mirror of
https://github.com/QuantumNous/new-api.git
synced 2026-09-11 06:30:21 +00:00
* 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
190 lines
6.2 KiB
Go
190 lines
6.2 KiB
Go
package relay
|
|
|
|
import (
|
|
"fmt"
|
|
"io"
|
|
"net/http"
|
|
"strings"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/constant"
|
|
"github.com/QuantumNous/new-api/relay/channel"
|
|
openaichannel "github.com/QuantumNous/new-api/relay/channel/openai"
|
|
relaycommon "github.com/QuantumNous/new-api/relay/common"
|
|
relayconstant "github.com/QuantumNous/new-api/relay/constant"
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
"github.com/QuantumNous/new-api/relaykit/types"
|
|
"github.com/QuantumNous/new-api/service"
|
|
|
|
"github.com/gin-gonic/gin"
|
|
)
|
|
|
|
func applySystemPromptIfNeeded(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) {
|
|
if info == nil || request == nil {
|
|
return
|
|
}
|
|
if info.ChannelSetting.SystemPrompt == "" {
|
|
return
|
|
}
|
|
|
|
systemRole := request.GetSystemRoleName()
|
|
|
|
containSystemPrompt := false
|
|
for _, message := range request.Messages {
|
|
if message.Role == systemRole {
|
|
containSystemPrompt = true
|
|
break
|
|
}
|
|
}
|
|
if !containSystemPrompt {
|
|
systemMessage := dto.Message{
|
|
Role: systemRole,
|
|
Content: info.ChannelSetting.SystemPrompt,
|
|
}
|
|
request.Messages = append([]dto.Message{systemMessage}, request.Messages...)
|
|
return
|
|
}
|
|
|
|
if !info.ChannelSetting.SystemPromptOverride {
|
|
return
|
|
}
|
|
|
|
common.SetContextKey(c, constant.ContextKeySystemPromptOverride, true)
|
|
for i, message := range request.Messages {
|
|
if message.Role != systemRole {
|
|
continue
|
|
}
|
|
if message.IsStringContent() {
|
|
request.Messages[i].SetStringContent(info.ChannelSetting.SystemPrompt + "\n" + message.StringContent())
|
|
return
|
|
}
|
|
contents := message.ParseContent()
|
|
contents = append([]dto.MediaContent{
|
|
{
|
|
Type: dto.ContentTypeText,
|
|
Text: info.ChannelSetting.SystemPrompt,
|
|
},
|
|
}, contents...)
|
|
request.Messages[i].Content = contents
|
|
return
|
|
}
|
|
}
|
|
|
|
func chatCompletionsViaResponses(c *gin.Context, info *relaycommon.RelayInfo, adaptor channel.Adaptor, request *dto.GeneralOpenAIRequest) (*dto.Usage, *types.NewAPIError) {
|
|
chatJSON, err := common.Marshal(request)
|
|
if err != nil {
|
|
return nil, types.NewError(err, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
|
|
}
|
|
|
|
chatJSON, err = relaycommon.RemoveDisabledFields(chatJSON, info.ChannelOtherSettings, info.ChannelSetting.PassThroughBodyEnabled)
|
|
if err != nil {
|
|
return nil, types.NewError(err, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
|
|
}
|
|
|
|
if len(info.ParamOverride) > 0 {
|
|
chatJSON, err = relaycommon.ApplyParamOverrideWithRelayInfo(chatJSON, info)
|
|
if err != nil {
|
|
return nil, newAPIErrorFromParamOverride(err)
|
|
}
|
|
}
|
|
|
|
var overriddenChatReq dto.GeneralOpenAIRequest
|
|
if err := common.Unmarshal(chatJSON, &overriddenChatReq); err != nil {
|
|
return nil, types.NewError(err, types.ErrorCodeChannelParamOverrideInvalid, types.ErrOptionWithSkipRetry())
|
|
}
|
|
|
|
result, err := service.ConvertRequestVia(c, info, &overriddenChatReq, types.RelayFormatOpenAI, types.RelayFormatOpenAIResponses)
|
|
if err != nil {
|
|
return nil, types.NewErrorWithStatusCode(err, types.ErrorCodeInvalidRequest, http.StatusBadRequest, types.ErrOptionWithSkipRetry())
|
|
}
|
|
responsesReq, ok := result.Value.(*dto.OpenAIResponsesRequest)
|
|
if !ok {
|
|
return nil, types.NewError(fmt.Errorf("expected OpenAI responses request, got %T", result.Value), types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
|
|
}
|
|
|
|
savedRelayMode := info.RelayMode
|
|
savedRequestURLPath := info.RequestURLPath
|
|
defer func() {
|
|
info.RelayMode = savedRelayMode
|
|
info.RequestURLPath = savedRequestURLPath
|
|
}()
|
|
|
|
info.RelayMode = relayconstant.RelayModeResponses
|
|
info.RequestURLPath = "/v1/responses"
|
|
|
|
convertedRequest, err := adaptor.ConvertOpenAIResponsesRequest(c, info, *responsesReq)
|
|
if err != nil {
|
|
return nil, types.NewError(err, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
|
|
}
|
|
relaycommon.AppendRequestConversionFromRequest(info, convertedRequest)
|
|
|
|
jsonData, err := common.Marshal(convertedRequest)
|
|
if err != nil {
|
|
return nil, types.NewError(err, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
|
|
}
|
|
|
|
jsonData, err = relaycommon.RemoveDisabledFields(jsonData, info.ChannelOtherSettings, info.ChannelSetting.PassThroughBodyEnabled)
|
|
if err != nil {
|
|
return nil, types.NewError(err, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
|
|
}
|
|
|
|
body, size, closer, err := relaycommon.NewOutboundJSONBody(jsonData)
|
|
if err != nil {
|
|
return nil, types.NewError(err, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
|
|
}
|
|
defer closer.Close()
|
|
jsonData = nil
|
|
info.UpstreamRequestBodySize = size
|
|
var requestBody io.Reader = body
|
|
|
|
var httpResp *http.Response
|
|
resp, err := adaptor.DoRequest(c, info, requestBody)
|
|
if err != nil {
|
|
return nil, types.NewOpenAIError(err, types.ErrorCodeDoRequestFailed, http.StatusInternalServerError)
|
|
}
|
|
if resp == nil {
|
|
return nil, types.NewOpenAIError(nil, types.ErrorCodeBadResponse, http.StatusInternalServerError)
|
|
}
|
|
|
|
statusCodeMappingStr := c.GetString("status_code_mapping")
|
|
|
|
httpResp = resp.(*http.Response)
|
|
clientStream := info.IsStream
|
|
upstreamStream := isResponsesEventStreamContentType(httpResp.Header.Get("Content-Type"))
|
|
info.IsStream = clientStream || upstreamStream
|
|
if httpResp.StatusCode != http.StatusOK {
|
|
newApiErr := service.RelayErrorHandler(c.Request.Context(), httpResp, false)
|
|
service.ResetStatusCode(newApiErr, statusCodeMappingStr)
|
|
return nil, newApiErr
|
|
}
|
|
|
|
if upstreamStream && clientStream {
|
|
usage, newApiErr := openaichannel.OaiResponsesToChatStreamHandler(c, info, httpResp)
|
|
if newApiErr != nil {
|
|
service.ResetStatusCode(newApiErr, statusCodeMappingStr)
|
|
return nil, newApiErr
|
|
}
|
|
return usage, nil
|
|
}
|
|
if upstreamStream {
|
|
info.IsStream = false
|
|
usage, newApiErr := openaichannel.OaiResponsesToChatBufferedStreamHandler(c, info, httpResp)
|
|
if newApiErr != nil {
|
|
service.ResetStatusCode(newApiErr, statusCodeMappingStr)
|
|
return nil, newApiErr
|
|
}
|
|
return usage, nil
|
|
}
|
|
|
|
usage, newApiErr := openaichannel.OaiResponsesToChatHandler(c, info, httpResp)
|
|
if newApiErr != nil {
|
|
service.ResetStatusCode(newApiErr, statusCodeMappingStr)
|
|
return nil, newApiErr
|
|
}
|
|
return usage, nil
|
|
}
|
|
|
|
func isResponsesEventStreamContentType(contentType string) bool {
|
|
return strings.Contains(strings.ToLower(contentType), "text/event-stream")
|
|
}
|