初始化导入 new-api 源码

This commit is contained in:
OpenClaw Task Bot
2026-04-09 22:31:14 +08:00
commit 75bda2e845
994 changed files with 250292 additions and 0 deletions

View File

@@ -0,0 +1,402 @@
package volcengine
import (
"bytes"
"encoding/json"
"errors"
"fmt"
"io"
"net/http"
"path/filepath"
"strings"
channelconstant "github.com/QuantumNous/new-api/constant"
"github.com/QuantumNous/new-api/dto"
"github.com/QuantumNous/new-api/relay/channel"
"github.com/QuantumNous/new-api/relay/channel/claude"
"github.com/QuantumNous/new-api/relay/channel/openai"
relaycommon "github.com/QuantumNous/new-api/relay/common"
"github.com/QuantumNous/new-api/relay/constant"
"github.com/QuantumNous/new-api/setting/model_setting"
"github.com/QuantumNous/new-api/types"
"github.com/gin-gonic/gin"
"github.com/samber/lo"
)
const (
contextKeyTTSRequest = "volcengine_tts_request"
contextKeyResponseFormat = "response_format"
)
type Adaptor struct {
}
func (a *Adaptor) ConvertGeminiRequest(*gin.Context, *relaycommon.RelayInfo, *dto.GeminiChatRequest) (any, error) {
//TODO implement me
return nil, errors.New("not implemented")
}
func (a *Adaptor) ConvertClaudeRequest(c *gin.Context, info *relaycommon.RelayInfo, req *dto.ClaudeRequest) (any, error) {
if _, ok := channelconstant.ChannelSpecialBases[info.ChannelBaseUrl]; ok {
adaptor := claude.Adaptor{}
return adaptor.ConvertClaudeRequest(c, info, req)
}
adaptor := openai.Adaptor{}
return adaptor.ConvertClaudeRequest(c, info, req)
}
func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
if info.RelayMode != constant.RelayModeAudioSpeech {
return nil, errors.New("unsupported audio relay mode")
}
appID, token, err := parseVolcengineAuth(info.ApiKey)
if err != nil {
return nil, err
}
voiceType := mapVoiceType(request.Voice)
speedRatio := lo.FromPtrOr(request.Speed, 0.0)
encoding := mapEncoding(request.ResponseFormat)
c.Set(contextKeyResponseFormat, encoding)
volcRequest := VolcengineTTSRequest{
App: VolcengineTTSApp{
AppID: appID,
Token: token,
Cluster: "volcano_tts",
},
User: VolcengineTTSUser{
UID: "openai_relay_user",
},
Audio: VolcengineTTSAudio{
VoiceType: voiceType,
Encoding: encoding,
SpeedRatio: speedRatio,
Rate: 24000,
},
Request: VolcengineTTSReqInfo{
ReqID: generateRequestID(),
Text: request.Input,
Operation: "submit",
Model: info.OriginModelName,
},
}
if len(request.Metadata) > 0 {
if err = json.Unmarshal(request.Metadata, &volcRequest); err != nil {
return nil, fmt.Errorf("error unmarshalling metadata to volcengine request: %w", err)
}
}
c.Set(contextKeyTTSRequest, volcRequest)
if volcRequest.Request.Operation == "submit" {
info.IsStream = true
}
jsonData, err := json.Marshal(volcRequest)
if err != nil {
return nil, fmt.Errorf("error marshalling volcengine request: %w", err)
}
return bytes.NewReader(jsonData), nil
}
func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
switch info.RelayMode {
case constant.RelayModeImagesGenerations:
return request, nil
// 根据官方文档,并没有发现豆包生图支持表单请求:https://www.volcengine.com/docs/82379/1824121
//case constant.RelayModeImagesEdits:
//
// var requestBody bytes.Buffer
// writer := multipart.NewWriter(&requestBody)
//
// writer.WriteField("model", request.Model)
//
// formData := c.Request.PostForm
// for key, values := range formData {
// if key == "model" {
// continue
// }
// for _, value := range values {
// writer.WriteField(key, value)
// }
// }
//
// if err := c.Request.ParseMultipartForm(32 << 20); err != nil {
// return nil, errors.New("failed to parse multipart form")
// }
//
// if c.Request.MultipartForm != nil && c.Request.MultipartForm.File != nil {
// var imageFiles []*multipart.FileHeader
// var exists bool
//
// if imageFiles, exists = c.Request.MultipartForm.File["image"]; !exists || len(imageFiles) == 0 {
// if imageFiles, exists = c.Request.MultipartForm.File["image[]"]; !exists || len(imageFiles) == 0 {
// 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 !foundArrayImages && (len(imageFiles) == 0) {
// return nil, errors.New("image is required")
// }
// }
// }
//
// 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()
//
// fieldName := "image"
// if len(imageFiles) > 1 {
// fieldName = "image[]"
// }
//
// mimeType := detectImageMimeType(fileHeader.Filename)
//
// 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)
// }
// }
//
// 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()
//
// mimeType := detectImageMimeType(maskFiles[0].Filename)
//
// 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")
// }
//
// writer.Close()
// c.Request.Header.Set("Content-Type", writer.FormDataContentType())
// return bytes.NewReader(requestBody.Bytes()), nil
default:
return request, nil
}
}
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:
if strings.HasPrefix(ext, ".jp") {
return "image/jpeg"
}
return "image/png"
}
}
func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
}
func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
baseUrl := info.ChannelBaseUrl
if baseUrl == "" {
baseUrl = channelconstant.ChannelBaseURLs[channelconstant.ChannelTypeVolcEngine]
}
specialPlan, hasSpecialPlan := channelconstant.ChannelSpecialBases[baseUrl]
switch info.RelayFormat {
case types.RelayFormatClaude:
if hasSpecialPlan && specialPlan.ClaudeBaseURL != "" {
return fmt.Sprintf("%s/v1/messages", specialPlan.ClaudeBaseURL), nil
}
if strings.HasPrefix(info.UpstreamModelName, "bot") {
return fmt.Sprintf("%s/api/v3/bots/chat/completions", baseUrl), nil
}
return fmt.Sprintf("%s/api/v3/chat/completions", baseUrl), nil
default:
switch info.RelayMode {
case constant.RelayModeChatCompletions:
if hasSpecialPlan && specialPlan.OpenAIBaseURL != "" {
return fmt.Sprintf("%s/chat/completions", specialPlan.OpenAIBaseURL), nil
}
if strings.HasPrefix(info.UpstreamModelName, "bot") {
return fmt.Sprintf("%s/api/v3/bots/chat/completions", baseUrl), nil
}
return fmt.Sprintf("%s/api/v3/chat/completions", baseUrl), nil
case constant.RelayModeEmbeddings:
return fmt.Sprintf("%s/api/v3/embeddings", baseUrl), nil
//豆包的图生图也走generations接口: https://www.volcengine.com/docs/82379/1824121
case constant.RelayModeImagesGenerations, constant.RelayModeImagesEdits:
return fmt.Sprintf("%s/api/v3/images/generations", baseUrl), nil
//case constant.RelayModeImagesEdits:
// return fmt.Sprintf("%s/api/v3/images/edits", baseUrl), nil
case constant.RelayModeRerank:
return fmt.Sprintf("%s/api/v3/rerank", baseUrl), nil
case constant.RelayModeResponses:
return fmt.Sprintf("%s/api/v3/responses", baseUrl), nil
case constant.RelayModeAudioSpeech:
if baseUrl == channelconstant.ChannelBaseURLs[channelconstant.ChannelTypeVolcEngine] {
return "wss://openspeech.bytedance.com/api/v1/tts/ws_binary", nil
}
return fmt.Sprintf("%s/v1/audio/speech", baseUrl), nil
default:
}
}
return "", fmt.Errorf("unsupported relay mode: %d", info.RelayMode)
}
func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
channel.SetupApiRequestHeader(info, c, req)
if info.RelayMode == constant.RelayModeAudioSpeech {
parts := strings.Split(info.ApiKey, "|")
if len(parts) == 2 {
req.Set("Authorization", "Bearer;"+parts[1])
}
req.Set("Content-Type", "application/json")
return nil
} else if info.RelayMode == constant.RelayModeImagesEdits {
req.Set("Content-Type", gin.MIMEJSON)
}
req.Set("Authorization", "Bearer "+info.ApiKey)
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 !model_setting.ShouldPreserveThinkingSuffix(info.OriginModelName) &&
strings.HasSuffix(info.UpstreamModelName, "-thinking") &&
strings.HasPrefix(info.UpstreamModelName, "deepseek") {
info.UpstreamModelName = strings.TrimSuffix(info.UpstreamModelName, "-thinking")
request.Model = info.UpstreamModelName
request.THINKING = json.RawMessage(`{"type": "enabled"}`)
}
return request, nil
}
func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
return nil, nil
}
func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
return request, nil
}
func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
return request, nil
}
func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
if info.RelayMode == constant.RelayModeAudioSpeech {
baseUrl := info.ChannelBaseUrl
if baseUrl == "" {
baseUrl = channelconstant.ChannelBaseURLs[channelconstant.ChannelTypeVolcEngine]
}
if baseUrl == channelconstant.ChannelBaseURLs[channelconstant.ChannelTypeVolcEngine] {
if info.IsStream {
return nil, nil
}
}
}
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) {
if info.RelayFormat == types.RelayFormatClaude {
if _, ok := channelconstant.ChannelSpecialBases[info.ChannelBaseUrl]; ok {
adaptor := claude.Adaptor{}
return adaptor.DoResponse(c, resp, info)
}
}
if info.RelayMode == constant.RelayModeAudioSpeech {
encoding := mapEncoding(c.GetString(contextKeyResponseFormat))
if info.IsStream {
volcRequestInterface, exists := c.Get(contextKeyTTSRequest)
if !exists {
return nil, types.NewErrorWithStatusCode(
errors.New("volcengine TTS request not found in context"),
types.ErrorCodeBadRequestBody,
http.StatusInternalServerError,
)
}
volcRequest, ok := volcRequestInterface.(VolcengineTTSRequest)
if !ok {
return nil, types.NewErrorWithStatusCode(
errors.New("invalid volcengine TTS request type"),
types.ErrorCodeBadRequestBody,
http.StatusInternalServerError,
)
}
// Get the WebSocket URL
requestURL, urlErr := a.GetRequestURL(info)
if urlErr != nil {
return nil, types.NewErrorWithStatusCode(
urlErr,
types.ErrorCodeBadRequestBody,
http.StatusInternalServerError,
)
}
return handleTTSWebSocketResponse(c, requestURL, volcRequest, info, encoding)
}
return handleTTSResponse(c, resp, info, encoding)
}
adaptor := openai.Adaptor{}
usage, err = adaptor.DoResponse(c, resp, info)
return
}
func (a *Adaptor) GetModelList() []string {
return ModelList
}
func (a *Adaptor) GetChannelName() string {
return ChannelName
}

View File

@@ -0,0 +1,19 @@
package volcengine
var ModelList = []string{
"Doubao-pro-128k",
"Doubao-pro-32k",
"Doubao-pro-4k",
"Doubao-lite-128k",
"Doubao-lite-32k",
"Doubao-lite-4k",
"Doubao-embedding",
"doubao-seedream-4-0-250828",
"seedream-4-0-250828",
"doubao-seedance-1-0-pro-250528",
"seedance-1-0-pro-250528",
"doubao-seed-1-6-thinking-250715",
"seed-1-6-thinking-250715",
}
var ChannelName = "volcengine"

View File

@@ -0,0 +1,533 @@
package volcengine
import (
"bytes"
"encoding/binary"
"fmt"
"io"
"math"
"github.com/gorilla/websocket"
)
type (
EventType int32
MsgType uint8
MsgTypeFlagBits uint8
VersionBits uint8
HeaderSizeBits uint8
SerializationBits uint8
CompressionBits uint8
)
const (
MsgTypeFlagNoSeq MsgTypeFlagBits = 0
MsgTypeFlagPositiveSeq MsgTypeFlagBits = 0b1
MsgTypeFlagNegativeSeq MsgTypeFlagBits = 0b11
MsgTypeFlagWithEvent MsgTypeFlagBits = 0b100
)
const (
Version1 VersionBits = iota + 1
)
const (
HeaderSize4 HeaderSizeBits = iota + 1
)
const (
SerializationJSON SerializationBits = 0b1
)
const (
CompressionNone CompressionBits = 0
)
const (
MsgTypeFullClientRequest MsgType = 0b1
MsgTypeAudioOnlyClient MsgType = 0b10
MsgTypeFullServerResponse MsgType = 0b1001
MsgTypeAudioOnlyServer MsgType = 0b1011
MsgTypeFrontEndResultServer MsgType = 0b1100
MsgTypeError MsgType = 0b1111
)
func (t MsgType) String() string {
switch t {
case MsgTypeFullClientRequest:
return "MsgType_FullClientRequest"
case MsgTypeAudioOnlyClient:
return "MsgType_AudioOnlyClient"
case MsgTypeFullServerResponse:
return "MsgType_FullServerResponse"
case MsgTypeAudioOnlyServer:
return "MsgType_AudioOnlyServer"
case MsgTypeError:
return "MsgType_Error"
case MsgTypeFrontEndResultServer:
return "MsgType_FrontEndResultServer"
default:
return fmt.Sprintf("MsgType_(%d)", t)
}
}
const (
EventType_None EventType = 0
EventType_StartConnection EventType = 1
EventType_FinishConnection EventType = 2
EventType_ConnectionStarted EventType = 50
EventType_ConnectionFailed EventType = 51
EventType_ConnectionFinished EventType = 52
EventType_StartSession EventType = 100
EventType_CancelSession EventType = 101
EventType_FinishSession EventType = 102
EventType_SessionStarted EventType = 150
EventType_SessionCanceled EventType = 151
EventType_SessionFinished EventType = 152
EventType_SessionFailed EventType = 153
EventType_UsageResponse EventType = 154
EventType_TaskRequest EventType = 200
EventType_UpdateConfig EventType = 201
EventType_AudioMuted EventType = 250
EventType_SayHello EventType = 300
EventType_TTSSentenceStart EventType = 350
EventType_TTSSentenceEnd EventType = 351
EventType_TTSResponse EventType = 352
EventType_TTSEnded EventType = 359
EventType_PodcastRoundStart EventType = 360
EventType_PodcastRoundResponse EventType = 361
EventType_PodcastRoundEnd EventType = 362
EventType_ASRInfo EventType = 450
EventType_ASRResponse EventType = 451
EventType_ASREnded EventType = 459
EventType_ChatTTSText EventType = 500
EventType_ChatResponse EventType = 550
EventType_ChatEnded EventType = 559
EventType_SourceSubtitleStart EventType = 650
EventType_SourceSubtitleResponse EventType = 651
EventType_SourceSubtitleEnd EventType = 652
EventType_TranslationSubtitleStart EventType = 653
EventType_TranslationSubtitleResponse EventType = 654
EventType_TranslationSubtitleEnd EventType = 655
)
func (t EventType) String() string {
switch t {
case EventType_None:
return "EventType_None"
case EventType_StartConnection:
return "EventType_StartConnection"
case EventType_FinishConnection:
return "EventType_FinishConnection"
case EventType_ConnectionStarted:
return "EventType_ConnectionStarted"
case EventType_ConnectionFailed:
return "EventType_ConnectionFailed"
case EventType_ConnectionFinished:
return "EventType_ConnectionFinished"
case EventType_StartSession:
return "EventType_StartSession"
case EventType_CancelSession:
return "EventType_CancelSession"
case EventType_FinishSession:
return "EventType_FinishSession"
case EventType_SessionStarted:
return "EventType_SessionStarted"
case EventType_SessionCanceled:
return "EventType_SessionCanceled"
case EventType_SessionFinished:
return "EventType_SessionFinished"
case EventType_SessionFailed:
return "EventType_SessionFailed"
case EventType_UsageResponse:
return "EventType_UsageResponse"
case EventType_TaskRequest:
return "EventType_TaskRequest"
case EventType_UpdateConfig:
return "EventType_UpdateConfig"
case EventType_AudioMuted:
return "EventType_AudioMuted"
case EventType_SayHello:
return "EventType_SayHello"
case EventType_TTSSentenceStart:
return "EventType_TTSSentenceStart"
case EventType_TTSSentenceEnd:
return "EventType_TTSSentenceEnd"
case EventType_TTSResponse:
return "EventType_TTSResponse"
case EventType_TTSEnded:
return "EventType_TTSEnded"
case EventType_PodcastRoundStart:
return "EventType_PodcastRoundStart"
case EventType_PodcastRoundResponse:
return "EventType_PodcastRoundResponse"
case EventType_PodcastRoundEnd:
return "EventType_PodcastRoundEnd"
case EventType_ASRInfo:
return "EventType_ASRInfo"
case EventType_ASRResponse:
return "EventType_ASRResponse"
case EventType_ASREnded:
return "EventType_ASREnded"
case EventType_ChatTTSText:
return "EventType_ChatTTSText"
case EventType_ChatResponse:
return "EventType_ChatResponse"
case EventType_ChatEnded:
return "EventType_ChatEnded"
case EventType_SourceSubtitleStart:
return "EventType_SourceSubtitleStart"
case EventType_SourceSubtitleResponse:
return "EventType_SourceSubtitleResponse"
case EventType_SourceSubtitleEnd:
return "EventType_SourceSubtitleEnd"
case EventType_TranslationSubtitleStart:
return "EventType_TranslationSubtitleStart"
case EventType_TranslationSubtitleResponse:
return "EventType_TranslationSubtitleResponse"
case EventType_TranslationSubtitleEnd:
return "EventType_TranslationSubtitleEnd"
default:
return fmt.Sprintf("EventType_(%d)", t)
}
}
type Message struct {
Version VersionBits
HeaderSize HeaderSizeBits
MsgType MsgType
MsgTypeFlag MsgTypeFlagBits
Serialization SerializationBits
Compression CompressionBits
EventType EventType
SessionID string
ConnectID string
Sequence int32
ErrorCode uint32
Payload []byte
}
func NewMessageFromBytes(data []byte) (*Message, error) {
if len(data) < 3 {
return nil, fmt.Errorf("data too short: expected at least 3 bytes, got %d", len(data))
}
typeAndFlag := data[1]
msg, err := NewMessage(MsgType(typeAndFlag>>4), MsgTypeFlagBits(typeAndFlag&0b00001111))
if err != nil {
return nil, err
}
if err := msg.Unmarshal(data); err != nil {
return nil, err
}
return msg, nil
}
func NewMessage(msgType MsgType, flag MsgTypeFlagBits) (*Message, error) {
return &Message{
MsgType: msgType,
MsgTypeFlag: flag,
Version: Version1,
HeaderSize: HeaderSize4,
Serialization: SerializationJSON,
Compression: CompressionNone,
}, nil
}
func (m *Message) String() string {
switch m.MsgType {
case MsgTypeAudioOnlyServer, MsgTypeAudioOnlyClient:
if m.MsgTypeFlag == MsgTypeFlagPositiveSeq || m.MsgTypeFlag == MsgTypeFlagNegativeSeq {
return fmt.Sprintf("%s, %s, Sequence: %d, PayloadSize: %d", m.MsgType, m.EventType, m.Sequence, len(m.Payload))
}
return fmt.Sprintf("%s, %s, PayloadSize: %d", m.MsgType, m.EventType, len(m.Payload))
case MsgTypeError:
return fmt.Sprintf("%s, %s, ErrorCode: %d, Payload: %s", m.MsgType, m.EventType, m.ErrorCode, string(m.Payload))
default:
if m.MsgTypeFlag == MsgTypeFlagPositiveSeq || m.MsgTypeFlag == MsgTypeFlagNegativeSeq {
return fmt.Sprintf("%s, %s, Sequence: %d, Payload: %s",
m.MsgType, m.EventType, m.Sequence, string(m.Payload))
}
return fmt.Sprintf("%s, %s, Payload: %s", m.MsgType, m.EventType, string(m.Payload))
}
}
func (m *Message) Marshal() ([]byte, error) {
buf := new(bytes.Buffer)
header := []uint8{
uint8(m.Version)<<4 | uint8(m.HeaderSize),
uint8(m.MsgType)<<4 | uint8(m.MsgTypeFlag),
uint8(m.Serialization)<<4 | uint8(m.Compression),
}
headerSize := 4 * int(m.HeaderSize)
if padding := headerSize - len(header); padding > 0 {
header = append(header, make([]uint8, padding)...)
}
if err := binary.Write(buf, binary.BigEndian, header); err != nil {
return nil, err
}
writers, err := m.writers()
if err != nil {
return nil, err
}
for _, write := range writers {
if err := write(buf); err != nil {
return nil, err
}
}
return buf.Bytes(), nil
}
func (m *Message) Unmarshal(data []byte) error {
buf := bytes.NewBuffer(data)
versionAndHeaderSize, err := buf.ReadByte()
if err != nil {
return err
}
m.Version = VersionBits(versionAndHeaderSize >> 4)
m.HeaderSize = HeaderSizeBits(versionAndHeaderSize & 0b00001111)
_, err = buf.ReadByte()
if err != nil {
return err
}
serializationCompression, err := buf.ReadByte()
if err != nil {
return err
}
m.Serialization = SerializationBits(serializationCompression & 0b11110000)
m.Compression = CompressionBits(serializationCompression & 0b00001111)
headerSize := 4 * int(m.HeaderSize)
readSize := 3
if paddingSize := headerSize - readSize; paddingSize > 0 {
if n, err := buf.Read(make([]byte, paddingSize)); err != nil || n < paddingSize {
return fmt.Errorf("insufficient header bytes: expected %d, got %d", paddingSize, n)
}
}
readers, err := m.readers()
if err != nil {
return err
}
for _, read := range readers {
if err := read(buf); err != nil {
return err
}
}
if _, err := buf.ReadByte(); err != io.EOF {
return fmt.Errorf("unexpected data after message: %v", err)
}
return nil
}
func (m *Message) writers() (writers []func(*bytes.Buffer) error, _ error) {
if m.MsgTypeFlag == MsgTypeFlagWithEvent {
writers = append(writers, m.writeEvent, m.writeSessionID)
}
switch m.MsgType {
case MsgTypeFullClientRequest, MsgTypeFullServerResponse, MsgTypeFrontEndResultServer, MsgTypeAudioOnlyClient, MsgTypeAudioOnlyServer:
if m.MsgTypeFlag == MsgTypeFlagPositiveSeq || m.MsgTypeFlag == MsgTypeFlagNegativeSeq {
writers = append(writers, m.writeSequence)
}
case MsgTypeError:
writers = append(writers, m.writeErrorCode)
default:
return nil, fmt.Errorf("unsupported message type: %d", m.MsgType)
}
writers = append(writers, m.writePayload)
return writers, nil
}
func (m *Message) writeEvent(buf *bytes.Buffer) error {
return binary.Write(buf, binary.BigEndian, m.EventType)
}
func (m *Message) writeSessionID(buf *bytes.Buffer) error {
switch m.EventType {
case EventType_StartConnection, EventType_FinishConnection,
EventType_ConnectionStarted, EventType_ConnectionFailed:
return nil
}
size := len(m.SessionID)
if int64(size) > math.MaxUint32 {
return fmt.Errorf("session ID size (%d) exceeds max(uint32)", size)
}
if err := binary.Write(buf, binary.BigEndian, uint32(size)); err != nil {
return err
}
buf.WriteString(m.SessionID)
return nil
}
func (m *Message) writeSequence(buf *bytes.Buffer) error {
return binary.Write(buf, binary.BigEndian, m.Sequence)
}
func (m *Message) writeErrorCode(buf *bytes.Buffer) error {
return binary.Write(buf, binary.BigEndian, m.ErrorCode)
}
func (m *Message) writePayload(buf *bytes.Buffer) error {
size := len(m.Payload)
if int64(size) > math.MaxUint32 {
return fmt.Errorf("payload size (%d) exceeds max(uint32)", size)
}
if err := binary.Write(buf, binary.BigEndian, uint32(size)); err != nil {
return err
}
buf.Write(m.Payload)
return nil
}
func (m *Message) readers() (readers []func(*bytes.Buffer) error, _ error) {
switch m.MsgType {
case MsgTypeFullClientRequest, MsgTypeFullServerResponse, MsgTypeFrontEndResultServer, MsgTypeAudioOnlyClient, MsgTypeAudioOnlyServer:
if m.MsgTypeFlag == MsgTypeFlagPositiveSeq || m.MsgTypeFlag == MsgTypeFlagNegativeSeq {
readers = append(readers, m.readSequence)
}
case MsgTypeError:
readers = append(readers, m.readErrorCode)
default:
return nil, fmt.Errorf("unsupported message type: %d", m.MsgType)
}
if m.MsgTypeFlag == MsgTypeFlagWithEvent {
readers = append(readers, m.readEvent, m.readSessionID, m.readConnectID)
}
readers = append(readers, m.readPayload)
return readers, nil
}
func (m *Message) readEvent(buf *bytes.Buffer) error {
return binary.Read(buf, binary.BigEndian, &m.EventType)
}
func (m *Message) readSessionID(buf *bytes.Buffer) error {
switch m.EventType {
case EventType_StartConnection, EventType_FinishConnection,
EventType_ConnectionStarted, EventType_ConnectionFailed,
EventType_ConnectionFinished:
return nil
}
var size uint32
if err := binary.Read(buf, binary.BigEndian, &size); err != nil {
return err
}
if size > 0 {
m.SessionID = string(buf.Next(int(size)))
}
return nil
}
func (m *Message) readConnectID(buf *bytes.Buffer) error {
switch m.EventType {
case EventType_ConnectionStarted, EventType_ConnectionFailed,
EventType_ConnectionFinished:
default:
return nil
}
var size uint32
if err := binary.Read(buf, binary.BigEndian, &size); err != nil {
return err
}
if size > 0 {
m.ConnectID = string(buf.Next(int(size)))
}
return nil
}
func (m *Message) readSequence(buf *bytes.Buffer) error {
return binary.Read(buf, binary.BigEndian, &m.Sequence)
}
func (m *Message) readErrorCode(buf *bytes.Buffer) error {
return binary.Read(buf, binary.BigEndian, &m.ErrorCode)
}
func (m *Message) readPayload(buf *bytes.Buffer) error {
var size uint32
if err := binary.Read(buf, binary.BigEndian, &size); err != nil {
return err
}
if size > 0 {
m.Payload = buf.Next(int(size))
}
return nil
}
func ReceiveMessage(conn *websocket.Conn) (*Message, error) {
mt, frame, err := conn.ReadMessage()
if err != nil {
return nil, err
}
if mt != websocket.BinaryMessage && mt != websocket.TextMessage {
return nil, fmt.Errorf("unexpected Websocket message type: %d", mt)
}
msg, err := NewMessageFromBytes(frame)
if err != nil {
return nil, err
}
return msg, nil
}
func FullClientRequest(conn *websocket.Conn, payload []byte) error {
msg, err := NewMessage(MsgTypeFullClientRequest, MsgTypeFlagNoSeq)
if err != nil {
return err
}
msg.Payload = payload
frame, err := msg.Marshal()
if err != nil {
return err
}
return conn.WriteMessage(websocket.BinaryMessage, frame)
}

View File

@@ -0,0 +1,305 @@
package volcengine
import (
"context"
"encoding/base64"
"encoding/json"
"errors"
"fmt"
"io"
"net/http"
"strings"
"github.com/QuantumNous/new-api/dto"
relaycommon "github.com/QuantumNous/new-api/relay/common"
"github.com/QuantumNous/new-api/types"
"github.com/gin-gonic/gin"
"github.com/google/uuid"
"github.com/gorilla/websocket"
)
type VolcengineTTSRequest struct {
App VolcengineTTSApp `json:"app"`
User VolcengineTTSUser `json:"user"`
Audio VolcengineTTSAudio `json:"audio"`
Request VolcengineTTSReqInfo `json:"request"`
}
type VolcengineTTSApp struct {
AppID string `json:"appid"`
Token string `json:"token"`
Cluster string `json:"cluster"`
}
type VolcengineTTSUser struct {
UID string `json:"uid"`
}
type VolcengineTTSAudio struct {
VoiceType string `json:"voice_type"`
Encoding string `json:"encoding"`
SpeedRatio float64 `json:"speed_ratio"`
Rate int `json:"rate"`
Bitrate int `json:"bitrate,omitempty"`
LoudnessRatio float64 `json:"loudness_ratio,omitempty"`
EnableEmotion bool `json:"enable_emotion,omitempty"`
Emotion string `json:"emotion,omitempty"`
EmotionScale float64 `json:"emotion_scale,omitempty"`
ExplicitLanguage string `json:"explicit_language,omitempty"`
ContextLanguage string `json:"context_language,omitempty"`
}
type VolcengineTTSReqInfo struct {
ReqID string `json:"reqid"`
Text string `json:"text"`
Operation string `json:"operation"`
Model string `json:"model,omitempty"`
TextType string `json:"text_type,omitempty"`
SilenceDuration float64 `json:"silence_duration,omitempty"`
WithTimestamp interface{} `json:"with_timestamp,omitempty"`
ExtraParam *VolcengineTTSExtraParam `json:"extra_param,omitempty"`
}
type VolcengineTTSExtraParam struct {
DisableMarkdownFilter bool `json:"disable_markdown_filter,omitempty"`
EnableLatexTn bool `json:"enable_latex_tn,omitempty"`
MuteCutThreshold string `json:"mute_cut_threshold,omitempty"`
MuteCutRemainMs string `json:"mute_cut_remain_ms,omitempty"`
DisableEmojiFilter bool `json:"disable_emoji_filter,omitempty"`
UnsupportedCharRatioThresh float64 `json:"unsupported_char_ratio_thresh,omitempty"`
AigcWatermark bool `json:"aigc_watermark,omitempty"`
CacheConfig *VolcengineTTSCacheConfig `json:"cache_config,omitempty"`
}
type VolcengineTTSCacheConfig struct {
TextType int `json:"text_type,omitempty"`
UseCache bool `json:"use_cache,omitempty"`
}
type VolcengineTTSResponse struct {
ReqID string `json:"reqid"`
Code int `json:"code"`
Message string `json:"message"`
Sequence int `json:"sequence"`
Data string `json:"data"`
Addition *VolcengineTTSAdditionInfo `json:"addition,omitempty"`
}
type VolcengineTTSAdditionInfo struct {
Duration string `json:"duration"`
}
var openAIToVolcengineVoiceMap = map[string]string{
"alloy": "zh_male_M392_conversation_wvae_bigtts",
"echo": "zh_male_wenhao_mars_bigtts",
"fable": "zh_female_tianmei_mars_bigtts",
"onyx": "zh_male_zhibei_mars_bigtts",
"nova": "zh_female_shuangkuaisisi_mars_bigtts",
"shimmer": "zh_female_cancan_mars_bigtts",
}
var responseFormatToEncodingMap = map[string]string{
"mp3": "mp3",
"opus": "ogg_opus",
"aac": "mp3",
"flac": "mp3",
"wav": "wav",
"pcm": "pcm",
}
func parseVolcengineAuth(apiKey string) (appID, token string, err error) {
parts := strings.Split(apiKey, "|")
if len(parts) != 2 {
return "", "", errors.New("invalid api key format, expected: appid|access_token")
}
return parts[0], parts[1], nil
}
func mapVoiceType(openAIVoice string) string {
if voice, ok := openAIToVolcengineVoiceMap[openAIVoice]; ok {
return voice
}
return openAIVoice
}
func mapEncoding(responseFormat string) string {
if encoding, ok := responseFormatToEncodingMap[responseFormat]; ok {
return encoding
}
return "mp3"
}
func getContentTypeByEncoding(encoding string) string {
contentTypeMap := map[string]string{
"mp3": "audio/mpeg",
"ogg_opus": "audio/ogg",
"wav": "audio/wav",
"pcm": "audio/pcm",
}
if ct, ok := contentTypeMap[encoding]; ok {
return ct
}
return "application/octet-stream"
}
func handleTTSResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo, encoding string) (usage any, err *types.NewAPIError) {
body, readErr := io.ReadAll(resp.Body)
if readErr != nil {
return nil, types.NewErrorWithStatusCode(
errors.New("failed to read volcengine response"),
types.ErrorCodeReadResponseBodyFailed,
http.StatusInternalServerError,
)
}
defer resp.Body.Close()
var volcResp VolcengineTTSResponse
if unmarshalErr := json.Unmarshal(body, &volcResp); unmarshalErr != nil {
return nil, types.NewErrorWithStatusCode(
errors.New("failed to parse volcengine response"),
types.ErrorCodeBadResponseBody,
http.StatusInternalServerError,
)
}
if volcResp.Code != 3000 {
return nil, types.NewErrorWithStatusCode(
errors.New(volcResp.Message),
types.ErrorCodeBadResponse,
http.StatusBadRequest,
)
}
audioData, decodeErr := base64.StdEncoding.DecodeString(volcResp.Data)
if decodeErr != nil {
return nil, types.NewErrorWithStatusCode(
errors.New("failed to decode audio data"),
types.ErrorCodeBadResponseBody,
http.StatusInternalServerError,
)
}
contentType := getContentTypeByEncoding(encoding)
c.Header("Content-Type", contentType)
c.Data(http.StatusOK, contentType, audioData)
usage = &dto.Usage{
PromptTokens: info.GetEstimatePromptTokens(),
CompletionTokens: 0,
TotalTokens: info.GetEstimatePromptTokens(),
}
return usage, nil
}
func generateRequestID() string {
return uuid.New().String()
}
func handleTTSWebSocketResponse(c *gin.Context, requestURL string, volcRequest VolcengineTTSRequest, info *relaycommon.RelayInfo, encoding string) (usage any, err *types.NewAPIError) {
_, token, parseErr := parseVolcengineAuth(info.ApiKey)
if parseErr != nil {
return nil, types.NewErrorWithStatusCode(
parseErr,
types.ErrorCodeChannelInvalidKey,
http.StatusUnauthorized,
)
}
header := http.Header{}
header.Set("Authorization", fmt.Sprintf("Bearer;%s", token))
conn, resp, dialErr := websocket.DefaultDialer.DialContext(context.Background(), requestURL, header)
if dialErr != nil {
if resp != nil {
return nil, types.NewErrorWithStatusCode(
fmt.Errorf("failed to connect to websocket: %w, status: %d", dialErr, resp.StatusCode),
types.ErrorCodeBadResponseStatusCode,
http.StatusBadGateway,
)
}
return nil, types.NewErrorWithStatusCode(
fmt.Errorf("failed to connect to websocket: %w", dialErr),
types.ErrorCodeBadResponseStatusCode,
http.StatusBadGateway,
)
}
defer conn.Close()
payload, marshalErr := json.Marshal(volcRequest)
if marshalErr != nil {
return nil, types.NewErrorWithStatusCode(
fmt.Errorf("failed to marshal request: %w", marshalErr),
types.ErrorCodeBadRequestBody,
http.StatusInternalServerError,
)
}
if sendErr := FullClientRequest(conn, payload); sendErr != nil {
return nil, types.NewErrorWithStatusCode(
fmt.Errorf("failed to send request: %w", sendErr),
types.ErrorCodeBadRequestBody,
http.StatusInternalServerError,
)
}
contentType := getContentTypeByEncoding(encoding)
c.Header("Content-Type", contentType)
c.Header("Transfer-Encoding", "chunked")
for {
msg, recvErr := ReceiveMessage(conn)
if recvErr != nil {
if websocket.IsCloseError(recvErr, websocket.CloseNormalClosure, websocket.CloseGoingAway) {
break
}
return nil, types.NewErrorWithStatusCode(
fmt.Errorf("failed to receive message: %w", recvErr),
types.ErrorCodeBadResponse,
http.StatusInternalServerError,
)
}
switch msg.MsgType {
case MsgTypeError:
return nil, types.NewErrorWithStatusCode(
fmt.Errorf("received error from server: code=%d, %s", msg.ErrorCode, string(msg.Payload)),
types.ErrorCodeBadResponse,
http.StatusBadRequest,
)
case MsgTypeFrontEndResultServer:
continue
case MsgTypeAudioOnlyServer:
if len(msg.Payload) > 0 {
if _, writeErr := c.Writer.Write(msg.Payload); writeErr != nil {
return nil, types.NewErrorWithStatusCode(
fmt.Errorf("failed to write audio data: %w", writeErr),
types.ErrorCodeBadResponse,
http.StatusInternalServerError,
)
}
c.Writer.Flush()
}
if msg.Sequence < 0 {
c.Status(http.StatusOK)
usage = &dto.Usage{
PromptTokens: info.GetEstimatePromptTokens(),
CompletionTokens: 0,
TotalTokens: info.GetEstimatePromptTokens(),
}
return usage, nil
}
default:
continue
}
}
c.Status(http.StatusOK)
usage = &dto.Usage{
PromptTokens: info.GetEstimatePromptTokens(),
CompletionTokens: 0,
TotalTokens: info.GetEstimatePromptTokens(),
}
return usage, nil
}