feat: collect model performance metrics (#4635)

service/quota.go

@@ -14,6 +14,7 @@ import (
 	"github.com/QuantumNous/new-api/logger"
 	"github.com/QuantumNous/new-api/model"
 	"github.com/QuantumNous/new-api/pkg/billingexpr"
+	perfmetrics "github.com/QuantumNous/new-api/pkg/perf_metrics"
 	relaycommon "github.com/QuantumNous/new-api/relay/common"
 	"github.com/QuantumNous/new-api/setting/ratio_setting"
 	"github.com/QuantumNous/new-api/setting/system_setting"
@@ -219,7 +220,7 @@ func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, mod
 		// in this case, must be some error happened
 		// we cannot just return, because we may have to return the pre-consumed quota
 		quota = 0
-		logContent += fmt.Sprintf("（可能是上游超时）")
+		logContent += "（可能是上游超时）"
 		logger.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, relayInfo.FinalPreConsumedQuota))
 	} else {
@@ -340,7 +341,7 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, u
 		// in this case, must be some error happened
 		// we cannot just return, because we may have to return the pre-consumed quota
 		quota = 0
-		logContent += fmt.Sprintf("（可能是上游超时）")
+		logContent += "（可能是上游超时）"
 		logger.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, relayInfo.OriginModelName, relayInfo.FinalPreConsumedQuota))
 	} else {
@@ -375,6 +376,9 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, u
 		Group:            relayInfo.UsingGroup,
 		Other:            other,
 	})
+	gopool.Go(func() {
+		perfmetrics.RecordRelaySample(relayInfo, true)
+	})
 }
 
 func PreConsumeTokenQuota(relayInfo *relaycommon.RelayInfo, quota int) error {