[FEATURE] add metrics to zarf-agent

examples/big-bang/README.md

@@ -42,3 +42,125 @@ To view the example in its entirety, select the `Edit this page` link below the
 :::
 
 <ExampleYAML example="big-bang/yolo" showLink={false} />
+
+## Big Bang Scrape Zarf Agent Metrics
+
+The Zarf Agent emits Prometheus metrics that can be scraped by Big Bang's Prometheus Operator. To enable this, set `monitoring.enabled` to true in the `config/disable-all.yaml`, and uncomment the `disable-all.yaml` under the `components.extentions.bigbang.valuesFiles` section in `zarf.yaml`.
+
+Finally, create a `ServiceMonitor` for the Zarf Agent. Since this the Zarf Agent exposes an `https` port, we need to provide the `bearerTokenFile` and `tlsConfig` to specify the TLS settings for scraping agaist the service. 
+
+```yaml
+kubectl create -f -<<EOF
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  labels:
+    artifact: monitoring-agent-hook
+  name: monitoring-agent-hook
+  namespace: monitoring
+spec:
+  endpoints:
+  - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
+    targetPort: 443
+    path: /metrics
+    scheme: https
+    tlsConfig:
+      caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+      insecureSkipVerify: false
+      # host name for the TLS handshake
+      serverName: zarf-agent.zarf.svc.cluster.local 
+  jobLabel: zarf-agent
+  namespaceSelector:
+    matchNames:
+    - zarf
+  selector:
+    matchLabels:
+      app: agent-hook
+EOF
+```
+
+At this point, we can curl against the Prometheus API to ensure the Zarf Agent target has been picked up by the Prometheus Operator.
+
+```bash
+# terminal 1
+$ kubectl port-forward svc/prometheus-operated 9090 -n monitoring
+
+# terminal 2 
+$ curl http://localhost:9090/api/v1/targets | jq | grep -A 28 -B 10 '__meta_kubernetes_pod_name": "agent-hook'
+
+          "__meta_kubernetes_pod_controller_kind": "ReplicaSet",
+          "__meta_kubernetes_pod_controller_name": "agent-hook-566b5959d4",
+          "__meta_kubernetes_pod_host_ip": "172.18.0.2",
+          "__meta_kubernetes_pod_ip": "10.42.0.13",
+          "__meta_kubernetes_pod_label_app": "agent-hook",
+          "__meta_kubernetes_pod_label_pod_template_hash": "566b5959d4",
+          "__meta_kubernetes_pod_label_zarf_dev_agent": "ignore",
+          "__meta_kubernetes_pod_labelpresent_app": "true",
+          "__meta_kubernetes_pod_labelpresent_pod_template_hash": "true",
+          "__meta_kubernetes_pod_labelpresent_zarf_dev_agent": "true",
+          "__meta_kubernetes_pod_name": "agent-hook-566b5959d4-gs875",
+          "__meta_kubernetes_pod_node_name": "k3d-k3s-default-server-0",
+          "__meta_kubernetes_pod_phase": "Running",
+          "__meta_kubernetes_pod_ready": "true",
+          "__meta_kubernetes_pod_uid": "a66fbd5c-dfe5-4fef-9645-0e0c6cbfed8d",
+          "__meta_kubernetes_service_annotation_meta_helm_sh_release_name": "zarf-d2db14ef40305397791454e883b26fc94ad9615d",
+          "__meta_kubernetes_service_annotation_meta_helm_sh_release_namespace": "zarf",
+          "__meta_kubernetes_service_annotationpresent_meta_helm_sh_release_name": "true",
+          "__meta_kubernetes_service_annotationpresent_meta_helm_sh_release_namespace": "true",
+          "__meta_kubernetes_service_label_app_kubernetes_io_managed_by": "Helm",
+          "__meta_kubernetes_service_label_zarf_dev": "agent",
+          "__meta_kubernetes_service_labelpresent_app_kubernetes_io_managed_by": "true",
+          "__meta_kubernetes_service_labelpresent_zarf_dev": "true",
+          "__meta_kubernetes_service_name": "agent-hook",
+          "__metrics_path__": "/metrics",
+          "__scheme__": "https",
+          "__scrape_interval__": "30s",
+          "__scrape_timeout__": "10s",
+          "__tmp_prometheus_job_name": "serviceMonitor/monitoring/monitoring-agent-hook/0"
+        }
+      },
+      {
+        "discoveredLabels": {
+          "__address__": "10.42.0.14:8443",
+          "__meta_kubernetes_endpoint_address_target_kind": "Pod",
+          "__meta_kubernetes_endpoint_address_target_name": "agent-hook-566b5959d4-kxx2m",
+          "__meta_kubernetes_endpoint_node_name": "k3d-k3s-default-server-0",
+          "__meta_kubernetes_endpoint_port_protocol": "TCP",
+          "__meta_kubernetes_endpoint_ready": "true",
+--
+          "__meta_kubernetes_pod_controller_kind": "ReplicaSet",
+          "__meta_kubernetes_pod_controller_name": "agent-hook-566b5959d4",
+          "__meta_kubernetes_pod_host_ip": "172.18.0.2",
+          "__meta_kubernetes_pod_ip": "10.42.0.14",
+          "__meta_kubernetes_pod_label_app": "agent-hook",
+          "__meta_kubernetes_pod_label_pod_template_hash": "566b5959d4",
+          "__meta_kubernetes_pod_label_zarf_dev_agent": "ignore",
+          "__meta_kubernetes_pod_labelpresent_app": "true",
+          "__meta_kubernetes_pod_labelpresent_pod_template_hash": "true",
+          "__meta_kubernetes_pod_labelpresent_zarf_dev_agent": "true",
+          "__meta_kubernetes_pod_name": "agent-hook-566b5959d4-kxx2m",
+          "__meta_kubernetes_pod_node_name": "k3d-k3s-default-server-0",
+          "__meta_kubernetes_pod_phase": "Running",
+          "__meta_kubernetes_pod_ready": "true",
+          "__meta_kubernetes_pod_uid": "252d5cd0-b9be-4a23-97cf-d94d349e50a5",
+          "__meta_kubernetes_service_annotation_meta_helm_sh_release_name": "zarf-d2db14ef40305397791454e883b26fc94ad9615d",
+          "__meta_kubernetes_service_annotation_meta_helm_sh_release_namespace": "zarf",
+          "__meta_kubernetes_service_annotationpresent_meta_helm_sh_release_name": "true",
+          "__meta_kubernetes_service_annotationpresent_meta_helm_sh_release_namespace": "true",
+          "__meta_kubernetes_service_label_app_kubernetes_io_managed_by": "Helm",
+          "__meta_kubernetes_service_label_zarf_dev": "agent",
+          "__meta_kubernetes_service_labelpresent_app_kubernetes_io_managed_by": "true",
+          "__meta_kubernetes_service_labelpresent_zarf_dev": "true",
+          "__meta_kubernetes_service_name": "agent-hook",
+          "__metrics_path__": "/metrics",
+          "__scheme__": "https",
+          "__scrape_interval__": "30s",
+          "__scrape_timeout__": "10s",
+          "__tmp_prometheus_job_name": "serviceMonitor/monitoring/monitoring-agent-hook/0"
+        }
+      },
+```
+
+To see your metrics head to the Prometheus UI at http://localhost:9090/graph and select the `agent_hook` target.
+
+:::

packages/zarf-agent/manifests/service.yaml

@@ -3,6 +3,8 @@ kind: Service
 metadata:
   name: agent-hook
   namespace: zarf
+  labels:
+    app: agent-hook
 spec:
   selector:
     app: agent-hook

src/internal/agent/http/server.go

@@ -10,6 +10,7 @@ import (
 
 	"github.com/defenseunicorns/zarf/src/internal/agent/hooks"
 	"github.com/defenseunicorns/zarf/src/pkg/message"
+	"github.com/prometheus/client_golang/prometheus/promhttp"
 )
 
 // NewAdmissionServer creates an http.Server for the mutating webhook admission handler.
@@ -26,6 +27,7 @@ func NewAdmissionServer(port string) *http.Server {
 	mux.Handle("/healthz", healthz())
 	mux.Handle("/mutate/pod", ah.Serve(podsMutation))
 	mux.Handle("/mutate/flux-gitrepository", ah.Serve(gitRepositoryMutation))
+	mux.Handle("/metrics", promhttp.Handler())
 
 	return &http.Server{
 		Addr:    fmt.Sprintf(":%s", port),
@@ -40,6 +42,7 @@ func NewProxyServer(port string) *http.Server {
 	mux := http.NewServeMux()
 	mux.Handle("/healthz", healthz())
 	mux.Handle("/", ProxyHandler())
+	mux.Handle("/metrics", promhttp.Handler())
 
 	return &http.Server{
 		Addr:    fmt.Sprintf(":%s", port),