fix(secrets): populate the empty sops placeholders and drop the unused one

fix(storage): pin minio tenant to a published image release
2026-10-06 10:02:45 +08:00 · 2026-10-06 09:45:45 +08:00
14 changed files with 30 additions and 560 deletions
@@ -48,7 +48,7 @@ spec:
                  mountPath: /backup
          containers:
            - name: mc-mirror
-              image: docker.io/bitnamilegacy/minio-client:2025.7.21-debian-12-r3@sha256:73bd39f7899a0cef12b8dd5df13aa93a3ed1aaa44236542442e9ac76819ac158
+              image: quay.io/minio/mc:latest
              env:
                - name: ACCESS_KEY
                  valueFrom:
@@ -1,20 +0,0 @@
-apiVersion: argoproj.io/v1alpha1
-kind: Application
-metadata:
-  name: oidc-bootstrap
-  namespace: argocd
-  annotations:
-    argocd.argoproj.io/sync-wave: "5"
-spec:
-  project: homelab
-  source:
-    repoURL: https://forgejo.riotpiao.com/riotpiao-poimen/homelab.git
-    targetRevision: main
-    path: k8s/infra/oidc-bootstrap
-  destination:
-    server: https://kubernetes.default.svc
-    namespace: kube-system
-  syncPolicy:
-    automated:
-      prune: true
-      selfHeal: true
@@ -1,27 +0,0 @@
-apiVersion: v1
-kind: Secret
-metadata:
-    name: etcd-defrag-creds
-    namespace: kube-system
-    labels:
-        app.kubernetes.io/name: etcd-defrag
-type: Opaque
-stringData:
-    ca.crt: ENC[AES256_GCM,data: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,iv:KnW9LYNzxZ6r3Q6LTeOrgSLLPgiJlibVp6YmTEKBkjE=,tag:KTL1nOWdNWDA4dLVaA4//g==,type:str]
-    client.crt: ENC[AES256_GCM,data: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,iv:l8BwxxEfHfYrm+mM5UE6Yj42DeeU9y23jjIE1KjIiME=,tag:HwRT6/myIsxc84BYDj3K6w==,type:str]
-    client.key: ENC[AES256_GCM,data:QD/Glf3lFslBEdEoJ3CNrYzlw2HLCvGSeVuJLtxnFne2aJOuw0sk/e0h/kSAxvG4dZ+LIWJLLbqTjKHOAhkvS/ZOA7GSea4ubNkvTkw8+JBRuYwb2D2iB8kZhlER/CpiGkYJukjkgGP1CzHdvBY1M88pW9w6rH74MD3jY47qExIaNduQj5vkUQZ8ajqkd79l0nk98ZTawfPG4AFcEtAIKAPIuubT2GZ3qqNLjOI7agbtRv8xI44hhb2wj5J9xdl1GrbOWwG5EOo+hLNrcAAOCcWBpNTUCKBy7mrk2ID8jX3HsFWN76DDlQzkhcphMhlM7g==,iv:49HGJAEgllEkB3YSiZLmbWs/vlbFbY52kiKesdGVC/Y=,tag:g8YZ9at3V2l6RFRfvO2lAQ==,type:str]
-sops:
-    age:
-        - enc: |
-            -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB4Z0h0R2dhbDdRcFJydE9o
-            R0hWeCtwVzluZWZlR0VtOXcxdW9FbklOQXlzCmo3eXNyNlFjejNETkJiVVRVWFhr
-            a2pORnhIQTI0UUk2N3dWMDZJcEhYU1UKLS0tIEduaHlmMHQza1A0TGVZb0JrbTYz
-            MWJwQjcrdkkzQXhOTmhycERsM0FtNVEKG+gBRcvUsyfRzuW999EQNzyDh2/5fY6p
-            8ab2xvTOJPiMUBTBuQZsA+iDImytUO/02ROQsbEZkALijp1nqrsV/g==
-            -----END AGE ENCRYPTED FILE-----
-          recipient: age1e5fq3hwxy78psus2nfvmtmua36g0u3suk78ephw6246l974d2utsvn0hla
-    encrypted_regex: ^(data|stringData)$
-    lastmodified: "2026-10-07T05:37:26Z"
-    mac: ENC[AES256_GCM,data:vu6ltV0jYQNGV4eqIcqAp9p2TJ8ULBX5JBELUgm/nA9GX+I6Pv3fyjpcHRSWY0HbLvCwgXd22CG4IYcj4HJFtQGZR7OcQA5WM5plZH3RCPdvPNix/798vkETfpJxorQjlHoq4nlr3dEmUCbzdtE07qV2W1M6GJr4C9xKvB947bQ=,iv:aA9mjZCFAoLEhGqkl6NfyBZ3x3vWGfLYYAEe8jXuA4U=,tag:Drdiji33ckDd8ildpvSEXw==,type:str]
-    version: 3.13.2
@@ -1,24 +0,0 @@
-apiVersion: v1
-kind: Secret
-type: Opaque
-metadata:
-    name: pi-code-agent-api-keys
-    namespace: poimen-sandbox
-stringData:
-    ANTHROPIC_API_KEY: ENC[AES256_GCM,data:TBcno/dzj3qykHjeX96UKZekuA/WMQT2E7a1ziPyYo5J6lWLPydgli84KeJZhH62/8CnnFtFOhVIe4FWCGPGjvqKH6M8WbiQHaP9y7FN0qQUpFHKNVAQ2R+s0wInhw0eUmANvd7bRx8aIZ2X,iv:oex19yVtWUevoJ0A3mkMLCfWu85o1gPSNp43x1iV0LE=,tag:BW3zQnwvagPceeNird9CZg==,type:str]
-    DEEPSEEK_API_KEY: ENC[AES256_GCM,data:vq/5gOsMVjlVMd0oXiBtHFHFEr+IF2YR2iP2OBFWx3ZFNoQ=,iv:QhLU/BRIJb/7QKDCRyw+HWPphZifVEhIOLywYDgOb20=,tag:BZdtXw+WsuK+P4E0caTa0Q==,type:str]
-sops:
-    age:
-        - enc: |
-            -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBqNm1LNE5nWktnd3c3STg3
-            UlVWbWJxWElxUHMwa0JVMk81Z0c4d0JaQm1vCnpLQWJWV3hxOU00NzJIaG51Mmlr
-            ZWpNTFJWcmdtV0w4YndQeHpvSUx2MTAKLS0tIDVnNkNuVWhPUFZ5V2hFOEt1eitG
-            blVqRy8yNnYzSU1FNzZGNkxrRElvWVEKL3J77INje75+CvKXaJHC3CvONgHv7d0a
-            a10MITvfreFr6M4AN3Z/mno49SDMp15Q4oQRagHHxSTS1K54mWHo8g==
-            -----END AGE ENCRYPTED FILE-----
-          recipient: age1e5fq3hwxy78psus2nfvmtmua36g0u3suk78ephw6246l974d2utsvn0hla
-    encrypted_regex: ^(data|stringData)$
-    lastmodified: "2026-10-06T01:19:49Z"
-    mac: ENC[AES256_GCM,data:GpYl8IRefms36GvO3RW41c0US7SOgoOhd4rumxsCdEf5ME9kJ0eOxPx8klMgnlYrkBnwHmad8jj7C+HcA5Eim7mdUaYOZZWPFohvC6N4GLHX85aH78P09CelqG5tdm/Gm+1QfxYu0vANYGCAVjLK7YbBbZjbZmbvVfQvAbs3mOY=,iv:y3lglGu8FhTHQpO1poSIKgGYJFu5J9yjIaOjulda6fY=,tag:5Sgh4TbtNFMw7xOJjYRn0g==,type:str]
-    version: 3.13.2
@@ -7,34 +7,32 @@ metadata:
      exec:
        path: ksops
 files:
-    - agent-pod-models.enc.yaml
-    - agent-pod-ssh-key.enc.yaml
-    - authentik-secrets.enc.yaml
-    - cloudflare-secrets.enc.yaml
-    - forgejo-registry-pat.enc.yaml
-    - forgejo-registry-pat-api.enc.yaml
-    - forgejo-registry-pull.enc.yaml
-    - forgejo-runner-token.enc.yaml
-    - forgejo-secrets.enc.yaml
-    - grafana-oidc-secrets.enc.yaml
-    - grafana-secrets.enc.yaml
-    - homarr-auth-oidc.enc.yaml
-    - homarr-db-encryption.enc.yaml
-    - homarr-secrets.enc.yaml
-    - homelab-ca-secrets.enc.yaml
-    - loki-secrets.enc.yaml
-    - minio-secrets.enc.yaml
-    - paperless-secrets.enc.yaml
-    - vault-secrets.enc.yaml
-    - vault-unseal-keys.enc.yaml
-    - portfolio-secrets.enc.yaml
-    - gotify-admin-secrets.enc.yaml
-    - gotify-tokens-secrets.enc.yaml
-    - gotify-smtp-secrets.enc.yaml
-    - forgejo-smtp-secrets.enc.yaml
-    - paperless-ai-secrets.enc.yaml
+  - agent-pod-models.enc.yaml
+  - agent-pod-ssh-key.enc.yaml
+  - authentik-secrets.enc.yaml
+  - cloudflare-secrets.enc.yaml
+  - forgejo-registry-pat.enc.yaml
+  - forgejo-registry-pat-api.enc.yaml
+  - forgejo-registry-pull.enc.yaml
+  - forgejo-runner-token.enc.yaml
+  - forgejo-secrets.enc.yaml
+  - grafana-oidc-secrets.enc.yaml
+  - grafana-secrets.enc.yaml
+  - homarr-auth-oidc.enc.yaml
+  - homarr-db-encryption.enc.yaml
+  - homarr-secrets.enc.yaml
+  - homelab-ca-secrets.enc.yaml
+  - loki-secrets.enc.yaml
+  - minio-secrets.enc.yaml
+  - paperless-secrets.enc.yaml
+  - vault-secrets.enc.yaml
+  - vault-unseal-keys.enc.yaml
+  - portfolio-secrets.enc.yaml
+  - gotify-admin-secrets.enc.yaml
+  - gotify-tokens-secrets.enc.yaml
+  - gotify-smtp-secrets.enc.yaml
+  - forgejo-smtp-secrets.enc.yaml
+  - paperless-ai-secrets.enc.yaml
    - memory-agent-oidc.enc.yaml
    - oauth2-credentials.enc.yaml
    - forgejo-registry-token.enc.yaml
-    - pi-sandbox-secrets.enc.yaml
-    - etcd-defrag-creds.enc.yaml
@@ -1,177 +0,0 @@
-# etcd backend maintenance: compact, defrag, disarm NOSPACE.
-#
-# Why this exists
-# ---------------
-# etcd's backend file only grows. The apiserver compacts every 5m, but
-# compaction marks superseded revisions free *inside* the file; only `defrag`
-# returns that space to the filesystem. Nothing ran defrag, so the file grew
-# until it crossed the 2 GiB quota:
-#
-#   2026-10-07  backend 2,148,843,520 B (2.1 GB) on talos-cp-1 and talos-cp-3
-#               -> etcd raised NOSPACE on those two members
-#               -> etcd rejected ALL writes cluster-wide
-#               -> kubelets could not post node status: 3 nodes NotReady
-#               -> apiserver writes returned 500, the tunnel API path 502
-#
-# The live data was tiny: 15,943 keys, 69 MB after compaction. The rest was
-# dead pages. Recovery was `compact <current-revision>` then `defrag` per
-# member then `alarm disarm`. Compaction had also stalled while the alarm was
-# up, so `dbSizeInUse` read 100% of the file - defrag alone would NOT have
-# worked. Order matters: compact first, then defrag.
-#
-# The earlier revision of this file never ran, for two independent reasons:
-#   1. it existed only on branch fix/etcd-defrag-cron; the ArgoCD application
-#      `cluster-maintenance` tracks `main` (targetRevision: main), so the
-#      cluster never had the CronJob or the Secret.
-#   2. the image was quay.io/coreos/etcd, which has NO /bin/sh (verified:
-#      `exec: "/bin/sh": no such file or directory`). Any container that runs
-#      a shell script needs an image that ships one.
-# This revision fixes both: image bitnamilegacy/etcd (ships bash + etcdctl
-# 3.6.4, matching the 3.6.11 servers) pinned by digest.
-#
-# Cadence: every 15 days. Measured growth is ~29 MB/day, so a 15-day cycle
-# peaks near 500 MB - comfortably under the 2 GiB quota. The schedule is daily
-# and the script exits unless the UTC epoch day is a multiple of 15. That gives
-# an exact 15-day interval; `*/15` in the day-of-month field does not (it fires
-# on the 1st, 16th and 31st, which puts two runs one day apart).
-#
-# Safety
-# ------
-# 1. Compaction uses the MINIMUM revision across members. Compacting to a
-#    revision a member has not reached wedges that member - measured on
-#    2026-10-07, when talos-cp-2 froze ~1.2M entries behind the leader and
-#    needed a reboot to rejoin.
-# 2. A member whose raft applied index lags the leader by more than 100000 is
-#    skipped and reported. Defragging a frozen member reclaims nothing.
-# 3. Members are defragged one at a time. A defrag pauses the member's apply
-#    loop for the duration of the file copy.
-#
-# Credentials: Secret etcd-defrag-creds in kube-system, SOPS-managed in
-# k8s/argocd/secrets/etcd-defrag-creds.enc.yaml (ksops generator 00-secrets).
-# Its client certificate is signed by the cluster's etcd CA and expires
-# 2036-10; rotate it before then by re-running the mint and re-encrypting.
-#
-# Companion alerts (monitoring): etcd_mvcc_db_total_size_in_bytes /
-# etcd_server_quota_backend_bytes > 0.8, and an etcd NOSPACE alarm alert.
-apiVersion: batch/v1
-kind: CronJob
-metadata:
-  name: etcd-defrag
-  namespace: kube-system
-  labels:
-    app.kubernetes.io/name: etcd-defrag
-    app.kubernetes.io/part-of: cluster-maintenance
-spec:
-  schedule: "0 3 * * *"            # daily; the script acts only every 15th day
-  concurrencyPolicy: Forbid
-  startingDeadlineSeconds: 600
-  successfulJobsHistoryLimit: 3
-  failedJobsHistoryLimit: 3
-  jobTemplate:
-    spec:
-      backoffLimit: 2
-      template:
-        spec:
-          restartPolicy: OnFailure
-          tolerations:
-            - key: node-role.kubernetes.io/control-plane
-              operator: Exists
-              effect: NoSchedule
-          containers:
-            - name: defrag
-              image: bitnamilegacy/etcd:3.6.4@sha256:c86c06f1ce6a08b6df21eb7a9655b1818778b64c85b5cbb8413ebf7534789730
-              env:
-                - name: ETCDCTL_API
-                  value: "3"
-                - name: ETCDCTL_CACERT
-                  value: /etc/etcd/ca.crt
-                - name: ETCDCTL_CERT
-                  value: /etc/etcd/client.crt
-                - name: ETCDCTL_KEY
-                  value: /etc/etcd/client.key
-                - name: EPS
-                  value: "https://192.168.1.166:2379 https://192.168.1.214:2379 https://192.168.1.162:2379"
-              command: ["/bin/bash", "-c"]
-              args:
-                - |
-                  set -u
-
-                  DAY=$(( $(date -u +%s) / 86400 ))
-                  if [ $(( DAY % 15 )) -ne 0 ]; then
-                    echo "skip: UTC epoch day $DAY is not a 15-day boundary"
-                    exit 0
-                  fi
-
-                  echo "== before =="
-                  for ep in $EPS; do
-                    etcdctl --endpoints="$ep" endpoint status -w table || true
-                  done
-
-                  MINREV=""
-                  MAXAPPLIED=0
-                  for ep in $EPS; do
-                    json=$(etcdctl --endpoints="$ep" endpoint status -w json 2>/dev/null) || continue
-                    rev=$(printf '%s' "$json" | sed -n 's/.*"revision":\([0-9]*\).*/\1/p' | head -1)
-                    app=$(printf '%s' "$json" | sed -n 's/.*"raftAppliedIndex":\([0-9]*\).*/\1/p' | head -1)
-                    echo "member $ep revision=${rev:-?} raftAppliedIndex=${app:-?}"
-                    if [ -n "$rev" ] && { [ -z "$MINREV" ] || [ "$rev" -lt "$MINREV" ]; }; then
-                      MINREV="$rev"
-                    fi
-                    if [ -n "$app" ] && [ "$app" -gt "$MAXAPPLIED" ]; then
-                      MAXAPPLIED="$app"
-                    fi
-                  done
-
-                  if [ -z "$MINREV" ]; then
-                    echo "FATAL: no member returned a revision; nothing attempted"
-                    exit 1
-                  fi
-
-                  echo "== compact to revision $MINREV =="
-                  etcdctl --endpoints="$(echo "$EPS" | awk '{print $1}')" compact "$MINREV" || echo "COMPACT-FAILED (continuing: defrag still reclaims free pages)"
-
-                  # Physical deletion of superseded keys runs in the background
-                  # after the compaction commit; give it a moment to drain.
-                  sleep 20
-
-                  echo "== defrag each member (sequential, one at a time) =="
-                  rc=0
-                  for ep in $EPS; do
-                    json=$(etcdctl --endpoints="$ep" endpoint status -w json 2>/dev/null) || { echo "SKIP $ep (unreachable)"; rc=1; continue; }
-                    app=$(printf '%s' "$json" | sed -n 's/.*"raftAppliedIndex":\([0-9]*\).*/\1/p' | head -1)
-                    if [ -n "$app" ] && [ "$app" -lt $(( MAXAPPLIED - 100000 )) ]; then
-                      echo "SKIP $ep (applied index $app lags leader $MAXAPPLIED; defrag would reclaim nothing)"
-                      rc=1
-                      continue
-                    fi
-                    echo "-- $ep"
-                    if ! etcdctl --endpoints="$ep" defrag; then
-                      echo "DEFRAG-FAILED $ep"
-                      rc=1
-                    fi
-                  done
-
-                  echo "== disarm NOSPACE =="
-                  for ep in $EPS; do
-                    etcdctl --endpoints="$ep" alarm list 2>/dev/null || true
-                    etcdctl --endpoints="$ep" alarm disarm 2>/dev/null || true
-                  done
-
-                  echo "== after =="
-                  for ep in $EPS; do
-                    etcdctl --endpoints="$ep" endpoint status -w table || true
-                  done
-                  etcdctl --endpoints="$(echo "$EPS" | awk '{print $1}')" alarm list || true
-                  exit $rc
-              resources:
-                requests: { cpu: 10m, memory: 32Mi }
-                limits:   { cpu: 200m, memory: 128Mi }
-              volumeMounts:
-                - name: creds
-                  mountPath: /etc/etcd
-                  readOnly: true
-          volumes:
-            - name: creds
-              secret:
-                secretName: etcd-defrag-creds
-                defaultMode: 0444
@@ -52,14 +52,14 @@ spec:
      restartPolicy: Never
      initContainers:
        - name: kubectl-copy
-          image: bitnami/kubectl:latest@sha256:f7f9e4f64d9e114650c115a4ac6fd383394b3d494061a8f17b1a0f6c8d55bc25
+          image: bitnami/kubectl:latest
          command: ["sh", "-c", "cp $(which kubectl) /shared/kubectl"]
          volumeMounts:
            - name: shared
              mountPath: /shared
      containers:
        - name: provision
-          image: docker.io/bitnamilegacy/minio-client:2025.7.21-debian-12-r3@sha256:73bd39f7899a0cef12b8dd5df13aa93a3ed1aaa44236542442e9ac76819ac158
+          image: quay.io/minio/mc:latest
          volumeMounts:
            - name: shared
              mountPath: /shared
@@ -16,10 +16,7 @@ spec:
  # backend could not resolve minio-cluster-hl. Official images now need registry auth
  # (quay.io/minio/minio returns 401), so this pins a public mirror of the same upstream
  # release; swap it for the official image once MinIO registry credentials exist.
-  # The digest freezes those bytes, so a retag or a deletion on the mirror cannot break
-  # the pull again. The same digest already sits in the containerd cache on talos-cp-1,
-  # so the first start needs no registry access.
-  image: docker.io/coollabsio/minio:RELEASE.2025-10-15T17-29-55Z@sha256:69b55a1c1c5dc285ce04db96689f5b2102317fc77a50680a1874ca6efd1c87f9
+  image: coollabsio/minio:RELEASE.2025-10-15T17-29-55Z

  # Disable operator auto-TLS: MinIO serves plain HTTP internally on 9000.
  # External TLS is terminated at nginx ingress (wildcard riotpiao-com-tls cert).
@@ -27,24 +27,6 @@ spec:
          annotations:
            summary: "{{ $value }} pod(s) stuck in Pending state for >10m"

-        # ImagePullBackOff on a vendor-deleted image produced no alert for 13 days
-        - alert: PodImagePullFailure
-          expr: sum(kube_pod_container_status_waiting_reason{reason=~"ImagePullBackOff|ErrImagePull"}) by (namespace, pod) > 0
-          for: 10m
-          labels:
-            severity: critical
-          annotations:
-            summary: "{{ $labels.namespace }}/{{ $labels.pod }} cannot pull its image"
-
-        # Pod not ready
-        - alert: PodNotReady
-          expr: sum(kube_pod_status_ready{condition="false"}) by (namespace, pod) > 0
-          for: 15m
-          labels:
-            severity: warning
-          annotations:
-            summary: "{{ $labels.namespace }}/{{ $labels.pod }} is not ready"
-
        # CrashLoopBackOff
        - alert: PodCrashLooping
          expr: sum(kube_pod_container_status_waiting_reason{reason="CrashLoopBackOff"}) by (namespace, pod) > 0
@@ -1,59 +0,0 @@
-# One-shot bootstrap: restart the control-plane apiservers ONCE so they pick up the
-# OIDC authenticator (they last started before the Authentik provider existed, so OIDC
-# tokens were never accepted -> every login got 401). Delete this whole directory after.
---
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: oidc-bootstrap
-  namespace: kube-system
---
-apiVersion: rbac.authorization.k8s.io/v1
-kind: Role
-metadata:
-  name: oidc-bootstrap
-  namespace: kube-system
-rules:
-  - apiGroups: [""]
-    resources: ["pods"]
-    verbs: ["get", "list", "delete"]
---
-apiVersion: rbac.authorization.k8s.io/v1
-kind: RoleBinding
-metadata:
-  name: oidc-bootstrap
-  namespace: kube-system
-subjects:
-  - kind: ServiceAccount
-    name: oidc-bootstrap
-    namespace: kube-system
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: Role
-  name: oidc-bootstrap
---
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: oidc-bootstrap-restart-apiserver-v2
-  namespace: kube-system
-spec:
-  backoffLimit: 4
-  ttlSecondsAfterFinished: 7200
-  template:
-    spec:
-      serviceAccountName: oidc-bootstrap
-      restartPolicy: Never
-      containers:
-        - name: restart
-          image: docker.io/curlimages/curl:8.22.0
-          command: ["/bin/sh", "-c"]
-          args:
-            - |
-              set -u
-              TOKEN=$(cat /var/run/secrets/kubernetes.io/serviceaccount/token)
-              CA=/var/run/secrets/kubernetes.io/serviceaccount/ca.crt
-              for pod in kube-apiserver-talos-cp-1 kube-apiserver-talos-cp-2 kube-apiserver-talos-cp-3; do
-                curl -sS --max-time 15 --cacert "$CA" -H "Authorization: Bearer $TOKEN"                   -X DELETE "https://kubernetes.default.svc/api/v1/namespaces/kube-system/pods/$pod?gracePeriodSeconds=0"                   -o /dev/null -w "$pod -> HTTP %{http_code}\n" || echo "$pod -> request failed"
-              done
-              echo "deletes requested; kubelet recreates each static pod in ~20-40s"
@@ -1,141 +0,0 @@
-# One-shot: restart the control-plane API servers so their OIDC authenticator initialises.
-#
-# Two earlier mechanisms failed and are documented so nobody repeats them:
-#   1. deleting the mirror pod does NOT restart a static pod (deletes returned 200, no restart);
-#   2. matching /proc/*/cmdline for 'kube-apiserver' also matched this script's own cmdline,
-#      so every pod SIGTERMed itself (exit 143) before reaching the real process.
-# This version matches /proc/<pid>/comm (the process name) and skips \$\$, so self-kill is
-# impossible. hostPID + privileged are permitted in the 'cicd' namespace. Delays stagger the
-# three control planes by 2 minutes each, so only one API server is down at a time.
---
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: oidc-restart-apiserver-cp1-v2
-  namespace: cicd
-spec:
-  backoffLimit: 0
-  ttlSecondsAfterFinished: 3600
-  template:
-    spec:
-      hostPID: true
-      restartPolicy: Never
-      nodeSelector:
-        kubernetes.io/hostname: talos-cp-1
-      tolerations:
-        - key: node-role.kubernetes.io/control-plane
-          operator: Exists
-          effect: NoSchedule
-        - key: node-role.kubernetes.io/master
-          operator: Exists
-          effect: NoSchedule
-      containers:
-        - name: kill
-          image: docker.io/library/busybox:1.36
-          securityContext:
-            privileged: true
-          command: ["/bin/sh", "-c"]
-          args:
-            - |
-              echo "sleeping 10s before restarting the API server on talos-cp-1"
-              sleep 10
-              self=$$
-              killed=0
-              for d in /proc/[0-9]*; do
-                pid=${d#/proc/}
-                [ "$pid" = "$self" ] && continue
-                comm=$(cat "$d/comm" 2>/dev/null)
-                [ "$comm" = "kube-apiserver" ] || continue
-                echo "SIGTERM -> pid $pid"
-                kill -TERM "$pid" 2>/dev/null && killed=$((killed+1))
-              done
-              echo "signalled $killed API server process(es); kubelet recreates the static pod"
-
---
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: oidc-restart-apiserver-cp2-v2
-  namespace: cicd
-spec:
-  backoffLimit: 0
-  ttlSecondsAfterFinished: 3600
-  template:
-    spec:
-      hostPID: true
-      restartPolicy: Never
-      nodeSelector:
-        kubernetes.io/hostname: talos-cp-2
-      tolerations:
-        - key: node-role.kubernetes.io/control-plane
-          operator: Exists
-          effect: NoSchedule
-        - key: node-role.kubernetes.io/master
-          operator: Exists
-          effect: NoSchedule
-      containers:
-        - name: kill
-          image: docker.io/library/busybox:1.36
-          securityContext:
-            privileged: true
-          command: ["/bin/sh", "-c"]
-          args:
-            - |
-              echo "sleeping 120s before restarting the API server on talos-cp-2"
-              sleep 120
-              self=$$
-              killed=0
-              for d in /proc/[0-9]*; do
-                pid=${d#/proc/}
-                [ "$pid" = "$self" ] && continue
-                comm=$(cat "$d/comm" 2>/dev/null)
-                [ "$comm" = "kube-apiserver" ] || continue
-                echo "SIGTERM -> pid $pid"
-                kill -TERM "$pid" 2>/dev/null && killed=$((killed+1))
-              done
-              echo "signalled $killed API server process(es); kubelet recreates the static pod"
-
---
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: oidc-restart-apiserver-cp3-v2
-  namespace: cicd
-spec:
-  backoffLimit: 0
-  ttlSecondsAfterFinished: 3600
-  template:
-    spec:
-      hostPID: true
-      restartPolicy: Never
-      nodeSelector:
-        kubernetes.io/hostname: talos-cp-3
-      tolerations:
-        - key: node-role.kubernetes.io/control-plane
-          operator: Exists
-          effect: NoSchedule
-        - key: node-role.kubernetes.io/master
-          operator: Exists
-          effect: NoSchedule
-      containers:
-        - name: kill
-          image: docker.io/library/busybox:1.36
-          securityContext:
-            privileged: true
-          command: ["/bin/sh", "-c"]
-          args:
-            - |
-              echo "sleeping 240s before restarting the API server on talos-cp-3"
-              sleep 240
-              self=$$
-              killed=0
-              for d in /proc/[0-9]*; do
-                pid=${d#/proc/}
-                [ "$pid" = "$self" ] && continue
-                comm=$(cat "$d/comm" 2>/dev/null)
-                [ "$comm" = "kube-apiserver" ] || continue
-                echo "SIGTERM -> pid $pid"
-                kill -TERM "$pid" 2>/dev/null && killed=$((killed+1))
-              done
-              echo "signalled $killed API server process(es); kubelet recreates the static pod"
-
@@ -9,4 +9,3 @@ resources:
  - poimen-sandbox-namespace.yaml
  - poimen-sandbox-quota.yaml
  - pi-session-netpol.yaml
-  - pi-agent-workspace-pv.yaml
@@ -1,57 +0,0 @@
-apiVersion: v1
-kind: PersistentVolume
-metadata:
-  finalizers:
-  - kubernetes.io/pv-protection
-  labels:
-    app: pi-coding-agent-sandbox
-    part-of: poimen-toolkit
-  name: pi-agent-workspace-pv
-  annotations:
-    argocd.argoproj.io/sync-wave: '-1'
-spec:
-  accessModes:
-  - ReadWriteOnce
-  capacity:
-    storage: 10Gi
-  claimRef:
-    apiVersion: v1
-    kind: PersistentVolumeClaim
-    name: pi-agent-workspace
-    namespace: poimen-sandbox
-  hostPath:
-    path: /var/lib/pi-agent-sandbox
-    type: DirectoryOrCreate
-  nodeAffinity:
-    required:
-      nodeSelectorTerms:
-      - matchExpressions:
-        - key: kubernetes.io/hostname
-          operator: In
-          values:
-          - talos-cp-2
-  persistentVolumeReclaimPolicy: Retain
-  volumeMode: Filesystem
---
-apiVersion: v1
-kind: PersistentVolumeClaim
-metadata:
-  annotations:
-    pv.kubernetes.io/bind-completed: 'yes'
-    argocd.argoproj.io/sync-wave: '-1'
-  finalizers:
-  - kubernetes.io/pvc-protection
-  labels:
-    app: pi-coding-agent-sandbox
-    part-of: poimen-toolkit
-  name: pi-agent-workspace
-  namespace: poimen-sandbox
-spec:
-  accessModes:
-  - ReadWriteOnce
-  resources:
-    requests:
-      storage: 10Gi
-  storageClassName: ''
-  volumeMode: Filesystem
-  volumeName: pi-agent-workspace-pv
@@ -39,7 +39,6 @@
    rewrite name comfy.riotpiao.com ingress-nginx-controller.ingress-nginx.svc.cluster.local
    rewrite name comfyui.riotpiao.com ingress-nginx-controller.ingress-nginx.svc.cluster.local
    rewrite name gotify.riotpiao.com ingress-nginx-controller.ingress-nginx.svc.cluster.local
-    rewrite name pi.riotpiao.com ingress-nginx-controller.ingress-nginx.svc.cluster.local
    rewrite name igotify.riotpiao.com ingress-nginx-controller.ingress-nginx.svc.cluster.local
    rewrite name riotpiao.com ingress-nginx-controller.ingress-nginx.svc.cluster.local
Author	SHA1	Message	Date
rock	f6207ff2b0	fix(secrets): populate the empty sops placeholders and drop the unused one	2026-10-06 10:02:45 +08:00
rock	8bb8851a1f	fix(storage): pin minio tenant to a published image release	2026-10-06 09:45:45 +08:00