refactor: deprecate int32 (#7025)

* refactor: deprecate int32

* fix(db): reject legacy user quota schemas at startup

* fix(quota): enforce wallet bounds and saturating billing conversions

* fix(rate-limit): keep count*duration from wrapping int64

* fix: error message

service/quota.go

@@ -3,7 +3,6 @@ package service
 import (
 	"errors"
 	"fmt"
-	"math"
 	"strings"
 	"time"
 
@@ -272,11 +271,16 @@ func CalcOpenRouterCacheCreateTokens(usage dto.Usage, priceData types.PriceData)
 	completionTokens := float64(usage.CompletionTokens)
 	promptCacheReadTokens := float64(usage.PromptTokensDetails.CachedTokens)
 
-	return int(math.Round((cost -
+	value := (cost -
 		totalPromptTokens*quotaPrice +
 		promptCacheReadTokens*(quotaPrice-promptCacheReadPrice) -
 		completionTokens*completionPrice) /
-		(promptCacheCreatePrice - quotaPrice)))
+		(promptCacheCreatePrice - quotaPrice)
+	quota, clamp := common.QuotaRoundChecked(value)
+	if clamp != nil {
+		return -1
+	}
+	return quota
 }
 
 func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage *dto.Usage, extraContent string) {

service/quota_saturation_test.go

@@ -1,12 +1,15 @@
 package service
 
 import (
+	"math"
 	"net/http"
 	"testing"
 
 	"github.com/QuantumNous/new-api/common"
 	relaycommon "github.com/QuantumNous/new-api/relay/common"
+	"github.com/QuantumNous/new-api/relaykit/dto"
 	"github.com/QuantumNous/new-api/relaykit/types"
+	hosttypes "github.com/QuantumNous/new-api/types"
 
 	"github.com/gin-gonic/gin"
 	"github.com/stretchr/testify/require"
@@ -42,6 +45,28 @@ func TestAttachQuotaSaturationNestsUnderAdminInfo(t *testing.T) {
 	require.Equal(t, common.MaxQuota, sat["clamped"])
 }
 
+func TestCalcViolationFeeQuotaSaturates(t *testing.T) {
+	oldQuotaPerUnit := common.QuotaPerUnit
+	common.QuotaPerUnit = 500_000
+	t.Cleanup(func() { common.QuotaPerUnit = oldQuotaPerUnit })
+
+	require.Equal(t, common.MaxQuota, calcViolationFeeQuota(1e20, 1))
+}
+
+func TestCalcOpenRouterCacheCreateTokensDoesNotWrap(t *testing.T) {
+	oldQuotaPerUnit := common.QuotaPerUnit
+	common.QuotaPerUnit = 500_000
+	t.Cleanup(func() { common.QuotaPerUnit = oldQuotaPerUnit })
+
+	got := CalcOpenRouterCacheCreateTokens(dto.Usage{Cost: math.Inf(1)}, hosttypes.PriceData{
+		ModelRatio:         1,
+		CacheCreationRatio: 2,
+		CacheRatio:         1,
+		CompletionRatio:    1,
+	})
+	require.Equal(t, -1, got)
+}
+
 // TestAttachQuotaSaturationPreservesExistingAdminInfo verifies the marker is
 // merged into a pre-existing admin_info map without clobbering it.
 func TestAttachQuotaSaturationPreservesExistingAdminInfo(t *testing.T) {

service/text_quota.go

@@ -216,8 +216,8 @@ func composeTieredTextQuota(relayInfo *relaycommon.RelayInfo, summary textQuotaS
 	}
 
 	// Saturate the final sum, not just the surcharge: tieredQuota can be near
-	// MaxQuota and adding the surcharge could push the total past the int32
-	// quota policy bound (persisted quota columns are 32-bit).
+	// MaxQuota and adding the surcharge could push the total past the
+	// single-request quota policy bound.
 	total, clamp := common.QuotaFromDecimalChecked(
 		decimal.NewFromInt(int64(tieredQuota)).Add(summary.ToolCallSurchargeQuota),
 	)

service/text_quota_test.go

@@ -774,9 +774,9 @@ func TestComposeTieredTextQuotaErrorFallbackUsesPreConsumedQuota(t *testing.T) {
 // settlement both saturates the quota and records the clamp on RelayInfo, so
 // every consume path (text, audio, WSS) can surface it under admin_info.
 func TestTryTieredSettleRecordsClampOnOverflow(t *testing.T) {
-	// exprOutput = p * 1e9; quotaBeforeGroup = p*1e9 / 1e6 * 5e5 far exceeds
-	// MaxInt32 and must saturate.
-	exprStr := `tier("base", p * 1000000000)`
+	// exprOutput = p * 1e12; quotaBeforeGroup = p*1e12 / 1e6 * 5e5 far exceeds
+	// the supported single-request range and must saturate.
+	exprStr := `tier("base", p * 1000000000000)`
 	relayInfo := &relaycommon.RelayInfo{
 		OriginModelName: "overflow-model",
 		TieredBillingSnapshot: &billingexpr.BillingSnapshot{
@@ -792,7 +792,7 @@ func TestTryTieredSettleRecordsClampOnOverflow(t *testing.T) {
 
 	require.True(t, ok)
 	require.NotNil(t, result)
-	require.Equal(t, math.MaxInt32, quota, "oversized settlement must clamp, never wrap negative")
+	require.Equal(t, common.MaxQuota, quota, "oversized settlement must clamp, never wrap negative")
 	require.NotNil(t, relayInfo.QuotaClamp, "clamp must be recorded on RelayInfo for admin auditing")
 	require.Equal(t, common.QuotaClampOverflow, relayInfo.QuotaClamp.Kind)
 }

service/tiered_settle.go

@@ -180,7 +180,7 @@ func TryTieredSettle(relayInfo *relaycommon.RelayInfo, params billingexpr.TokenP
 		return true, quota, nil
 	}
 
-	// Surface any int32 saturation from settlement onto RelayInfo so the
+	// Surface any single-request saturation from settlement onto RelayInfo so the
 	// consume log records it under admin_info, regardless of which caller
 	// (text, audio, WSS) consumes the returned quota. First non-nil wins.
 	noteQuotaClamp(relayInfo, tr.Clamp)

service/token_counter.go

@@ -140,11 +140,11 @@ func getImageToken(c *gin.Context, fileMeta *types.FileMeta, model string, strea
 			if imageTokens > 1536 {
 				imageTokens = 1536
 			}
-			return int(math.Round(float64(imageTokens) * multiplier)), nil
+			return common.QuotaRound(float64(imageTokens) * multiplier), nil
 		}
 		// below cap
 		imageTokens := rawPatches
-		return int(math.Round(float64(imageTokens) * multiplier)), nil
+		return common.QuotaRound(float64(imageTokens) * multiplier), nil
 	}
 
 	// Tile-based calculation for 4o/4.1/4.5/o1/o3/etc.

service/violation_fee.go

@@ -88,15 +88,14 @@ func calcViolationFeeQuota(amount, groupRatio float64) int {
 	if groupRatio <= 0 {
 		return 0
 	}
-	quota := decimal.NewFromFloat(amount).
+	quota := common.QuotaFromDecimal(decimal.NewFromFloat(amount).
 		Mul(decimal.NewFromFloat(common.QuotaPerUnit)).
 		Mul(decimal.NewFromFloat(groupRatio)).
-		Round(0).
-		IntPart()
+		Round(0))
 	if quota <= 0 {
 		return 0
 	}
-	return int(quota)
+	return quota
 }
 
 // ChargeViolationFeeIfNeeded charges an additional fee after the normal flow finishes (including refund).