* 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
189 lines
5.5 KiB
Go
189 lines
5.5 KiB
Go
package aws
|
|
|
|
import (
|
|
"fmt"
|
|
"io"
|
|
"net/http"
|
|
"strings"
|
|
|
|
"github.com/QuantumNous/new-api/relay/channel"
|
|
"github.com/QuantumNous/new-api/relay/channel/claude"
|
|
relaycommon "github.com/QuantumNous/new-api/relay/common"
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
"github.com/QuantumNous/new-api/relaykit/types"
|
|
"github.com/QuantumNous/new-api/service"
|
|
"github.com/aws/aws-sdk-go-v2/service/bedrockruntime"
|
|
"github.com/pkg/errors"
|
|
|
|
"github.com/gin-gonic/gin"
|
|
)
|
|
|
|
type ClientMode int
|
|
|
|
const (
|
|
ClientModeApiKey ClientMode = iota + 1
|
|
ClientModeAKSK
|
|
)
|
|
|
|
type Adaptor struct {
|
|
ClientMode ClientMode
|
|
AwsClient *bedrockruntime.Client
|
|
AwsModelId string
|
|
AwsReq any
|
|
IsNova bool
|
|
}
|
|
|
|
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, request *dto.ClaudeRequest) (any, error) {
|
|
for i, message := range request.Messages {
|
|
updated := false
|
|
if !message.IsStringContent() {
|
|
content, err := message.ParseContent()
|
|
if err != nil {
|
|
return nil, errors.Wrap(err, "failed to parse message content")
|
|
}
|
|
for i2, mediaMessage := range content {
|
|
if mediaMessage.Source != nil {
|
|
if mediaMessage.Source.Type == "url" {
|
|
// 使用统一的文件服务获取图片数据
|
|
source := types.NewURLFileSource(mediaMessage.Source.Url)
|
|
base64Data, mimeType, err := service.GetBase64Data(c, source, "formatting image for Claude")
|
|
if err != nil {
|
|
return nil, fmt.Errorf("get file base64 from url failed: %s", err.Error())
|
|
}
|
|
mediaMessage.Source.MediaType = mimeType
|
|
mediaMessage.Source.Data = base64Data
|
|
mediaMessage.Source.Url = ""
|
|
mediaMessage.Source.Type = "base64"
|
|
content[i2] = mediaMessage
|
|
updated = true
|
|
}
|
|
}
|
|
}
|
|
if updated {
|
|
message.SetContent(content)
|
|
}
|
|
}
|
|
if updated {
|
|
request.Messages[i] = message
|
|
}
|
|
}
|
|
return request, 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) {
|
|
if info.ChannelOtherSettings.AwsKeyType == dto.AwsKeyTypeApiKey {
|
|
awsModelId := getAwsModelID(info.UpstreamModelName)
|
|
a.ClientMode = ClientModeApiKey
|
|
awsSecret := strings.Split(info.ApiKey, "|")
|
|
if len(awsSecret) != 2 {
|
|
return "", errors.New("invalid aws api key, should be in format of <api-key>|<region>")
|
|
}
|
|
return fmt.Sprintf("https://bedrock-runtime.%s.amazonaws.com/model/%s/converse", awsModelId, awsSecret[1]), nil
|
|
} else {
|
|
a.ClientMode = ClientModeAKSK
|
|
return "", nil
|
|
}
|
|
}
|
|
|
|
func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
|
|
claude.CommonClaudeHeadersOperation(c, req, info)
|
|
if a.ClientMode == ClientModeApiKey {
|
|
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")
|
|
}
|
|
// 检查是否为Nova模型
|
|
if isNovaModel(request.Model) {
|
|
novaReq := convertToNovaRequest(request)
|
|
a.IsNova = true
|
|
return novaReq, nil
|
|
}
|
|
|
|
// 原有的Claude模型处理逻辑
|
|
result, err := service.ConvertRequest(c, info, types.RelayFormatClaude, request)
|
|
if err != nil {
|
|
return nil, errors.Wrap(err, "failed to convert openai request to claude request")
|
|
}
|
|
claudeReq, ok := result.Value.(*dto.ClaudeRequest)
|
|
if !ok {
|
|
return nil, fmt.Errorf("expected Anthropic Messages request, got %T", result.Value)
|
|
}
|
|
info.UpstreamModelName = claudeReq.Model
|
|
return claudeReq, err
|
|
}
|
|
|
|
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) {
|
|
//TODO implement me
|
|
return nil, errors.New("not implemented")
|
|
}
|
|
|
|
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) {
|
|
if a.ClientMode == ClientModeApiKey {
|
|
return channel.DoApiRequest(a, c, info, requestBody)
|
|
} else {
|
|
return doAwsClientRequest(c, info, a, requestBody)
|
|
}
|
|
}
|
|
|
|
func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
|
|
if a.ClientMode == ClientModeApiKey {
|
|
claudeAdaptor := claude.Adaptor{}
|
|
usage, err = claudeAdaptor.DoResponse(c, resp, info)
|
|
} else {
|
|
if a.IsNova {
|
|
err, usage = handleNovaRequest(c, info, a)
|
|
} else {
|
|
if info.IsStream {
|
|
err, usage = awsStreamHandler(c, info, a)
|
|
} else {
|
|
err, usage = awsHandler(c, info, a)
|
|
}
|
|
}
|
|
}
|
|
return
|
|
}
|
|
|
|
func (a *Adaptor) GetModelList() (models []string) {
|
|
for n := range awsModelIDMap {
|
|
models = append(models, n)
|
|
}
|
|
|
|
return
|
|
}
|
|
|
|
func (a *Adaptor) GetChannelName() string {
|
|
return ChannelName
|
|
}
|