feat: add Prometheus metrics to listener service

Add an optional Prometheus metrics HTTP endpoint to the listener for
monitoring deployment operations. Includes four metrics:

- homelab_deploy_deployments_total (counter with status/action/error_code)
- homelab_deploy_deployment_duration_seconds (histogram with action/success)
- homelab_deploy_deployment_in_progress (gauge)
- homelab_deploy_info (gauge with hostname/tier/role/version)

New CLI flags: --metrics-enabled, --metrics-addr (default :9972)
New NixOS options: metrics.enable, metrics.address, metrics.openFirewall

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
2026-02-07 07:58:22 +01:00
parent 56365835c7
commit 79db119d1c
10 changed files with 613 additions and 9 deletions

View File

@@ -16,7 +16,7 @@ import (
"github.com/urfave/cli/v3"
)
const version = "0.1.7"
const version = "0.1.8"
func main() {
app := &cli.Command{
@@ -90,6 +90,15 @@ func listenerCommand() *cli.Command {
Usage: "NATS subject for host discovery requests",
Value: "deploy.discover",
},
&cli.BoolFlag{
Name: "metrics-enabled",
Usage: "Enable Prometheus metrics endpoint",
},
&cli.StringFlag{
Name: "metrics-addr",
Usage: "Address for Prometheus metrics HTTP server",
Value: ":9972",
},
},
Action: func(ctx context.Context, c *cli.Command) error {
tier := c.String("tier")
@@ -107,6 +116,9 @@ func listenerCommand() *cli.Command {
Timeout: time.Duration(c.Int("timeout")) * time.Second,
DeploySubjects: c.StringSlice("deploy-subject"),
DiscoverSubject: c.String("discover-subject"),
MetricsEnabled: c.Bool("metrics-enabled"),
MetricsAddr: c.String("metrics-addr"),
Version: version,
}
logger := slog.New(slog.NewJSONHandler(os.Stdout, &slog.HandlerOptions{