docs: update readme

feat: update feishu oauth login
feat: support gzip decode (#1962 )
2026-02-19 04:14:24 +08:00 · 2024-12-21 00:33:20 +08:00 · 2024-12-20 23:27:00 +08:00 · 2024-12-04 23:34:24 +08:00 · 2024-11-10 17:18:46 +08:00 · 2024-11-10 15:09:02 +08:00
71 changed files with 639 additions and 731 deletions
--- a/.computenest/.computenest_parameters.yaml
+++ b/.computenest/.computenest_parameters.yaml
@@ -1 +0,0 @@
 {"ServicePort":"80","SecurityPorts":[80],"RepoName":"hanans426/one-api","Arch":"EcsSingle","RunCommand":"echo \"start run command\"\necho \"${AdminPassword}\"\n","SourceCodePath":".","CommandTimeout":3600,"ServiceType":"private","AllowedRegions":["cn-hangzhou","cn-shanghai","cn-beijing"],"ArtifactSourceType":"SourceCode","ImageId":"centos_7_9_x64_20G_alibase_20230613.vhd","RegionId":"cn-hangzhou","CustomParameters":[{"NoEcho":true,"Type":"String","AssociationProperty":"ALIYUN::ECS::Instance::Password","Label":"管理员密码","Name":"AdminPassword"}]}
--- a/.computenest/README.md
+++ b/.computenest/README.md
@@ -1,21 +0,0 @@
 # 代码仓库结构
 ## 文档目录说明：
 ```
 .
 ├── README.md                   - README
 ├── docs                        - 服务文档相关文件
 │   └── index.md
 ├── resources                   - 服务资源文件
 │   ├── icons
 │   │   └── service_logo.png    - 服务logo
 │   └── artifact_resources      - 部署物相关资源文件
 ├── ros_templates               - 服务ROS模板目录，支持多模板
 │   └── template.yaml           - ROS模板，ROS模板引擎根据该模板会自动创建出所有的资源
 ├── config.yaml                 - 服务配置文件，服务构建过程中会使用计算巢命令行工具computenest-cli，computenest-cli会基于该配置文件构建服务
 ├── preset_parameters.yaml      - （该文件只有托管版有）服务商预设参数，如VpcId，VSwitchId等，该ros模板内容会渲染为表单方便服务商填写
 ```
 ## 其他
 关于ROS模板，请参见 [资源编排](https://help.aliyun.com/zh/ros)。
 关于computenest-cli请参见 [computenest-cli](https://pypi.org/project/computenest-cli/)。
--- a/.computenest/config.yaml
+++ b/.computenest/config.yaml
@@ -1,28 +0,0 @@
 Service:
  RegionId: cn-hangzhou
  DeployType: ros
  DeployMetadata:
    SupplierDeployMetadata:
      FileArtifactRelation:
        '{{ computenest::file::hanans426_one-api }}':
          ArtifactId: ${Artifact.Artifact_1.ArtifactId}
          ArtifactVersion: ${Artifact.Artifact_1.ArtifactVersion}
    TemplateConfigs:
      - Name: 单机版
        Url: 'ros_templates/template.yaml'
        AllowedRegions:
          - cn-hangzhou
          - cn-shanghai
          - cn-beijing
  ServiceType: private
  ServiceInfo:
    Locale: zh-CN
    ShortDescription: demo
    Image: 'resources/icons/service_logo.png'
 Artifact:
  Artifact_1:
    ArtifactType: File
    ArtifactName: hanans426_one-api
    ArtifactProperty:
      RegionId: cn-hangzhou
      Url: 'resources/artifact_resources/file/hanans426_one-api.tar.gz'
--- a/.computenest/docs/architecture_ecs_single.png
+++ b/.computenest/docs/architecture_ecs_single.png
--- a/.computenest/docs/index_ecs_single.md
+++ b/.computenest/docs/index_ecs_single.md
@@ -1,70 +0,0 @@
 # 服务模板说明文档
 ## 服务说明
 **简单描述服务的功能和用途。**  
 例如：  
 _（服务功能描述，如“WordPress 是一款免费开源的 CMS，适用于创建和管理各种类型的网站。”）_
 _（服务快速上手链接或文档，如果有的话）_
 ## 服务架构
 此服务模板构建出的服务的部署架构为单机ecs部署。
 <img src="architecture_ecs_single.png" width="600" height="400" align="bottom"/>
 ## 计费说明
 通过此服务模板构建服务不产生费用。  
 用户部署构建出的服务时，资源费用主要涉及：
 - 所选ECS实例规格
 - 磁盘容量
 - 公网带宽
 计费方式包括：
 - 按量付费（小时）
 - 包年包月
 预估费用在部署前可实时看到。
 ## RAM账号所需权限
 此服务模板构建出的服务需要对ECS、VPC等资源进行访问和创建操作，若使用RAM用户创建服务实例，需要在创建服务实例前，对使用的RAM用户的账号添加相应资源的权限。添加RAM权限的详细操作，请参见[为RAM用户授权](https://help.aliyun.com/document_detail/121945.html)。所需权限如下表所示：
 | 权限策略名称                              | 备注                            |
 |-------------------------------------|-------------------------------|
 | AliyunECSFullAccess                 | 管理云服务器服务（ECS）的权限              |
 | AliyunVPCFullAccess                 | 管理专有网络（VPC）的权限                |
 | AliyunROSFullAccess                 | 管理资源编排服务（ROS）的权限              |
 | AliyunComputeNestUserFullAccess     | 管理计算巢服务（ComputeNest）的用户侧权限    |
 | AliyunComputeNestSupplierFullAccess | 管理计算巢服务（ComputeNest）的服务商侧权限 ｜ |
 ## 服务实例计费说明
 **详细说明服务实例的计费方式。**  
 _（描述费用构成，例如所选 vCPU 和内存规格，系统盘类型和容量等）_
 _（列出计费方式，例如按量付费或包年包月）_
 ## 服务实例部署流程
 ### 部署参数说明
 | 参数组                             | 参数项    | 说明                                                                      |
 |---------------------------------|--------|-------------------------------------------------------------------------|
 | 服务实例                            | 服务实例名称 | 长度不超过64个字符，必须以英文字母开头，可包含数字、英文字母、短划线（-）和下划线（_）。                          |
 |                                 | 地域     | 服务实例部署的地域。                                                              |
 |                                 | 付费类型   | 资源的计费类型：按量付费和包年包月。                                                      |
 | ECS实例配置                         | 实例类型   | ECS实例规格配置。                                                              |
 |                                 | 实例密码   | 长度8-30，必须包含三项（大写字母、小写字母、数字、 ()`~!@#$%^&*-+=&#124;{}[]:;'<>,.?/ 中的特殊符号）。 |
 | 网络配置                            | 可用区    | ECS实例所在可用区。                                                             |
 ### 部署步骤
 **简述如何一步步部署服务实例。**  
 1. _（步骤1描述和相关链接或图片，如果有的话）_
 2. _（步骤2描述和相关链接或图片，如果有的话）_
 ...
 [部署链接](部署链接地址)
--- a/.computenest/resources/artifact_resources/file/hanans426_one-api.tar.gz
+++ b/.computenest/resources/artifact_resources/file/hanans426_one-api.tar.gz
--- a/.computenest/resources/icons/service_logo.png
+++ b/.computenest/resources/icons/service_logo.png
--- a/.computenest/ros_templates/template.yaml
+++ b/.computenest/ros_templates/template.yaml
@@ -1,218 +0,0 @@
 ROSTemplateFormatVersion: '2015-09-01'
 Description:
  en: Source Code Service Ros Template
  zh-cn: 源代码服务模板
 Parameters:
  PayType:
    Type: String
    Label:
      en: ECS Instance Charge Type
      zh-cn: 付费类型
    Default: PostPaid
    AllowedValues:
      - PostPaid
      - PrePaid
    AssociationProperty: ChargeType
    AssociationPropertyMetadata:
      LocaleKey: InstanceChargeType
  PayPeriodUnit:
    Type: String
    Label:
      en: Pay Period Unit
      zh-cn: 购买资源时长周期
    Default: Month
    AllowedValues:
      - Month
      - Year
    AssociationProperty: PayPeriodUnit
    AssociationPropertyMetadata:
      Visible:
        Condition:
          Fn::Not:
            Fn::Equals:
              - ${PayType}
              - PostPaid
  PayPeriod:
    Type: Number
    Label:
      en: Period
      zh-cn: 购买资源时长
    Default: 1
    AllowedValues:
      - 1
      - 2
      - 3
      - 4
      - 5
      - 6
      - 7
      - 8
      - 9
    AssociationProperty: PayPeriod
    AssociationPropertyMetadata:
      Visible:
        Condition:
          Fn::Not:
            Fn::Equals:
              - ${PayType}
              - PostPaid
  EcsInstanceType:
    Type: String
    Label:
      en: Instance Type
      zh-cn: 实例类型
    AssociationProperty: ALIYUN::ECS::Instance::InstanceType
    AssociationPropertyMetadata:
      InstanceChargeType: ${PayType}
      Constraints:
        InstanceTypeFamily:
          - ecs.u1
          - ecs.e
  InstancePassword:
    NoEcho: true
    Type: String
    Description:
      en: Server login password, Length 8-30, must contain three(Capital letters, lowercase letters, numbers, ()`~!@#$%^&*_-+=|{}[]:;'<>,.?/ Special symbol in)
      zh-cn: 服务器登录密码,长度8-30，必须包含三项（大写字母、小写字母、数字、 ()`~!@#$%^&*_-+=|{}[]:;'<>,.?/ 中的特殊符号）
    AllowedPattern: '^[a-zA-Z0-9-\(\)\`\~\!\@\#\$\%\^\&\*\_\-\+\=\|\{\}\[\]\:\;\<\>\,\.\?\/]*$'
    Label:
      en: Instance Password
      zh-cn: 实例密码
    ConstraintDescription:
      en: Length 8-30, must contain three(Capital letters, lowercase letters, numbers, ()`~!@#$%^&*_-+=|{}[]:;'<>,.?/ Special symbol in)
      zh-cn: 长度8-30，必须包含三项（大写字母、小写字母、数字、 ()`~!@#$%^&*_-+=|{}[]:;'<>,.?/ 中的特殊符号）
    MinLength: 8
    MaxLength: 30
    AssociationProperty: ALIYUN::ECS::Instance::Password
  ZoneId:
    Type: String
    Label:
      en: Zone ID
      zh-cn: 可用区ID
    AssociationProperty: ALIYUN::ECS::Instance::ZoneId
  VpcId:
    Type: String
    Label:
      en: VPC ID
      zh-cn: 专有网络VPC实例ID
    AssociationProperty: 'ALIYUN::ECS::VPC::VPCId'
  VSwitchId:
    Type: String
    Label:
      en: VSwitch ID
      zh-cn: 交换机实例ID
    Default: ''
    AssociationProperty: 'ALIYUN::ECS::VSwitch::VSwitchId'
    AssociationPropertyMetadata:
      VpcId: VpcId
      ZoneId: ZoneId
  AdminPassword:
    Type: String
    AssociationProperty: ALIYUN::ECS::Instance::Password
    Label: 管理员密码
    NoEcho: True
 Resources:
  SecurityGroup:
    Type: ALIYUN::ECS::SecurityGroup
    Properties:
      SecurityGroupName:
        Ref: ALIYUN::StackName
      VpcId:
        Ref: VpcId
      SecurityGroupIngress:
        - PortRange: 80/80
          Priority: 1
          SourceCidrIp: 0.0.0.0/0
          IpProtocol: tcp
          NicType: internet
  InstanceGroup:
    Type: ALIYUN::ECS::InstanceGroup
    Properties:
      # 付费类型
      InstanceChargeType:
        Ref: PayType
      PeriodUnit:
        Ref: PayPeriodUnit
      Period:
        Ref: PayPeriod
      VpcId:
        Ref: VpcId
      VSwitchId:
        Ref: VSwitchId
      ZoneId:
        Ref: ZoneId
      SecurityGroupId:
        Ref: SecurityGroup
      ImageId: centos_7_9_x64_20G_alibase_20230613.vhd
      Password:
        Ref: InstancePassword
      InstanceType:
        Ref: EcsInstanceType
      SystemDiskCategory: cloud_essd
      SystemDiskSize: 200
      InternetMaxBandwidthOut: 5
      IoOptimized: optimized
      MaxAmount: 1
  RunInstallCommand:
    Type: ALIYUN::ECS::RunCommand
    Properties:
      InstanceIds:
        Fn::GetAtt:
        - InstanceGroup
        - InstanceIds
      Type: RunShellScript
      Sync: true
      Timeout: 3600
      CommandContent:
        Fn::Sub:
          - |
            #!/bin/bash
            # 源代码通过computenest-cli被打包为tar.gz包，并发布为部署物
            wget '{{ computenest::file::hanans426_one-api }}' -O hanans426_one-api.tar.gz > /var/log/download.log
            tar -zxvf hanans426_one-api.tar.gz && cd "$(tar -tzf hanans426_one-api.tar.gz | head -1 | awk -F'/' '{print $1}')"
            echo "start run command"
            echo "${AdminPassword}"
            ARGUS_VERSION=3.5.7 /bin/bash -c "$(curl -sS https://cms-agent-${RegionId}.oss-${RegionId}-internal.aliyuncs.com/Argus/agent_install_ecs-1.7.sh)" >> /root/install_cms_agent.log 2>&1
          - RegionId:
              Ref: ALIYUN::Region
 Outputs:
  ServerAddress:
    Description:
      en: ServerAddress.
      zh-cn: 访问页面。
    Value:
      Fn::Sub:
        - 'http://${ServerAddress}:80'
        - ServerAddress:
            Fn::Select:
            - 0
            - Fn::GetAtt:
              - InstanceGroup
              - PublicIps
 Metadata:
  ALIYUN::ROS::Interface:
    ParameterGroups:
      - Parameters:
          - PayType
          - PayPeriodUnit
          - PayPeriod
        Label:
          default: 付费类型配置
      - Parameters:
          - EcsInstanceType
          - InstancePassword
        Label:
          default: 资源配置
      - Parameters:
          - ZoneId
          - VpcId
          - VSwitchId
        Label:
          default: 可用区配置
      - Parameters:
          - AdminPassword
        Label:
          en: Software Configuration
          zh-cn: 软件配置
--- a/README.en.md
+++ b/README.en.md
@@ -204,17 +204,6 @@ If you encounter a blank page after deployment, refer to [#97](https://github.co
 </div>
 </details>
 <details>
 <summary><strong>Deployment on Aliyun</strong></summary>
 <div>
 > Aliyun support one-click deployment to a dedicated VPC.。
 Aliyun support the fast deployment，[Deployment Link](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=One%20API%20%E7%A4%BE%E5%8C%BA%E7%89%88)
 </div>
 </details>
 ## Configuration
 The system is ready to use out of the box.
--- a/README.md
+++ b/README.md
@@ -90,6 +90,7 @@ _✨ 通过标准的 OpenAI API 格式访问所有的大模型，开箱即用
   + [x] [together.ai](https://www.together.ai/)
   + [x] [novita.ai](https://www.novita.ai/)
   + [x] [硅基流动 SiliconCloud](https://siliconflow.cn/siliconcloud)
   + [x] [xAI](https://x.ai/)
 2. 支持配置镜像以及众多[第三方代理服务](https://iamazing.cn/page/openai-api-third-party-services)。
 3. 支持通过**负载均衡**的方式访问多个渠道。
 4. 支持 **stream 模式**，可以通过流式传输实现打字机效果。
@@ -114,8 +115,8 @@ _✨ 通过标准的 OpenAI API 格式访问所有的大模型，开箱即用
 21. 支持 Cloudflare Turnstile 用户校验。
 22. 支持用户管理，支持**多种用户登录注册方式**：
    + 邮箱登录注册（支持注册邮箱白名单）以及通过邮箱进行密码重置。
-    + 支持使用飞书进行授权登录。
+    + 支持[飞书授权登录](https://open.feishu.cn/document/uAjLw4CM/ukTMukTMukTM/reference/authen-v1/authorize/get)（[这里有 One API 的实现细节阐述供参考](https://iamazing.cn/page/feishu-oauth-login)）。
-    + [GitHub 开放授权](https://github.com/settings/applications/new)。
+    + 支持 [GitHub 授权登录](https://github.com/settings/applications/new)。
    + 微信公众号授权（需要额外部署 [WeChat Server](https://github.com/songquanpeng/wechat-server)）。
 23. 支持主题切换，设置环境变量 `THEME` 即可，默认为 `default`，欢迎 PR 更多主题，具体参考[此处](./web/README.md)。
 24. 配合 [Message Pusher](https://github.com/songquanpeng/message-pusher) 可将报警信息推送到多种 App 上。
@@ -302,17 +303,6 @@ Render 可以直接部署 docker 镜像，不需要 fork 仓库：https://dashbo
 </div>
 </details>
 <details>
 <summary><strong>部署到阿里云</strong></summary>
 <div>
 > 阿里云支持一键部署到专属VPC。
 阿里云支持快速一键部署，[部署链接](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=One%20API%20%E7%A4%BE%E5%8C%BA%E7%89%88)
 </div>
 </details>
 ## 配置
 系统本身开箱即用。
@@ -410,6 +400,7 @@ graph LR
 26. `METRIC_SUCCESS_RATE_THRESHOLD`：请求成功率阈值，默认为 `0.8`。
 27. `INITIAL_ROOT_TOKEN`：如果设置了该值，则在系统首次启动时会自动创建一个值为该环境变量值的 root 用户令牌。
 28. `INITIAL_ROOT_ACCESS_TOKEN`：如果设置了该值，则在系统首次启动时会自动创建一个值为该环境变量的 root 用户创建系统管理令牌。
 29. `ENFORCE_INCLUDE_USAGE`：是否强制在 stream 模型下返回 usage，默认不开启，可选值为 `true` 和 `false`。
 ### 命令行参数
 1. `--port <port_number>`: 指定服务器监听的端口号，默认为 `3000`。
--- a/common/config/config.go
+++ b/common/config/config.go
@@ -160,3 +160,5 @@ var OnlyOneLogFile = env.Bool("ONLY_ONE_LOG_FILE", false)
 var RelayProxy = env.String("RELAY_PROXY", "")
 var UserContentRequestProxy = env.String("USER_CONTENT_REQUEST_PROXY", "")
 var UserContentRequestTimeout = env.Int("USER_CONTENT_REQUEST_TIMEOUT", 30)
 var EnforceIncludeUsage = env.Bool("ENFORCE_INCLUDE_USAGE", false)
--- a/common/ctxkey/key.go
+++ b/common/ctxkey/key.go
@@ -20,4 +20,5 @@ const (
 	BaseURL           = "base_url"
 	AvailableModels   = "available_models"
 	KeyRequestBody    = "key_request_body"
 	SystemPrompt      = "system_prompt"
 )
--- a/common/helper/helper.go
+++ b/common/helper/helper.go
@@ -137,3 +137,23 @@ func String2Int(str string) int {
 	}
 	return num
 }
 func Float64PtrMax(p *float64, maxValue float64) *float64 {
 	if p == nil {
 		return nil
 	}
 	if *p > maxValue {
 		return &maxValue
 	}
 	return p
 }
 func Float64PtrMin(p *float64, minValue float64) *float64 {
 	if p == nil {
 		return nil
 	}
 	if *p < minValue {
 		return &minValue
 	}
 	return p
 }
--- a/controller/auth/lark.go
+++ b/controller/auth/lark.go
@@ -40,7 +40,7 @@ func getLarkUserInfoByCode(code string) (*LarkUser, error) {
 	if err != nil {
 		return nil, err
 	}
-	req, err := http.NewRequest("POST", "https://passport.feishu.cn/suite/passport/oauth/token", bytes.NewBuffer(jsonData))
+	req, err := http.NewRequest("POST", "https://open.feishu.cn/open-apis/authen/v2/oauth/token", bytes.NewBuffer(jsonData))
 	if err != nil {
 		return nil, err
 	}
--- a/controller/channel-test.go
+++ b/controller/channel-test.go
@@ -76,9 +76,9 @@ func testChannel(channel *model.Channel, request *relaymodel.GeneralOpenAIReques
 		if len(modelNames) > 0 {
 			modelName = modelNames[0]
 		}
-		if modelMap != nil && modelMap[modelName] != "" {
+	}
-			modelName = modelMap[modelName]
+	if modelMap != nil && modelMap[modelName] != "" {
-		}
+		modelName = modelMap[modelName]
 	}
 	meta.OriginModelName, meta.ActualModelName = request.Model, modelName
 	request.Model = modelName
--- a/middleware/distributor.go
+++ b/middleware/distributor.go
@@ -61,6 +61,9 @@ func SetupContextForSelectedChannel(c *gin.Context, channel *model.Channel, mode
 	c.Set(ctxkey.Channel, channel.Type)
 	c.Set(ctxkey.ChannelId, channel.Id)
 	c.Set(ctxkey.ChannelName, channel.Name)
 	if channel.SystemPrompt != nil && *channel.SystemPrompt != "" {
 		c.Set(ctxkey.SystemPrompt, *channel.SystemPrompt)
 	}
 	c.Set(ctxkey.ModelMapping, channel.GetModelMapping())
 	c.Set(ctxkey.OriginalModel, modelName) // for retry
 	c.Request.Header.Set("Authorization", fmt.Sprintf("Bearer %s", channel.Key))
--- a/middleware/gzip.go
+++ b/middleware/gzip.go
@@ -0,0 +1,27 @@
 package middleware
 import (
 	"compress/gzip"
 	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 )
 func GzipDecodeMiddleware() gin.HandlerFunc {
 	return func(c *gin.Context) {
 		if c.GetHeader("Content-Encoding") == "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)
 		}
 		// Continue processing the request
 		c.Next()
 	}
 }
--- a/model/channel.go
+++ b/model/channel.go
@@ -37,6 +37,7 @@ type Channel struct {
 	ModelMapping       *string `json:"model_mapping" gorm:"type:varchar(1024);default:''"`
 	Priority           *int64  `json:"priority" gorm:"bigint;default:0"`
 	Config             string  `json:"config"`
 	SystemPrompt       *string `json:"system_prompt" gorm:"type:text"`
 }
 type ChannelConfig struct {
--- a/BIN
+++ b/BIN
--- a/relay/adaptor/ali/main.go
+++ b/relay/adaptor/ali/main.go
@@ -36,9 +36,7 @@ func ConvertRequest(request model.GeneralOpenAIRequest) *ChatRequest {
 		enableSearch = true
 		aliModel = strings.TrimSuffix(aliModel, EnableSearchModelSuffix)
 	}
-	if request.TopP >= 1 {
+	request.TopP = helper.Float64PtrMax(request.TopP, 0.9999)
 		request.TopP = 0.9999
 	}
 	return &ChatRequest{
 		Model: aliModel,
 		Input: Input{
--- a/relay/adaptor/ali/model.go
+++ b/relay/adaptor/ali/model.go
@@ -16,13 +16,13 @@ type Input struct {
 }
 type Parameters struct {
-	TopP              float64      `json:"top_p,omitempty"`
+	TopP              *float64     `json:"top_p,omitempty"`
 	TopK              int          `json:"top_k,omitempty"`
 	Seed              uint64       `json:"seed,omitempty"`
 	EnableSearch      bool         `json:"enable_search,omitempty"`
 	IncrementalOutput bool         `json:"incremental_output,omitempty"`
 	MaxTokens         int          `json:"max_tokens,omitempty"`
-	Temperature       float64      `json:"temperature,omitempty"`
+	Temperature       *float64     `json:"temperature,omitempty"`
 	ResultFormat      string       `json:"result_format,omitempty"`
 	Tools             []model.Tool `json:"tools,omitempty"`
 }
--- a/relay/adaptor/anthropic/constants.go
+++ b/relay/adaptor/anthropic/constants.go
@@ -3,7 +3,11 @@ package anthropic
 var ModelList = []string{
 	"claude-instant-1.2", "claude-2.0", "claude-2.1",
 	"claude-3-haiku-20240307",
 	"claude-3-5-haiku-20241022",
 	"claude-3-sonnet-20240229",
 	"claude-3-opus-20240229",
 	"claude-3-5-sonnet-20240620",
 	"claude-3-5-sonnet-20241022",
 	"claude-3-5-sonnet-latest",
 	"claude-3-5-haiku-20241022",
 }
--- a/relay/adaptor/anthropic/model.go
+++ b/relay/adaptor/anthropic/model.go
@@ -48,8 +48,8 @@ type Request struct {
 	MaxTokens     int       `json:"max_tokens,omitempty"`
 	StopSequences []string  `json:"stop_sequences,omitempty"`
 	Stream        bool      `json:"stream,omitempty"`
-	Temperature   float64   `json:"temperature,omitempty"`
+	Temperature   *float64  `json:"temperature,omitempty"`
-	TopP          float64   `json:"top_p,omitempty"`
+	TopP          *float64  `json:"top_p,omitempty"`
 	TopK          int       `json:"top_k,omitempty"`
 	Tools         []Tool    `json:"tools,omitempty"`
 	ToolChoice    any       `json:"tool_choice,omitempty"`
--- a/relay/adaptor/aws/claude/main.go
+++ b/relay/adaptor/aws/claude/main.go
@@ -29,10 +29,13 @@ var AwsModelIDMap = map[string]string{
 	"claude-instant-1.2":         "anthropic.claude-instant-v1",
 	"claude-2.0":                 "anthropic.claude-v2",
 	"claude-2.1":                 "anthropic.claude-v2:1",
 	"claude-3-sonnet-20240229":   "anthropic.claude-3-sonnet-20240229-v1:0",
 	"claude-3-5-sonnet-20240620": "anthropic.claude-3-5-sonnet-20240620-v1:0",
 	"claude-3-opus-20240229":     "anthropic.claude-3-opus-20240229-v1:0",
 	"claude-3-haiku-20240307":    "anthropic.claude-3-haiku-20240307-v1:0",
 	"claude-3-sonnet-20240229":   "anthropic.claude-3-sonnet-20240229-v1:0",
 	"claude-3-opus-20240229":     "anthropic.claude-3-opus-20240229-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-sonnet-latest":   "anthropic.claude-3-5-sonnet-20241022-v2:0",
 	"claude-3-5-haiku-20241022":  "anthropic.claude-3-5-haiku-20241022-v1:0",
 }
 func awsModelID(requestModel string) (string, error) {
--- a/relay/adaptor/aws/claude/model.go
+++ b/relay/adaptor/aws/claude/model.go
@@ -11,8 +11,8 @@ type Request struct {
 	Messages         []anthropic.Message `json:"messages"`
 	System           string              `json:"system,omitempty"`
 	MaxTokens        int                 `json:"max_tokens,omitempty"`
-	Temperature      float64             `json:"temperature,omitempty"`
+	Temperature      *float64            `json:"temperature,omitempty"`
-	TopP             float64             `json:"top_p,omitempty"`
+	TopP             *float64            `json:"top_p,omitempty"`
 	TopK             int                 `json:"top_k,omitempty"`
 	StopSequences    []string            `json:"stop_sequences,omitempty"`
 	Tools            []anthropic.Tool    `json:"tools,omitempty"`
--- a/relay/adaptor/aws/llama3/model.go
+++ b/relay/adaptor/aws/llama3/model.go
@@ -4,10 +4,10 @@ package aws
 //
 // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html
 type Request struct {
-	Prompt      string  `json:"prompt"`
+	Prompt      string   `json:"prompt"`
-	MaxGenLen   int     `json:"max_gen_len,omitempty"`
+	MaxGenLen   int      `json:"max_gen_len,omitempty"`
-	Temperature float64 `json:"temperature,omitempty"`
+	Temperature *float64 `json:"temperature,omitempty"`
-	TopP        float64 `json:"top_p,omitempty"`
+	TopP        *float64 `json:"top_p,omitempty"`
 }
 // Response is the response from AWS Llama3
--- a/relay/adaptor/baidu/main.go
+++ b/relay/adaptor/baidu/main.go
@@ -35,9 +35,9 @@ type Message struct {
 type ChatRequest struct {
 	Messages        []Message `json:"messages"`
-	Temperature     float64   `json:"temperature,omitempty"`
+	Temperature     *float64  `json:"temperature,omitempty"`
-	TopP            float64   `json:"top_p,omitempty"`
+	TopP            *float64  `json:"top_p,omitempty"`
-	PenaltyScore    float64   `json:"penalty_score,omitempty"`
+	PenaltyScore    *float64  `json:"penalty_score,omitempty"`
 	Stream          bool      `json:"stream,omitempty"`
 	System          string    `json:"system,omitempty"`
 	DisableSearch   bool      `json:"disable_search,omitempty"`
--- a/relay/adaptor/cloudflare/model.go
+++ b/relay/adaptor/cloudflare/model.go
@@ -9,5 +9,5 @@ type Request struct {
 	Prompt      string          `json:"prompt,omitempty"`
 	Raw         bool            `json:"raw,omitempty"`
 	Stream      bool            `json:"stream,omitempty"`
-	Temperature float64         `json:"temperature,omitempty"`
+	Temperature *float64        `json:"temperature,omitempty"`
 }
--- a/relay/adaptor/cohere/main.go
+++ b/relay/adaptor/cohere/main.go
@@ -43,7 +43,7 @@ func ConvertRequest(textRequest model.GeneralOpenAIRequest) *Request {
 		K:                textRequest.TopK,
 		Stream:           textRequest.Stream,
 		FrequencyPenalty: textRequest.FrequencyPenalty,
-		PresencePenalty:  textRequest.FrequencyPenalty,
+		PresencePenalty:  textRequest.PresencePenalty,
 		Seed:             int(textRequest.Seed),
 	}
 	if cohereRequest.Model == "" {
--- a/relay/adaptor/cohere/model.go
+++ b/relay/adaptor/cohere/model.go
@@ -10,15 +10,15 @@ type Request struct {
 	PromptTruncation string        `json:"prompt_truncation,omitempty"` // 默认值为"AUTO"
 	Connectors       []Connector   `json:"connectors,omitempty"`
 	Documents        []Document    `json:"documents,omitempty"`
-	Temperature      float64       `json:"temperature,omitempty"` // 默认值为0.3
+	Temperature      *float64      `json:"temperature,omitempty"` // 默认值为0.3
 	MaxTokens        int           `json:"max_tokens,omitempty"`
 	MaxInputTokens   int           `json:"max_input_tokens,omitempty"`
 	K                int           `json:"k,omitempty"` // 默认值为0
-	P                float64       `json:"p,omitempty"` // 默认值为0.75
+	P                *float64      `json:"p,omitempty"` // 默认值为0.75
 	Seed             int           `json:"seed,omitempty"`
 	StopSequences    []string      `json:"stop_sequences,omitempty"`
-	FrequencyPenalty float64       `json:"frequency_penalty,omitempty"` // 默认值为0.0
+	FrequencyPenalty *float64      `json:"frequency_penalty,omitempty"` // 默认值为0.0
-	PresencePenalty  float64       `json:"presence_penalty,omitempty"`  // 默认值为0.0
+	PresencePenalty  *float64      `json:"presence_penalty,omitempty"`  // 默认值为0.0
 	Tools            []Tool        `json:"tools,omitempty"`
 	ToolResults      []ToolResult  `json:"tool_results,omitempty"`
 }
--- a/relay/adaptor/gemini/main.go
+++ b/relay/adaptor/gemini/main.go
@@ -4,11 +4,12 @@ import (
 	"bufio"
 	"encoding/json"
 	"fmt"
 	"github.com/songquanpeng/one-api/common/render"
 	"io"
 	"net/http"
 	"strings"
 	"github.com/songquanpeng/one-api/common/render"
 	"github.com/songquanpeng/one-api/common"
 	"github.com/songquanpeng/one-api/common/config"
 	"github.com/songquanpeng/one-api/common/helper"
@@ -28,6 +29,11 @@ const (
 	VisionMaxImageNum = 16
 )
 var mimeTypeMap = map[string]string{
 	"json_object": "application/json",
 	"text":        "text/plain",
 }
 // Setting safety to the lowest possible values since Gemini is already powerless enough
 func ConvertRequest(textRequest model.GeneralOpenAIRequest) *ChatRequest {
 	geminiRequest := ChatRequest{
@@ -56,6 +62,15 @@ func ConvertRequest(textRequest model.GeneralOpenAIRequest) *ChatRequest {
 			MaxOutputTokens: textRequest.MaxTokens,
 		},
 	}
 	if textRequest.ResponseFormat != nil {
 		if mimeType, ok := mimeTypeMap[textRequest.ResponseFormat.Type]; ok {
 			geminiRequest.GenerationConfig.ResponseMimeType = mimeType
 		}
 		if textRequest.ResponseFormat.JsonSchema != nil {
 			geminiRequest.GenerationConfig.ResponseSchema = textRequest.ResponseFormat.JsonSchema.Schema
 			geminiRequest.GenerationConfig.ResponseMimeType = mimeTypeMap["json_object"]
 		}
 	}
 	if textRequest.Tools != nil {
 		functions := make([]model.Function, 0, len(textRequest.Tools))
 		for _, tool := range textRequest.Tools {
--- a/relay/adaptor/gemini/model.go
+++ b/relay/adaptor/gemini/model.go
@@ -65,10 +65,12 @@ type ChatTools struct {
 }
 type ChatGenerationConfig struct {
-	Temperature     float64  `json:"temperature,omitempty"`
+	ResponseMimeType string   `json:"responseMimeType,omitempty"`
-	TopP            float64  `json:"topP,omitempty"`
+	ResponseSchema   any      `json:"responseSchema,omitempty"`
-	TopK            float64  `json:"topK,omitempty"`
+	Temperature      *float64 `json:"temperature,omitempty"`
-	MaxOutputTokens int      `json:"maxOutputTokens,omitempty"`
+	TopP             *float64 `json:"topP,omitempty"`
-	CandidateCount  int      `json:"candidateCount,omitempty"`
+	TopK             float64  `json:"topK,omitempty"`
-	StopSequences   []string `json:"stopSequences,omitempty"`
+	MaxOutputTokens  int      `json:"maxOutputTokens,omitempty"`
 	CandidateCount   int      `json:"candidateCount,omitempty"`
 	StopSequences    []string `json:"stopSequences,omitempty"`
 }
--- a/relay/adaptor/groq/constants.go
+++ b/relay/adaptor/groq/constants.go
@@ -4,14 +4,24 @@ package groq
 var ModelList = []string{
 	"gemma-7b-it",
 	"mixtral-8x7b-32768",
 	"llama3-8b-8192",
 	"llama3-70b-8192",
 	"gemma2-9b-it",
 	"llama-3.1-405b-reasoning",
 	"llama-3.1-70b-versatile",
 	"llama-3.1-8b-instant",
 	"llama-3.2-11b-text-preview",
 	"llama-3.2-11b-vision-preview",
 	"llama-3.2-1b-preview",
 	"llama-3.2-3b-preview",
 	"llama-3.2-11b-vision-preview",
 	"llama-3.2-90b-text-preview",
 	"llama-3.2-90b-vision-preview",
 	"llama-guard-3-8b",
 	"llama3-70b-8192",
 	"llama3-8b-8192",
 	"llama3-groq-70b-8192-tool-use-preview",
 	"llama3-groq-8b-8192-tool-use-preview",
 	"llava-v1.5-7b-4096-preview",
 	"mixtral-8x7b-32768",
 	"distil-whisper-large-v3-en",
 	"whisper-large-v3",
 	"whisper-large-v3-turbo",
 }
--- a/relay/adaptor/ollama/model.go
+++ b/relay/adaptor/ollama/model.go
@@ -1,14 +1,14 @@
 package ollama
 type Options struct {
-	Seed             int     `json:"seed,omitempty"`
+	Seed             int      `json:"seed,omitempty"`
-	Temperature      float64 `json:"temperature,omitempty"`
+	Temperature      *float64 `json:"temperature,omitempty"`
-	TopK             int     `json:"top_k,omitempty"`
+	TopK             int      `json:"top_k,omitempty"`
-	TopP             float64 `json:"top_p,omitempty"`
+	TopP             *float64 `json:"top_p,omitempty"`
-	FrequencyPenalty float64 `json:"frequency_penalty,omitempty"`
+	FrequencyPenalty *float64 `json:"frequency_penalty,omitempty"`
-	PresencePenalty  float64 `json:"presence_penalty,omitempty"`
+	PresencePenalty  *float64 `json:"presence_penalty,omitempty"`
-	NumPredict  	 int 	 `json:"num_predict,omitempty"`
+	NumPredict       int      `json:"num_predict,omitempty"`
-	NumCtx  	 int 	 `json:"num_ctx,omitempty"`
+	NumCtx           int      `json:"num_ctx,omitempty"`
 }
 type Message struct {
--- a/relay/adaptor/openai/adaptor.go
+++ b/relay/adaptor/openai/adaptor.go
@@ -75,6 +75,13 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.G
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
 	if request.Stream {
 		// always return usage in stream mode
 		if request.StreamOptions == nil {
 			request.StreamOptions = &model.StreamOptions{}
 		}
 		request.StreamOptions.IncludeUsage = true
 	}
 	return request, nil
 }
--- a/relay/adaptor/openai/compatible.go
+++ b/relay/adaptor/openai/compatible.go
@@ -11,9 +11,10 @@ import (
 	"github.com/songquanpeng/one-api/relay/adaptor/mistral"
 	"github.com/songquanpeng/one-api/relay/adaptor/moonshot"
 	"github.com/songquanpeng/one-api/relay/adaptor/novita"
 	"github.com/songquanpeng/one-api/relay/adaptor/siliconflow"
 	"github.com/songquanpeng/one-api/relay/adaptor/stepfun"
 	"github.com/songquanpeng/one-api/relay/adaptor/togetherai"
-	"github.com/songquanpeng/one-api/relay/adaptor/siliconflow"
+	"github.com/songquanpeng/one-api/relay/adaptor/xai"
 	"github.com/songquanpeng/one-api/relay/channeltype"
 )
@@ -32,6 +33,7 @@ var CompatibleChannels = []int{
 	channeltype.TogetherAI,
 	channeltype.Novita,
 	channeltype.SiliconFlow,
 	channeltype.XAI,
 }
 func GetCompatibleChannelMeta(channelType int) (string, []string) {
@@ -64,6 +66,8 @@ func GetCompatibleChannelMeta(channelType int) (string, []string) {
 		return "novita", novita.ModelList
 	case channeltype.SiliconFlow:
 		return "siliconflow", siliconflow.ModelList
 	case channeltype.XAI:
 		return "xai", xai.ModelList
 	default:
 		return "openai", ModelList
 	}
--- a/relay/adaptor/palm/model.go
+++ b/relay/adaptor/palm/model.go
@@ -19,11 +19,11 @@ type Prompt struct {
 }
 type ChatRequest struct {
-	Prompt         Prompt  `json:"prompt"`
+	Prompt         Prompt   `json:"prompt"`
-	Temperature    float64 `json:"temperature,omitempty"`
+	Temperature    *float64 `json:"temperature,omitempty"`
-	CandidateCount int     `json:"candidateCount,omitempty"`
+	CandidateCount int      `json:"candidateCount,omitempty"`
-	TopP           float64 `json:"topP,omitempty"`
+	TopP           *float64 `json:"topP,omitempty"`
-	TopK           int     `json:"topK,omitempty"`
+	TopK           int      `json:"topK,omitempty"`
 }
 type Error struct {
--- a/relay/adaptor/tencent/main.go
+++ b/relay/adaptor/tencent/main.go
@@ -39,8 +39,8 @@ func ConvertRequest(request model.GeneralOpenAIRequest) *ChatRequest {
 		Model:       &request.Model,
 		Stream:      &request.Stream,
 		Messages:    messages,
-		TopP:        &request.TopP,
+		TopP:        request.TopP,
-		Temperature: &request.Temperature,
+		Temperature: request.Temperature,
 	}
 }
--- a/relay/adaptor/vertexai/claude/adapter.go
+++ b/relay/adaptor/vertexai/claude/adapter.go
@@ -13,7 +13,12 @@ import (
 )
 var ModelList = []string{
-	"claude-3-haiku@20240307", "claude-3-opus@20240229", "claude-3-5-sonnet@20240620", "claude-3-sonnet@20240229",
+	"claude-3-haiku@20240307",
 	"claude-3-sonnet@20240229",
 	"claude-3-opus@20240229",
 	"claude-3-5-sonnet@20240620",
 	"claude-3-5-sonnet-v2@20241022",
 	"claude-3-5-haiku@20241022",
 }
 const anthropicVersion = "vertex-2023-10-16"
--- a/relay/adaptor/vertexai/claude/model.go
+++ b/relay/adaptor/vertexai/claude/model.go
@@ -11,8 +11,8 @@ type Request struct {
 	MaxTokens     int                 `json:"max_tokens,omitempty"`
 	StopSequences []string            `json:"stop_sequences,omitempty"`
 	Stream        bool                `json:"stream,omitempty"`
-	Temperature   float64             `json:"temperature,omitempty"`
+	Temperature   *float64            `json:"temperature,omitempty"`
-	TopP          float64             `json:"top_p,omitempty"`
+	TopP          *float64            `json:"top_p,omitempty"`
 	TopK          int                 `json:"top_k,omitempty"`
 	Tools         []anthropic.Tool    `json:"tools,omitempty"`
 	ToolChoice    any                 `json:"tool_choice,omitempty"`
--- a/relay/adaptor/vertexai/gemini/adapter.go
+++ b/relay/adaptor/vertexai/gemini/adapter.go
@@ -15,7 +15,7 @@ import (
 )
 var ModelList = []string{
-	"gemini-1.5-pro-001", "gemini-1.5-flash-001", "gemini-pro", "gemini-pro-vision",
+	"gemini-1.5-pro-001", "gemini-1.5-flash-001", "gemini-pro", "gemini-pro-vision", "gemini-1.5-pro-002", "gemini-1.5-flash-002", 
 }
 type Adaptor struct {
--- a/relay/adaptor/xai/constants.go
+++ b/relay/adaptor/xai/constants.go
@@ -0,0 +1,5 @@
 package xai
 var ModelList = []string{
 	"grok-beta",
 }
--- a/relay/adaptor/xunfei/constants.go
+++ b/relay/adaptor/xunfei/constants.go
@@ -7,5 +7,6 @@ var ModelList = []string{
 	"SparkDesk-v3.1",
 	"SparkDesk-v3.1-128K",
 	"SparkDesk-v3.5",
 	"SparkDesk-v3.5-32K",
 	"SparkDesk-v4.0",
 }
--- a/relay/adaptor/xunfei/main.go
+++ b/relay/adaptor/xunfei/main.go
@@ -283,7 +283,7 @@ func parseAPIVersionByModelName(modelName string) string {
 func apiVersion2domain(apiVersion string) string {
 	switch apiVersion {
 	case "v1.1":
-		return "general"
+		return "lite"
 	case "v2.1":
 		return "generalv2"
 	case "v3.1":
@@ -292,6 +292,8 @@ func apiVersion2domain(apiVersion string) string {
 		return "pro-128k"
 	case "v3.5":
 		return "generalv3.5"
 	case "v3.5-32K":
 		return "max-32k"
 	case "v4.0":
 		return "4.0Ultra"
 	}
@@ -303,7 +305,10 @@ func getXunfeiAuthUrl(apiVersion string, apiKey string, apiSecret string) (strin
 	domain := apiVersion2domain(apiVersion)
 	switch apiVersion {
 	case "v3.1-128K":
-		authUrl = buildXunfeiAuthUrl(fmt.Sprintf("wss://spark-api.xf-yun.com/%s/pro-128k", apiVersion), apiKey, apiSecret)
+		authUrl = buildXunfeiAuthUrl(fmt.Sprintf("wss://spark-api.xf-yun.com/chat/pro-128k"), apiKey, apiSecret)
 		break
 	case "v3.5-32K":
 		authUrl = buildXunfeiAuthUrl(fmt.Sprintf("wss://spark-api.xf-yun.com/chat/max-32k"), apiKey, apiSecret)
 		break
 	default:
 		authUrl = buildXunfeiAuthUrl(fmt.Sprintf("wss://spark-api.xf-yun.com/%s/chat", apiVersion), apiKey, apiSecret)
--- a/relay/adaptor/xunfei/model.go
+++ b/relay/adaptor/xunfei/model.go
@@ -19,11 +19,11 @@ type ChatRequest struct {
 	} `json:"header"`
 	Parameter struct {
 		Chat struct {
-			Domain      string  `json:"domain,omitempty"`
+			Domain      string   `json:"domain,omitempty"`
-			Temperature float64 `json:"temperature,omitempty"`
+			Temperature *float64 `json:"temperature,omitempty"`
-			TopK        int     `json:"top_k,omitempty"`
+			TopK        int      `json:"top_k,omitempty"`
-			MaxTokens   int     `json:"max_tokens,omitempty"`
+			MaxTokens   int      `json:"max_tokens,omitempty"`
-			Auditing    bool    `json:"auditing,omitempty"`
+			Auditing    bool     `json:"auditing,omitempty"`
 		} `json:"chat"`
 	} `json:"parameter"`
 	Payload struct {
--- a/relay/adaptor/zhipu/adaptor.go
+++ b/relay/adaptor/zhipu/adaptor.go
@@ -4,13 +4,13 @@ import (
 	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
 	"github.com/songquanpeng/one-api/common/helper"
 	"github.com/songquanpeng/one-api/relay/adaptor"
 	"github.com/songquanpeng/one-api/relay/adaptor/openai"
 	"github.com/songquanpeng/one-api/relay/meta"
 	"github.com/songquanpeng/one-api/relay/model"
 	"github.com/songquanpeng/one-api/relay/relaymode"
 	"io"
 	"math"
 	"net/http"
 	"strings"
 )
@@ -65,13 +65,13 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.G
 		baiduEmbeddingRequest, err := ConvertEmbeddingRequest(*request)
 		return baiduEmbeddingRequest, err
 	default:
-		// TopP (0.0, 1.0)
+		// TopP [0.0, 1.0]
-		request.TopP = math.Min(0.99, request.TopP)
+		request.TopP = helper.Float64PtrMax(request.TopP, 1)
-		request.TopP = math.Max(0.01, request.TopP)
+		request.TopP = helper.Float64PtrMin(request.TopP, 0)
-		// Temperature (0.0, 1.0)
+		// Temperature [0.0, 1.0]
-		request.Temperature = math.Min(0.99, request.Temperature)
+		request.Temperature = helper.Float64PtrMax(request.Temperature, 1)
-		request.Temperature = math.Max(0.01, request.Temperature)
+		request.Temperature = helper.Float64PtrMin(request.Temperature, 0)
 		a.SetVersionByModeName(request.Model)
 		if a.APIVersion == "v4" {
 			return request, nil
--- a/relay/adaptor/zhipu/model.go
+++ b/relay/adaptor/zhipu/model.go
@@ -12,8 +12,8 @@ type Message struct {
 type Request struct {
 	Prompt      []Message `json:"prompt"`
-	Temperature float64   `json:"temperature,omitempty"`
+	Temperature *float64  `json:"temperature,omitempty"`
-	TopP        float64   `json:"top_p,omitempty"`
+	TopP        *float64  `json:"top_p,omitempty"`
 	RequestId   string    `json:"request_id,omitempty"`
 	Incremental bool      `json:"incremental,omitempty"`
 }
--- a/relay/billing/ratio/model.go
+++ b/relay/billing/ratio/model.go
@@ -79,8 +79,10 @@ var ModelRatio = map[string]float64{
 	"claude-2.0":                 8.0 / 1000 * USD,
 	"claude-2.1":                 8.0 / 1000 * USD,
 	"claude-3-haiku-20240307":    0.25 / 1000 * USD,
 	"claude-3-5-haiku-20241022":  1.0 / 1000 * USD,
 	"claude-3-sonnet-20240229":   3.0 / 1000 * USD,
 	"claude-3-5-sonnet-20240620": 3.0 / 1000 * USD,
 	"claude-3-5-sonnet-20241022": 3.0 / 1000 * USD,
 	"claude-3-opus-20240229":     15.0 / 1000 * USD,
 	// https://cloud.baidu.com/doc/WENXINWORKSHOP/s/hlrk4akp7
 	"ERNIE-4.0-8K":       0.120 * RMB,
@@ -130,6 +132,7 @@ var ModelRatio = map[string]float64{
 	"SparkDesk-v3.1":            1.2858, // ￥0.018 / 1k tokens
 	"SparkDesk-v3.1-128K":       1.2858, // ￥0.018 / 1k tokens
 	"SparkDesk-v3.5":            1.2858, // ￥0.018 / 1k tokens
 	"SparkDesk-v3.5-32K":        1.2858, // ￥0.018 / 1k tokens
 	"SparkDesk-v4.0":            1.2858, // ￥0.018 / 1k tokens
 	"360GPT_S2_V9":              0.8572, // ¥0.012 / 1k tokens
 	"embedding-bert-512-v1":     0.0715, // ¥0.001 / 1k tokens
@@ -161,15 +164,21 @@ var ModelRatio = map[string]float64{
 	"mistral-embed":         0.1 / 1000 * USD,
 	// https://wow.groq.com/#:~:text=inquiries%C2%A0here.-,Model,-Current%20Speed
 	"gemma-7b-it":                           0.07 / 1000000 * USD,
 	"mixtral-8x7b-32768":                    0.24 / 1000000 * USD,
 	"llama3-8b-8192":                        0.05 / 1000000 * USD,
 	"llama3-70b-8192":                       0.59 / 1000000 * USD,
 	"gemma2-9b-it":                          0.20 / 1000000 * USD,
 	"llama-3.1-405b-reasoning":              0.89 / 1000000 * USD,
 	"llama-3.1-70b-versatile":               0.59 / 1000000 * USD,
 	"llama-3.1-8b-instant":                  0.05 / 1000000 * USD,
 	"llama-3.2-11b-text-preview":            0.05 / 1000000 * USD,
 	"llama-3.2-11b-vision-preview":          0.05 / 1000000 * USD,
 	"llama-3.2-1b-preview":                  0.05 / 1000000 * USD,
 	"llama-3.2-3b-preview":                  0.05 / 1000000 * USD,
 	"llama-3.2-90b-text-preview":            0.59 / 1000000 * USD,
 	"llama-guard-3-8b":                      0.05 / 1000000 * USD,
 	"llama3-70b-8192":                       0.59 / 1000000 * USD,
 	"llama3-8b-8192":                        0.05 / 1000000 * USD,
 	"llama3-groq-70b-8192-tool-use-preview": 0.89 / 1000000 * USD,
 	"llama3-groq-8b-8192-tool-use-preview":  0.19 / 1000000 * USD,
 	"mixtral-8x7b-32768":                    0.24 / 1000000 * USD,
 	// https://platform.lingyiwanwu.com/docs#-计费单元
 	"yi-34b-chat-0205": 2.5 / 1000 * RMB,
 	"yi-34b-chat-200k": 12.0 / 1000 * RMB,
@@ -200,6 +209,8 @@ var ModelRatio = map[string]float64{
 	"deepl-zh": 25.0 / 1000 * USD,
 	"deepl-en": 25.0 / 1000 * USD,
 	"deepl-ja": 25.0 / 1000 * USD,
 	// https://console.x.ai/
 	"grok-beta": 5.0 / 1000 * USD,
 }
 var CompletionRatio = map[string]float64{
@@ -364,6 +375,8 @@ func GetCompletionRatio(name string, channelType int) float64 {
 		return 3
 	case "command-r-plus":
 		return 5
 	case "grok-beta":
 		return 3
 	}
 	return 1
 }
--- a/relay/channeltype/define.go
+++ b/relay/channeltype/define.go
@@ -46,5 +46,6 @@ const (
 	VertextAI
 	Proxy
 	SiliconFlow
 	XAI
 	Dummy
 )
--- a/relay/channeltype/url.go
+++ b/relay/channeltype/url.go
@@ -45,7 +45,8 @@ var ChannelBaseURLs = []string{
 	"https://api.novita.ai/v3/openai",           // 41
 	"",                                          // 42
 	"",                                          // 43
-	"https://api.siliconflow.cn",                 // 44
+	"https://api.siliconflow.cn",                // 44
 	"https://api.x.ai",                          // 45
 }
 func init() {
--- a/relay/constant/role/define.go
+++ b/relay/constant/role/define.go
@@ -1,5 +1,6 @@
 package role
 const (
 	System    = "system"
 	Assistant = "assistant"
 )
--- a/relay/controller/helper.go
+++ b/relay/controller/helper.go
@@ -4,6 +4,7 @@ import (
 	"context"
 	"errors"
 	"fmt"
 	"github.com/songquanpeng/one-api/relay/constant/role"
 	"math"
 	"net/http"
 	"strings"
@@ -90,7 +91,7 @@ func preConsumeQuota(ctx context.Context, textRequest *relaymodel.GeneralOpenAIR
 	return preConsumedQuota, nil
 }
-func postConsumeQuota(ctx context.Context, usage *relaymodel.Usage, meta *meta.Meta, textRequest *relaymodel.GeneralOpenAIRequest, ratio float64, preConsumedQuota int64, modelRatio float64, groupRatio float64) {
+func postConsumeQuota(ctx context.Context, usage *relaymodel.Usage, meta *meta.Meta, textRequest *relaymodel.GeneralOpenAIRequest, ratio float64, preConsumedQuota int64, modelRatio float64, groupRatio float64, systemPromptReset bool) {
 	if usage == nil {
 		logger.Error(ctx, "usage is nil, which is unexpected")
 		return
@@ -118,7 +119,11 @@ func postConsumeQuota(ctx context.Context, usage *relaymodel.Usage, meta *meta.M
 	if err != nil {
 		logger.Error(ctx, "error update user quota cache: "+err.Error())
 	}
-	logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f，补全倍率 %.2f", modelRatio, groupRatio, completionRatio)
+	var extraLog string
 	if systemPromptReset {
 		extraLog = " （注意系统提示词已被重置）"
 	}
 	logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f，补全倍率 %.2f%s", modelRatio, groupRatio, completionRatio, extraLog)
 	model.RecordConsumeLog(ctx, meta.UserId, meta.ChannelId, promptTokens, completionTokens, textRequest.Model, meta.TokenName, quota, logContent)
 	model.UpdateUserUsedQuotaAndRequestCount(meta.UserId, quota)
 	model.UpdateChannelUsedQuota(meta.ChannelId, quota)
@@ -154,3 +159,23 @@ func isErrorHappened(meta *meta.Meta, resp *http.Response) bool {
 	}
 	return false
 }
 func setSystemPrompt(ctx context.Context, request *relaymodel.GeneralOpenAIRequest, prompt string) (reset bool) {
 	if prompt == "" {
 		return false
 	}
 	if len(request.Messages) == 0 {
 		return false
 	}
 	if request.Messages[0].Role == role.System {
 		request.Messages[0].Content = prompt
 		logger.Infof(ctx, "rewrite system prompt")
 		return true
 	}
 	request.Messages = append([]relaymodel.Message{{
 		Role:    role.System,
 		Content: prompt,
 	}}, request.Messages...)
 	logger.Infof(ctx, "add system prompt")
 	return true
 }
--- a/relay/controller/text.go
+++ b/relay/controller/text.go
@@ -4,6 +4,7 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
 	"github.com/songquanpeng/one-api/common/config"
 	"io"
 	"net/http"
@@ -35,6 +36,8 @@ func RelayTextHelper(c *gin.Context) *model.ErrorWithStatusCode {
 	meta.OriginModelName = textRequest.Model
 	textRequest.Model, _ = getMappedModelName(textRequest.Model, meta.ModelMapping)
 	meta.ActualModelName = textRequest.Model
 	// set system prompt if not empty
 	systemPromptReset := setSystemPrompt(ctx, textRequest, meta.SystemPrompt)
 	// get model ratio & group ratio
 	modelRatio := billingratio.GetModelRatio(textRequest.Model, meta.ChannelType)
 	groupRatio := billingratio.GetGroupRatio(meta.Group)
@@ -79,12 +82,12 @@ func RelayTextHelper(c *gin.Context) *model.ErrorWithStatusCode {
 		return respErr
 	}
 	// post-consume quota
-	go postConsumeQuota(ctx, usage, meta, textRequest, ratio, preConsumedQuota, modelRatio, groupRatio)
+	go postConsumeQuota(ctx, usage, meta, textRequest, ratio, preConsumedQuota, modelRatio, groupRatio, systemPromptReset)
 	return nil
 }
 func getRequestBody(c *gin.Context, meta *meta.Meta, textRequest *model.GeneralOpenAIRequest, adaptor adaptor.Adaptor) (io.Reader, error) {
-	if meta.APIType == apitype.OpenAI && meta.OriginModelName == meta.ActualModelName && meta.ChannelType != channeltype.Baichuan {
+	if !config.EnforceIncludeUsage && meta.APIType == apitype.OpenAI && meta.OriginModelName == meta.ActualModelName && meta.ChannelType != channeltype.Baichuan {
 		// no need to convert request for openai
 		return c.Request.Body, nil
 	}
--- a/relay/meta/relay_meta.go
+++ b/relay/meta/relay_meta.go
@@ -30,6 +30,7 @@ type Meta struct {
 	ActualModelName string
 	RequestURLPath  string
 	PromptTokens    int // only for DoResponse
 	SystemPrompt    string
 }
 func GetByContext(c *gin.Context) *Meta {
@@ -46,6 +47,7 @@ func GetByContext(c *gin.Context) *Meta {
 		BaseURL:         c.GetString(ctxkey.BaseURL),
 		APIKey:          strings.TrimPrefix(c.Request.Header.Get("Authorization"), "Bearer "),
 		RequestURLPath:  c.Request.URL.String(),
 		SystemPrompt:    c.GetString(ctxkey.SystemPrompt),
 	}
 	cfg, ok := c.Get(ctxkey.Config)
 	if ok {
--- a/relay/model/constant.go
+++ b/relay/model/constant.go
@@ -1,6 +1,7 @@
 package model
 const (
-	ContentTypeText     = "text"
+	ContentTypeText       = "text"
-	ContentTypeImageURL = "image_url"
+	ContentTypeImageURL   = "image_url"
 	ContentTypeInputAudio = "input_audio"
 )
--- a/relay/model/general.go
+++ b/relay/model/general.go
@@ -12,32 +12,59 @@ type JSONSchema struct {
 	Strict      *bool                  `json:"strict,omitempty"`
 }
 type Audio struct {
 	Voice  string `json:"voice,omitempty"`
 	Format string `json:"format,omitempty"`
 }
 type StreamOptions struct {
 	IncludeUsage bool `json:"include_usage,omitempty"`
 }
 type GeneralOpenAIRequest struct {
-	Messages         []Message       `json:"messages,omitempty"`
+	// https://platform.openai.com/docs/api-reference/chat/create
-	Model            string          `json:"model,omitempty"`
+	Messages            []Message       `json:"messages,omitempty"`
-	FrequencyPenalty float64         `json:"frequency_penalty,omitempty"`
+	Model               string          `json:"model,omitempty"`
-	MaxTokens        int             `json:"max_tokens,omitempty"`
+	Store               *bool           `json:"store,omitempty"`
-	N                int             `json:"n,omitempty"`
+	Metadata            any             `json:"metadata,omitempty"`
-	PresencePenalty  float64         `json:"presence_penalty,omitempty"`
+	FrequencyPenalty    *float64        `json:"frequency_penalty,omitempty"`
-	ResponseFormat   *ResponseFormat `json:"response_format,omitempty"`
+	LogitBias           any             `json:"logit_bias,omitempty"`
-	Seed             float64         `json:"seed,omitempty"`
+	Logprobs            *bool           `json:"logprobs,omitempty"`
-	Stop             any             `json:"stop,omitempty"`
+	TopLogprobs         *int            `json:"top_logprobs,omitempty"`
-	Stream           bool            `json:"stream,omitempty"`
+	MaxTokens           int             `json:"max_tokens,omitempty"`
-	Temperature      float64         `json:"temperature,omitempty"`
+	MaxCompletionTokens *int            `json:"max_completion_tokens,omitempty"`
-	TopP             float64         `json:"top_p,omitempty"`
+	N                   int             `json:"n,omitempty"`
-	TopK             int             `json:"top_k,omitempty"`
+	Modalities          []string        `json:"modalities,omitempty"`
-	Tools            []Tool          `json:"tools,omitempty"`
+	Prediction          any             `json:"prediction,omitempty"`
-	ToolChoice       any             `json:"tool_choice,omitempty"`
+	Audio               *Audio          `json:"audio,omitempty"`
-	FunctionCall     any             `json:"function_call,omitempty"`
+	PresencePenalty     *float64        `json:"presence_penalty,omitempty"`
-	Functions        any             `json:"functions,omitempty"`
+	ResponseFormat      *ResponseFormat `json:"response_format,omitempty"`
-	User             string          `json:"user,omitempty"`
+	Seed                float64         `json:"seed,omitempty"`
-	Prompt           any             `json:"prompt,omitempty"`
+	ServiceTier         *string         `json:"service_tier,omitempty"`
-	Input            any             `json:"input,omitempty"`
+	Stop                any             `json:"stop,omitempty"`
-	EncodingFormat   string          `json:"encoding_format,omitempty"`
+	Stream              bool            `json:"stream,omitempty"`
-	Dimensions       int             `json:"dimensions,omitempty"`
+	StreamOptions       *StreamOptions  `json:"stream_options,omitempty"`
-	Instruction      string          `json:"instruction,omitempty"`
+	Temperature         *float64        `json:"temperature,omitempty"`
-	Size             string          `json:"size,omitempty"`
+	TopP                *float64        `json:"top_p,omitempty"`
-	NumCtx           int         	 `json:"num_ctx,omitempty"`
+	TopK                int             `json:"top_k,omitempty"`
 	Tools               []Tool          `json:"tools,omitempty"`
 	ToolChoice          any             `json:"tool_choice,omitempty"`
 	ParallelTooCalls    *bool           `json:"parallel_tool_calls,omitempty"`
 	User                string          `json:"user,omitempty"`
 	FunctionCall        any             `json:"function_call,omitempty"`
 	Functions           any             `json:"functions,omitempty"`
 	// https://platform.openai.com/docs/api-reference/embeddings/create
 	Input          any    `json:"input,omitempty"`
 	EncodingFormat string `json:"encoding_format,omitempty"`
 	Dimensions     int    `json:"dimensions,omitempty"`
 	// https://platform.openai.com/docs/api-reference/images/create
 	Prompt  any     `json:"prompt,omitempty"`
 	Quality *string `json:"quality,omitempty"`
 	Size    string  `json:"size,omitempty"`
 	Style   *string `json:"style,omitempty"`
 	// Others
 	Instruction string `json:"instruction,omitempty"`
 	NumCtx      int    `json:"num_ctx,omitempty"`
 }
 func (r GeneralOpenAIRequest) ParseInput() []string {
--- a/router/relay.go
+++ b/router/relay.go
@@ -9,6 +9,7 @@ import (
 func SetRelayRouter(router *gin.Engine) {
 	router.Use(middleware.CORS())
 	router.Use(middleware.GzipDecodeMiddleware())
 	// https://platform.openai.com/docs/api-reference/introduction
 	modelsRouter := router.Group("/v1/models")
 	modelsRouter.Use(middleware.TokenAuth())
--- a/web/air/src/components/TokensTable.js
+++ b/web/air/src/components/TokensTable.js
@@ -395,7 +395,7 @@ const TokensTable = () => {
        url = mjLink + `/#/?settings={"key":"sk-${key}","url":"${serverAddress}"}`;
        break;
      case 'lobechat':
-        url = chatLink + `/?settings={"keyVaults":{"openai":{"apiKey":"sk-${key}","baseURL":"${serverAddress}"/v1"}}}`;
+        url = chatLink + `/?settings={"keyVaults":{"openai":{"apiKey":"sk-${key}","baseURL":"${serverAddress}/v1"}}}`;
        break;
      default:
        if (!chatLink) {
--- a/web/air/src/constants/channel.constants.js
+++ b/web/air/src/constants/channel.constants.js
@@ -30,6 +30,7 @@ export const CHANNEL_OPTIONS = [
  { key: 42, text: 'VertexAI', value: 42, color: 'blue' },
  { key: 43, text: 'Proxy', value: 43, color: 'blue' },
  { key: 44, text: 'SiliconFlow', value: 44, color: 'blue' },
  { key: 45, text: 'xAI', value: 45, color: 'blue' },
  { key: 8, text: '自定义渠道', value: 8, color: 'pink' },
  { key: 22, text: '知识库：FastGPT', value: 22, color: 'blue' },
  { key: 21, text: '知识库：AI Proxy', value: 21, color: 'purple' },
--- a/web/air/src/pages/Channel/EditChannel.js
+++ b/web/air/src/pages/Channel/EditChannel.js
@@ -43,6 +43,7 @@ const EditChannel = (props) => {
        base_url: '',
        other: '',
        model_mapping: '',
        system_prompt: '',
        models: [],
        auto_ban: 1,
        groups: ['default']
@@ -63,7 +64,7 @@ const EditChannel = (props) => {
            let localModels = [];
            switch (value) {
                case 14:
-                    localModels = ["claude-instant-1.2", "claude-2", "claude-2.0", "claude-2.1", "claude-3-opus-20240229", "claude-3-sonnet-20240229", "claude-3-haiku-20240307", "claude-3-5-sonnet-20240620"];
+                    localModels = ["claude-instant-1.2", "claude-2", "claude-2.0", "claude-2.1", "claude-3-opus-20240229", "claude-3-sonnet-20240229", "claude-3-haiku-20240307", "claude-3-5-haiku-20241022", "claude-3-5-sonnet-20240620", "claude-3-5-sonnet-20241022"];
                    break;
                case 11:
                    localModels = ['PaLM-2'];
@@ -78,7 +79,7 @@ const EditChannel = (props) => {
                    localModels = ['chatglm_pro', 'chatglm_std', 'chatglm_lite'];
                    break;
                case 18:
-                    localModels = ['SparkDesk', 'SparkDesk-v1.1', 'SparkDesk-v2.1', 'SparkDesk-v3.1', 'SparkDesk-v3.1-128K', 'SparkDesk-v3.5', 'SparkDesk-v4.0'];
+                    localModels = ['SparkDesk', 'SparkDesk-v1.1', 'SparkDesk-v2.1', 'SparkDesk-v3.1', 'SparkDesk-v3.1-128K', 'SparkDesk-v3.5', 'SparkDesk-v3.5-32K', 'SparkDesk-v4.0'];
                    break;
                case 19:
                    localModels = ['360GPT_S2_V9', 'embedding-bert-512-v1', 'embedding_s1_v1', 'semantic_similarity_s1_v1'];
@@ -304,163 +305,163 @@ const EditChannel = (props) => {
                width={isMobile() ? '100%' : 600}
            >
                <Spin spinning={loading}>
-                    <div style={{marginTop: 10}}>
+                    <div style={{ marginTop: 10 }}>
                        <Typography.Text strong>类型：</Typography.Text>
                    </div>
                    <Select
-                        name='type'
+                      name='type'
-                        required
+                      required
-                        optionList={CHANNEL_OPTIONS}
+                      optionList={CHANNEL_OPTIONS}
-                        value={inputs.type}
+                      value={inputs.type}
-                        onChange={value => handleInputChange('type', value)}
+                      onChange={value => handleInputChange('type', value)}
-                        style={{width: '50%'}}
+                      style={{ width: '50%' }}
                    />
                    {
-                        inputs.type === 3 && (
+                      inputs.type === 3 && (
-                            <>
+                        <>
-                                <div style={{marginTop: 10}}>
+                            <div style={{ marginTop: 10 }}>
-                                    <Banner type={"warning"} description={
+                                <Banner type={"warning"} description={
-                                        <>
+                                    <>
-                                            注意，<strong>模型部署名称必须和模型名称保持一致</strong>，因为 One API 会把请求体中的
+                                        注意，<strong>模型部署名称必须和模型名称保持一致</strong>，因为 One API 会把请求体中的
-                                            model
+                                        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'
+                                        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'>图片演示</a>。
+                                                                                          href='https://github.com/songquanpeng/one-api/issues/133?notification_referrer_id=NT_kwDOAmJSYrM2NjIwMzI3NDgyOjM5OTk4MDUw#issuecomment-1571602271'>图片演示</a>。
-                                        </>
+                                    </>
-                                    }>
+                                }>
-                                    </Banner>
+                                </Banner>
-                                </div>
+                            </div>
-                                <div style={{marginTop: 10}}>
+                            <div style={{ marginTop: 10 }}>
-                                    <Typography.Text strong>AZURE_OPENAI_ENDPOINT：</Typography.Text>
+                                <Typography.Text strong>AZURE_OPENAI_ENDPOINT：</Typography.Text>
-                                </div>
+                            </div>
-                                <Input
+                            <Input
-                                    label='AZURE_OPENAI_ENDPOINT'
+                              label='AZURE_OPENAI_ENDPOINT'
-                                    name='azure_base_url'
+                              name='azure_base_url'
-                                    placeholder={'请输入 AZURE_OPENAI_ENDPOINT，例如：https://docs-test-001.openai.azure.com'}
+                              placeholder={'请输入 AZURE_OPENAI_ENDPOINT，例如：https://docs-test-001.openai.azure.com'}
-                                    onChange={value => {
+                              onChange={value => {
-                                        handleInputChange('base_url', value)
+                                  handleInputChange('base_url', value)
-                                    }}
+                              }}
-                                    value={inputs.base_url}
+                              value={inputs.base_url}
-                                    autoComplete='new-password'
+                              autoComplete='new-password'
-                                />
+                            />
-                                <div style={{marginTop: 10}}>
+                            <div style={{ marginTop: 10 }}>
-                                    <Typography.Text strong>默认 API 版本：</Typography.Text>
+                                <Typography.Text strong>默认 API 版本：</Typography.Text>
-                                </div>
+                            </div>
-                                <Input
+                            <Input
-                                    label='默认 API 版本'
+                              label='默认 API 版本'
-                                    name='azure_other'
+                              name='azure_other'
-                                    placeholder={'请输入默认 API 版本，例如：2024-03-01-preview，该配置可以被实际的请求查询参数所覆盖'}
+                              placeholder={'请输入默认 API 版本，例如：2024-03-01-preview，该配置可以被实际的请求查询参数所覆盖'}
-                                    onChange={value => {
+                              onChange={value => {
-                                        handleInputChange('other', value)
+                                  handleInputChange('other', value)
-                                    }}
+                              }}
-                                    value={inputs.other}
+                              value={inputs.other}
-                                    autoComplete='new-password'
+                              autoComplete='new-password'
-                                />
+                            />
-                            </>
+                        </>
-                        )
+                      )
                    }
                    {
-                        inputs.type === 8 && (
+                      inputs.type === 8 && (
-                            <>
+                        <>
-                                <div style={{marginTop: 10}}>
+                            <div style={{ marginTop: 10 }}>
-                                    <Typography.Text strong>Base URL：</Typography.Text>
+                                <Typography.Text strong>Base URL：</Typography.Text>
-                                </div>
+                            </div>
-                                <Input
+                            <Input
-                                    name='base_url'
+                              name='base_url'
-                                    placeholder={'请输入自定义渠道的 Base URL'}
+                              placeholder={'请输入自定义渠道的 Base URL'}
-                                    onChange={value => {
+                              onChange={value => {
-                                        handleInputChange('base_url', value)
+                                  handleInputChange('base_url', value)
-                                    }}
+                              }}
-                                    value={inputs.base_url}
+                              value={inputs.base_url}
-                                    autoComplete='new-password'
+                              autoComplete='new-password'
-                                />
+                            />
-                            </>
+                        </>
-                        )
+                      )
                    }
-                    <div style={{marginTop: 10}}>
+                    <div style={{ marginTop: 10 }}>
                        <Typography.Text strong>名称：</Typography.Text>
                    </div>
                    <Input
-                        required
+                      required
-                        name='name'
+                      name='name'
-                        placeholder={'请为渠道命名'}
+                      placeholder={'请为渠道命名'}
-                        onChange={value => {
+                      onChange={value => {
-                            handleInputChange('name', value)
+                          handleInputChange('name', value)
-                        }}
+                      }}
-                        value={inputs.name}
+                      value={inputs.name}
-                        autoComplete='new-password'
+                      autoComplete='new-password'
                    />
-                    <div style={{marginTop: 10}}>
+                    <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'}
+                      placeholder={'请选择可以使用该渠道的分组'}
-                        name='groups'
+                      name='groups'
-                        required
+                      required
-                        multiple
+                      multiple
-                        selection
+                      selection
-                        allowAdditions
+                      allowAdditions
-                        additionLabel={'请在系统设置页面编辑分组倍率以添加新的分组：'}
+                      additionLabel={'请在系统设置页面编辑分组倍率以添加新的分组：'}
-                        onChange={value => {
+                      onChange={value => {
-                            handleInputChange('groups', value)
+                          handleInputChange('groups', value)
-                        }}
+                      }}
-                        value={inputs.groups}
+                      value={inputs.groups}
-                        autoComplete='new-password'
+                      autoComplete='new-password'
-                        optionList={groupOptions}
+                      optionList={groupOptions}
                    />
                    {
-                        inputs.type === 18 && (
+                      inputs.type === 18 && (
-                            <>
+                        <>
-                                <div style={{marginTop: 10}}>
+                            <div style={{ marginTop: 10 }}>
-                                    <Typography.Text strong>模型版本：</Typography.Text>
+                                <Typography.Text strong>模型版本：</Typography.Text>
-                                </div>
+                            </div>
-                                <Input
+                            <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'}
+                              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'}
-                                    onChange={value => {
+                              onChange={value => {
-                                        handleInputChange('other', value)
+                                  handleInputChange('other', value)
-                                    }}
+                              }}
-                                    value={inputs.other}
+                              value={inputs.other}
-                                    autoComplete='new-password'
+                              autoComplete='new-password'
-                                />
+                            />
-                            </>
+                        </>
-                        )
+                      )
                    }
                    {
-                        inputs.type === 21 && (
+                      inputs.type === 21 && (
-                            <>
+                        <>
-                                <div style={{marginTop: 10}}>
+                            <div style={{ marginTop: 10 }}>
-                                    <Typography.Text strong>知识库 ID：</Typography.Text>
+                                <Typography.Text strong>知识库 ID：</Typography.Text>
-                                </div>
+                            </div>
-                                <Input
+                            <Input
-                                    label='知识库 ID'
+                              label='知识库 ID'
-                                    name='other'
+                              name='other'
-                                    placeholder={'请输入知识库 ID，例如：123456'}
+                              placeholder={'请输入知识库 ID，例如：123456'}
-                                    onChange={value => {
+                              onChange={value => {
-                                        handleInputChange('other', value)
+                                  handleInputChange('other', value)
-                                    }}
+                              }}
-                                    value={inputs.other}
+                              value={inputs.other}
-                                    autoComplete='new-password'
+                              autoComplete='new-password'
-                                />
+                            />
-                            </>
+                        </>
-                        )
+                      )
                    }
-                    <div style={{marginTop: 10}}>
+                    <div style={{ marginTop: 10 }}>
                        <Typography.Text strong>模型：</Typography.Text>
                    </div>
                    <Select
-                        placeholder={'请选择该渠道所支持的模型'}
+                      placeholder={'请选择该渠道所支持的模型'}
-                        name='models'
+                      name='models'
-                        required
+                      required
-                        multiple
+                      multiple
-                        selection
+                      selection
-                        onChange={value => {
+                      onChange={value => {
-                            handleInputChange('models', value)
+                          handleInputChange('models', value)
-                        }}
+                      }}
-                        value={inputs.models}
+                      value={inputs.models}
-                        autoComplete='new-password'
+                      autoComplete='new-password'
-                        optionList={modelOptions}
+                      optionList={modelOptions}
                    />
-                    <div style={{lineHeight: '40px', marginBottom: '12px'}}>
+                    <div style={{ lineHeight: '40px', marginBottom: '12px' }}>
                        <Space>
                            <Button type='primary' onClick={() => {
                                handleInputChange('models', basicModels);
@@ -473,28 +474,41 @@ const EditChannel = (props) => {
                            }}>清除所有模型</Button>
                        </Space>
                        <Input
-                            addonAfter={
+                          addonAfter={
-                                <Button type='primary' onClick={addCustomModel}>填入</Button>
+                              <Button type='primary' onClick={addCustomModel}>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}
+                          value={customModel}
-                            onChange={(value) => {
+                          onChange={(value) => {
-                                setCustomModel(value.trim());
+                              setCustomModel(value.trim());
-                            }}
+                          }}
                        />
                    </div>
-                    <div style={{marginTop: 10}}>
+                    <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，例如：\n${JSON.stringify(MODEL_MAPPING_EXAMPLE, null, 2)}`}
+                      placeholder={`此项可选，用于修改请求体中的模型名称，为一个 JSON 字符串，键为请求中模型名称，值为要替换的模型名称，例如：\n${JSON.stringify(MODEL_MAPPING_EXAMPLE, null, 2)}`}
-                        name='model_mapping'
+                      name='model_mapping'
-                        onChange={value => {
+                      onChange={value => {
-                            handleInputChange('model_mapping', value)
+                          handleInputChange('model_mapping', value)
-                        }}
+                      }}
-                        autosize
+                      autosize
-                        value={inputs.model_mapping}
+                      value={inputs.model_mapping}
-                        autoComplete='new-password'
+                      autoComplete='new-password'
                    />
                    <div style={{ marginTop: 10 }}>
                        <Typography.Text strong>系统提示词：</Typography.Text>
                    </div>
                    <TextArea
                      placeholder={`此项可选，用于强制设置给定的系统提示词，请配合自定义模型 & 模型重定向使用，首先创建一个唯一的自定义模型名称并在上面填入，之后将该自定义模型重定向映射到该渠道一个原生支持的模型`}
                      name='system_prompt'
                      onChange={value => {
                          handleInputChange('system_prompt', value)
                      }}
                      autosize
                      value={inputs.system_prompt}
                      autoComplete='new-password'
                    />
                    <Typography.Text style={{
                        color: 'rgba(var(--semi-blue-5), 1)',
@@ -507,116 +521,116 @@ const EditChannel = (props) => {
                    }>
                        填入模板
                    </Typography.Text>
-                    <div style={{marginTop: 10}}>
+                    <div style={{ marginTop: 10 }}>
                        <Typography.Text strong>密钥：</Typography.Text>
                    </div>
                    {
                        batch ?
-                            <TextArea
+                          <TextArea
-                                label='密钥'
+                            label='密钥'
-                                name='key'
+                            name='key'
-                                required
+                            required
-                                placeholder={'请输入密钥，一行一个'}
+                            placeholder={'请输入密钥，一行一个'}
-                                onChange={value => {
+                            onChange={value => {
-                                    handleInputChange('key', value)
+                                handleInputChange('key', value)
-                                }}
+                            }}
-                                value={inputs.key}
+                            value={inputs.key}
-                                style={{minHeight: 150, fontFamily: 'JetBrains Mono, Consolas'}}
+                            style={{ minHeight: 150, fontFamily: 'JetBrains Mono, Consolas' }}
-                                autoComplete='new-password'
+                            autoComplete='new-password'
-                            />
+                          />
-                            :
+                          :
-                            <Input
+                          <Input
-                                label='密钥'
+                            label='密钥'
-                                name='key'
+                            name='key'
-                                required
+                            required
-                                placeholder={type2secretPrompt(inputs.type)}
+                            placeholder={type2secretPrompt(inputs.type)}
-                                onChange={value => {
+                            onChange={value => {
-                                    handleInputChange('key', value)
+                                handleInputChange('key', value)
-                                }}
+                            }}
-                                value={inputs.key}
+                            value={inputs.key}
-                                autoComplete='new-password'
+                            autoComplete='new-password'
-                            />
+                          />
                    }
-                    <div style={{marginTop: 10}}>
+                    <div style={{ marginTop: 10 }}>
                        <Typography.Text strong>组织：</Typography.Text>
                    </div>
                    <Input
-                        label='组织，可选，不填则为默认组织'
+                      label='组织，可选，不填则为默认组织'
-                        name='openai_organization'
+                      name='openai_organization'
-                        placeholder='请输入组织org-xxx'
+                      placeholder='请输入组织org-xxx'
-                        onChange={value => {
+                      onChange={value => {
-                            handleInputChange('openai_organization', value)
+                          handleInputChange('openai_organization', value)
-                        }}
+                      }}
-                        value={inputs.openai_organization}
+                      value={inputs.openai_organization}
                    />
-                    <div style={{marginTop: 10, display: 'flex'}}>
+                    <div style={{ marginTop: 10, display: 'flex' }}>
                        <Space>
                            <Checkbox
-                                name='auto_ban'
+                              name='auto_ban'
-                                checked={autoBan}
+                              checked={autoBan}
-                                onChange={
+                              onChange={
-                                    () => {
+                                  () => {
-                                        setAutoBan(!autoBan);
+                                      setAutoBan(!autoBan);
-                                    }
+                                  }
-                                }
+                              }
-                                // onChange={handleInputChange}
+                              // onChange={handleInputChange}
                            />
                            <Typography.Text
-                                strong>是否自动禁用（仅当自动禁用开启时有效），关闭后不会自动禁用该渠道：</Typography.Text>
+                              strong>是否自动禁用（仅当自动禁用开启时有效），关闭后不会自动禁用该渠道：</Typography.Text>
                        </Space>
                    </div>
                    {
-                        !isEdit && (
+                      !isEdit && (
-                            <div style={{marginTop: 10, display: 'flex'}}>
+                        <div style={{ marginTop: 10, display: 'flex' }}>
-                                <Space>
+                            <Space>
-                                    <Checkbox
+                                <Checkbox
-                                        checked={batch}
+                                  checked={batch}
-                                        label='批量创建'
+                                  label='批量创建'
-                                        name='batch'
+                                  name='batch'
-                                        onChange={() => setBatch(!batch)}
+                                  onChange={() => setBatch(!batch)}
-                                    />
+                                />
-                                    <Typography.Text strong>批量创建</Typography.Text>
+                                <Typography.Text strong>批量创建</Typography.Text>
-                                </Space>
+                            </Space>
                        </div>
                      )
                    }
                    {
                      inputs.type !== 3 && inputs.type !== 8 && inputs.type !== 22 && (
                        <>
                            <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 !== 3 && inputs.type !== 8 && inputs.type !== 22 && (
+                      inputs.type === 22 && (
-                            <>
+                        <>
-                                <div style={{marginTop: 10}}>
+                            <div style={{ marginTop: 10 }}>
-                                    <Typography.Text strong>代理：</Typography.Text>
+                                <Typography.Text strong>私有部署地址：</Typography.Text>
-                                </div>
+                            </div>
-                                <Input
+                            <Input
-                                    label='代理'
+                              name='base_url'
-                                    name='base_url'
+                              placeholder={'请输入私有部署地址，格式为：https://fastgpt.run/api/openapi'}
-                                    placeholder={'此项可选，用于通过代理站来进行 API 调用'}
+                              onChange={value => {
-                                    onChange={value => {
+                                  handleInputChange('base_url', value)
-                                        handleInputChange('base_url', value)
+                              }}
-                                    }}
+                              value={inputs.base_url}
-                                    value={inputs.base_url}
+                              autoComplete='new-password'
-                                    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'
                                />
                            </>
                        )
                    }
                </Spin>
--- a/web/berry/src/constants/ChannelConstants.js
+++ b/web/berry/src/constants/ChannelConstants.js
@@ -179,6 +179,12 @@ export const CHANNEL_OPTIONS = {
    value: 44,
    color: 'primary'
  },
  45: {
    key: 45,
    text: 'xAI',
    value: 45,
    color: 'primary'
  },
  41: {
    key: 41,
    text: 'Novita',
--- a/web/berry/src/utils/common.js
+++ b/web/berry/src/utils/common.js
@@ -95,7 +95,7 @@ export async function onLarkOAuthClicked(lark_client_id) {
  const state = await getOAuthState();
  if (!state) return;
  let redirect_uri = `${window.location.origin}/oauth/lark`;
-  window.open(`https://open.feishu.cn/open-apis/authen/v1/index?redirect_uri=${redirect_uri}&app_id=${lark_client_id}&state=${state}`);
+  window.open(`https://accounts.feishu.cn/open-apis/authen/v1/authorize?redirect_uri=${redirect_uri}&client_id=${lark_client_id}&state=${state}`);
 }
 export async function onOidcClicked(auth_url, client_id, openInNewTab = false) {
--- a/web/berry/src/views/Channel/component/EditModal.js
+++ b/web/berry/src/views/Channel/component/EditModal.js
@@ -595,6 +595,28 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
                  <FormHelperText id="helper-tex-channel-model_mapping-label"> {inputPrompt.model_mapping} </FormHelperText>
                )}
              </FormControl>
              <FormControl fullWidth error={Boolean(touched.system_prompt && errors.system_prompt)} sx={{ ...theme.typography.otherInput }}>
                {/* <InputLabel htmlFor="channel-model_mapping-label">{inputLabel.model_mapping}</InputLabel> */}
                <TextField
                  multiline
                  id="channel-system_prompt-label"
                  label={inputLabel.system_prompt}
                  value={values.system_prompt}
                  name="system_prompt"
                  onBlur={handleBlur}
                  onChange={handleChange}
                  aria-describedby="helper-text-channel-system_prompt-label"
                  minRows={5}
                  placeholder={inputPrompt.system_prompt}
                />
                {touched.system_prompt && errors.system_prompt ? (
                  <FormHelperText error id="helper-tex-channel-system_prompt-label">
                    {errors.system_prompt}
                  </FormHelperText>
                ) : (
                  <FormHelperText id="helper-tex-channel-system_prompt-label"> {inputPrompt.system_prompt} </FormHelperText>
                )}
              </FormControl>
              <DialogActions>
                <Button onClick={onCancel}>取消</Button>
                <Button disableElevation disabled={isSubmitting} type="submit" variant="contained" color="primary">
--- a/web/berry/src/views/Channel/type/Config.js
+++ b/web/berry/src/views/Channel/type/Config.js
@@ -18,6 +18,7 @@ const defaultConfig = {
    other: '其他参数',
    models: '模型',
    model_mapping: '模型映射关系',
    system_prompt: '系统提示词',
    groups: '用户组',
    config: null
  },
@@ -30,6 +31,7 @@ const defaultConfig = {
    models: '请选择该渠道所支持的模型',
    model_mapping:
      '请输入要修改的模型映射关系，格式为：api请求模型ID:实际转发给渠道的模型ID，使用JSON数组表示，例如：{"gpt-3.5": "gpt-35"}',
    system_prompt:"此项可选，用于强制设置给定的系统提示词，请配合自定义模型 & 模型重定向使用，首先创建一个唯一的自定义模型名称并在上面填入，之后将该自定义模型重定向映射到该渠道一个原生支持的模型此项可选，用于强制设置给定的系统提示词，请配合自定义模型 & 模型重定向使用，首先创建一个唯一的自定义模型名称并在上面填入，之后将该自定义模型重定向映射到该渠道一个原生支持的模型",
    groups: '请选择该渠道所支持的用户组',
    config: null
  },
@@ -91,7 +93,7 @@ const typeConfig = {
      other: '版本号'
    },
    input: {
-      models: ['SparkDesk', 'SparkDesk-v1.1', 'SparkDesk-v2.1', 'SparkDesk-v3.1', 'SparkDesk-v3.1-128K', 'SparkDesk-v3.5', 'SparkDesk-v4.0']
+      models: ['SparkDesk', 'SparkDesk-v1.1', 'SparkDesk-v2.1', 'SparkDesk-v3.1', 'SparkDesk-v3.1-128K', 'SparkDesk-v3.5', 'SparkDesk-v3.5-32K', 'SparkDesk-v4.0']
    },
    prompt: {
      key: '按照如下格式输入：APPID|APISecret|APIKey',
@@ -223,6 +225,9 @@ const typeConfig = {
    },
    modelGroup: 'anthropic'
  },
  45: {
    modelGroup: 'xai'
  },
 };
 export { defaultConfig, typeConfig };
--- a/web/berry/src/views/Token/component/TableRow.js
+++ b/web/berry/src/views/Token/component/TableRow.js
@@ -33,7 +33,7 @@ const COPY_OPTIONS = [
  },
  { key: 'ama', text: 'BotGem', url: 'ama://set-api-key?server={serverAddress}&key=sk-{key}', encode: true },
  { key: 'opencat', text: 'OpenCat', url: 'opencat://team/join?domain={serverAddress}&token=sk-{key}', encode: true },
-  { key: 'lobechat', text: 'LobeChat', url: 'https://lobehub.com/?settings={"keyVaults":{"openai":{"apiKey":"user-key","baseURL":"https://your-proxy.com/v1"}}}', encode: true }
+  { key: 'lobechat', text: 'LobeChat', url: 'https://lobehub.com/?settings={"keyVaults":{"openai":{"apiKey":"sk-{key}","baseURL":"{serverAddress}"}}}', encode: true }
 ];
 function replacePlaceholders(text, key, serverAddress) {
--- a/web/build.sh
+++ b/web/build.sh
--- a/web/default/src/components/ChannelsTable.js
+++ b/web/default/src/components/ChannelsTable.js
@@ -59,6 +59,12 @@ function renderBalance(type, balance) {
  }
 }
 function isShowDetail() {
  return localStorage.getItem("show_detail") === "true";
 }
 const promptID = "detail"
 const ChannelsTable = () => {
  const [channels, setChannels] = useState([]);
  const [loading, setLoading] = useState(true);
@@ -66,7 +72,8 @@ const ChannelsTable = () => {
  const [searchKeyword, setSearchKeyword] = useState('');
  const [searching, setSearching] = useState(false);
  const [updatingBalance, setUpdatingBalance] = useState(false);
-  const [showPrompt, setShowPrompt] = useState(shouldShowPrompt("channel-test"));
+  const [showPrompt, setShowPrompt] = useState(shouldShowPrompt(promptID));
  const [showDetail, setShowDetail] = useState(isShowDetail());
  const loadChannels = async (startIdx) => {
    const res = await API.get(`/api/channel/?p=${startIdx}`);
@@ -120,6 +127,11 @@ const ChannelsTable = () => {
    await loadChannels(activePage - 1);
  };
  const toggleShowDetail = () => {
    setShowDetail(!showDetail);
    localStorage.setItem("show_detail", (!showDetail).toString());
  }
  useEffect(() => {
    loadChannels(0)
      .then()
@@ -364,11 +376,13 @@ const ChannelsTable = () => {
        showPrompt && (
          <Message onDismiss={() => {
            setShowPrompt(false);
-            setPromptShown("channel-test");
+            setPromptShown(promptID);
          }}>
            OpenAI 渠道已经不再支持通过 key 获取余额，因此余额显示为 0。对于支持的渠道类型，请点击余额进行刷新。
            <br/>
            渠道测试仅支持 chat 模型，优先使用 gpt-3.5-turbo，如果该模型不可用则使用你所配置的模型列表中的第一个模型。
            <br/>
            点击下方详情按钮可以显示余额以及设置额外的测试模型。
          </Message>
        )
      }
@@ -428,6 +442,7 @@ const ChannelsTable = () => {
              onClick={() => {
                sortChannel('balance');
              }}
              hidden={!showDetail}
            >
              余额
            </Table.HeaderCell>
@@ -439,7 +454,7 @@ const ChannelsTable = () => {
            >
              优先级
            </Table.HeaderCell>
-            <Table.HeaderCell>测试模型</Table.HeaderCell>
+            <Table.HeaderCell hidden={!showDetail}>测试模型</Table.HeaderCell>
            <Table.HeaderCell>操作</Table.HeaderCell>
          </Table.Row>
        </Table.Header>
@@ -467,7 +482,7 @@ const ChannelsTable = () => {
                      basic
                    />
                  </Table.Cell>
-                  <Table.Cell>
+                  <Table.Cell hidden={!showDetail}>
                    <Popup
                      trigger={<span onClick={() => {
                        updateChannelBalance(channel.id, channel.name, idx);
@@ -494,7 +509,7 @@ const ChannelsTable = () => {
                      basic
                    />
                  </Table.Cell>
-                  <Table.Cell>
+                  <Table.Cell hidden={!showDetail}>
                    <Dropdown
                      placeholder='请选择测试模型'
                      selection
@@ -573,7 +588,7 @@ const ChannelsTable = () => {
        <Table.Footer>
          <Table.Row>
-            <Table.HeaderCell colSpan='9'>
+            <Table.HeaderCell colSpan={showDetail ? "10" : "8"}>
              <Button size='small' as={Link} to='/channel/add' loading={loading}>
                添加新的渠道
              </Button>
@@ -611,6 +626,7 @@ const ChannelsTable = () => {
                }
              />
              <Button size='small' onClick={refresh} loading={loading}>刷新</Button>
              <Button size='small' onClick={toggleShowDetail}>{showDetail ? "隐藏详情" : "详情"}</Button>
            </Table.HeaderCell>
          </Table.Row>
        </Table.Footer>
--- a/web/default/src/components/TokensTable.js
+++ b/web/default/src/components/TokensTable.js
@@ -117,7 +117,7 @@ const TokensTable = () => {
        url = nextUrl;
        break;
      case 'lobechat':
-        url = nextLink + `/?settings={"keyVaults":{"openai":{"apiKey":"sk-${key}","baseURL":"${serverAddress}"/v1"}}}`;
+        url = nextLink + `/?settings={"keyVaults":{"openai":{"apiKey":"sk-${key}","baseURL":"${serverAddress}/v1"}}}`;
        break;
      default:
        url = `sk-${key}`;
@@ -160,7 +160,7 @@ const TokensTable = () => {
        break;
      case 'lobechat':
-        url = chatLink + `/?settings={"keyVaults":{"openai":{"apiKey":"sk-${key}","baseURL":"${serverAddress}"/v1"}}}`;
+        url = chatLink + `/?settings={"keyVaults":{"openai":{"apiKey":"sk-${key}","baseURL":"${serverAddress}/v1"}}}`;
        break;
      default:
--- a/web/default/src/constants/channel.constants.js
+++ b/web/default/src/constants/channel.constants.js
@@ -30,6 +30,7 @@ export const CHANNEL_OPTIONS = [
    { key: 42, text: 'VertexAI', value: 42, color: 'blue' },
    { key: 43, text: 'Proxy', value: 43, color: 'blue' },
    { key: 44, text: 'SiliconFlow', value: 44, color: 'blue' },
    { key: 45, text: 'xAI', value: 45, color: 'blue' },
    { key: 8, text: '自定义渠道', value: 8, color: 'pink' },
    { key: 22, text: '知识库：FastGPT', value: 22, color: 'blue' },
    { key: 21, text: '知识库：AI Proxy', value: 21, color: 'purple' },
--- a/web/default/src/pages/Channel/EditChannel.js
+++ b/web/default/src/pages/Channel/EditChannel.js
@@ -43,6 +43,7 @@ const EditChannel = () => {
    base_url: '',
    other: '',
    model_mapping: '',
    system_prompt: '',
    models: [],
    groups: ['default']
  };
@@ -425,7 +426,7 @@ const EditChannel = () => {
            )
          }
          {
-          inputs.type !== 43 && (
+          inputs.type !== 43 && (<>
              <Form.Field>
                <Form.TextArea
                  label='模型重定向'
@@ -437,6 +438,18 @@ const EditChannel = () => {
                  autoComplete='new-password'
                />
              </Form.Field>
            <Form.Field>
                <Form.TextArea
                  label='系统提示词'
                  placeholder={`此项可选，用于强制设置给定的系统提示词，请配合自定义模型 & 模型重定向使用，首先创建一个唯一的自定义模型名称并在上面填入，之后将该自定义模型重定向映射到该渠道一个原生支持的模型`}
                  name='system_prompt'
                  onChange={handleInputChange}
                  value={inputs.system_prompt}
                  style={{ minHeight: 150, fontFamily: 'JetBrains Mono, Consolas' }}
                  autoComplete='new-password'
                />
              </Form.Field>
              </>
            )
          }
          {
--- a/web/default/src/pages/Channel/index.js
+++ b/web/default/src/pages/Channel/index.js
@@ -2,7 +2,7 @@ import React from 'react';
 import { Header, Segment } from 'semantic-ui-react';
 import ChannelsTable from '../../components/ChannelsTable';
-const File = () => (
+const Channel = () => (
  <>
    <Segment>
      <Header as='h3'>管理渠道</Header>
@@ -11,4 +11,4 @@ const File = () => (
  </>
 );
-export default File;
+export default Channel;
Author	SHA1	Message	Date
JustSong	36c8f4f15c	docs: update readme Some checks are pending CI / Unit tests (push) Waiting to run Details CI / commit_lint (push) Waiting to run Details	2024-12-21 00:33:20 +08:00
JustSong	45b51ea0ee	feat: update feishu oauth login	2024-12-20 23:27:00 +08:00
Calcium-Ion	7c8628bd95	feat: support gzip decode (#1962 ) Some checks failed CI / Unit tests (push) Has been cancelled Details CI / commit_lint (push) Has been cancelled Details	2024-12-04 23:34:24 +08:00
JustSong	6ab87f8a08	feat: add warning in log when system prompt is reset Some checks failed CI / Unit tests (push) Has been cancelled Details CI / commit_lint (push) Has been cancelled Details	2024-11-10 17:18:46 +08:00
JustSong	833fa7ad6f	feat: support set system_prompt for theme air & berry	2024-11-10 15:09:02 +08:00
JustSong	6eb0770a89	feat: support set system prompt for channel (close #1920 )	2024-11-10 14:53:34 +08:00
JustSong	92cd46d64f	feat: able to use ENFORCE_INCLUDE_USAGE to enforce include usage in response Some checks are pending CI / Unit tests (push) Waiting to run Details CI / commit_lint (push) Waiting to run Details	2024-11-10 00:36:08 +08:00
lihangfu	2b2dc2c733	fix: update Spark Lite's domain to lite (#1896 )	2024-11-09 23:55:55 +08:00
JustSong	a3d7df7f89	feat: update GeneralOpenAIRequest	2024-11-09 23:43:08 +08:00
wanthigh	c368232f50	fix: changeoptional field to pointer type (#1907 ) * fix:修复在渠道配置中设置模型重定向时，temperature为0被忽略的问题 * fix: set optional fields to pointer type --------- Co-authored-by: JustSong <songquanpeng@foxmail.com>	2024-11-09 23:31:46 +08:00
Laisky.Cai	cbfc983dc3	feat: add new claude models (#1910 ) * feat: Add new models to ModelList in constants.go * feat: update model lists and mappings for Claude 3.5 versions --------- Co-authored-by: JustSong <39998050+songquanpeng@users.noreply.github.com>	2024-11-09 22:48:54 +08:00
Ryo Shen	8ec092ba44	feat: add support for xAI (#1915 ) Some checks failed CI / Unit tests (push) Has been cancelled Details CI / commit_lint (push) Has been cancelled Details	2024-11-07 23:52:38 +08:00
shaoyun	b0b88a79ff	feat: added support for Claude 3.5 Haiku (#1912 )	2024-11-07 23:51:17 +08:00
JustSong	7e51b04221	feat: able to hide test model selector and balance col Some checks failed CI / Unit tests (push) Has been cancelled Details CI / commit_lint (push) Has been cancelled Details	2024-10-27 18:31:43 +08:00
JustSong	f75a17f8eb	feat: always return usage in stream mode	2024-10-27 17:58:44 +08:00
Wei Tingjiang	6f13a3bb3c	feat: update Gemini adaptor to support custom response format (#1892 )	2024-10-27 17:10:50 +08:00
shaoyun	f092eed1db	feat: add support for Claude Sonnet 3.5 v2 (#1888 )	2024-10-27 17:10:02 +08:00
longkeyy	629378691b	feat: update groq model and price (#1864 )	2024-10-27 17:07:24 +08:00
liangjs	3716e1b0e6	fix: use modelMap when testing a channel (#1855 ) Co-authored-by: oliang <oliang@tencent.com>	2024-10-27 17:06:41 +08:00
Pan, Wen-Ming	a4d6e7a886	feat: add Vertex AI gemini-1.5-pro-002 and gemini-1.5-flash-002 (#1854 )	2024-10-27 17:04:41 +08:00
千寻简	cb772e5d06	fix：unsuccessful lobechat redirection link (#1843 )	2024-10-27 17:03:35 +08:00
lihangfu	e32cb0b844	feat: support SparkDesk-v3.5-32K (#1832 ) Co-authored-by: lihangfu <hfli8@iflytek.com>	2024-10-27 17:02:54 +08:00
		`@@ -1 +0,0 @@`
			{"ServicePort":"80","SecurityPorts":[80],"RepoName":"hanans426/one-api","Arch":"EcsSingle","RunCommand":"echo \"start run command\"\necho \"${AdminPassword}\"\n","SourceCodePath":".","CommandTimeout":3600,"ServiceType":"private","AllowedRegions":["cn-hangzhou","cn-shanghai","cn-beijing"],"ArtifactSourceType":"SourceCode","ImageId":"centos_7_9_x64_20G_alibase_20230613.vhd","RegionId":"cn-hangzhou","CustomParameters":[{"NoEcho":true,"Type":"String","AssociationProperty":"ALIYUN::ECS::Instance::Password","Label":"管理员密码","Name":"AdminPassword"}]}