mirror of
https://github.com/QuantumNous/new-api.git
synced 2026-09-12 23:30:35 +00:00
* test(relayconvert): add golden snapshot matrix and relaykit boundary guard Phase 0 of the relaykit extraction plan: pin byte-level output of every registered (from,to) request/response/stream conversion route, and forbid kit-bound packages from growing host-only imports. * wip(relayconvert): drop gin.Context from converter signatures; add convmeta draft Phase 1 in progress: relayconvert now takes context.Context; host media resolver adapts gin.Context back at the service boundary. * refactor(relayconvert): decouple converters from RelayInfo, gin, and settings Phase 1 of the relaykit extraction plan: - converters now depend on convmeta.Meta (implemented by RelayInfo) instead of *relaycommon.RelayInfo; ClaudeConvertInfo and the format guesser move to convmeta with aliases left behind - host settings reach converters via a convmeta.Options snapshot built in RelayInfo.ConvOptions; no more model_setting/reasoning global reads inside the conversion layer - effort-suffix helpers move to service/relayconvert/reasoning (old package forwards); chat-to-responses upgrade policy moves to service (host routing logic, not conversion) - golden conversion matrix unchanged * test(relayconvert): tighten boundary — kit packages now free of gin/setting imports * refactor(dto): drop gin and logger dependencies Phase 2 (part 1): dto.Request.IsStream now takes *http.Request instead of *gin.Context (Gemini's impl reads query/path off the std request); dto's three logger calls become common.SysError. Boundary test allowlist is now empty — kit-bound packages import no gin/setting/logger/model. * refactor(kit): extract dependency-free kitutil; dto/types/relayconvert stop importing common Phase 2 of the relaykit extraction plan: - new service/relayconvert/kitutil holds the pure helpers the kit needs (JSON wrappers, pointer/string/uuid/timestamp utils, MaskSensitiveInfo, pluggable LogInfo/LogError hooks, Debug flag) - dto, types, and all relayconvert packages now use kitutil; their only remaining internal deps are dto/types/constant - common keeps every original symbol (MaskSensitiveInfo delegates to kitutil) so host code is untouched; main.go routes kit logging into common.SysLog/SysError and mirrors DebugEnabled - golden conversion matrix unchanged * refactor(kit): move EndpointType/FinishReason to types; OpenRouter dialect via Options Kit packages (dto/types/relayconvert/reasonmap) no longer import constant: - EndpointType and finish-reason values live in types; constant re-exports - the OpenRouter special-case in claude->openai request conversion reads Options.OpenRouterDialect, set by the host from the channel type; InitChannelMeta invalidates the cached snapshot on channel switch * refactor: extract relaykit submodule (dto/types/relayconvert/reasonmap) Phase 3 of the relaykit extraction plan: - new go module github.com/QuantumNous/new-api/relaykit containing dto (minus task family), types, relayconvert (with convmeta/kitutil/reasoning), and reasonmap; host consumes it via require + replace, go.work for dev - task-family dto (task/suno/midjourney/video) stays in the host dto package; dual-consumer host files alias it as taskdto - relaykit builds and tests standalone (GOWORK=off): no host imports, no gin, no DB, no settings - golden conversion matrix unchanged * build(docker): copy relaykit/go.mod before go mod download The local-replace submodule's go.mod must exist inside the build context for the main module graph to resolve. * fix: address relaykit extraction regressions * fix: address relaykit review regressions * docs: document Meta nil receiver contract * fix(relaykit): fail OpenAI→Claude conversion without max_tokens; reject negative default_max_tokens The Claude Messages API requires max_tokens (omitting it is a 400 "Field required"), but with a nil Options.Claude.DefaultMaxTokens hook the converters silently emitted a request the upstream is guaranteed to reject. Both OpenAI Chat and Responses → Claude conversions now return sharedclaude.ErrMissingMaxTokens when no path (client value, default hook, thinking-adapter floor) supplied one. Unreachable in the host, which always configures the hook. Host side, claude.default_max_tokens now rejects negative values at the option API before persisting — they would wrap into huge unsigned values during conversion. Zero stays allowed: the current API treats max_tokens: 0 as cache pre-warming. * fix: make Gemini safety settings read path race-free
293 lines
8.7 KiB
Go
293 lines
8.7 KiB
Go
package xunfei
|
|
|
|
import (
|
|
"crypto/hmac"
|
|
"crypto/sha256"
|
|
"encoding/base64"
|
|
"encoding/json"
|
|
"fmt"
|
|
"io"
|
|
"net/url"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/constant"
|
|
"github.com/QuantumNous/new-api/relay/helper"
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
"github.com/QuantumNous/new-api/relaykit/types"
|
|
"github.com/samber/lo"
|
|
|
|
"github.com/gin-gonic/gin"
|
|
"github.com/gorilla/websocket"
|
|
)
|
|
|
|
// https://console.xfyun.cn/services/cbm
|
|
// https://www.xfyun.cn/doc/spark/Web.html
|
|
|
|
func requestOpenAI2Xunfei(request dto.GeneralOpenAIRequest, xunfeiAppId string, domain string) *XunfeiChatRequest {
|
|
messages := make([]XunfeiMessage, 0, len(request.Messages))
|
|
shouldCovertSystemMessage := !strings.HasSuffix(request.Model, "3.5")
|
|
for _, message := range request.Messages {
|
|
if message.Role == "system" && shouldCovertSystemMessage {
|
|
messages = append(messages, XunfeiMessage{
|
|
Role: "user",
|
|
Content: message.StringContent(),
|
|
})
|
|
messages = append(messages, XunfeiMessage{
|
|
Role: "assistant",
|
|
Content: "Okay",
|
|
})
|
|
} else {
|
|
messages = append(messages, XunfeiMessage{
|
|
Role: message.Role,
|
|
Content: message.StringContent(),
|
|
})
|
|
}
|
|
}
|
|
xunfeiRequest := XunfeiChatRequest{}
|
|
xunfeiRequest.Header.AppId = xunfeiAppId
|
|
xunfeiRequest.Parameter.Chat.Domain = domain
|
|
xunfeiRequest.Parameter.Chat.Temperature = request.Temperature
|
|
xunfeiRequest.Parameter.Chat.TopK = lo.FromPtrOr(request.N, 0)
|
|
xunfeiRequest.Parameter.Chat.MaxTokens = request.GetMaxTokens()
|
|
xunfeiRequest.Payload.Message.Text = messages
|
|
return &xunfeiRequest
|
|
}
|
|
|
|
func responseXunfei2OpenAI(response *XunfeiChatResponse) *dto.OpenAITextResponse {
|
|
if len(response.Payload.Choices.Text) == 0 {
|
|
response.Payload.Choices.Text = []XunfeiChatResponseTextItem{
|
|
{
|
|
Content: "",
|
|
},
|
|
}
|
|
}
|
|
choice := dto.OpenAITextResponseChoice{
|
|
Index: 0,
|
|
Message: dto.Message{
|
|
Role: "assistant",
|
|
Content: response.Payload.Choices.Text[0].Content,
|
|
},
|
|
FinishReason: constant.FinishReasonStop,
|
|
}
|
|
fullTextResponse := dto.OpenAITextResponse{
|
|
Object: "chat.completion",
|
|
Created: common.GetTimestamp(),
|
|
Choices: []dto.OpenAITextResponseChoice{choice},
|
|
Usage: response.Payload.Usage.Text,
|
|
}
|
|
return &fullTextResponse
|
|
}
|
|
|
|
func streamResponseXunfei2OpenAI(xunfeiResponse *XunfeiChatResponse) *dto.ChatCompletionsStreamResponse {
|
|
if len(xunfeiResponse.Payload.Choices.Text) == 0 {
|
|
xunfeiResponse.Payload.Choices.Text = []XunfeiChatResponseTextItem{
|
|
{
|
|
Content: "",
|
|
},
|
|
}
|
|
}
|
|
var choice dto.ChatCompletionsStreamResponseChoice
|
|
choice.Delta.SetContentString(xunfeiResponse.Payload.Choices.Text[0].Content)
|
|
if xunfeiResponse.Payload.Choices.Status == 2 {
|
|
choice.FinishReason = &constant.FinishReasonStop
|
|
}
|
|
response := dto.ChatCompletionsStreamResponse{
|
|
Object: "chat.completion.chunk",
|
|
Created: common.GetTimestamp(),
|
|
Model: "SparkDesk",
|
|
Choices: []dto.ChatCompletionsStreamResponseChoice{choice},
|
|
}
|
|
return &response
|
|
}
|
|
|
|
func buildXunfeiAuthUrl(hostUrl string, apiKey, apiSecret string) string {
|
|
HmacWithShaToBase64 := func(algorithm, data, key string) string {
|
|
mac := hmac.New(sha256.New, []byte(key))
|
|
mac.Write([]byte(data))
|
|
encodeData := mac.Sum(nil)
|
|
return base64.StdEncoding.EncodeToString(encodeData)
|
|
}
|
|
ul, err := url.Parse(hostUrl)
|
|
if err != nil {
|
|
fmt.Println(err)
|
|
}
|
|
date := time.Now().UTC().Format(time.RFC1123)
|
|
signString := []string{"host: " + ul.Host, "date: " + date, "GET " + ul.Path + " HTTP/1.1"}
|
|
sign := strings.Join(signString, "\n")
|
|
sha := HmacWithShaToBase64("hmac-sha256", sign, apiSecret)
|
|
authUrl := fmt.Sprintf("hmac username=\"%s\", algorithm=\"%s\", headers=\"%s\", signature=\"%s\"", apiKey,
|
|
"hmac-sha256", "host date request-line", sha)
|
|
authorization := base64.StdEncoding.EncodeToString([]byte(authUrl))
|
|
v := url.Values{}
|
|
v.Add("host", ul.Host)
|
|
v.Add("date", date)
|
|
v.Add("authorization", authorization)
|
|
callUrl := hostUrl + "?" + v.Encode()
|
|
return callUrl
|
|
}
|
|
|
|
func xunfeiStreamHandler(c *gin.Context, textRequest dto.GeneralOpenAIRequest, appId string, apiSecret string, apiKey string) (*dto.Usage, *types.NewAPIError) {
|
|
domain, authUrl := getXunfeiAuthUrl(c, apiKey, apiSecret, textRequest.Model)
|
|
dataChan, stopChan, err := xunfeiMakeRequest(textRequest, domain, authUrl, appId)
|
|
if err != nil {
|
|
return nil, types.NewError(err, types.ErrorCodeDoRequestFailed)
|
|
}
|
|
helper.SetEventStreamHeaders(c)
|
|
var usage dto.Usage
|
|
c.Stream(func(w io.Writer) bool {
|
|
select {
|
|
case xunfeiResponse := <-dataChan:
|
|
usage.PromptTokens += xunfeiResponse.Payload.Usage.Text.PromptTokens
|
|
usage.CompletionTokens += xunfeiResponse.Payload.Usage.Text.CompletionTokens
|
|
usage.TotalTokens += xunfeiResponse.Payload.Usage.Text.TotalTokens
|
|
response := streamResponseXunfei2OpenAI(&xunfeiResponse)
|
|
jsonResponse, err := json.Marshal(response)
|
|
if err != nil {
|
|
common.SysLog("error marshalling stream response: " + err.Error())
|
|
return true
|
|
}
|
|
c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
|
|
return true
|
|
case <-stopChan:
|
|
c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
|
|
return false
|
|
}
|
|
})
|
|
return &usage, nil
|
|
}
|
|
|
|
func xunfeiHandler(c *gin.Context, textRequest dto.GeneralOpenAIRequest, appId string, apiSecret string, apiKey string) (*dto.Usage, *types.NewAPIError) {
|
|
domain, authUrl := getXunfeiAuthUrl(c, apiKey, apiSecret, textRequest.Model)
|
|
dataChan, stopChan, err := xunfeiMakeRequest(textRequest, domain, authUrl, appId)
|
|
if err != nil {
|
|
return nil, types.NewError(err, types.ErrorCodeDoRequestFailed)
|
|
}
|
|
var usage dto.Usage
|
|
var content string
|
|
var xunfeiResponse XunfeiChatResponse
|
|
stop := false
|
|
for !stop {
|
|
select {
|
|
case xunfeiResponse = <-dataChan:
|
|
if len(xunfeiResponse.Payload.Choices.Text) == 0 {
|
|
continue
|
|
}
|
|
content += xunfeiResponse.Payload.Choices.Text[0].Content
|
|
usage.PromptTokens += xunfeiResponse.Payload.Usage.Text.PromptTokens
|
|
usage.CompletionTokens += xunfeiResponse.Payload.Usage.Text.CompletionTokens
|
|
usage.TotalTokens += xunfeiResponse.Payload.Usage.Text.TotalTokens
|
|
case stop = <-stopChan:
|
|
}
|
|
}
|
|
if len(xunfeiResponse.Payload.Choices.Text) == 0 {
|
|
xunfeiResponse.Payload.Choices.Text = []XunfeiChatResponseTextItem{
|
|
{
|
|
Content: "",
|
|
},
|
|
}
|
|
}
|
|
xunfeiResponse.Payload.Choices.Text[0].Content = content
|
|
|
|
response := responseXunfei2OpenAI(&xunfeiResponse)
|
|
jsonResponse, err := json.Marshal(response)
|
|
if err != nil {
|
|
return nil, types.NewError(err, types.ErrorCodeBadResponseBody)
|
|
}
|
|
c.Writer.Header().Set("Content-Type", "application/json")
|
|
_, _ = c.Writer.Write(jsonResponse)
|
|
return &usage, nil
|
|
}
|
|
|
|
func xunfeiMakeRequest(textRequest dto.GeneralOpenAIRequest, domain, authUrl, appId string) (chan XunfeiChatResponse, chan bool, error) {
|
|
d := websocket.Dialer{
|
|
HandshakeTimeout: 5 * time.Second,
|
|
}
|
|
conn, resp, err := d.Dial(authUrl, nil)
|
|
if err != nil || resp.StatusCode != 101 {
|
|
return nil, nil, err
|
|
}
|
|
|
|
data := requestOpenAI2Xunfei(textRequest, appId, domain)
|
|
err = conn.WriteJSON(data)
|
|
if err != nil {
|
|
return nil, nil, err
|
|
}
|
|
|
|
dataChan := make(chan XunfeiChatResponse)
|
|
stopChan := make(chan bool)
|
|
go func() {
|
|
defer func() {
|
|
conn.Close()
|
|
}()
|
|
for {
|
|
_, msg, err := conn.ReadMessage()
|
|
if err != nil {
|
|
common.SysLog("error reading stream response: " + err.Error())
|
|
break
|
|
}
|
|
var response XunfeiChatResponse
|
|
err = json.Unmarshal(msg, &response)
|
|
if err != nil {
|
|
common.SysLog("error unmarshalling stream response: " + err.Error())
|
|
break
|
|
}
|
|
dataChan <- response
|
|
if response.Payload.Choices.Status == 2 {
|
|
if err != nil {
|
|
common.SysLog("error closing websocket connection: " + err.Error())
|
|
}
|
|
break
|
|
}
|
|
}
|
|
stopChan <- true
|
|
}()
|
|
|
|
return dataChan, stopChan, nil
|
|
}
|
|
|
|
func apiVersion2domain(apiVersion string) string {
|
|
switch apiVersion {
|
|
case "v1.1":
|
|
return "lite"
|
|
case "v2.1":
|
|
return "generalv2"
|
|
case "v3.1":
|
|
return "generalv3"
|
|
case "v3.5":
|
|
return "generalv3.5"
|
|
case "v4.0":
|
|
return "4.0Ultra"
|
|
}
|
|
return "general" + apiVersion
|
|
}
|
|
|
|
func getXunfeiAuthUrl(c *gin.Context, apiKey string, apiSecret string, modelName string) (string, string) {
|
|
apiVersion := getAPIVersion(c, modelName)
|
|
domain := apiVersion2domain(apiVersion)
|
|
authUrl := buildXunfeiAuthUrl(fmt.Sprintf("wss://spark-api.xf-yun.com/%s/chat", apiVersion), apiKey, apiSecret)
|
|
return domain, authUrl
|
|
}
|
|
|
|
func getAPIVersion(c *gin.Context, modelName string) string {
|
|
query := c.Request.URL.Query()
|
|
apiVersion := query.Get("api-version")
|
|
if apiVersion != "" {
|
|
return apiVersion
|
|
}
|
|
parts := strings.Split(modelName, "-")
|
|
if len(parts) == 2 {
|
|
apiVersion = parts[1]
|
|
return apiVersion
|
|
|
|
}
|
|
apiVersion = c.GetString("api_version")
|
|
if apiVersion != "" {
|
|
return apiVersion
|
|
}
|
|
apiVersion = "v1.1"
|
|
common.SysLog("api_version not found, using default: " + apiVersion)
|
|
return apiVersion
|
|
}
|