Merge remote-tracking branch 'origin/alpha' into alpha

relay/relay-text.go

@@ -517,6 +517,9 @@ func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 		common.LogError(ctx, fmt.Sprintf("total tokens is 0, cannot consume quota, userId %d, channelId %d, "+
 			"tokenId %d, model %s， pre-consumed quota %d", relayInfo.UserId, relayInfo.ChannelId, relayInfo.TokenId, modelName, preConsumedQuota))
 	} else {
+		if !ratio.IsZero() && quota == 0 {
+			quota = 1
+		}
 		model.UpdateUserUsedQuotaAndRequestCount(relayInfo.UserId, quota)
 		model.UpdateChannelUsedQuota(relayInfo.ChannelId, quota)
 	}

setting/rate_limit.go

@@ -3,6 +3,7 @@ package setting
 import (
 	"encoding/json"
 	"fmt"
+	"math"
 	"one-api/common"
 	"sync"
 )
@@ -58,6 +59,9 @@ func CheckModelRequestRateLimitGroup(jsonStr string) error {
 		if limits[0] < 0 || limits[1] < 1 {
 			return fmt.Errorf("group %s has negative rate limit values: [%d, %d]", group, limits[0], limits[1])
 		}
+		if limits[0] > math.MaxInt32 || limits[1] > math.MaxInt32 {
+			return fmt.Errorf("group %s [%d, %d] has max rate limits value 2147483647", group, limits[0], limits[1])
+		}
 	}
 
 	return nil

web/src/helpers/render.js

@@ -883,12 +883,22 @@ export function renderQuotaWithAmount(amount) {
 }
 
 export function renderQuota(quota, digits = 2) {
+
   let quotaPerUnit = localStorage.getItem('quota_per_unit');
   let displayInCurrency = localStorage.getItem('display_in_currency');
   quotaPerUnit = parseFloat(quotaPerUnit);
   displayInCurrency = displayInCurrency === 'true';
   if (displayInCurrency) {
-    return '$' + (quota / quotaPerUnit).toFixed(digits);
+    const result = quota / quotaPerUnit;
+    const fixedResult = result.toFixed(digits);
+    
+    // 如果 toFixed 后结果为 0 但原始值不为 0，显示最小值
+    if (parseFloat(fixedResult) === 0 && quota > 0 && result > 0) {
+      const minValue = Math.pow(10, -digits);
+      return '$' + minValue.toFixed(digits);
+    }
+    
+    return '$' + fixedResult;
   }
   return renderNumber(quota);
 }

web/src/pages/Setting/RateLimit/SettingsRequestRateLimit.js

@@ -147,6 +147,7 @@ export default function RequestRateLimit(props) {
                   label={t('用户每周期最多请求次数')}
                   step={1}
                   min={0}
+                  max={100000000}
                   suffix={t('次')}
                   extraText={t('包括失败请求的次数，0代表不限制')}
                   field={'ModelRequestRateLimitCount'}
@@ -163,6 +164,7 @@ export default function RequestRateLimit(props) {
                   label={t('用户每周期最多请求完成次数')}
                   step={1}
                   min={1}
+                  max={100000000}
                   suffix={t('次')}
                   extraText={t('只包括请求成功的次数')}
                   field={'ModelRequestRateLimitSuccessCount'}
@@ -199,6 +201,7 @@ export default function RequestRateLimit(props) {
                         <li>{t('使用 JSON 对象格式，格式为：{"组名": [最多请求次数, 最多请求完成次数]}')}</li>
                       <li>{t('示例：{"default": [200, 100], "vip": [0, 1000]}。')}</li>
                       <li>{t('[最多请求次数]必须大于等于0，[最多请求完成次数]必须大于等于1。')}</li>
+                        <li>{t('[最多请求次数]和[最多请求完成次数]的最大值为2147483647。')}</li>
                         <li>{t('分组速率配置优先级高于全局速率限制。')}</li>
                         <li>{t('限制周期统一使用上方配置的“限制周期”值。')}</li>
                       </ul>