))
 		choice := dto.OpenAITextResponseChoice{
@@ -228,123 +370,120 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
 		choices = append(choices, choice)
 	} else {
 		fullTextResponse.Id = claudeResponse.Id
-		for i, message := range claudeResponse.Content {
-			content, _ := json.Marshal(message.Text)
-			choice := dto.OpenAITextResponseChoice{
-				Index: i,
-				Message: dto.Message{
-					Role:    "assistant",
-					Content: content,
-				},
-				FinishReason: stopReasonClaude2OpenAI(claudeResponse.StopReason),
+		for _, message := range claudeResponse.Content {
+			if message.Type == "tool_use" {
+				args, _ := json.Marshal(message.Input)
+				tools = append(tools, dto.ToolCall{
+					ID:   message.Id,
+					Type: "function", // compatible with other OpenAI derivative applications
+					Function: dto.FunctionCall{
+						Name:      message.Name,
+						Arguments: string(args),
+					},
+				})
 			}
-			choices = append(choices, choice)
 		}
 	}
-
+	choice := dto.OpenAITextResponseChoice{
+		Index: 0,
+		Message: dto.Message{
+			Role: "assistant",
+		},
+		FinishReason: stopReasonClaude2OpenAI(claudeResponse.StopReason),
+	}
+	choice.SetStringContent(responseText)
+	if len(tools) > 0 {
+		choice.Message.ToolCalls = tools
+	}
+	fullTextResponse.Model = claudeResponse.Model
+	choices = append(choices, choice)
 	fullTextResponse.Choices = choices
 	return &fullTextResponse
 }
 
-func claudeStreamHandler(requestMode int, modelName string, promptTokens int, c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+func ClaudeStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo, requestMode int) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	responseId := fmt.Sprintf("chatcmpl-%s", common.GetUUID())
 	var usage *dto.Usage
 	usage = &dto.Usage{}
 	responseText := ""
 	createdTime := common.GetTimestamp()
 	scanner := bufio.NewScanner(resp.Body)
-	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
-		if atEOF && len(data) == 0 {
-			return 0, nil, nil
+	scanner.Split(bufio.ScanLines)
+	service.SetEventStreamHeaders(c)
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		info.SetFirstResponseTime()
+		if len(data) < 6 || !strings.HasPrefix(data, "data:") {
+			continue
 		}
-		if i := strings.Index(string(data), "\n"); i >= 0 {
-			return i + 1, data[0:i], nil
+		data = strings.TrimPrefix(data, "data:")
+		data = strings.TrimSpace(data)
+		var claudeResponse ClaudeResponse
+		err := json.Unmarshal([]byte(data), &claudeResponse)
+		if err != nil {
+			common.SysError("error unmarshalling stream response: " + err.Error())
+			continue
 		}
-		if atEOF {
-			return len(data), data, nil
+
+		response, claudeUsage := StreamResponseClaude2OpenAI(requestMode, &claudeResponse)
+		if response == nil {
+			continue
 		}
-		return 0, nil, nil
-	})
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
-	go func() {
-		for scanner.Scan() {
-			data := scanner.Text()
-			if !strings.HasPrefix(data, "data: ") {
+		if requestMode == RequestModeCompletion {
+			responseText += claudeResponse.Completion
+			responseId = response.Id
+		} else {
+			if claudeResponse.Type == "message_start" {
+				// message_start, 获取usage
+				responseId = claudeResponse.Message.Id
+				info.UpstreamModelName = claudeResponse.Message.Model
+				usage.PromptTokens = claudeUsage.InputTokens
+			} else if claudeResponse.Type == "content_block_delta" {
+				responseText += claudeResponse.Delta.Text
+			} else if claudeResponse.Type == "message_delta" {
+				usage.CompletionTokens = claudeUsage.OutputTokens
+				usage.TotalTokens = claudeUsage.InputTokens + claudeUsage.OutputTokens
+			} else if claudeResponse.Type == "content_block_start" {
+
+			} else {
 				continue
 			}
-			data = strings.TrimPrefix(data, "data: ")
-			dataChan <- data
 		}
-		stopChan <- true
-	}()
-	service.SetEventStreamHeaders(c)
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			// some implementations may add \r at the end of data
-			data = strings.TrimSuffix(data, "\r")
-			var claudeResponse ClaudeResponse
-			err := json.Unmarshal([]byte(data), &claudeResponse)
-			if err != nil {
-				common.SysError("error unmarshalling stream response: " + err.Error())
-				return true
-			}
+		//response.Id = responseId
+		response.Id = responseId
+		response.Created = createdTime
+		response.Model = info.UpstreamModelName
 
-			response, claudeUsage := StreamResponseClaude2OpenAI(requestMode, &claudeResponse)
-			if response == nil {
-				return true
-			}
-			if requestMode == RequestModeCompletion {
-				responseText += claudeResponse.Completion
-				responseId = response.Id
-			} else {
-				if claudeResponse.Type == "message_start" {
-					// message_start, 获取usage
-					responseId = claudeResponse.Message.Id
-					modelName = claudeResponse.Message.Model
-					usage.PromptTokens = claudeUsage.InputTokens
-				} else if claudeResponse.Type == "content_block_delta" {
-					responseText += claudeResponse.Delta.Text
-				} else if claudeResponse.Type == "message_delta" {
-					usage.CompletionTokens = claudeUsage.OutputTokens
-					usage.TotalTokens = claudeUsage.InputTokens + claudeUsage.OutputTokens
-				} else {
-					return true
-				}
-			}
-			//response.Id = responseId
-			response.Id = responseId
-			response.Created = createdTime
-			response.Model = modelName
-
-			jsonStr, err := json.Marshal(response)
-			if err != nil {
-				common.SysError("error marshalling stream response: " + err.Error())
-				return true
-			}
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonStr)})
-			return true
-		case <-stopChan:
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
-			return false
+		err = service.ObjectData(c, response)
+		if err != nil {
+			common.LogError(c, "send_stream_response_failed: "+err.Error())
 		}
-	})
-	err := resp.Body.Close()
-	if err != nil {
-		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
+
 	if requestMode == RequestModeCompletion {
-		usage, _ = service.ResponseText2Usage(responseText, modelName, promptTokens)
+		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
 	} else {
+		if usage.PromptTokens == 0 {
+			usage.PromptTokens = info.PromptTokens
+		}
 		if usage.CompletionTokens == 0 {
-			usage, _ = service.ResponseText2Usage(responseText, modelName, usage.PromptTokens)
+			usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, usage.PromptTokens)
 		}
 	}
+	if info.ShouldIncludeUsage {
+		response := service.GenerateFinalUsageResponse(responseId, createdTime, info.UpstreamModelName, *usage)
+		err := service.ObjectData(c, response)
+		if err != nil {
+			common.SysError("send final response failed: " + err.Error())
+		}
+	}
+	service.Done(c)
+	resp.Body.Close()
 	return nil, usage
 }
 
-func claudeHandler(requestMode int, c *gin.Context, resp *http.Response, promptTokens int, model string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+func ClaudeHandler(c *gin.Context, resp *http.Response, requestMode int, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
@@ -370,15 +509,15 @@ func claudeHandler(requestMode int, c *gin.Context, resp *http.Response, promptT
 		}, nil
 	}
 	fullTextResponse := ResponseClaude2OpenAI(requestMode, &claudeResponse)
-	completionTokens, err, _ := service.CountTokenText(claudeResponse.Completion, model, false)
+	completionTokens, err := service.CountTokenText(claudeResponse.Completion, info.OriginModelName)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "count_token_text_failed", http.StatusInternalServerError), nil
 	}
 	usage := dto.Usage{}
 	if requestMode == RequestModeCompletion {
-		usage.PromptTokens = promptTokens
+		usage.PromptTokens = info.PromptTokens
 		usage.CompletionTokens = completionTokens
-		usage.TotalTokens = promptTokens + completionTokens
+		usage.TotalTokens = info.PromptTokens + completionTokens
 	} else {
 		usage.PromptTokens = claudeResponse.Usage.InputTokens
 		usage.CompletionTokens = claudeResponse.Usage.OutputTokens

relay/channel/cloudflare/adaptor.go

@@ -0,0 +1,105 @@
+package cloudflare
+
+import (
+	"bytes"
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+	"one-api/relay/constant"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	switch info.RelayMode {
+	case constant.RelayModeChatCompletions:
+		return fmt.Sprintf("%s/client/v4/accounts/%s/ai/v1/chat/completions", info.BaseUrl, info.ApiVersion), nil
+	case constant.RelayModeEmbeddings:
+		return fmt.Sprintf("%s/client/v4/accounts/%s/ai/v1/embeddings", info.BaseUrl, info.ApiVersion), nil
+	default:
+		return fmt.Sprintf("%s/client/v4/accounts/%s/ai/run/%s", info.BaseUrl, info.ApiVersion, info.UpstreamModelName), nil
+	}
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	switch info.RelayMode {
+	case constant.RelayModeCompletions:
+		return convertCf2CompletionsRequest(*request), nil
+	default:
+		return request, nil
+	}
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return request, nil
+}
+
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	// 添加文件字段
+	file, _, err := c.Request.FormFile("file")
+	if err != nil {
+		return nil, errors.New("file is required")
+	}
+	defer file.Close()
+	// 打开临时文件用于保存上传的文件内容
+	requestBody := &bytes.Buffer{}
+
+	// 将上传的文件内容复制到临时文件
+	if _, err := io.Copy(requestBody, file); err != nil {
+		return nil, err
+	}
+	return requestBody, nil
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+	switch info.RelayMode {
+	case constant.RelayModeEmbeddings:
+		fallthrough
+	case constant.RelayModeChatCompletions:
+		if info.IsStream {
+			err, usage = cfStreamHandler(c, resp, info)
+		} else {
+			err, usage = cfHandler(c, resp, info)
+		}
+	case constant.RelayModeAudioTranslation:
+		fallthrough
+	case constant.RelayModeAudioTranscription:
+		err, usage = cfSTTHandler(c, resp, info)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/cloudflare/constant.go

@@ -0,0 +1,39 @@
+package cloudflare
+
+var ModelList = []string{
+	"@cf/meta/llama-3.1-8b-instruct",
+	"@cf/meta/llama-2-7b-chat-fp16",
+	"@cf/meta/llama-2-7b-chat-int8",
+	"@cf/mistral/mistral-7b-instruct-v0.1",
+	"@hf/thebloke/deepseek-coder-6.7b-base-awq",
+	"@hf/thebloke/deepseek-coder-6.7b-instruct-awq",
+	"@cf/deepseek-ai/deepseek-math-7b-base",
+	"@cf/deepseek-ai/deepseek-math-7b-instruct",
+	"@cf/thebloke/discolm-german-7b-v1-awq",
+	"@cf/tiiuae/falcon-7b-instruct",
+	"@cf/google/gemma-2b-it-lora",
+	"@hf/google/gemma-7b-it",
+	"@cf/google/gemma-7b-it-lora",
+	"@hf/nousresearch/hermes-2-pro-mistral-7b",
+	"@hf/thebloke/llama-2-13b-chat-awq",
+	"@cf/meta-llama/llama-2-7b-chat-hf-lora",
+	"@cf/meta/llama-3-8b-instruct",
+	"@hf/thebloke/llamaguard-7b-awq",
+	"@hf/thebloke/mistral-7b-instruct-v0.1-awq",
+	"@hf/mistralai/mistral-7b-instruct-v0.2",
+	"@cf/mistral/mistral-7b-instruct-v0.2-lora",
+	"@hf/thebloke/neural-chat-7b-v3-1-awq",
+	"@cf/openchat/openchat-3.5-0106",
+	"@hf/thebloke/openhermes-2.5-mistral-7b-awq",
+	"@cf/microsoft/phi-2",
+	"@cf/qwen/qwen1.5-0.5b-chat",
+	"@cf/qwen/qwen1.5-1.8b-chat",
+	"@cf/qwen/qwen1.5-14b-chat-awq",
+	"@cf/qwen/qwen1.5-7b-chat-awq",
+	"@cf/defog/sqlcoder-7b-2",
+	"@hf/nexusflow/starling-lm-7b-beta",
+	"@cf/tinyllama/tinyllama-1.1b-chat-v1.0",
+	"@hf/thebloke/zephyr-7b-beta-awq",
+}
+
+var ChannelName = "cloudflare"

relay/channel/cloudflare/dto.go

@@ -0,0 +1,21 @@
+package cloudflare
+
+import "one-api/dto"
+
+type CfRequest struct {
+	Messages    []dto.Message `json:"messages,omitempty"`
+	Lora        string        `json:"lora,omitempty"`
+	MaxTokens   int           `json:"max_tokens,omitempty"`
+	Prompt      string        `json:"prompt,omitempty"`
+	Raw         bool          `json:"raw,omitempty"`
+	Stream      bool          `json:"stream,omitempty"`
+	Temperature float64       `json:"temperature,omitempty"`
+}
+
+type CfAudioResponse struct {
+	Result CfSTTResult `json:"result"`
+}
+
+type CfSTTResult struct {
+	Text string `json:"text"`
+}

relay/channel/cloudflare/relay_cloudflare.go

@@ -0,0 +1,156 @@
+package cloudflare
+
+import (
+	"bufio"
+	"encoding/json"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/dto"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
+	"strings"
+	"time"
+)
+
+func convertCf2CompletionsRequest(textRequest dto.GeneralOpenAIRequest) *CfRequest {
+	p, _ := textRequest.Prompt.(string)
+	return &CfRequest{
+		Prompt:      p,
+		MaxTokens:   textRequest.GetMaxTokens(),
+		Stream:      textRequest.Stream,
+		Temperature: textRequest.Temperature,
+	}
+}
+
+func cfStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	scanner := bufio.NewScanner(resp.Body)
+	scanner.Split(bufio.ScanLines)
+
+	service.SetEventStreamHeaders(c)
+	id := service.GetResponseID(c)
+	var responseText string
+	isFirst := true
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		if len(data) < len("data: ") {
+			continue
+		}
+		data = strings.TrimPrefix(data, "data: ")
+		data = strings.TrimSuffix(data, "\r")
+
+		if data == "[DONE]" {
+			break
+		}
+
+		var response dto.ChatCompletionsStreamResponse
+		err := json.Unmarshal([]byte(data), &response)
+		if err != nil {
+			common.LogError(c, "error_unmarshalling_stream_response: "+err.Error())
+			continue
+		}
+		for _, choice := range response.Choices {
+			choice.Delta.Role = "assistant"
+			responseText += choice.Delta.GetContentString()
+		}
+		response.Id = id
+		response.Model = info.UpstreamModelName
+		err = service.ObjectData(c, response)
+		if isFirst {
+			isFirst = false
+			info.FirstResponseTime = time.Now()
+		}
+		if err != nil {
+			common.LogError(c, "error_rendering_stream_response: "+err.Error())
+		}
+	}
+
+	if err := scanner.Err(); err != nil {
+		common.LogError(c, "error_scanning_stream_response: "+err.Error())
+	}
+	usage, _ := service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+	if info.ShouldIncludeUsage {
+		response := service.GenerateFinalUsageResponse(id, info.StartTime.Unix(), info.UpstreamModelName, *usage)
+		err := service.ObjectData(c, response)
+		if err != nil {
+			common.LogError(c, "error_rendering_final_usage_response: "+err.Error())
+		}
+	}
+	service.Done(c)
+
+	err := resp.Body.Close()
+	if err != nil {
+		common.LogError(c, "close_response_body_failed: "+err.Error())
+	}
+
+	return nil, usage
+}
+
+func cfHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapperLocal(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	var response dto.TextResponse
+	err = json.Unmarshal(responseBody, &response)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	response.Model = info.UpstreamModelName
+	var responseText string
+	for _, choice := range response.Choices {
+		responseText += choice.Message.StringContent()
+	}
+	usage, _ := service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+	response.Usage = *usage
+	response.Id = service.GetResponseID(c)
+	jsonResponse, err := json.Marshal(response)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, _ = c.Writer.Write(jsonResponse)
+	return nil, usage
+}
+
+func cfSTTHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	var cfResp CfAudioResponse
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = json.Unmarshal(responseBody, &cfResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+
+	audioResp := &dto.AudioResponse{
+		Text: cfResp.Result.Text,
+	}
+
+	jsonResponse, err := json.Marshal(audioResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, _ = c.Writer.Write(jsonResponse)
+
+	usage := &dto.Usage{}
+	usage.PromptTokens = info.PromptTokens
+	usage.CompletionTokens, _ = service.CountTokenText(cfResp.Result.Text, info.UpstreamModelName)
+	usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
+
+	return nil, usage
+}

relay/channel/cohere/adaptor.go

@@ -1,6 +1,7 @@
 package cohere
 
 import (
+	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
 	"io"
@@ -8,16 +9,31 @@ import (
 	"one-api/dto"
 	"one-api/relay/channel"
 	relaycommon "one-api/relay/common"
+	"one-api/relay/constant"
 )
 
 type Adaptor struct {
 }
 
-func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-	return fmt.Sprintf("%s/v1/chat", info.BaseUrl), nil
+	if info.RelayMode == constant.RelayModeRerank {
+		return fmt.Sprintf("%s/v1/rerank", info.BaseUrl), nil
+	} else {
+		return fmt.Sprintf("%s/v1/chat", info.BaseUrl), nil
+	}
 }
 
 func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
@@ -26,7 +42,7 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *re
 	return nil
 }
 
-func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
 	return requestOpenAI2Cohere(*request), nil
 }
 
@@ -34,11 +50,19 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return requestConvertRerank2Cohere(request), nil
+}
+
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
-	if info.IsStream {
-		err, usage = cohereStreamHandler(c, resp, info.UpstreamModelName, info.PromptTokens)
+	if info.RelayMode == constant.RelayModeRerank {
+		err, usage = cohereRerankHandler(c, resp, info)
 	} else {
-		err, usage = cohereHandler(c, resp, info.UpstreamModelName, info.PromptTokens)
+		if info.IsStream {
+			err, usage = cohereStreamHandler(c, resp, info)
+		} else {
+			err, usage = cohereHandler(c, resp, info.UpstreamModelName, info.PromptTokens)
+		}
 	}
 	return
 }

relay/channel/cohere/constant.go

@@ -1,7 +1,11 @@
 package cohere
 
 var ModelList = []string{
-	"command-r", "command-r-plus", "command-light", "command-light-nightly", "command", "command-nightly",
+	"command-r", "command-r-plus",
+	"command-r-08-2024", "command-r-plus-08-2024",
+	"c4ai-aya-23-35b", "c4ai-aya-23-8b",
+	"command-light", "command-light-nightly", "command", "command-nightly",
+	"rerank-english-v3.0", "rerank-multilingual-v3.0", "rerank-english-v2.0", "rerank-multilingual-v2.0",
 }
 
 var ChannelName = "cohere"

relay/channel/cohere/dto.go

@@ -1,11 +1,14 @@
 package cohere
 
+import "one-api/dto"
+
 type CohereRequest struct {
 	Model       string        `json:"model"`
 	ChatHistory []ChatHistory `json:"chat_history"`
 	Message     string        `json:"message"`
 	Stream      bool          `json:"stream"`
-	MaxTokens   int64         `json:"max_tokens"`
+	MaxTokens   int           `json:"max_tokens"`
+	SafetyMode  string        `json:"safety_mode,omitempty"`
 }
 
 type ChatHistory struct {
@@ -28,6 +31,19 @@ type CohereResponseResult struct {
 	Meta         CohereMeta `json:"meta"`
 }
 
+type CohereRerankRequest struct {
+	Documents       []any  `json:"documents"`
+	Query           string `json:"query"`
+	Model           string `json:"model"`
+	TopN            int    `json:"top_n"`
+	ReturnDocuments bool   `json:"return_documents"`
+}
+
+type CohereRerankResponseResult struct {
+	Results []dto.RerankResponseDocument `json:"results"`
+	Meta    CohereMeta                   `json:"meta"`
+}
+
 type CohereMeta struct {
 	//Tokens CohereTokens `json:"tokens"`
 	BilledUnits CohereBilledUnits `json:"billed_units"`

relay/channel/cohere/relay-cohere.go

@@ -9,8 +9,10 @@ import (
 	"net/http"
 	"one-api/common"
 	"one-api/dto"
+	relaycommon "one-api/relay/common"
 	"one-api/service"
 	"strings"
+	"time"
 )
 
 func requestOpenAI2Cohere(textRequest dto.GeneralOpenAIRequest) *CohereRequest {
@@ -21,6 +23,9 @@ func requestOpenAI2Cohere(textRequest dto.GeneralOpenAIRequest) *CohereRequest {
 		Stream:      textRequest.Stream,
 		MaxTokens:   textRequest.GetMaxTokens(),
 	}
+	if common.CohereSafetySetting != "NONE" {
+		cohereReq.SafetyMode = common.CohereSafetySetting
+	}
 	if cohereReq.MaxTokens == 0 {
 		cohereReq.MaxTokens = 4000
 	}
@@ -42,6 +47,21 @@ func requestOpenAI2Cohere(textRequest dto.GeneralOpenAIRequest) *CohereRequest {
 			})
 		}
 	}
+
+	return &cohereReq
+}
+
+func requestConvertRerank2Cohere(rerankRequest dto.RerankRequest) *CohereRerankRequest {
+	if rerankRequest.TopN == 0 {
+		rerankRequest.TopN = 1
+	}
+	cohereReq := CohereRerankRequest{
+		Query:           rerankRequest.Query,
+		Documents:       rerankRequest.Documents,
+		Model:           rerankRequest.Model,
+		TopN:            rerankRequest.TopN,
+		ReturnDocuments: true,
+	}
 	return &cohereReq
 }
 
@@ -56,7 +76,7 @@ func stopReasonCohere2OpenAI(reason string) string {
 	}
 }
 
-func cohereStreamHandler(c *gin.Context, resp *http.Response, modelName string, promptTokens int) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+func cohereStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	responseId := fmt.Sprintf("chatcmpl-%s", common.GetUUID())
 	createdTime := common.GetTimestamp()
 	usage := &dto.Usage{}
@@ -84,9 +104,14 @@ func cohereStreamHandler(c *gin.Context, resp *http.Response, modelName string,
 		stopChan <- true
 	}()
 	service.SetEventStreamHeaders(c)
+	isFirst := true
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
+			if isFirst {
+				isFirst = false
+				info.FirstResponseTime = time.Now()
+			}
 			data = strings.TrimSuffix(data, "\r")
 			var cohereResp CohereResponse
 			err := json.Unmarshal([]byte(data), &cohereResp)
@@ -98,7 +123,7 @@ func cohereStreamHandler(c *gin.Context, resp *http.Response, modelName string,
 			openaiResp.Id = responseId
 			openaiResp.Created = createdTime
 			openaiResp.Object = "chat.completion.chunk"
-			openaiResp.Model = modelName
+			openaiResp.Model = info.UpstreamModelName
 			if cohereResp.IsFinished {
 				finishReason := stopReasonCohere2OpenAI(cohereResp.FinishReason)
 				openaiResp.Choices = []dto.ChatCompletionsStreamResponseChoice{
@@ -137,7 +162,7 @@ func cohereStreamHandler(c *gin.Context, resp *http.Response, modelName string,
 		}
 	})
 	if usage.PromptTokens == 0 {
-		usage, _ = service.ResponseText2Usage(responseText, modelName, promptTokens)
+		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
 	}
 	return nil, usage
 }
@@ -187,3 +212,42 @@ func cohereHandler(c *gin.Context, resp *http.Response, modelName string, prompt
 	_, err = c.Writer.Write(jsonResponse)
 	return nil, &usage
 }
+
+func cohereRerankHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	var cohereResp CohereRerankResponseResult
+	err = json.Unmarshal(responseBody, &cohereResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	usage := dto.Usage{}
+	if cohereResp.Meta.BilledUnits.InputTokens == 0 {
+		usage.PromptTokens = info.PromptTokens
+		usage.CompletionTokens = 0
+		usage.TotalTokens = info.PromptTokens
+	} else {
+		usage.PromptTokens = cohereResp.Meta.BilledUnits.InputTokens
+		usage.CompletionTokens = cohereResp.Meta.BilledUnits.OutputTokens
+		usage.TotalTokens = cohereResp.Meta.BilledUnits.InputTokens + cohereResp.Meta.BilledUnits.OutputTokens
+	}
+
+	var rerankResp dto.RerankResponse
+	rerankResp.Results = cohereResp.Results
+	rerankResp.Usage = usage
+
+	jsonResponse, err := json.Marshal(rerankResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = c.Writer.Write(jsonResponse)
+	return nil, &usage
+}

relay/channel/dify/adaptor.go

@@ -0,0 +1,70 @@
+package dify
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	return fmt.Sprintf("%s/v1/chat-messages", info.BaseUrl), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Header.Set("Authorization", "Bearer "+info.ApiKey)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	return requestOpenAI2Dify(*request), nil
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+	if info.IsStream {
+		err, usage = difyStreamHandler(c, resp, info)
+	} else {
+		err, usage = difyHandler(c, resp, info)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/dify/constants.go

@@ -0,0 +1,5 @@
+package dify
+
+var ModelList []string
+
+var ChannelName = "dify"

relay/channel/dify/dto.go

@@ -0,0 +1,35 @@
+package dify
+
+import "one-api/dto"
+
+type DifyChatRequest struct {
+	Inputs           map[string]interface{} `json:"inputs"`
+	Query            string                 `json:"query"`
+	ResponseMode     string                 `json:"response_mode"`
+	User             string                 `json:"user"`
+	AutoGenerateName bool                   `json:"auto_generate_name"`
+}
+
+type DifyMetaData struct {
+	Usage dto.Usage `json:"usage"`
+}
+
+type DifyData struct {
+	WorkflowId string `json:"workflow_id"`
+	NodeId     string `json:"node_id"`
+}
+
+type DifyChatCompletionResponse struct {
+	ConversationId string       `json:"conversation_id"`
+	Answer         string       `json:"answer"`
+	CreateAt       int64        `json:"create_at"`
+	MetaData       DifyMetaData `json:"metadata"`
+}
+
+type DifyChunkChatCompletionResponse struct {
+	Event          string       `json:"event"`
+	ConversationId string       `json:"conversation_id"`
+	Answer         string       `json:"answer"`
+	Data           DifyData     `json:"data"`
+	MetaData       DifyMetaData `json:"metadata"`
+}