feat: define a run ID per continuous execution of a session

.github/workflows/deploy-pr.yaml

@@ -97,7 +97,7 @@ jobs:
           echo "KUBECONFIG=${KUBECONFIG}" >> "$GITHUB_ENV"
 
       - name: Build and deploy
-        uses: SwissDataScienceCenter/renku-actions/deploy-renku@v1.22.1
+        uses: SwissDataScienceCenter/renku-actions/deploy-renku@leafty/what-da-heck
         env:
           DOCKER_PASSWORD: ${{ secrets.RENKU_DOCKER_PASSWORD }}
           DOCKER_USERNAME: ${{ secrets.RENKU_DOCKER_USERNAME }}

api/v1alpha1/amaltheasession_children.go

@@ -218,12 +218,22 @@ func (cr *AmaltheaSession) StatefulSet(cfg config.AmaltheaSessionConfiguration)
 		return appsv1.StatefulSet{}, err
 	}
 
+	labels := cr.childLabels()
+	annotations := map[string]string{}
+	for key := range cr.Spec.Template.Metadata.Annotations {
+		annotations[key] = cr.Spec.Template.Metadata.Annotations[key]
+	}
+	// Add the annotation for the runID
+	if cr.Status.RunId != "" {
+		annotations["renku.io/run_id"] = cr.Status.RunId
+	}
+
 	sts := appsv1.StatefulSet{
 		ObjectMeta: metav1.ObjectMeta{
 			Name:        cr.Name,
 			Namespace:   cr.Namespace,
-			Labels:      cr.childLabels(),
-			Annotations: cr.Spec.Template.Metadata.Annotations,
+			Labels:      labels,
+			Annotations: annotations,
 		},
 		Spec: appsv1.StatefulSetSpec{
 			// NOTE: Parallel pod management policy is important
@@ -235,8 +245,8 @@ func (cr *AmaltheaSession) StatefulSet(cfg config.AmaltheaSessionConfiguration)
 			},
 			Template: v1.PodTemplateSpec{
 				ObjectMeta: metav1.ObjectMeta{
-					Labels:      cr.childLabels(),
-					Annotations: cr.Spec.Template.Metadata.Annotations,
+					Labels:      labels,
+					Annotations: annotations,
 				},
 				Spec: *pod,
 			},

api/v1alpha1/amaltheasession_types.go

@@ -485,6 +485,10 @@ type AmaltheaSessionStatus struct {
 	// The date-time when the session is hibernated.
 	WillHibernateAt metav1.Time `json:"willHibernateAt,omitempty"`
 
+	// The ID of the current run of the workload. A run is a continuous execution of the workload;
+	// every time a session gets resumed from hibernation, it gets a new runID.
+	RunId string `json:"runID,omitempty"`
+
 	// If the state is failed then the message will contain information about what went wrong, otherwise it is empty
 	// +optional
 	Error string `json:"error,omitempty"`

config/crd/bases/amalthea.dev_amaltheasessions.yaml

@@ -6590,6 +6590,11 @@ spec:
                   total:
                     type: integer
                 type: object
+              runID:
+                description: |-
+                  The ID of the current run of the workload. A run is a continuous execution of the workload;
+                  every time a session gets resumed from hibernation, it gets a new runID.
+                type: string
               state:
                 default: NotReady
                 enum:

go.mod

@@ -19,6 +19,7 @@ require (
 	github.com/oapi-codegen/oapi-codegen/v2 v2.5.0
 	github.com/oapi-codegen/runtime v1.1.2
 	github.com/oasdiff/yaml v0.0.0-20250309154309-f31be36b4037
+	github.com/oklog/ulid/v2 v2.1.1
 	github.com/onsi/ginkgo/v2 v2.23.4
 	github.com/onsi/gomega v1.37.0
 	github.com/prometheus/client_golang v1.19.1

go.sum

@@ -209,6 +209,8 @@ github.com/oasdiff/yaml v0.0.0-20250309154309-f31be36b4037 h1:G7ERwszslrBzRxj//J
 github.com/oasdiff/yaml v0.0.0-20250309154309-f31be36b4037/go.mod h1:2bpvgLBZEtENV5scfDFEtB/5+1M4hkQhDQrccEJ/qGw=
 github.com/oasdiff/yaml3 v0.0.0-20250309153720-d2182401db90 h1:bQx3WeLcUWy+RletIKwUIt4x3t8n2SxavmoclizMb8c=
 github.com/oasdiff/yaml3 v0.0.0-20250309153720-d2182401db90/go.mod h1:y5+oSEHCPT/DGrS++Wc/479ERge0zTFxaF8PbGKcg2o=
+github.com/oklog/ulid/v2 v2.1.1 h1:suPZ4ARWLOJLegGFiZZ1dFAkqzhMjL3J1TzI+5wHz8s=
+github.com/oklog/ulid/v2 v2.1.1/go.mod h1:rcEKHmBBKfef9DhnvX7y1HZBYxjXb0cP5ExxNsTT1QQ=
 github.com/onsi/ginkgo v1.6.0/go.mod h1:lLunBs/Ym6LB5Z9jYTR76FiuTmxDTDusOGeTQH+WWjE=
 github.com/onsi/ginkgo v1.10.2/go.mod h1:lLunBs/Ym6LB5Z9jYTR76FiuTmxDTDusOGeTQH+WWjE=
 github.com/onsi/ginkgo v1.12.1/go.mod h1:zj2OWP4+oCPe1qIXoGWkgMRwljMUYCdkwsT2108oapk=
@@ -226,6 +228,7 @@ github.com/onsi/gomega v1.37.0 h1:CdEG8g0S133B4OswTDC/5XPSzE1OeP29QOioj2PID2Y=
 github.com/onsi/gomega v1.37.0/go.mod h1:8D9+Txp43QWKhM24yyOBEdpkzN8FvJyAwecBgsU4KU0=
 github.com/opencontainers/go-digest v1.0.0 h1:apOUWs51W5PlhuyGyz9FCeeBIOUDA/6nW8Oi/yOhh5U=
 github.com/opencontainers/go-digest v1.0.0/go.mod h1:0JzlMkj0TRzQZfJkVvzbP0HBR3IKzErnv2BNG4W4MAM=
+github.com/pborman/getopt v0.0.0-20170112200414-7148bc3a4c30/go.mod h1:85jBQOZwpVEaDAr341tbn15RS4fCAsIst0qp7i8ex1o=
 github.com/pelletier/go-toml/v2 v2.2.3 h1:YmeHyLY8mFWbdkNWwpr+qIL2bEqT0o95WSdkNHvL12M=
 github.com/pelletier/go-toml/v2 v2.2.3/go.mod h1:MfCQTFTvCcUyyvvwm1+G6H/jORL20Xlb6rzQu9GuUkc=
 github.com/perimeterx/marshmallow v1.1.5 h1:a2LALqQ1BlHM8PZblsDdidgv1mWi1DgC2UmX50IvK2s=

helm-chart/amalthea-sessions/templates/amaltheasession-crd.yaml

@@ -6592,6 +6592,11 @@ spec:
                   total:
                     type: integer
                 type: object
+              runID:
+                description: |-
+                  The ID of the current run of the workload. A run is a continuous execution of the workload;
+                  every time a session gets resumed from hibernation, it gets a new runID.
+                type: string
               state:
                 default: NotReady
                 enum:

internal/controller/amaltheasession_controller.go

@@ -24,6 +24,7 @@ import (
 	"time"
 
 	"github.com/getsentry/sentry-go"
+	"github.com/oklog/ulid/v2"
 
 	appsv1 "k8s.io/api/apps/v1"
 	corev1 "k8s.io/api/core/v1"
@@ -144,6 +145,8 @@ func (r *AmaltheaSessionReconciler) reconcileInner(ctx context.Context, req ctrl
 		if reflect.DeepEqual(amaltheasession.Status, amaltheadevv1alpha1.AmaltheaSessionStatus{State: amaltheadevv1alpha1.NotReady, Idle: false}) {
 			// First status update/render
 			amaltheasession.Status.URL = amaltheasession.GetURLString()
+			// NEW, do we need this here?
+			// amaltheasession.Status.RunId = ulid.Make().String()
 			err := r.Status().Update(ctx, amaltheasession)
 			if err != nil {
 				err = r.Get(ctx, req.NamespacedName, amaltheasession)
@@ -199,6 +202,18 @@ func (r *AmaltheaSessionReconciler) reconcileInner(ctx context.Context, req ctrl
 		return ctrl.Result{Requeue: true}, nil
 	}
 
+	// NEW
+	// We need to handle run ID before generating children resources
+	runID := amaltheasession.Status.RunId
+	if amaltheasession.Spec.Hibernated {
+		// The session is getting hibernated, unset the run ID
+		runID = ""
+	} else if runID == "" {
+		// The session just got created or is being resumed, set the new run ID
+		runID = ulid.Make().String()
+	}
+	amaltheasession.Status.RunId = runID
+
 	children, err := NewChildResources(amaltheasession, r.Configuration)
 	if err != nil {
 		log.Error(

internal/controller/children.go

@@ -823,6 +823,16 @@ func (c ChildResourceUpdates) Status(
 
 	hibernationDate := calculateHibernationDate(log, cr.GetCreationTimestamp(), cr.Status, cr.Spec.Culling)
 
+	// NEW
+	// runID := cr.Status.RunId
+	// if cr.Spec.Hibernated {
+	// 	// The session is getting hibernated, unset the run ID
+	// 	runID = ""
+	// } else if runID == "" {
+	// 	// The session just got created or is being resumed, set the new run ID
+	// 	runID = ulid.Make().String()
+	// }
+
 	status := amaltheadevv1alpha1.AmaltheaSessionStatus{
 		Conditions:            Conditions(state, ctx, r, cr),
 		State:                 state,
@@ -833,6 +843,7 @@ func (c ChildResourceUpdates) Status(
 		FailingSince:          failingSince,
 		HibernatedSince:       hibernatedSince,
 		WillHibernateAt:       hibernationDate,
+		RunId:                 cr.Status.RunId,
 		Error:                 failMsg,
 	}
 	warning := c.warningMessage(pod)