* 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
247 lines
7.8 KiB
Go
247 lines
7.8 KiB
Go
package baidu
|
|
|
|
import (
|
|
"encoding/json"
|
|
"errors"
|
|
"fmt"
|
|
"io"
|
|
"net/http"
|
|
"strings"
|
|
"sync"
|
|
"time"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/constant"
|
|
relaycommon "github.com/QuantumNous/new-api/relay/common"
|
|
"github.com/QuantumNous/new-api/relay/helper"
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
"github.com/QuantumNous/new-api/relaykit/types"
|
|
"github.com/QuantumNous/new-api/service"
|
|
"github.com/samber/lo"
|
|
|
|
"github.com/gin-gonic/gin"
|
|
)
|
|
|
|
// https://cloud.baidu.com/doc/WENXINWORKSHOP/s/flfmc9do2
|
|
|
|
var baiduTokenStore sync.Map
|
|
|
|
func requestOpenAI2Baidu(request dto.GeneralOpenAIRequest) *BaiduChatRequest {
|
|
baiduRequest := BaiduChatRequest{
|
|
Temperature: request.Temperature,
|
|
TopP: lo.FromPtrOr(request.TopP, 0),
|
|
PenaltyScore: lo.FromPtrOr(request.FrequencyPenalty, 0),
|
|
Stream: lo.FromPtrOr(request.Stream, false),
|
|
DisableSearch: false,
|
|
EnableCitation: false,
|
|
UserId: request.User,
|
|
}
|
|
if request.GetMaxTokens() != 0 {
|
|
maxTokens := int(request.GetMaxTokens())
|
|
if request.GetMaxTokens() == 1 {
|
|
maxTokens = 2
|
|
}
|
|
baiduRequest.MaxOutputTokens = &maxTokens
|
|
}
|
|
for _, message := range request.Messages {
|
|
if message.Role == "system" {
|
|
baiduRequest.System = message.StringContent()
|
|
} else {
|
|
baiduRequest.Messages = append(baiduRequest.Messages, BaiduMessage{
|
|
Role: message.Role,
|
|
Content: message.StringContent(),
|
|
})
|
|
}
|
|
}
|
|
return &baiduRequest
|
|
}
|
|
|
|
func responseBaidu2OpenAI(response *BaiduChatResponse) *dto.OpenAITextResponse {
|
|
choice := dto.OpenAITextResponseChoice{
|
|
Index: 0,
|
|
Message: dto.Message{
|
|
Role: "assistant",
|
|
Content: response.Result,
|
|
},
|
|
FinishReason: "stop",
|
|
}
|
|
fullTextResponse := dto.OpenAITextResponse{
|
|
Id: response.Id,
|
|
Object: "chat.completion",
|
|
Created: response.Created,
|
|
Choices: []dto.OpenAITextResponseChoice{choice},
|
|
Usage: response.Usage,
|
|
}
|
|
return &fullTextResponse
|
|
}
|
|
|
|
func streamResponseBaidu2OpenAI(baiduResponse *BaiduChatStreamResponse) *dto.ChatCompletionsStreamResponse {
|
|
var choice dto.ChatCompletionsStreamResponseChoice
|
|
choice.Delta.SetContentString(baiduResponse.Result)
|
|
if baiduResponse.IsEnd {
|
|
choice.FinishReason = &constant.FinishReasonStop
|
|
}
|
|
response := dto.ChatCompletionsStreamResponse{
|
|
Id: baiduResponse.Id,
|
|
Object: "chat.completion.chunk",
|
|
Created: baiduResponse.Created,
|
|
Model: "ernie-bot",
|
|
Choices: []dto.ChatCompletionsStreamResponseChoice{choice},
|
|
}
|
|
return &response
|
|
}
|
|
|
|
func embeddingRequestOpenAI2Baidu(request dto.EmbeddingRequest) *BaiduEmbeddingRequest {
|
|
return &BaiduEmbeddingRequest{
|
|
Input: request.ParseInput(),
|
|
}
|
|
}
|
|
|
|
func embeddingResponseBaidu2OpenAI(response *BaiduEmbeddingResponse) *dto.OpenAIEmbeddingResponse {
|
|
openAIEmbeddingResponse := dto.OpenAIEmbeddingResponse{
|
|
Object: "list",
|
|
Data: make([]dto.OpenAIEmbeddingResponseItem, 0, len(response.Data)),
|
|
Model: "baidu-embedding",
|
|
Usage: response.Usage,
|
|
}
|
|
for _, item := range response.Data {
|
|
openAIEmbeddingResponse.Data = append(openAIEmbeddingResponse.Data, dto.OpenAIEmbeddingResponseItem{
|
|
Object: item.Object,
|
|
Index: item.Index,
|
|
Embedding: item.Embedding,
|
|
})
|
|
}
|
|
return &openAIEmbeddingResponse
|
|
}
|
|
|
|
func baiduStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*types.NewAPIError, *dto.Usage) {
|
|
usage := &dto.Usage{}
|
|
helper.StreamScannerHandler(c, resp, info, func(data string, sr *helper.StreamResult) {
|
|
var baiduResponse BaiduChatStreamResponse
|
|
if err := common.Unmarshal([]byte(data), &baiduResponse); err != nil {
|
|
common.SysLog("error unmarshalling stream response: " + err.Error())
|
|
sr.Error(err)
|
|
return
|
|
}
|
|
if baiduResponse.Usage.TotalTokens != 0 {
|
|
usage.TotalTokens = baiduResponse.Usage.TotalTokens
|
|
usage.PromptTokens = baiduResponse.Usage.PromptTokens
|
|
usage.CompletionTokens = baiduResponse.Usage.TotalTokens - baiduResponse.Usage.PromptTokens
|
|
}
|
|
response := streamResponseBaidu2OpenAI(&baiduResponse)
|
|
if err := helper.ObjectData(c, response); err != nil {
|
|
common.SysLog("error sending stream response: " + err.Error())
|
|
sr.Error(err)
|
|
}
|
|
})
|
|
service.CloseResponseBodyGracefully(resp)
|
|
return nil, usage
|
|
}
|
|
|
|
func baiduHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*types.NewAPIError, *dto.Usage) {
|
|
var baiduResponse BaiduChatResponse
|
|
responseBody, err := io.ReadAll(resp.Body)
|
|
if err != nil {
|
|
return types.NewError(err, types.ErrorCodeBadResponseBody), nil
|
|
}
|
|
service.CloseResponseBodyGracefully(resp)
|
|
err = json.Unmarshal(responseBody, &baiduResponse)
|
|
if err != nil {
|
|
return types.NewError(err, types.ErrorCodeBadResponseBody), nil
|
|
}
|
|
if baiduResponse.ErrorMsg != "" {
|
|
return types.NewError(fmt.Errorf("%s", baiduResponse.ErrorMsg), types.ErrorCodeBadResponseBody), nil
|
|
}
|
|
fullTextResponse := responseBaidu2OpenAI(&baiduResponse)
|
|
jsonResponse, err := json.Marshal(fullTextResponse)
|
|
if err != nil {
|
|
return types.NewError(err, types.ErrorCodeBadResponseBody), nil
|
|
}
|
|
c.Writer.Header().Set("Content-Type", "application/json")
|
|
c.Writer.WriteHeader(resp.StatusCode)
|
|
_, err = c.Writer.Write(jsonResponse)
|
|
return nil, &fullTextResponse.Usage
|
|
}
|
|
|
|
func baiduEmbeddingHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*types.NewAPIError, *dto.Usage) {
|
|
var baiduResponse BaiduEmbeddingResponse
|
|
responseBody, err := io.ReadAll(resp.Body)
|
|
if err != nil {
|
|
return types.NewError(err, types.ErrorCodeBadResponseBody), nil
|
|
}
|
|
service.CloseResponseBodyGracefully(resp)
|
|
err = json.Unmarshal(responseBody, &baiduResponse)
|
|
if err != nil {
|
|
return types.NewError(err, types.ErrorCodeBadResponseBody), nil
|
|
}
|
|
if baiduResponse.ErrorMsg != "" {
|
|
return types.NewError(fmt.Errorf("%s", baiduResponse.ErrorMsg), types.ErrorCodeBadResponseBody), nil
|
|
}
|
|
fullTextResponse := embeddingResponseBaidu2OpenAI(&baiduResponse)
|
|
jsonResponse, err := json.Marshal(fullTextResponse)
|
|
if err != nil {
|
|
return types.NewError(err, types.ErrorCodeBadResponseBody), nil
|
|
}
|
|
c.Writer.Header().Set("Content-Type", "application/json")
|
|
c.Writer.WriteHeader(resp.StatusCode)
|
|
_, err = c.Writer.Write(jsonResponse)
|
|
return nil, &fullTextResponse.Usage
|
|
}
|
|
|
|
func getBaiduAccessToken(apiKey string) (string, error) {
|
|
if val, ok := baiduTokenStore.Load(apiKey); ok {
|
|
var accessToken BaiduAccessToken
|
|
if accessToken, ok = val.(BaiduAccessToken); ok {
|
|
// soon this will expire
|
|
if time.Now().Add(time.Hour).After(accessToken.ExpiresAt) {
|
|
go func() {
|
|
_, _ = getBaiduAccessTokenHelper(apiKey)
|
|
}()
|
|
}
|
|
return accessToken.AccessToken, nil
|
|
}
|
|
}
|
|
accessToken, err := getBaiduAccessTokenHelper(apiKey)
|
|
if err != nil {
|
|
return "", err
|
|
}
|
|
if accessToken == nil {
|
|
return "", errors.New("getBaiduAccessToken return a nil token")
|
|
}
|
|
return (*accessToken).AccessToken, nil
|
|
}
|
|
|
|
func getBaiduAccessTokenHelper(apiKey string) (*BaiduAccessToken, error) {
|
|
parts := strings.Split(apiKey, "|")
|
|
if len(parts) != 2 {
|
|
return nil, errors.New("invalid baidu apikey")
|
|
}
|
|
req, err := http.NewRequest("POST", fmt.Sprintf("https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=%s&client_secret=%s",
|
|
parts[0], parts[1]), nil)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
req.Header.Add("Content-Type", "application/json")
|
|
req.Header.Add("Accept", "application/json")
|
|
res, err := service.GetHttpClient().Do(req)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
defer res.Body.Close()
|
|
|
|
var accessToken BaiduAccessToken
|
|
err = json.NewDecoder(res.Body).Decode(&accessToken)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
if accessToken.Error != "" {
|
|
return nil, errors.New(accessToken.Error + ": " + accessToken.ErrorDescription)
|
|
}
|
|
if accessToken.AccessToken == "" {
|
|
return nil, errors.New("getBaiduAccessTokenHelper get empty access token")
|
|
}
|
|
accessToken.ExpiresAt = time.Now().Add(time.Duration(accessToken.ExpiresIn) * time.Second)
|
|
baiduTokenStore.Store(apiKey, accessToken)
|
|
return &accessToken, nil
|
|
}
|