Files
new-api/relay/compatible_handler.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

224 lines
7.8 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/logger"
relaycommon "github.com/QuantumNous/new-api/relay/common"
relayconstant "github.com/QuantumNous/new-api/relay/constant"
"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/QuantumNous/new-api/setting/model_setting"
"github.com/QuantumNous/new-api/setting/ratio_setting"
"github.com/samber/lo"
"github.com/gin-gonic/gin"
)
func TextHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *types.NewAPIError) {
info.InitChannelMeta(c)
textReq, ok := info.Request.(*dto.GeneralOpenAIRequest)
if !ok {
return types.NewErrorWithStatusCode(fmt.Errorf("invalid request type, expected dto.GeneralOpenAIRequest, got %T", info.Request), types.ErrorCodeInvalidRequest, http.StatusBadRequest, types.ErrOptionWithSkipRetry())
}
request, err := common.DeepCopy(textReq)
if err != nil {
return types.NewError(fmt.Errorf("failed to copy request to GeneralOpenAIRequest: %w", err), types.ErrorCodeInvalidRequest, types.ErrOptionWithSkipRetry())
}
if request.WebSearchOptions != nil {
c.Set("chat_completion_web_search_context_size", request.WebSearchOptions.SearchContextSize)
}
err = helper.ModelMappedHelper(c, info, request)
if err != nil {
return types.NewError(err, types.ErrorCodeChannelModelMappedError, types.ErrOptionWithSkipRetry())
}
includeUsage := true
// 判断用户是否需要返回使用情况
if request.StreamOptions != nil {
includeUsage = request.StreamOptions.IncludeUsage
}
// 如果不支持StreamOptions,将StreamOptions设置为nil
if !info.SupportStreamOptions || !lo.FromPtrOr(request.Stream, false) {
request.StreamOptions = nil
} else {
// 如果支持StreamOptions,且请求中没有设置StreamOptions,根据配置文件设置StreamOptions
if constant.ForceStreamOption {
request.StreamOptions = &dto.StreamOptions{
IncludeUsage: true,
}
}
}
info.ShouldIncludeUsage = includeUsage
adaptor := GetAdaptor(info.ApiType)
if adaptor == nil {
return types.NewError(fmt.Errorf("invalid api type: %d", info.ApiType), types.ErrorCodeInvalidApiType, types.ErrOptionWithSkipRetry())
}
adaptor.Init(info)
passThroughGlobal := model_setting.GetGlobalSettings().PassThroughRequestEnabled
if info.RelayMode == relayconstant.RelayModeChatCompletions &&
!passThroughGlobal &&
!info.ChannelSetting.PassThroughBodyEnabled &&
service.ShouldChatCompletionsUseResponsesGlobal(info.ChannelId, info.ChannelType, info.OriginModelName) {
applySystemPromptIfNeeded(c, info, request)
usage, newApiErr := chatCompletionsViaResponses(c, info, adaptor, request)
if newApiErr != nil {
return newApiErr
}
var containAudioTokens = usage.CompletionTokenDetails.AudioTokens > 0 || usage.PromptTokensDetails.AudioTokens > 0
var containsAudioRatios = ratio_setting.ContainsAudioRatio(info.OriginModelName) || ratio_setting.ContainsAudioCompletionRatio(info.OriginModelName)
if containAudioTokens && containsAudioRatios {
service.PostAudioConsumeQuota(c, info, usage, "")
} else {
service.PostTextConsumeQuota(c, info, usage, nil)
}
return nil
}
var requestBody io.Reader
if passThroughGlobal || info.ChannelSetting.PassThroughBodyEnabled {
storage, err := common.GetBodyStorage(c)
if err != nil {
return types.NewErrorWithStatusCode(err, types.ErrorCodeReadRequestBodyFailed, http.StatusBadRequest, types.ErrOptionWithSkipRetry())
}
if common.DebugEnabled {
if debugBytes, bErr := storage.Bytes(); bErr == nil {
logger.LogDebug(c, "requestBody: %s", debugBytes)
}
}
requestBody = common.ReaderOnly(storage)
} else {
convertedRequest, err := adaptor.ConvertOpenAIRequest(c, info, request)
if err != nil {
return types.NewError(err, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
}
relaycommon.AppendRequestConversionFromRequest(info, convertedRequest)
if info.ChannelSetting.SystemPrompt != "" {
// 如果有系统提示,则将其添加到请求中
request, ok := convertedRequest.(*dto.GeneralOpenAIRequest)
if ok {
containSystemPrompt := false
for _, message := range request.Messages {
if message.Role == request.GetSystemRoleName() {
containSystemPrompt = true
break
}
}
if !containSystemPrompt {
// 如果没有系统提示,则添加系统提示
systemMessage := dto.Message{
Role: request.GetSystemRoleName(),
Content: info.ChannelSetting.SystemPrompt,
}
request.Messages = append([]dto.Message{systemMessage}, request.Messages...)
} else if info.ChannelSetting.SystemPromptOverride {
common.SetContextKey(c, constant.ContextKeySystemPromptOverride, true)
// 如果有系统提示,且允许覆盖,则拼接到前面
for i, message := range request.Messages {
if message.Role == request.GetSystemRoleName() {
if message.IsStringContent() {
request.Messages[i].SetStringContent(info.ChannelSetting.SystemPrompt + "\n" + message.StringContent())
} else {
contents := message.ParseContent()
contents = append([]dto.MediaContent{
{
Type: dto.ContentTypeText,
Text: info.ChannelSetting.SystemPrompt,
},
}, contents...)
request.Messages[i].Content = contents
}
break
}
}
}
}
}
jsonData, err := common.Marshal(convertedRequest)
if err != nil {
return types.NewError(err, types.ErrorCodeJsonMarshalFailed, types.ErrOptionWithSkipRetry())
}
// remove disabled fields for OpenAI API
jsonData, err = relaycommon.RemoveDisabledFields(jsonData, info.ChannelOtherSettings, info.ChannelSetting.PassThroughBodyEnabled)
if err != nil {
return types.NewError(err, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
}
// apply param override
if len(info.ParamOverride) > 0 {
jsonData, err = relaycommon.ApplyParamOverrideWithRelayInfo(jsonData, info)
if err != nil {
return newAPIErrorFromParamOverride(err)
}
}
logger.LogDebug(c, "text request body: %s", jsonData)
body, size, closer, err := relaycommon.NewOutboundJSONBody(jsonData)
if err != nil {
return types.NewError(err, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
}
defer closer.Close()
jsonData = nil
info.UpstreamRequestBodySize = size
requestBody = body
}
var httpResp *http.Response
resp, err := adaptor.DoRequest(c, info, requestBody)
if err != nil {
return types.NewOpenAIError(err, types.ErrorCodeDoRequestFailed, http.StatusInternalServerError)
}
statusCodeMappingStr := c.GetString("status_code_mapping")
if resp != nil {
httpResp = resp.(*http.Response)
info.IsStream = info.IsStream || strings.HasPrefix(httpResp.Header.Get("Content-Type"), "text/event-stream")
if httpResp.StatusCode != http.StatusOK {
newApiErr := service.RelayErrorHandler(c.Request.Context(), httpResp, false)
// reset status code 重置状态码
service.ResetStatusCode(newApiErr, statusCodeMappingStr)
return newApiErr
}
}
usage, newApiErr := adaptor.DoResponse(c, httpResp, info)
if newApiErr != nil {
// reset status code 重置状态码
service.ResetStatusCode(newApiErr, statusCodeMappingStr)
return newApiErr
}
var containAudioTokens = usage.(*dto.Usage).CompletionTokenDetails.AudioTokens > 0 || usage.(*dto.Usage).PromptTokensDetails.AudioTokens > 0
var containsAudioRatios = ratio_setting.ContainsAudioRatio(info.OriginModelName) || ratio_setting.ContainsAudioCompletionRatio(info.OriginModelName)
if containAudioTokens && containsAudioRatios {
service.PostAudioConsumeQuota(c, info, usage.(*dto.Usage), "")
} else {
service.PostTextConsumeQuota(c, info, usage.(*dto.Usage), nil)
}
return nil
}