Files
new-api/service/violation_fee.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

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
}