Files
new-api/pkg/billingexpr/settle.go
T
CaIon bae799ccb1 fix(billing): surface quota saturation events for admin auditing
Thread int32 saturation clamps from tiered settlement and video task
recompute into the consume/task logs under admin_info, so oversized or
malformed billing inputs stay auditable. Clamp negative audio duration
before token conversion and gate the saturation UI markers on admin.
2026-07-07 12:20:07 +08:00

39 lines
1.4 KiB
Go

package billingexpr
import "github.com/QuantumNous/new-api/common"
// quotaConversion converts raw expression output to quota based on the
// expression version. This is the central dispatch point for future versions
// that may use a different conversion formula.
func quotaConversion(exprOutput float64, snap *BillingSnapshot) float64 {
switch snap.ExprVersion {
default: // v1: coefficients are $/1M tokens prices
return exprOutput / 1_000_000 * snap.QuotaPerUnit
}
}
// ComputeTieredQuota runs the Expr from a frozen BillingSnapshot against
// actual token counts and returns the settlement result.
func ComputeTieredQuota(snap *BillingSnapshot, params TokenParams) (TieredResult, error) {
return ComputeTieredQuotaWithRequest(snap, params, RequestInput{})
}
func ComputeTieredQuotaWithRequest(snap *BillingSnapshot, params TokenParams, request RequestInput) (TieredResult, error) {
cost, trace, err := RunExprByHashWithRequest(snap.ExprString, snap.ExprHash, params, request)
if err != nil {
return TieredResult{}, err
}
quotaBeforeGroup := quotaConversion(cost, snap)
afterGroup, clamp := common.QuotaRoundChecked(quotaBeforeGroup * snap.GroupRatio)
crossed := trace.MatchedTier != snap.EstimatedTier
return TieredResult{
ActualQuotaBeforeGroup: quotaBeforeGroup,
ActualQuotaAfterGroup: afterGroup,
MatchedTier: trace.MatchedTier,
CrossedTier: crossed,
Clamp: clamp,
}, nil
}