Merge pull request #594 from Calcium-Ion/gzip

fix: 标签分组功能开启时无法展开测试模型
2026-04-07 20:27:26 +00:00 · 2024-12-05 14:42:16 +08:00 · 2024-12-05 14:41:40 +08:00 · 2024-12-04 23:56:14 +08:00 · 2024-12-04 23:53:02 +08:00 · 2024-12-04 23:25:19 +08:00
45 changed files with 1991 additions and 755 deletions
--- a/.env.example
+++ b/.env.example
@@ -53,7 +53,7 @@
 # Gemini 安全设置
 # GEMINI_SAFETY_SETTING=BLOCK_NONE
 # Gemini版本设置
-# GEMINI_MODEL_MAP=gemini-1.5-pro-latest:v1beta,gemini-1.5-pro-001:v1beta
+# GEMINI_MODEL_MAP=gemini-1.0-pro:v1
 # Cohere 安全设置
 # COHERE_SAFETY_SETTING=NONE
 # 是否统计图片token
--- a/BT.md
+++ b/BT.md
@@ -0,0 +1,3 @@
+密钥为环境变量SESSION_SECRET
+
+![8285bba413e770fe9620f1bf9b40d44e](https://github.com/user-attachments/assets/7a6fc03e-c457-45e4-b8f9-184508fc26b0)
--- a/README.md
+++ b/README.md
@@ -68,19 +68,37 @@

 ## 比原版One API多出的配置
 - `GENERATE_DEFAULT_TOKEN`：是否为新注册用户生成初始令牌，默认为 `false`。
- `STREAMING_TIMEOUT`：设置流式一次回复的超时时间，默认为 30 秒。
+- `STREAMING_TIMEOUT`：设置流式一次回复的超时时间，默认为 60 秒。
 - `DIFY_DEBUG`：设置 Dify 渠道是否输出工作流和节点信息到客户端，默认为 `true`。
 - `FORCE_STREAM_OPTION`：是否覆盖客户端stream_options参数，请求上游返回流模式usage，默认为 `true`，建议开启，不影响客户端传入stream_options参数返回结果。
- `GET_MEDIA_TOKEN`：是统计图片token，默认为 `true`，关闭后将不再在本地计算图片token，可能会导致和上游计费不同，此项覆盖 `GET_MEDIA_TOKEN_NOT_STREAM` 选项作用。
+- `GET_MEDIA_TOKEN`：是否统计图片token，默认为 `true`，关闭后将不再在本地计算图片token，可能会导致和上游计费不同，此项覆盖 `GET_MEDIA_TOKEN_NOT_STREAM` 选项作用。
 - `GET_MEDIA_TOKEN_NOT_STREAM`：是否在非流（`stream=false`）情况下统计图片token，默认为 `true`。
 - `UPDATE_TASK`：是否更新异步任务（Midjourney、Suno），默认为 `true`，关闭后将不会更新任务进度。
- `GEMINI_MODEL_MAP`：Gemini模型指定版本(v1/v1beta)，使用“模型:版本”指定，","分隔，例如：-e GEMINI_MODEL_MAP="gemini-1.5-pro-latest:v1beta,gemini-1.5-pro-001:v1beta"，为空则使用默认配置
+- `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`。
 ## 部署
 ### 部署要求
 - 本地数据库（默认）：SQLite（Docker 部署默认使用 SQLite，必须挂载 `/data` 目录到宿主机）
 - 远程数据库：MySQL 版本 >= 5.7.8，PgSQL 版本 >= 9.6
+
+### 使用宝塔面板Docker功能部署
+安装宝塔面板 (**9.2.0版本**及以上)，前往 [宝塔面板](https://www.bt.cn/new/download.html) 官网，选择正式版的脚本下载安装  
+安装后登录宝塔面板，在菜单栏中点击 Docker ，首次进入会提示安装 Docker 服务，点击立即安装，按提示完成安装  
+安装完成后在应用商店中找到 **New-API** ，点击安装，配置基本选项 即可完成安装  
+[图文教程](BT.md)
+
 ### 基于 Docker 进行部署
+### 使用 Docker Compose 部署（推荐）
+```shell
+# 下载项目
+git clone https://github.com/Calcium-Ion/new-api.git
+cd new-api
+# 按需编辑 docker-compose.yml
+# 启动
+docker-compose up -d
+```
+
+### 直接使用 Docker 镜像
 ```shell
 # 使用 SQLite 的部署命令：
 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
@@ -88,16 +106,6 @@ docker run --name new-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -
 # 例如：
 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
 ```
-### 使用宝塔面板Docker功能部署
-```shell
-# 使用 SQLite 的部署命令：
-docker run --name new-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -v /www/wwwroot/new-api:/data calciumion/new-api:latest
-# 使用 MySQL 的部署命令，在上面的基础上添加 `-e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi"`，请自行修改数据库连接参数。
-# 例如：
-# 注意：数据库要开启远程访问，并且只允许服务器IP访问
-docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:123456@tcp(宝塔的服务器地址:宝塔数据库端口)/宝塔数据库名称" -e TZ=Asia/Shanghai -v /www/wwwroot/new-api:/data calciumion/new-api:latest
-# 注意：数据库要开启远程访问，并且只允许服务器IP访问
-```

 ## 渠道重试
 渠道重试功能已经实现，可以在`设置->运营设置->通用设置`设置重试次数，**建议开启缓存**功能。  
@@ -128,6 +136,7 @@ docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:1234
 ![796df8d287b7b7bd7853b2497e7df511](https://github.com/user-attachments/assets/255b5e97-2d3a-4434-b4fa-e922ad88ff5a)

 ![image](https://github.com/Calcium-Ion/new-api/assets/61247483/ad0e7aae-0203-471c-9716-2d83768927d4)
+![image](https://github.com/user-attachments/assets/29f81de5-33fc-4fc5-a5ff-f9b54b653c7c)

 ![image](https://github.com/Calcium-Ion/new-api/assets/61247483/3ca0b282-00ff-4c96-bf9d-e29ef615c605)
 夜间模式  
@@ -135,7 +144,7 @@ docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:1234
 ![image](https://github.com/Calcium-Ion/new-api/assets/61247483/af9a07ee-5101-4b3d-8bd9-ae21a4fd7e9e)

 ## 交流群
-<img src="https://github.com/Calcium-Ion/new-api/assets/61247483/de536a8a-0161-47a7-a0a2-66ef6de81266" width="200">
+<img src="https://github.com/user-attachments/assets/9ca0bc82-e057-4230-a28d-9f198fa022e3" width="200">

 ## 相关项目
 - [One API](https://github.com/songquanpeng/one-api)：原版项目
--- a/common/constants.go
+++ b/common/constants.go
@@ -254,7 +254,7 @@ var ChannelBaseURLs = []string{
 	"https://open.bigmodel.cn",            // 16
 	"https://dashscope.aliyuncs.com",      // 17
 	"",                                    // 18
-	"https://ai.360.cn",                   // 19
+	"https://api.360.cn",                   // 19
 	"https://openrouter.ai/api",           // 20
 	"https://api.aiproxy.io",              // 21
 	"https://fastgpt.run/api/openapi",     // 22
--- a/common/email.go
+++ b/common/email.go
@@ -9,12 +9,20 @@ import (
 	"time"
 )

-func generateMessageID() string {
+func generateMessageID() (string, error) {
+	split := strings.Split(SMTPAccount, "@")
+	if len(split) < 2 {
+		return "", fmt.Errorf("invalid SMTP account")
+	}
 	domain := strings.Split(SMTPAccount, "@")[1]
-	return fmt.Sprintf("<%d.%s@%s>", time.Now().UnixNano(), GetRandomString(12), domain)
+	return fmt.Sprintf("<%d.%s@%s>", time.Now().UnixNano(), GetRandomString(12), domain), nil
 }

 func SendEmail(subject string, receiver string, content string) error {
+	id, err2 := generateMessageID()
+	if err2 != nil {
+		return err2
+	}
 	if SMTPFrom == "" { // for compatibility
 		SMTPFrom = SMTPAccount
 	}
@@ -28,7 +36,7 @@ func SendEmail(subject string, receiver string, content string) error {
 		"Date: %s\r\n"+
 		"Message-ID: %s\r\n"+ // 添加 Message-ID 头
 		"Content-Type: text/html; charset=UTF-8\r\n\r\n%s\r\n",
-		receiver, SystemName, SMTPFrom, encodedSubject, time.Now().Format(time.RFC1123Z), generateMessageID(), content))
+		receiver, SystemName, SMTPFrom, encodedSubject, time.Now().Format(time.RFC1123Z), id, content))
 	auth := smtp.PlainAuth("", SMTPAccount, SMTPToken, SMTPServer)
 	addr := fmt.Sprintf("%s:%d", SMTPServer, SMTPPort)
 	to := strings.Split(receiver, ";")
--- a/common/group-ratio.go
+++ b/common/group-ratio.go
@@ -2,6 +2,7 @@ package common

 import (
 	"encoding/json"
+	"errors"
 )

 var GroupRatio = map[string]float64{
@@ -31,3 +32,17 @@ func GetGroupRatio(name string) float64 {
 	}
 	return ratio
 }
+
+func CheckGroupRatio(jsonStr string) error {
+	checkGroupRatio := make(map[string]float64)
+	err := json.Unmarshal([]byte(jsonStr), &checkGroupRatio)
+	if err != nil {
+		return err
+	}
+	for name, ratio := range checkGroupRatio {
+		if ratio < 0 {
+			return errors.New("group ratio must be not less than 0: " + name)
+		}
+	}
+	return nil
+}
--- a/common/model-ratio.go
+++ b/common/model-ratio.go
@@ -33,17 +33,18 @@ var defaultModelRatio = map[string]float64{
 	"gpt-4-32k":  30,
 	//"gpt-4-32k-0314":               30, //deprecated
 	"gpt-4-32k-0613":                  30,
-	"gpt-4-1106-preview":              5,    // $0.01 / 1K tokens
-	"gpt-4-0125-preview":              5,    // $0.01 / 1K tokens
-	"gpt-4-turbo-preview":             5,    // $0.01 / 1K tokens
-	"gpt-4-vision-preview":            5,    // $0.01 / 1K tokens
-	"gpt-4-1106-vision-preview":       5,    // $0.01 / 1K tokens
-	"chatgpt-4o-latest":               2.5,  // $0.01 / 1K tokens
-	"gpt-4o":                          1.25, // $0.01 / 1K tokens
-	"gpt-4o-audio-preview":            1.25, // $0.0015 / 1K tokens
-	"gpt-4o-audio-preview-2024-10-01": 1.25, // $0.0015 / 1K tokens
-	"gpt-4o-2024-08-06":               1.25, // $0.01 / 1K tokens
-	"gpt-4o-2024-05-13":               2.5,
+	"gpt-4-1106-preview":              5,    // $10 / 1M tokens
+	"gpt-4-0125-preview":              5,    // $10 / 1M tokens
+	"gpt-4-turbo-preview":             5,    // $10 / 1M tokens
+	"gpt-4-vision-preview":            5,    // $10 / 1M tokens
+	"gpt-4-1106-vision-preview":       5,    // $10 / 1M tokens
+	"chatgpt-4o-latest":               2.5,  // $5 / 1M tokens
+	"gpt-4o":                          1.25, // $2.5 / 1M tokens
+	"gpt-4o-audio-preview":            1.25, // $2.5 / 1M tokens
+	"gpt-4o-audio-preview-2024-10-01": 1.25, // $2.5 / 1M tokens
+	"gpt-4o-2024-05-13":               2.5,  // $5 / 1M tokens
+	"gpt-4o-2024-08-06":               1.25, // $2.5 / 1M tokens
+	"gpt-4o-2024-11-20":               1.25, // $2.5 / 1M tokens
 	"gpt-4o-realtime-preview":         2.5,
 	"o1-preview":                      7.5,
 	"o1-preview-2024-09-12":           7.5,
@@ -149,6 +150,7 @@ var defaultModelRatio = map[string]float64{
 	"360gpt-turbo":                   0.0858, // ¥0.0012 / 1k tokens
 	"360gpt-turbo-responsibility-8k": 0.8572, // ¥0.012 / 1k tokens
 	"360gpt-pro":                     0.8572, // ¥0.012 / 1k tokens
+	"360gpt2-pro":                    0.8572, // ¥0.012 / 1k tokens
 	"embedding-bert-512-v1":          0.0715, // ¥0.001 / 1k tokens
 	"embedding_s1_v1":                0.0715, // ¥0.001 / 1k tokens
 	"semantic_similarity_s1_v1":      0.0715, // ¥0.001 / 1k tokens
--- a/constant/env.go
+++ b/constant/env.go
@@ -7,7 +7,7 @@ import (
 	"strings"
 )

-var StreamingTimeout = common.GetEnvOrDefault("STREAMING_TIMEOUT", 30)
+var StreamingTimeout = common.GetEnvOrDefault("STREAMING_TIMEOUT", 60)
 var DifyDebug = common.GetEnvOrDefaultBool("DIFY_DEBUG", true)

 // ForceStreamOption 覆盖请求参数，强制返回usage信息
@@ -20,16 +20,7 @@ var GetMediaTokenNotStream = common.GetEnvOrDefaultBool("GET_MEDIA_TOKEN_NOT_STR
 var UpdateTask = common.GetEnvOrDefaultBool("UPDATE_TASK", true)

 var GeminiModelMap = map[string]string{
-	"gemini-1.5-pro-latest":     "v1beta",
-	"gemini-1.5-pro-001":        "v1beta",
-	"gemini-1.5-pro":            "v1beta",
-	"gemini-1.5-pro-exp-0801":   "v1beta",
-	"gemini-1.5-pro-exp-0827":   "v1beta",
-	"gemini-1.5-flash-latest":   "v1beta",
-	"gemini-1.5-flash-exp-0827": "v1beta",
-	"gemini-1.5-flash-001":      "v1beta",
-	"gemini-1.5-flash":          "v1beta",
-	"gemini-ultra":              "v1beta",
+	"gemini-1.0-pro": "v1",
 }

 func InitEnv() {
--- a/controller/channel.go
+++ b/controller/channel.go
@@ -3,12 +3,13 @@ package controller
 import (
 	"encoding/json"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"net/http"
 	"one-api/common"
 	"one-api/model"
 	"strconv"
 	"strings"
+
+	"github.com/gin-gonic/gin"
 )

 type OpenAIModel struct {
@@ -48,19 +49,41 @@ func GetAllChannels(c *gin.Context) {
 	if pageSize < 0 {
 		pageSize = common.ItemsPerPage
 	}
+	channelData := make([]*model.Channel, 0)
 	idSort, _ := strconv.ParseBool(c.Query("id_sort"))
-	channels, err := model.GetAllChannels(p*pageSize, pageSize, false, idSort)
-	if err != nil {
-		c.JSON(http.StatusOK, gin.H{
-			"success": false,
-			"message": err.Error(),
-		})
-		return
+	enableTagMode, _ := strconv.ParseBool(c.Query("tag_mode"))
+	if enableTagMode {
+		tags, err := model.GetPaginatedTags(p*pageSize, pageSize)
+		if err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": err.Error(),
+			})
+			return
+		}
+		for _, tag := range tags {
+			if tag != nil && *tag != "" {
+				tagChannel, err := model.GetChannelsByTag(*tag)
+				if err == nil {
+					channelData = append(channelData, tagChannel...)
+				}
+			}
+		}
+	} else {
+		channels, err := model.GetAllChannels(p*pageSize, pageSize, false, idSort)
+		if err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": err.Error(),
+			})
+			return
+		}
+		channelData = channels
 	}
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
-		"data":    channels,
+		"data":    channelData,
 	})
 	return
 }
@@ -144,8 +167,8 @@ func SearchChannels(c *gin.Context) {
 	keyword := c.Query("keyword")
 	group := c.Query("group")
 	modelKeyword := c.Query("model")
-	//idSort, _ := strconv.ParseBool(c.Query("id_sort"))
-	channels, err := model.SearchChannels(keyword, group, modelKeyword)
+	idSort, _ := strconv.ParseBool(c.Query("id_sort"))
+	channels, err := model.SearchChannels(keyword, group, modelKeyword, idSort)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -279,6 +302,98 @@ func DeleteDisabledChannel(c *gin.Context) {
 	return
 }

+type ChannelTag struct {
+	Tag          string  `json:"tag"`
+	NewTag       *string `json:"new_tag"`
+	Priority     *int64  `json:"priority"`
+	Weight       *uint   `json:"weight"`
+	ModelMapping *string `json:"model_mapping"`
+	Models       *string `json:"models"`
+	Groups       *string `json:"groups"`
+}
+
+func DisableTagChannels(c *gin.Context) {
+	channelTag := ChannelTag{}
+	err := c.ShouldBindJSON(&channelTag)
+	if err != nil || channelTag.Tag == "" {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "参数错误",
+		})
+		return
+	}
+	err = model.DisableChannelByTag(channelTag.Tag)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+	})
+	return
+}
+
+func EnableTagChannels(c *gin.Context) {
+	channelTag := ChannelTag{}
+	err := c.ShouldBindJSON(&channelTag)
+	if err != nil || channelTag.Tag == "" {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "参数错误",
+		})
+		return
+	}
+	err = model.EnableChannelByTag(channelTag.Tag)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+	})
+	return
+}
+
+func EditTagChannels(c *gin.Context) {
+	channelTag := ChannelTag{}
+	err := c.ShouldBindJSON(&channelTag)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "参数错误",
+		})
+		return
+	}
+	if channelTag.Tag == "" {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "tag不能为空",
+		})
+		return
+	}
+	err = model.EditChannelByTag(channelTag.Tag, channelTag.NewTag, channelTag.ModelMapping, channelTag.Models, channelTag.Groups, channelTag.Priority, channelTag.Weight)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+	})
+	return
+}
+
 type ChannelBatch struct {
 	Ids []int `json:"ids"`
 }
--- a/controller/github.go
+++ b/controller/github.go
@@ -142,8 +142,13 @@ func GitHubOAuth(c *gin.Context) {
 			user.Email = githubUser.Email
 			user.Role = common.RoleCommonUser
 			user.Status = common.UserStatusEnabled
+			affCode := session.Get("aff")
+			inviterId := 0
+			if affCode != nil {
+				inviterId, _ = model.GetUserIdByAffCode(affCode.(string))
+			}

-			if err := user.Insert(0); err != nil {
+			if err := user.Insert(inviterId); err != nil {
 				c.JSON(http.StatusOK, gin.H{
 					"success": false,
 					"message": err.Error(),
@@ -227,6 +232,10 @@ func GitHubBind(c *gin.Context) {
 func GenerateOAuthCode(c *gin.Context) {
 	session := sessions.Default(c)
 	state := common.GetRandomString(12)
+	affCode := c.Query("aff")
+	if affCode != "" {
+		session.Set("aff", affCode)
+	}
 	session.Set("oauth_state", state)
 	err := session.Save()
 	if err != nil {
--- a/controller/linuxdo.go
+++ b/controller/linuxdo.go
@@ -237,7 +237,13 @@ func LinuxdoOAuth(c *gin.Context) {
 			user.Role = common.RoleCommonUser
 			user.Status = common.UserStatusEnabled

-			if err := user.Insert(0); err != nil {
+			affCode := session.Get("aff")
+			inviterId := 0
+			if affCode != nil {
+				inviterId, _ = model.GetUserIdByAffCode(affCode.(string))
+			}
+
+			if err := user.Insert(inviterId); err != nil {
 				c.JSON(http.StatusOK, gin.H{
 					"success": false,
 					"message": err.Error(),
--- a/controller/option.go
+++ b/controller/option.go
@@ -82,6 +82,15 @@ func UpdateOption(c *gin.Context) {
 			})
 			return
 		}
+	case "GroupRatio":
+		err = common.CheckGroupRatio(option.Value)
+		if err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": err.Error(),
+			})
+			return
+		}
 	}
 	err = model.UpdateOption(option.Key, option.Value)
 	if err != nil {
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -3,7 +3,6 @@ version: '3.4'
 services:
  new-api:
    image: calciumion/new-api:latest
-    # build: .
    container_name: new-api
    restart: always
    command: --log-dir /app/logs
@@ -13,16 +12,17 @@ services:
      - ./data:/data
      - ./logs:/app/logs
    environment:
-      - SQL_DSN=root:123456@tcp(host.docker.internal:3306)/new-api  # 修改此行，或注释掉以使用 SQLite 作为数据库
+      - SQL_DSN=root:123456@tcp(mysql:3306)/new-api  # Point to the mysql service
      - REDIS_CONN_STRING=redis://redis
-      - SESSION_SECRET=random_string  # 修改为随机字符串
      - TZ=Asia/Shanghai
-#      - NODE_TYPE=slave  # 多机部署时从节点取消注释该行
-#      - SYNC_FREQUENCY=60  # 需要定期从数据库加载数据时取消注释该行
-#      - FRONTEND_BASE_URL=https://openai.justsong.cn  # 多机部署时从节点取消注释该行
+    #      - SESSION_SECRET=random_string  # 多机部署时设置，必须修改这个随机字符串！！！！！！！
+    #      - NODE_TYPE=slave  # Uncomment for slave node in multi-node deployment
+    #      - SYNC_FREQUENCY=60  # Uncomment if regular database syncing is needed
+    #      - FRONTEND_BASE_URL=https://openai.justsong.cn  # Uncomment for multi-node deployment with front-end URL

    depends_on:
      - redis
+      - mysql
    healthcheck:
      test: [ "CMD-SHELL", "wget -q -O - http://localhost:3000/api/status | grep -o '\"success\":\\s*true' | awk -F: '{print $2}'" ]
      interval: 30s
@@ -33,3 +33,18 @@ services:
    image: redis:latest
    container_name: redis
    restart: always
+
+  mysql:
+    image: mysql:8.2
+    container_name: mysql
+    restart: always
+    environment:
+      MYSQL_ROOT_PASSWORD: 123456  # Ensure this matches the password in SQL_DSN
+      MYSQL_DATABASE: new-api
+    volumes:
+      - mysql_data:/var/lib/mysql
+    # ports:
+    #   - "3306:3306"  # If you want to access MySQL from outside Docker, uncomment
+
+volumes:
+  mysql_data:
--- a/go.mod
+++ b/go.mod
@@ -7,11 +7,13 @@ toolchain go1.22.4

 require (
 	github.com/Calcium-Ion/go-epay v0.0.2
+	github.com/andybalholm/brotli v1.1.1
 	github.com/anknown/ahocorasick v0.0.0-20190904063843-d75dbd5169c0
 	github.com/aws/aws-sdk-go-v2 v1.26.1
 	github.com/aws/aws-sdk-go-v2/credentials v1.17.11
 	github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.7.4
 	github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b
+	github.com/bytedance/sonic v1.12.4
 	github.com/gin-contrib/cors v1.4.0
 	github.com/gin-contrib/gzip v0.0.6
 	github.com/gin-contrib/sessions v0.0.5
@@ -23,6 +25,7 @@ require (
 	github.com/google/uuid v1.6.0
 	github.com/gorilla/websocket v1.5.0
 	github.com/jinzhu/copier v0.4.0
+	github.com/joho/godotenv v1.5.1
 	github.com/pkg/errors v0.9.1
 	github.com/pkoukk/tiktoken-go v0.1.7
 	github.com/samber/lo v1.39.0
@@ -41,9 +44,10 @@ require (
 	github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.5 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.5 // indirect
 	github.com/aws/smithy-go v1.20.2 // indirect
-	github.com/bytedance/sonic v1.9.1 // indirect
+	github.com/bytedance/sonic/loader v0.2.1 // indirect
 	github.com/cespare/xxhash/v2 v2.3.0 // indirect
-	github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 // indirect
+	github.com/cloudwego/base64x v0.1.4 // indirect
+	github.com/cloudwego/iasm v0.2.0 // indirect
 	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
 	github.com/dlclark/regexp2 v1.11.0 // indirect
 	github.com/gabriel-vasile/mimetype v1.4.3 // indirect
@@ -63,9 +67,8 @@ require (
 	github.com/jackc/puddle/v2 v2.2.1 // indirect
 	github.com/jinzhu/inflection v1.0.0 // indirect
 	github.com/jinzhu/now v1.1.5 // indirect
-	github.com/joho/godotenv v1.5.1 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
-	github.com/klauspost/cpuid/v2 v2.2.4 // indirect
+	github.com/klauspost/cpuid/v2 v2.2.9 // indirect
 	github.com/leodido/go-urn v1.4.0 // indirect
 	github.com/mattn/go-isatty v0.0.20 // indirect
 	github.com/mattn/go-sqlite3 v2.0.3+incompatible // indirect
@@ -79,11 +82,11 @@ require (
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
 	github.com/ugorji/go/codec v1.2.11 // indirect
 	github.com/yusufpapurcu/wmi v1.2.3 // indirect
-	golang.org/x/arch v0.3.0 // indirect
+	golang.org/x/arch v0.12.0 // indirect
 	golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0 // indirect
 	golang.org/x/net v0.28.0 // indirect
 	golang.org/x/sync v0.8.0 // indirect
-	golang.org/x/sys v0.24.0 // indirect
+	golang.org/x/sys v0.27.0 // indirect
 	golang.org/x/text v0.17.0 // indirect
 	google.golang.org/protobuf v1.34.2 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
--- a/go.sum
+++ b/go.sum
@@ -1,5 +1,7 @@
 github.com/Calcium-Ion/go-epay v0.0.2 h1:3knFBuaBFpHzsGeGQU/QxUqZSHh5s0+jGo0P62pJzWc=
 github.com/Calcium-Ion/go-epay v0.0.2/go.mod h1:cxo/ZOg8ClvE3VAnCmEzbuyAZINSq7kFEN9oHj5WQ2U=
+github.com/andybalholm/brotli v1.1.1 h1:PR2pgnyFznKEugtsUo0xLdDop5SKXd5Qf5ysW+7XdTA=
+github.com/andybalholm/brotli v1.1.1/go.mod h1:05ib4cKhjx3OQYUY22hTVd34Bc8upXjOLL2rKwwZBoA=
 github.com/anknown/ahocorasick v0.0.0-20190904063843-d75dbd5169c0 h1:onfun1RA+KcxaMk1lfrRnwCd1UUuOjJM/lri5eM1qMs=
 github.com/anknown/ahocorasick v0.0.0-20190904063843-d75dbd5169c0/go.mod h1:4yg+jNTYlDEzBjhGS96v+zjyA3lfXlFd5CiTLIkPBLI=
 github.com/anknown/darts v0.0.0-20151216065714-83ff685239e6 h1:HblK3eJHq54yET63qPCTJnks3loDse5xRmmqHgHzwoI=
@@ -20,14 +22,17 @@ github.com/aws/smithy-go v1.20.2 h1:tbp628ireGtzcHDDmLT/6ADHidqnwgF57XOXZe6tp4Q=
 github.com/aws/smithy-go v1.20.2/go.mod h1:krry+ya/rV9RDcV/Q16kpu6ypI4K2czasz0NC3qS14E=
 github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b h1:LTGVFpNmNHhj0vhOlfgWueFJ32eK9blaIlHR2ciXOT0=
 github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b/go.mod h1:2ZlV9BaUH4+NXIBF0aMdKKAnHTzqH+iMU4KUjAbL23Q=
-github.com/bytedance/sonic v1.5.0/go.mod h1:ED5hyg4y6t3/9Ku1R6dU/4KyJ48DZ4jPhfY1O2AihPM=
-github.com/bytedance/sonic v1.9.1 h1:6iJ6NqdoxCDr6mbY8h18oSO+cShGSMRGCEo7F2h0x8s=
-github.com/bytedance/sonic v1.9.1/go.mod h1:i736AoUSYt75HyZLoJW9ERYxcy6eaN6h4BZXU064P/U=
+github.com/bytedance/sonic v1.12.4 h1:9Csb3c9ZJhfUWeMtpCDCq6BUoH5ogfDFLUgQ/jG+R0k=
+github.com/bytedance/sonic v1.12.4/go.mod h1:B8Gt/XvtZ3Fqj+iSKMypzymZxw/FVwgIGKzMzT9r/rk=
+github.com/bytedance/sonic/loader v0.1.1/go.mod h1:ncP89zfokxS5LZrJxl5z0UJcsk4M4yY2JpfqGeCtNLU=
+github.com/bytedance/sonic/loader v0.2.1 h1:1GgorWTqf12TA8mma4DDSbaQigE2wOgQo7iCjjJv3+E=
+github.com/bytedance/sonic/loader v0.2.1/go.mod h1:ncP89zfokxS5LZrJxl5z0UJcsk4M4yY2JpfqGeCtNLU=
 github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
 github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
-github.com/chenzhuoyu/base64x v0.0.0-20211019084208-fb5309c8db06/go.mod h1:DH46F32mSOjUmXrMHnKwZdA8wcEefY7UVqBKYGjpdQY=
-github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 h1:qSGYFH7+jGhDF8vLC+iwCD4WpbV1EBDSzWkJODFLams=
-github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311/go.mod h1:b583jCggY9gE99b6G5LEC39OIiVsWj+R97kbl5odCEk=
+github.com/cloudwego/base64x v0.1.4 h1:jwCgWpFanWmN8xoIUHa2rtzmkd5J2plF/dnLS6Xd/0Y=
+github.com/cloudwego/base64x v0.1.4/go.mod h1:0zlkT4Wn5C6NdauXdJRhSKRlJvmclQ1hhJgA0rcu/8w=
+github.com/cloudwego/iasm v0.2.0 h1:1KNIy1I1H9hNNFEEH3DVnI4UujN+1zjpuk6gwHLTssg=
+github.com/cloudwego/iasm v0.2.0/go.mod h1:8rXZaNYT2n95jn+zTI1sDr+IgcD2GVs0nlbbQPiEFhY=
 github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
@@ -117,8 +122,9 @@ github.com/json-iterator/go v1.1.9/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/u
 github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
 github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
 github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
-github.com/klauspost/cpuid/v2 v2.2.4 h1:acbojRNwl3o09bUq+yDCtZFc1aiwaAAxtcn8YkZXnvk=
-github.com/klauspost/cpuid/v2 v2.2.4/go.mod h1:RVVoqg1df56z8g3pUjL/3lE5UfnlrJX8tyFgg4nqhuY=
+github.com/klauspost/cpuid/v2 v2.2.9 h1:66ze0taIn2H33fBvCkXuv9BmCwDfafmiIVpKV9kKGuY=
+github.com/klauspost/cpuid/v2 v2.2.9/go.mod h1:rqkxqrZ1EhYM9G+hXH7YdowN5R5RGN6NK4QwQ3WMXF8=
+github.com/knz/go-libedit v1.10.1/go.mod h1:MZTVkCWyz0oBc7JOWP3wNAzd002ZbM/5hgShxwh4x8M=
 github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
 github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
 github.com/kr/pretty v0.3.0 h1:WgNl7dwNpEZ6jJ9k1snq4pZsg7DOEN8hP9Xw0Tsjwk0=
@@ -194,11 +200,12 @@ github.com/ugorji/go/codec v1.1.7/go.mod h1:Ax+UKWsSmolVDwsd+7N3ZtXu+yMGCf907BLY
 github.com/ugorji/go/codec v1.2.7/go.mod h1:WGN1fab3R1fzQlVQTkfxVtIBhWDRqOviHU95kRgeqEY=
 github.com/ugorji/go/codec v1.2.11 h1:BMaWp1Bb6fHwEtbplGBGJ498wD+LKlNSl25MjdZY4dU=
 github.com/ugorji/go/codec v1.2.11/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
+github.com/xyproto/randomstring v1.0.5 h1:YtlWPoRdgMu3NZtP45drfy1GKoojuR7hmRcnhZqKjWU=
+github.com/xyproto/randomstring v1.0.5/go.mod h1:rgmS5DeNXLivK7YprL0pY+lTuhNQW3iGxZ18UQApw/E=
 github.com/yusufpapurcu/wmi v1.2.3 h1:E1ctvB7uKFMOJw3fdOW32DwGE9I7t++CRUEMKvFoFiw=
 github.com/yusufpapurcu/wmi v1.2.3/go.mod h1:SBZ9tNy3G9/m5Oi98Zks0QjeHVDvuK0qfxQmPyzfmi0=
-golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
-golang.org/x/arch v0.3.0 h1:02VY4/ZcO/gBOH6PUaoiptASxtXU10jazRCP865E97k=
-golang.org/x/arch v0.3.0/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
+golang.org/x/arch v0.12.0 h1:UsYJhbzPYGsT0HbEdmYcqtCv8UNGvnaL561NnIUvaKg=
+golang.org/x/arch v0.12.0/go.mod h1:FEVrYAQjsQXMVJ1nsMoVVXPZg6p2JE2mx8psSWTDQys=
 golang.org/x/crypto v0.0.0-20210711020723-a769d52b0f97/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/crypto v0.26.0 h1:RrRspgV4mU+YwB4FYnuBoKsUapNIL5cohGAmSH3azsw=
 golang.org/x/crypto v0.26.0/go.mod h1:GY7jblb9wI+FOo5y8/S2oY4zWP07AkOJ4+jxCqdqn54=
@@ -219,12 +226,11 @@ golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBc
 golang.org/x/sys v0.0.0-20210630005230-0f9fa26af87c/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20210806184541-e5e7981a1069/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220110181412-a018aaa089fe/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.0.0-20220704084225-05e143d24a9e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.11.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.24.0 h1:Twjiwq9dn6R1fQcyiK+wQyHWfaz/BJB+YIpzU/Cv3Xg=
-golang.org/x/sys v0.24.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.27.0 h1:wBqf8DvsY9Y/2P8gAfPDEYNuS30J4lPHJxXSb/nJZ+s=
+golang.org/x/sys v0.27.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
@@ -262,4 +268,4 @@ gorm.io/gorm v1.23.8/go.mod h1:l2lP/RyAtc1ynaTjFksBde/O8v9oOGIApu2/xRitmZk=
 gorm.io/gorm v1.24.0/go.mod h1:DVrVomtaYTbqs7gB/x2uVvqnXzv0nqjB396B8cG4dBA=
 gorm.io/gorm v1.25.0 h1:+KtYtb2roDz14EQe4bla8CbQlmb9dN3VejSai3lprfU=
 gorm.io/gorm v1.25.0/go.mod h1:L4uxeKpfBml98NYqVqwAdmV1a2nBtAec/cf3fpucW/k=
-rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4=
+nullprogram.com/x/optparse v1.0.0/go.mod h1:KdyPE+Igbe0jQUrVfMqDMeJQIJZEuyV7pjYmp6pbG50=
--- a/middleware/auth.go
+++ b/middleware/auth.go
@@ -212,6 +212,7 @@ func TokenAuth() func(c *gin.Context) {
 		}
 		c.Set("id", token.UserId)
 		c.Set("token_id", token.Id)
+		c.Set("token_key", token.Key)
 		c.Set("token_name", token.Name)
 		c.Set("token_unlimited_quota", token.UnlimitedQuota)
 		if !token.UnlimitedQuota {
--- a/middleware/gzip.go
+++ b/middleware/gzip.go
@@ -0,0 +1,38 @@
+package middleware
+
+import (
+	"compress/gzip"
+	"github.com/andybalholm/brotli"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+)
+
+func DecompressRequestMiddleware() gin.HandlerFunc {
+	return func(c *gin.Context) {
+		if c.Request.Body == nil || c.Request.Method == http.MethodGet {
+			c.Next()
+			return
+		}
+		switch c.GetHeader("Content-Encoding") {
+		case "gzip":
+			gzipReader, err := gzip.NewReader(c.Request.Body)
+			if err != nil {
+				c.AbortWithStatus(http.StatusBadRequest)
+				return
+			}
+			defer gzipReader.Close()
+
+			// Replace the request body with the decompressed data
+			c.Request.Body = io.NopCloser(gzipReader)
+			c.Request.Header.Del("Content-Encoding")
+		case "br":
+			reader := brotli.NewReader(c.Request.Body)
+			c.Request.Body = io.NopCloser(reader)
+			c.Request.Header.Del("Content-Encoding")
+		}
+
+		// Continue processing the request
+		c.Next()
+	}
+}
--- a/model/ability.go
+++ b/model/ability.go
@@ -10,12 +10,13 @@ import (
 )

 type Ability struct {
-	Group     string `json:"group" gorm:"type:varchar(64);primaryKey;autoIncrement:false"`
-	Model     string `json:"model" gorm:"type:varchar(64);primaryKey;autoIncrement:false"`
-	ChannelId int    `json:"channel_id" gorm:"primaryKey;autoIncrement:false;index"`
-	Enabled   bool   `json:"enabled"`
-	Priority  *int64 `json:"priority" gorm:"bigint;default:0;index"`
-	Weight    uint   `json:"weight" gorm:"default:0;index"`
+	Group     string  `json:"group" gorm:"type:varchar(64);primaryKey;autoIncrement:false"`
+	Model     string  `json:"model" gorm:"type:varchar(64);primaryKey;autoIncrement:false"`
+	ChannelId int     `json:"channel_id" gorm:"primaryKey;autoIncrement:false;index"`
+	Enabled   bool    `json:"enabled"`
+	Priority  *int64  `json:"priority" gorm:"bigint;default:0;index"`
+	Weight    uint    `json:"weight" gorm:"default:0;index"`
+	Tag       *string `json:"tag" gorm:"index"`
 }

 func GetGroupModels(group string) []string {
@@ -149,6 +150,7 @@ func (channel *Channel) AddAbilities() error {
 				Enabled:   channel.Status == common.ChannelStatusEnabled,
 				Priority:  channel.Priority,
 				Weight:    uint(channel.GetWeight()),
+				Tag:       channel.Tag,
 			}
 			abilities = append(abilities, ability)
 		}
@@ -190,6 +192,24 @@ func UpdateAbilityStatus(channelId int, status bool) error {
 	return DB.Model(&Ability{}).Where("channel_id = ?", channelId).Select("enabled").Update("enabled", status).Error
 }

+func UpdateAbilityStatusByTag(tag string, status bool) error {
+	return DB.Model(&Ability{}).Where("tag = ?", tag).Select("enabled").Update("enabled", status).Error
+}
+
+func UpdateAbilityByTag(tag string, newTag *string, priority *int64, weight *uint) error {
+	ability := Ability{}
+	if newTag != nil {
+		ability.Tag = newTag
+	}
+	if priority != nil {
+		ability.Priority = priority
+	}
+	if weight != nil {
+		ability.Weight = *weight
+	}
+	return DB.Model(&Ability{}).Where("tag = ?", tag).Updates(ability).Error
+}
+
 func FixAbility() (int, error) {
 	var channelIds []int
 	count := 0
--- a/model/channel.go
+++ b/model/channel.go
@@ -2,9 +2,10 @@ package model

 import (
 	"encoding/json"
-	"gorm.io/gorm"
 	"one-api/common"
 	"strings"
+
+	"gorm.io/gorm"
 )

 type Channel struct {
@@ -32,6 +33,7 @@ type Channel struct {
 	Priority          *int64  `json:"priority" gorm:"bigint;default:0"`
 	AutoBan           *int    `json:"auto_ban" gorm:"default:1"`
 	OtherInfo         string  `json:"other_info"`
+	Tag               *string `json:"tag" gorm:"index"`
 }

 func (channel *Channel) GetModels() []string {
@@ -61,6 +63,17 @@ func (channel *Channel) SetOtherInfo(otherInfo map[string]interface{}) {
 	channel.OtherInfo = string(otherInfoBytes)
 }

+func (channel *Channel) GetTag() string {
+	if channel.Tag == nil {
+		return ""
+	}
+	return *channel.Tag
+}
+
+func (channel *Channel) SetTag(tag string) {
+	channel.Tag = &tag
+}
+
 func (channel *Channel) GetAutoBan() bool {
 	if channel.AutoBan == nil {
 		return false
@@ -87,7 +100,13 @@ func GetAllChannels(startIdx int, num int, selectAll bool, idSort bool) ([]*Chan
 	return channels, err
 }

-func SearchChannels(keyword string, group string, model string) ([]*Channel, error) {
+func GetChannelsByTag(tag string) ([]*Channel, error) {
+	var channels []*Channel
+	err := DB.Where("tag = ?", tag).Find(&channels).Error
+	return channels, err
+}
+
+func SearchChannels(keyword string, group string, model string, idSort bool) ([]*Channel, error) {
 	var channels []*Channel
 	keyCol := "`key`"
 	groupCol := "`group`"
@@ -100,6 +119,11 @@ func SearchChannels(keyword string, group string, model string) ([]*Channel, err
 		modelsCol = `"models"`
 	}

+	order := "priority desc"
+	if idSort {
+		order = "id desc"
+	}
+
 	// 构造基础查询
 	baseQuery := DB.Model(&Channel{}).Omit(keyCol)

@@ -122,7 +146,7 @@ func SearchChannels(keyword string, group string, model string) ([]*Channel, err
 	}

 	// 执行查询
-	err := baseQuery.Where(whereClause, args...).Order("priority desc").Find(&channels).Error
+	err := baseQuery.Where(whereClause, args...).Order(order).Find(&channels).Error
 	if err != nil {
 		return nil, err
 	}
@@ -288,6 +312,74 @@ func UpdateChannelStatusById(id int, status int, reason string) {

 }

+func EnableChannelByTag(tag string) error {
+	err := DB.Model(&Channel{}).Where("tag = ?", tag).Update("status", common.ChannelStatusEnabled).Error
+	if err != nil {
+		return err
+	}
+	err = UpdateAbilityStatusByTag(tag, true)
+	return err
+}
+
+func DisableChannelByTag(tag string) error {
+	err := DB.Model(&Channel{}).Where("tag = ?", tag).Update("status", common.ChannelStatusManuallyDisabled).Error
+	if err != nil {
+		return err
+	}
+	err = UpdateAbilityStatusByTag(tag, false)
+	return err
+}
+
+func EditChannelByTag(tag string, newTag *string, modelMapping *string, models *string, group *string, priority *int64, weight *uint) error {
+	updateData := Channel{}
+	shouldReCreateAbilities := false
+	updatedTag := tag
+	// 如果 newTag 不为空且不等于 tag，则更新 tag
+	if newTag != nil && *newTag != tag {
+		updateData.Tag = newTag
+		updatedTag = *newTag
+	}
+	if modelMapping != nil && *modelMapping != "" {
+		updateData.ModelMapping = modelMapping
+	}
+	if models != nil && *models != "" {
+		shouldReCreateAbilities = true
+		updateData.Models = *models
+	}
+	if group != nil && *group != "" {
+		shouldReCreateAbilities = true
+		updateData.Group = *group
+	}
+	if priority != nil {
+		updateData.Priority = priority
+	}
+	if weight != nil {
+		updateData.Weight = weight
+	}
+
+	err := DB.Model(&Channel{}).Where("tag = ?", tag).Updates(updateData).Error
+	if err != nil {
+		return err
+	}
+	if shouldReCreateAbilities {
+		channels, err := GetChannelsByTag(updatedTag)
+		if err == nil {
+			for _, channel := range channels {
+				err = channel.UpdateAbilities()
+				if err != nil {
+					common.SysError("failed to update abilities: " + err.Error())
+				}
+			}
+		}
+	} else {
+		err := UpdateAbilityByTag(tag, newTag, priority, weight)
+		if err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
 func UpdateChannelUsedQuota(id int, quota int) {
 	if common.BatchUpdateEnabled {
 		addNewRecord(BatchUpdateTypeChannelUsedQuota, id, quota)
@@ -312,3 +404,9 @@ func DeleteDisabledChannel() (int64, error) {
 	result := DB.Where("status = ? or status = ?", common.ChannelStatusAutoDisabled, common.ChannelStatusManuallyDisabled).Delete(&Channel{})
 	return result.RowsAffected, result.Error
 }
+
+func GetPaginatedTags(offset int, limit int) ([]*string, error) {
+	var tags []*string
+	err := DB.Model(&Channel{}).Select("DISTINCT tag").Where("tag != ''").Offset(offset).Limit(limit).Find(&tags).Error
+	return tags, err
+}
--- a/relay/channel/ai360/constants.go
+++ b/relay/channel/ai360/constants.go
@@ -4,6 +4,7 @@ var ModelList = []string{
 	"360gpt-turbo",
 	"360gpt-turbo-responsibility-8k",
 	"360gpt-pro",
+	"360gpt2-pro",
 	"360GPT_S2_V9",
 	"embedding-bert-512-v1",
 	"embedding_s1_v1",
--- a/relay/channel/aws/constants.go
+++ b/relay/channel/aws/constants.go
@@ -9,6 +9,7 @@ var awsModelIDMap = map[string]string{
 	"claude-3-haiku-20240307":    "anthropic.claude-3-haiku-20240307-v1:0",
 	"claude-3-5-sonnet-20240620": "anthropic.claude-3-5-sonnet-20240620-v1:0",
 	"claude-3-5-sonnet-20241022": "anthropic.claude-3-5-sonnet-20241022-v2:0",
+	"claude-3-5-haiku-20241022": "anthropic.claude-3-5-haiku-20241022-v1:0",
 }

 var ChannelName = "aws"
--- a/relay/channel/aws/dto.go
+++ b/relay/channel/aws/dto.go
@@ -7,9 +7,9 @@ import (
 type AwsClaudeRequest struct {
 	// AnthropicVersion should be "bedrock-2023-05-31"
 	AnthropicVersion string                 `json:"anthropic_version"`
-	System           string                 `json:"system"`
+	System           string                 `json:"system,omitempty"`
 	Messages         []claude.ClaudeMessage `json:"messages"`
-	MaxTokens        int                    `json:"max_tokens,omitempty"`
+	MaxTokens        uint                   `json:"max_tokens,omitempty"`
 	Temperature      float64                `json:"temperature,omitempty"`
 	TopP             float64                `json:"top_p,omitempty"`
 	TopK             int                    `json:"top_k,omitempty"`
@@ -17,3 +17,18 @@ type AwsClaudeRequest struct {
 	Tools            []claude.Tool          `json:"tools,omitempty"`
 	ToolChoice       any                    `json:"tool_choice,omitempty"`
 }
+
+func copyRequest(req *claude.ClaudeRequest) *AwsClaudeRequest {
+	return &AwsClaudeRequest{
+		AnthropicVersion: "bedrock-2023-05-31",
+		System:           req.System,
+		Messages:         req.Messages,
+		MaxTokens:        req.MaxTokens,
+		Temperature:      req.Temperature,
+		TopP:             req.TopP,
+		TopK:             req.TopK,
+		StopSequences:    req.StopSequences,
+		Tools:            req.Tools,
+		ToolChoice:       req.ToolChoice,
+	}
+}
--- a/relay/channel/aws/relay-aws.go
+++ b/relay/channel/aws/relay-aws.go
@@ -5,7 +5,6 @@ import (
 	"encoding/json"
 	"fmt"
 	"github.com/gin-gonic/gin"
-	"github.com/jinzhu/copier"
 	"github.com/pkg/errors"
 	"io"
 	"net/http"
@@ -78,13 +77,7 @@ func awsHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode int) (*
 		return wrapErr(errors.New("request not found")), nil
 	}
 	claudeReq := claudeReq_.(*claude.ClaudeRequest)
-	awsClaudeReq := &AwsClaudeRequest{
-		AnthropicVersion: "bedrock-2023-05-31",
-	}
-	if err = copier.Copy(awsClaudeReq, claudeReq); err != nil {
-		return wrapErr(errors.Wrap(err, "copy request")), nil
-	}
-
+	awsClaudeReq := copyRequest(claudeReq)
 	awsReq.Body, err = json.Marshal(awsClaudeReq)
 	if err != nil {
 		return wrapErr(errors.Wrap(err, "marshal request")), nil
@@ -136,12 +129,7 @@ func awsStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 	}
 	claudeReq := claudeReq_.(*claude.ClaudeRequest)

-	awsClaudeReq := &AwsClaudeRequest{
-		AnthropicVersion: "bedrock-2023-05-31",
-	}
-	if err = copier.Copy(awsClaudeReq, claudeReq); err != nil {
-		return wrapErr(errors.Wrap(err, "copy request")), nil
-	}
+	awsClaudeReq := copyRequest(claudeReq)
 	awsReq.Body, err = json.Marshal(awsClaudeReq)
 	if err != nil {
 		return wrapErr(errors.Wrap(err, "marshal request")), nil
--- a/relay/channel/gemini/adaptor.go
+++ b/relay/channel/gemini/adaptor.go
@@ -30,13 +30,13 @@ func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
 }

 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-	// 从映射中获取模型名称对应的版本，如果找不到就使用 info.ApiVersion 或默认的版本 "v1"
+	// 从映射中获取模型名称对应的版本，如果找不到就使用 info.ApiVersion 或默认的版本 "v1beta"
 	version, beta := constant.GeminiModelMap[info.UpstreamModelName]
 	if !beta {
 		if info.ApiVersion != "" {
 			version = info.ApiVersion
 		} else {
-			version = "v1"
+			version = "v1beta"
 		}
 	}

--- a/relay/channel/gemini/constant.go
+++ b/relay/channel/gemini/constant.go
@@ -7,6 +7,7 @@ const (
 var ModelList = []string{
 	"gemini-1.0-pro-latest", "gemini-1.0-pro-001", "gemini-1.5-pro-latest", "gemini-1.5-flash-latest", "gemini-ultra",
 	"gemini-1.0-pro-vision-latest", "gemini-1.0-pro-vision-001", "gemini-1.5-pro-exp-0827", "gemini-1.5-flash-exp-0827",
+	"gemini-exp-1114",
 }

 var ChannelName = "google gemini"
--- a/relay/channel/openai/adaptor.go
+++ b/relay/channel/openai/adaptor.go
@@ -32,11 +32,15 @@ func (a *Adaptor) Init(info *relaycommon.RelayInfo) {

 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	if info.RelayMode == constant.RelayModeRealtime {
-		// trim https
-		baseUrl := strings.TrimPrefix(info.BaseUrl, "https://")
-		baseUrl = strings.TrimPrefix(baseUrl, "http://")
-		baseUrl = "wss://" + baseUrl
-		info.BaseUrl = baseUrl
+		if strings.HasPrefix(info.BaseUrl, "https://") {
+			baseUrl := strings.TrimPrefix(info.BaseUrl, "https://")
+			baseUrl = "wss://" + baseUrl
+			info.BaseUrl = baseUrl
+		} else if strings.HasPrefix(info.BaseUrl, "http://") {
+			baseUrl := strings.TrimPrefix(info.BaseUrl, "http://")
+			baseUrl = "ws://" + baseUrl
+			info.BaseUrl = baseUrl
+		}
 	}
 	switch info.ChannelType {
 	case common.ChannelTypeAzure:
@@ -132,6 +136,19 @@ func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInf

 		writer.WriteField("model", request.Model)

+		// 获取所有表单字段
+		formData := c.Request.PostForm
+
+		// 遍历表单字段并打印输出
+		for key, values := range formData {
+			if key == "model" {
+				continue
+			}
+			for _, value := range values {
+				writer.WriteField(key, value)
+			}
+		}
+
 		// 添加文件字段
 		file, header, err := c.Request.FormFile("file")
 		if err != nil {
--- a/relay/channel/openai/constant.go
+++ b/relay/channel/openai/constant.go
@@ -9,7 +9,7 @@ var ModelList = []string{
 	"gpt-4-turbo-preview", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
 	"gpt-4-vision-preview",
 	"chatgpt-4o-latest",
-	"gpt-4o", "gpt-4o-2024-05-13", "gpt-4o-2024-08-06",
+	"gpt-4o", "gpt-4o-2024-05-13", "gpt-4o-2024-08-06", "gpt-4o-2024-11-20",
 	"gpt-4o-mini", "gpt-4o-mini-2024-07-18",
 	"o1-preview", "o1-preview-2024-09-12",
 	"o1-mini", "o1-mini-2024-09-12",
--- a/relay/channel/openai/relay-openai.go
+++ b/relay/channel/openai/relay-openai.go
@@ -98,6 +98,11 @@ func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 				shouldSendLastResp = false
 			}
 		}
+		for _, choice := range lastStreamResponse.Choices {
+			if choice.FinishReason != nil {
+				shouldSendLastResp = true
+			}
+		}
 	}
 	if shouldSendLastResp {
 		service.StringData(c, lastStreamData)
@@ -279,7 +284,6 @@ func OpenaiTTSHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 }

 func OpenaiSTTHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo, responseFormat string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
-	var audioResp dto.AudioResponse
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
@@ -288,11 +292,6 @@ func OpenaiSTTHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
-	err = json.Unmarshal(responseBody, &audioResp)
-	if err != nil {
-		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
-	}
-
 	// Reset response body
 	resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
 	// We shouldn't set the header before we parse the response body, because the parse part may fail.
--- a/relay/common/relay_info.go
+++ b/relay/common/relay_info.go
@@ -14,6 +14,7 @@ type RelayInfo struct {
 	ChannelType          int
 	ChannelId            int
 	TokenId              int
+	TokenKey             string
 	UserId               int
 	Group                string
 	TokenUnlimited       bool
@@ -58,6 +59,7 @@ func GenRelayInfo(c *gin.Context) *RelayInfo {
 	channelId := c.GetInt("channel_id")

 	tokenId := c.GetInt("token_id")
+	tokenKey := c.GetString("token_key")
 	userId := c.GetInt("id")
 	group := c.GetString("group")
 	tokenUnlimited := c.GetBool("token_unlimited_quota")
@@ -73,6 +75,7 @@ func GenRelayInfo(c *gin.Context) *RelayInfo {
 		ChannelType:       channelType,
 		ChannelId:         channelId,
 		TokenId:           tokenId,
+		TokenKey:          tokenKey,
 		UserId:            userId,
 		Group:             group,
 		TokenUnlimited:    tokenUnlimited,
--- a/relay/relay-audio.go
+++ b/relay/relay-audio.go
@@ -33,12 +33,19 @@ func getAndValidAudioRequest(c *gin.Context, info *relaycommon.RelayInfo) (*dto.
 			}
 		}
 	default:
-		if audioRequest.Model == "" {
-			audioRequest.Model = c.PostForm("model")
+		err = c.Request.ParseForm()
+		if err != nil {
+			return nil, err
 		}
+		formData := c.Request.PostForm
+		if audioRequest.Model == "" {
+			audioRequest.Model = formData.Get("model")
+		}
+
 		if audioRequest.Model == "" {
 			return nil, errors.New("model is required")
 		}
+		audioRequest.ResponseFormat = formData.Get("response_format")
 		if audioRequest.ResponseFormat == "" {
 			audioRequest.ResponseFormat = "json"
 		}
--- a/relay/relay-text.go
+++ b/relay/relay-text.go
@@ -2,7 +2,6 @@ package relay

 import (
 	"bytes"
-	"context"
 	"encoding/json"
 	"errors"
 	"fmt"
@@ -19,6 +18,8 @@ import (
 	"strings"
 	"time"

+	"github.com/bytedance/sonic"
+
 	"github.com/gin-gonic/gin"
 )

@@ -35,7 +36,7 @@ func getAndValidateTextRequest(c *gin.Context, relayInfo *relaycommon.RelayInfo)
 		textRequest.Model = c.Param("model")
 	}

-	if textRequest.MaxTokens < 0 || textRequest.MaxTokens > math.MaxInt32/2 {
+	if textRequest.MaxTokens > math.MaxInt32/2 {
 		return nil, errors.New("max_tokens is invalid")
 	}
 	if textRequest.Model == "" {
@@ -47,12 +48,12 @@ func getAndValidateTextRequest(c *gin.Context, relayInfo *relaycommon.RelayInfo)
 			return nil, errors.New("field prompt is required")
 		}
 	case relayconstant.RelayModeChatCompletions:
-		if textRequest.Messages == nil || len(textRequest.Messages) == 0 {
+		if len(textRequest.Messages) == 0 {
 			return nil, errors.New("field messages is required")
 		}
 	case relayconstant.RelayModeEmbeddings:
 	case relayconstant.RelayModeModerations:
-		if textRequest.Input == "" || textRequest.Input == nil {
+		if textRequest.Input == nil || textRequest.Input == "" {
 			return nil, errors.New("field input is required")
 		}
 	case relayconstant.RelayModeEdits:
@@ -76,7 +77,7 @@ func TextHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 	}

 	// map model name
-	isModelMapped := false
+	//isModelMapped := false
 	modelMapping := c.GetString("model_mapping")
 	//isModelMapped := false
 	if modelMapping != "" && modelMapping != "{}" {
@@ -86,7 +87,7 @@ func TextHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 			return service.OpenAIErrorWrapperLocal(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError)
 		}
 		if modelMap[textRequest.Model] != "" {
-			isModelMapped = true
+			//isModelMapped = true
 			textRequest.Model = modelMap[textRequest.Model]
 			// set upstream model name
 			//isModelMapped = true
@@ -165,23 +166,25 @@ func TextHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 	adaptor.Init(relayInfo)
 	var requestBody io.Reader

-	if relayInfo.ChannelType == common.ChannelTypeOpenAI && !isModelMapped {
-		body, err := common.GetRequestBody(c)
-		if err != nil {
-			return service.OpenAIErrorWrapperLocal(err, "get_request_body_failed", http.StatusInternalServerError)
-		}
-		requestBody = bytes.NewBuffer(body)
-	} else {
-		convertedRequest, err := adaptor.ConvertRequest(c, relayInfo, textRequest)
-		if err != nil {
-			return service.OpenAIErrorWrapperLocal(err, "convert_request_failed", http.StatusInternalServerError)
-		}
-		jsonData, err := json.Marshal(convertedRequest)
-		if err != nil {
-			return service.OpenAIErrorWrapperLocal(err, "json_marshal_failed", http.StatusInternalServerError)
-		}
-		requestBody = bytes.NewBuffer(jsonData)
+	//if relayInfo.ChannelType == common.ChannelTypeOpenAI && !isModelMapped {
+	//	body, err := common.GetRequestBody(c)
+	//	if err != nil {
+	//		return service.OpenAIErrorWrapperLocal(err, "get_request_body_failed", http.StatusInternalServerError)
+	//	}
+	//	requestBody = bytes.NewBuffer(body)
+	//} else {
+	//
+	//}
+
+	convertedRequest, err := adaptor.ConvertRequest(c, relayInfo, textRequest)
+	if err != nil {
+		return service.OpenAIErrorWrapperLocal(err, "convert_request_failed", http.StatusInternalServerError)
 	}
+	jsonData, err := sonic.Marshal(convertedRequest)
+	if err != nil {
+		return service.OpenAIErrorWrapperLocal(err, "json_marshal_failed", http.StatusInternalServerError)
+	}
+	requestBody = bytes.NewBuffer(jsonData)

 	statusCodeMappingStr := c.GetString("status_code_mapping")
 	var httpResp *http.Response
@@ -261,7 +264,7 @@ func preConsumeQuota(c *gin.Context, preConsumedQuota int, relayInfo *relaycommo
 		return 0, 0, service.OpenAIErrorWrapperLocal(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
 	}
 	if userQuota-preConsumedQuota < 0 {
-		return 0, 0, service.OpenAIErrorWrapperLocal(errors.New(fmt.Sprintf("chat pre-consumed quota failed, user quota: %d, need quota: %d", userQuota, preConsumedQuota)), "insufficient_user_quota", http.StatusBadRequest)
+		return 0, 0, service.OpenAIErrorWrapperLocal(fmt.Errorf("chat pre-consumed quota failed, user quota: %d, need quota: %d", userQuota, preConsumedQuota), "insufficient_user_quota", http.StatusBadRequest)
 	}
 	err = model.CacheDecreaseUserQuota(relayInfo.UserId, preConsumedQuota)
 	if err != nil {
@@ -295,13 +298,14 @@ func preConsumeQuota(c *gin.Context, preConsumedQuota int, relayInfo *relaycommo

 func returnPreConsumedQuota(c *gin.Context, relayInfo *relaycommon.RelayInfo, userQuota int, preConsumedQuota int) {
 	if preConsumedQuota != 0 {
-		go func(ctx context.Context) {
-			// return pre-consumed quota
-			err := model.PostConsumeTokenQuota(relayInfo, userQuota, -preConsumedQuota, 0, false)
+		go func() {
+			relayInfoCopy := *relayInfo
+
+			err := model.PostConsumeTokenQuota(&relayInfoCopy, userQuota, -preConsumedQuota, 0, false)
 			if err != nil {
 				common.SysError("error return pre-consumed quota: " + err.Error())
 			}
-		}(c)
+		}()
 	}
 }

--- a/router/api-router.go
+++ b/router/api-router.go
@@ -91,6 +91,9 @@ func SetApiRouter(router *gin.Engine) {
 			channelRoute.POST("/", controller.AddChannel)
 			channelRoute.PUT("/", controller.UpdateChannel)
 			channelRoute.DELETE("/disabled", controller.DeleteDisabledChannel)
+			channelRoute.POST("/tag/disabled", controller.DisableTagChannels)
+			channelRoute.POST("/tag/enabled", controller.EnableTagChannels)
+			channelRoute.PUT("/tag", controller.EditTagChannels)
 			channelRoute.DELETE("/:id", controller.DeleteChannel)
 			channelRoute.POST("/batch", controller.DeleteChannelBatch)
 			channelRoute.POST("/fix", controller.FixChannelsAbilities)
--- a/router/relay-router.go
+++ b/router/relay-router.go
@@ -9,6 +9,7 @@ import (

 func SetRelayRouter(router *gin.Engine) {
 	router.Use(middleware.CORS())
+	router.Use(middleware.DecompressRequestMiddleware())
 	// https://platform.openai.com/docs/api-reference/introduction
 	modelsRouter := router.Group("/v1/models")
 	modelsRouter.Use(middleware.TokenAuth())
--- a/service/quota.go
+++ b/service/quota.go
@@ -22,7 +22,7 @@ func PreWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usag
 		return err
 	}

-	token, err := model.CacheGetTokenByKey(strings.TrimLeft(relayInfo.ApiKey, "sk-"))
+	token, err := model.CacheGetTokenByKey(strings.TrimLeft(relayInfo.TokenKey, "sk-"))
 	if err != nil {
 		return err
 	}
@@ -53,7 +53,7 @@ func PreWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usag
 		return errors.New(fmt.Sprintf("用户额度不足，剩余额度为 %d", userQuota))
 	}

-	if token.RemainQuota < quota {
+	if !token.UnlimitedQuota && token.RemainQuota < quota {
 		return errors.New(fmt.Sprintf("令牌额度不足，剩余额度为 %d", token.RemainQuota))
 	}

--- a/web/src/components/ChannelsTable.js
+++ b/web/src/components/ChannelsTable.js
--- a/web/src/components/LoginForm.js
+++ b/web/src/components/LoginForm.js
@@ -44,8 +44,15 @@ const LoginForm = () => {
  const [turnstileToken, setTurnstileToken] = useState('');
  let navigate = useNavigate();
  const [status, setStatus] = useState({});
+  const [showWeChatLoginModal, setShowWeChatLoginModal] = useState(false);
+
  const logo = getLogo();

+  let affCode = new URLSearchParams(window.location.search).get('aff');
+  if (affCode) {
+    localStorage.setItem('aff', affCode);
+  }
+
  useEffect(() => {
    if (searchParams.get('expired')) {
      showError('未登录或登录已过期，请重新登录！');
@@ -61,7 +68,6 @@ const LoginForm = () => {
    }
  }, []);

-  const [showWeChatLoginModal, setShowWeChatLoginModal] = useState(false);

  const onWeChatLoginClicked = () => {
    setShowWeChatLoginModal(true);
--- a/web/src/components/RegisterForm.js
+++ b/web/src/components/RegisterForm.js
@@ -1,10 +1,16 @@
 import React, { useEffect, useState } from 'react';
 import { Link, useNavigate } from 'react-router-dom';
-import { API, getLogo, showError, showInfo, showSuccess } from '../helpers';
+import { API, getLogo, showError, showInfo, showSuccess, updateAPI } from '../helpers';
 import Turnstile from 'react-turnstile';
-import { Button, Card, Form, Layout } from '@douyinfe/semi-ui';
+import { Button, Card, Divider, Form, Icon, Layout, Modal } from '@douyinfe/semi-ui';
 import Title from '@douyinfe/semi-ui/lib/es/typography/title';
 import Text from '@douyinfe/semi-ui/lib/es/typography/text';
+import { IconGithubLogo } from '@douyinfe/semi-icons';
+import { onGitHubOAuthClicked, onLinuxDOOAuthClicked } from './utils.js';
+import LinuxDoIcon from './LinuxDoIcon.js';
+import WeChatIcon from './WeChatIcon.js';
+import TelegramLoginButton from 'react-telegram-login/src';
+import { setUserData } from '../helpers/data.js';

 const RegisterForm = () => {
  const [inputs, setInputs] = useState({
@@ -20,7 +26,11 @@ const RegisterForm = () => {
  const [turnstileSiteKey, setTurnstileSiteKey] = useState('');
  const [turnstileToken, setTurnstileToken] = useState('');
  const [loading, setLoading] = useState(false);
+  const [showWeChatLoginModal, setShowWeChatLoginModal] = useState(false);
+  const [status, setStatus] = useState({});
+  let navigate = useNavigate();
  const logo = getLogo();
+
  let affCode = new URLSearchParams(window.location.search).get('aff');
  if (affCode) {
    localStorage.setItem('aff', affCode);
@@ -30,6 +40,7 @@ const RegisterForm = () => {
    let status = localStorage.getItem('status');
    if (status) {
      status = JSON.parse(status);
+      setStatus(status);
      setShowEmailVerification(status.email_verification);
      if (status.turnstile_check) {
        setTurnstileEnabled(true);
@@ -38,7 +49,32 @@ const RegisterForm = () => {
    }
  });

-  let navigate = useNavigate();
+
+  const onWeChatLoginClicked = () => {
+    setShowWeChatLoginModal(true);
+  };
+
+  const onSubmitWeChatVerificationCode = async () => {
+    if (turnstileEnabled && turnstileToken === '') {
+      showInfo('请稍后几秒重试，Turnstile 正在检查用户环境！');
+      return;
+    }
+    const res = await API.get(
+      `/api/oauth/wechat?code=${inputs.wechat_verification_code}`,
+    );
+    const { success, message, data } = res.data;
+    if (success) {
+      userDispatch({ type: 'login', payload: data });
+      localStorage.setItem('user', JSON.stringify(data));
+      setUserData(data);
+      updateAPI();
+      navigate('/');
+      showSuccess('登录成功！');
+      setShowWeChatLoginModal(false);
+    } else {
+      showError(message);
+    }
+  };

  function handleChange(name, value) {
    setInputs((inputs) => ({ ...inputs, [name]: value }));
@@ -189,14 +225,127 @@ const RegisterForm = () => {
                    </Link>
                  </Text>
                </div>
+                {status.github_oauth ||
+                status.wechat_login ||
+                status.telegram_oauth ||
+                status.linuxdo_oauth ? (
+                  <>
+                    <Divider margin='12px' align='center'>
+                      第三方登录
+                    </Divider>
+                    <div
+                      style={{
+                        display: 'flex',
+                        justifyContent: 'center',
+                        marginTop: 20,
+                      }}
+                    >
+                      {status.github_oauth ? (
+                        <Button
+                          type='primary'
+                          icon={<IconGithubLogo />}
+                          onClick={() =>
+                            onGitHubOAuthClicked(status.github_client_id)
+                          }
+                        />
+                      ) : (
+                        <></>
+                      )}
+                      {status.linuxdo_oauth ? (
+                        <Button
+                          icon={<LinuxDoIcon />}
+                          onClick={() =>
+                            onLinuxDOOAuthClicked(status.linuxdo_client_id)
+                          }
+                        />
+                      ) : (
+                        <></>
+                      )}
+                      {status.wechat_login ? (
+                        <Button
+                          type='primary'
+                          style={{ color: 'rgba(var(--semi-green-5), 1)' }}
+                          icon={<Icon svg={<WeChatIcon />} />}
+                          onClick={onWeChatLoginClicked}
+                        />
+                      ) : (
+                        <></>
+                      )}
+                    </div>
+                    {status.telegram_oauth ? (
+                      <>
+                        <div
+                          style={{
+                            display: 'flex',
+                            justifyContent: 'center',
+                            marginTop: 5,
+                          }}
+                        >
+                          <TelegramLoginButton
+                            dataOnauth={onTelegramLoginClicked}
+                            botName={status.telegram_bot_name}
+                          />
+                        </div>
+                      </>
+                    ) : (
+                      <></>
+                    )}
+                  </>
+                ) : (
+                  <></>
+                )}
              </Card>
-              {turnstileEnabled ? (
-                <Turnstile
-                  sitekey={turnstileSiteKey}
-                  onVerify={(token) => {
-                    setTurnstileToken(token);
+              <Modal
+                title='微信扫码登录'
+                visible={showWeChatLoginModal}
+                maskClosable={true}
+                onOk={onSubmitWeChatVerificationCode}
+                onCancel={() => setShowWeChatLoginModal(false)}
+                okText={'登录'}
+                size={'small'}
+                centered={true}
+              >
+                <div
+                  style={{
+                    display: 'flex',
+                    alignItem: 'center',
+                    flexDirection: 'column',
                  }}
-                />
+                >
+                  <img src={status.wechat_qrcode} />
+                </div>
+                <div style={{ textAlign: 'center' }}>
+                  <p>
+                    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）
+                  </p>
+                </div>
+                <Form size='large'>
+                  <Form.Input
+                    field={'wechat_verification_code'}
+                    placeholder='验证码'
+                    label={'验证码'}
+                    value={inputs.wechat_verification_code}
+                    onChange={(value) =>
+                      handleChange('wechat_verification_code', value)
+                    }
+                  />
+                </Form>
+              </Modal>
+              {turnstileEnabled ? (
+                <div
+                  style={{
+                    display: 'flex',
+                    justifyContent: 'center',
+                    marginTop: 20,
+                  }}
+                >
+                  <Turnstile
+                    sitekey={turnstileSiteKey}
+                    onVerify={(token) => {
+                      setTurnstileToken(token);
+                    }}
+                  />
+                </div>
              ) : (
                <></>
              )}
--- a/web/src/components/custom/TextInput.js
+++ b/web/src/components/custom/TextInput.js
@@ -0,0 +1,21 @@
+import { Input, Typography } from '@douyinfe/semi-ui';
+import React from 'react';
+
+const TextInput = ({ label, name, value, onChange, placeholder, type = 'text' }) => {
+  return (
+    <>
+      <div style={{ marginTop: 10 }}>
+        <Typography.Text strong>{label}</Typography.Text>
+      </div>
+      <Input
+        name={name}
+        placeholder={placeholder}
+        onChange={(value) => onChange(value)}
+        value={value}
+        autoComplete="new-password"
+      />
+    </>
+  );
+}
+
+export default TextInput;
--- a/web/src/components/custom/TextNumberInput.js
+++ b/web/src/components/custom/TextNumberInput.js
@@ -0,0 +1,21 @@
+import { Input, InputNumber, Typography } from '@douyinfe/semi-ui';
+import React from 'react';
+
+const TextNumberInput = ({ label, name, value, onChange, placeholder }) => {
+  return (
+    <>
+      <div style={{ marginTop: 10 }}>
+        <Typography.Text strong>{label}</Typography.Text>
+      </div>
+      <InputNumber
+        name={name}
+        placeholder={placeholder}
+        onChange={(value) => onChange(value)}
+        value={value}
+        autoComplete="new-password"
+      />
+    </>
+  );
+}
+
+export default TextNumberInput;
--- a/web/src/components/utils.js
+++ b/web/src/components/utils.js
@@ -1,7 +1,12 @@
 import { API, showError } from '../helpers';

 export async function getOAuthState() {
-  const res = await API.get('/api/oauth/state');
+  let path = '/api/oauth/state';
+  let affCode = localStorage.getItem('aff');
+  if (affCode && affCode.length > 0) {
+    path += `?aff=${affCode}`;
+  }
+  const res = await API.get(path);
  const { success, message, data } = res.data;
  if (success) {
    return data;
--- a/web/src/helpers/api.js
+++ b/web/src/helpers/api.js
@@ -6,7 +6,8 @@ export let API = axios.create({
    ? import.meta.env.VITE_REACT_APP_SERVER_URL
    : '',
  headers: {
-    'New-API-User': getUserIdFromLocalStorage()
+    'New-API-User': getUserIdFromLocalStorage(),
+    'Cache-Control': 'no-store'
  }
 });

@@ -16,7 +17,8 @@ export function updateAPI() {
      ? import.meta.env.VITE_REACT_APP_SERVER_URL
      : '',
    headers: {
-      'New-API-User': getUserIdFromLocalStorage()
+      'New-API-User': getUserIdFromLocalStorage(),
+      'Cache-Control': 'no-store'
    }
  });
 }
--- a/web/src/helpers/render.js
+++ b/web/src/helpers/render.js
@@ -67,6 +67,8 @@ export function renderQuotaNumberWithDigit(num, digits = 2) {
 }

 export function renderNumberWithPoint(num) {
+  if (num === undefined)
+    return '';
  num = num.toFixed(2);
  if (num >= 100000) {
    // Convert number to string to manipulate it
--- a/web/src/pages/Channel/EditChannel.js
+++ b/web/src/pages/Channel/EditChannel.js
@@ -6,7 +6,7 @@ import {
  showError,
  showInfo,
  showSuccess,
-  verifyJSON,
+  verifyJSON
 } from '../../helpers';
 import { CHANNEL_OPTIONS } from '../../constants';
 import Title from '@douyinfe/semi-ui/lib/es/typography/title';
@@ -21,28 +21,26 @@ import {
  Select,
  TextArea,
  Checkbox,
-  Banner,
+  Banner
 } from '@douyinfe/semi-ui';
 import { Divider } from 'semantic-ui-react';
 import { getChannelModels, loadChannelModels } from '../../components/utils.js';
 import axios from 'axios';

 const MODEL_MAPPING_EXAMPLE = {
-  'gpt-3.5-turbo-0301': 'gpt-3.5-turbo',
-  'gpt-4-0314': 'gpt-4',
-  'gpt-4-32k-0314': 'gpt-4-32k',
+  'gpt-3.5-turbo': 'gpt-3.5-turbo-0125'
 };

 const STATUS_CODE_MAPPING_EXAMPLE = {
-  400: '500',
+  400: '500'
 };

 const REGION_EXAMPLE = {
-  "default": "us-central1",
-  "claude-3-5-sonnet-20240620": "europe-west1"
-}
+  'default': 'us-central1',
+  'claude-3-5-sonnet-20240620': 'europe-west1'
+};

-const fetchButtonTips = "1. 新建渠道时，请求通过当前浏览器发出；2. 编辑已有渠道，请求通过后端服务器发出"
+const fetchButtonTips = '1. 新建渠道时，请求通过当前浏览器发出；2. 编辑已有渠道，请求通过后端服务器发出';

 function type2secretPrompt(type) {
  // inputs.type === 15 ? '按照如下格式输入：APIKey|SecretKey' : (inputs.type === 18 ? '按照如下格式输入：APPID|APISecret|APIKey' : '请输入渠道对应的鉴权密钥')
@@ -84,6 +82,9 @@ const EditChannel = (props) => {
    auto_ban: 1,
    test_model: '',
    groups: ['default'],
+    priority: 0,
+    weight: 0,
+    tag: ''
  };
  const [batch, setBatch] = useState(false);
  const [autoBan, setAutoBan] = useState(true);
@@ -108,7 +109,7 @@ const EditChannel = (props) => {
            'mj_blend',
            'mj_upscale',
            'mj_describe',
-            'mj_uploads',
+            'mj_uploads'
          ];
          break;
        case 5:
@@ -128,13 +129,13 @@ const EditChannel = (props) => {
            'mj_high_variation',
            'mj_low_variation',
            'mj_pan',
-            'mj_uploads',
+            'mj_uploads'
          ];
          break;
        case 36:
          localModels = [
            'suno_music',
-            'suno_lyrics',
+            'suno_lyrics'
          ];
          break;
        default:
@@ -171,7 +172,7 @@ const EditChannel = (props) => {
        data.model_mapping = JSON.stringify(
          JSON.parse(data.model_mapping),
          null,
-          2,
+          2
        );
      }
      setInputs(data);
@@ -190,70 +191,69 @@ const EditChannel = (props) => {


  const fetchUpstreamModelList = async (name) => {
-    if (inputs["type"] !== 1) {
-      showError("仅支持 OpenAI 接口格式")
+    if (inputs['type'] !== 1) {
+      showError('仅支持 OpenAI 接口格式');
      return;
    }
-    setLoading(true)
-    const models = inputs["models"] || []
+    setLoading(true);
+    const models = inputs['models'] || [];
    let err = false;
    if (isEdit) {
-      const res = await API.get("/api/channel/fetch_models/" + channelId)
+      const res = await API.get('/api/channel/fetch_models/' + channelId);
      if (res.data && res.data?.success) {
-        models.push(...res.data.data)
+        models.push(...res.data.data);
      } else {
-        err = true
+        err = true;
      }
    } else {
-      if (!inputs?.["key"]) {
-        showError("请填写密钥")
-        err = true
+      if (!inputs?.['key']) {
+        showError('请填写密钥');
+        err = true;
      } else {
        try {
-          const host = new URL((inputs["base_url"] || "https://api.openai.com"))
+          const host = new URL((inputs['base_url'] || 'https://api.openai.com'));

          const url = `https://${host.hostname}/v1/models`;
-          const key = inputs["key"];
+          const key = inputs['key'];
          const res = await axios.get(url, {
            headers: {
              'Authorization': `Bearer ${key}`
            }
-          })
+          });
          if (res.data && res.data?.success) {
-            models.push(...res.data.data.map((model) => model.id))
+            models.push(...res.data.data.map((model) => model.id));
          } else {
-            err = true
+            err = true;
          }
-        }
-        catch (error) {
-          err = true
+        } catch (error) {
+          err = true;
        }
      }
    }
    if (!err) {
      handleInputChange(name, Array.from(new Set(models)));
-      showSuccess("获取模型列表成功");
+      showSuccess('获取模型列表成功');
    } else {
      showError('获取模型列表失败');
    }
    setLoading(false);
-  }
+  };

  const fetchModels = async () => {
    try {
      let res = await API.get(`/api/channel/models`);
      let localModelOptions = res.data.data.map((model) => ({
        label: model.id,
-        value: model.id,
+        value: model.id
      }));
      setOriginModelOptions(localModelOptions);
      setFullModels(res.data.data.map((model) => model.id));
      setBasicModels(
        res.data.data
          .filter((model) => {
-            return model.id.startsWith('gpt-3') || model.id.startsWith('text-');
+            return model.id.startsWith('gpt-') || model.id.startsWith('text-');
          })
-          .map((model) => model.id),
+          .map((model) => model.id)
      );
    } catch (error) {
      showError(error.message);
@@ -269,8 +269,8 @@ const EditChannel = (props) => {
      setGroupOptions(
        res.data.data.map((group) => ({
          label: group,
-          value: group,
-        })),
+          value: group
+        }))
      );
    } catch (error) {
      showError(error.message);
@@ -280,10 +280,10 @@ const EditChannel = (props) => {
  useEffect(() => {
    let localModelOptions = [...originModelOptions];
    inputs.models.forEach((model) => {
-      if (!localModelOptions.find((option) => option.key === model)) {
+      if (!localModelOptions.find((option) => option.label === model)) {
        localModelOptions.push({
          label: model,
-          value: model,
+          value: model
        });
      }
    });
@@ -320,7 +320,7 @@ const EditChannel = (props) => {
    if (localInputs.base_url && localInputs.base_url.endsWith('/')) {
      localInputs.base_url = localInputs.base_url.slice(
        0,
-        localInputs.base_url.length - 1,
+        localInputs.base_url.length - 1
      );
    }
    if (localInputs.type === 3 && localInputs.other === '') {
@@ -341,7 +341,7 @@ const EditChannel = (props) => {
    if (isEdit) {
      res = await API.put(`/api/channel/`, {
        ...localInputs,
-        id: parseInt(channelId),
+        id: parseInt(channelId)
      });
    } else {
      res = await API.post(`/api/channel/`, localInputs);
@@ -378,7 +378,7 @@ const EditChannel = (props) => {
          // 添加到下拉选项
          key: model,
          text: model,
-          value: model,
+          value: model
        });
      } else if (model) {
        showError('某些模型已存在！');
@@ -409,11 +409,11 @@ const EditChannel = (props) => {
        footer={
          <div style={{ display: 'flex', justifyContent: 'flex-end' }}>
            <Space>
-              <Button theme='solid' size={'large'} onClick={submit}>
+              <Button theme="solid" size={'large'} onClick={submit}>
                提交
              </Button>
              <Button
-                theme='solid'
+                theme="solid"
                size={'large'}
                type={'tertiary'}
                onClick={handleCancel}
@@ -432,7 +432,7 @@ const EditChannel = (props) => {
            <Typography.Text strong>类型：</Typography.Text>
          </div>
          <Select
-            name='type'
+            name="type"
            required
            optionList={CHANNEL_OPTIONS}
            value={inputs.type}
@@ -450,8 +450,8 @@ const EditChannel = (props) => {
                      ，因为 One API 会把请求体中的 model
                      参数替换为你的部署名称（模型名称中的点会被剔除），
                      <a
-                        target='_blank'
-                        href='https://github.com/songquanpeng/one-api/issues/133?notification_referrer_id=NT_kwDOAmJSYrM2NjIwMzI3NDgyOjM5OTk4MDUw#issuecomment-1571602271'
+                        target="_blank"
+                        href="https://github.com/songquanpeng/one-api/issues/133?notification_referrer_id=NT_kwDOAmJSYrM2NjIwMzI3NDgyOjM5OTk4MDUw#issuecomment-1571602271"
                      >
                        图片演示
                      </a>
@@ -466,8 +466,8 @@ const EditChannel = (props) => {
                </Typography.Text>
              </div>
              <Input
-                label='AZURE_OPENAI_ENDPOINT'
-                name='azure_base_url'
+                label="AZURE_OPENAI_ENDPOINT"
+                name="azure_base_url"
                placeholder={
                  '请输入 AZURE_OPENAI_ENDPOINT，例如：https://docs-test-001.openai.azure.com'
                }
@@ -475,14 +475,14 @@ const EditChannel = (props) => {
                  handleInputChange('base_url', value);
                }}
                value={inputs.base_url}
-                autoComplete='new-password'
+                autoComplete="new-password"
              />
              <div style={{ marginTop: 10 }}>
                <Typography.Text strong>默认 API 版本：</Typography.Text>
              </div>
              <Input
-                label='默认 API 版本'
-                name='azure_other'
+                label="默认 API 版本"
+                name="azure_other"
                placeholder={
                  '请输入默认 API 版本，例如：2023-06-01-preview，该配置可以被实际的请求查询参数所覆盖'
                }
@@ -490,7 +490,7 @@ const EditChannel = (props) => {
                  handleInputChange('other', value);
                }}
                value={inputs.other}
-                autoComplete='new-password'
+                autoComplete="new-password"
              />
            </>
          )}
@@ -512,7 +512,7 @@ const EditChannel = (props) => {
                </Typography.Text>
              </div>
              <Input
-                name='base_url'
+                name="base_url"
                placeholder={
                  '请输入完整的URL，例如：https://api.openai.com/v1/chat/completions'
                }
@@ -520,49 +520,84 @@ const EditChannel = (props) => {
                  handleInputChange('base_url', value);
                }}
                value={inputs.base_url}
-                autoComplete='new-password'
+                autoComplete="new-password"
+              />
+            </>
+          )}
+          {inputs.type !== 3 && inputs.type !== 8 && inputs.type !== 22 && inputs.type !== 36 && (
+            <>
+              <div style={{ marginTop: 10 }}>
+                <Typography.Text strong>代理：</Typography.Text>
+              </div>
+              <Input
+                label="代理"
+                name="base_url"
+                placeholder={'此项可选，用于通过代理站来进行 API 调用'}
+                onChange={(value) => {
+                  handleInputChange('base_url', value);
+                }}
+                value={inputs.base_url}
+                autoComplete="new-password"
+              />
+            </>
+          )}
+          {inputs.type === 22 && (
+            <>
+              <div style={{ marginTop: 10 }}>
+                <Typography.Text strong>私有部署地址：</Typography.Text>
+              </div>
+              <Input
+                name="base_url"
+                placeholder={
+                  '请输入私有部署地址，格式为：https://fastgpt.run/api/openapi'
+                }
+                onChange={(value) => {
+                  handleInputChange('base_url', value);
+                }}
+                value={inputs.base_url}
+                autoComplete="new-password"
              />
            </>
          )}
          {inputs.type === 36 && (
-              <>
-                <div style={{marginTop: 10}}>
-                  <Typography.Text strong>
-                    注意非Chat API，请务必填写正确的API地址，否则可能导致无法使用
-                  </Typography.Text>
-                </div>
-                <Input
-                    name='base_url'
-                    placeholder={
-                      '请输入到 /suno 前的路径，通常就是域名，例如：https://api.example.com '
-                    }
-                    onChange={(value) => {
-                      handleInputChange('base_url', value);
-                    }}
-                    value={inputs.base_url}
-                    autoComplete='new-password'
-                />
-              </>
+            <>
+              <div style={{ marginTop: 10 }}>
+                <Typography.Text strong>
+                  注意非Chat API，请务必填写正确的API地址，否则可能导致无法使用
+                </Typography.Text>
+              </div>
+              <Input
+                name="base_url"
+                placeholder={
+                  '请输入到 /suno 前的路径，通常就是域名，例如：https://api.example.com '
+                }
+                onChange={(value) => {
+                  handleInputChange('base_url', value);
+                }}
+                value={inputs.base_url}
+                autoComplete="new-password"
+              />
+            </>
          )}
-          <div style={{marginTop: 10}}>
+          <div style={{ marginTop: 10 }}>
            <Typography.Text strong>名称：</Typography.Text>
          </div>
          <Input
-              required
-              name='name'
+            required
+            name="name"
            placeholder={'请为渠道命名'}
            onChange={(value) => {
              handleInputChange('name', value);
            }}
            value={inputs.name}
-            autoComplete='new-password'
+            autoComplete="new-password"
          />
          <div style={{ marginTop: 10 }}>
            <Typography.Text strong>分组：</Typography.Text>
          </div>
          <Select
            placeholder={'请选择可以使用该渠道的分组'}
-            name='groups'
+            name="groups"
            required
            multiple
            selection
@@ -572,7 +607,7 @@ const EditChannel = (props) => {
              handleInputChange('groups', value);
            }}
            value={inputs.groups}
-            autoComplete='new-password'
+            autoComplete="new-password"
            optionList={groupOptions}
          />
          {inputs.type === 18 && (
@@ -581,7 +616,7 @@ const EditChannel = (props) => {
                <Typography.Text strong>模型版本：</Typography.Text>
              </div>
              <Input
-                name='other'
+                name="other"
                placeholder={
                  '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'
                }
@@ -589,7 +624,7 @@ const EditChannel = (props) => {
                  handleInputChange('other', value);
                }}
                value={inputs.other}
-                autoComplete='new-password'
+                autoComplete="new-password"
              />
            </>
          )}
@@ -599,7 +634,7 @@ const EditChannel = (props) => {
                <Typography.Text strong>部署地区：</Typography.Text>
              </div>
              <TextArea
-                name='other'
+                name="other"
                placeholder={
                  '请输入部署地区，例如：us-central1\n支持使用模型映射格式\n' +
                  '{\n' +
@@ -612,18 +647,18 @@ const EditChannel = (props) => {
                  handleInputChange('other', value);
                }}
                value={inputs.other}
-                autoComplete='new-password'
+                autoComplete="new-password"
              />
              <Typography.Text
                style={{
                  color: 'rgba(var(--semi-blue-5), 1)',
                  userSelect: 'none',
-                  cursor: 'pointer',
+                  cursor: 'pointer'
                }}
                onClick={() => {
                  handleInputChange(
                    'other',
-                    JSON.stringify(REGION_EXAMPLE, null, 2),
+                    JSON.stringify(REGION_EXAMPLE, null, 2)
                  );
                }}
              >
@@ -637,14 +672,14 @@ const EditChannel = (props) => {
                <Typography.Text strong>知识库 ID：</Typography.Text>
              </div>
              <Input
-                label='知识库 ID'
-                name='other'
+                label="知识库 ID"
+                name="other"
                placeholder={'请输入知识库 ID，例如：123456'}
                onChange={(value) => {
                  handleInputChange('other', value);
                }}
                value={inputs.other}
-                autoComplete='new-password'
+                autoComplete="new-password"
              />
            </>
          )}
@@ -654,7 +689,7 @@ const EditChannel = (props) => {
                <Typography.Text strong>Account ID：</Typography.Text>
              </div>
              <Input
-                name='other'
+                name="other"
                placeholder={
                  '请输入Account ID，例如：d6b5da8hk1awo8nap34ube6gh'
                }
@@ -662,7 +697,7 @@ const EditChannel = (props) => {
                  handleInputChange('other', value);
                }}
                value={inputs.other}
-                autoComplete='new-password'
+                autoComplete="new-password"
              />
            </>
          )}
@@ -671,7 +706,7 @@ const EditChannel = (props) => {
          </div>
          <Select
            placeholder={'请选择该渠道所支持的模型'}
-            name='models'
+            name="models"
            required
            multiple
            selection
@@ -679,13 +714,13 @@ const EditChannel = (props) => {
              handleInputChange('models', value);
            }}
            value={inputs.models}
-            autoComplete='new-password'
+            autoComplete="new-password"
            optionList={modelOptions}
          />
          <div style={{ lineHeight: '40px', marginBottom: '12px' }}>
            <Space>
              <Button
-                type='primary'
+                type="primary"
                onClick={() => {
                  handleInputChange('models', basicModels);
                }}
@@ -693,7 +728,7 @@ const EditChannel = (props) => {
                填入相关模型
              </Button>
              <Button
-                type='secondary'
+                type="secondary"
                onClick={() => {
                  handleInputChange('models', fullModels);
                }}
@@ -702,7 +737,7 @@ const EditChannel = (props) => {
              </Button>
              <Tooltip content={fetchButtonTips}>
                <Button
-                  type='tertiary'
+                  type="tertiary"
                  onClick={() => {
                    fetchUpstreamModelList('models');
                  }}
@@ -711,7 +746,7 @@ const EditChannel = (props) => {
                </Button>
              </Tooltip>
              <Button
-                type='warning'
+                type="warning"
                onClick={() => {
                  handleInputChange('models', []);
                }}
@@ -721,11 +756,11 @@ const EditChannel = (props) => {
            </Space>
            <Input
              addonAfter={
-                <Button type='primary' onClick={addCustomModels}>
+                <Button type="primary" onClick={addCustomModels}>
                  填入
                </Button>
              }
-              placeholder='输入自定义模型名称'
+              placeholder="输入自定义模型名称"
              value={customModel}
              onChange={(value) => {
                setCustomModel(value.trim());
@@ -737,24 +772,24 @@ const EditChannel = (props) => {
          </div>
          <TextArea
            placeholder={`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：\n${JSON.stringify(MODEL_MAPPING_EXAMPLE, null, 2)}`}
-            name='model_mapping'
+            name="model_mapping"
            onChange={(value) => {
              handleInputChange('model_mapping', value);
            }}
            autosize
            value={inputs.model_mapping}
-            autoComplete='new-password'
+            autoComplete="new-password"
          />
          <Typography.Text
            style={{
              color: 'rgba(var(--semi-blue-5), 1)',
              userSelect: 'none',
-              cursor: 'pointer',
+              cursor: 'pointer'
            }}
            onClick={() => {
              handleInputChange(
                'model_mapping',
-                JSON.stringify(MODEL_MAPPING_EXAMPLE, null, 2),
+                JSON.stringify(MODEL_MAPPING_EXAMPLE, null, 2)
              );
            }}
          >
@@ -765,8 +800,8 @@ const EditChannel = (props) => {
          </div>
          {batch ? (
            <TextArea
-              label='密钥'
-              name='key'
+              label="密钥"
+              name="key"
              required
              placeholder={'请输入密钥，一行一个'}
              onChange={(value) => {
@@ -774,14 +809,14 @@ const EditChannel = (props) => {
              }}
              value={inputs.key}
              style={{ minHeight: 150, fontFamily: 'JetBrains Mono, Consolas' }}
-              autoComplete='new-password'
+              autoComplete="new-password"
            />
          ) : (
            <>
              {inputs.type === 41 ? (
                <TextArea
-                  label='鉴权json'
-                  name='key'
+                  label="鉴权json"
+                  name="key"
                  required
                  placeholder={'{\n' +
                    '  "type": "service_account",\n' +
@@ -801,23 +836,36 @@ const EditChannel = (props) => {
                  }}
                  autosize={{ minRows: 10 }}
                  value={inputs.key}
-                  autoComplete='new-password'
+                  autoComplete="new-password"
                />
              ) : (
                <Input
-                  label='密钥'
-                  name='key'
+                  label="密钥"
+                  name="key"
                  required
                  placeholder={type2secretPrompt(inputs.type)}
                  onChange={(value) => {
                    handleInputChange('key', value);
                  }}
                  value={inputs.key}
-                  autoComplete='new-password'
+                  autoComplete="new-password"
                />
              )
              }
-              </>
+            </>
+          )}
+          {!isEdit && (
+            <div style={{ marginTop: 10, display: 'flex' }}>
+              <Space>
+                <Checkbox
+                  checked={batch}
+                  label="批量创建"
+                  name="batch"
+                  onChange={() => setBatch(!batch)}
+                />
+                <Typography.Text strong>批量创建</Typography.Text>
+              </Space>
+            </div>
          )}
          {inputs.type === 1 && (
            <>
@@ -825,9 +873,9 @@ const EditChannel = (props) => {
                <Typography.Text strong>组织：</Typography.Text>
              </div>
              <Input
-                label='组织，可选，不填则为默认组织'
-                name='openai_organization'
-                placeholder='请输入组织org-xxx'
+                label="组织，可选，不填则为默认组织"
+                name="openai_organization"
+                placeholder="请输入组织org-xxx"
                onChange={(value) => {
                  handleInputChange('openai_organization', value);
                }}
@@ -839,8 +887,8 @@ const EditChannel = (props) => {
            <Typography.Text strong>默认测试模型：</Typography.Text>
          </div>
          <Input
-            name='test_model'
-            placeholder='不填则为模型列表第一个'
+            name="test_model"
+            placeholder="不填则为模型列表第一个"
            onChange={(value) => {
              handleInputChange('test_model', value);
            }}
@@ -849,7 +897,7 @@ const EditChannel = (props) => {
          <div style={{ marginTop: 10, display: 'flex' }}>
            <Space>
              <Checkbox
-                name='auto_ban'
+                name="auto_ban"
                checked={autoBan}
                onChange={() => {
                  setAutoBan(!autoBan);
@@ -861,55 +909,6 @@ const EditChannel = (props) => {
              </Typography.Text>
            </Space>
          </div>
-
-          {!isEdit && (
-            <div style={{ marginTop: 10, display: 'flex' }}>
-              <Space>
-                <Checkbox
-                  checked={batch}
-                  label='批量创建'
-                  name='batch'
-                  onChange={() => setBatch(!batch)}
-                />
-                <Typography.Text strong>批量创建</Typography.Text>
-              </Space>
-            </div>
-          )}
-          {inputs.type !== 3 && inputs.type !== 8 && inputs.type !== 22 && inputs.type !== 36 && (
-            <>
-              <div style={{ marginTop: 10 }}>
-                <Typography.Text strong>代理：</Typography.Text>
-              </div>
-              <Input
-                label='代理'
-                name='base_url'
-                placeholder={'此项可选，用于通过代理站来进行 API 调用'}
-                onChange={(value) => {
-                  handleInputChange('base_url', value);
-                }}
-                value={inputs.base_url}
-                autoComplete='new-password'
-              />
-            </>
-          )}
-          {inputs.type === 22 && (
-            <>
-              <div style={{ marginTop: 10 }}>
-                <Typography.Text strong>私有部署地址：</Typography.Text>
-              </div>
-              <Input
-                name='base_url'
-                placeholder={
-                  '请输入私有部署地址，格式为：https://fastgpt.run/api/openapi'
-                }
-                onChange={(value) => {
-                  handleInputChange('base_url', value);
-                }}
-                value={inputs.base_url}
-                autoComplete='new-password'
-              />
-            </>
-          )}
          <div style={{ marginTop: 10 }}>
            <Typography.Text strong>
              状态码复写（仅影响本地判断，不修改返回到上游的状态码）：
@@ -917,43 +916,74 @@ const EditChannel = (props) => {
          </div>
          <TextArea
            placeholder={`此项可选，用于复写返回的状态码，比如将claude渠道的400错误复写为500（用于重试），请勿滥用该功能，例如：\n${JSON.stringify(STATUS_CODE_MAPPING_EXAMPLE, null, 2)}`}
-            name='status_code_mapping'
+            name="status_code_mapping"
            onChange={(value) => {
              handleInputChange('status_code_mapping', value);
            }}
            autosize
            value={inputs.status_code_mapping}
-            autoComplete='new-password'
+            autoComplete="new-password"
          />
          <Typography.Text
            style={{
              color: 'rgba(var(--semi-blue-5), 1)',
              userSelect: 'none',
-              cursor: 'pointer',
+              cursor: 'pointer'
            }}
            onClick={() => {
              handleInputChange(
                'status_code_mapping',
-                JSON.stringify(STATUS_CODE_MAPPING_EXAMPLE, null, 2),
+                JSON.stringify(STATUS_CODE_MAPPING_EXAMPLE, null, 2)
              );
            }}
          >
            填入模板
          </Typography.Text>
-          {/*<div style={{ marginTop: 10 }}>*/}
-          {/*  <Typography.Text strong>*/}
-          {/*    最大请求token（0表示不限制）：*/}
-          {/*  </Typography.Text>*/}
-          {/*</div>*/}
-          {/*<Input*/}
-          {/*  label='最大请求token'*/}
-          {/*  name='max_input_tokens'*/}
-          {/*  placeholder='默认为0，表示不限制'*/}
-          {/*  onChange={(value) => {*/}
-          {/*    handleInputChange('max_input_tokens', value);*/}
-          {/*  }}*/}
-          {/*  value={inputs.max_input_tokens}*/}
-          {/*/>*/}
+          <div style={{ marginTop: 10 }}>
+            <Typography.Text strong>
+              渠道标签
+            </Typography.Text>
+          </div>
+          <Input
+            label="渠道标签"
+            name="tag"
+            placeholder={'渠道标签'}
+            onChange={(value) => {
+              handleInputChange('tag', value);
+            }}
+            value={inputs.tag}
+            autoComplete="new-password"
+          />
+          <div style={{ marginTop: 10 }}>
+            <Typography.Text strong>
+              渠道优先级
+            </Typography.Text>
+          </div>
+          <Input
+            label="渠道优先级"
+            name="priority"
+            placeholder={'渠道优先级'}
+            onChange={(value) => {
+              handleInputChange('priority', parseInt(value));
+            }}
+            value={inputs.priority}
+            autoComplete="new-password"
+          />
+          <div style={{ marginTop: 10 }}>
+            <Typography.Text strong>
+              渠道权重
+            </Typography.Text>
+          </div>
+          <Input
+            label="渠道权重"
+            name="weight"
+            placeholder={'渠道权重'}
+            onChange={(value) => {
+              handleInputChange('weight', parseInt(value));
+            }}
+            value={inputs.weight}
+            autoComplete="new-password"
+          />
        </Spin>
      </SideSheet>
    </>
--- a/web/src/pages/Channel/EditTagModal.js
+++ b/web/src/pages/Channel/EditTagModal.js
@@ -0,0 +1,317 @@
+import React, { useState, useEffect } from 'react';
+import { API, showError, showInfo, showSuccess, showWarning, verifyJSON } from '../../helpers';
+import { SideSheet, Space, Button, Input, Typography, Spin, Modal, Select, Banner, TextArea } from '@douyinfe/semi-ui';
+import TextInput from '../../components/custom/TextInput.js';
+import { getChannelModels } from '../../components/utils.js';
+
+const MODEL_MAPPING_EXAMPLE = {
+  'gpt-3.5-turbo': 'gpt-3.5-turbo-0125'
+};
+
+const EditTagModal = (props) => {
+  const { visible, tag, handleClose, refresh } = props;
+  const [loading, setLoading] = useState(false);
+  const [originModelOptions, setOriginModelOptions] = useState([]);
+  const [modelOptions, setModelOptions] = useState([]);
+  const [groupOptions, setGroupOptions] = useState([]);
+  const [basicModels, setBasicModels] = useState([]);
+  const [fullModels, setFullModels] = useState([]);
+  const originInputs = {
+    tag: '',
+    new_tag: null,
+    model_mapping: null,
+    groups: [],
+    models: [],
+  }
+  const [inputs, setInputs] = useState(originInputs);
+
+  const handleInputChange = (name, value) => {
+    setInputs((inputs) => ({ ...inputs, [name]: value }));
+    if (name === 'type') {
+      let localModels = [];
+      switch (value) {
+        case 2:
+          localModels = [
+            'mj_imagine',
+            'mj_variation',
+            'mj_reroll',
+            'mj_blend',
+            'mj_upscale',
+            'mj_describe',
+            'mj_uploads'
+          ];
+          break;
+        case 5:
+          localModels = [
+            'swap_face',
+            'mj_imagine',
+            'mj_variation',
+            'mj_reroll',
+            'mj_blend',
+            'mj_upscale',
+            'mj_describe',
+            'mj_zoom',
+            'mj_shorten',
+            'mj_modal',
+            'mj_inpaint',
+            'mj_custom_zoom',
+            'mj_high_variation',
+            'mj_low_variation',
+            'mj_pan',
+            'mj_uploads'
+          ];
+          break;
+        case 36:
+          localModels = [
+            'suno_music',
+            'suno_lyrics'
+          ];
+          break;
+        default:
+          localModels = getChannelModels(value);
+          break;
+      }
+      if (inputs.models.length === 0) {
+        setInputs((inputs) => ({ ...inputs, models: localModels }));
+      }
+      setBasicModels(localModels);
+    }
+  };
+
+  const fetchModels = async () => {
+    try {
+      let res = await API.get(`/api/channel/models`);
+      let localModelOptions = res.data.data.map((model) => ({
+        label: model.id,
+        value: model.id
+      }));
+      setOriginModelOptions(localModelOptions);
+      setFullModels(res.data.data.map((model) => model.id));
+      setBasicModels(
+        res.data.data
+          .filter((model) => {
+            return model.id.startsWith('gpt-') || model.id.startsWith('text-');
+          })
+          .map((model) => model.id)
+      );
+    } catch (error) {
+      showError(error.message);
+    }
+  };
+
+  const fetchGroups = async () => {
+    try {
+      let res = await API.get(`/api/group/`);
+      if (res === undefined) {
+        return;
+      }
+      setGroupOptions(
+        res.data.data.map((group) => ({
+          label: group,
+          value: group
+        }))
+      );
+    } catch (error) {
+      showError(error.message);
+    }
+  };
+
+
+  const handleSave = async () => {
+    setLoading(true);
+    let data = {
+      tag: tag,
+    }
+    if (inputs.model_mapping !== null && inputs.model_mapping !== '') {
+      if (inputs.model_mapping !== '' && !verifyJSON(inputs.model_mapping)) {
+        showInfo('模型映射必须是合法的 JSON 格式！');
+        setLoading(false);
+        return;
+      }
+      data.model_mapping = inputs.model_mapping
+    }
+    if (inputs.groups.length > 0) {
+      data.groups = inputs.groups.join(',');
+    }
+    if (inputs.models.length > 0) {
+      data.models = inputs.models.join(',');
+    }
+    data.new_tag = inputs.new_tag;
+    // check have any change
+    if (data.model_mapping === undefined && data.groups === undefined && data.models === undefined && data.new_tag === undefined) {
+      showWarning('没有任何修改！');
+      setLoading(false);
+      return;
+    }
+    await submit(data);
+    setLoading(false);
+  };
+
+  const submit = async (data) => {
+    try {
+      const res = await API.put('/api/channel/tag', data);
+      if (res?.data?.success) {
+        showSuccess('标签更新成功！');
+        refresh();
+        handleClose();
+      }
+    } catch (error) {
+      showError(error);
+    }
+  }
+
+  useEffect(() => {
+    let localModelOptions = [...originModelOptions];
+    inputs.models.forEach((model) => {
+      if (!localModelOptions.find((option) => option.label === model)) {
+        localModelOptions.push({
+          label: model,
+          value: model
+        });
+      }
+    });
+    setModelOptions(localModelOptions);
+  }, [originModelOptions, inputs.models]);
+
+  useEffect(() => {
+    setInputs({
+      ...originInputs,
+      tag: tag,
+      new_tag: tag,
+    })
+    fetchModels().then();
+    fetchGroups().then();
+  }, [visible]);
+
+  return (
+    <SideSheet
+      title="编辑标签"
+      visible={visible}
+      onCancel={handleClose}
+      footer={
+        <div style={{ display: 'flex', justifyContent: 'flex-end' }}>
+          <Space>
+            <Button onClick={handleClose}>取消</Button>
+            <Button type="primary" onClick={handleSave} loading={loading}>保存</Button>
+          </Space>
+        </div>
+      }
+    >
+      <div style={{ marginTop: 10 }}>
+        <Banner
+          type={'warning'}
+          description={
+            <>
+              所有编辑均为覆盖操作，留空则不更改
+            </>
+          }
+        ></Banner>
+      </div>
+      <Spin spinning={loading}>
+        <TextInput
+          label="新标签，留空则不更改"
+          name="newTag"
+          value={inputs.new_tag}
+          onChange={(value) => setInputs({ ...inputs, new_tag: value })}
+          placeholder="请输入新标签"
+        />
+        <div style={{ marginTop: 10 }}>
+          <Typography.Text strong>模型，留空则不更改：</Typography.Text>
+        </div>
+        <Select
+          placeholder={'请选择该渠道所支持的模型，留空则不更改'}
+          name="models"
+          required
+          multiple
+          selection
+          onChange={(value) => {
+            handleInputChange('models', value);
+          }}
+          value={inputs.models}
+          autoComplete="new-password"
+          optionList={modelOptions}
+        />
+        <div style={{ marginTop: 10 }}>
+          <Typography.Text strong>分组，留空则不更改：</Typography.Text>
+        </div>
+        <Select
+          placeholder={'请选择可以使用该渠道的分组，留空则不更改'}
+          name="groups"
+          required
+          multiple
+          selection
+          allowAdditions
+          additionLabel={'请在系统设置页面编辑分组倍率以添加新的分组：'}
+          onChange={(value) => {
+            handleInputChange('groups', value);
+          }}
+          value={inputs.groups}
+          autoComplete="new-password"
+          optionList={groupOptions}
+        />
+        <div style={{ marginTop: 10 }}>
+          <Typography.Text strong>模型重定向：</Typography.Text>
+        </div>
+        <TextArea
+          placeholder={`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，留空则不更改`}
+          name="model_mapping"
+          onChange={(value) => {
+            handleInputChange('model_mapping', value);
+          }}
+          autosize
+          value={inputs.model_mapping}
+          autoComplete="new-password"
+        />
+        <Space>
+          <Typography.Text
+            style={{
+              color: 'rgba(var(--semi-blue-5), 1)',
+              userSelect: 'none',
+              cursor: 'pointer'
+            }}
+            onClick={() => {
+              handleInputChange(
+                'model_mapping',
+                JSON.stringify(MODEL_MAPPING_EXAMPLE, null, 2)
+              );
+            }}
+          >
+            填入模板
+          </Typography.Text>
+          <Typography.Text
+            style={{
+              color: 'rgba(var(--semi-blue-5), 1)',
+              userSelect: 'none',
+              cursor: 'pointer'
+            }}
+            onClick={() => {
+              handleInputChange(
+                'model_mapping',
+                JSON.stringify({}, null, 2)
+              );
+            }}
+          >
+            清空重定向
+          </Typography.Text>
+          <Typography.Text
+            style={{
+              color: 'rgba(var(--semi-blue-5), 1)',
+              userSelect: 'none',
+              cursor: 'pointer'
+            }}
+            onClick={() => {
+              handleInputChange(
+                'model_mapping',
+                ""
+              );
+            }}
+          >
+            不更改
+          </Typography.Text>
+        </Space>
+      </Spin>
+    </SideSheet>
+  );
+};
+
+export default EditTagModal;
--- a/web/src/pages/Setting/Operation/SettingsMagnification.js
+++ b/web/src/pages/Setting/Operation/SettingsMagnification.js
@@ -50,10 +50,17 @@ export default function SettingsMagnification(props) {
              if (res.includes(undefined))
                return showError('部分保存失败，请重试');
            }
+            for (let i = 0; i < res.length; i++) {
+              if (!res[i].data.success) {
+                return showError(res[i].data.message)
+              }
+            }
            showSuccess('保存成功');
            props.refresh();
          })
-          .catch(() => {
+          .catch(error => {
+            console.error('Unexpected error in Promise.all:', error);
+
            showError('保存失败，请重试');
          })
          .finally(() => {
Author	SHA1	Message	Date
Calcium-Ion	c645bf7eb0	Merge pull request #594 from Calcium-Ion/gzip fix: 标签分组功能开启时无法展开测试模型	2024-12-05 14:42:16 +08:00
CalciumIon	b5d273b680	fix: 标签分组功能开启时无法展开测试模型	2024-12-05 14:41:40 +08:00
Calcium-Ion	6b2f675308	Merge pull request #593 from Calcium-Ion/gzip feat: support br	2024-12-04 23:56:14 +08:00
CalciumIon	4c809277aa	feat: support br	2024-12-04 23:53:02 +08:00
Calcium-Ion	c75bc956b3	Merge pull request #592 from Calcium-Ion/gzip feat: support gzip	2024-12-04 23:25:19 +08:00
CalciumIon	3089af6b08	feat: support gzip	2024-12-04 23:24:46 +08:00
CalciumIon	d9b622c8ed	fix: email panic	2024-12-04 22:08:47 +08:00
Calcium-Ion	4937a6d1ed	Merge pull request #591 from Calcium-Ion/no-cache feat: add Cache-Control header to API requests	2024-12-04 20:53:22 +08:00
CalciumIon	de9a0d65ae	feat: add Cache-Control header to API requests	2024-12-04 20:51:55 +08:00
Calcium-Ion	ee99041910	Merge pull request #590 from iszcz/new512 realtime令牌额度检测和http	2024-12-04 19:49:57 +08:00
iszcz	c8a29251ac	1	2024-12-04 16:20:42 +08:00
CalciumIon	07b1c9a4db	Update docker-compose.yml	2024-12-03 16:48:38 +08:00
Calcium-Ion	5d8de46e4c	Merge pull request #589 from mrhaoji/main fix: 360智脑接口地址更新	2024-12-03 13:41:14 +08:00
Benny	28885feea2	fix: 360智能接口地址更新	2024-12-02 15:59:08 +00:00
Calcium-Ion	f693c13ce6	Merge pull request #588 from iszcz/new512 渠道tag编辑名称	2024-12-01 23:14:35 +08:00
iszcz	89cd0db28c	Update EditTagModal.js	2024-12-01 22:36:51 +08:00
Calcium-Ion	ae57dd7b8b	Update README.md	2024-12-01 21:58:36 +08:00
CalciumIon	87d763e641	Merge remote-tracking branch 'origin/main'	2024-12-01 13:59:13 +08:00
Calcium-Ion	08f3562e53	Merge pull request #587 from Calcium-Ion/channel-tag feat: add tag aggregation mode to channels API and UI	2024-12-01 09:25:43 +08:00
CalciumIon	88b0e6a768	feat: add tag aggregation mode to channels API and UI	2024-12-01 09:24:43 +08:00
CalciumIon	a9f739a7e2	refactor: improve validation logic and error handling in relay-text.go - Simplified validation checks for MaxTokens and Messages fields. - Enhanced error messages for better clarity. - Updated goroutine to avoid passing context unnecessarily.	2024-12-01 08:24:41 +08:00
CalciumIon	6d4edc1f5b	fix: realtime	2024-11-30 23:32:42 +08:00
CalciumIon	2d1b2676f7	Update docker-compose.yml	2024-11-30 21:36:34 +08:00
CalciumIon	1035a8e0df	Update README.md	2024-11-30 20:47:26 +08:00
Calcium-Ion	ea433b2ed6	Merge pull request #586 from Calcium-Ion/channel-tag fix: tag channel copy	2024-11-30 19:52:58 +08:00
CalciumIon	bb0c504709	fix: tag channel copy	2024-11-30 19:52:36 +08:00
Calcium-Ion	48abfd055c	Merge pull request #574 from Calcium-Ion/channel-tag feat: 初步集成渠道标签分组功能	2024-11-30 17:45:16 +08:00
CalciumIon	6693072c49	feat: 完善标签编辑（优先级，权重）	2024-11-30 17:43:03 +08:00
CalciumIon	3053d94170	feat: 完善标签编辑	2024-11-30 16:57:58 +08:00
CalciumIon	1774be8536	fix: xAI missing finish_reason #572	2024-11-30 16:57:57 +08:00
Calcium-Ion	821f3a7522	Merge pull request #582 from prnake/patch-1 feat: add claude-3-5-haiku-20241022	2024-11-30 15:07:31 +08:00
CalciumIon	9c4d30602c	feat: 完善标签编辑	2024-11-29 23:58:31 +08:00
CalciumIon	7b3394d863	chore: update default STREAMING_TIMEOUT	2024-11-28 23:59:10 +08:00
papersnake	999ba11363	feat: add claude-3-5-haiku-20241022	2024-11-27 13:33:37 +08:00
CalciumIon	7ebc1cfb60	fix: stt模型计费	2024-11-25 19:31:59 +08:00
Calcium-Ion	b71e33b095	Update README.md	2024-11-24 16:51:46 +08:00
CalciumIon	15842163be	feat: support audio response_format #580	2024-11-24 16:44:27 +08:00
CalciumIon	e57788375e	Update README.md	2024-11-23 16:58:57 +08:00
CalciumIon	78cac7085c	Update README.md	2024-11-23 16:38:59 +08:00
Calcium-Ion	76f7474640	Merge pull request #579 from HynoR/main Chore: support gpt-4o-2024-11-20	2024-11-23 16:34:41 +08:00
CalciumIon	0dd1953cd6	Update BT.md	2024-11-23 16:33:24 +08:00
Calcium-Ion	019361a762	Update BT.md	2024-11-23 16:28:06 +08:00
CalciumIon	9b9d73e725	Update README.md	2024-11-23 16:27:39 +08:00
CalciumIon	9e08709756	chore: Update docker-compose.yml	2024-11-23 16:26:30 +08:00
CalciumIon	05b5d6f255	Update README.md	2024-11-23 16:26:15 +08:00
HynoR	79b6c0a73e	Chore: support gpt-4o-2024-11-20	2024-11-21 09:14:23 +08:00
Calcium-Ion	462c2cc1a1	Merge pull request #493 from xixingya/feature/bug-fix ratio must gte 0	2024-11-19 18:34:24 +08:00
CalciumIon	e8286e479b	chore: go.mod	2024-11-19 15:14:40 +08:00
CalciumIon	ed2ec69545	feat: 暂时禁用透传功能	2024-11-19 15:06:54 +08:00
CalciumIon	a167dd9a23	feat: 暂时禁用透传功能	2024-11-19 15:04:19 +08:00
CalciumIon	6e6e390f6f	feat: 一键编辑标签下渠道重定向	2024-11-19 01:43:05 +08:00
CalciumIon	807385d3d1	fix: search channel #442	2024-11-19 01:39:27 +08:00
CalciumIon	0ce600ed49	feat: 渠道标签分组	2024-11-19 01:13:18 +08:00
CalciumIon	334a2424e9	fix: oauth aff	2024-11-18 18:53:55 +08:00
CalciumIon	7db703374c	fix: oauth aff	2024-11-18 18:52:14 +08:00
Calcium-Ion	6a42ccf00e	Merge pull request #569 from utopeadia/main Modify the default gemini API to v1beta	2024-11-17 16:27:38 +08:00
Calcium-Ion	7aa7114bb9	Merge branch 'main' into main	2024-11-17 16:27:29 +08:00
Calcium-Ion	c3e6b2408e	Merge pull request #570 from leezhuuuuu/main 增加对于gemini-exp-1114模型的支持，映射到v1beta	2024-11-17 16:26:36 +08:00
leezhuuuuu	4601932902	feat: add support for gemini-exp-1114 model / 添加 gemini-exp-1114 模型支持 # feat: add support for gemini-exp-1114 model / 添加 gemini-exp-1114 模型支持 ## Changes / 更改内容 - Add gemini-exp-1114 to ModelList in constant.go - Add gemini-exp-1114 to GeminiModelMap with v1beta API version - 在 constant.go 的 ModelList 中添加 gemini-exp-1114 模型 - 在 GeminiModelMap 中添加 gemini-exp-1114 的 v1beta API 版本映射 ## Testing / 测试情况 - [x] Tested gemini-exp-1114 model API calls / 已测试 gemini-exp-1114 模型的 API 调用 - [x] Verified existing models still work / 验证现有模型仍然正常工作 - [x] Confirmed v1beta API version works correctly / 确认 v1beta API 版本正常工作 ## Related Issues / 相关问题 - Fix 404 error when calling gemini-exp-1114 model / 修复调用 gemini-exp-1114 模型时的 404 错误 ## Implementation Details / 实现细节 - Use configuration-based approach instead of code modification / 使用基于配置的方式而不是修改代码 - Maintain clean separation of concerns / 保持关注点分离 - Keep backward compatibility / 保持向后兼容性 ## Notes / 注意事项 - This PR follows the principle of minimal invasion / 本 PR 遵循最小侵入原则 - Configuration changes only / 仅包含配置更改	2024-11-16 21:52:37 +08:00
leezhuuuuu	5d96f7b2cc	增加对于gemini-exp-1114模型的支持，映射到v1beta feat(gemini): add support for gemini-exp-1114 model - Add gemini-exp-1114 to ModelList in constant.go - Update GetRequestURL in adaptor.go to use v1beta API version for gemini-exp-1114 - Keep backward compatibility for other models This change enables the use of the experimental gemini-exp-1114 model by correctly routing its requests to the v1beta API endpoint while maintaining existing functionality for other models.	2024-11-16 21:29:35 +08:00
HowieWood	8eb32e9b3f	Modify the default gemini API to v1beta	2024-11-16 12:21:50 +00:00
CalciumIon	320e6ec5a4	fix: aws claude	2024-11-14 15:12:34 +08:00
liuzhifei	e0f19e5ed7	ratio must gte 0	2024-09-20 18:33:17 +08:00
liuzhifei	3d33079de0	ratio must gte 0	2024-09-20 18:27:16 +08:00
liuzhifei	1d064a2e88	ratio must gte 0	2024-09-20 18:09:40 +08:00
liuzhifei	4eae3b2177	ratio must gte 0	2024-09-20 17:51:42 +08:00