* 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
228 lines
8.6 KiB
Go
228 lines
8.6 KiB
Go
package relay
|
|
|
|
import (
|
|
"encoding/json"
|
|
"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"
|
|
"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/reasoning"
|
|
|
|
"github.com/gin-gonic/gin"
|
|
)
|
|
|
|
func ClaudeHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *types.NewAPIError) {
|
|
|
|
info.InitChannelMeta(c)
|
|
|
|
claudeReq, ok := info.Request.(*dto.ClaudeRequest)
|
|
|
|
if !ok {
|
|
return types.NewErrorWithStatusCode(fmt.Errorf("invalid request type, expected *dto.ClaudeRequest, got %T", info.Request), types.ErrorCodeInvalidRequest, http.StatusBadRequest, types.ErrOptionWithSkipRetry())
|
|
}
|
|
|
|
request, err := common.DeepCopy(claudeReq)
|
|
if err != nil {
|
|
return types.NewError(fmt.Errorf("failed to copy request to ClaudeRequest: %w", err), types.ErrorCodeInvalidRequest, types.ErrOptionWithSkipRetry())
|
|
}
|
|
|
|
err = helper.ModelMappedHelper(c, info, request)
|
|
if err != nil {
|
|
return types.NewError(err, types.ErrorCodeChannelModelMappedError, types.ErrOptionWithSkipRetry())
|
|
}
|
|
|
|
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)
|
|
|
|
if request.MaxTokens == nil || *request.MaxTokens == 0 {
|
|
defaultMaxTokens := uint(model_setting.GetClaudeSettings().GetDefaultMaxTokens(request.Model))
|
|
request.MaxTokens = &defaultMaxTokens
|
|
}
|
|
|
|
if baseModel, effortLevel, ok := reasoning.TrimEffortSuffix(request.Model); ok && effortLevel != "" &&
|
|
(strings.HasPrefix(request.Model, "claude-opus-4-6") ||
|
|
strings.HasPrefix(request.Model, "claude-opus-4-7") ||
|
|
strings.HasPrefix(request.Model, "claude-opus-4-8")) {
|
|
request.Model = baseModel
|
|
request.Thinking = &dto.Thinking{
|
|
Type: "adaptive",
|
|
}
|
|
request.OutputConfig = json.RawMessage(fmt.Sprintf(`{"effort":"%s"}`, effortLevel))
|
|
if strings.HasPrefix(request.Model, "claude-opus-4-7") ||
|
|
strings.HasPrefix(request.Model, "claude-opus-4-8") {
|
|
// Opus 4.7/4.8 reject non-default temperature/top_p/top_k with 400
|
|
// and defaults display to "omitted"; restore the 4.6 visible summary.
|
|
request.Thinking.Display = "summarized"
|
|
request.Temperature = nil
|
|
request.TopP = nil
|
|
request.TopK = nil
|
|
} else {
|
|
request.Temperature = common.GetPointer[float64](1.0)
|
|
}
|
|
info.UpstreamModelName = request.Model
|
|
} else if model_setting.GetClaudeSettings().ThinkingAdapterEnabled &&
|
|
strings.HasSuffix(request.Model, "-thinking") {
|
|
if request.Thinking == nil {
|
|
baseModel := strings.TrimSuffix(request.Model, "-thinking")
|
|
if strings.HasPrefix(baseModel, "claude-opus-4-7") ||
|
|
strings.HasPrefix(baseModel, "claude-opus-4-8") {
|
|
// Opus 4.7/4.8 reject thinking.type="enabled"; use adaptive at high effort.
|
|
request.Thinking = &dto.Thinking{Type: "adaptive", Display: "summarized"}
|
|
request.OutputConfig = json.RawMessage(`{"effort":"high"}`)
|
|
request.Temperature = nil
|
|
request.TopP = nil
|
|
request.TopK = nil
|
|
} else {
|
|
// 因为BudgetTokens 必须大于1024
|
|
if request.MaxTokens == nil || *request.MaxTokens < 1280 {
|
|
request.MaxTokens = common.GetPointer[uint](1280)
|
|
}
|
|
|
|
// BudgetTokens 为 max_tokens 的 80%
|
|
request.Thinking = &dto.Thinking{
|
|
Type: "enabled",
|
|
BudgetTokens: common.GetPointer[int](int(float64(*request.MaxTokens) * model_setting.GetClaudeSettings().ThinkingAdapterBudgetTokensPercentage)),
|
|
}
|
|
// TODO: 临时处理
|
|
// https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking#important-considerations-when-using-extended-thinking
|
|
request.Temperature = common.GetPointer[float64](1.0)
|
|
}
|
|
}
|
|
if !model_setting.ShouldPreserveThinkingSuffix(info.OriginModelName) {
|
|
request.Model = strings.TrimSuffix(request.Model, "-thinking")
|
|
}
|
|
info.UpstreamModelName = request.Model
|
|
}
|
|
|
|
if info.ChannelSetting.SystemPrompt != "" {
|
|
if request.System == nil {
|
|
request.SetStringSystem(info.ChannelSetting.SystemPrompt)
|
|
} else if info.ChannelSetting.SystemPromptOverride {
|
|
common.SetContextKey(c, constant.ContextKeySystemPromptOverride, true)
|
|
if request.IsStringSystem() {
|
|
existing := strings.TrimSpace(request.GetStringSystem())
|
|
if existing == "" {
|
|
request.SetStringSystem(info.ChannelSetting.SystemPrompt)
|
|
} else {
|
|
request.SetStringSystem(info.ChannelSetting.SystemPrompt + "\n" + existing)
|
|
}
|
|
} else {
|
|
systemContents := request.ParseSystem()
|
|
newSystem := dto.ClaudeMediaMessage{Type: dto.ContentTypeText}
|
|
newSystem.SetText(info.ChannelSetting.SystemPrompt)
|
|
if len(systemContents) == 0 {
|
|
request.System = []dto.ClaudeMediaMessage{newSystem}
|
|
} else {
|
|
request.System = append([]dto.ClaudeMediaMessage{newSystem}, systemContents...)
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
if !model_setting.GetGlobalSettings().PassThroughRequestEnabled &&
|
|
!info.ChannelSetting.PassThroughBodyEnabled &&
|
|
service.ShouldChatCompletionsUseResponsesGlobal(info.ChannelId, info.ChannelType, info.OriginModelName) {
|
|
result, convErr := service.ConvertRequest(c, info, types.RelayFormatOpenAI, request)
|
|
if convErr != nil {
|
|
return types.NewError(convErr, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
|
|
}
|
|
openAIRequest, ok := result.Value.(*dto.GeneralOpenAIRequest)
|
|
if !ok {
|
|
return types.NewError(fmt.Errorf("expected OpenAI chat completions request, got %T", result.Value), types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
|
|
}
|
|
|
|
usage, newApiErr := chatCompletionsViaResponses(c, info, adaptor, openAIRequest)
|
|
if newApiErr != nil {
|
|
return newApiErr
|
|
}
|
|
|
|
service.PostTextConsumeQuota(c, info, usage, nil)
|
|
return nil
|
|
}
|
|
|
|
var requestBody io.Reader
|
|
if model_setting.GetGlobalSettings().PassThroughRequestEnabled || info.ChannelSetting.PassThroughBodyEnabled {
|
|
storage, err := common.GetBodyStorage(c)
|
|
if err != nil {
|
|
return types.NewErrorWithStatusCode(err, types.ErrorCodeReadRequestBodyFailed, http.StatusBadRequest, types.ErrOptionWithSkipRetry())
|
|
}
|
|
info.UpstreamRequestBodySize = storage.Size()
|
|
requestBody = common.ReaderOnly(storage)
|
|
} else {
|
|
convertedRequest, err := adaptor.ConvertClaudeRequest(c, info, request)
|
|
if err != nil {
|
|
return types.NewError(err, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
|
|
}
|
|
relaycommon.AppendRequestConversionFromRequest(info, convertedRequest)
|
|
jsonData, err := common.Marshal(convertedRequest)
|
|
if err != nil {
|
|
return types.NewError(err, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
|
|
}
|
|
|
|
// remove disabled fields for Claude 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, "requestBody: %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
|
|
}
|
|
|
|
statusCodeMappingStr := c.GetString("status_code_mapping")
|
|
var httpResp *http.Response
|
|
resp, err := adaptor.DoRequest(c, info, requestBody)
|
|
if err != nil {
|
|
return types.NewOpenAIError(err, types.ErrorCodeDoRequestFailed, http.StatusInternalServerError)
|
|
}
|
|
|
|
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 {
|
|
newAPIError = service.RelayErrorHandler(c.Request.Context(), httpResp, false)
|
|
// reset status code 重置状态码
|
|
service.ResetStatusCode(newAPIError, statusCodeMappingStr)
|
|
return newAPIError
|
|
}
|
|
}
|
|
|
|
usage, newAPIError := adaptor.DoResponse(c, httpResp, info)
|
|
if newAPIError != nil {
|
|
// reset status code 重置状态码
|
|
service.ResetStatusCode(newAPIError, statusCodeMappingStr)
|
|
return newAPIError
|
|
}
|
|
|
|
service.PostTextConsumeQuota(c, info, usage.(*dto.Usage), nil)
|
|
return nil
|
|
}
|