* 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
165 lines
4.7 KiB
Go
165 lines
4.7 KiB
Go
package service
|
|
|
|
import (
|
|
"fmt"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/logger"
|
|
"github.com/QuantumNous/new-api/model"
|
|
relaycommon "github.com/QuantumNous/new-api/relay/common"
|
|
"github.com/QuantumNous/new-api/relaykit/types"
|
|
"github.com/QuantumNous/new-api/setting/model_setting"
|
|
|
|
"github.com/shopspring/decimal"
|
|
|
|
"github.com/gin-gonic/gin"
|
|
)
|
|
|
|
const (
|
|
ViolationFeeCodePrefix = "violation_fee."
|
|
CSAMViolationMarker = "Failed check: SAFETY_CHECK_TYPE"
|
|
ContentViolatesUsageMarker = "Content violates usage guidelines"
|
|
)
|
|
|
|
func IsViolationFeeCode(code types.ErrorCode) bool {
|
|
return strings.HasPrefix(string(code), ViolationFeeCodePrefix)
|
|
}
|
|
|
|
func HasCSAMViolationMarker(err *types.NewAPIError) bool {
|
|
if err == nil {
|
|
return false
|
|
}
|
|
if strings.Contains(err.Error(), CSAMViolationMarker) || strings.Contains(err.Error(), ContentViolatesUsageMarker) {
|
|
return true
|
|
}
|
|
msg := err.ToOpenAIError().Message
|
|
return strings.Contains(msg, CSAMViolationMarker) || strings.Contains(err.Error(), ContentViolatesUsageMarker)
|
|
}
|
|
|
|
func WrapAsViolationFeeGrokCSAM(err *types.NewAPIError) *types.NewAPIError {
|
|
if err == nil {
|
|
return nil
|
|
}
|
|
oai := err.ToOpenAIError()
|
|
oai.Type = string(types.ErrorCodeViolationFeeGrokCSAM)
|
|
oai.Code = string(types.ErrorCodeViolationFeeGrokCSAM)
|
|
return types.WithOpenAIError(oai, err.StatusCode, types.ErrOptionWithSkipRetry())
|
|
}
|
|
|
|
// NormalizeViolationFeeError ensures:
|
|
// - if the CSAM marker is present, error.code is set to a stable violation-fee code and skip-retry is enabled.
|
|
// - if error.code already has the violation-fee prefix, skip-retry is enabled.
|
|
//
|
|
// It must be called before retry decision logic.
|
|
func NormalizeViolationFeeError(err *types.NewAPIError) *types.NewAPIError {
|
|
if err == nil {
|
|
return nil
|
|
}
|
|
|
|
if HasCSAMViolationMarker(err) {
|
|
return WrapAsViolationFeeGrokCSAM(err)
|
|
}
|
|
|
|
if IsViolationFeeCode(err.GetErrorCode()) {
|
|
oai := err.ToOpenAIError()
|
|
return types.WithOpenAIError(oai, err.StatusCode, types.ErrOptionWithSkipRetry())
|
|
}
|
|
|
|
return err
|
|
}
|
|
|
|
func shouldChargeViolationFee(err *types.NewAPIError) bool {
|
|
if err == nil {
|
|
return false
|
|
}
|
|
if err.GetErrorCode() == types.ErrorCodeViolationFeeGrokCSAM {
|
|
return true
|
|
}
|
|
// In case some callers didn't normalize, keep a safety net.
|
|
return HasCSAMViolationMarker(err)
|
|
}
|
|
|
|
func calcViolationFeeQuota(amount, groupRatio float64) int {
|
|
if amount <= 0 {
|
|
return 0
|
|
}
|
|
if groupRatio <= 0 {
|
|
return 0
|
|
}
|
|
quota := decimal.NewFromFloat(amount).
|
|
Mul(decimal.NewFromFloat(common.QuotaPerUnit)).
|
|
Mul(decimal.NewFromFloat(groupRatio)).
|
|
Round(0).
|
|
IntPart()
|
|
if quota <= 0 {
|
|
return 0
|
|
}
|
|
return int(quota)
|
|
}
|
|
|
|
// ChargeViolationFeeIfNeeded charges an additional fee after the normal flow finishes (including refund).
|
|
// It uses Grok fee settings as the fee policy.
|
|
func ChargeViolationFeeIfNeeded(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, apiErr *types.NewAPIError) bool {
|
|
if ctx == nil || relayInfo == nil || apiErr == nil {
|
|
return false
|
|
}
|
|
//if relayInfo.IsPlayground {
|
|
// return false
|
|
//}
|
|
if !shouldChargeViolationFee(apiErr) {
|
|
return false
|
|
}
|
|
|
|
settings := model_setting.GetGrokSettings()
|
|
if settings == nil || !settings.ViolationDeductionEnabled {
|
|
return false
|
|
}
|
|
|
|
groupRatio := relayInfo.PriceData.GroupRatioInfo.GroupRatio
|
|
feeQuota := calcViolationFeeQuota(settings.ViolationDeductionAmount, groupRatio)
|
|
if feeQuota <= 0 {
|
|
return false
|
|
}
|
|
|
|
if err := PostConsumeQuota(relayInfo, feeQuota, 0, true); err != nil {
|
|
logger.LogError(ctx, fmt.Sprintf("failed to charge violation fee: %s", err.Error()))
|
|
return false
|
|
}
|
|
|
|
model.UpdateUserUsedQuotaAndRequestCount(relayInfo.UserId, feeQuota)
|
|
model.UpdateChannelUsedQuota(relayInfo.ChannelId, feeQuota)
|
|
|
|
useTimeSeconds := time.Now().Unix() - relayInfo.StartTime.Unix()
|
|
tokenName := ctx.GetString("token_name")
|
|
oai := apiErr.ToOpenAIError()
|
|
|
|
other := map[string]any{
|
|
"violation_fee": true,
|
|
"violation_fee_code": string(types.ErrorCodeViolationFeeGrokCSAM),
|
|
"fee_quota": feeQuota,
|
|
"base_amount": settings.ViolationDeductionAmount,
|
|
"group_ratio": groupRatio,
|
|
"status_code": apiErr.StatusCode,
|
|
"upstream_error_type": oai.Type,
|
|
"upstream_error_code": fmt.Sprintf("%v", oai.Code),
|
|
"violation_fee_marker": CSAMViolationMarker,
|
|
}
|
|
|
|
model.RecordConsumeLog(ctx, relayInfo.UserId, model.RecordConsumeLogParams{
|
|
ChannelId: relayInfo.ChannelId,
|
|
ModelName: relayInfo.OriginModelName,
|
|
TokenName: tokenName,
|
|
Quota: feeQuota,
|
|
Content: "Violation fee charged",
|
|
TokenId: relayInfo.TokenId,
|
|
UseTimeSeconds: int(useTimeSeconds),
|
|
IsStream: relayInfo.IsStream,
|
|
Group: relayInfo.UsingGroup,
|
|
Other: other,
|
|
})
|
|
|
|
return true
|
|
}
|