feat: able to disable channel by success rate

monitor/channel.go

@@ -0,0 +1,46 @@
+package monitor
+
+import (
+	"fmt"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/logger"
+	"github.com/songquanpeng/one-api/model"
+)
+
+func notifyRootUser(subject string, content string) {
+	if config.RootUserEmail == "" {
+		config.RootUserEmail = model.GetRootUserEmail()
+	}
+	err := common.SendEmail(subject, config.RootUserEmail, content)
+	if err != nil {
+		logger.SysError(fmt.Sprintf("failed to send email: %s", err.Error()))
+	}
+}
+
+// DisableChannel disable & notify
+func DisableChannel(channelId int, channelName string, reason string) {
+	model.UpdateChannelStatusById(channelId, common.ChannelStatusAutoDisabled)
+	logger.SysLog(fmt.Sprintf("channel #%d has been disabled: %s", channelId, reason))
+	subject := fmt.Sprintf("通道「%s」（#%d）已被禁用", channelName, channelId)
+	content := fmt.Sprintf("通道「%s」（#%d）已被禁用，原因：%s", channelName, channelId, reason)
+	notifyRootUser(subject, content)
+}
+
+func MetricDisableChannel(channelId int, successRate float64) {
+	model.UpdateChannelStatusById(channelId, common.ChannelStatusAutoDisabled)
+	logger.SysLog(fmt.Sprintf("channel #%d has been disabled due to low success rate: %.2f", channelId, successRate*100))
+	subject := fmt.Sprintf("通道 #%d 已被禁用", channelId)
+	content := fmt.Sprintf("该渠道在最近 %d 次调用中成功率为 %.2f%%，低于阈值 %.2f%%，因此被系统自动禁用。",
+		config.MetricQueueSize, successRate*100, config.MetricSuccessRateThreshold*100)
+	notifyRootUser(subject, content)
+}
+
+// EnableChannel enable & notify
+func EnableChannel(channelId int, channelName string) {
+	model.UpdateChannelStatusById(channelId, common.ChannelStatusEnabled)
+	logger.SysLog(fmt.Sprintf("channel #%d has been enabled", channelId))
+	subject := fmt.Sprintf("通道「%s」（#%d）已被启用", channelName, channelId)
+	content := fmt.Sprintf("通道「%s」（#%d）已被启用", channelName, channelId)
+	notifyRootUser(subject, content)
+}

monitor/metric.go

@@ -0,0 +1,79 @@
+package monitor
+
+import (
+	"github.com/songquanpeng/one-api/common/config"
+)
+
+var store = make(map[int][]bool)
+var metricSuccessChan = make(chan int, config.MetricSuccessChanSize)
+var metricFailChan = make(chan int, config.MetricFailChanSize)
+
+func consumeSuccess(channelId int) {
+	if len(store[channelId]) > config.MetricQueueSize {
+		store[channelId] = store[channelId][1:]
+	}
+	store[channelId] = append(store[channelId], true)
+}
+
+func consumeFail(channelId int) (bool, float64) {
+	if len(store[channelId]) > config.MetricQueueSize {
+		store[channelId] = store[channelId][1:]
+	}
+	store[channelId] = append(store[channelId], false)
+	successCount := 0
+	for _, success := range store[channelId] {
+		if success {
+			successCount++
+		}
+	}
+	successRate := float64(successCount) / float64(len(store[channelId]))
+	if len(store[channelId]) < config.MetricQueueSize {
+		return false, successRate
+	}
+	if successRate < config.MetricSuccessRateThreshold {
+		store[channelId] = make([]bool, 0)
+		return true, successRate
+	}
+	return false, successRate
+}
+
+func metricSuccessConsumer() {
+	for {
+		select {
+		case channelId := <-metricSuccessChan:
+			consumeSuccess(channelId)
+		}
+	}
+}
+
+func metricFailConsumer() {
+	for {
+		select {
+		case channelId := <-metricFailChan:
+			disable, successRate := consumeFail(channelId)
+			if disable {
+				go MetricDisableChannel(channelId, successRate)
+			}
+		}
+	}
+}
+
+func init() {
+	if config.EnableMetric {
+		go metricSuccessConsumer()
+		go metricFailConsumer()
+	}
+}
+
+func Emit(channelId int, success bool) {
+	if !config.EnableMetric {
+		return
+	}
+	go func() {
+		if success {
+			metricSuccessChan <- channelId
+		} else {
+			metricFailChan <- channelId
+		}
+	}()
+}