Files
new-api/relay/channel/aws/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

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
}