maintenance: harden metis recovery and fix harbor rollout

scripts/dashboards_render_atlas.py

@@ -1295,48 +1295,53 @@ def build_overview():
             },
         }
     )
-    panels.append(
+    test_success = timeseries_panel(
-        timeseries_panel(
+        42,
-            42,
+        "Platform Test Success Rate",
-            "Ariadne + Metis Test Success Rate",
+        TEST_SUCCESS_RATE,
-            TEST_SUCCESS_RATE,
+        {"h": 6, "w": 6, "x": 12, "y": 14},
-            {"h": 6, "w": 6, "x": 12, "y": 14},
+        unit="percent",
-            unit="percent",
+        max_value=100,
-            max_value=100,
+        legend=None,
-            legend=None,
+        legend_display="list",
-            legend_display="list",
-        )
     )
-    panels.append(
+    test_success["description"] = (
-        bargauge_panel(
+        "Atlas Overview mirrors the Atlas Jobs internal dashboard for automation test health. "
-            43,
+        "Add new test series there first so they roll up here."
-            "Ariadne + Metis Tests with Failures (24h)",
+    )
-            TEST_FAILURES_24H,
+    panels.append(test_success)
-            {"h": 6, "w": 6, "x": 18, "y": 14},
+    test_failures = bargauge_panel(
-            unit="none",
+        43,
-            instant=True,
+        "Platform Tests with Failures (24h)",
-            legend="{{result}}",
+        TEST_FAILURES_24H,
-            overrides=[
+        {"h": 6, "w": 6, "x": 18, "y": 14},
-                {
+        unit="none",
-                    "matcher": {"id": "byName", "options": "error"},
+        instant=True,
-                    "properties": [{"id": "color", "value": {"mode": "fixed", "fixedColor": "yellow"}}],
+        legend="{{result}}",
-                },
+        overrides=[
-                {
+            {
-                    "matcher": {"id": "byName", "options": "failed"},
+                "matcher": {"id": "byName", "options": "error"},
-                    "properties": [{"id": "color", "value": {"mode": "fixed", "fixedColor": "red"}}],
+                "properties": [{"id": "color", "value": {"mode": "fixed", "fixedColor": "yellow"}}],
-                },
-            ],
-            thresholds={
-                "mode": "absolute",
-                "steps": [
-                    {"color": "green", "value": None},
-                    {"color": "yellow", "value": 1},
-                    {"color": "orange", "value": 5},
-                    {"color": "red", "value": 10},
-                ],
             },
-        )
+            {
+                "matcher": {"id": "byName", "options": "failed"},
+                "properties": [{"id": "color", "value": {"mode": "fixed", "fixedColor": "red"}}],
+            },
+        ],
+        thresholds={
+            "mode": "absolute",
+            "steps": [
+                {"color": "green", "value": None},
+                {"color": "yellow", "value": 1},
+                {"color": "orange", "value": 5},
+                {"color": "red", "value": 10},
+            ],
+        },
     )
+    test_failures["description"] = (
+        "This summary is sourced from the Atlas Jobs internal dashboard rather than a separate overview-only query."
+    )
+    panels.append(test_failures)
 
     cpu_scope = "$namespace_scope_cpu"
     gpu_scope = "$namespace_scope_gpu"
@@ -2654,29 +2659,31 @@ def build_jobs_dashboard():
             legend="{{status}}",
         )
     )
-    panels.append(
+    coverage_panel = stat_panel(
-        stat_panel(
+        17,
-            17,
+        "Platform CI Coverage (%)",
-            "Ariadne + Metis CI Coverage (%)",
+        TEST_CI_COVERAGE,
-            TEST_CI_COVERAGE,
+        {"h": 6, "w": 4, "x": 8, "y": 11},
-            {"h": 6, "w": 4, "x": 8, "y": 11},
+        unit="percent",
-            unit="percent",
+        decimals=1,
-            decimals=1,
+        instant=True,
-            instant=True,
+        legend="{{branch}}",
-            legend="{{branch}}",
-        )
     )
-    panels.append(
+    coverage_panel["description"] = "Internal source panel for Atlas Overview automation test rollups."
-        table_panel(
+    panels.append(coverage_panel)
-            18,
+    tests_panel = table_panel(
-            "Ariadne + Metis CI Tests (latest)",
+        18,
-            TEST_CI_TESTS,
+        "Platform CI Tests (latest)",
-            {"h": 6, "w": 12, "x": 12, "y": 11},
+        TEST_CI_TESTS,
-            unit="none",
+        {"h": 6, "w": 12, "x": 12, "y": 11},
-            transformations=[{"id": "labelsToFields", "options": {}}, {"id": "sortBy", "options": {"fields": ["Value"], "order": "desc"}}],
+        unit="none",
-            instant=True,
+        transformations=[{"id": "labelsToFields", "options": {}}, {"id": "sortBy", "options": {"fields": ["Value"], "order": "desc"}}],
-        )
+        instant=True,
     )
+    tests_panel["description"] = (
+        "Atlas Overview test panels depend on these internal repo-tagged CI series."
+    )
+    panels.append(tests_panel)
 
     return {
         "uid": "atlas-jobs",

services/harbor/helmrelease.yaml

@@ -437,8 +437,7 @@ spec:
                           - $patch: replace
                           - name: VAULT_ENV_FILE
                             value: /vault/secrets/harbor-jobservice-env.sh
-                        envFrom:
+                        envFrom: []
-                          - $patch: replace
                           - configMapRef:
                               name: harbor-jobservice-env
                         volumeMounts:

services/jenkins/configmap-jcasc.yaml

@@ -167,6 +167,58 @@ data:
               }
             }
           }
+          pipelineJob('metis') {
+            properties {
+              pipelineTriggers {
+                triggers {
+                  scmTrigger {
+                    scmpoll_spec('H/2 * * * *')
+                    ignorePostCommitHooks(false)
+                  }
+                }
+              }
+            }
+            definition {
+              cpsScm {
+                scm {
+                  git {
+                    remote {
+                      url('https://scm.bstein.dev/bstein/metis.git')
+                      credentials('gitea-pat')
+                    }
+                    branches('*/master')
+                  }
+                }
+                scriptPath('Jenkinsfile')
+              }
+            }
+          }
+          pipelineJob('metis') {
+            properties {
+              pipelineTriggers {
+                triggers {
+                  scmTrigger {
+                    scmpoll_spec('H/5 * * * *')
+                    ignorePostCommitHooks(false)
+                  }
+                }
+              }
+            }
+            definition {
+              cpsScm {
+                scm {
+                  git {
+                    remote {
+                      url('https://scm.bstein.dev/bstein/metis.git')
+                      credentials('gitea-pat')
+                    }
+                    branches('*/master')
+                  }
+                }
+                scriptPath('Jenkinsfile')
+              }
+            }
+          }
           pipelineJob('atlasbot') {
             properties {
               pipelineTriggers {

services/maintenance/ariadne-deployment.yaml

@@ -302,11 +302,11 @@ spec:
             - name: ARIADNE_SCHEDULE_FIREFLY_CRON
               value: "0 3 * * *"
             - name: ARIADNE_SCHEDULE_POD_CLEANER
-              value: "0 * * * *"
+              value: "*/30 * * * *"
             - name: ARIADNE_SCHEDULE_OPENSEARCH_PRUNE
               value: "23 3 * * *"
             - name: ARIADNE_SCHEDULE_IMAGE_SWEEPER
-              value: "30 4 * * *"
+              value: "0 */4 * * *"
             - name: ARIADNE_SCHEDULE_VAULT_K8S_AUTH
               value: "*/15 * * * *"
             - name: ARIADNE_SCHEDULE_VAULT_OIDC
@@ -320,9 +320,9 @@ spec:
             - name: ARIADNE_SCHEDULE_COMMS_SEED_ROOM
               value: "*/10 * * * *"
             - name: ARIADNE_SCHEDULE_CLUSTER_STATE
-              value: "*/15 * * * *"
+              value: "*/10 * * * *"
             - name: ARIADNE_CLUSTER_STATE_KEEP
-              value: "168"
+              value: "720"
             - name: WELCOME_EMAIL_ENABLED
               value: "true"
             - name: K8S_API_TIMEOUT_SEC
@@ -339,6 +339,12 @@ spec:
               value: "1099511627776"
             - name: OPENSEARCH_INDEX_PATTERNS
               value: kube-*,journald-*,trace-analytics-*
+            - name: METIS_BASE_URL
+              value: http://metis.maintenance.svc.cluster.local
+            - name: METIS_TIMEOUT_SEC
+              value: "15"
+            - name: ARIADNE_SCHEDULE_METIS_SENTINEL_WATCH
+              value: "*/30 * * * *"
             - name: METRICS_PATH
               value: "/metrics"
           resources:

services/maintenance/image.yaml

@@ -24,6 +24,52 @@ spec:
 ---
 apiVersion: image.toolkit.fluxcd.io/v1beta2
 kind: ImageRepository
+metadata:
+  name: metis
+  namespace: maintenance
+spec:
+  image: registry.bstein.dev/bstein/metis
+  interval: 1m0s
+  secretRef:
+    name: harbor-regcred
+---
+apiVersion: image.toolkit.fluxcd.io/v1beta2
+kind: ImagePolicy
+metadata:
+  name: metis
+  namespace: maintenance
+spec:
+  imageRepositoryRef:
+    name: metis
+  policy:
+    semver:
+      range: ">=0.1.0-0"
+---
+apiVersion: image.toolkit.fluxcd.io/v1beta2
+kind: ImageRepository
+metadata:
+  name: metis-sentinel
+  namespace: maintenance
+spec:
+  image: registry.bstein.dev/bstein/metis-sentinel
+  interval: 1m0s
+  secretRef:
+    name: harbor-regcred
+---
+apiVersion: image.toolkit.fluxcd.io/v1beta2
+kind: ImagePolicy
+metadata:
+  name: metis-sentinel
+  namespace: maintenance
+spec:
+  imageRepositoryRef:
+    name: metis-sentinel
+  policy:
+    semver:
+      range: ">=0.1.0-0"
+---
+apiVersion: image.toolkit.fluxcd.io/v1beta2
+kind: ImageRepository
 metadata:
   name: soteria
   namespace: maintenance

services/maintenance/kustomization.yaml

@@ -6,32 +6,47 @@ resources:
   - image.yaml
   - secretproviderclass.yaml
   - soteria-configmap.yaml
+  - metis-configmap.yaml
+  - metis-data-pvc.yaml
   - vault-serviceaccount.yaml
   - vault-sync-deployment.yaml
   - ariadne-serviceaccount.yaml
   - ariadne-rbac.yaml
   - disable-k3s-traefik-serviceaccount.yaml
   - k3s-traefik-cleanup-rbac.yaml
+  - metis-serviceaccount.yaml
+  - metis-rbac.yaml
+  - metis-token-sync-serviceaccount.yaml
+  - metis-token-sync-rbac.yaml
   - node-nofile-serviceaccount.yaml
   - pod-cleaner-rbac.yaml
   - soteria-serviceaccount.yaml
   - soteria-rbac.yaml
   - ariadne-deployment.yaml
+  - metis-deployment.yaml
   - oneoffs/ariadne-migrate-job.yaml
   - ariadne-service.yaml
   - soteria-deployment.yaml
   - disable-k3s-traefik-daemonset.yaml
   - oneoffs/k3s-traefik-cleanup-job.yaml
   - node-nofile-daemonset.yaml
+  - metis-sentinel-daemonset.yaml
+  - metis-k3s-token-sync-cronjob.yaml
   - k3s-agent-restart-daemonset.yaml
   - pod-cleaner-cronjob.yaml
   - node-image-sweeper-serviceaccount.yaml
   - node-image-sweeper-daemonset.yaml
   - image-sweeper-cronjob.yaml
+  - metis-service.yaml
+  - metis-ingress.yaml
   - soteria-service.yaml
 images:
   - name: registry.bstein.dev/bstein/ariadne
     newTag: 0.1.0-22 # {"$imagepolicy": "maintenance:ariadne:tag"}
+  - name: registry.bstein.dev/bstein/metis
+    newTag: 0.1.0-0 # {"$imagepolicy": "maintenance:metis:tag"}
+  - name: registry.bstein.dev/bstein/metis-sentinel
+    newTag: 0.1.0-0 # {"$imagepolicy": "maintenance:metis-sentinel:tag"}
   - name: registry.bstein.dev/bstein/soteria
     newTag: 0.1.0-11 # {"$imagepolicy": "maintenance:soteria:tag"}
 configMapGenerator:

services/maintenance/metis-configmap.yaml

@@ -0,0 +1,20 @@
+# services/maintenance/metis-configmap.yaml
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: metis
+  namespace: maintenance
+data:
+  METIS_BIND_ADDR: :8080
+  METIS_INVENTORY_PATH: /app/inventory.titan-rpi4.yaml
+  METIS_DATA_DIR: /var/lib/metis
+  METIS_DEFAULT_FLASH_HOST: titan-22
+  METIS_FLASH_HOSTS: titan-22
+  METIS_LOCAL_HOST: titan-22
+  METIS_ALLOWED_GROUPS: admin,maintainer
+  METIS_MAX_DEVICE_BYTES: "300000000000"
+  METIS_SENTINEL_PUSH_URL: http://metis.maintenance.svc.cluster.local/internal/sentinel/snapshot
+  METIS_SENTINEL_INTERVAL_SEC: "1800"
+  METIS_SENTINEL_NSENTER: "1"
+  METIS_IMAGE_RPI4_ARMBIAN_LONGHORN: https://armbian.chi.auroradev.org/dl/rpi4b/archive/Armbian_26.2.1_Rpi4b_noble_current_6.18.9_minimal.img.xz
+  METIS_IMAGE_RPI4_ARMBIAN_LONGHORN_SHA256: sha256:c450687adf4cc6a59725c43aefd58baf42ec71bdd379227d403cdde281768e46

services/maintenance/metis-data-pvc.yaml

@@ -0,0 +1,13 @@
+# services/maintenance/metis-data-pvc.yaml
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: metis-data
+  namespace: maintenance
+spec:
+  accessModes:
+    - ReadWriteOnce
+  resources:
+    requests:
+      storage: 40Gi
+  storageClassName: local-path

services/maintenance/metis-deployment.yaml

@@ -0,0 +1,47 @@
+# services/maintenance/metis-deployment.yaml
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: metis
+  namespace: maintenance
+spec:
+  replicas: 1
+  revisionHistoryLimit: 3
+  selector:
+    matchLabels:
+      app: metis
+  template:
+    metadata:
+      labels:
+        app: metis
+      annotations:
+        prometheus.io/scrape: "true"
+        prometheus.io/port: "8080"
+        prometheus.io/path: "/metrics"
+    spec:
+      serviceAccountName: metis
+      nodeSelector:
+        kubernetes.io/hostname: titan-22
+        kubernetes.io/arch: amd64
+        node-role.kubernetes.io/worker: "true"
+      containers:
+        - name: metis
+          image: registry.bstein.dev/bstein/metis:latest
+          imagePullPolicy: Always
+          envFrom:
+            - configMapRef:
+                name: metis
+          ports:
+            - name: http
+              containerPort: 8080
+          resources:
+            requests:
+              cpu: 100m
+              memory: 128Mi
+            limits:
+              cpu: 500m
+              memory: 512Mi
+          securityContext:
+            allowPrivilegeEscalation: false
+            capabilities:
+              drop: ["ALL"]

services/maintenance/metis-ingress.yaml

@@ -0,0 +1,27 @@
+# services/maintenance/metis-ingress.yaml
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: metis
+  namespace: maintenance
+  annotations:
+    kubernetes.io/ingress.class: traefik
+    cert-manager.io/cluster-issuer: letsencrypt
+    traefik.ingress.kubernetes.io/router.entrypoints: websecure
+    traefik.ingress.kubernetes.io/router.tls: "true"
+    traefik.ingress.kubernetes.io/router.middlewares: sso-oauth2-proxy-forward-auth@kubernetescrd
+spec:
+  tls:
+    - hosts: ["metis.bstein.dev"]
+      secretName: metis-tls
+  rules:
+    - host: metis.bstein.dev
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: metis
+                port:
+                  number: 80

services/maintenance/metis-k3s-token-sync-cronjob.yaml

@@ -0,0 +1,51 @@
+# services/maintenance/metis-k3s-token-sync-cronjob.yaml
+apiVersion: batch/v1
+kind: CronJob
+metadata:
+  name: metis-k3s-token-sync
+  namespace: maintenance
+spec:
+  schedule: "11 */6 * * *"
+  concurrencyPolicy: Forbid
+  successfulJobsHistoryLimit: 1
+  failedJobsHistoryLimit: 2
+  jobTemplate:
+    spec:
+      template:
+        spec:
+          serviceAccountName: metis-token-sync
+          restartPolicy: OnFailure
+          nodeSelector:
+            kubernetes.io/arch: arm64
+            node-role.kubernetes.io/control-plane: "true"
+          tolerations:
+            - key: node-role.kubernetes.io/control-plane
+              operator: Exists
+              effect: NoSchedule
+            - key: node-role.kubernetes.io/master
+              operator: Exists
+              effect: NoSchedule
+          containers:
+            - name: sync
+              image: registry.bstein.dev/bstein/kubectl:1.35.0
+              imagePullPolicy: IfNotPresent
+              command:
+                - /bin/sh
+                - -c
+              args:
+                - |
+                  set -euo pipefail
+                  token="$(tr -d '\n' < /host/var/lib/rancher/k3s/server/node-token)"
+                  kubectl -n maintenance create secret generic metis-runtime \
+                    --from-literal=k3s_token="${token}" \
+                    --dry-run=client -o yaml | kubectl apply -f -
+              securityContext:
+                runAsUser: 0
+              volumeMounts:
+                - name: k3s-server
+                  mountPath: /host/var/lib/rancher/k3s/server
+                  readOnly: true
+          volumes:
+            - name: k3s-server
+              hostPath:
+                path: /var/lib/rancher/k3s/server

services/maintenance/metis-rbac.yaml

@@ -0,0 +1,27 @@
+# services/maintenance/metis-rbac.yaml
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: metis-node-manager
+rules:
+  - apiGroups: [""]
+    resources:
+      - nodes
+    verbs:
+      - get
+      - list
+      - watch
+      - delete
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: metis-node-manager
+subjects:
+  - kind: ServiceAccount
+    name: metis
+    namespace: maintenance
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: metis-node-manager

services/maintenance/metis-sentinel-daemonset.yaml

@@ -0,0 +1,133 @@
+# services/maintenance/metis-sentinel-daemonset.yaml
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: metis-sentinel
+  namespace: maintenance
+spec:
+  selector:
+    matchLabels:
+      app: metis-sentinel
+  updateStrategy:
+    type: RollingUpdate
+  template:
+    metadata:
+      labels:
+        app: metis-sentinel
+      annotations:
+        prometheus.io/scrape: "true"
+        prometheus.io/port: "8080"
+        prometheus.io/path: "/metrics"
+    spec:
+      serviceAccountName: metis
+      nodeSelector:
+        kubernetes.io/os: linux
+        node-role.kubernetes.io/worker: "true"
+      containers:
+        - name: metis-sentinel
+          image: registry.bstein.dev/bstein/metis-sentinel:latest
+          imagePullPolicy: Always
+          command:
+            - /bin/sh
+            - -c
+          args:
+            - |
+              set -eu
+              out_dir="${METIS_SENTINEL_OUT:-/var/run/metis-sentinel}"
+              interval="${METIS_SENTINEL_INTERVAL_SEC:-120}"
+              mkdir -p "${out_dir}"
+              while true; do
+                ts="$(date -u +%Y%m%dT%H%M%SZ)"
+                node="${METIS_SENTINEL_NODE:-unknown}"
+                tmp="${out_dir}/${node}-${ts}.json.tmp"
+                out="${out_dir}/${node}-${ts}.json"
+                if metis-sentinel > "${tmp}"; then
+                  mv "${tmp}" "${out}"
+                else
+                  rm -f "${tmp}" || true
+                fi
+                sleep "${interval}"
+              done
+          envFrom:
+            - configMapRef:
+                name: metis
+          env:
+            - name: METIS_SENTINEL_NODE
+              valueFrom:
+                fieldRef:
+                  fieldPath: spec.nodeName
+          ports:
+            - name: http
+              containerPort: 8080
+          volumeMounts:
+            - name: sentinel-output
+              mountPath: /var/run/metis-sentinel
+          resources:
+            requests:
+              cpu: 25m
+              memory: 64Mi
+            limits:
+              cpu: 250m
+              memory: 256Mi
+          securityContext:
+            allowPrivilegeEscalation: false
+            runAsUser: 0
+            capabilities:
+              drop: ["ALL"]
+        - name: sentinel-pusher
+          image: curlimages/curl:8.12.1
+          imagePullPolicy: IfNotPresent
+          command:
+            - /bin/sh
+            - -c
+          args:
+            - |
+              set -eu
+              out_dir="${METIS_SENTINEL_OUT:-/var/run/metis-sentinel}"
+              push_url="${METIS_SENTINEL_PUSH_URL:-}"
+              interval="${METIS_SENTINEL_PUSH_INTERVAL_SEC:-120}"
+              timeout="${METIS_SENTINEL_PUSH_TIMEOUT_SEC:-10}"
+              mkdir -p "${out_dir}"
+              while true; do
+                for snapshot in "${out_dir}"/*.json; do
+                  [ -f "${snapshot}" ] || continue
+                  if [ -z "${push_url}" ]; then
+                    break
+                  fi
+                  if curl -fsS --connect-timeout "${timeout}" --max-time "${timeout}" \
+                    -X POST \
+                    -H "Content-Type: application/json" \
+                    -H "X-Metis-Node: ${METIS_SENTINEL_NODE:-unknown}" \
+                    --data-binary "@${snapshot}" \
+                    "${push_url}"; then
+                    rm -f "${snapshot}"
+                  fi
+                done
+                sleep "${interval}"
+              done
+          envFrom:
+            - configMapRef:
+                name: metis
+          env:
+            - name: METIS_SENTINEL_NODE
+              valueFrom:
+                fieldRef:
+                  fieldPath: spec.nodeName
+          volumeMounts:
+            - name: sentinel-output
+              mountPath: /var/run/metis-sentinel
+          resources:
+            requests:
+              cpu: 10m
+              memory: 32Mi
+            limits:
+              cpu: 100m
+              memory: 128Mi
+          securityContext:
+            allowPrivilegeEscalation: false
+            runAsUser: 0
+            capabilities:
+              drop: ["ALL"]
+      volumes:
+        - name: sentinel-output
+          emptyDir: {}

services/maintenance/metis-service.yaml

@@ -0,0 +1,18 @@
+# services/maintenance/metis-service.yaml
+apiVersion: v1
+kind: Service
+metadata:
+  name: metis
+  namespace: maintenance
+  annotations:
+    prometheus.io/scrape: "true"
+    prometheus.io/port: "80"
+    prometheus.io/path: "/metrics"
+spec:
+  type: ClusterIP
+  selector:
+    app: metis
+  ports:
+    - name: http
+      port: 80
+      targetPort: http

services/maintenance/metis-serviceaccount.yaml

@@ -0,0 +1,6 @@
+# services/maintenance/metis-serviceaccount.yaml
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: metis
+  namespace: maintenance

services/maintenance/metis-token-sync-rbac.yaml

@@ -0,0 +1,30 @@
+# services/maintenance/metis-token-sync-rbac.yaml
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  name: metis-token-sync
+  namespace: maintenance
+rules:
+  - apiGroups: [""]
+    resources:
+      - secrets
+    verbs:
+      - get
+      - list
+      - create
+      - update
+      - patch
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  name: metis-token-sync
+  namespace: maintenance
+subjects:
+  - kind: ServiceAccount
+    name: metis-token-sync
+    namespace: maintenance
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: metis-token-sync

services/maintenance/metis-token-sync-serviceaccount.yaml

@@ -0,0 +1,6 @@
+# services/maintenance/metis-token-sync-serviceaccount.yaml
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: metis-token-sync
+  namespace: maintenance

services/monitoring/dashboards/atlas-jobs.json

@@ -1125,7 +1125,7 @@
     {
       "id": 17,
       "type": "stat",
-      "title": "Ariadne + Metis CI Coverage (%)",
+      "title": "Platform CI Coverage (%)",
       "datasource": {
         "type": "prometheus",
         "uid": "atlas-vm"
@@ -1183,12 +1183,13 @@
           "values": false
         },
         "textMode": "value"
-      }
+      },
+      "description": "Internal source panel for Atlas Overview automation test rollups."
     },
     {
       "id": 18,
       "type": "table",
-      "title": "Ariadne + Metis CI Tests (latest)",
+      "title": "Platform CI Tests (latest)",
       "datasource": {
         "type": "prometheus",
         "uid": "atlas-vm"
@@ -1233,7 +1234,8 @@
             "order": "desc"
           }
         }
-      ]
+      ],
+      "description": "Atlas Overview test panels depend on these internal repo-tagged CI series."
     }
   ],
   "time": {

services/monitoring/dashboards/atlas-overview.json

@@ -1677,7 +1677,7 @@
     {
       "id": 42,
       "type": "timeseries",
-      "title": "Ariadne + Metis Test Success Rate",
+      "title": "Platform Test Success Rate",
       "datasource": {
         "type": "prometheus",
         "uid": "atlas-vm"
@@ -1709,12 +1709,13 @@
         "tooltip": {
           "mode": "multi"
         }
-      }
+      },
+      "description": "Atlas Overview mirrors the Atlas Jobs internal dashboard for automation test health. Add new test series there first so they roll up here."
     },
     {
       "id": 43,
       "type": "bargauge",
-      "title": "Ariadne + Metis Tests with Failures (24h)",
+      "title": "Platform Tests with Failures (24h)",
       "datasource": {
         "type": "prometheus",
         "uid": "atlas-vm"
@@ -1814,7 +1815,8 @@
             "order": "desc"
           }
         }
-      ]
+      ],
+      "description": "This summary is sourced from the Atlas Jobs internal dashboard rather than a separate overview-only query."
     },
     {
       "id": 11,

services/monitoring/grafana-dashboard-jobs.yaml

@@ -1134,7 +1134,7 @@ data:
         {
           "id": 17,
           "type": "stat",
-          "title": "Ariadne + Metis CI Coverage (%)",
+          "title": "Platform CI Coverage (%)",
           "datasource": {
             "type": "prometheus",
             "uid": "atlas-vm"
@@ -1192,12 +1192,13 @@ data:
               "values": false
             },
             "textMode": "value"
-          }
+          },
+          "description": "Internal source panel for Atlas Overview automation test rollups."
         },
         {
           "id": 18,
           "type": "table",
-          "title": "Ariadne + Metis CI Tests (latest)",
+          "title": "Platform CI Tests (latest)",
           "datasource": {
             "type": "prometheus",
             "uid": "atlas-vm"
@@ -1242,7 +1243,8 @@ data:
                 "order": "desc"
               }
             }
-          ]
+          ],
+          "description": "Atlas Overview test panels depend on these internal repo-tagged CI series."
         }
       ],
       "time": {

services/monitoring/grafana-dashboard-overview.yaml

@@ -1686,7 +1686,7 @@ data:
         {
           "id": 42,
           "type": "timeseries",
-          "title": "Ariadne + Metis Test Success Rate",
+          "title": "Platform Test Success Rate",
           "datasource": {
             "type": "prometheus",
             "uid": "atlas-vm"
@@ -1718,12 +1718,13 @@ data:
             "tooltip": {
               "mode": "multi"
             }
-          }
+          },
+          "description": "Atlas Overview mirrors the Atlas Jobs internal dashboard for automation test health. Add new test series there first so they roll up here."
         },
         {
           "id": 43,
           "type": "bargauge",
-          "title": "Ariadne + Metis Tests with Failures (24h)",
+          "title": "Platform Tests with Failures (24h)",
           "datasource": {
             "type": "prometheus",
             "uid": "atlas-vm"
@@ -1823,7 +1824,8 @@ data:
                 "order": "desc"
               }
             }
-          ]
+          ],
+          "description": "This summary is sourced from the Atlas Jobs internal dashboard rather than a separate overview-only query."
         },
         {
           "id": 11,