opencatd-open/backend/internal/channel/health.go

package channel

import (
	"context"
	"fmt"
	"opencatd-open/internal/dao"
	"opencatd-open/internal/store"
	"opencatd-open/internal/pkg/crypto"
	"net/http"
	"time"
)

// HealthConfig 健康检查配置
type HealthConfig struct {
	Interval          time.Duration // 检查间隔
	Timeout           time.Duration // 请求超时
	FailureThreshold  int           // 连续失败次数阈值
	DegradedCooldown  time.Duration // degraded 冷却时间
	CooldownCooldown  time.Duration // cooldown 冷却时间
}

// DefaultHealthConfig 返回默认健康检查配置
func DefaultHealthConfig() HealthConfig {
	return HealthConfig{
		Interval:         5 * time.Minute,
		Timeout:          10 * time.Second,
		FailureThreshold: 3,
		DegradedCooldown: 5 * time.Minute,
		CooldownCooldown: 15 * time.Minute,
	}
}

type HealthChecker struct {
	channelDAO *dao.ChannelDAO
	service    *Service
	client     *http.Client
	config     HealthConfig
}

func NewHealthChecker(channelDAO *dao.ChannelDAO, service *Service, config ...HealthConfig) *HealthChecker {
	cfg := DefaultHealthConfig()
	if len(config) > 0 {
		cfg = config[0]
	}
	return &HealthChecker{
		channelDAO: channelDAO,
		service:    service,
		client: &http.Client{
			Timeout: cfg.Timeout,
		},
		config: cfg,
	}
}

// CheckChannel performs a health check on a channel
func (hc *HealthChecker) CheckChannel(ctx context.Context, channel *store.Channel) error {
	apiKey, err := crypto.Decrypt(channel.APIKeyEnc)
	if err != nil {
		return fmt.Errorf("failed to decrypt API key: %w", err)
	}

	// Simple health check: try to list models
	var url string
	switch channel.Provider {
	case store.ChannelProviderOpenAI:
		url = channel.UpstreamURL("chat", "/models")
	case store.ChannelProviderAnthropic:
		url = "https://api.anthropic.com/v1/models"
	default:
		url = channel.UpstreamURL("chat", "/models")
	}

	req, err := http.NewRequestWithContext(ctx, "GET", url, nil)
	if err != nil {
		return fmt.Errorf("failed to create request: %w", err)
	}

	// Set headers based on provider
	switch channel.Provider {
	case store.ChannelProviderOpenAI, store.ChannelProviderCompatible:
		req.Header.Set("Authorization", "Bearer "+apiKey)
	case store.ChannelProviderAnthropic:
		req.Header.Set("x-api-key", apiKey)
		req.Header.Set("anthropic-version", "2023-06-01")
	}
	req.Header.Set("Content-Type", "application/json")

	resp, err := hc.client.Do(req)
	if err != nil {
		hc.service.RecordFailure(channel.ID)
		return fmt.Errorf("health check failed: %w", err)
	}
	defer resp.Body.Close()

	if resp.StatusCode == http.StatusOK {
		hc.service.RecordSuccess(channel.ID)
		return nil
	}

	hc.service.RecordFailure(channel.ID)
	return fmt.Errorf("health check returned status %d", resp.StatusCode)
}

// CheckAllChannels checks health of all enabled channels
func (hc *HealthChecker) CheckAllChannels(ctx context.Context) error {
	channels, err := hc.channelDAO.ListEnabled()
	if err != nil {
		return err
	}

	for _, ch := range channels {
		if err := hc.CheckChannel(ctx, ch); err != nil {
			fmt.Printf("Channel %s health check failed: %v\n", ch.Name, err)
		}
	}
	return nil
}

// StartPeriodicCheck starts periodic health checks
func (hc *HealthChecker) StartPeriodicCheck(ctx context.Context, interval ...time.Duration) {
	interval_ := hc.config.Interval
	if len(interval) > 0 {
		interval_ = interval[0]
	}
	ticker := time.NewTicker(interval_)
	defer ticker.Stop()

	for {
		select {
		case <-ctx.Done():
			return
		case <-ticker.C:
			if err := hc.CheckAllChannels(ctx); err != nil {
				fmt.Printf("Periodic health check error: %v\n", err)
			}
		}
	}
}