Files
new-api/relay/claude_handler.go
CaIon 7c044d7c5c feat(relay): explicit @ model modifiers and canonical billing identity
Model-name post-processing is rebuilt around an explicit trailing
@key:value modifier syntax (thinking/effort/temperature/topp) that
overrides request fields, survives model mapping, and records
conversion diagnostics on the consume log.

- Legacy naked aliases (-thinking, -nothinking, -thinking-<budget>,
  effort tails) now parse only for positively matched families
  (gpt-*/o-series, claude-*, gemini-*, incl. vendor/ namespaces);
  names like qwen-max stay opaque. EffortTailModelIDs remains the
  escape hatch for real in-family IDs such as gpt-5.1-codex-max.
- Billing identity resolves once in ModelPriceHelper via a ladder:
  configured request name first (legacy wildcard entries intact), then
  canonical billing names rebuilt from parsed intent
  (base@effort:E@thinking:S, then base@thinking:S; order, duplicates,
  and budget values are irrelevant; temperature/topp never priced),
  then base. Routing and token limits fall back through
  RoutingMatchModelName; pricing lookups stay wildcard-only.
- Pass-through stays byte-identical: modifiers and aliases are neither
  parsed nor validated there and forward verbatim for the upstream
  (or a chained gateway) to interpret.
- Unknown modifier keys and invalid known-key values are rejected with
  400; models whose real names contain @tag:value are exempted via the
  thinking-suffix blacklist, which now supports re:-prefixed Go regex
  entries.
- Claude reasoning render coerces unsupported combinations (disable,
  adaptive, budgets) with warning diagnostics instead of erroring;
  native-protocol requests without host syntax pass through untouched.

BREAKING(openrouter): drop the host-invented "-thinking" model-name
alias (added in 4f6d16e36) that trimmed any *-thinking model on
OpenRouter channels and injected reasoning.enabled. It matched too
broadly and mangled real model IDs such as kimi-k2-thinking.
Migration: use some-model@thinking:on, or keep the old public name via
a channel model mapping {"some-model-thinking": "some-model@thinking:on"}.
Claude/Gemini family aliases (incl. anthropic/claude-*-thinking) keep
working via the family whitelist.
2026-09-04 20:45:52 +08:00

158 lines
5.5 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"
"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/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())
}
if err := helper.ApplyReasoningModelSuffix(c, info, request); err != nil {
return newConvertRequestFailedError(c, info, err)
}
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 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) {
usage, newApiErr := textRequestViaResponses(c, info, adaptor, request)
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())
}
requestBody = common.NewReplayableBodyReader(storage)
} else {
convertedRequest, err := adaptor.ConvertClaudeRequest(c, info, request)
if err != nil {
return newConvertRequestFailedError(c, info, err)
}
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, closer, err := relaycommon.NewOutboundJSONBody(jsonData)
if err != nil {
return types.NewError(err, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
}
defer closer.Close()
jsonData = nil
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
}