Files
new-api/relay/channel/baidu/adaptor.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

171 lines
4.8 KiB
Go

package baidu
import (
"errors"
"fmt"
"io"
"net/http"
"strings"
"github.com/QuantumNous/new-api/relay/channel"
relaycommon "github.com/QuantumNous/new-api/relay/common"
"github.com/QuantumNous/new-api/relay/constant"
"github.com/QuantumNous/new-api/relaykit/dto"
"github.com/QuantumNous/new-api/relaykit/types"
"github.com/gin-gonic/gin"
)
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(*gin.Context, *relaycommon.RelayInfo, *dto.ClaudeRequest) (any, error) {
//TODO implement me
panic("implement me")
return nil, nil
}
func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
//TODO implement me
return nil, errors.New("not implemented")
}
func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
//TODO implement me
return nil, errors.New("not implemented")
}
func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
}
func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
// https://cloud.baidu.com/doc/WENXINWORKSHOP/s/clntwmv7t
suffix := "chat/"
if strings.HasPrefix(info.UpstreamModelName, "Embedding") {
suffix = "embeddings/"
}
if strings.HasPrefix(info.UpstreamModelName, "bge-large") {
suffix = "embeddings/"
}
if strings.HasPrefix(info.UpstreamModelName, "tao-8k") {
suffix = "embeddings/"
}
switch info.UpstreamModelName {
case "ERNIE-4.0":
suffix += "completions_pro"
case "ERNIE-Bot-4":
suffix += "completions_pro"
case "ERNIE-Bot":
suffix += "completions"
case "ERNIE-Bot-turbo":
suffix += "eb-instant"
case "ERNIE-Speed":
suffix += "ernie_speed"
case "ERNIE-4.0-8K":
suffix += "completions_pro"
case "ERNIE-3.5-8K":
suffix += "completions"
case "ERNIE-3.5-8K-0205":
suffix += "ernie-3.5-8k-0205"
case "ERNIE-3.5-8K-1222":
suffix += "ernie-3.5-8k-1222"
case "ERNIE-Bot-8K":
suffix += "ernie_bot_8k"
case "ERNIE-3.5-4K-0205":
suffix += "ernie-3.5-4k-0205"
case "ERNIE-Speed-8K":
suffix += "ernie_speed"
case "ERNIE-Speed-128K":
suffix += "ernie-speed-128k"
case "ERNIE-Lite-8K-0922":
suffix += "eb-instant"
case "ERNIE-Lite-8K-0308":
suffix += "ernie-lite-8k"
case "ERNIE-Tiny-8K":
suffix += "ernie-tiny-8k"
case "BLOOMZ-7B":
suffix += "bloomz_7b1"
case "Embedding-V1":
suffix += "embedding-v1"
case "bge-large-zh":
suffix += "bge_large_zh"
case "bge-large-en":
suffix += "bge_large_en"
case "tao-8k":
suffix += "tao_8k"
default:
suffix += strings.ToLower(info.UpstreamModelName)
}
fullRequestURL := fmt.Sprintf("%s/rpc/2.0/ai_custom/v1/wenxinworkshop/%s", info.ChannelBaseUrl, suffix)
var accessToken string
var err error
if accessToken, err = getBaiduAccessToken(info.ApiKey); err != nil {
return "", err
}
fullRequestURL += "?access_token=" + accessToken
return fullRequestURL, nil
}
func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
channel.SetupApiRequestHeader(info, c, req)
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")
}
switch info.RelayMode {
default:
baiduRequest := requestOpenAI2Baidu(*request)
return baiduRequest, 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) {
baiduEmbeddingRequest := embeddingRequestOpenAI2Baidu(request)
return baiduEmbeddingRequest, nil
}
func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
// TODO implement me
return nil, errors.New("not implemented")
}
func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
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.IsStream {
err, usage = baiduStreamHandler(c, info, resp)
} else {
switch info.RelayMode {
case constant.RelayModeEmbeddings:
err, usage = baiduEmbeddingHandler(c, info, resp)
default:
err, usage = baiduHandler(c, info, resp)
}
}
return
}
func (a *Adaptor) GetModelList() []string {
return ModelList
}
func (a *Adaptor) GetChannelName() string {
return ChannelName
}