* 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
96 lines
3.0 KiB
Go
96 lines
3.0 KiB
Go
package service
|
|
|
|
import (
|
|
"fmt"
|
|
"net/http"
|
|
|
|
"github.com/QuantumNous/new-api/logger"
|
|
relaycommon "github.com/QuantumNous/new-api/relay/common"
|
|
"github.com/QuantumNous/new-api/relaykit/types"
|
|
"github.com/gin-gonic/gin"
|
|
)
|
|
|
|
const (
|
|
BillingSourceWallet = "wallet"
|
|
BillingSourceSubscription = "subscription"
|
|
)
|
|
|
|
// PreConsumeBilling 根据用户计费偏好创建 BillingSession 并执行预扣费。
|
|
// 会话存储在 relayInfo.Billing 上,供后续 Settle / Refund 使用。
|
|
func PreConsumeBilling(c *gin.Context, preConsumedQuota int, relayInfo *relaycommon.RelayInfo) *types.NewAPIError {
|
|
if relayInfo != nil && relayInfo.QuotaClamp != nil {
|
|
return types.NewErrorWithStatusCode(
|
|
relayInfo.QuotaClamp,
|
|
types.ErrorCodeModelPriceError,
|
|
http.StatusBadRequest,
|
|
types.ErrOptionWithSkipRetry(),
|
|
)
|
|
}
|
|
if preConsumedQuota < 0 {
|
|
return types.NewErrorWithStatusCode(
|
|
fmt.Errorf("pre-consume quota cannot be negative: %d", preConsumedQuota),
|
|
types.ErrorCodeModelPriceError,
|
|
http.StatusBadRequest,
|
|
types.ErrOptionWithSkipRetry(),
|
|
)
|
|
}
|
|
session, apiErr := NewBillingSession(c, relayInfo, preConsumedQuota)
|
|
if apiErr != nil {
|
|
return apiErr
|
|
}
|
|
relayInfo.Billing = session
|
|
return nil
|
|
}
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// SettleBilling — 后结算辅助函数
|
|
// ---------------------------------------------------------------------------
|
|
|
|
// SettleBilling 执行计费结算。如果 RelayInfo 上有 BillingSession 则通过 session 结算,
|
|
// 否则回退到旧的 PostConsumeQuota 路径(兼容按次计费等场景)。
|
|
func SettleBilling(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, actualQuota int) error {
|
|
if relayInfo.Billing != nil {
|
|
preConsumed := relayInfo.Billing.GetPreConsumedQuota()
|
|
delta := actualQuota - preConsumed
|
|
|
|
if delta > 0 {
|
|
logger.LogInfo(ctx, fmt.Sprintf("预扣费后补扣费:%s(实际消耗:%s,预扣费:%s)",
|
|
logger.FormatQuota(delta),
|
|
logger.FormatQuota(actualQuota),
|
|
logger.FormatQuota(preConsumed),
|
|
))
|
|
} else if delta < 0 {
|
|
logger.LogInfo(ctx, fmt.Sprintf("预扣费后返还扣费:%s(实际消耗:%s,预扣费:%s)",
|
|
logger.FormatQuota(-delta),
|
|
logger.FormatQuota(actualQuota),
|
|
logger.FormatQuota(preConsumed),
|
|
))
|
|
} else {
|
|
logger.LogInfo(ctx, fmt.Sprintf("预扣费与实际消耗一致,无需调整:%s(按次计费)",
|
|
logger.FormatQuota(actualQuota),
|
|
))
|
|
}
|
|
|
|
if err := relayInfo.Billing.Settle(actualQuota); err != nil {
|
|
return err
|
|
}
|
|
|
|
// 发送额度通知(订阅计费使用订阅剩余额度)
|
|
if actualQuota != 0 {
|
|
if relayInfo.BillingSource == BillingSourceSubscription {
|
|
checkAndSendSubscriptionQuotaNotify(relayInfo)
|
|
} else {
|
|
checkAndSendQuotaNotify(relayInfo, actualQuota-preConsumed, preConsumed)
|
|
}
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// 回退:无 BillingSession 时使用旧路径
|
|
quotaDelta := actualQuota - relayInfo.FinalPreConsumedQuota
|
|
if quotaDelta != 0 {
|
|
return PostConsumeQuota(relayInfo, quotaDelta, relayInfo.FinalPreConsumedQuota, true)
|
|
}
|
|
return nil
|
|
}
|