Files
new-api/relay/chat_completions_via_responses.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

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")
}