Files
new-api/relay/channel/baidu/relay-baidu.go
T
Calcium-Ion 86ac0f7745 refactor: extract protocol conversion layer into standalone relaykit module (#6369)
* 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
2026-07-27 15:56:21 +08:00

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
}