feat: 算力引擎 Go 后端核心（new-api）

- 统一 OpenAI 兼容 /v1 中继 + 渠道/额度/令牌/流水
- 各领域包：relay 模型网关、model 数据层、controller 管理 API

pkg/billingexpr/settle.go

@@ -0,0 +1,39 @@
+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,
+		RequestRules:           trace.RequestRules,
+		CrossedTier:            crossed,
+		Clamp:                  clamp,
+	}, nil
+}