monlet/agent/internal/config/config.go

package config

import (
	"fmt"
	"os"
	"regexp"
	"time"

	"github.com/BurntSushi/toml"
)

var idPattern = regexp.MustCompile(`^[A-Za-z0-9._:-]+$`)

const (
	maxIDLen           = 128
	defaultHeartbeat   = 30 * time.Second
	defaultBatch       = 10 * time.Second
	defaultMetricsAddr = "127.0.0.1:9465"
)

type Config struct {
	AgentID  string        `toml:"agent_id"`
	Hostname string        `toml:"hostname"`
	Mode     string        `toml:"mode"`
	StateDir string        `toml:"state_dir"`
	Server   ServerConfig  `toml:"server"`
	Metrics  MetricsConfig `toml:"metrics"`
	Checks   []CheckConfig `toml:"checks"`
}

type ServerConfig struct {
	URL               string   `toml:"url"`
	Token             string   `toml:"token"`
	HeartbeatInterval Duration `toml:"heartbeat_interval"`
	BatchInterval     Duration `toml:"batch_interval"`
}

type MetricsConfig struct {
	Enabled bool   `toml:"enabled"`
	Listen  string `toml:"listen"`
}

type CheckConfig struct {
	ID                string   `toml:"id"`
	Name              string   `toml:"name"`
	Command           []string `toml:"command"`
	Interval          Duration `toml:"interval"`
	Timeout           Duration `toml:"timeout"`
	NotificationOwner string   `toml:"notification_owner"`
	DedupeKey         string   `toml:"dedupe_key"`
}

type Duration struct{ time.Duration }

func (d *Duration) UnmarshalText(b []byte) error {
	v, err := time.ParseDuration(string(b))
	if err != nil {
		return err
	}
	d.Duration = v
	return nil
}

func Load(path string) (*Config, error) {
	var c Config
	if _, err := toml.DecodeFile(path, &c); err != nil {
		return nil, fmt.Errorf("read config: %w", err)
	}
	c.applyDefaults()
	if err := c.Validate(); err != nil {
		return nil, err
	}
	return &c, nil
}

func (c *Config) applyDefaults() {
	if c.Mode == "" {
		c.Mode = "hybrid"
	}
	if c.Hostname == "" {
		if h, err := os.Hostname(); err == nil {
			c.Hostname = h
		}
	}
	if c.Server.HeartbeatInterval.Duration == 0 {
		c.Server.HeartbeatInterval.Duration = defaultHeartbeat
	}
	if c.Server.BatchInterval.Duration == 0 {
		c.Server.BatchInterval.Duration = defaultBatch
	}
	if c.Metrics.Listen == "" {
		c.Metrics.Listen = defaultMetricsAddr
	}
}

func (c *Config) Validate() error {
	if c.AgentID != "" {
		if err := ValidateID("agent_id", c.AgentID); err != nil {
			return err
		}
	}
	switch c.Mode {
	case "prometheus_only", "push_only", "hybrid":
	default:
		return fmt.Errorf("invalid mode %q", c.Mode)
	}
	if c.StateDir == "" {
		return fmt.Errorf("state_dir is required")
	}
	if c.PushesToServer() {
		if c.Server.URL == "" {
			return fmt.Errorf("server.url is required for mode %q", c.Mode)
		}
		if c.Server.Token == "" {
			return fmt.Errorf("server.token is required for mode %q", c.Mode)
		}
	}
	if len(c.Checks) == 0 {
		return fmt.Errorf("at least one check is required")
	}
	seen := make(map[string]struct{}, len(c.Checks))
	for i := range c.Checks {
		ch := &c.Checks[i]
		if err := ValidateID("checks[].id", ch.ID); err != nil {
			return err
		}
		if _, dup := seen[ch.ID]; dup {
			return fmt.Errorf("duplicate check id %q", ch.ID)
		}
		seen[ch.ID] = struct{}{}
		if len(ch.Command) == 0 {
			return fmt.Errorf("check %q: command is required", ch.ID)
		}
		if ch.Interval.Duration <= 0 {
			return fmt.Errorf("check %q: interval must be > 0", ch.ID)
		}
		if ch.Timeout.Duration <= 0 {
			return fmt.Errorf("check %q: timeout must be > 0", ch.ID)
		}
		if ch.Timeout.Duration > ch.Interval.Duration {
			return fmt.Errorf("check %q: timeout must be <= interval", ch.ID)
		}
		switch ch.NotificationOwner {
		case "", "server", "prometheus", "none":
		default:
			return fmt.Errorf("check %q: invalid notification_owner %q", ch.ID, ch.NotificationOwner)
		}
		if ch.NotificationOwner == "" {
			ch.NotificationOwner = "server"
		}
		if len(ch.DedupeKey) > 256 {
			return fmt.Errorf("check %q: dedupe_key too long", ch.ID)
		}
	}
	return nil
}

// PushesToServer is true when the mode requires heartbeat/events push.
func (c *Config) PushesToServer() bool {
	return c.Mode == "push_only" || c.Mode == "hybrid"
}

// ExposesMetrics is true when the agent should serve /metrics.
// `metrics.enabled` is an independent gate; both must agree.
func (c *Config) ExposesMetrics() bool {
	return c.Metrics.Enabled && (c.Mode == "prometheus_only" || c.Mode == "hybrid")
}

func ValidateID(field, v string) error {
	if v == "" {
		return fmt.Errorf("%s is empty", field)
	}
	if len(v) > maxIDLen {
		return fmt.Errorf("%s exceeds %d chars", field, maxIDLen)
	}
	if !idPattern.MatchString(v) {
		return fmt.Errorf("%s has invalid characters", field)
	}
	return nil
}