new-api/relay/channel/openai/adaptor.go

package openai

import (
	"bytes"
	"encoding/json"
	"errors"
	"fmt"
	"io"
	"mime/multipart"
	"net/http"
	"net/textproto"
	"one-api/common"
	"one-api/constant"
	"one-api/dto"
	"one-api/relay/channel"
	"one-api/relay/channel/ai360"
	"one-api/relay/channel/lingyiwanwu"
	"one-api/relay/channel/minimax"
	"one-api/relay/channel/openrouter"
	"one-api/relay/channel/xinference"
	relaycommon "one-api/relay/common"
	"one-api/relay/common_handler"
	relayconstant "one-api/relay/constant"
	"one-api/service"
	"one-api/types"
	"path/filepath"
	"strings"

	"github.com/gin-gonic/gin"
)

type Adaptor struct {
	ChannelType    int
	ResponseFormat string
}

// parseReasoningEffortFromModelSuffix 从模型名称中解析推理级别
// support OAI models: o1-mini/o3-mini/o4-mini/o1/o3 etc...
// minimal effort only available in gpt-5
func parseReasoningEffortFromModelSuffix(model string) (string, string) {
	effortSuffixes := []string{"-high", "-minimal", "-low", "-medium"}
	for _, suffix := range effortSuffixes {
		if strings.HasSuffix(model, suffix) {
			effort := strings.TrimPrefix(suffix, "-")
			originModel := strings.TrimSuffix(model, suffix)
			return effort, originModel
		}
	}
	return "", model
}

func (a *Adaptor) ConvertGeminiRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeminiChatRequest) (any, error) {
	// 使用 service.GeminiToOpenAIRequest 转换请求格式
	openaiRequest, err := service.GeminiToOpenAIRequest(request, info)
	if err != nil {
		return nil, err
	}
	return a.ConvertOpenAIRequest(c, info, openaiRequest)
}

func (a *Adaptor) ConvertClaudeRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.ClaudeRequest) (any, error) {
	//if !strings.Contains(request.Model, "claude") {
	//	return nil, fmt.Errorf("you are using openai channel type with path /v1/messages, only claude model supported convert, but got %s", request.Model)
	//}
	//if common.DebugEnabled {
	//	bodyBytes := []byte(common.GetJsonString(request))
	//	err := os.WriteFile(fmt.Sprintf("claude_request_%s.txt", c.GetString(common.RequestIdKey)), bodyBytes, 0644)
	//	if err != nil {
	//		println(fmt.Sprintf("failed to save request body to file: %v", err))
	//	}
	//}
	aiRequest, err := service.ClaudeToOpenAIRequest(*request, info)
	if err != nil {
		return nil, err
	}
	//if common.DebugEnabled {
	//	println(fmt.Sprintf("convert claude to openai request result: %s", common.GetJsonString(aiRequest)))
	//	// Save request body to file for debugging
	//	bodyBytes := []byte(common.GetJsonString(aiRequest))
	//	err = os.WriteFile(fmt.Sprintf("claude_to_openai_request_%s.txt", c.GetString(common.RequestIdKey)), bodyBytes, 0644)
	//	if err != nil {
	//		println(fmt.Sprintf("failed to save request body to file: %v", err))
	//	}
	//}
	if info.SupportStreamOptions && info.IsStream {
		aiRequest.StreamOptions = &dto.StreamOptions{
			IncludeUsage: true,
		}
	}
	return a.ConvertOpenAIRequest(c, info, aiRequest)
}

func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
	a.ChannelType = info.ChannelType

	// initialize ThinkingContentInfo when thinking_to_content is enabled
	if info.ChannelSetting.ThinkingToContent {
		info.ThinkingContentInfo = relaycommon.ThinkingContentInfo{
			IsFirstThinkingContent:  true,
			SendLastThinkingContent: false,
			HasSentThinkingContent:  false,
		}
	}
}

func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
	if info.RelayMode == relayconstant.RelayModeRealtime {
		if strings.HasPrefix(info.BaseUrl, "https://") {
			baseUrl := strings.TrimPrefix(info.BaseUrl, "https://")
			baseUrl = "wss://" + baseUrl
			info.BaseUrl = baseUrl
		} else if strings.HasPrefix(info.BaseUrl, "http://") {
			baseUrl := strings.TrimPrefix(info.BaseUrl, "http://")
			baseUrl = "ws://" + baseUrl
			info.BaseUrl = baseUrl
		}
	}
	switch info.ChannelType {
	case constant.ChannelTypeAzure:
		apiVersion := info.ApiVersion
		if apiVersion == "" {
			apiVersion = constant.AzureDefaultAPIVersion
		}
		// https://learn.microsoft.com/en-us/azure/cognitive-services/openai/chatgpt-quickstart?pivots=rest-api&tabs=command-line#rest-api
		requestURL := strings.Split(info.RequestURLPath, "?")[0]
		requestURL = fmt.Sprintf("%s?api-version=%s", requestURL, apiVersion)
		task := strings.TrimPrefix(requestURL, "/v1/")

		// 特殊处理 responses API
		if info.RelayMode == relayconstant.RelayModeResponses {
			requestURL = fmt.Sprintf("/openai/v1/responses?api-version=preview")
			return relaycommon.GetFullRequestURL(info.BaseUrl, requestURL, info.ChannelType), nil
		}

		model_ := info.UpstreamModelName
		// 2025年5月10日后创建的渠道不移除.
		if info.ChannelCreateTime < constant.AzureNoRemoveDotTime {
			model_ = strings.Replace(model_, ".", "", -1)
		}
		// https://github.com/songquanpeng/one-api/issues/67
		requestURL = fmt.Sprintf("/openai/deployments/%s/%s", model_, task)
		if info.RelayMode == relayconstant.RelayModeRealtime {
			requestURL = fmt.Sprintf("/openai/realtime?deployment=%s&api-version=%s", model_, apiVersion)
		}
		return relaycommon.GetFullRequestURL(info.BaseUrl, requestURL, info.ChannelType), nil
	case constant.ChannelTypeMiniMax:
		return minimax.GetRequestURL(info)
	case constant.ChannelTypeCustom:
		url := info.BaseUrl
		url = strings.Replace(url, "{model}", info.UpstreamModelName, -1)
		return url, nil
	default:
		if info.RelayFormat == relaycommon.RelayFormatClaude || info.RelayFormat == relaycommon.RelayFormatGemini {
			return fmt.Sprintf("%s/v1/chat/completions", info.BaseUrl), nil
		}
		return relaycommon.GetFullRequestURL(info.BaseUrl, info.RequestURLPath, info.ChannelType), nil
	}
}

func (a *Adaptor) SetupRequestHeader(c *gin.Context, header *http.Header, info *relaycommon.RelayInfo) error {
	channel.SetupApiRequestHeader(info, c, header)
	if info.ChannelType == constant.ChannelTypeAzure {
		header.Set("api-key", info.ApiKey)
		return nil
	}
	if info.ChannelType == constant.ChannelTypeOpenAI && "" != info.Organization {
		header.Set("OpenAI-Organization", info.Organization)
	}
	if info.RelayMode == relayconstant.RelayModeRealtime {
		swp := c.Request.Header.Get("Sec-WebSocket-Protocol")
		if swp != "" {
			items := []string{
				"realtime",
				"openai-insecure-api-key." + info.ApiKey,
				"openai-beta.realtime-v1",
			}
			header.Set("Sec-WebSocket-Protocol", strings.Join(items, ","))
			//req.Header.Set("Sec-WebSocket-Key", c.Request.Header.Get("Sec-WebSocket-Key"))
			//req.Header.Set("Sec-Websocket-Extensions", c.Request.Header.Get("Sec-Websocket-Extensions"))
			//req.Header.Set("Sec-Websocket-Version", c.Request.Header.Get("Sec-Websocket-Version"))
		} else {
			header.Set("openai-beta", "realtime=v1")
			header.Set("Authorization", "Bearer "+info.ApiKey)
		}
	} else {
		header.Set("Authorization", "Bearer "+info.ApiKey)
	}
	if info.ChannelType == constant.ChannelTypeOpenRouter {
		header.Set("HTTP-Referer", "https://www.newapi.ai")
		header.Set("X-Title", "New API")
	}
	return nil
}

func (a *Adaptor) ConvertOpenAIRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
	if request == nil {
		return nil, errors.New("request is nil")
	}
	if info.ChannelType != constant.ChannelTypeOpenAI && info.ChannelType != constant.ChannelTypeAzure {
		request.StreamOptions = nil
	}
	if info.ChannelType == constant.ChannelTypeOpenRouter {
		if len(request.Usage) == 0 {
			request.Usage = json.RawMessage(`{"include":true}`)
		}
		// 适配 OpenRouter 的 thinking 后缀
		if strings.HasSuffix(info.UpstreamModelName, "-thinking") {
			info.UpstreamModelName = strings.TrimSuffix(info.UpstreamModelName, "-thinking")
			request.Model = info.UpstreamModelName
			if len(request.Reasoning) == 0 {
				reasoning := map[string]any{
					"enabled": true,
				}
				if request.ReasoningEffort != "" && request.ReasoningEffort != "none" {
					reasoning["effort"] = request.ReasoningEffort
				}
				marshal, err := common.Marshal(reasoning)
				if err != nil {
					return nil, fmt.Errorf("error marshalling reasoning: %w", err)
				}
				request.Reasoning = marshal
			}
		} else {
			if len(request.Reasoning) == 0 {
				// 适配 OpenAI 的 ReasoningEffort 格式
				if request.ReasoningEffort != "" {
					reasoning := map[string]any{
						"enabled": true,
					}
					if request.ReasoningEffort != "none" {
						reasoning["effort"] = request.ReasoningEffort
						marshal, err := common.Marshal(reasoning)
						if err != nil {
							return nil, fmt.Errorf("error marshalling reasoning: %w", err)
						}
						request.Reasoning = marshal
					}
				}
			}
		}
	}
	if strings.HasPrefix(request.Model, "o") || strings.HasPrefix(request.Model, "gpt-5") {
		if request.MaxCompletionTokens == 0 && request.MaxTokens != 0 {
			request.MaxCompletionTokens = request.MaxTokens
			request.MaxTokens = 0
		}

		if strings.HasPrefix(request.Model, "o") {
			request.Temperature = nil
		}

		if strings.HasPrefix(request.Model, "gpt-5") {
			if request.Model != "gpt-5-chat-latest" {
				request.Temperature = nil
			}
		}

		// 转换模型推理力度后缀
		effort, originModel := parseReasoningEffortFromModelSuffix(request.Model)
		if effort != "" {
			request.ReasoningEffort = effort
			request.Model = originModel
		}

		info.ReasoningEffort = request.ReasoningEffort
		info.UpstreamModelName = request.Model

		// o系列模型developer适配（o1-mini除外）
		if !strings.HasPrefix(request.Model, "o1-mini") && !strings.HasPrefix(request.Model, "o1-preview") {
			//修改第一个Message的内容，将system改为developer
			if len(request.Messages) > 0 && request.Messages[0].Role == "system" {
				request.Messages[0].Role = "developer"
			}
		}
	}

	return request, nil
}

func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
	return request, nil
}

func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
	return request, nil
}

func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
	a.ResponseFormat = request.ResponseFormat
	if info.RelayMode == relayconstant.RelayModeAudioSpeech {
		jsonData, err := json.Marshal(request)
		if err != nil {
			return nil, fmt.Errorf("error marshalling object: %w", err)
		}
		return bytes.NewReader(jsonData), nil
	} else {
		var requestBody bytes.Buffer
		writer := multipart.NewWriter(&requestBody)

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

		// 获取所有表单字段
		formData := c.Request.PostForm

		// 遍历表单字段并打印输出
		for key, values := range formData {
			if key == "model" {
				continue
			}
			for _, value := range values {
				writer.WriteField(key, value)
			}
		}

		// 添加文件字段
		file, header, err := c.Request.FormFile("file")
		if err != nil {
			return nil, errors.New("file is required")
		}
		defer file.Close()

		part, err := writer.CreateFormFile("file", header.Filename)
		if err != nil {
			return nil, errors.New("create form file failed")
		}
		if _, err := io.Copy(part, file); err != nil {
			return nil, errors.New("copy file failed")
		}

		// 关闭 multipart 编写器以设置分界线
		writer.Close()
		c.Request.Header.Set("Content-Type", writer.FormDataContentType())
		return &requestBody, nil
	}
}

func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
	switch info.RelayMode {
	case relayconstant.RelayModeImagesEdits:

		var requestBody bytes.Buffer
		writer := multipart.NewWriter(&requestBody)

		writer.WriteField("model", request.Model)
		// 获取所有表单字段
		formData := c.Request.PostForm
		// 遍历表单字段并打印输出
		for key, values := range formData {
			if key == "model" {
				continue
			}
			for _, value := range values {
				writer.WriteField(key, value)
			}
		}

		// Parse the multipart form to handle both single image and multiple images
		if err := c.Request.ParseMultipartForm(32 << 20); err != nil { // 32MB max memory
			return nil, errors.New("failed to parse multipart form")
		}

		if c.Request.MultipartForm != nil && c.Request.MultipartForm.File != nil {
			// Check if "image" field exists in any form, including array notation
			var imageFiles []*multipart.FileHeader
			var exists bool

			// First check for standard "image" field
			if imageFiles, exists = c.Request.MultipartForm.File["image"]; !exists || len(imageFiles) == 0 {
				// If not found, check for "image[]" field
				if imageFiles, exists = c.Request.MultipartForm.File["image[]"]; !exists || len(imageFiles) == 0 {
					// If still not found, iterate through all fields to find any that start with "image["
					foundArrayImages := false
					for fieldName, files := range c.Request.MultipartForm.File {
						if strings.HasPrefix(fieldName, "image[") && len(files) > 0 {
							foundArrayImages = true
							for _, file := range files {
								imageFiles = append(imageFiles, file)
							}
						}
					}

					// If no image fields found at all
					if !foundArrayImages && (len(imageFiles) == 0) {
						return nil, errors.New("image is required")
					}
				}
			}

			// Process all image files
			for i, fileHeader := range imageFiles {
				file, err := fileHeader.Open()
				if err != nil {
					return nil, fmt.Errorf("failed to open image file %d: %w", i, err)
				}
				defer file.Close()

				// If multiple images, use image[] as the field name
				fieldName := "image"
				if len(imageFiles) > 1 {
					fieldName = "image[]"
				}

				// Determine MIME type based on file extension
				mimeType := detectImageMimeType(fileHeader.Filename)

				// Create a form file with the appropriate content type
				h := make(textproto.MIMEHeader)
				h.Set("Content-Disposition", fmt.Sprintf(`form-data; name="%s"; filename="%s"`, fieldName, fileHeader.Filename))
				h.Set("Content-Type", mimeType)

				part, err := writer.CreatePart(h)
				if err != nil {
					return nil, fmt.Errorf("create form part failed for image %d: %w", i, err)
				}

				if _, err := io.Copy(part, file); err != nil {
					return nil, fmt.Errorf("copy file failed for image %d: %w", i, err)
				}
			}

			// Handle mask file if present
			if maskFiles, exists := c.Request.MultipartForm.File["mask"]; exists && len(maskFiles) > 0 {
				maskFile, err := maskFiles[0].Open()
				if err != nil {
					return nil, errors.New("failed to open mask file")
				}
				defer maskFile.Close()

				// Determine MIME type for mask file
				mimeType := detectImageMimeType(maskFiles[0].Filename)

				// Create a form file with the appropriate content type
				h := make(textproto.MIMEHeader)
				h.Set("Content-Disposition", fmt.Sprintf(`form-data; name="mask"; filename="%s"`, maskFiles[0].Filename))
				h.Set("Content-Type", mimeType)

				maskPart, err := writer.CreatePart(h)
				if err != nil {
					return nil, errors.New("create form file failed for mask")
				}

				if _, err := io.Copy(maskPart, maskFile); err != nil {
					return nil, errors.New("copy mask file failed")
				}
			}
		} else {
			return nil, errors.New("no multipart form data found")
		}

		// 关闭 multipart 编写器以设置分界线
		writer.Close()
		c.Request.Header.Set("Content-Type", writer.FormDataContentType())
		return bytes.NewReader(requestBody.Bytes()), nil

	default:
		return request, nil
	}
}

// detectImageMimeType determines the MIME type based on the file extension
func detectImageMimeType(filename string) string {
	ext := strings.ToLower(filepath.Ext(filename))
	switch ext {
	case ".jpg", ".jpeg":
		return "image/jpeg"
	case ".png":
		return "image/png"
	case ".webp":
		return "image/webp"
	default:
		// Try to detect from extension if possible
		if strings.HasPrefix(ext, ".jp") {
			return "image/jpeg"
		}
		// Default to png as a fallback
		return "image/png"
	}
}

func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
	//  转换模型推理力度后缀
	effort, originModel := parseReasoningEffortFromModelSuffix(request.Model)
	if effort != "" {
		request.Reasoning.Effort = effort
		request.Model = originModel
	}
	return request, nil
}

func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
	if info.RelayMode == relayconstant.RelayModeAudioTranscription ||
		info.RelayMode == relayconstant.RelayModeAudioTranslation ||
		info.RelayMode == relayconstant.RelayModeImagesEdits {
		return channel.DoFormRequest(a, c, info, requestBody)
	} else if info.RelayMode == relayconstant.RelayModeRealtime {
		return channel.DoWssRequest(a, c, info, requestBody)
	} else {
		return channel.DoApiRequest(a, c, info, requestBody)
	}
}

func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
	switch info.RelayMode {
	case relayconstant.RelayModeRealtime:
		err, usage = OpenaiRealtimeHandler(c, info)
	case relayconstant.RelayModeAudioSpeech:
		usage = OpenaiTTSHandler(c, resp, info)
	case relayconstant.RelayModeAudioTranslation:
		fallthrough
	case relayconstant.RelayModeAudioTranscription:
		err, usage = OpenaiSTTHandler(c, resp, info, a.ResponseFormat)
	case relayconstant.RelayModeImagesGenerations, relayconstant.RelayModeImagesEdits:
		usage, err = OpenaiHandlerWithUsage(c, info, resp)
	case relayconstant.RelayModeRerank:
		usage, err = common_handler.RerankHandler(c, info, resp)
	case relayconstant.RelayModeResponses:
		if info.IsStream {
			usage, err = OaiResponsesStreamHandler(c, info, resp)
		} else {
			usage, err = OaiResponsesHandler(c, info, resp)
		}
	default:
		if info.IsStream {
			usage, err = OaiStreamHandler(c, info, resp)
		} else {
			usage, err = OpenaiHandler(c, info, resp)
		}
	}
	return
}

func (a *Adaptor) GetModelList() []string {
	switch a.ChannelType {
	case constant.ChannelType360:
		return ai360.ModelList
	case constant.ChannelTypeLingYiWanWu:
		return lingyiwanwu.ModelList
	case constant.ChannelTypeMiniMax:
		return minimax.ModelList
	case constant.ChannelTypeXinference:
		return xinference.ModelList
	case constant.ChannelTypeOpenRouter:
		return openrouter.ModelList
	default:
		return ModelList
	}
}

func (a *Adaptor) GetChannelName() string {
	switch a.ChannelType {
	case constant.ChannelType360:
		return ai360.ChannelName
	case constant.ChannelTypeLingYiWanWu:
		return lingyiwanwu.ChannelName
	case constant.ChannelTypeMiniMax:
		return minimax.ChannelName
	case constant.ChannelTypeXinference:
		return xinference.ChannelName
	case constant.ChannelTypeOpenRouter:
		return openrouter.ChannelName
	default:
		return ChannelName
	}
}