refactor: Enhance error handling in Gemini request conversion

- Updated `CovertGemini2OpenAI` function to return an error alongside the GeminiChatRequest, improving error reporting for image processing. - Modified `ConvertRequest` methods in both `adaptor.go` files to handle potential errors from the Gemini conversion, ensuring robust request handling. - Improved clarity and maintainability of the code by explicitly managing error cases during request conversion.
feat: Add GEMINI_VISION_MAX_IMAGE_NUM configuration
2026-04-17 13:07:27 +00:00 · 2024-12-20 21:50:58 +08:00 · 2024-12-20 21:36:23 +08:00 · 2024-12-20 20:33:01 +08:00 · 2024-12-20 20:32:47 +08:00 · 2024-12-20 20:32:23 +08:00
33 changed files with 1350 additions and 837 deletions
--- a/README.en.md
+++ b/README.en.md
@@ -0,0 +1,151 @@
+<div align="center">
+
+![new-api](/web/public/logo.png)
+
+# New API
+
+🍥 Next Generation LLM Gateway and AI Asset Management System
+
+<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>
+
+<p align="center">
+  <a href="https://raw.githubusercontent.com/Calcium-Ion/new-api/main/LICENSE">
+    <img src="https://img.shields.io/github/license/Calcium-Ion/new-api?color=brightgreen" alt="license">
+  </a>
+  <a href="https://github.com/Calcium-Ion/new-api/releases/latest">
+    <img src="https://img.shields.io/github/v/release/Calcium-Ion/new-api?color=brightgreen&include_prereleases" alt="release">
+  </a>
+  <a href="https://github.com/users/Calcium-Ion/packages/container/package/new-api">
+    <img src="https://img.shields.io/badge/docker-ghcr.io-blue" alt="docker">
+  </a>
+  <a href="https://hub.docker.com/r/CalciumIon/new-api">
+    <img src="https://img.shields.io/badge/docker-dockerHub-blue" alt="docker">
+  </a>
+  <a href="https://goreportcard.com/report/github.com/Calcium-Ion/new-api">
+    <img src="https://goreportcard.com/badge/github.com/Calcium-Ion/new-api" alt="GoReportCard">
+  </a>
+</p>
+</div>
+
+## 📝 Project Description
+
+> [!NOTE]  
+> This is an open-source project developed based on [One API](https://github.com/songquanpeng/one-api)
+
+> [!IMPORTANT]  
+> - Users must comply with OpenAI's [Terms of Use](https://openai.com/policies/terms-of-use) and relevant laws and regulations. Not to be used for illegal purposes.
+> - This project is for personal learning only. Stability is not guaranteed, and no technical support is provided.
+
+## ✨ Key Features
+
+1. 🎨 New UI interface (some interfaces pending update)
+2. 🌍 Multi-language support (work in progress)
+3. 🎨 Added [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy) interface support, [Integration Guide](Midjourney.md)
+4. 💰 Online recharge support, configurable in system settings:
+    - [x] EasyPay
+5. 🔍 Query usage quota by key:
+    - Works with [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool)
+6. 📑 Configurable items per page in pagination
+7. 🔄 Compatible with original One API database (one-api.db)
+8. 💵 Support per-request model pricing, configurable in System Settings - Operation Settings
+9. ⚖️ Support channel **weighted random** selection
+10. 📈 Data dashboard (console)
+11. 🔒 Configurable model access per token
+12. 🤖 Telegram authorization login support:
+    1. System Settings - Configure Login Registration - Allow Telegram Login
+    2. Send /setdomain command to [@Botfather](https://t.me/botfather)
+    3. Select your bot, then enter http(s)://your-website/login
+    4. Telegram Bot name is the bot username without @
+13. 🎵 Added [Suno API](https://github.com/Suno-API/Suno-API) interface support, [Integration Guide](Suno.md)
+14. 🔄 Support for Rerank models, compatible with Cohere and Jina, can integrate with Dify, [Integration Guide](Rerank.md)
+15. ⚡ **[OpenAI Realtime API](https://platform.openai.com/docs/guides/realtime/integration)** - Support for OpenAI's Realtime API, including Azure channels
+
+## Model Support
+This version additionally supports:
+1. Third-party model **gps** (gpt-4-gizmo-*)
+2. [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy) interface, [Integration Guide](Midjourney.md)
+3. Custom channels with full API URL support
+4. [Suno API](https://github.com/Suno-API/Suno-API) interface, [Integration Guide](Suno.md)
+5. Rerank models, supporting [Cohere](https://cohere.ai/) and [Jina](https://jina.ai/), [Integration Guide](Rerank.md)
+6. Dify
+
+You can add custom models gpt-4-gizmo-* in channels. These are third-party models and cannot be called with official OpenAI keys.
+
+## Additional Configurations Beyond One API
+- `GENERATE_DEFAULT_TOKEN`: Generate initial token for new users, default `false`
+- `STREAMING_TIMEOUT`: Set streaming response timeout, default 60 seconds
+- `DIFY_DEBUG`: Output workflow and node info to client for Dify channel, default `true`
+- `FORCE_STREAM_OPTION`: Override client stream_options parameter, default `true`
+- `GET_MEDIA_TOKEN`: Calculate image tokens, default `true`
+- `GET_MEDIA_TOKEN_NOT_STREAM`: Calculate image tokens in non-stream mode, default `true`
+- `UPDATE_TASK`: Update async tasks (Midjourney, Suno), default `true`
+- `GEMINI_MODEL_MAP`: Specify Gemini model versions (v1/v1beta), format: "model:version", comma-separated
+- `COHERE_SAFETY_SETTING`: Cohere model [safety settings](https://docs.cohere.com/docs/safety-modes#overview), options: `NONE`, `CONTEXTUAL`, `STRICT`, default `NONE`
+- `GEMINI_VISION_MAX_IMAGE_NUM`: Gemini model maximum image number, default `16`, set to `-1` to disable
+
+## Deployment
+> [!TIP]
+> Latest Docker image: `calciumion/new-api:latest`  
+> Default account: root, password: 123456  
+> Update command:
+> ```
+> docker run --rm -v /var/run/docker.sock:/var/run/docker.sock containrrr/watchtower -cR
+> ```
+
+### Requirements
+- Local database (default): SQLite (Docker deployment must mount `/data` directory)
+- Remote database: MySQL >= 5.7.8, PgSQL >= 9.6
+
+### Docker Deployment
+### Using Docker Compose (Recommended)
+```shell
+# Clone project
+git clone https://github.com/Calcium-Ion/new-api.git
+cd new-api
+# Edit docker-compose.yml as needed
+# Start
+docker-compose up -d
+```
+
+### Direct Docker Image Usage
+```shell
+# SQLite deployment:
+docker run --name new-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/data calciumion/new-api:latest
+# MySQL deployment (add -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi"), modify database connection parameters as needed
+# Example:
+docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/data calciumion/new-api:latest
+```
+
+## Channel Retry
+Channel retry is implemented, configurable in `Settings->Operation Settings->General Settings`. **Cache recommended**.  
+First retry uses same priority, second retry uses next priority, and so on.
+
+### Cache Configuration
+1. `REDIS_CONN_STRING`: Use Redis as cache
+    + Example: `REDIS_CONN_STRING=redis://default:redispw@localhost:49153`
+2. `MEMORY_CACHE_ENABLED`: Enable memory cache, default `false`
+    + Example: `MEMORY_CACHE_ENABLED=true`
+
+### Why Some Errors Don't Retry
+Error codes 400, 504, 524 won't retry
+### To Enable Retry for 400
+In `Channel->Edit`, set `Status Code Override` to:
+```json
+{
+  "400": "500"
+}
+```
+
+## Integration Guides
+- [Midjourney Integration](Midjourney.md)
+- [Suno Integration](Suno.md)
+
+## Related Projects
+- [One API](https://github.com/songquanpeng/one-api): Original project
+- [Midjourney-Proxy](https://github.com/novicezk/midjourney-proxy): Midjourney interface support
+- [chatnio](https://github.com/Deeptrain-Community/chatnio): Next-gen AI B/C solution
+- [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool): Query usage quota by key
+
+## 🌟 Star History
+
+[![Star History Chart](https://api.star-history.com/svg?repos=Calcium-Ion/new-api&type=Date)](https://star-history.com/#Calcium-Ion/new-api&Date)
--- a/README.md
+++ b/README.md
@@ -1,59 +1,79 @@
+<p align="right">
+   <strong>中文</strong> | <a href="./README.en.md">English</a>
+</p>
 <div align="center">

 ![new-api](/web/public/logo.png)

 # New API

+
+🍥新一代大模型网关与AI资产管理系统
+
 <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>

+<p align="center">
+  <a href="https://raw.githubusercontent.com/Calcium-Ion/new-api/main/LICENSE">
+    <img src="https://img.shields.io/github/license/Calcium-Ion/new-api?color=brightgreen" alt="license">
+  </a>
+  <a href="https://github.com/Calcium-Ion/new-api/releases/latest">
+    <img src="https://img.shields.io/github/v/release/Calcium-Ion/new-api?color=brightgreen&include_prereleases" alt="release">
+  </a>
+  <a href="https://github.com/users/Calcium-Ion/packages/container/package/new-api">
+    <img src="https://img.shields.io/badge/docker-ghcr.io-blue" alt="docker">
+  </a>
+  <a href="https://hub.docker.com/r/CalciumIon/new-api">
+    <img src="https://img.shields.io/badge/docker-dockerHub-blue" alt="docker">
+  </a>
+  <a href="https://goreportcard.com/report/github.com/Calcium-Ion/new-api">
+    <img src="https://goreportcard.com/badge/github.com/Calcium-Ion/new-api" alt="GoReportCard">
+  </a>
+</p>
 </div>

-> [!NOTE]
+## 📝 项目说明
+
+> [!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

-> [!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。
-> 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。
+> [!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。
+> - 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。

-## 主要变更
-此分叉版本的主要变更如下：
+## ✨ 主要特性

-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)
-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
-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
-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）
-8. 支持模型按次数收费，可在 系统设置-运营设置 中设置
-9. 支持渠道**加权随机**
-10. 数据看板
-11. 可设置令牌能调用的模型
-12. 支持Telegram授权登录。
+1. 🎨 全新的UI界面（部分界面还待更新）
+2. 🌍 多语言支持（待完善）
+3. 🎨 添加[Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy)接口支持，[对接文档](Midjourney.md)
+4. 💰 支持在线充值功能，可在系统设置中设置：
+    - [x] 易支付
+5. 🔍 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
+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）
+8. 💵 支持模型按次数收费，可在 系统设置-运营设置 中设置
+9. ⚖️ 支持渠道**加权随机**
+10. 📈 数据看板（控制台）
+11. 🔒 可设置令牌能调用的模型
+12. 🤖 支持Telegram授权登录：
    1. 系统设置-配置登录注册-允许通过Telegram登录
    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)
-15. **[OpenAI Realtime API](https://platform.openai.com/docs/guides/realtime/integration)** - 支持OpenAI的Realtime API，支持Azure渠道。
+13. 🎵 添加 [Suno API](https://github.com/Suno-API/Suno-API)接口支持，[对接文档](Suno.md)
+14. 🔄 支持Rerank模型，目前兼容Cohere和Jina，可接入Dify，[对接文档](Rerank.md)
+15. ⚡ **[OpenAI Realtime API](https://platform.openai.com/docs/guides/realtime/integration)** - 支持OpenAI的Realtime API，支持Azure渠道
+16. 支持使用路由/chat2link 进入聊天界面

 ## 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-*）
-2. 智谱glm-4v，glm-4v识图
-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
+2. [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy)接口，[对接文档](Midjourney.md)
+3. 自定义渠道，支持填入完整调用地址
+4. [Suno API](https://github.com/Suno-API/Suno-API) 接口，[对接文档](Suno.md)
+5. Rerank模型，目前支持[Cohere](https://cohere.ai/)和[Jina](https://jina.ai/)，[对接文档](Rerank.md)
+6. Dify

 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。

@@ -67,6 +87,7 @@
 - `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(v1beta)
 - `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`。
+- `GEMINI_VISION_MAX_IMAGE_NUM`：Gemini模型最大图片数量，默认为 `16`，设置为 `-1` 则不限制。
 ## 部署
 > [!TIP]
 > 最新版Docker镜像：`calciumion/new-api:latest`  
@@ -151,6 +172,10 @@ docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:1234
 - [chatnio](https://github.com/Deeptrain-Community/chatnio)：下一代 AI 一站式 B/C 端解决方案
 - [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool)：用key查询使用额度

-## Star History
+其他基于New API的项目：
+- [new-api-horizon](https://github.com/Calcium-Ion/new-api-horizon)：New API高性能优化版，并支持Claude格式
+- [VoAPI](https://github.com/VoAPI/VoAPI)：基于New API的闭源项目
+
+## 🌟 Star History

 [![Star History Chart](https://api.star-history.com/svg?repos=Calcium-Ion/new-api&type=Date)](https://star-history.com/#Calcium-Ion/new-api&Date)
--- a/constant/channel_setting.go
+++ b/constant/channel_setting.go
@@ -0,0 +1,5 @@
+package constant
+
+var (
+	ForceFormat = "force_format" // ForceFormat 强制格式化为OpenAI格式
+)
--- a/constant/env.go
+++ b/constant/env.go
@@ -23,6 +23,8 @@ var GeminiModelMap = map[string]string{
 	"gemini-1.0-pro": "v1",
 }

+var GeminiVisionMaxImageNum = common.GetEnvOrDefault("GEMINI_VISION_MAX_IMAGE_NUM", 16)
+
 func InitEnv() {
 	modelVersionMapStr := strings.TrimSpace(os.Getenv("GEMINI_MODEL_MAP"))
 	if modelVersionMapStr == "" {
--- a/controller/channel-test.go
+++ b/controller/channel-test.go
@@ -153,6 +153,8 @@ func buildTestRequest(model string) *dto.GeneralOpenAIRequest {
 	}
 	if strings.HasPrefix(model, "o1-") {
 		testRequest.MaxCompletionTokens = 1
+	} else if strings.HasPrefix(model, "gemini-2.0-flash-thinking") {
+		testRequest.MaxTokens = 2
 	} else {
 		testRequest.MaxTokens = 1
 	}
--- a/i18n/en.json
+++ b/i18n/en.json
@@ -1,538 +0,0 @@
-{
-	"＄%.6f 额度": "＄%.6f quota",
-	"%d 点额度": "%d point quota",
-	"尚未实现": "Not yet implemented",
-	"余额不足": "Insufficient balance",
-	"危险操作": "Hazardous operations",
-	"输入你的账户名": "Enter your account name",
-	"确认删除": "Confirm Delete",
-	"确认绑定": "Confirm Binding",
-	"您正在删除自己的帐户，将清空所有数据且不可恢复": "You are deleting your account, all data will be cleared and unrecoverable.",
-	"\"通道「%s」（#%d）已被禁用\"": "\"Channel %s (#%d) has been disabled\"",
-	"通道「%s」（#%d）已被禁用，原因：%s": "Channel %s (#%d) has been disabled, reason: %s",
-	"测试已在运行中": "Test is already running",
-	"响应时间 %.2fs 超过阈值 %.2fs": "Response time %.2fs exceeds threshold %.2fs",
-	"通道测试完成": "Channel test completed",
-	"通道测试完成，如果没有收到禁用通知，说明所有通道都正常": "Channel test completed, if you have not received the disable notification, it means that all channels are normal",
-	"无法连接至 GitHub 服务器，请稍后重试！": "Unable to connect to GitHub server, please try again later!",
-	"返回值非法，用户字段为空，请稍后重试！": "The return value is illegal, the user field is empty, please try again later!",
-	"管理员未开启通过 GitHub 登录以及注册": "The administrator did not turn on login and registration via GitHub",
-	"管理员关闭了新用户注册": "The administrator has turned off new user registration",
-	"用户已被封禁": "User has been banned",
-	"该 GitHub 账户已被绑定": "The GitHub account has been bound",
-	"邮箱地址已被占用": "Email address is occupied",
-	"%s邮箱验证邮件": "%s Email verification email",
-	"<p>您好，你正在进行%s邮箱验证。</p>": "<p>Hello, you are verifying %s email.</p>",
-	"<p>您的验证码为: <strong>%s</strong></p>": "<p>Your verification code is: <strong>%s</strong></p>",
-	"<p>验证码 %d 分钟内有效，如果不是本人操作，请忽略。</p>": "<p>The verification code is valid within %d minutes. If it is not your operation, please ignore it.</p>",
-	"无效的参数": "Invalid parameter",
-	"该邮箱地址未注册": "The email address is not registered",
-	"%s密码重置": "%s Password reset",
-	"<p>您好，你正在进行%s密码重置。</p>": "<p>Hello, you are resetting %s password.</p>",
-	"<p>点击<a href='%s'>此处</a>进行密码重置。</p>": "<p>Click <a href='%s'>here</a> to reset your password.</p>",
-	"<p>重置链接 %d 分钟内有效，如果不是本人操作，请忽略。</p>": "<p>The reset link is valid within %d minutes. If it is not your operation, please ignore it.</p>",
-	"重置链接非法或已过期": "Reset link is illegal or expired",
-	"无法启用 GitHub OAuth，请先填入 GitHub Client ID 以及 GitHub Client Secret！": "Unable to enable GitHub OAuth, please fill in GitHub Client ID and GitHub Client Secret first!",
-	"无法启用微信登录，请先填入微信登录相关配置信息！": "Unable to enable WeChat login, please fill in the relevant configuration information for WeChat login first!",
-	"无法启用 Turnstile 校验，请先填入 Turnstile 校验相关配置信息！": "Unable to enable Turnstile verification, please fill in the relevant configuration information for Turnstile verification first!",
-	"兑换码名称长度必须在1-20之间": "The length of the redemption code name must be between 1-20",
-	"兑换码个数必须大于0": "The number of redemption codes must be greater than 0",
-	"一次兑换码批量生成的个数不能大于 100": "The number of redemption codes generated in a batch cannot be greater than 100",
-	"通过令牌「%s」使用模型 %s 消耗 %s（模型倍率 %.2f，分组倍率 %.2f）": "Using model %s with token %s consumes %s (model rate %.2f, group rate %.2f)",
-	"当前分组上游负载已饱和，请稍后再试": "The current group load is saturated, please try again later",
-	"令牌名称过长": "Token name is too long",
-	"令牌已过期，无法启用，请先修改令牌过期时间，或者设置为永不过期": "The token has expired and cannot be enabled. Please modify the expiration time of the token, or set it to never expire.",
-	"令牌可用额度已用尽，无法启用，请先修改令牌剩余额度，或者设置为无限额度": "The available quota of the token has been used up and cannot be enabled. Please modify the remaining quota of the token, or set it to unlimited quota",
-	"管理员关闭了密码登录": "The administrator has turned off password login",
-	"无法保存会话信息，请重试": "Unable to save session information, please try again",
-	"管理员关闭了通过密码进行注册，请使用第三方账户验证的形式进行注册": "The administrator has turned off registration via password. Please use the form of third-party account verification to register",
-	"输入不合法 ": "Input is illegal ",
-	"管理员开启了邮箱验证，请输入邮箱地址和验证码": "The administrator has turned on email verification, please enter the email address and verification code",
-	"验证码错误或已过期": "Verification code error or expired",
-	"无权获取同级或更高等级用户的信息": "No permission to get information of users at the same level or higher",
-	"请重试，系统生成的 UUID 竟然重复了！": "Please try again, the system-generated UUID is actually duplicated!",
-	"输入不合法": "Input is illegal",
-	"无权更新同权限等级或更高权限等级的用户信息": "No permission to update user information with the same permission level or higher permission level",
-	"管理员将用户额度从 %s修改为 %s": "The administrator changed the user quota from %s to %s",
-	"无权删除同权限等级或更高权限等级的用户": "No permission to delete users with the same permission level or higher permission level",
-	"无法创建权限大于等于自己的用户": "Unable to create users with permissions greater than or equal to your own",
-	"用户不存在": "User does not exist",
-	"无法禁用超级管理员用户": "Unable to disable super administrator user",
-	"无法删除超级管理员用户": "Unable to delete super administrator user",
-	"普通管理员用户无法提升其他用户为管理员": "Ordinary administrator users cannot promote other users to administrators",
-	"该用户已经是管理员": "The user is already an administrator",
-	"无法降级超级管理员用户": "Unable to downgrade super administrator user",
-	"该用户已经是普通用户": "The user is already an ordinary user",
-	"管理员未开启通过微信登录以及注册": "The administrator has not enabled login and registration via WeChat",
-	"该微信账号已被绑定": "The WeChat account has been bound",
-	"无权进行此操作，未登录且未提供 access token": "No permission to perform this operation, not logged in and no access token provided",
-	"无权进行此操作，access token 无效": "No permission to perform this operation, access token is invalid",
-	"无权进行此操作，权限不足": "No permission to perform this operation, insufficient permissions",
-	"普通用户不支持指定渠道": "Ordinary users do not support specifying channels",
-	"无效的渠道 ID": "Invalid channel ID",
-	"该渠道已被禁用": "The channel has been disabled",
-	"无效的请求": "Invalid request",
-	"无可用渠道": "No available channels",
-	"Turnstile token 为空": "Turnstile token is empty",
-	"Turnstile 校验失败，请刷新重试！": "Turnstile verification failed, please refresh and try again!",
-	"id 为空！": "id is empty!",
-	"未提供兑换码": "No redemption code provided",
-	"无效的 user id": "Invalid user id",
-	"无效的兑换码": "Invalid redemption code",
-	"该兑换码已被使用": "The redemption code has been used",
-	"通过兑换码充值 %s": "Recharge %s through redemption code",
-	"未提供令牌": "No token provided",
-	"该令牌状态不可用": "The token status is not available",
-	"该令牌已过期": "The token has expired",
-	"该令牌额度已用尽": "The token quota has been used up",
-	"无效的令牌": "Invalid token",
-	"id 或 userId 为空！": "id or userId is empty!",
-	"quota 不能为负数！": "quota cannot be negative!",
-	"令牌额度不足": "Insufficient token quota",
-	"用户额度不足": "Insufficient user quota",
-	"您的额度即将用尽": "Your quota is about to run out",
-	"您的额度已用尽": "Your quota has been used up",
-	"%s，当前剩余额度为 %d，为了不影响您的使用，请及时充值。<br/>充值链接：<a href='%s'>%s</a>": "%s, the current remaining quota is %d, in order not to affect your use, please recharge in time. <br/> Recharge link: <a href='%s'>%s</a>",
-	"affCode 为空！": "affCode is empty!",
-	"新用户注册赠送 %s": "New user registration gives %s",
-	"使用邀请码赠送 %s": "Use invitation code to give %s",
-	"邀请用户赠送 %s": "Invite users to give %s",
-	"用户名或密码为空": "Username or password is empty",
-	"用户名或密码错误，或用户已被封禁": "Username or password is wrong, or user has been banned",
-	"email 为空！": "email is empty!",
-	"GitHub id 为空！": "GitHub id is empty!",
-	"WeChat id 为空！": "WeChat id is empty!",
-	"username 为空！": "username is empty!",
-	"邮箱地址或密码为空！": "Email address or password is empty!",
-	"OpenAI 接口聚合管理，支持多种渠道包括 Azure，可用于二次分发管理 key，仅单可执行文件，已打包好 Docker 镜像，一键部署，开箱即用": "OpenAI interface aggregation management, supports multiple channels including Azure, can be used for secondary distribution management key, only single executable file, Docker image has been packaged, one-click deployment, out of the box",
-	"未知类型": "Unknown type",
-	"不支持": "Not supported",
-	"操作成功完成！": "Operation completed successfully!",
-	"已启用": "Enabled",
-	"已禁用": "Disabled",
-	"未知状态": "Unknown status",
-	" 秒": "s",
-	" 分钟 ": " m ",
-	" 小时 ": " h ",
-	" 天 ": " d ",
-	" 个月 ": " M ",
-	" 年 ": " y ",
-	"未测试": "Not tested",
-	"通道 ${name} 测试成功，耗时 ${time.toFixed(2)} 秒。": "Channel ${name} test succeeded, time consumed ${time.toFixed(2)} s.",
-	"已成功开始测试所有已启用通道，请刷新页面查看结果。": "All enabled channels have been successfully tested, please refresh the page to view the results.",
-	"通道 ${name} 余额更新成功！": "Channel ${name} balance updated successfully!",
-	"已更新完毕所有已启用通道余额！": "The balance of all enabled channels has been updated!",
-	"搜索渠道的 ID，名称和密钥 ...": "Search for channel ID, name and key ...",
-	"名称": "Name",
-	"分组": "Group",
-	"类型": "Type",
-	"状态": "Status",
-	"响应时间": "Response time",
-	"余额": "Balance",
-	"操作": "Operation",
-	"未更新": "Not updated",
-	"测试": "Test",
-	"更新余额": "Update balance",
-	"删除": "Delete",
-	"删除渠道 {channel.name}": "Delete channel {channel.name}",
-	"禁用": "Disable",
-	"启用": "Enable",
-	"编辑": "Edit",
-	"添加新的渠道": "Add a new channel",
-	"测试所有已启用通道": "Test all enabled channels",
-	"更新所有已启用通道余额": "Update the balance of all enabled channels",
-	"刷新": "Refresh",
-	"处理中...": "Processing...",
-	"绑定成功！": "Binding succeeded!",
-	"登录成功！": "Login succeeded!",
-	"操作失败，重定向至登录界面中...": "Operation failed, redirecting to the login page...",
-	"出现错误，第 ${count} 次重试中...": "An error occurred, retrying for the ${count} time...",
-	"首页": "Home",
-	"渠道": "Channel",
-	"令牌": "Token",
-	"兑换": "Redeem",
-	"充值": "Recharge",
-	"用户": "User",
-	"日志": "Log",
-	"设置": "Settings",
-	"关于": "About",
-	"聊天": "Chat",
-	"注销成功!": "Logout succeeded!",
-	"注销": "Logout",
-	"登录": "Login",
-	"注册": "Register",
-	"加载{name}中...": "Loading {name}...",
-	"未登录或登录已过期，请重新登录！": "Not logged in or login has expired, please log in again!",
-	"用户登录": "User login",
-	"\"用户名\"": "\"Username\"",
-	"\"密码\"": "\"Password\"",
-	"忘记密码？": "Forget password?",
-	"点击重置": "Click to reset",
-	"； 没有账户？": "; No account?",
-	"点击注册": "Click to register",
-	"微信扫码关注公众号，输入「验证码」获取验证码（三分钟内有效）": "Scan the QR code of WeChat to follow the official account, enter \"verification code\" to get the verification code (valid within three minutes)",
-	"\"验证码\"": "\"Verification code\"",
-	"全部用户": "All users",
-	"当前用户": "Current user",
-	"全部'": "All'",
-	"充值'": "Recharge'",
-	"消费'": "Consumption'",
-	"管理'": "Management'",
-	"系统'": "System'",
-	" 充值 ": " Recharge ",
-	" 消费 ": " Consumption ",
-	" 管理 ": " Management ",
-	" 系统 ": " System ",
-	" 未知 ": " Unknown ",
-	"时间": "Time",
-	"详情": "Details",
-	"选择模式": "Select mode",
-	"选择明细分类": "Select details category",
-	"模型倍率不是合法的 JSON 字符串": "Model rate is not a valid JSON string",
-	"分组倍率不是合法的 JSON 字符串": "Group rate is not a valid JSON string",
-	"通用设置": "General Settings",
-	"充值链接": "Recharge Link",
-	"例如发卡网站的购买链接": "For example, the purchase link of the card issuing website",
-	"聊天页面链接": "Chat Page Link",
-	"例如 ChatGPT Next Web 的部署地址": "For example, the deployment address of ChatGPT Next Web",
-	"单位美元额度": "Unit Dollar Quota",
-	"一单位货币能兑换的额度": "Quota that can be exchanged for one unit of currency",
-	"启用额度消费日志记录": "Enable quota consumption log recording",
-	"以货币形式显示额度": "Display quota in the form of currency",
-	"相关 API 显示令牌额度而非用户额度": "Related API displays token quota instead of user quota",
-	"保存通用设置": "Save General Settings",
-	"监控设置": "Monitoring Settings",
-	"最长响应时间": "Longest Response Time",
-	"单位秒": "Unit in seconds",
-	"当运行通道全部测试时": "When all operating channels are tested",
-	"超过此时间将自动禁用通道": "Channels will be automatically disabled if this time is exceeded",
-	"额度提醒阈值": "Quota reminder threshold",
-	"低于此额度时将发送邮件提醒用户": "Email will be sent to remind users when the quota is below this",
-	"失败时自动禁用通道": "Automatically disable the channel when it fails",
-	"保存监控设置": "Save Monitoring Settings",
-	"额度设置": "Quota Settings",
-	"新用户初始额度": "Initial quota for new users",
-	"例如": "For example",
-	"请求预扣费额度": "Request for pre-deducted quota",
-	"请求结束后多退少补": "Refund more or less after the request ends",
-	"邀请新用户奖励额度": "Invite new users to reward quota",
-	"新用户使用邀请码奖励额度": "New user rewards quota using invitation code",
-	"保存额度设置": "Save Quota Settings",
-	"倍率设置": "Rate Settings",
-	"模型倍率": "Model rate",
-	"为一个 JSON 文本": "Is a JSON text",
-	"键为模型名称": "Key is model name",
-	"值为倍率": "Value is the rate",
-	"分组倍率": "Group rate",
-	"键为分组名称": "Key is group name",
-	"保存倍率设置": "Save Rate Settings",
-	"已是最新版本": "Is the latest version",
-	"检查更新": "Check for updates",
-	"公告": "Announcement",
-	"在此输入新的公告内容，支持 Markdown & HTML 代码": "Enter the new announcement content here, supports Markdown & HTML code",
-	"保存公告": "Save Announcement",
-	"个性化设置": "Personalization Settings",
-	"系统名称": "System Name",
-	"在此输入系统名称": "Enter the system name here",
-	"设置系统名称": "Set system name",
-	"图片地址": "Image URL",
-	"在此输入 Logo 图片地址": "Enter the Logo image URL here",
-	"首页内容": "Home Page Content",
-	"在此输入首页内容，支持 Markdown & HTML 代码，设置后首页的状态信息将不再显示。如果输入的是一个链接，则会使用该链接作为 iframe 的 src 属性，这允许你设置任意网页作为首页": "Enter the homepage content here, supports Markdown & HTML code. Once set, the status information of the homepage will not be displayed. If a link is entered, it will be used as the src attribute of the iframe, allowing you to set any webpage as the homepage.",
-	"保存首页内容": "Save Home Page Content",
-	"在此输入新的关于内容，支持 Markdown & HTML 代码。如果输入的是一个链接，则会使用该链接作为 iframe 的 src 属性，这允许你设置任意网页作为关于页面": "Enter new about content here, supports Markdown & HTML code. If a link is entered, it will be used as the src attribute of the iframe, allowing you to set any webpage as the about page.",
-	"保存关于": "Save About",
-	"移除 One API 的版权标识必须首先获得授权，项目维护需要花费大量精力，如果本项目对你有意义，请主动支持本项目": "Removal of One API copyright mark must first be authorized. Project maintenance requires a lot of effort. If this project is meaningful to you, please actively support it.",
-	"页脚": "Footer",
-	"在此输入新的页脚，留空则使用默认页脚，支持 HTML 代码": "Enter the new footer here, leave blank to use the default footer, supports HTML code.",
-	"设置页脚": "Set Footer",
-	"新版本": "New Version",
-	"关闭": "Close",
-	"密码已重置并已复制到剪贴板": "Password has been reset and copied to clipboard",
-	"密码重置确认": "Password Reset Confirmation",
-	"邮箱地址": "Email Address",
-	"提交": "Submit",
-	"请稍后几秒重试": "Please retry in a few seconds",
-	"正在检查用户环境": "Checking user environment",
-	"重置邮件发送成功": "Reset mail sent successfully",
-	"请检查邮箱": "Please check your email",
-	"密码重置": "Password Reset",
-	"令牌已重置并已复制到剪贴板": "Token has been reset and copied to clipboard",
-	"邀请链接已复制到剪切板": "Invitation link has been copied to clipboard",
-	"微信账户绑定成功": "WeChat account binding succeeded",
-	"验证码发送成功": "Verification code sent successfully",
-	"邮箱账户绑定成功": "Email account binding succeeded",
-	"注意": "Note",
-	"此处生成的令牌用于系统管理": "The token generated here is used for system management",
-	"而非用于请求 OpenAI 相关的服务": "Not for requesting OpenAI related services",
-	"请知悉": "Please be aware",
-	"更新个人信息": "Update Personal Information",
-	"生成系统访问令牌": "Generate System Access Token",
-	"复制邀请链接": "Copy Invitation Link",
-	"账号绑定": "Account Binding",
-	"绑定微信账号": "Bind WeChat Account",
-	"微信扫码关注公众号": "Scan the QR code with WeChat to follow the official account",
-	"输入": "Enter",
-	"验证码": "Verification Code",
-	"获取验证码": "Get Verification Code",
-	"三分钟内有效": "Valid for three minutes",
-	"绑定": "Bind",
-	"绑定 GitHub 账号": "Bind GitHub Account",
-	"绑定邮箱地址": "Bind Email Address",
-	"输入邮箱地址": "Enter Email Address",
-	"未使用": "Unused",
-	"已使用": "Used",
-	"操作成功完成": "Operation successfully completed",
-	"搜索兑换码的 ID 和名称": "Search for ID and name",
-	"额度": "Quota",
-	"创建时间": "Creation Time",
-	"兑换时间": "Redemption Time",
-	"尚未兑换": "Not yet redeemed",
-	"已复制到剪贴板": "Copied to clipboard",
-	"无法复制到剪贴板": "Unable to copy to clipboard",
-	"请手动复制": "Please copy manually",
-	"已将兑换码填入搜索框": "The voucher code has been filled into the search box",
-	"复制": "Copy",
-	"添加新的兑换码": "Add a new voucher",
-	"密码长度不得小于 8 位": "Password length must not be less than 8 characters",
-	"两次输入的密码不一致": "The two passwords entered do not match",
-	"注册成功": "Registration succeeded",
-	"请稍后几秒重试，Turnstile 正在检查用户环境": "Please retry in a few seconds, Turnstile is checking user environment",
-	"验证码发送成功，请检查你的邮箱": "Verification code sent successfully, please check your email",
-	"新用户注册": "New User Registration",
-	"输入用户名，最长 12 位": "Enter username, up to 12 characters",
-	"输入密码，最短 8 位，最长 20 位": "Enter password, at least 8 characters and up to 20 characters",
-	"输入验证码": "Enter Verification Code",
-	"已有账户": "Already have an account",
-	"点击登录": "Click to log in",
-	"服务器地址": "Server Address",
-	"更新服务器地址": "Update Server Address",
-	"配置登录注册": "Configure Login/Registration",
-	"允许通过密码进行登录": "Allow login via password",
-	"允许通过密码进行注册": "Allow registration via password",
-	"通过密码注册时需要进行邮箱验证": "Email verification is required when registering via password",
-	"允许通过 GitHub 账户登录 & 注册": "Allow login & registration via GitHub account",
-	"允许通过微信登录 & 注册": "Allow login & registration via WeChat",
-	"允许新用户注册（此项为否时，新用户将无法以任何方式进行注册": "Allow new user registration (if this option is off, new users will not be able to register in any way",
-	"启用 Turnstile 用户校验": "Enable Turnstile user verification",
-	"配置 SMTP": "Configure SMTP",
-	"用以支持系统的邮件发送": "To support the system email sending",
-	"SMTP 服务器地址": "SMTP Server Address",
-	"例如：smtp.qq.com": "For example: smtp.qq.com",
-	"SMTP 端口": "SMTP Port",
-	"默认: 587": "Default: 587",
-	"SMTP 账户": "SMTP Account",
-	"通常是邮箱地址": "Usually an email address",
-	"发送者邮箱": "Sender email",
-	"通常和邮箱地址保持一致": "Usually consistent with the email address",
-	"SMTP 访问凭证": "SMTP Access Credential",
-	"敏感信息不会发送到前端显示": "Sensitive information will not be displayed in the frontend",
-	"保存 SMTP 设置": "Save SMTP Settings",
-	"配置 GitHub OAuth App": "Configure GitHub OAuth App",
-	"配置 Linuxdo OAuth App": "Configure Linuxdo OAuth App",
-	"用以支持通过 GitHub 进行登录注册": "To support login & registration via GitHub",
-	"点击此处": "Click here",
-	"管理你的 GitHub OAuth App": "Manage your GitHub OAuth App",
-	"输入你注册的 GitHub OAuth APP 的 ID": "Enter your registered GitHub OAuth APP ID",
-	"保存 GitHub OAuth 设置": "Save GitHub OAuth Settings",
-	"配置 WeChat Server": "Configure WeChat Server",
-	"用以支持通过微信进行登录注册": "To support login & registration via WeChat",
-	"了解 WeChat Server": "Learn about WeChat Server",
-	"WeChat Server 访问凭证": "WeChat Server Access Credential",
-	"微信公众号二维码图片链接": "WeChat Public Account QR Code Image Link",
-	"输入一个图片链接": "Enter an image link",
-	"保存 WeChat Server 设置": "Save WeChat Server Settings",
-	"配置 Turnstile": "Configure Turnstile",
-	"用以支持用户校验": "To support user verification",
-	"管理你的 Turnstile Sites，推荐选择 Invisible Widget Type": "Manage your Turnstile Sites, recommend selecting Invisible Widget Type",
-	"输入你注册的 Turnstile Site Key": "Enter your registered Turnstile Site Key",
-	"保存 Turnstile 设置": "Save Turnstile Settings",
-	"已过期": "Expired",
-	"已耗尽": "Exhausted",
-	"搜索令牌的名称 ...": "Search for the name of the token...",
-	"已用额度": "Quota used",
-	"剩余额度": "Remaining quota",
-	"过期时间": "Expiration time",
-	"无": "None",
-	"无限制": "Unlimited",
-	"永不过期": "Never expires",
-	"无法复制到剪贴板，请手动复制，已将令牌填入搜索框": "Unable to copy to clipboard, please copy manually, the token has been entered into the search box",
-	"删除令牌": "Delete Token",
-	"添加新的令牌": "Add New Token",
-	"普通用户": "Regular User",
-	"管理员": "Admin",
-	"超级管理员": "Super Admin",
-	"未知身份": "Unknown Identity",
-	"已激活": "Activated",
-	"已封禁": "Banned",
-	"搜索用户的 ID，用户名，显示名称，以及邮箱地址 ...": "Search user ID, username, display name, and email address...",
-	"用户名": "Username",
-	"统计信息": "Statistics",
-	"用户角色": "User Role",
-	"未绑定邮箱地址": "Email not bound",
-	"请求次数": "Number of Requests",
-	"提升": "Promote",
-	"降级": "Demote",
-	"删除用户": "Delete User",
-	"添加新的用户": "Add New User",
-	"自定义": "Custom",
-	"等价金额": "Equivalent Amount",
-	"等价金额：{{quota}}：": "Equivalent amount: {{quota}}",
-	"未登录或登录已过期，请重新登录": "Not logged in or login has expired, please log in again",
-	"请求次数过多，请稍后再试": "Too many requests, please try again later",
-	"服务器内部错误，请联系管理员": "Server internal error, please contact the administrator",
-	"本站仅作演示之用，无服务端": "This site is for demonstration purposes only, no server-side",
-	"超级管理员未设置充值链接！": "Super administrator has not set the recharge link!",
-	"错误：": "Error: ",
-	"新版本可用：${data.version}，请使用快捷键 Shift + F5 刷新页面": "New version available: ${data.version}, please refresh the page using shortcut Shift + F5",
-	"无法正常连接至服务器": "Unable to connect to the server normally",
-	"管理渠道": "Manage Channels",
-	"系统状况": "System Status",
-	"系统信息": "System Information",
-	"系统信息总览": "System Information Overview",
-	"版本": "Version",
-	"源码": "Source Code",
-	"启动时间": "Startup Time",
-	"系统配置": "System Configuration",
-	"系统配置总览": "System Configuration Overview",
-	"邮箱验证": "Email Verification",
-	"未启用": "Not Enabled",
-	"GitHub 身份验证": "GitHub Authentication",
-	"微信身份验证": "WeChat Authentication",
-	"Turnstile 用户校验": "Turnstile User Verification",
-	"创建新的渠道": "Create New Channel",
-	"镜像": "Mirror",
-	"请输入镜像站地址，格式为：https://domain.com，可不填，不填则使用渠道默认值": "Please enter the mirror site address, the format is: https://domain.com, it can be left blank, if left blank, the default value of the channel will be used",
-	"模型": "Model",
-	"请选择该通道所支持的模型": "Please select the model supported by the channel",
-	"填入基础模型": "Fill in the basic model",
-	"填入所有模型": "Fill in all models",
-	"清除所有模型": "Clear all models",
-	"密钥": "Key",
-	"请输入密钥": "Please enter the key",
-	"批量创建": "Batch Create",
-	"更新渠道信息": "Update Channel Information",
-	"我的令牌": "My Tokens",
-	"管理兑换码": "Manage Redeem Codes",
-	"兑换码": "Redeem Code",
-	"管理用户": "Manage Users",
-	"额度明细": "Quota Details",
-	"个人设置": "Personal Settings",
-	"运营设置": "Operation Settings",
-	"系统设置": "System Settings",
-	"其他设置": "Other Settings",
-	"项目仓库地址": "Project Repository Address",
-	"可在设置页面设置关于内容，支持 HTML & Markdown": "You can set the content about in the settings page, support HTML & Markdown",
-	"由{' '}": "built by{' '}",
-	"构建，源代码遵循{' '}": ", the source code licensed under{' '}",
-	"MIT 协议": "MIT License",
-	"充值额度": "Recharge Quota",
-	"获取兑换码": "Get Redeem Code",
-	"一个月后过期": "Expires after one month",
-	"一天后过期": "Expires after one day",
-	"一小时后过期": "Expires after one hour",
-	"一分钟后过期": "Expires after one minute",
-	"创建新的令牌": "Create New Token",
-	"注意，令牌的额度仅用于限制令牌本身的最大额度使用量，实际的使用受到账户的剩余额度限制。": "Note that the quota of the token is only used to limit the maximum quota usage of the token itself, and the actual usage is limited by the remaining quota of the account.",
-	"设为无限额度": "Set to unlimited quota",
-	"更新令牌信息": "Update Token Information",
-	"请输入充值码！": "Please enter the recharge code!",
-	"请输入名称": "Please enter a name",
-	"请输入密钥，一行一个": "Please enter the key, one per line",
-	"请输入额度": "Please enter the quota",
-	"令牌创建成功": "Token created successfully",
-	"令牌更新成功": "Token updated successfully",
-	"充值成功！": "Recharge successful!",
-	"更新用户信息": "Update User Information",
-	"请输入新的用户名": "Please enter a new username",
-	"密码": "Password",
-	"请输入新的密码": "Please enter a new password",
-	"显示名称": "Display Name",
-	"请输入新的显示名称": "Please enter a new display name",
-	"已绑定的 GitHub 账户": "GitHub Account Bound",
-	"此项只读，需要用户通过个人设置页面的相关绑定按钮进行绑定，不可直接修改": "This item is read-only. Users need to bind through the relevant binding button on the personal settings page, and cannot be modified directly",
-	"已绑定的微信账户": "WeChat Account Bound",
-	"已绑定的邮箱账户": "Email Account Bound",
-	"用户信息更新成功！": "User information updated successfully!",
-	"模型倍率 %.2f，分组倍率 %.2f": "model rate %.2f, group rate %.2f",
-	"使用明细（总消耗额度：{renderQuota(stat.quota)}）": "Usage Details (Total Consumption Quota: {renderQuota(stat.quota)})",
-	"用户名称": "User Name",
-	"令牌名称": "Token Name",
-	"留空则查询全部用户": "Leave blank to query all users",
-	"留空则查询全部令牌": "Leave blank to query all tokens",
-	"模型名称": "Model Name",
-	"留空则查询全部模型": "Leave blank to query all models",
-	"起始时间": "Start Time",
-	"结束时间": "End Time",
-	"查询": "Query",
-	"提示": "Prompt",
-	"补全": "Completion",
-	"消耗额度": "Used Quota",
-	"可选值": "Optional Values",
-	"渠道不存在：%d": "Channel does not exist: %d",
-	"数据库一致性已被破坏，请联系管理员": "Database consistency has been broken, please contact the administrator",
-	"使用近似的方式估算 token 数以减少计算量": "Estimate the number of tokens in an approximate way to reduce computational load",
-	"请填写ChannelName和ChannelKey！": "Please fill in the ChannelName and ChannelKey!",
-	"请至少选择一个Model！": "Please select at least one Model!",
-	"加载首页内容失败": "Failed to load the homepage content",
-	"加载关于内容失败": "Failed to load the About content",
-	"兑换码更新成功！": "Redemption code updated successfully!",
-	"兑换码创建成功！": "Redemption code created successfully!",
-	"用户账户创建成功！": "User account created successfully!",
-	"生成数量": "Generate quantity",
-	"请输入生成数量": "Please enter the quantity to generate",
-	"创建新用户账户": "Create new user account",
-	"渠道更新成功！": "Channel updated successfully!",
-	"渠道创建成功！": "Channel created successfully!",
-	"请选择分组": "Please select a group",
-	"更新兑换码信息": "Update redemption code information",
-	"创建新的兑换码": "Create a new redemption code",
-	"请在系统设置页面编辑分组倍率以添加新的分组：": "Please edit the group ratio in the system settings page to add a new group:",
-	"未找到所请求的页面": "The requested page was not found",
-	"过期时间格式错误！": "Expiration time format error!",
-	"请输入过期时间，格式为 yyyy-MM-dd HH:mm:ss，-1 表示无限制": "Please enter the expiration time, the format is yyyy-MM-dd HH:mm:ss, -1 means no limit",
-	"此项可选，为一个 JSON 文本，键为用户请求的模型名称，值为要替换的模型名称，例如：": "This is optional, it's a JSON text, the key is the model name requested by the user, and the value is the model name to be replaced, for example:",
-	"此项可选，输入镜像站地址，格式为：": "This is optional, enter the mirror site address, the format is:",
-	"模型映射": "Model mapping",
-	"请输入默认 API 版本，例如：2023-03-15-preview，该配置可以被实际的请求查询参数所覆盖": "Please enter the default API version, for example: 2023-03-15-preview, this configuration can be overridden by the actual request query parameters",
-	"默认": "Default",
-	"图片演示": "Image demo",
-	"参数替换为你的部署名称（模型名称中的点会被剔除）": "Replace the parameter with your deployment name (dots in the model name will be removed)",
-	"模型映射必须是合法的 JSON 格式！": "Model mapping must be in valid JSON format!",
-	"取消无限额度": "Cancel unlimited quota",
-	"取消": "Cancel",
-	"请输入新的剩余额度": "Please enter the new remaining quota",
-	"请输入单个兑换码中包含的额度": "Please enter the quota included in a single redemption code",
-	"请输入用户名": "Please enter username",
-	"请输入显示名称": "Please enter display name",
-	"请输入密码": "Please enter password",
-	"模型部署名称必须和模型名称保持一致": "The model deployment name must be consistent with the model name",
-	"，因为 One API 会把请求体中的 model": ", because One API will take the model in the request body",
-	"请输入 AZURE_OPENAI_ENDPOINT": "Please enter AZURE_OPENAI_ENDPOINT",
-	"请输入自定义渠道的 Base URL": "Please enter the Base URL of the custom channel",
-	"Homepage URL 填": "Fill in the Homepage URL",
-	"Authorization callback URL 填": "Fill in the Authorization callback URL",
-	"请为通道命名": "Please name the channel",
-	"此项可选，用于修改请求体中的模型名称，为一个 JSON 字符串，键为请求中模型名称，值为要替换的模型名称，例如：": "This is optional, used to modify the model name in the request body, it's a JSON string, the key is the model name in the request, and the value is the model name to be replaced, for example:",
-	"模型重定向": "Model redirection",
-	"请输入渠道对应的鉴权密钥": "Please enter the authentication key corresponding to the channel",
-	"注意，": "Note that, ",
-	"，图片演示。": "related image demo.",
-	"令牌创建成功，请在列表页面点击复制获取令牌！": "Token created successfully, please click copy on the list page to get the token!",
-	"代理": "Proxy",
-	"此项可选，用于通过代理站来进行 API 调用，请输入代理站地址，格式为：https://domain.com": "This is optional, used to make API calls through the proxy site, please enter the proxy site address, the format is: https://domain.com",
-	"取消密码登录将导致所有未绑定其他登录方式的用户（包括管理员）无法通过密码登录，确认取消？": "Canceling password login will cause all users (including administrators) who have not bound other login methods to be unable to log in via password, confirm cancel?",
-	"按照如下格式输入：": "Enter in the following format:",
-	"模型版本": "Model version",
-	"请输入星火大模型版本，注意是接口地址中的版本号，例如：v2.1": "Please enter the version of the Starfire model, note that it is the version number in the interface address, for example: v2.1",
-	"点击查看": "click to view",
-	"请确保已在 Azure 上创建了 gpt-35-turbo 模型，并且 apiVersion 已正确填写！": "Please make sure that the gpt-35-turbo model has been created on Azure, and the apiVersion has been filled in correctly!",
-	"第 {{start}} - {{end}} 条，共 {{total}} 条": "Items {{start}} - {{end}} of {{total}}",
-	"模型测试": "Model test",
-	"请选择最长响应时间": "Please select the longest response time",
-	"成功时自动启用通道": "Enable channel when successful",
-	"分钟": "minutes",
-	"设置过短会影响数据库性能": "Setting too short will affect database performance",
-	"仅修改展示粒度，统计精确到小时": "Only modify display granularity, statistics accurate to the hour",
-	"当运行通道全部测试时，超过此时间将自动禁用通道": "When running all channel tests, the channel will be automatically disabled when this time is exceeded"
-}
--- a/i18n/translate.py
+++ b/i18n/translate.py
@@ -1,61 +0,0 @@
-import argparse
-import json
-import os
-
-def list_file_paths(path):
-    file_paths = []
-    for root, dirs, files in os.walk(path):
-        if "node_modules" in dirs:
-            dirs.remove("node_modules")
-        if "build" in dirs:
-            dirs.remove("build")
-        if "i18n" in dirs:
-            dirs.remove("i18n")
-        for file in files:
-            file_path = os.path.join(root, file)
-            if file_path.endswith("png") or file_path.endswith("ico") or file_path.endswith("db") or file_path.endswith("exe"):
-                continue
-            file_paths.append(file_path)
-
-        for dir in dirs:
-            dir_path = os.path.join(root, dir)
-            file_paths += list_file_paths(dir_path)
-
-    return file_paths
-
-
-def replace_keys_in_repository(repo_path, json_file_path):
-    with open(json_file_path, 'r', encoding="utf-8") as json_file:
-        key_value_pairs = json.load(json_file)
-
-    pairs = []
-    for key, value in key_value_pairs.items():
-        pairs.append((key, value))
-    pairs.sort(key=lambda x: len(x[0]), reverse=True)
-
-    files = list_file_paths(repo_path)
-    print('Total files: {}'.format(len(files)))
-    for file_path in files:
-        replace_keys_in_file(file_path, pairs)
-
-
-def replace_keys_in_file(file_path, pairs):
-    try:
-        with open(file_path, 'r', encoding="utf-8") as file:
-            content = file.read()
-
-        for key, value in pairs:
-            content = content.replace(key, value)
-
-        with open(file_path, 'w', encoding="utf-8") as file:
-            file.write(content)
-    except UnicodeDecodeError:
-        print('UnicodeDecodeError: {}'.format(file_path))
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description='Replace keys in repository.')
-    parser.add_argument('--repository_path', help='Path to repository')
-    parser.add_argument('--json_file_path', help='Path to JSON file')
-    args = parser.parse_args()
-    replace_keys_in_repository(args.repository_path, args.json_file_path)
--- a/middleware/distributor.go
+++ b/middleware/distributor.go
@@ -213,6 +213,7 @@ func SetupContextForSelectedChannel(c *gin.Context, channel *model.Channel, mode
 	c.Set("channel_id", channel.Id)
 	c.Set("channel_name", channel.Name)
 	c.Set("channel_type", channel.Type)
+	c.Set("channel_setting", channel.GetSetting())
 	if nil != channel.OpenAIOrganization && "" != *channel.OpenAIOrganization {
 		c.Set("channel_organization", *channel.OpenAIOrganization)
 	}
--- a/model/cache.go
+++ b/model/cache.go
@@ -342,3 +342,14 @@ func CacheGetChannel(id int) (*Channel, error) {
 	}
 	return c, nil
 }
+
+func CacheUpdateChannelStatus(id int, status int) {
+    if (!common.MemoryCacheEnabled) {
+        return
+    }
+    channelSyncLock.Lock()
+    defer channelSyncLock.Unlock()
+    if channel, ok := channelsIDM[id]; ok {
+        channel.Status = status
+    }
+}
--- a/model/channel.go
+++ b/model/channel.go
@@ -4,6 +4,7 @@ import (
 	"encoding/json"
 	"one-api/common"
 	"strings"
+	"sync"

 	"gorm.io/gorm"
 )
@@ -34,6 +35,7 @@ type Channel struct {
 	AutoBan           *int    `json:"auto_ban" gorm:"default:1"`
 	OtherInfo         string  `json:"other_info"`
 	Tag               *string `json:"tag" gorm:"index"`
+	Setting           string  `json:"setting" gorm:"type:text"`
 }

 func (channel *Channel) GetModels() []string {
@@ -289,7 +291,25 @@ func (channel *Channel) Delete() error {
 	return err
 }

+var channelStatusLock sync.Mutex
+
 func UpdateChannelStatusById(id int, status int, reason string) {
+	if common.MemoryCacheEnabled {
+		channelStatusLock.Lock()
+		channelCache, _ := CacheGetChannel(id)
+		// 如果缓存渠道存在，且状态已是目标状态，直接返回
+		if channelCache != nil && channelCache.Status == status {
+			channelStatusLock.Unlock()
+			return
+		}
+		// 如果缓存渠道不存在(说明已经被禁用)，且要设置的状态不为启用，直接返回
+		if channelCache == nil && status != common.ChannelStatusEnabled {
+			channelStatusLock.Unlock()
+			return
+		}
+		CacheUpdateChannelStatus(id, status)
+		channelStatusLock.Unlock()
+	}
 	err := UpdateAbilityStatus(id, status == common.ChannelStatusEnabled)
 	if err != nil {
 		common.SysError("failed to update ability status: " + err.Error())
@@ -469,3 +489,23 @@ func SearchTags(keyword string, group string, model string, idSort bool) ([]*str

 	return tags, nil
 }
+
+func (channel *Channel) GetSetting() map[string]interface{} {
+	setting := make(map[string]interface{})
+	if channel.Setting != "" {
+		err := json.Unmarshal([]byte(channel.Setting), &setting)
+		if err != nil {
+			common.SysError("failed to unmarshal setting: " + err.Error())
+		}
+	}
+	return setting
+}
+
+func (channel *Channel) SetSetting(setting map[string]interface{}) {
+	settingBytes, err := json.Marshal(setting)
+	if err != nil {
+		common.SysError("failed to marshal setting: " + err.Error())
+		return
+	}
+	channel.Setting = string(settingBytes)
+}
--- a/relay/channel/gemini/adaptor.go
+++ b/relay/channel/gemini/adaptor.go
@@ -57,7 +57,11 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
-	return CovertGemini2OpenAI(*request), nil
+	ai, err := CovertGemini2OpenAI(*request)
+	if err != nil {
+		return nil, err
+	}
+	return ai, nil
 }

 func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
--- a/relay/channel/gemini/constant.go
+++ b/relay/channel/gemini/constant.go
@@ -1,14 +1,19 @@
 package gemini

-const (
-	GeminiVisionMaxImageNum = 16
-)
-
 var ModelList = []string{
-	"gemini-1.5-pro-latest", "gemini-1.5-flash-latest", "gemini-ultra",
+	// stable version
+	"gemini-1.5-pro", "gemini-1.5-flash", "gemini-1.5-flash-8b",
+	// latest version
+	"gemini-1.5-pro-latest", "gemini-1.5-flash-latest",
+	// legacy version
 	"gemini-1.5-pro-exp-0827", "gemini-1.5-flash-exp-0827",
-	"gemini-exp-1114", "gemini-exp-1206",
+	// exp
+	"gemini-exp-1114", "gemini-exp-1121", "gemini-exp-1206",
+	// flash exp
 	"gemini-2.0-flash-exp",
+	// thinking exp
+	"gemini-2.0-flash-thinking-exp",
+	"gemini-2.0-flash-thinking-exp-1219",
 }

 var ChannelName = "google gemini"
--- a/relay/channel/gemini/dto.go
+++ b/relay/channel/gemini/dto.go
@@ -1,10 +1,11 @@
 package gemini

 type GeminiChatRequest struct {
-	Contents         []GeminiChatContent        `json:"contents"`
-	SafetySettings   []GeminiChatSafetySettings `json:"safety_settings,omitempty"`
-	GenerationConfig GeminiChatGenerationConfig `json:"generation_config,omitempty"`
-	Tools            []GeminiChatTools          `json:"tools,omitempty"`
+	Contents           []GeminiChatContent        `json:"contents"`
+	SafetySettings     []GeminiChatSafetySettings `json:"safety_settings,omitempty"`
+	GenerationConfig   GeminiChatGenerationConfig `json:"generation_config,omitempty"`
+	Tools              []GeminiChatTools          `json:"tools,omitempty"`
+	SystemInstructions *GeminiChatContent         `json:"system_instruction,omitempty"`
 }

 type GeminiInlineData struct {
--- a/relay/channel/gemini/relay-gemini.go
+++ b/relay/channel/gemini/relay-gemini.go
@@ -4,7 +4,6 @@ import (
 	"bufio"
 	"encoding/json"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/common"
@@ -13,10 +12,12 @@ import (
 	relaycommon "one-api/relay/common"
 	"one-api/service"
 	"strings"
+
+	"github.com/gin-gonic/gin"
 )

 // Setting safety to the lowest possible values since Gemini is already powerless enough
-func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest) *GeminiChatRequest {
+func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest) (*GeminiChatRequest, error) {
 	geminiRequest := GeminiChatRequest{
 		Contents: make([]GeminiChatContent, 0, len(textRequest.Messages)),
 		SafetySettings: []GeminiChatSafetySettings{
@@ -36,6 +37,10 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest) *GeminiChatReques
 				Category:  "HARM_CATEGORY_DANGEROUS_CONTENT",
 				Threshold: common.GeminiSafetySetting,
 			},
+			{
+				Category:  "HARM_CATEGORY_CIVIC_INTEGRITY",
+				Threshold: common.GeminiSafetySetting,
+			},
 		},
 		GenerationConfig: GeminiChatGenerationConfig{
 			Temperature:     textRequest.Temperature,
@@ -72,29 +77,40 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest) *GeminiChatReques
 			},
 		}
 	}
-	shouldAddDummyModelMessage := false
+	//shouldAddDummyModelMessage := false
 	for _, message := range textRequest.Messages {
+
+		if message.Role == "system" {
+			geminiRequest.SystemInstructions = &GeminiChatContent{
+				Parts: []GeminiPart{
+					{
+						Text: message.StringContent(),
+					},
+				},
+			}
+			continue
+		}
 		content := GeminiChatContent{
 			Role: message.Role,
-			Parts: []GeminiPart{
-				{
-					Text: message.StringContent(),
-				},
-			},
+			//Parts: []GeminiPart{
+			//	{
+			//		Text: message.StringContent(),
+			//	},
+			//},
 		}
 		openaiContent := message.ParseContent()
 		var parts []GeminiPart
 		imageNum := 0
 		for _, part := range openaiContent {
-
 			if part.Type == dto.ContentTypeText {
 				parts = append(parts, GeminiPart{
 					Text: part.Text,
 				})
 			} else if part.Type == dto.ContentTypeImageURL {
 				imageNum += 1
-				if imageNum > GeminiVisionMaxImageNum {
-					continue
+
+				if constant.GeminiVisionMaxImageNum != -1 && imageNum > constant.GeminiVisionMaxImageNum {
+					return nil, fmt.Errorf("too many images in the message, max allowed is %d", constant.GeminiVisionMaxImageNum)
 				}
 				// 判断是否是url
 				if strings.HasPrefix(part.ImageUrl.(dto.MessageImageUrl).Url, "http") {
@@ -109,7 +125,7 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest) *GeminiChatReques
 				} else {
 					_, format, base64String, err := service.DecodeBase64ImageData(part.ImageUrl.(dto.MessageImageUrl).Url)
 					if err != nil {
-						continue
+						return nil, fmt.Errorf("decode base64 image data failed: %s", err.Error())
 					}
 					parts = append(parts, GeminiPart{
 						InlineData: &GeminiInlineData{
@@ -127,26 +143,26 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest) *GeminiChatReques
 			content.Role = "model"
 		}
 		// Converting system prompt to prompt from user for the same reason
-		if content.Role == "system" {
-			content.Role = "user"
-			shouldAddDummyModelMessage = true
-		}
+		//if content.Role == "system" {
+		//	content.Role = "user"
+		//	shouldAddDummyModelMessage = true
+		//}
 		geminiRequest.Contents = append(geminiRequest.Contents, content)
-
-		// If a system message is the last message, we need to add a dummy model message to make gemini happy
-		if shouldAddDummyModelMessage {
-			geminiRequest.Contents = append(geminiRequest.Contents, GeminiChatContent{
-				Role: "model",
-				Parts: []GeminiPart{
-					{
-						Text: "Okay",
-					},
-				},
-			})
-			shouldAddDummyModelMessage = false
-		}
+		//
+		//// If a system message is the last message, we need to add a dummy model message to make gemini happy
+		//if shouldAddDummyModelMessage {
+		//	geminiRequest.Contents = append(geminiRequest.Contents, GeminiChatContent{
+		//		Role: "model",
+		//		Parts: []GeminiPart{
+		//			{
+		//				Text: "Okay",
+		//			},
+		//		},
+		//	})
+		//	shouldAddDummyModelMessage = false
+		//}
 	}
-	return &geminiRequest
+	return &geminiRequest, nil
 }

 func (g *GeminiChatResponse) GetResponseText() string {
@@ -205,7 +221,11 @@ func responseGeminiChat2OpenAI(response *GeminiChatResponse) *dto.OpenAITextResp
 				choice.FinishReason = constant.FinishReasonToolCalls
 				choice.Message.ToolCalls = getToolCalls(&candidate)
 			} else {
-				choice.Message.SetStringContent(candidate.Content.Parts[0].Text)
+				var texts []string
+				for _, part := range candidate.Content.Parts {
+					texts = append(texts, part.Text)
+				}
+				choice.Message.SetStringContent(strings.Join(texts, "\n"))
 			}
 		}
 		fullTextResponse.Choices = append(fullTextResponse.Choices, choice)
@@ -217,13 +237,17 @@ func streamResponseGeminiChat2OpenAI(geminiResponse *GeminiChatResponse) *dto.Ch
 	var choice dto.ChatCompletionsStreamResponseChoice
 	//choice.Delta.SetContentString(geminiResponse.GetResponseText())
 	if len(geminiResponse.Candidates) > 0 && len(geminiResponse.Candidates[0].Content.Parts) > 0 {
-		respFirst := geminiResponse.Candidates[0].Content.Parts[0]
-		if respFirst.FunctionCall != nil {
+		respFirstParts := geminiResponse.Candidates[0].Content.Parts
+		if respFirstParts[0].FunctionCall != nil {
 			// function response
 			choice.Delta.ToolCalls = getToolCalls(&geminiResponse.Candidates[0])
 		} else {
 			// text response
-			choice.Delta.SetContentString(respFirst.Text)
+			var texts []string
+			for _, part := range respFirstParts {
+				texts = append(texts, part.Text)
+			}
+			choice.Delta.SetContentString(strings.Join(texts, "\n"))
 		}
 	}
 	var response dto.ChatCompletionsStreamResponse
--- a/relay/channel/openai/relay-openai.go
+++ b/relay/channel/openai/relay-openai.go
@@ -5,9 +5,6 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
-	"github.com/bytedance/gopkg/util/gopool"
-	"github.com/gin-gonic/gin"
-	"github.com/gorilla/websocket"
 	"io"
 	"net/http"
 	"one-api/common"
@@ -19,9 +16,33 @@ import (
 	"strings"
 	"sync"
 	"time"
+
+	"github.com/bytedance/gopkg/util/gopool"
+	"github.com/gin-gonic/gin"
+	"github.com/gorilla/websocket"
 )

+func sendStreamData(c *gin.Context, data string, forceFormat bool) error {
+	if data == "" {
+		return nil
+	}
+
+	if forceFormat {
+		var lastStreamResponse dto.ChatCompletionsStreamResponse
+		if err := json.Unmarshal(common.StringToByteSlice(data), &lastStreamResponse); err != nil {
+			return err
+		}
+		return service.ObjectData(c, lastStreamResponse)
+	}
+	return service.StringData(c, data)
+}
+
 func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	if resp == nil || resp.Body == nil {
+		common.LogError(c, "invalid response or response body")
+		return service.OpenAIErrorWrapper(fmt.Errorf("invalid response"), "invalid_response", http.StatusInternalServerError), nil
+	}
+
 	containStreamUsage := false
 	var responseId string
 	var createAt int64 = 0
@@ -31,6 +52,13 @@ func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 	var responseTextBuilder strings.Builder
 	var usage = &dto.Usage{}
 	var streamItems []string // store stream items
+	var forceFormat bool
+
+	if info.ChannelType == common.ChannelTypeCustom {
+		if forceFmt, ok := info.ChannelSetting["force_format"].(bool); ok {
+			forceFormat = forceFmt
+		}
+	}

 	toolCount := 0
 	scanner := bufio.NewScanner(resp.Body)
@@ -62,7 +90,7 @@ func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 			data = data[6:]
 			if !strings.HasPrefix(data, "[DONE]") {
 				if lastStreamData != "" {
-					err := service.StringData(c, lastStreamData)
+					err := sendStreamData(c, lastStreamData, forceFormat)
 					if err != nil {
 						common.LogError(c, "streaming error: "+err.Error())
 					}
@@ -105,7 +133,7 @@ func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 		}
 	}
 	if shouldSendLastResp {
-		service.StringData(c, lastStreamData)
+		sendStreamData(c, lastStreamData, forceFormat)
 	}

 	// 计算token
@@ -375,6 +403,10 @@ func getTextFromJSON(body []byte) (string, error) {
 }

 func OpenaiRealtimeHandler(c *gin.Context, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.RealtimeUsage) {
+	if info == nil || info.ClientWs == nil || info.TargetWs == nil {
+		return service.OpenAIErrorWrapper(fmt.Errorf("invalid websocket connection"), "invalid_connection", http.StatusBadRequest), nil
+	}
+
 	info.IsStream = true
 	clientConn := info.ClientWs
 	targetConn := info.TargetWs
@@ -390,6 +422,11 @@ func OpenaiRealtimeHandler(c *gin.Context, info *relaycommon.RelayInfo) (*dto.Op
 	sumUsage := &dto.RealtimeUsage{}

 	gopool.Go(func() {
+		defer func() {
+			if r := recover(); r != nil {
+				errChan <- fmt.Errorf("panic in client reader: %v", r)
+			}
+		}()
 		for {
 			select {
 			case <-c.Done():
@@ -445,6 +482,11 @@ func OpenaiRealtimeHandler(c *gin.Context, info *relaycommon.RelayInfo) (*dto.Op
 	})

 	gopool.Go(func() {
+		defer func() {
+			if r := recover(); r != nil {
+				errChan <- fmt.Errorf("panic in target reader: %v", r)
+			}
+		}()
 		for {
 			select {
 			case <-c.Done():
@@ -568,6 +610,10 @@ func OpenaiRealtimeHandler(c *gin.Context, info *relaycommon.RelayInfo) (*dto.Op
 }

 func preConsumeUsage(ctx *gin.Context, info *relaycommon.RelayInfo, usage *dto.RealtimeUsage, totalUsage *dto.RealtimeUsage) error {
+	if usage == nil || totalUsage == nil {
+		return fmt.Errorf("invalid usage pointer")
+	}
+
 	totalUsage.TotalTokens += usage.TotalTokens
 	totalUsage.InputTokens += usage.InputTokens
 	totalUsage.OutputTokens += usage.OutputTokens
--- a/relay/channel/vertex/adaptor.go
+++ b/relay/channel/vertex/adaptor.go
@@ -135,7 +135,10 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 		c.Set("request_model", request.Model)
 		return vertexClaudeReq, nil
 	} else if a.RequestMode == RequestModeGemini {
-		geminiRequest := gemini.CovertGemini2OpenAI(*request)
+		geminiRequest, err := gemini.CovertGemini2OpenAI(*request)
+		if err != nil {
+			return nil, err
+		}
 		c.Set("request_model", request.Model)
 		return geminiRequest, nil
 	} else if a.RequestMode == RequestModeLlama {
--- a/relay/common/relay_info.go
+++ b/relay/common/relay_info.go
@@ -1,13 +1,14 @@
 package common

 import (
-	"github.com/gin-gonic/gin"
-	"github.com/gorilla/websocket"
 	"one-api/common"
 	"one-api/dto"
 	"one-api/relay/constant"
 	"strings"
 	"time"
+
+	"github.com/gin-gonic/gin"
+	"github.com/gorilla/websocket"
 )

 type RelayInfo struct {
@@ -43,6 +44,7 @@ type RelayInfo struct {
 	RealtimeTools        []dto.RealTimeTool
 	IsFirstRequest       bool
 	AudioUsage           bool
+	ChannelSetting       map[string]interface{}
 }

 func GenRelayInfoWs(c *gin.Context, ws *websocket.Conn) *RelayInfo {
@@ -57,6 +59,7 @@ func GenRelayInfoWs(c *gin.Context, ws *websocket.Conn) *RelayInfo {
 func GenRelayInfo(c *gin.Context) *RelayInfo {
 	channelType := c.GetInt("channel_type")
 	channelId := c.GetInt("channel_id")
+	channelSetting := c.GetStringMap("channel_setting")

 	tokenId := c.GetInt("token_id")
 	tokenKey := c.GetString("token_key")
@@ -87,6 +90,7 @@ func GenRelayInfo(c *gin.Context) *RelayInfo {
 		ApiVersion:        c.GetString("api_version"),
 		ApiKey:            strings.TrimPrefix(c.Request.Header.Get("Authorization"), "Bearer "),
 		Organization:      c.GetString("channel_organization"),
+		ChannelSetting:    channelSetting,
 	}
 	if strings.HasPrefix(c.Request.URL.Path, "/pg") {
 		info.IsPlayground = true
--- a/web/src/App.js
+++ b/web/src/App.js
@@ -27,44 +27,15 @@ import Task from "./pages/Task/index.js";
 import Playground from './pages/Playground/Playground.js';
 import OAuth2Callback from "./components/OAuth2Callback.js";
 import { useTranslation } from 'react-i18next';
+import { StatusContext } from './context/Status';
+import { setStatusData } from './helpers/data.js';
+import { API, showError } from './helpers';

 const Home = lazy(() => import('./pages/Home'));
 const Detail = lazy(() => import('./pages/Detail'));
 const About = lazy(() => import('./pages/About'));

 function App() {
-  const [userState, userDispatch] = useContext(UserContext);
-  // const [statusState, statusDispatch] = useContext(StatusContext);
-  const { i18n } = useTranslation();
-
-  const loadUser = () => {
-    let user = localStorage.getItem('user');
-    if (user) {
-      let data = JSON.parse(user);
-      userDispatch({ type: 'login', payload: data });
-    }
-  };
-
-  useEffect(() => {
-    loadUser();
-    let systemName = getSystemName();
-    if (systemName) {
-      document.title = systemName;
-    }
-    let logo = getLogo();
-    if (logo) {
-      let linkElement = document.querySelector("link[rel~='icon']");
-      if (linkElement) {
-        linkElement.href = logo;
-      }
-    }
-    // 从localStorage获取上次使用的语言
-    const savedLang = localStorage.getItem('i18nextLng');
-    if (savedLang) {
-      i18n.changeLanguage(savedLang);
-    }
-  }, [i18n]);
-
  return (
    <>
      <Routes>
--- a/web/src/components/ChannelsTable.js
+++ b/web/src/components/ChannelsTable.js
@@ -249,7 +249,7 @@ const ChannelsTable = () => {
      }
    },
    {
-      title: '优先级',
+      title: t('优先级'),
      dataIndex: 'priority',
      render: (text, record, index) => {
        if (record.children === undefined) {
@@ -276,8 +276,8 @@ const ChannelsTable = () => {
              keepFocus={true}
              onBlur={(e) => {
                Modal.warning({
-                  title: '修改子渠道优先级',
-                  content: '确定要修改所有子渠道优先级为 ' + e.target.value + ' 吗？',
+                  title: t('修改子渠道优先级'),
+                  content: t('确定要修改所有子渠道优先级为 ') + e.target.value + t(' 吗？'),
                  onOk: () => {
                    if (e.target.value === '') {
                      return;
@@ -298,7 +298,7 @@ const ChannelsTable = () => {
      }
    },
    {
-      title: '权重',
+      title: t('权重'),
      dataIndex: 'weight',
      render: (text, record, index) => {
        if (record.children === undefined) {
@@ -325,8 +325,8 @@ const ChannelsTable = () => {
              keepFocus={true}
              onBlur={(e) => {
                Modal.warning({
-                  title: '修改子渠道权重',
-                  content: '确定要修改所有子渠道权重为 ' + e.target.value + ' 吗？',
+                  title: t('修改子渠道权重'),
+                  content: t('确定要修改所有子渠道权重为 ') + e.target.value + t(' 吗？'),
                  onOk: () => {
                    if (e.target.value === '') {
                      return;
@@ -646,25 +646,25 @@ const ChannelsTable = () => {

  const copySelectedChannel = async (record) => {
    const channelToCopy = record
-    channelToCopy.name += '_复制';
+    channelToCopy.name += t('_复制');
    channelToCopy.created_time = null;
    channelToCopy.balance = 0;
    channelToCopy.used_quota = 0;
    if (!channelToCopy) {
-      showError('渠道未找到，请刷新页面后重试。');
+      showError(t('渠道未找到，请刷新页面后重试。'));
      return;
    }
    try {
      const newChannel = { ...channelToCopy, id: undefined };
      const response = await API.post('/api/channel/', newChannel);
      if (response.data.success) {
-        showSuccess('渠道复制成功');
+        showSuccess(t('渠道复制成功'));
        await refresh();
      } else {
        showError(response.data.message);
      }
    } catch (error) {
-      showError('渠道复制失败: ' + error.message);
+      showError(t('渠道复制失败: ') + error.message);
    }
  };

@@ -723,7 +723,7 @@ const ChannelsTable = () => {
    }
    const { success, message } = res.data;
    if (success) {
-      showSuccess('操作成功完成！');
+      showSuccess(t('操作成功完成！'));
      let channel = res.data.data;
      let newChannels = [...channels];
      if (action === 'delete') {
--- a/web/src/components/HeaderBar.js
+++ b/web/src/components/HeaderBar.js
@@ -14,6 +14,7 @@ import {
  IconHelpCircle,
  IconHome,
  IconHomeStroked, IconIndentLeft,
+  IconComment,
  IconKey, IconMenu,
  IconNoteMoneyStroked,
  IconPriceTag,
@@ -25,24 +26,6 @@ import { stringToColor } from '../helpers/render';
 import Text from '@douyinfe/semi-ui/lib/es/typography/text';
 import { StyleContext } from '../context/Style/index.js';

-// HeaderBar Buttons
-let headerButtons = [
-  {
-    text: '关于',
-    itemKey: 'about',
-    to: '/about',
-    icon: <IconHelpCircle />,
-  },
-];
-
-if (localStorage.getItem('chat_link')) {
-  headerButtons.splice(1, 0, {
-    name: '聊天',
-    to: '/chat',
-    icon: 'comments',
-  });
-}
-
 const HeaderBar = () => {
  const { t, i18n } = useTranslation();
  const [userState, userDispatch] = useContext(UserContext);
@@ -105,16 +88,27 @@ const HeaderBar = () => {
  useEffect(() => {
    if (theme === 'dark') {
      document.body.setAttribute('theme-mode', 'dark');
+    } else {
+      document.body.removeAttribute('theme-mode');
+    }
+    // 发送当前主题模式给子页面
+    const iframe = document.querySelector('iframe');
+    if (iframe) {
+      iframe.contentWindow.postMessage({ themeMode: theme }, '*');
    }

    if (isNewYear) {
      console.log('Happy New Year!');
    }
-  }, []);
+  }, [theme]);

  useEffect(() => {
    const handleLanguageChanged = (lng) => {
      setCurrentLang(lng);
+      const iframe = document.querySelector('iframe');
+      if (iframe) {
+        iframe.contentWindow.postMessage({ lang: lng }, '*');
+      }
    };

    i18n.on('languageChanged', handleLanguageChanged);
@@ -143,6 +137,7 @@ const HeaderBar = () => {
                pricing: '/pricing',
                detail: '/detail',
                home: '/',
+                chat: '/chat',
              };
              return (
                <div onClick={(e) => {
@@ -223,13 +218,13 @@ const HeaderBar = () => {
                  position='bottomRight'
                  render={
                    <Dropdown.Menu>
-                      <Dropdown.Item 
+                      <Dropdown.Item
                        onClick={() => handleLanguageChange('zh')}
                        type={currentLang === 'zh' ? 'primary' : 'tertiary'}
                      >
                        中文
                      </Dropdown.Item>
-                      <Dropdown.Item 
+                      <Dropdown.Item
                        onClick={() => handleLanguageChange('en')}
                        type={currentLang === 'en' ? 'primary' : 'tertiary'}
                      >
@@ -238,8 +233,8 @@ const HeaderBar = () => {
                    </Dropdown.Menu>
                  }
                >
-                  <Nav.Item 
-                    itemKey={'language'} 
+                  <Nav.Item
+                    itemKey={'language'}
                    icon={<IconLanguage />}
                  />
                </Dropdown>
--- a/web/src/components/MjLogsTable.js
+++ b/web/src/components/MjLogsTable.js
@@ -46,7 +46,6 @@ const LogsTable = () => {
  const [isModalOpen, setIsModalOpen] = useState(false);
  const [modalContent, setModalContent] = useState('');
  function renderType(type) {
-    const { t } = useTranslation();
    
    switch (type) {
      case 'IMAGINE':
@@ -155,7 +154,6 @@ const LogsTable = () => {
  }
  
  function renderCode(code) {
-    const { t } = useTranslation();
    
    switch (code) {
      case 1:
@@ -192,7 +190,6 @@ const LogsTable = () => {
  }
  
  function renderStatus(type) {
-    const { t } = useTranslation();
    
    switch (type) {
      case 'SUCCESS':
@@ -254,7 +251,6 @@ const LogsTable = () => {
  };
  // 修改renderDuration函数以包含颜色逻辑
  function renderDuration(submit_time, finishTime) {
-    const { t } = useTranslation();
    
    if (!submit_time || !finishTime) return 'N/A';

--- a/web/src/components/OperationSetting.js
+++ b/web/src/components/OperationSetting.js
@@ -1,5 +1,5 @@
 import React, { useEffect, useState } from 'react';
-import { Card, Spin } from '@douyinfe/semi-ui';
+import { Card, Spin, Tabs } from '@douyinfe/semi-ui';
 import SettingsGeneral from '../pages/Setting/Operation/SettingsGeneral.js';
 import SettingsDrawing from '../pages/Setting/Operation/SettingsDrawing.js';
 import SettingsSensitiveWords from '../pages/Setting/Operation/SettingsSensitiveWords.js';
@@ -8,11 +8,17 @@ import SettingsDataDashboard from '../pages/Setting/Operation/SettingsDataDashbo
 import SettingsMonitoring from '../pages/Setting/Operation/SettingsMonitoring.js';
 import SettingsCreditLimit from '../pages/Setting/Operation/SettingsCreditLimit.js';
 import SettingsMagnification from '../pages/Setting/Operation/SettingsMagnification.js';
+import ModelSettingsVisualEditor from '../pages/Setting/Operation/ModelSettingsVisualEditor.js';
+import GroupRatioSettings from '../pages/Setting/Operation/GroupRatioSettings.js';
+import ModelRatioSettings from '../pages/Setting/Operation/ModelRatioSettings.js';
+

 import { API, showError, showSuccess } from '../helpers';
 import SettingsChats from '../pages/Setting/Operation/SettingsChats.js';
+import { useTranslation } from 'react-i18next';

 const OperationSetting = () => {
+  const { t } = useTranslation();
  let [inputs, setInputs] = useState({
    QuotaForNewUser: 0,
    QuotaForInviter: 0,
@@ -137,9 +143,20 @@ const OperationSetting = () => {
        <Card style={{ marginTop: '10px' }}>
          <SettingsChats options={inputs} refresh={onRefresh} />
        </Card>
-        {/* 倍率设置 */}
+        {/* 分组倍率设置 */}
        <Card style={{ marginTop: '10px' }}>
-          <SettingsMagnification options={inputs} refresh={onRefresh} />
+          <GroupRatioSettings options={inputs} refresh={onRefresh} />
+        </Card>
+        {/* 合并模型倍率设置和可视化倍率设置 */}
+        <Card style={{ marginTop: '10px' }}>
+          <Tabs type="line">
+            <Tabs.TabPane tab={t('模型倍率设置')} itemKey="model">
+              <ModelRatioSettings options={inputs} refresh={onRefresh} />
+            </Tabs.TabPane>
+            <Tabs.TabPane tab={t('可视化倍率设置')} itemKey="visual">
+              <ModelSettingsVisualEditor options={inputs} refresh={onRefresh} />
+            </Tabs.TabPane>
+          </Tabs>
        </Card>
      </Spin>
    </>
--- a/web/src/components/PageLayout.js
+++ b/web/src/components/PageLayout.js
@@ -4,15 +4,65 @@ import SiderBar from './SiderBar.js';
 import App from '../App.js';
 import FooterBar from './Footer.js';
 import { ToastContainer } from 'react-toastify';
-import React, { useContext } from 'react';
+import React, { useContext, useEffect } from 'react';
 import { StyleContext } from '../context/Style/index.js';
 import { useTranslation } from 'react-i18next';
+import { API, getLogo, getSystemName, showError } from '../helpers/index.js';
+import { setStatusData } from '../helpers/data.js';
+import { UserContext } from '../context/User/index.js';
+import { StatusContext } from '../context/Status/index.js';
 const { Sider, Content, Header, Footer } = Layout;


 const PageLayout = () => {
+  const [userState, userDispatch] = useContext(UserContext);
+  const [statusState, statusDispatch] = useContext(StatusContext);
  const [styleState, styleDispatch] = useContext(StyleContext);
-  const { t } = useTranslation();
+  const { i18n } = useTranslation();
+
+  const loadUser = () => {
+    let user = localStorage.getItem('user');
+    if (user) {
+      let data = JSON.parse(user);
+      userDispatch({ type: 'login', payload: data });
+    }
+  };
+
+  const loadStatus = async () => {
+    try {
+      const res = await API.get('/api/status');
+      const { success, data } = res.data;
+      if (success) {
+        statusDispatch({ type: 'set', payload: data });
+        setStatusData(data);
+      } else {
+        showError('Unable to connect to server');
+      }
+    } catch (error) {
+      showError('Failed to load status');
+    }
+  };
+
+  useEffect(() => {
+    loadUser();
+    loadStatus().catch(console.error);
+    let systemName = getSystemName();
+    if (systemName) {
+      document.title = systemName;
+    }
+    let logo = getLogo();
+    if (logo) {
+      let linkElement = document.querySelector("link[rel~='icon']");
+      if (linkElement) {
+        linkElement.href = logo;
+      }
+    }
+    // 从localStorage获取上次使用的语言
+    const savedLang = localStorage.getItem('i18nextLng');
+    if (savedLang) {
+      i18n.changeLanguage(savedLang);
+    }
+  }, [i18n]);

  return (
    <Layout style={{ height: '100vh', display: 'flex', flexDirection: 'column' }}>
--- a/web/src/components/PersonalSetting.js
+++ b/web/src/components/PersonalSetting.js
@@ -25,6 +25,7 @@ import {
    Space,
    Tag,
    Typography,
+    Collapsible,
 } from '@douyinfe/semi-ui';
 import {
    getQuotaPerUnit,
@@ -64,6 +65,8 @@ const PersonalSetting = () => {
    const [models, setModels] = useState([]);
    const [openTransfer, setOpenTransfer] = useState(false);
    const [transferAmount, setTransferAmount] = useState(0);
+    const [isModelsExpanded, setIsModelsExpanded] = useState(false);
+    const MODELS_DISPLAY_COUNT = 10;  // 默认显示的模型数量

    useEffect(() => {
        // let user = localStorage.getItem('user');
@@ -289,10 +292,10 @@ const PersonalSetting = () => {

    const copyText = async (text) => {
        if (await copy(text)) {
-            showSuccess('已复制：' + text);
+            showSuccess(t('已复制：') + text);
        } else {
            // setSearchKeyword(text);
-            Modal.error({title: '无法复制到剪贴板，请手动复制', content: text});
+            Modal.error({title: t('无法复制到剪贴板，请手动复制'), content: text});
        }
    };

@@ -364,6 +367,80 @@ const PersonalSetting = () => {
                                    </Space>
                                </>
                            }
+                            footer={
+                            <>
+                                <div style={{ display: 'flex', alignItems: 'center', gap: 8 }}>
+                                    <Typography.Title heading={6}>{t('可用模型')}</Typography.Title>
+                                </div>
+                                <div style={{marginTop: 10}}>
+                                    {models.length <= MODELS_DISPLAY_COUNT ? (
+                                        <Space wrap>
+                                            {models.map((model) => (
+                                                <Tag
+                                                    key={model}
+                                                    color='cyan'
+                                                    onClick={() => {
+                                                        copyText(model);
+                                                    }}
+                                                >
+                                                    {model}
+                                                </Tag>
+                                            ))}
+                                        </Space>
+                                    ) : (
+                                        <>
+                                            <Collapsible isOpen={isModelsExpanded}>
+                                                <Space wrap>
+                                                    {models.map((model) => (
+                                                        <Tag
+                                                            key={model}
+                                                            color='cyan'
+                                                            onClick={() => {
+                                                                copyText(model);
+                                                            }}
+                                                        >
+                                                            {model}
+                                                        </Tag>
+                                                    ))}
+                                                    <Tag 
+                                                        color='blue' 
+                                                        type="light"
+                                                        style={{ cursor: 'pointer' }}
+                                                        onClick={() => setIsModelsExpanded(false)}
+                                                    >
+                                                        {t('收起')}
+                                                    </Tag>
+                                                </Space>
+                                            </Collapsible>
+                                            {!isModelsExpanded && (
+                                                <Space wrap>
+                                                    {models.slice(0, MODELS_DISPLAY_COUNT).map((model) => (
+                                                        <Tag
+                                                            key={model}
+                                                            color='cyan'
+                                                            onClick={() => {
+                                                                copyText(model);
+                                                            }}
+                                                        >
+                                                            {model}
+                                                        </Tag>
+                                                    ))}
+                                                    <Tag 
+                                                        color='blue'
+                                                        type="light"
+                                                        style={{ cursor: 'pointer' }}
+                                                        onClick={() => setIsModelsExpanded(true)}
+                                                    >
+                                                        {t('更多')} {models.length - MODELS_DISPLAY_COUNT} {t('个模型')}
+                                                    </Tag>
+                                                </Space>
+                                            )}
+                                        </>
+                                    )}
+                                </div>
+                            </>
+
+                            }
                        >
                            <Descriptions row>
                                <Descriptions.Item itemKey={t('当前余额')}>
--- a/web/src/components/SiderBar.js
+++ b/web/src/components/SiderBar.js
@@ -168,31 +168,13 @@ const SiderBar = () => {
    ],
  );

-  const loadStatus = async () => {
-    const res = await API.get('/api/status');
-    if (res === undefined) {
-      return;
-    }
-    const { success, data } = res.data;
-    if (success) {
-      statusDispatch({ type: 'set', payload: data });
-      setStatusData(data);
-    } else {
-      showError('无法正常连接至服务器！');
-    }
-  };
-
  useEffect(() => {
-    loadStatus().then(() => {
-      setIsCollapsed(
-          localStorage.getItem('default_collapse_sidebar') === 'true',
-      );
-    });
    let localKey = window.location.pathname.split('/')[1];
    if (localKey === '') {
      localKey = 'home';
    }
    setSelectedKeys([localKey]);
+    
    let chatLink = localStorage.getItem('chat_link');
    if (!chatLink) {
        let chats = localStorage.getItem('chats');
@@ -220,6 +202,8 @@ const SiderBar = () => {
            }
        }
    }
+    
+    setIsCollapsed(localStorage.getItem('default_collapse_sidebar') === 'true');
  }, []);

  return (
--- a/web/src/i18n/locales/en.json
+++ b/web/src/i18n/locales/en.json
@@ -709,7 +709,7 @@
  "密码修改成功！": "Password changed successfully!",
  "划转金额最低为": "The minimum transfer amount is",
  "请输入邮箱！": "Please enter your email!",
-  "验证码发送成功，请检查<EFBFBD><EFBFBD><EFBFBD>箱！": "The verification code was sent successfully, please check your email!",
+  "验证码发送成功，请检查邮箱！": "The verification code was sent successfully, please check your email!",
  "请输入邮箱验证码！": "Please enter the email verification code!",
  "请输入要划转的数量": "Please enter the amount to be transferred",
  "当前余额": "Current balance",
@@ -720,7 +720,7 @@
  "修改绑定": "Modify binding",
  "绑定邮箱": "Bind email",
  "确认新密码": "Confirm new password",
-  "历史消耗": "Historical consumption",
+  "历史消耗": "Consumption",
  "查看": "Check",
  "修改密码": "Change password",
  "删除个人账户": "Delete personal account",
@@ -797,7 +797,7 @@
  "管理员未开启Stripe在线充值！": "The administrator has not enabled Stripe online recharge!",
  "当前充值1美金=": "Current recharge = 1 USD =",
  "请选择充值方式！": "Please choose a recharge method!",
-  "元": "RMB/CNY",
+  "元": "CNY",
  "充值记录": "Recharge record",
  "返利记录": "Rebate record",
  "确定要充值 $": "Confirm to top up $",
@@ -827,8 +827,8 @@
  "模型消耗分布": "Model consumption distribution",
  "模型调用次数占比": "Proportion of model calls",
  "用户消耗分布": "User consumption distribution",
-  "时间粒度": "time granularity",
-  "天": "sky",
+  "时间粒度": "Time granularity",
+  "天": "day",
  "模型概览": "Model overview",
  "用户概览": "User overview",
  "正在策划中": "Under planning",
@@ -963,7 +963,7 @@
  "请输入星火大模型版本，注意是接口地址中的版本号，例如：v2[1]": "Please enter the Spark model version, note that it is the version number in the interface address, for example: v2.1",
  "等待中": "Waiting",
  "所有各厂聊天模型请统一使用OpenAI方式请求，支持OpenAI官方库": "Please use the OpenAI method to request all chat models from each factory, and support the OpenAI official library.",
-  "实付金额：": "Actual payment amount:",
+  "实付金额：": "Actual payment amount: ",
  "金额": "Amount",
  "充值金额": "Recharge amount",
  "易支付 实付金额：": "Easy Pay Actual payment amount:",
@@ -984,7 +984,7 @@
  "保存失败，请重试": "Save failed, please try again",
  "没有可用的使用信息": "No usage information available",
  "使用详情": "Usage details",
-  "收起": "close",
+  "收起": "Collapse",
  "计费详情": "Billing details",
  "提示Token": "Tip Token",
  "补全Token": "Complete Token",
@@ -1161,7 +1161,7 @@
  "默认折叠侧边栏": "Default collapse sidebar",
  "聊天链接功能已经弃用，请使用下方聊天设置功能": "Chat link function has been deprecated, please use the chat settings below",
  "你似乎并没有修改什么": "You seem to have not modified anything",
-  "令牌聊天设置": "Token chat settings",
+  "令牌聊天设置": "Chat settings",
  "必须将上方聊天链接全部设置为空，才能使用下方聊天设置功能": "Must set all chat links above to empty to use the chat settings below",
  "链接中的{key}将自动替换为sk-xxxx，{address}将自动替换为系统设置的服务器地址，末尾不带/和/v1": "The {key} in the link will be automatically replaced with sk-xxxx, the {address} will be automatically replaced with the server address in system settings, and the end will not have / and /v1",
  "聊天配置": "Chat configuration",
@@ -1209,5 +1209,30 @@
  "首页内容已更新": "Home page content updated",
  "关于已更新": "About updated",
  "模型测试": "model test",
-  "当前未开启Midjourney回调，部分项目可能无法获得绘图结果，可在运营设置中开启。": "Current Midjourney callback is not enabled, some projects may not be able to obtain drawing results, which can be enabled in the operation settings."
+  "当前未开启Midjourney回调，部分项目可能无法获得绘图结果，可在运营设置中开启。": "Current Midjourney callback is not enabled, some projects may not be able to obtain drawing results, which can be enabled in the operation settings.",
+  "Telegram 身份验证": "Telegram authentication",
+  "Linux DO 身份验证": "Linux DO authentication",
+  "协议": "License",
+  "修改子渠道权重": "Modify sub-channel weight",
+  "确定要修改所有子渠道权重为 ": "Confirm to modify all sub-channel weights to ",
+  " 吗？": "?",
+  "修改子渠道优先级": "Modify sub-channel priority",
+  "确定要修改所有子渠道优先级为 ": "Confirm to modify all sub-channel priorities to ",
+  "分组设置": "Group settings",
+  "用户可选分组": "User selectable groups",
+  "保存分组倍率设置": "Save group ratio settings",
+  "模型倍率设置": "Model ratio settings",
+  "可视化倍率设置": "Visual model ratio settings",
+  "确定重置模型倍率吗？": "Confirm to reset model ratio?",
+  "模型固定价格": "Model price per call",
+  "模型补全倍率（仅对自定义模型有效）": "Model completion ratio (only effective for custom models)",
+  "保存模型倍率设置": "Save model ratio settings",
+  "重置模型倍率": "Reset model ratio",
+  "一次调用消耗多少刀，优先级大于模型倍率": "How much USD one call costs, priority over model ratio",
+  "仅对自定义模型有效": "Only effective for custom models",
+  "添加模型": "Add model",
+  "应用更改": "Apply changes",
+  "更多": "Expand more",
+  "个模型": "models",
+  "可用模型": "Available models"
 }
--- a/web/src/pages/Channel/EditChannel.js
+++ b/web/src/pages/Channel/EditChannel.js
@@ -222,7 +222,7 @@ const EditChannel = (props) => {
              'Authorization': `Bearer ${key}`
            }
          });
-          if (res.data && res.data?.success) {
+          if (res.data) {
            models.push(...res.data.data.map((model) => model.id));
          } else {
            err = true;
@@ -964,6 +964,42 @@ const EditChannel = (props) => {
            value={inputs.weight}
            autoComplete="new-password"
          />
+          {inputs.type === 8 && (
+          <>
+            <div style={{ marginTop: 10 }}>
+              <Typography.Text strong>
+                {t('渠道额外设置')}：
+              </Typography.Text>
+            </div>
+            <TextArea
+              placeholder={t('此项可选，用于配置渠道特定设置，为一个 JSON 字符串，例如：') + '\n{\n  "force_format": true\n}'}
+              name="setting"
+              onChange={(value) => {
+                handleInputChange('setting', value);
+              }}
+              autosize
+              value={inputs.setting}
+              autoComplete="new-password"
+            />
+            <Typography.Text
+              style={{
+                color: 'rgba(var(--semi-blue-5), 1)', 
+                userSelect: 'none',
+                cursor: 'pointer'
+              }}
+              onClick={() => {
+                handleInputChange(
+                  'setting',
+                  JSON.stringify({
+                    force_format: true
+                  }, null, 2)
+                );
+              }}
+            >
+              {t('填入模板')}
+              </Typography.Text>
+            </>
+          )}  
        </Spin>
      </SideSheet>
    </>
--- a/web/src/pages/Home/index.js
+++ b/web/src/pages/Home/index.js
@@ -4,8 +4,10 @@ import { API, showError, showNotice, timestamp2string } from '../../helpers';
 import { StatusContext } from '../../context/Status';
 import { marked } from 'marked';
 import { StyleContext } from '../../context/Style/index.js';
+import { useTranslation } from 'react-i18next';

 const Home = () => {
+  const { t, i18n } = useTranslation();
  const [statusState] = useContext(StatusContext);
  const [homePageContentLoaded, setHomePageContentLoaded] = useState(false);
  const [homePageContent, setHomePageContent] = useState('');
@@ -37,6 +39,20 @@ const Home = () => {
      }
      setHomePageContent(content);
      localStorage.setItem('home_page_content', content);
+
+        // 如果内容是 URL，则发送主题模式
+        if (data.startsWith('https://')) {
+            const iframe = document.querySelector('iframe');
+            if (iframe) {
+                const theme = localStorage.getItem('theme-mode') || 'light';
+                // 测试是否正确传递theme-mode给iframe
+                // console.log('Sending theme-mode to iframe:', theme); 
+                iframe.onload = () => {
+                    iframe.contentWindow.postMessage({ themeMode: theme }, '*');
+                    iframe.contentWindow.postMessage({ lang: i18n.language }, '*');
+                };
+            }
+        }
    } else {
      showError(message);
      setHomePageContent('加载首页内容失败...');
@@ -52,7 +68,8 @@ const Home = () => {
  useEffect(() => {
    displayNotice().then();
    displayHomePageContent().then();
-  }, []);
+  });
+
  return (
    <>
      {homePageContentLoaded && homePageContent === '' ? (
@@ -60,13 +77,13 @@ const Home = () => {
          <Card
            bordered={false}
            headerLine={false}
-            title='系统状况'
+            title={t('系统状况')}
            bodyStyle={{ padding: '10px 20px' }}
          >
            <Row gutter={16}>
              <Col span={12}>
                <Card
-                  title='系统信息'
+                  title={t('系统信息')}
                  headerExtraContent={
                    <span
                      style={{
@@ -74,19 +91,19 @@ const Home = () => {
                        color: 'var(--semi-color-text-1)',
                      }}
                    >
-                      系统信息总览
+                      {t('系统信息总览')}
                    </span>
                  }
                >
-                  <p>名称：{statusState?.status?.system_name}</p>
+                  <p>{t('名称')}：{statusState?.status?.system_name}</p>
                  <p>
-                    版本：
+                    {t('版本')}：
                    {statusState?.status?.version
                      ? statusState?.status?.version
                      : 'unknown'}
                  </p>
                  <p>
-                    源码：
+                    {t('源码')}：
                    <a
                      href='https://github.com/Calcium-Ion/new-api'
                      target='_blank'
@@ -96,7 +113,7 @@ const Home = () => {
                    </a>
                  </p>
                  <p>
-                    协议：
+                    {t('协议')}：
                    <a
                      href='https://www.apache.org/licenses/LICENSE-2.0'
                      target='_blank'
@@ -105,12 +122,12 @@ const Home = () => {
                      Apache-2.0 License
                    </a>
                  </p>
-                  <p>启动时间：{getStartTimeString()}</p>
+                  <p>{t('启动时间')}：{getStartTimeString()}</p>
                </Card>
              </Col>
              <Col span={12}>
                <Card
-                  title='系统配置'
+                  title={t('系统配置')}
                  headerExtraContent={
                    <span
                      style={{
@@ -118,45 +135,45 @@ const Home = () => {
                        color: 'var(--semi-color-text-1)',
                      }}
                    >
-                      系统配置总览
+                      {t('系统配置总览')}
                    </span>
                  }
                >
                  <p>
-                    邮箱验证：
+                    {t('邮箱验证')}：
                    {statusState?.status?.email_verification === true
-                      ? '已启用'
-                      : '未启用'}
+                      ? t('已启用')
+                      : t('未启用')}
                  </p>
                  <p>
-                    GitHub 身份验证：
+                    {t('GitHub 身份验证')}：
                    {statusState?.status?.github_oauth === true
-                      ? '已启用'
-                      : '未启用'}
+                      ? t('已启用')
+                      : t('未启用')}
                  </p>
                  <p>
-                    微信身份验证：
+                    {t('微信身份验证')}：
                    {statusState?.status?.wechat_login === true
-                      ? '已启用'
-                      : '未启用'}
+                      ? t('已启用')
+                      : t('未启用')}
                  </p>
                  <p>
-                    Turnstile 用户校验：
+                    {t('Turnstile 用户校验')}：
                    {statusState?.status?.turnstile_check === true
-                      ? '已启用'
-                      : '未启用'}
+                      ? t('已启用')
+                      : t('未启用')}
                  </p>
                  <p>
-                    Telegram 身份验证：
+                    {t('Telegram 身份验证')}：
                    {statusState?.status?.telegram_oauth === true
-                      ? '已启用'
-                      : '未启用'}
+                      ? t('已启用')
+                      : t('未启用')}
                  </p>
                  <p>
-                    Linux DO 身份验证：
+                    {t('Linux DO 身份验证')}：
                    {statusState?.status?.linuxdo_oauth === true
-                      ? '已启用'
-                      : '未启用'}
+                      ? t('已启用')
+                      : t('未启用')}
                  </p>
                </Card>
              </Col>
--- a/web/src/pages/Playground/Playground.js
+++ b/web/src/pages/Playground/Playground.js
@@ -97,32 +97,29 @@ const Playground = () => {
    let res = await API.get(`/api/user/self/groups`);
    const { success, message, data } = res.data;
    if (success) {
-      // return data is a map, key is group name, value is group description
-      // label is group description, value is group name
      let localGroupOptions = Object.keys(data).map((group) => ({
        label: data[group],
        value: group,
      }));
-      // handleInputChange('group', localGroupOptions[0].value);

-      if (localGroupOptions.length > 0) {
-        // set user group at first
-        if (userState.user && userState.user.group) {
-          let userGroup = userState.user.group;
-          // Find and move user's group to the front
+      if (localGroupOptions.length === 0) {
+        localGroupOptions = [{
+          label: t('用户分组'),
+          value: '',
+        }];
+      } else {
+        const localUser = JSON.parse(localStorage.getItem('user'));
+        const userGroup = (userState.user && userState.user.group) || (localUser && localUser.group);
+        
+        if (userGroup) {
          const userGroupIndex = localGroupOptions.findIndex(g => g.value === userGroup);
          if (userGroupIndex > -1) {
            const userGroupOption = localGroupOptions.splice(userGroupIndex, 1)[0];
            localGroupOptions.unshift(userGroupOption);
          }
        }
-      } else {
-        localGroupOptions = [{
-          label: t('用户分组'),
-          value: '',
-        }];
-        setGroups(localGroupOptions);
      }
+
      setGroups(localGroupOptions);
      handleInputChange('group', localGroupOptions[0].value);
    } else {
--- a/web/src/pages/Redemption/EditRedemption.js
+++ b/web/src/pages/Redemption/EditRedemption.js
@@ -71,7 +71,7 @@ const EditRedemption = (props) => {
    let name = inputs.name;
    if (!isEdit && inputs.name === '') {
      // set default name
-      name = t('新建兑换码') + ' ' + renderQuota(quota);
+      name = renderQuota(quota);
    }
    setLoading(true);
    let localInputs = inputs;
--- a/web/src/pages/Setting/Operation/GroupRatioSettings.js
+++ b/web/src/pages/Setting/Operation/GroupRatioSettings.js
@@ -0,0 +1,131 @@
+import React, { useEffect, useState, useRef } from 'react';
+import { Button, Col, Form, Row, Spin } from '@douyinfe/semi-ui';
+import {
+  compareObjects,
+  API,
+  showError,
+  showSuccess,
+  showWarning,
+  verifyJSON,
+} from '../../../helpers';
+import { useTranslation } from 'react-i18next';
+
+export default function GroupRatioSettings(props) {
+  const { t } = useTranslation();
+  const [loading, setLoading] = useState(false);
+  const [inputs, setInputs] = useState({
+    GroupRatio: '',
+    UserUsableGroups: ''
+  });
+  const refForm = useRef();
+  const [inputsRow, setInputsRow] = useState(inputs);
+
+  async function onSubmit() {
+    try {
+      await refForm.current.validate().then(() => {
+        const updateArray = compareObjects(inputs, inputsRow);
+        if (!updateArray.length) return showWarning(t('你似乎并没有修改什么'));
+        
+        const requestQueue = updateArray.map((item) => {
+          const value = typeof inputs[item.key] === 'boolean' 
+            ? String(inputs[item.key]) 
+            : inputs[item.key];
+          return API.put('/api/option/', { key: item.key, value });
+        });
+
+        setLoading(true);
+        Promise.all(requestQueue)
+          .then((res) => {
+            if (res.includes(undefined)) {
+              return showError(requestQueue.length > 1 ? t('部分保存失败，请重试') : t('保存失败'));
+            }
+            
+            for (let i = 0; i < res.length; i++) {
+              if (!res[i].data.success) {
+                return showError(res[i].data.message);
+              }
+            }
+            
+            showSuccess(t('保存成功'));
+            props.refresh();
+          })
+          .catch(error => {
+            console.error('Unexpected error:', error);
+            showError(t('保存失败，请重试'));
+          })
+          .finally(() => {
+            setLoading(false);
+          });
+      }).catch(() => {
+        showError(t('请检查输入'));
+      });
+    } catch (error) {
+      showError(t('请检查输入'));
+      console.error(error);
+    }
+  }
+
+  useEffect(() => {
+    const currentInputs = {};
+    for (let key in props.options) {
+      if (Object.keys(inputs).includes(key)) {
+        currentInputs[key] = props.options[key];
+      }
+    }
+    setInputs(currentInputs);
+    setInputsRow(structuredClone(currentInputs));
+    refForm.current.setValues(currentInputs);
+  }, [props.options]);
+
+  return (
+    <Spin spinning={loading}>
+      <Form
+        values={inputs}
+        getFormApi={(formAPI) => (refForm.current = formAPI)}
+        style={{ marginBottom: 15 }}
+      >
+        <Form.Section text={t('分组设置')}>
+          <Row gutter={16}>
+            <Col span={16}>
+              <Form.TextArea
+                label={t('分组倍率')}
+                placeholder={t('为一个 JSON 文本，键为分组名称，值为倍率')}
+                field={'GroupRatio'}
+                autosize={{ minRows: 6, maxRows: 12 }}
+                trigger='blur'
+                stopValidateWithError
+                rules={[
+                  {
+                    validator: (rule, value) => verifyJSON(value),
+                    message: t('不是合法的 JSON 字符串')
+                  }
+                ]}
+                onChange={(value) => setInputs({ ...inputs, GroupRatio: value })}
+              />
+            </Col>
+          </Row>
+          <Row gutter={16}>
+            <Col span={16}>
+              <Form.TextArea
+                label={t('用户可选分组')}
+                placeholder={t('为一个 JSON 文本，键为分组名称，值为分组描述')}
+                field={'UserUsableGroups'}
+                autosize={{ minRows: 6, maxRows: 12 }}
+                trigger='blur'
+                stopValidateWithError
+                rules={[
+                  {
+                    validator: (rule, value) => verifyJSON(value),
+                    message: t('不是合法的 JSON 字符串')
+                  }
+                ]}
+                onChange={(value) => setInputs({ ...inputs, UserUsableGroups: value })}
+              />
+            </Col>
+          </Row>
+        </Form.Section>
+      </Form>
+      <Button onClick={onSubmit}>{t('保存分组倍率设置')}</Button>
+    </Spin>
+  );
+} 
--- a/web/src/pages/Setting/Operation/ModelRatioSettings.js
+++ b/web/src/pages/Setting/Operation/ModelRatioSettings.js
@@ -0,0 +1,178 @@
+import React, { useEffect, useState, useRef } from 'react';
+import { Button, Col, Form, Popconfirm, Row, Space, Spin } from '@douyinfe/semi-ui';
+import {
+  compareObjects,
+  API,
+  showError,
+  showSuccess,
+  showWarning,
+  verifyJSON,
+} from '../../../helpers';
+import { useTranslation } from 'react-i18next';
+
+export default function ModelRatioSettings(props) {
+  const [loading, setLoading] = useState(false);
+  const [inputs, setInputs] = useState({
+    ModelPrice: '',
+    ModelRatio: '',
+    CompletionRatio: '',
+  });
+  const refForm = useRef();
+  const [inputsRow, setInputsRow] = useState(inputs);
+  const { t } = useTranslation();
+
+  async function onSubmit() {
+    try {
+      await refForm.current.validate().then(() => {
+        const updateArray = compareObjects(inputs, inputsRow);
+        if (!updateArray.length) return showWarning(t('你似乎并没有修改什么'));
+        
+        const requestQueue = updateArray.map((item) => {
+          const value = typeof inputs[item.key] === 'boolean' 
+            ? String(inputs[item.key]) 
+            : inputs[item.key];
+          return API.put('/api/option/', { key: item.key, value });
+        });
+
+        setLoading(true);
+        Promise.all(requestQueue)
+          .then((res) => {
+            if (res.includes(undefined)) {
+              return showError(requestQueue.length > 1 ? t('部分保存失败，请重试') : t('保存失败'));
+            }
+            
+            for (let i = 0; i < res.length; i++) {
+              if (!res[i].data.success) {
+                return showError(res[i].data.message);
+              }
+            }
+            
+            showSuccess(t('保存成功'));
+            props.refresh();
+          })
+          .catch(error => {
+            console.error('Unexpected error:', error);
+            showError(t('保存失败，请重试'));
+          })
+          .finally(() => {
+            setLoading(false);
+          });
+      }).catch(() => {
+        showError(t('请检查输入'));
+      });
+    } catch (error) {
+      showError(t('请检查输入'));
+      console.error(error);
+    }
+  }
+
+  async function resetModelRatio() {
+    try {
+      let res = await API.post(`/api/option/rest_model_ratio`);
+      if (res.data.success) {
+        showSuccess(res.data.message);
+        props.refresh();
+      } else {
+        showError(res.data.message);
+      }
+    } catch (error) {
+      showError(error);
+    }
+  }
+
+  useEffect(() => {
+    const currentInputs = {};
+    for (let key in props.options) {
+      if (Object.keys(inputs).includes(key)) {
+        currentInputs[key] = props.options[key];
+      }
+    }
+    setInputs(currentInputs);
+    setInputsRow(structuredClone(currentInputs));
+    refForm.current.setValues(currentInputs);
+  }, [props.options]);
+
+  return (
+    <Spin spinning={loading}>
+      <Form
+        values={inputs}
+        getFormApi={(formAPI) => (refForm.current = formAPI)}
+        style={{ marginBottom: 15 }}
+      >
+        <Form.Section>
+          <Row gutter={16}>
+            <Col span={16}>
+              <Form.TextArea
+                label={t('模型固定价格')}
+                extraText={t('一次调用消耗多少刀，优先级大于模型倍率')}
+                placeholder={t('为一个 JSON 文本，键为模型名称，值为一次调用消耗多少刀，比如 "gpt-4-gizmo-*": 0.1，一次消耗0.1刀')}
+                field={'ModelPrice'}
+                autosize={{ minRows: 6, maxRows: 12 }}
+                trigger='blur'
+                stopValidateWithError
+                rules={[
+                  {
+                    validator: (rule, value) => verifyJSON(value),
+                    message: '不是合法的 JSON 字符串'
+                  }
+                ]}
+                onChange={(value) => setInputs({ ...inputs, ModelPrice: value })}
+              />
+            </Col>
+          </Row>
+          <Row gutter={16}>
+            <Col span={16}>
+              <Form.TextArea
+                label={t('模型倍率')}
+                placeholder={t('为一个 JSON 文本，键为模型名称，值为倍率')}
+                field={'ModelRatio'}
+                autosize={{ minRows: 6, maxRows: 12 }}
+                trigger='blur'
+                stopValidateWithError
+                rules={[
+                  {
+                    validator: (rule, value) => verifyJSON(value),
+                    message: '不是合法的 JSON 字符串'
+                  }
+                ]}
+                onChange={(value) => setInputs({ ...inputs, ModelRatio: value })}
+              />
+            </Col>
+          </Row>
+          <Row gutter={16}>
+            <Col span={16}>
+              <Form.TextArea
+                label={t('模型补全倍率（仅对自定义模型有效）')}
+                extraText={t('仅对自定义模型有效')}
+                placeholder={t('为一个 JSON 文本，键为模型名称，值为倍率')}
+                field={'CompletionRatio'}
+                autosize={{ minRows: 6, maxRows: 12 }}
+                trigger='blur'
+                stopValidateWithError
+                rules={[
+                  {
+                    validator: (rule, value) => verifyJSON(value),
+                    message: '不是合法的 JSON 字符串'
+                  }
+                ]}
+                onChange={(value) => setInputs({ ...inputs, CompletionRatio: value })}
+              />
+            </Col>
+          </Row>
+        </Form.Section>
+      </Form>
+      <Space>
+        <Button onClick={onSubmit}>{t('保存模型倍率设置')}</Button>
+        <Popconfirm
+          title={t('确定重置模型倍率吗？')}
+          content={t('此修改将不可逆')}
+          okType={'danger'}
+          position={'top'}
+          onConfirm={resetModelRatio}
+        >
+          <Button type={'danger'}>{t('重置模型倍率')}</Button>
+        </Popconfirm>
+      </Space>
+    </Spin>
+  );
+} 
--- a/web/src/pages/Setting/Operation/ModelSettingsVisualEditor.js
+++ b/web/src/pages/Setting/Operation/ModelSettingsVisualEditor.js
@@ -0,0 +1,314 @@
+// ModelSettingsVisualEditor.js
+import React, { useEffect, useState } from 'react';
+import { Table, Button, Input, Modal, Form, Space } from '@douyinfe/semi-ui';
+import { IconDelete, IconPlus, IconSearch, IconSave } from '@douyinfe/semi-icons';
+import { showError, showSuccess } from '../../../helpers';
+import { API } from '../../../helpers';
+import { useTranslation } from 'react-i18next';
+
+export default function ModelSettingsVisualEditor(props) {
+  const { t } = useTranslation();
+  const [models, setModels] = useState([]);
+  const [visible, setVisible] = useState(false);
+  const [currentModel, setCurrentModel] = useState(null);
+  const [searchText, setSearchText] = useState('');
+  const [currentPage, setCurrentPage] = useState(1);
+  const [loading, setLoading] = useState(false);
+  const pageSize = 10;
+
+  useEffect(() => {
+    try {
+      const modelPrice = JSON.parse(props.options.ModelPrice || '{}');
+      const modelRatio = JSON.parse(props.options.ModelRatio || '{}');
+      const completionRatio = JSON.parse(props.options.CompletionRatio || '{}');
+
+      // 合并所有模型名称
+      const modelNames = new Set([
+        ...Object.keys(modelPrice),
+        ...Object.keys(modelRatio),
+        ...Object.keys(completionRatio)
+      ]);
+
+      const modelData = Array.from(modelNames).map(name => ({
+        name,
+        price: modelPrice[name] === undefined ? '' : modelPrice[name],
+        ratio: modelRatio[name] === undefined ? '' : modelRatio[name],
+        completionRatio: completionRatio[name] === undefined ? '' : completionRatio[name]
+      }));
+
+      setModels(modelData);
+    } catch (error) {
+      console.error('JSON解析错误:', error);
+    }
+  }, [props.options]);
+
+  // 首先声明分页相关的工具函数
+  const getPagedData = (data, currentPage, pageSize) => {
+    const start = (currentPage - 1) * pageSize;
+    const end = start + pageSize;
+    return data.slice(start, end);
+  };
+
+  // 在 return 语句之前，先处理过滤和分页逻辑
+  const filteredModels = models.filter(model =>
+    searchText ? model.name.toLowerCase().includes(searchText.toLowerCase()) : true
+  );
+
+  // 然后基于过滤后的数据计算分页数据
+  const pagedData = getPagedData(filteredModels, currentPage, pageSize);
+
+  const SubmitData = async () => {
+    setLoading(true);
+    const output = {
+      ModelPrice: {},
+      ModelRatio: {},
+      CompletionRatio: {}
+    };
+    let currentConvertModelName = '';
+
+    try {
+      // 数据转换
+      models.forEach(model => {
+        currentConvertModelName = model.name;
+        if (model.price !== '') {
+          // 如果价格不为空，则转换为浮点数，忽略倍率参数
+          output.ModelPrice[model.name] = parseFloat(model.price)
+        } else {
+          if (model.ratio !== '') output.ModelRatio[model.name] = parseFloat(model.ratio);
+          if (model.completionRatio !== '') output.CompletionRatio[model.name] = parseFloat(model.completionRatio);
+        }
+      });
+
+      // 准备API请求数组
+      const finalOutput = {
+        ModelPrice: JSON.stringify(output.ModelPrice, null, 2),
+        ModelRatio: JSON.stringify(output.ModelRatio, null, 2),
+        CompletionRatio: JSON.stringify(output.CompletionRatio, null, 2)
+      };
+
+      const requestQueue = Object.entries(finalOutput).map(([key, value]) => {
+        return API.put('/api/option/', {
+          key,
+          value
+        });
+      });
+
+      // 批量处理请求
+      const results = await Promise.all(requestQueue);
+
+      // 验证结果
+      if (requestQueue.length === 1) {
+        if (results.includes(undefined)) return;
+      } else if (requestQueue.length > 1) {
+        if (results.includes(undefined)) {
+          return showError('部分保存失败，请重试');
+        }
+      }
+
+      // 检查每个请求的结果
+      for (const res of results) {
+        if (!res.data.success) {
+          return showError(res.data.message);
+        }
+      }
+
+      showSuccess('保存成功');
+      props.refresh();
+
+    } catch (error) {
+      console.error('保存失败:', error);
+      showError('保存失败，请重试');
+    } finally {
+      setLoading(false);
+    }
+  };
+
+  const columns = [
+    {
+      title: t('模型名称'),
+      dataIndex: 'name',
+      key: 'name',
+    },
+    {
+      title: t('模型固定价格'),
+      dataIndex: 'price',
+      key: 'price',
+      render: (text, record) => (
+        <Input
+          value={text}
+          placeholder={t('按量计费')}
+          onChange={value => updateModel(record.name, 'price', value)}
+        />
+      )
+    },
+    {
+      title: t('模型倍率'),
+      dataIndex: 'ratio',
+      key: 'ratio',
+      render: (text, record) => (
+        <Input
+          value={text}
+          placeholder={record.price !== '' ? t('模型倍率') : t('默认补全倍率')}
+          disabled={record.price !== ''}
+          onChange={value => updateModel(record.name, 'ratio', value)}
+        />
+      )
+    },
+    {
+      title: t('补全倍率'),
+      dataIndex: 'completionRatio',
+      key: 'completionRatio',
+      render: (text, record) => (
+        <Input
+          value={text}
+          placeholder={record.price !== '' ? t('补全倍率') : t('默认补全倍率')}
+          disabled={record.price !== ''}
+          onChange={value => updateModel(record.name, 'completionRatio', value)}
+        />
+      )
+    },
+    {
+      title: t('操作'),
+      key: 'action',
+      render: (_, record) => (
+        <Button
+          icon={<IconDelete />}
+          type="danger"
+          onClick={() => deleteModel(record.name)}
+        />
+      )
+    }
+  ];
+
+  const updateModel = (name, field, value) => {
+    if (isNaN(value)) {
+      showError('请输入数字');
+      return;
+    }
+    setModels(prev =>
+      prev.map(model =>
+        model.name === name
+          ? { ...model, [field]: value }
+          : model
+      )
+    );
+  };
+
+  const deleteModel = (name) => {
+    setModels(prev => prev.filter(model => model.name !== name));
+  };
+  const addModel = (values) => {
+    // 检查模型名称是否存在, 如果存在则拒绝添加
+    if (models.some(model => model.name === values.name)) {
+      showError('模型名称已存在');
+      return;
+    }
+    setModels(prev => [{
+      name: values.name,
+      price: values.price || '',
+      ratio: values.ratio || '',
+      completionRatio: values.completionRatio || ''
+    }, ...prev]);
+    setVisible(false);
+    showSuccess('添加成功');
+  };
+
+
+  return (
+    <>
+      <Space vertical align="start" style={{ width: '100%' }}>
+        <Space>
+          <Button icon={<IconPlus />} onClick={() => setVisible(true)}>
+            {t('添加模型')}
+          </Button>
+          <Button type="primary" icon={<IconSave />} onClick={SubmitData}>
+            {t('应用更改')}
+          </Button>
+          <Input
+            prefix={<IconSearch />}
+            placeholder={t('搜索模型名称')}
+            value={searchText}
+            onChange={value => {
+              setSearchText(value)
+              setCurrentPage(1);
+            }}
+            style={{ width: 200 }}
+          />
+        </Space>
+        <Table
+          columns={columns}
+          dataSource={pagedData}
+          pagination={{
+            currentPage: currentPage,
+            pageSize: pageSize,
+            total: filteredModels.length,
+            onPageChange: page => setCurrentPage(page),
+            formatPageText: (page) =>
+              t('第 {{start}} - {{end}} 条，共 {{total}} 条', {
+                start: page.currentStart,
+                end: page.currentEnd,
+                total: filteredModels.length
+              }),
+            showTotal: true,
+            showSizeChanger: false
+          }}
+        />
+      </Space>
+
+      <Modal
+        title={t('添加模型')}
+        visible={visible}
+        onCancel={() => setVisible(false)}
+        onOk={() => {
+          currentModel && addModel(currentModel);
+        }}
+      >
+        <Form>
+          <Form.Input
+            field="name"
+            label={t('模型名称')}
+            placeholder="strawberry"
+            required
+            onChange={value => setCurrentModel(prev => ({ ...prev, name: value }))}
+          />
+          <Form.Switch
+            field="priceMode"
+            label={<>{t('定价模式')}：{currentModel?.priceMode ? t("固定价格") : t("倍率模式")}</>}
+            onChange={checked => {
+              setCurrentModel(prev => ({
+                ...prev,
+                price: '',
+                ratio: '',
+                completionRatio: '',
+                priceMode: checked
+              }));
+            }}
+          />
+          {currentModel?.priceMode ? (
+            <Form.Input
+              field="price"
+              label={t('固定价格(每次)')}
+              placeholder={t('输入每次价格')}
+              onChange={value => setCurrentModel(prev => ({ ...prev, price: value }))}
+            />
+          ) : (
+            <>
+              <Form.Input
+                field="ratio"
+                label={t('模型倍率')}
+                placeholder={t('输入模型倍率')}
+                onChange={value => setCurrentModel(prev => ({ ...prev, ratio: value }))}
+              />
+              <Form.Input
+                field="completionRatio"
+                label={t('补全倍率')}
+                placeholder={t('输入补全价格')}
+                onChange={value => setCurrentModel(prev => ({ ...prev, completionRatio: value }))}
+              />
+            </>
+          )}
+        </Form>
+      </Modal>
+    </>
+  );
+}
Author	SHA1	Message	Date
CalciumIon	03256dbdad	refactor: Enhance error handling in Gemini request conversion - Updated `CovertGemini2OpenAI` function to return an error alongside the GeminiChatRequest, improving error reporting for image processing. - Modified `ConvertRequest` methods in both `adaptor.go` files to handle potential errors from the Gemini conversion, ensuring robust request handling. - Improved clarity and maintainability of the code by explicitly managing error cases during request conversion.	2024-12-20 21:50:58 +08:00
CalciumIon	f9a7f6085e	feat: Add GEMINI_VISION_MAX_IMAGE_NUM configuration - Introduced `GEMINI_VISION_MAX_IMAGE_NUM` to README files for better user guidance. - Updated `env.go` to retrieve the maximum image number from environment variables, defaulting to 16. - Modified image handling logic in `relay-gemini.go` to respect the new configuration, allowing disabling of the limit by setting it to -1. - Removed hardcoded constant for maximum image number in `constant.go` to streamline configuration management.	2024-12-20 21:36:23 +08:00
Calcium-Ion	c289694fe8	Merge pull request #636 from HynoR/fix/smfix fix: 修复添加模型切换模式时，初始化空值导致的判断问题	2024-12-20 20:33:01 +08:00
Calcium-Ion	c37319cb4c	Merge pull request #641 from HynoR/main chore: 更新遗漏的gemini模型	2024-12-20 20:32:47 +08:00
Calcium-Ion	57f036747b	Merge pull request #642 from MartialBE/fix_gemini_thinking fix: 修复gemini thinking在stream下会内容丢失	2024-12-20 20:32:23 +08:00
MartialBE	158edab974	fix: Fix the issue where Gemini loses content when converting OpenAI format in the stream.	2024-12-20 20:24:49 +08:00
HynoR	f3a7119745	chore: 更新gemini模型	2024-12-20 19:17:56 +08:00
HynoR	3fa1d93b9c	chore: 更新gemini模型	2024-12-20 19:14:53 +08:00
TAKO	5e3ba45748	Merge branch 'Calcium-Ion:main' into fix/smfix	2024-12-20 19:11:32 +08:00
CalciumIon	cab30014ad	feat: Add new experimental Gemini versions to ModelList - Included additional versions: "gemini-2.0-flash-thinking-exp" and "gemini-2.0-flash-thinking-exp-1219". - Added comments to categorize versions as old, experimental, and flash experimental for better clarity.	2024-12-20 13:26:51 +08:00
CalciumIon	9a54b345c5	feat: support gemini-2.0-flash-thinking #639 #637	2024-12-20 13:20:07 +08:00
HynoR	e3a0162206	fix: 修复添加模型切换模式时，初始化空值导致的判断问题	2024-12-19 19:08:04 +08:00
CalciumIon	2d865eb735	refactor: Improve channel status update logic and clean up code - Simplified conditional checks in UpdateChannelStatusById function in channel.go to enhance readability. - Commented out unused image number check in relay-gemini.go for clarity. - Updated JSON field in en.json for currency consistency, changing "元" from "RMB/CNY" to "CNY" and added a space in "实付金额：" for formatting.	2024-12-17 15:33:16 +08:00
Calcium-Ion	70e7860838	Merge pull request #631 from xqx333/main fix	2024-12-17 14:39:39 +08:00
xqx333	1f4fc2d590	Update channel.go	2024-12-17 14:30:31 +08:00
Calcium-Ion	c76021e9a1	Merge pull request #630 from xqx333/main 修复自动禁用会对数据库进行多次更新的问题	2024-12-17 12:22:27 +08:00
xqx333	173c9bc669	Update channel.go	2024-12-17 12:11:24 +08:00
xqx333	739c0cc334	Update cache.go	2024-12-17 12:10:05 +08:00
CalciumIon	4163713714	refactor: Update SystemInstructions type in GeminiChatRequest and adjust handling in CovertGemini2OpenAI - Changed SystemInstructions from GeminiPart to GeminiChatContent in GeminiChatRequest for improved structure. - Updated CovertGemini2OpenAI function to accommodate the new SystemInstructions type, ensuring proper handling of message content.	2024-12-16 22:41:23 +08:00
CalciumIon	76acfdc9e2	fix: Correct JSON field name for SystemInstructions in GeminiChatRequest - Updated the JSON field name from "system_instructions" to "system_instruction" to ensure consistency and accuracy in the data structure.	2024-12-16 22:12:56 +08:00
CalciumIon	fe6f3d7978	feat: Enhance Home component to support language messaging - Added language messaging functionality to the iframe in the Home component. - This update ensures that the iframe receives the current language setting, improving localization support.	2024-12-16 21:10:46 +08:00
Calcium-Ion	1f70904fc5	Merge pull request #628 from Calcium-Ion/pr482-merge merge 428	2024-12-16 21:05:58 +08:00
CalciumIon	fd86de19b5	feat: Enhance HeaderBar to support language change messaging - Added functionality to post a message to the iframe when the language is changed. - This update improves localization support by ensuring that the iframe content updates according to the selected language.	2024-12-16 21:05:02 +08:00
CalciumIon	c8f437c13a	Merge remote-tracking branch 'guoruqiang/main' into pr482-merge # Conflicts: # README.md # web/src/components/HeaderBar.js # web/src/components/SiderBar.js	2024-12-16 20:56:53 +08:00
CalciumIon	e6c6bbdef9	feat: support gemini SystemInstructions #408	2024-12-16 20:19:29 +08:00
CalciumIon	aab3887d2c	Update README.md	2024-12-16 18:12:17 +08:00
Calcium-Ion	25ab1d400f	Merge pull request #625 from QAbot-zh/fix/bindwechat fix bindWeChat tips	2024-12-15 20:59:47 +08:00
Q.A.zh	6c995d4bd9	fix bindWeChat tips	2024-12-15 12:53:16 +00:00
Calcium-Ion	fb9f50ce79	Merge pull request #624 from Calcium-Ion/channel-setting feat: Add collapsible section for available models in PersonalSettings	2024-12-15 16:32:09 +08:00
CalciumIon	e8444edce7	feat: Add collapsible section for available models in PersonalSettings	2024-12-15 16:31:00 +08:00
Calcium-Ion	c1a5b0e1bb	Merge pull request #623 from Calcium-Ion/channel-setting feat: implement channel settings configuration	2024-12-15 15:55:13 +08:00
CalciumIon	f2809917f8	feat: implement channel settings configuration fix #620	2024-12-15 15:52:41 +08:00
CalciumIon	a4c43bb83b	feat: Enhance Operation Settings with Group and Model Ratio Management - Added new components for GroupRatioSettings and ModelRatioSettings to manage group and model ratios. - Integrated tabs in OperationSetting to switch between model and visual ratio settings. - Updated translations for new settings and improved existing ones in the English locale file. - Refactored ModelSettingsVisualEditor to support dynamic pricing and ratio configurations. This update improves the user interface for managing operational settings, enhancing usability and localization support.	2024-12-14 22:13:31 +08:00
Calcium-Ion	6ca68651ff	Merge pull request #618 from HynoR/feat/modeledit feat: 可视化模型定价编辑器	2024-12-14 21:32:05 +08:00
Calcium-Ion	e2f6444b83	Merge pull request #617 from kingxjs/main Available models could not be populated when adding a new channel	2024-12-14 21:31:05 +08:00
Calcium-Ion	8e2b6d0aad	Merge pull request #622 from Calcium-Ion/i18n-fix feat: Enhance i18n support	2024-12-14 14:12:27 +08:00
CalciumIon	41a7cee98e	feat: Refactor App and ChannelsTable components for improved i18n support - Removed redundant user and status loading logic from the App component, centralizing it in the PageLayout component for better maintainability. - Enhanced the ChannelsTable component by integrating translation functions for various UI elements, ensuring consistent localization of titles and modal messages. - Updated the English locale file with new translation keys for sub-channel modifications, improving the overall localization coverage. - Streamlined the code structure in multiple components to enhance readability and performance.	2024-12-14 14:09:30 +08:00
CalciumIon	68b87736b6	feat: Enhance i18n support in Home component and update translations - Integrated translation functions in the Home component to support dynamic localization for various UI elements, improving accessibility for users in different languages. - Added new translation keys for "Telegram authentication", "Linux DO authentication", and "License" in the English locale file, expanding the localization coverage. - Updated existing text elements to utilize translation functions, ensuring consistency in language display across the application.	2024-12-14 12:58:10 +08:00
CalciumIon	b86aeb9150	feat: Implement status loading in App component and refactor SiderBar - Added a new function to load status data from the API in the App component, enhancing the application's ability to display real-time status updates. - Integrated error handling for API calls to improve user feedback in case of connection issues. - Removed the redundant status loading logic from the SiderBar component, streamlining the code and ensuring a single source of truth for status management. - Updated the useEffect hook in SiderBar to maintain sidebar collapse state based on local storage, improving user experience.	2024-12-14 12:57:56 +08:00
CalciumIon	cfdf6e48f1	Update README	2024-12-13 23:48:18 +08:00
CalciumIon	68b7e0e96a	refactor: Remove unused translation function calls in LogsTable component - Eliminated unnecessary calls to the translation function in the LogsTable component, streamlining the code and improving performance. - This change enhances readability and reduces potential overhead from unused localization logic.	2024-12-13 22:34:10 +08:00
CalciumIon	84130cdf50	Update README.en.md	2024-12-13 21:21:28 +08:00
CalciumIon	d54cab2ab9	Add README.en.md	2024-12-13 20:21:34 +08:00
CalciumIon	7aa8b88c89	Update README.md	2024-12-13 20:15:50 +08:00
HynoR	3587f2c6e9	feat: 增加价格和倍率的互斥验证，优化模型名称输入提示	2024-12-13 14:45:49 +08:00
HynoR	498590d9fd	feat: 优化模型设置可视化编辑器，增强输入验证和提示信息	2024-12-13 14:42:02 +08:00
HynoR	8504e07245	feat: 添加保存功能并优化模型数据提交逻辑	2024-12-13 14:29:43 +08:00
TAKO	2eddb93432	Merge branch 'Calcium-Ion:main' into feat/modeledit	2024-12-13 14:11:31 +08:00
HynoR	369ecf365a	feat: 添加模型设置可视化编辑器组件	2024-12-13 14:10:38 +08:00
迷糊虫	36bf4b3926	Update EditChannel.js Fixes an issue with the OpenAI models interface where it fails to get a list of models.	2024-12-13 13:36:03 +08:00
G.RQ	b0d655e2b9	Merge branch 'Calcium-Ion:main' into main	2024-09-25 14:40:51 +08:00
GuoRuqiang	e4ccaddf4a	撤回修改	2024-09-25 06:39:32 +00:00
GuoRuqiang	b139588aa1	更新LoginForm 提示	2024-09-25 06:38:17 +00:00
G.RQ	ee17e307f0	Update README.md 增加主要变更说明15. 支持使用路由/chat2link 进入聊天界面	2024-09-22 23:09:45 +08:00
GuoRuqiang	574d7a0914	使用postMessage向iframe传参theme-mode，实现切换子页面主题的功能子页面的js示例 ``` <script> // 接收父页面的主题模式 window.addEventListener('message', function(event) { if (event.data.themeMode) { var theme = event.data.themeMode; // 测试是否正确接受到theme-mode的值 // console.log('Received theme mode from parent:', theme); applyTheme(theme); } }); // 定义一个函数来应用主题 function applyTheme(theme) { var body = document.body; if (theme === 'dark') { body.classList.add("dark-mode"); document.getElementById("darkModeToggle").checked = true; } else { body.classList.remove("dark-mode"); document.getElementById("darkModeToggle").checked = false; } } </script> ```	2024-09-22 14:09:03 +00:00
GuoRuqiang	edce1f7046	手动合并upstream	2024-09-22 14:04:15 +00:00
GuoRuqiang	bab718e9bc	聊天按钮适配移动端	2024-09-20 04:45:33 +00:00
G.RQ	509a1a0bac	Merge branch 'Calcium-Ion:main' into main	2024-09-19 15:19:46 +08:00
GuoRuqiang	0b2ae561bf	Merge branch 'Calcium-Ion:main' into main	2024-09-18 20:53:24 +08:00
GuoRuqiang	016e071d50	update HeaderBar	2024-09-18 10:29:25 +00:00