style: prettier formatting for edu_master alerts and postgres readme

Deploy workflow uses git-tracked manifests, DISABLED flag and kustomize overlays; add webinar-checker metrics with ServiceMonitor and alerts; upgrade shared postgres to 17 with statuspage DB and probes/resources.

.gitea/workflows/ci.yaml

@@ -347,23 +347,3 @@ jobs:
                 ;;
             esac
           done
-
-  deploy-userbot-panel:
-    needs: build
-    if: github.ref_name == 'main' && contains(needs.build.outputs.services, 'userbot')
-    runs-on: [self-hosted, linux, arch, homelab, prod]
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
-
-      - name: Apply and roll out userbot panel
-        shell: bash
-        run: |
-          kubectl apply -f userbot/k8s/base/panel.yaml
-          kubectl get secret userbot-common-secrets -n default -o json \
-            | jq 'del(.metadata.annotations,.metadata.creationTimestamp,.metadata.resourceVersion,.metadata.uid,.metadata.managedFields) | .metadata.namespace = "userbot"' \
-            | kubectl apply -f -
-          # Keep legacy deployments (forust/anna) in sync with manifests; they have no replicas field, so apply leaves scaling to the user manager only.
-          kubectl apply -f userbot/k8s/base/userbots.yaml
-          kubectl rollout restart deployment/userbot-panel -n userbot
-          kubectl rollout status deployment/userbot-panel -n userbot --timeout=180s

.gitea/workflows/deploy.yaml

@@ -1,6 +1,9 @@
 name: deploy
 
 on:
+  push:
+    branches:
+      - main
   workflow_dispatch:
 
 concurrency:
@@ -19,9 +22,6 @@ jobs:
           DEPLOY_USER: ${{ secrets.DEPLOY_USER }}
           DEPLOY_PATH: ${{ secrets.DEPLOY_PATH }}
           DEPLOY_KEY: ${{ secrets.DEPLOY_SSH_KEY }}
-          # Set APPLY_PRUNE=true to enable kubectl apply --prune. Requires every
-          # manifest to carry label app.kubernetes.io/managed-by=homelab-deploy,
-          # otherwise previously applied resources get deleted on the next run.
           APPLY_PRUNE: ${{ vars.APPLY_PRUNE }}
         run: |
           set -euo pipefail
@@ -57,59 +57,170 @@ jobs:
           fi
 
           git -C "$repo" fetch origin main
-          git -C "$repo" reset --hard origin/main
 
-          # Runtime selection: a service is k8s-managed when $SERVICE/k8s/active
-          # exists. Otherwise it is compose-managed, and only k8s/routing/*
-          # manifests (external Services / EndpointSlices / ServersTransport /
-          # Ingresses that route to docker backends) are applied.
-          #   migrate:   touch SERVICE/k8s/active   (+ move routing files up)
-          #   rollback:  rm SERVICE/k8s/active
+          echo "== Workstation state =="
+          echo "  local:  $(git -C "$repo" rev-parse --short HEAD)"
+          echo "  remote: $(git -C "$repo" rev-parse --short origin/main)"
+
+          if [ -n "$(git -C "$repo" status --porcelain --untracked-files=no)" ]; then
+            echo "ERROR: workstation has local tracked modifications, refusing reset:"
+            git -C "$repo" status --porcelain --untracked-files=no
+            git -C "$repo" diff --stat
+            exit 1
+          fi
+
+          git -C "$repo" reset --hard origin/main
+          cd "$repo"
+
+          is_disabled() {
+            local target="$1"
+            if [ -f "$target" ]; then
+              target="$(dirname "$target")"
+            fi
+            while true; do
+              if [ -f "$target/DISABLED" ]; then
+                return 0
+              fi
+              if [ "$target" = "$repo" ]; then
+                break
+              fi
+              target="$(dirname "$target")"
+              case "$target" in
+                "$repo"/*) ;;
+                *) break ;;
+              esac
+            done
+            return 1
+          }
+
           collect_k8s() {
-            find "$1" -type f \( -name '*.yaml' -o -name '*.yml' \) \
-              ! -path '*/routing/*' ! -path '*/overlays/*' \
-              ! -name 'kustomization.y*ml' ! -name '*.example.y*ml' \
-              ! -name '*values.y*ml' ! -name 'patch-*.y*ml' \
+            git ls-files -- "$1" \
+              | grep -E '\.ya?ml$' \
+              | grep -Ev '/routing/|/overlays/' \
+              | grep -Ev '(^|/)(kustomization\.ya?ml|.*\.example\.ya?ml|.*values\.ya?ml|patch-.*\.ya?ml)$' \
+              | grep -Ev '(^|/)[^/]*secret[^/]*\.ya?ml$' \
               | sort
           }
 
           collect_k8s_inactive() {
-            find "$1" -type f \( -name '*.yaml' -o -name '*.yml' \) \
-              \( -name 'namespace.y*ml' -o -path '*/routing/*' \) \
-              ! -path '*/overlays/*' ! -name '*.example.y*ml' \
-              | sort
+            collect_k8s "$1" \
+              | grep -E '(^|/)namespace\.ya?ml$|/routing/'
           }
 
-          mapfile -t compose_stacks < <(
-            find "$repo" -type f \( -name 'compose.yaml' -o -name 'compose.yml' \) | sort
+          kustomize_overlay() {
+            if [ -f "$1/overlays/prod/kustomization.yaml" ]; then
+              echo "$1/overlays/prod"
+            elif [ -f "$1/base/kustomization.yaml" ]; then
+              echo "$1/base"
+            fi
+          }
+
+          mapfile -t k8s_dirs < <(
+            git ls-files '*.yaml' '*.yml' \
+              | grep -E '(^|/)k8s/' \
+              | sed -E 's#((^|.*/)k8s)/.*#\1#' \
+              | sort -u
           )
 
-          mapfile -t k8s_manifests < <(
-            for kd in $(find "$repo" -type d -name k8s ! -path '*/.git/*' | sort); do
-              if [ -f "$kd/active" ]; then
-                collect_k8s "$kd"
+          k8s_manifests=()
+          kustomize_apps=()
+          for kd_rel in "${k8s_dirs[@]}"; do
+            kd="$repo/$kd_rel"
+            if is_disabled "$kd"; then
+              echo "skip (DISABLED): $kd_rel"
+              continue
+            fi
+            if [ -f "$kd/active" ]; then
+              overlay="$(kustomize_overlay "$kd" || true)"
+              if [ -n "${overlay:-}" ]; then
+                echo "kustomize app: ${overlay#$repo/}"
+                kustomize_apps+=("$overlay")
               else
-                collect_k8s_inactive "$kd"
+                while IFS= read -r f; do
+                  [ -n "$f" ] && k8s_manifests+=("$repo/$f")
+                done < <(collect_k8s "$kd_rel" || true)
               fi
-            done
+            else
+              while IFS= read -r f; do
+                [ -n "$f" ] && k8s_manifests+=("$repo/$f")
+              done < <(collect_k8s_inactive "$kd_rel" || true)
+            fi
+          done
+
+          mapfile -t compose_rel < <(
+            git ls-files '*/compose.yaml' '*/compose.yml' compose.yaml compose.yml | sort
           )
 
+          compose_stacks=()
+          for cf_rel in "${compose_rel[@]}"; do
+            cf="$repo/$cf_rel"
+            if is_disabled "$cf"; then
+              echo "skip (DISABLED): $cf_rel"
+              continue
+            fi
+            if [ -f "$(dirname "$cf")/k8s/active" ]; then
+              echo "skip (k8s-managed): $cf_rel"
+              continue
+            fi
+            compose_stacks+=("$cf")
+          done
+
           echo "== Validate compose stacks =="
           for cf in "${compose_stacks[@]}"; do
-            dir=$(dirname "$cf")
-            if [ -f "$dir/k8s/active" ]; then
-              echo "  skip (k8s-managed): $dir"
-              continue
-            fi
             echo "  config: $cf"
             docker compose -f "$cf" config --quiet
           done
 
-          echo "== Validate k8s manifests (kubectl dry-run) =="
+          echo "== Validate k8s manifests (kubectl dry-run=client) =="
           for m in "${k8s_manifests[@]}"; do
             echo "  apply --dry-run=client $m"
             kubectl apply --dry-run=client -f "$m" >/dev/null
           done
+          for k in "${kustomize_apps[@]}"; do
+            echo "  apply -k --dry-run=client $k"
+            kubectl apply -k "$k" --dry-run=client >/dev/null
+          done
+
+          echo "== Validate k8s manifests (kubectl dry-run=server) =="
+          for m in "${k8s_manifests[@]}"; do
+            echo "  apply --dry-run=server $m"
+            kubectl apply --dry-run=server -f "$m" >/dev/null
+          done
+          for k in "${kustomize_apps[@]}"; do
+            echo "  apply -k --dry-run=server $k"
+            kubectl apply -k "$k" --dry-run=server >/dev/null
+          done
+
+          echo "== Checking referenced Secrets exist =="
+          echo "  (deploy never applies *secret*.yaml; create missing ones from the laptop)"
+          ref_secrets=()
+          if [ "${#k8s_manifests[@]}" -gt 0 ]; then
+            while IFS= read -r s; do
+              [ -n "$s" ] && ref_secrets+=("$s")
+            done < <(
+              {
+                grep -h -A1 -E 'secretRef:|secretKeyRef:' "${k8s_manifests[@]}" 2>/dev/null || true
+                grep -h -E 'secretName:' "${k8s_manifests[@]}" 2>/dev/null || true
+              } | grep -E 'name:' | sed -E 's/.*name:[[:space:]]*//' | tr -d '"'"'"' "'"'" | sed -E 's/[[:space:]]*#.*//' | awk 'NF' | sort -u || true
+            )
+          fi
+          missing_secrets=()
+          all_secrets="$(kubectl get secrets -A --no-headers -o custom-columns=:metadata.name 2>/dev/null || true)"
+          for s in "${ref_secrets[@]}"; do
+            if printf '%s\n' "$all_secrets" | grep -qx "$s"; then
+              echo "  ok: $s"
+            else
+              echo "  MISSING: $s"
+              missing_secrets+=("$s")
+            fi
+          done
+          if [ "${#missing_secrets[@]}" -gt 0 ]; then
+            echo "ERROR: ${#missing_secrets[@]} referenced Secret(s) not found in the cluster:"
+            printf '  - %s\n' "${missing_secrets[@]}"
+            echo "Create them manually from the laptop, e.g.:"
+            echo "  kubectl apply -f SERVICE/k8s/secrets.yaml  # see SERVICE/k8s/secrets.yaml.example"
+            exit 1
+          fi
 
           echo "== Applying Kubernetes manifests =="
           ns_files=()
@@ -130,15 +241,19 @@ jobs:
             echo "  namespaces first: ${ns_files[*]}"
             kubectl apply -f "${ns_files[@]}"
           fi
-          if [ -f "$repo/prometheus-stack/k8s/active" ]; then
+          if [ -f "$repo/prometheus-stack/k8s/active" ] && ! is_disabled "$repo/prometheus-stack/k8s"; then
+            if [ ! -f "$repo/prometheus-stack/k8s/grafana-values.yaml" ]; then
+              echo "ERROR: prometheus-stack/k8s/grafana-values.yaml (gitignored) missing on workstation, restore it first."
+              exit 1
+            fi
             echo "== Upgrading kube-prometheus-stack =="
             helm upgrade --install prometheus-stack prometheus-community/kube-prometheus-stack \
               --namespace prometheus \
               --version 86.2.3 \
               --values "$repo/prometheus-stack/k8s/grafana-values.yaml" \
-              --wait
+              --wait --timeout 10m
           fi
-          if [ -f "$repo/loki/k8s/active" ]; then
+          if [ -f "$repo/loki/k8s/active" ] && ! is_disabled "$repo/loki/k8s"; then
             echo "== Upgrading loki/alloy =="
             helm repo add grafana https://grafana.github.io/helm-charts >/dev/null 2>&1 || true
             helm repo update grafana >/dev/null 2>&1 || true
@@ -146,12 +261,12 @@ jobs:
               --version 7.3.0 \
               --namespace prometheus \
               --values "$repo/loki/k8s/loki-values.yaml" \
-              --wait
+              --wait --timeout 10m
             helm upgrade --install alloy grafana/alloy \
               --version 1.12.1 \
               --namespace prometheus \
               --values "$repo/loki/k8s/alloy-values.yaml" \
-              --wait
+              --wait --timeout 10m
           fi
 
           if [ "${#other_files[@]}" -gt 0 ]; then
@@ -159,14 +274,30 @@ jobs:
             kubectl apply "${prune_opts[@]}" -f "${other_files[@]}"
           fi
 
+          for k in "${kustomize_apps[@]}"; do
+            echo "== Applying kustomize app: ${k#$repo/} =="
+            kubectl apply -k "$k"
+          done
+
+          if [ -f "$repo/userbot/k8s/active" ] && ! is_disabled "$repo/userbot"; then
+            echo "== userbot panel hook =="
+            if kubectl get secret userbot-common-secrets -n userbot >/dev/null 2>&1; then
+              echo "  userbot-common-secrets already present in userbot ns, not touching"
+            elif kubectl get secret userbot-common-secrets -n default >/dev/null 2>&1; then
+              echo "  bootstrapping userbot-common-secrets into userbot ns"
+              kubectl get secret userbot-common-secrets -n default -o json \
+                | jq 'del(.metadata.annotations,.metadata.creationTimestamp,.metadata.resourceVersion,.metadata.uid,.metadata.managedFields) | .metadata.namespace = "userbot"' \
+                | kubectl apply -f -
+            else
+              echo "  WARNING: userbot-common-secrets missing in both default and userbot ns; create it manually from the laptop"
+            fi
+            kubectl rollout restart deployment/userbot-panel -n userbot
+            kubectl rollout status deployment/userbot-panel -n userbot --timeout=180s
+          fi
+
           echo "== Redeploying docker compose stacks =="
           for cf in "${compose_stacks[@]}"; do
-            dir=$(dirname "$cf")
-            if [ -f "$dir/k8s/active" ]; then
-              echo "  skip (k8s-managed): $dir"
-              continue
-            fi
-            echo "  compose: $dir"
+            echo "  compose: $cf"
             if grep -Eq '^\s+pull_policy:\s*build\b' "$cf"; then
               docker compose -f "$cf" build
               docker compose -f "$cf" push

adguardhome/k8s/adguard.yaml

@@ -62,6 +62,8 @@ spec:
     metadata:
       labels:
         app: adguard
+      annotations:
+        reloader.stakater.com/auto: "true"
     spec:
       containers:
         - name: adguard

adguardhome/k8s/certificate.yaml

@@ -0,0 +1,12 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: adguard-certs
+  namespace: adguard
+spec:
+  secretName: adguard-certs
+  dnsNames:
+    - dns.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer

adguardhome/k8s/ingress.yaml

@@ -7,7 +7,7 @@ spec:
   entryPoints:
     - websecure
   routes:
-    - match: Host(`adguard.forust.xyz`) || Host(`dns.forust.xyz`)
+    - match: Host(`dns.forust.xyz`)
       kind: Rule
       middlewares:
         - name: crowdsec-bouncer
@@ -15,13 +15,13 @@ spec:
       services:
         - name: adguard-service
           port: 3000
-    - match: (Host(`adguard.forust.xyz`) || Host(`dns.forust.xyz`)) && PathPrefix(`/dns-query`)
+    - match: (Host(`dns.forust.xyz`)) && PathPrefix(`/dns-query`)
       kind: Rule
       services:
         - name: adguard-service
           port: 3000
   tls:
-    certResolver: letsencrypt
+    secretName: adguard-certs
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -42,3 +42,5 @@ spec:
       services:
         - name: adguard-service
           port: 3000
+  tls:
+    secretName: internal-wildcard-tls

adguardhome/k8s/internal-certificate.yaml

@@ -0,0 +1,15 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: adguard
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

authentik/k8s/certificates.yaml

@@ -0,0 +1,28 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: authentik-prod-tls
+  namespace: authentik
+spec:
+  secretName: authentik-prod-tls
+  dnsNames:
+    - auth.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: authentik
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

authentik/k8s/ingress.yaml

@@ -16,7 +16,7 @@ spec:
         - name: authentik-server-service
           port: 9000
   tls:
-    certResolver: letsencrypt
+    secretName: authentik-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -32,3 +32,5 @@ spec:
       services:
         - name: authentik-server-service
           port: 9000
+  tls:
+    secretName: internal-wildcard-tls

cert-manager/k8s/cert-manager-values.yaml

@@ -0,0 +1,9 @@
+crds:
+  enabled: true
+prometheus:
+  servicemonitor:
+    enabled: true
+    interval: 60s
+    scrapeTimeout: 30s
+    labels:
+      release: prometheus-stack

cert-manager/k8s/clusterissuer.yaml

@@ -0,0 +1,29 @@
+apiVersion: cert-manager.io/v1
+kind: ClusterIssuer
+metadata:
+  name: letsencrypt-staging
+spec:
+  acme:
+    email: bobrovod@national.shitposting.agency
+    server: https://acme-staging-v02.api.letsencrypt.org/directory
+    privateKeySecretRef:
+      name: letsencrypt-staging-account-key
+    solvers:
+      - http01:
+          ingress:
+            class: traefik
+---
+apiVersion: cert-manager.io/v1
+kind: ClusterIssuer
+metadata:
+  name: letsencrypt-prod
+spec:
+  acme:
+    email: bobrovod@national.shitposting.agency
+    server: https://acme-v02.api.letsencrypt.org/directory
+    privateKeySecretRef:
+      name: letsencrypt-prod-account-key
+    solvers:
+      - http01:
+          ingress:
+            class: traefik

cert-manager/k8s/homelab-internal-root-ca.crt

@@ -0,0 +1,30 @@
+-----BEGIN CERTIFICATE-----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+-----END CERTIFICATE-----

cert-manager/k8s/internal-ca.yaml

@@ -0,0 +1,33 @@
+apiVersion: cert-manager.io/v1
+kind: ClusterIssuer
+metadata:
+  name: selfsigned
+spec:
+  selfSigned: {}
+---
+# Homelab internal root CA (10y). Install the .crt on clients (see below).
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-ca-root
+  namespace: cert-manager
+spec:
+  isCA: true
+  commonName: homelab internal root CA
+  duration: 87600h
+  renewBefore: 7200h
+  secretName: internal-ca-root
+  privateKey:
+    algorithm: RSA
+    size: 4096
+  issuerRef:
+    name: selfsigned
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: ClusterIssuer
+metadata:
+  name: internal-ca
+spec:
+  ca:
+    secretName: internal-ca-root

cert-manager/k8s/namespace.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: cert-manager

checkmk/k8s/certificates.yaml

@@ -0,0 +1,28 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: checkmk-prod-tls
+  namespace: checkmk
+spec:
+  secretName: checkmk-prod-tls
+  dnsNames:
+    - cmk.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: checkmk
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

checkmk/k8s/ingress.yaml

@@ -16,7 +16,7 @@ spec:
         - name: checkmk-service
           port: 5000
   tls:
-    certResolver: letsencrypt
+    secretName: checkmk-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRouteTCP
@@ -48,3 +48,5 @@ spec:
       services:
         - name: checkmk-service
           port: 5000
+  tls:
+    secretName: internal-wildcard-tls

converters/k8s/certificates.yaml

@@ -0,0 +1,42 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: convertx-prod-tls
+  namespace: converters
+spec:
+  secretName: convertx-prod-tls
+  dnsNames:
+    - forust.xyz
+    - www.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: bentopdf-prod-tls
+  namespace: converters
+spec:
+  secretName: bentopdf-prod-tls
+  dnsNames:
+    - pdf.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: converters
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

converters/k8s/ingress.yaml

@@ -14,7 +14,7 @@ spec:
         - name: convertx-service
           port: 3000
   tls:
-    certResolver: letsencrypt
+    secretName: convertx-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -31,6 +31,9 @@ spec:
       services:
         - name: convertx-service
           port: 3000
+  tls:
+    secretName: internal-wildcard-tls
+
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -47,7 +50,7 @@ spec:
         - name: bentopdf-service
           port: 8080
   tls:
-    certResolver: letsencrypt
+    secretName: bentopdf-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -63,3 +66,5 @@ spec:
       services:
         - name: bentopdf-service
           port: 8080
+  tls:
+    secretName: internal-wildcard-tls

dockmon/k8s/certificates.yaml

@@ -0,0 +1,28 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: dockmon-prod-tls
+  namespace: dockmon
+spec:
+  secretName: dockmon-prod-tls
+  dnsNames:
+    - dockmon.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: dockmon
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

dockmon/k8s/ingress.yaml

@@ -26,7 +26,7 @@ spec:
           port: 443
           serversTransport: dockmon-transport
   tls:
-    certResolver: letsencrypt
+    secretName: dockmon-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -43,3 +43,5 @@ spec:
         - name: dockmon-service
           port: 443
           serversTransport: dockmon-transport
+  tls:
+    secretName: internal-wildcard-tls

downtify/k8s/ingress.yaml

@@ -17,7 +17,7 @@ spec:
         - name: downtify-service
           port: 8000
   tls:
-    certResolver: letsencrypt
+    secretName: downtify-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -33,3 +33,5 @@ spec:
       services:
         - name: downtify-service
           port: 8000
+  tls:
+    secretName: internal-wildcard-tls

edu_master/PLAYWRIGHT_VERSION

@@ -0,0 +1 @@
+1.56.0

edu_master/compose.yaml

@@ -11,7 +11,7 @@ services:
       retries: 5
 
   playwright-service:
-    image: mcr.microsoft.com/playwright:v1.63.0-jammy
+    image: mcr.microsoft.com/playwright:v1.56.0-jammy
     restart: unless-stopped
     command: npx -y playwright@1.56.0 run-server --port 3000 --path /ws
 

edu_master/k8s/alerts.yaml

@@ -0,0 +1,77 @@
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: edu-master-webinar
+  namespace: edu-master
+  labels:
+    release: prometheus-stack
+spec:
+  groups:
+    - name: edu_master.webinar
+      rules:
+        # No successful webinar check for 5m (~2-3 missed 2-min checks).
+        # Catches: playwright hangs/timeouts, version skew, site changes, hung job.
+        - alert: WebinarCheckerNoSuccessfulCheck
+          expr: |
+            (time() - webinar_check_last_success_timestamp_seconds > 300)
+              and (webinar_check_last_run_timestamp_seconds > 0)
+          for: 2m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Webinar checker has no successful check for 5m"
+            description: "edu-master/webinar-checker: last successful webinar check was {{ $value | humanizeDuration }} ago. Checks are failing or hanging (see consecutive failures alert). Notifications about new webinars are NOT being sent."
+
+        # Fast path: 3 consecutive failures (~6+ min at 2-min interval).
+        - alert: WebinarCheckerConsecutiveFailures
+          expr: |
+            webinar_check_consecutive_failures >= 3
+          for: 5m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Webinar checker failing consecutively"
+            description: 'edu-master/webinar-checker: {{ $value }} consecutive webinar check failures (timeout / playwright error / page error). Check pod logs (Loki: {namespace="edu-master", container="webinar-checker"}).'
+
+        # Metrics endpoint not scraped for 10m: pod down, metrics server dead, or ServiceMonitor broken.
+        - alert: WebinarCheckerScrapeDown
+          expr: |
+            absent(webinar_check_last_run_timestamp_seconds) == 1
+          for: 10m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Webinar checker metrics missing"
+            description: "edu-master/webinar-checker: no metrics series for 10m. Pod may be down, metrics server dead, or ServiceMonitor/Service broken. Webinar checks are unobserved."
+
+        # EDU session lost: session-keeper down or credentials expired. Without PHPSESSID every check is skipped.
+        - alert: EduPhpsessidMissing
+          expr: |
+            edu_phpsessid_present == 0
+          for: 10m
+          labels:
+            severity: critical
+          annotations:
+            summary: "EDU_PHPSESSID missing"
+            description: "edu-master: EDU_PHPSESSID absent from redis for 10m. Webinar/diari/schedule checks are all skipped. Check session-keeper logs and EDU credentials."
+
+        # Hard deps: checker and playwright deployments unavailable.
+        - alert: WebinarCheckerDeploymentDown
+          expr: |
+            kube_deployment_status_replicas_unavailable{deployment="webinar-checker", namespace="edu-master"} > 0
+          for: 10m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Webinar checker deployment unavailable"
+            description: "edu-master/webinar-checker deployment has {{ $value }} unavailable replica(s) for 10m."
+
+        - alert: PlaywrightServiceDown
+          expr: |
+            kube_deployment_status_replicas_unavailable{deployment="playwright-service", namespace="edu-master"} > 0
+          for: 10m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Playwright service unavailable"
+            description: "edu-master/playwright-service deployment has {{ $value }} unavailable replica(s) for 10m. All webinar/diari/schedule checks fail without it."

edu_master/k8s/playwright.yaml

@@ -17,7 +17,8 @@ spec:
     spec:
       containers:
         - name: playwright
-          image: mcr.microsoft.com/playwright:v1.63.0-jammy
+          # renovate: datasource=docker depName=mcr.microsoft.com/playwright versioning=docker
+          image: mcr.microsoft.com/playwright:v1.56.0-jammy
           imagePullPolicy: IfNotPresent
           command:
             - npx

edu_master/k8s/secrets.yaml.example

@@ -21,6 +21,8 @@ stringData:
   WEBINAR_TELEGRAM_TOKEN: ""
   WEBINAR_ADMIN_ID: ""
   WEBINAR_CHECK_INTERVAL: "60"
+  # Prometheus metrics endpoint (scraped via ServiceMonitor, alerts in k8s/alerts.yaml)
+  METRICS_PORT: "8000"
   # Database
   REDIS_HOST: "redis"
   REDIS_PORT: "6379"

edu_master/k8s/service.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: webinar-checker
+  namespace: edu-master
+  labels:
+    app: edu-master-webinar-checker
+spec:
+  selector:
+    app: edu-master-webinar-checker
+  ports:
+    - name: metrics
+      port: 8000
+      targetPort: metrics
+      protocol: TCP

edu_master/k8s/servicemonitor.yaml

@@ -0,0 +1,16 @@
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: webinar-checker
+  namespace: edu-master
+  labels:
+    release: prometheus-stack
+spec:
+  selector:
+    matchLabels:
+      app: edu-master-webinar-checker
+  endpoints:
+    - port: metrics
+      path: /metrics
+      interval: 30s
+      scrapeTimeout: 10s

edu_master/k8s/webinar-checker.yaml

@@ -47,6 +47,10 @@ spec:
         - name: webinar-checker
           image: gcr.forust.xyz/forust/webinar-checker:latest
           imagePullPolicy: Always
+          ports:
+            - name: metrics
+              containerPort: 8000
+              protocol: TCP
           envFrom:
             - secretRef:
                 name: edu-master-secrets

edu_master/webinar-checker/Dockerfile

@@ -2,8 +2,11 @@ FROM python:3.11-slim
 
 WORKDIR /app
 
-# Install dependencies
-RUN pip install --no-cache-dir pip==25.0.1 && pip install --no-cache-dir playwright==1.56.0 redis==5.2.1 requests==2.32.3 "python-telegram-bot[job-queue]==21.10"
+# renovate: datasource=pypi depName=playwright versioning=pep440
+ARG PLAYWRIGHT_VERSION=1.56.0
+
+# Install dependencies - PLAYWRIGHT_VERSION is single-source, renovate updates ARG above and all other places via regexManagers
+RUN pip install --no-cache-dir pip==25.0.1 && pip install --no-cache-dir playwright==${PLAYWRIGHT_VERSION} redis==5.2.1 requests==2.32.3 "python-telegram-bot[job-queue]==21.10"
 
 COPY checker.py .
 

edu_master/webinar-checker/checker.py

@@ -1,12 +1,15 @@
+import asyncio
 import contextlib
 import json
 import logging
 import os
 import re
 import tempfile
+import threading
 import time
 from datetime import datetime, timedelta
 from html import escape
+from http.server import BaseHTTPRequestHandler, HTTPServer
 
 import redis
 from playwright.async_api import async_playwright
@@ -48,6 +51,106 @@ USER_AGENT = _env(
 )
 WEBINAR_TELEGRAM_TOKEN = _env('WEBINAR_TELEGRAM_TOKEN')
 ADMIN_ID = int(_env('WEBINAR_ADMIN_ID', '0'))
+METRICS_PORT = int(_env('METRICS_PORT', '8000'))
+
+# --- Prometheus metrics (stdlib only, no extra deps) ---
+# Scraped by prometheus-stack via ServiceMonitor (edu_master/k8s/servicemonitor.yaml).
+# Critical alerts in edu_master/k8s/alerts.yaml fire to Telegram via Alertmanager.
+_METRICS_LOCK = threading.Lock()
+_METRICS = {
+    'last_run': 0.0,  # Unix ts of last check start
+    'last_success': 0.0,  # Unix ts of last successful check
+    'last_duration': 0.0,  # Duration of last check in seconds
+    'success_total': 0,
+    'failure_total': 0,
+    'consecutive_failures': 0,
+    'phpsessid_present': 1,  # 1 if EDU_PHPSESSID found in redis, else 0
+}
+
+
+def _metric_check_start():
+    with _METRICS_LOCK:
+        _METRICS['last_run'] = time.time()
+
+
+def _metric_check_ok(duration: float):
+    now = time.time()
+    with _METRICS_LOCK:
+        _METRICS['last_success'] = now
+        _METRICS['last_duration'] = duration
+        _METRICS['success_total'] += 1
+        _METRICS['consecutive_failures'] = 0
+        _METRICS['phpsessid_present'] = 1
+
+
+def _metric_check_fail(duration: float, phpsessid_missing: bool = False):
+    with _METRICS_LOCK:
+        _METRICS['last_duration'] = duration
+        _METRICS['failure_total'] += 1
+        _METRICS['consecutive_failures'] += 1
+        _METRICS['phpsessid_present'] = 0 if phpsessid_missing else 1
+
+
+def _metrics_render() -> bytes:
+    with _METRICS_LOCK:
+        m = dict(_METRICS)
+    lines = [
+        '# HELP webinar_check_last_run_timestamp_seconds Unix timestamp of last webinar check start.',
+        '# TYPE webinar_check_last_run_timestamp_seconds gauge',
+        f'webinar_check_last_run_timestamp_seconds {m["last_run"]}',
+        '# HELP webinar_check_last_success_timestamp_seconds Unix timestamp of last successful webinar check.',
+        '# TYPE webinar_check_last_success_timestamp_seconds gauge',
+        f'webinar_check_last_success_timestamp_seconds {m["last_success"]}',
+        '# HELP webinar_check_last_duration_seconds Duration of last webinar check in seconds.',
+        '# TYPE webinar_check_last_duration_seconds gauge',
+        f'webinar_check_last_duration_seconds {m["last_duration"]}',
+        '# HELP webinar_check_success_total Total successful webinar checks.',
+        '# TYPE webinar_check_success_total counter',
+        f'webinar_check_success_total {m["success_total"]}',
+        '# HELP webinar_check_failure_total Total failed webinar checks (timeout, playwright error, page error).',
+        '# TYPE webinar_check_failure_total counter',
+        f'webinar_check_failure_total {m["failure_total"]}',
+        '# HELP webinar_check_consecutive_failures Consecutive failed webinar checks (reset on success).',
+        '# TYPE webinar_check_consecutive_failures gauge',
+        f'webinar_check_consecutive_failures {m["consecutive_failures"]}',
+        '# HELP edu_phpsessid_present 1 if EDU_PHPSESSID exists in redis, 0 otherwise.',
+        '# TYPE edu_phpsessid_present gauge',
+        f'edu_phpsessid_present {m["phpsessid_present"]}',
+    ]
+    return ('\n'.join(lines) + '\n').encode()
+
+
+class _MetricsHandler(BaseHTTPRequestHandler):
+    def do_GET(self):
+        if self.path == '/metrics':
+            body = _metrics_render()
+            self.send_response(200)
+            self.send_header('Content-Type', 'text/plain; version=0.0.4')
+            self.send_header('Content-Length', str(len(body)))
+            self.end_headers()
+            self.wfile.write(body)
+        elif self.path in ('/healthz', '/health'):
+            body = b'ok\n'
+            self.send_response(200)
+            self.send_header('Content-Type', 'text/plain')
+            self.send_header('Content-Length', str(len(body)))
+            self.end_headers()
+            self.wfile.write(body)
+        else:
+            self.send_response(404)
+            self.end_headers()
+
+    def log_message(self, *args):
+        pass  # keep bot logs clean
+
+
+def start_metrics_server(port: int = METRICS_PORT):
+    server = HTTPServer(('0.0.0.0', port), _MetricsHandler)  # noqa: S104 - k8s ServiceMonitor scrapes pod IP
+    thread = threading.Thread(target=server.serve_forever, name='metrics-server', daemon=True)
+    thread.start()
+    logger.info(f'Metrics server listening on :{port}/metrics')
+    return server
+
 
 # Redis Keys
 KEY_WHITELIST = 'bot:whitelist'
@@ -597,59 +700,66 @@ async def _collect_event_times(page) -> dict:
 async def fetch_diary_data(phpsessid: str) -> dict | None:
     logger.info('Fetching diary data via Playwright...')
     try:
-        async with async_playwright() as p:
-            browser = await p.chromium.connect(PLAYWRIGHT_WS)
-            try:
-                context_browser = await browser.new_context(user_agent=USER_AGENT)
-                await context_browser.add_cookies(
-                    [{'name': 'PHPSESSID', 'value': phpsessid, 'domain': 'edu.edu.vn.ua', 'path': '/'}]
-                )
-                page = await context_browser.new_page()
-
+        async with asyncio.timeout(60):
+            async with async_playwright() as p:
+                browser = await asyncio.wait_for(p.chromium.connect(PLAYWRIGHT_WS), timeout=15)
                 try:
-                    await page.goto(DIARY_URL, wait_until='domcontentloaded')
-                    await page.wait_for_selector('table.calendar', timeout=10000)
-                    await page.wait_for_timeout(1500)
-
-                    table_html = await page.evaluate("""
-                        () => {
-                            const t = document.querySelector('table.calendar');
-                            return t ? t.outerHTML : null;
-                        }
-                    """)
-                    if not table_html:
-                        logger.error('table.calendar not found in DOM')
-                        return None
-
-                    # Debug: save HTML for troubleshooting
-                    with contextlib.suppress(Exception), open('/tmp/diary_debug.html', 'w', encoding='utf-8') as f:  # noqa: S108
-                        f.write(table_html)
-
-                    month_text, days = _parse_calendar_html(table_html)
-
-                    # Read event times by opening each event's AJAX popup.
-                    times_by_id = await _collect_event_times(page)
-                    if times_by_id:
-                        for day_data in days.values():
-                            for ev in day_data.get('events', []):
-                                eid = ev.get('id')
-                                if eid and eid in times_by_id:
-                                    ev['time'] = times_by_id[eid]
-
-                    logger.info(
-                        f'Diary parsed: month={month_text!r}, days_with_events={sum(1 for d in days.values() if d["events"])}/{len(days)}'
+                    context_browser = await browser.new_context(user_agent=USER_AGENT)
+                    await context_browser.add_cookies(
+                        [{'name': 'PHPSESSID', 'value': phpsessid, 'domain': 'edu.edu.vn.ua', 'path': '/'}]
                     )
+                    page = await context_browser.new_page()
 
-                    return {'monthFullText': month_text, 'days': days}
+                    try:
+                        await asyncio.wait_for(page.goto(DIARY_URL, wait_until='domcontentloaded'), timeout=30)
+                        await page.wait_for_selector('table.calendar', timeout=10000)
+                        await page.wait_for_timeout(1500)
 
-                except Exception as e:
-                    logger.error(f'Error parsing diary: {e}')
-                    return None
+                        table_html = await page.evaluate("""
+                            () => {
+                                const t = document.querySelector('table.calendar');
+                                return t ? t.outerHTML : null;
+                            }
+                        """)
+                        if not table_html:
+                            logger.error('table.calendar not found in DOM')
+                            return None
+
+                        # Debug: save HTML for troubleshooting
+                        with contextlib.suppress(Exception), open('/tmp/diary_debug.html', 'w', encoding='utf-8') as f:  # noqa: S108
+                            f.write(table_html)
+
+                        month_text, days = _parse_calendar_html(table_html)
+
+                        # Read event times by opening each event's AJAX popup.
+                        times_by_id = await _collect_event_times(page)
+                        if times_by_id:
+                            for day_data in days.values():
+                                for ev in day_data.get('events', []):
+                                    eid = ev.get('id')
+                                    if eid and eid in times_by_id:
+                                        ev['time'] = times_by_id[eid]
+
+                        logger.info(
+                            f'Diary parsed: month={month_text!r}, days_with_events={sum(1 for d in days.values() if d["events"])}/{len(days)}'
+                        )
+
+                        return {'monthFullText': month_text, 'days': days}
+
+                    except Exception as e:
+                        logger.error(f'Error parsing diary: {e}')
+                        return None
+                    finally:
+                        with contextlib.suppress(Exception):
+                            await asyncio.wait_for(page.close(), timeout=5)
+                        with contextlib.suppress(Exception):
+                            await asyncio.wait_for(context_browser.close(), timeout=5)
                 finally:
-                    await page.close()
-                    await context_browser.close()
-            finally:
-                await browser.close()
+                    with contextlib.suppress(Exception):
+                        await asyncio.wait_for(browser.close(), timeout=5)
+    except TimeoutError:
+        logger.error('Diary fetch timed out (60s)')
+        return None
     except Exception as e:
         logger.error(f'Playwright error in diary fetch: {e}')
         return None
@@ -931,48 +1041,55 @@ def _parse_schedule_html(table_html: str) -> dict:
 async def fetch_schedule_data(phpsessid: str) -> dict | None:
     logger.info('Fetching schedule data via Playwright...')
     try:
-        async with async_playwright() as p:
-            browser = await p.chromium.connect(PLAYWRIGHT_WS)
-            try:
-                context_browser = await browser.new_context(user_agent=USER_AGENT)
-                await context_browser.add_cookies(
-                    [{'name': 'PHPSESSID', 'value': phpsessid, 'domain': 'edu.edu.vn.ua', 'path': '/'}]
-                )
-                page = await context_browser.new_page()
-
+        async with asyncio.timeout(60):
+            async with async_playwright() as p:
+                browser = await asyncio.wait_for(p.chromium.connect(PLAYWRIGHT_WS), timeout=15)
                 try:
-                    await page.goto(SCHEDULE_URL, wait_until='domcontentloaded')
-                    await page.wait_for_selector('table.schedule-table', timeout=10000)
-                    await page.wait_for_timeout(1500)
+                    context_browser = await browser.new_context(user_agent=USER_AGENT)
+                    await context_browser.add_cookies(
+                        [{'name': 'PHPSESSID', 'value': phpsessid, 'domain': 'edu.edu.vn.ua', 'path': '/'}]
+                    )
+                    page = await context_browser.new_page()
 
-                    table_html = await page.evaluate("""
-                        () => {
-                            const t = document.querySelector('table.schedule-table');
-                            return t ? t.outerHTML : null;
-                        }
-                    """)
-                    if not table_html:
-                        logger.error('table.schedule-table not found in DOM')
+                    try:
+                        await asyncio.wait_for(page.goto(SCHEDULE_URL, wait_until='domcontentloaded'), timeout=30)
+                        await page.wait_for_selector('table.schedule-table', timeout=10000)
+                        await page.wait_for_timeout(1500)
+
+                        table_html = await page.evaluate("""
+                            () => {
+                                const t = document.querySelector('table.schedule-table');
+                                return t ? t.outerHTML : null;
+                            }
+                        """)
+                        if not table_html:
+                            logger.error('table.schedule-table not found in DOM')
+                            return None
+
+                        debug_path = os.path.join(tempfile.gettempdir(), 'schedule_debug.html')
+                        with contextlib.suppress(Exception), open(debug_path, 'w', encoding='utf-8') as f:
+                            f.write(table_html)
+
+                        data = _parse_schedule_html(table_html)
+                        logger.info(list(data['weekdays'].keys()))
+                        logger.info(f'Schedule parsed: {len(data["weekdays"])} days, classes={data["classes"]}')
+
+                        return data
+
+                    except Exception as e:
+                        logger.error(f'Error parsing schedule: {e}')
                         return None
-
-                    debug_path = os.path.join(tempfile.gettempdir(), 'schedule_debug.html')
-                    with contextlib.suppress(Exception), open(debug_path, 'w', encoding='utf-8') as f:
-                        f.write(table_html)
-
-                    data = _parse_schedule_html(table_html)
-                    logger.info(list(data['weekdays'].keys()))
-                    logger.info(f'Schedule parsed: {len(data["weekdays"])} days, classes={data["classes"]}')
-
-                    return data
-
-                except Exception as e:
-                    logger.error(f'Error parsing schedule: {e}')
-                    return None
+                    finally:
+                        with contextlib.suppress(Exception):
+                            await asyncio.wait_for(page.close(), timeout=5)
+                        with contextlib.suppress(Exception):
+                            await asyncio.wait_for(context_browser.close(), timeout=5)
                 finally:
-                    await page.close()
-                    await context_browser.close()
-            finally:
-                await browser.close()
+                    with contextlib.suppress(Exception):
+                        await asyncio.wait_for(browser.close(), timeout=5)
+    except TimeoutError:
+        logger.error('Schedule fetch timed out (60s)')
+        return None
     except Exception as e:
         logger.error(f'Playwright error in schedule fetch: {e}')
         return None
@@ -1485,10 +1602,13 @@ async def check_webinars_job(context: ContextTypes.DEFAULT_TYPE):
         int: Number of webinars found, or None if check failed
     """
     logger.info('Running webinar check...')
+    _t0 = time.time()
+    _metric_check_start()
 
     phpsessid = redis_client.get(KEY_PHPSESSID)
     if not phpsessid:
         logger.warning('PHPSESSID missing. Skipping check.')
+        _metric_check_fail(time.time() - _t0, phpsessid_missing=True)
         # --- DEBUG LOGGING ---
         try:
             with open('phpsessid_missing.log', 'a') as f:
@@ -1502,78 +1622,88 @@ async def check_webinars_job(context: ContextTypes.DEFAULT_TYPE):
     content = ''
 
     try:
-        async with async_playwright() as p:
-            # Connect to remote Playwright service
-            browser = await p.chromium.connect(PLAYWRIGHT_WS)
-
-            try:
-                # Create browser context with user agent
-                context_browser = await browser.new_context(user_agent=USER_AGENT)
-
-                # Add PHPSESSID cookie
-                await context_browser.add_cookies(
-                    [{'name': 'PHPSESSID', 'value': phpsessid, 'domain': 'edu.edu.vn.ua', 'path': '/'}]
-                )
-
-                # Create new page
-                page = await context_browser.new_page()
+        async with asyncio.timeout(90):
+            async with async_playwright() as p:
+                # Connect to remote Playwright service
+                browser = await asyncio.wait_for(p.chromium.connect(PLAYWRIGHT_WS), timeout=15)
 
                 try:
-                    # Navigate to webinar page
-                    await page.goto(WEBINAR_URL, wait_until='domcontentloaded')
+                    # Create browser context with user agent
+                    context_browser = await browser.new_context(user_agent=USER_AGENT)
 
-                    # Wait for the table to load
-                    await page.wait_for_selector('#meetings table', timeout=10000)
-                    await page.wait_for_timeout(2000)
+                    # Add PHPSESSID cookie
+                    await context_browser.add_cookies(
+                        [{'name': 'PHPSESSID', 'value': phpsessid, 'domain': 'edu.edu.vn.ua', 'path': '/'}]
+                    )
 
-                    # Get page content
-                    content = await page.content()
+                    # Create new page
+                    page = await context_browser.new_page()
 
-                    # Check if "no webinar" message is present
-                    if NO_WEBINAR_MARKER not in content:
-                        logger.info('!!! WEBINAR FOUND !!!')
+                    try:
+                        # Navigate to webinar page
+                        await asyncio.wait_for(page.goto(WEBINAR_URL, wait_until='domcontentloaded'), timeout=30)
 
-                        # Extract webinar details from table rows
-                        rows = page.locator('#meetings table tbody tr')
-                        count = await rows.count()
+                        # Wait for the table to load
+                        await page.wait_for_selector('#meetings table', timeout=10000)
+                        await page.wait_for_timeout(2000)
 
-                        for i in range(count):
-                            row = rows.nth(i)
-                            text = await row.inner_text()
+                        # Get page content
+                        content = await page.content()
 
-                            if NO_WEBINAR_MARKER not in text:
-                                # Extract name (topic) from first column
-                                name_elem = row.locator('td').nth(0)
-                                name = await name_elem.inner_text()
-                                name = name.strip()
+                        # Check if "no webinar" message is present
+                        if NO_WEBINAR_MARKER not in content:
+                            logger.info('!!! WEBINAR FOUND !!!')
 
-                                # Extract join URL from fourth column
-                                url_elem = row.locator('td').nth(3).locator('a[href*="/webinar/join/"]').first
-                                url = await url_elem.get_attribute('href')
+                            # Extract webinar details from table rows
+                            rows = page.locator('#meetings table tbody tr')
+                            count = await rows.count()
 
-                                if name and url:
-                                    current_webinars.append({'name': name, 'url': url, 'text': text.strip()})
-                                    logger.info(f'Found webinar: {name} -> {url}')
-                    else:
-                        logger.info('No webinars found (expected message present)')
+                            for i in range(count):
+                                row = rows.nth(i)
+                                text = await row.inner_text()
 
-                except Exception as e:
-                    logger.error(f'Error checking page: {e}. Saving content for debug.')
-                    # If page content is available, save it on error
-                    with contextlib.suppress(Exception):
-                        if page and not content:
-                            content = await page.content()
+                                if NO_WEBINAR_MARKER not in text:
+                                    # Extract name (topic) from first column
+                                    name_elem = row.locator('td').nth(0)
+                                    name = await name_elem.inner_text()
+                                    name = name.strip()
+
+                                    # Extract join URL from fourth column
+                                    url_elem = row.locator('td').nth(3).locator('a[href*="/webinar/join/"]').first
+                                    url = await url_elem.get_attribute('href')
+
+                                    if name and url:
+                                        current_webinars.append({'name': name, 'url': url, 'text': text.strip()})
+                                        logger.info(f'Found webinar: {name} -> {url}')
+                        else:
+                            logger.info('No webinars found (expected message present)')
+
+                    except Exception as e:
+                        logger.error(f'Error checking page: {e}. Saving content for debug.')
+                        # If page content is available, save it on error
+                        with contextlib.suppress(Exception):
+                            if page and not content:
+                                content = await page.content()
+
+                        _metric_check_fail(time.time() - _t0)
+                        return None
+                    finally:
+                        with contextlib.suppress(Exception):
+                            await asyncio.wait_for(page.close(), timeout=5)
+                        with contextlib.suppress(Exception):
+                            await asyncio.wait_for(context_browser.close(), timeout=5)
 
-                    return None
                 finally:
-                    await page.close()
-                    await context_browser.close()
-
-            finally:
-                await browser.close()
+                    with contextlib.suppress(Exception):
+                        await asyncio.wait_for(browser.close(), timeout=5)
 
+    except TimeoutError:
+        logger.error('Webinar check timed out after 90s (playwright hang)')
+        _metric_check_fail(time.time() - _t0)
+        return None
     except Exception as e:
         logger.error(f'Playwright error: {e}')
+        _metric_check_fail(time.time() - _t0)
         return None
 
     # --- DEBUG LOGGING (Saving last response content) ---
@@ -1637,6 +1767,7 @@ async def check_webinars_job(context: ContextTypes.DEFAULT_TYPE):
         else:
             logger.info(f'Found {len(current_webinars)} webinar(s), but all are already known')
 
+    _metric_check_ok(time.time() - _t0)
     return len(current_webinars)
 
 
@@ -1680,6 +1811,8 @@ def main():
     job_queue = app.job_queue
     job_queue.run_repeating(check_webinars_job, interval=WEBINAR_CHECK_INTERVAL, first=10)
 
+    start_metrics_server()
+
     logger.info('Bot started polling...')
     app.run_polling()
 

gitea/k8s/certificates.yaml

@@ -0,0 +1,29 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: gitea-prod-tls
+  namespace: gitea
+spec:
+  secretName: gitea-prod-tls
+  dnsNames:
+    - gcr.forust.xyz
+    - gitea.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: gitea
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

gitea/k8s/gitea.yaml

@@ -31,7 +31,7 @@ spec:
     spec:
       containers:
         - name: gitea
-          image: docker.gitea.com/gitea:1.27.3
+          image: gitea/gitea:1.27.3
           envFrom:
             - configMapRef:
                 name: gitea-config

gitea/k8s/ingress.yaml

@@ -24,7 +24,7 @@ spec:
         - name: gitea-service
           port: 3000
   tls:
-    certResolver: letsencrypt
+    secretName: gitea-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -45,6 +45,9 @@ spec:
       services:
         - name: gitea-service
           port: 3000
+  tls:
+    secretName: internal-wildcard-tls
+
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRouteTCP

glance/k8s/certificates.yaml

@@ -0,0 +1,29 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: glance-prod-tls
+  namespace: glance
+spec:
+  secretName: glance-prod-tls
+  dnsNames:
+    - forust.xyz
+    - www.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: glance
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

glance/k8s/ingress.yaml

@@ -16,7 +16,7 @@ spec:
         - name: glance-service
           port: 8080
   tls:
-    certResolver: letsencrypt
+    secretName: glance-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -35,6 +35,9 @@ spec:
       services:
         - name: glance-service
           port: 8080
+  tls:
+    secretName: internal-wildcard-tls
+
 ---
 apiVersion: traefik.io/v1alpha1
 kind: Middleware

headscale/k8s/routing/certificates.yaml

@@ -0,0 +1,41 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: headscale-prod-tls
+  namespace: headscale
+spec:
+  secretName: headscale-prod-tls
+  dnsNames:
+    - hs.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: headplane-prod-tls
+  namespace: headscale
+spec:
+  secretName: headplane-prod-tls
+  dnsNames:
+    - hp.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: headscale
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

headscale/k8s/routing/ingress.yaml

@@ -38,7 +38,7 @@ spec:
         - name: headscale-server-external
           port: 9090
   tls:
-    certResolver: letsencrypt
+    secretName: headscale-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -64,7 +64,7 @@ spec:
         - name: headplane-external
           port: 3000
   tls:
-    certResolver: letsencrypt
+    secretName: headplane-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -90,6 +90,9 @@ spec:
       services:
         - name: headscale-server-external
           port: 9090
+  tls:
+    secretName: internal-wildcard-tls
+
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -110,3 +113,5 @@ spec:
       services:
         - name: headplane-external
           port: 3000
+  tls:
+    secretName: internal-wildcard-tls

homepages/k8s/certificates.yaml

@@ -0,0 +1,42 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: forust-homepage-prod-tls
+  namespace: homepages
+spec:
+  secretName: forust-homepage-prod-tls
+  dnsNames:
+    - forust.xyz
+    - www.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: xdfnx-homepage-prod-tls
+  namespace: homepages
+spec:
+  secretName: xdfnx-homepage-prod-tls
+  dnsNames:
+    - xdfnx.cfd
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: homepages
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

homepages/k8s/ingress.yaml

@@ -17,7 +17,7 @@ spec:
         - name: forust-homepage-service
           port: 80
   tls:
-    certResolver: letsencrypt
+    secretName: forust-homepage-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -34,6 +34,9 @@ spec:
       services:
         - name: forust-homepage-service
           port: 80
+  tls:
+    secretName: internal-wildcard-tls
+
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -53,7 +56,7 @@ spec:
         - name: xdfnx-homepage-service
           port: 80
   tls:
-    certResolver: letsencrypt
+    secretName: xdfnx-homepage-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -69,3 +72,5 @@ spec:
       services:
         - name: xdfnx-homepage-service
           port: 80
+  tls:
+    secretName: internal-wildcard-tls

kener/k8s/ingress.yaml

@@ -16,7 +16,7 @@ spec:
         - name: kener-service
           port: 3000
   tls:
-    certResolver: letsencrypt
+    secretName: kener-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -32,3 +32,5 @@ spec:
       services:
         - name: kener-service
           port: 3000
+  tls:
+    secretName: internal-wildcard-tls

metube/k8s/certificates.yaml

@@ -0,0 +1,28 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: metube-prod-tls
+  namespace: metube
+spec:
+  secretName: metube-prod-tls
+  dnsNames:
+    - metube.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: metube
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

metube/k8s/ingress.yaml

@@ -15,7 +15,7 @@ spec:
         - name: metube-service
           port: 8081
   tls:
-    certResolver: letsencrypt
+    secretName: metube-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -31,3 +31,5 @@ spec:
       services:
         - name: metube-service
           port: 8081
+  tls:
+    secretName: internal-wildcard-tls

n8n/k8s/ingress.yaml

@@ -32,3 +32,5 @@ spec:
       services:
         - name: n8n-service
           port: 5678
+  tls:
+    secretName: internal-wildcard-tls

n8n/k8s/internal-certificate.yaml

@@ -0,0 +1,15 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: n8n
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

netronome/k8s/certificates.yaml

@@ -0,0 +1,28 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: netronome-prod-tls
+  namespace: netronome
+spec:
+  secretName: netronome-prod-tls
+  dnsNames:
+    - nm.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: netronome
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

netronome/k8s/ingress.yaml

@@ -16,7 +16,7 @@ spec:
         - name: netronome-service
           port: 7575
   tls:
-    certResolver: letsencrypt
+    secretName: netronome-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -32,3 +32,5 @@ spec:
       services:
         - name: netronome-service
           port: 7575
+  tls:
+    secretName: internal-wildcard-tls

nextcloud/k8s/routing/certificates.yaml

@@ -0,0 +1,28 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: nextcloud-prod-tls
+  namespace: nextcloud
+spec:
+  secretName: nextcloud-prod-tls
+  dnsNames:
+    - nextcloud.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: nextcloud
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

nextcloud/k8s/routing/ingress.yaml

@@ -18,7 +18,7 @@ spec:
         - name: nextcloud-apache
           port: 11000
   tls:
-    certResolver: letsencrypt
+    secretName: nextcloud-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -38,26 +38,29 @@ spec:
       services:
         - name: nextcloud-apache
           port: 11000
-# ---
-# Nextcloud AIO
-# apiVersion: traefik.io/v1alpha1
-# kind: IngressRoute
-# metadata:
-#   name: naio-prod
-#   namespace: nextcloud
-# spec:
-#   entryPoints:
-# - websecure
-# routes:
-#   - match: Host(`naio.forust.xyz`)
-#     kind: Rule
-#     services:
-#       - name: nextcloud-aio
-#         port: 8888
-#         scheme: https
-#         serversTransport: insecure-transport
-# tls:
-#   certResolver: letsencrypt
+  # ---
+  # Nextcloud AIO
+  # apiVersion: traefik.io/v1alpha1
+  # kind: IngressRoute
+  # metadata:
+  #   name: naio-prod
+  #   namespace: nextcloud
+  # spec:
+  #   entryPoints:
+  # - websecure
+  # routes:
+  #   - match: Host(`naio.forust.xyz`)
+  #     kind: Rule
+  #     services:
+  #       - name: nextcloud-aio
+  #         port: 8888
+  #         scheme: https
+  #         serversTransport: insecure-transport
+  # tls:
+  #   certResolver: letsencrypt
+  tls:
+    secretName: internal-wildcard-tls
+
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -75,3 +78,5 @@ spec:
           port: 8888
           scheme: https
           serversTransport: insecure-transport
+  tls:
+    secretName: internal-wildcard-tls

portainer/k8s/certificates.yaml

@@ -0,0 +1,28 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: portainer-prod-tls
+  namespace: portainer
+spec:
+  secretName: portainer-prod-tls
+  dnsNames:
+    - portainer.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: portainer
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

portainer/k8s/ingress.yaml

@@ -16,7 +16,7 @@ spec:
         - name: portainer-service
           port: 9000
   tls:
-    certResolver: letsencrypt
+    secretName: portainer-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -32,3 +32,5 @@ spec:
       services:
         - name: portainer-service
           port: 9000
+  tls:
+    secretName: internal-wildcard-tls

postgres/.env.example

@@ -3,3 +3,4 @@ AUTHENTIK_DB_PASSWORD=
 GITEA_DB_PASSWORD=
 NETRONOME_DB_PASSWORD=
 PENPOT_DB_PASSWORD=
+STATUSPAGE_DB_PASSWORD=

postgres/README.md

@@ -1,23 +1,22 @@
 # Shared PostgreSQL
 
-This directory contains a PostgreSQL 15 deployment draft for Authentik, Gitea,
-Netronome, and Penpot. It creates one database and one login role per service;
-it does not migrate existing data or change application connection settings.
+This directory contains the shared PostgreSQL 17 deployment for Authentik,
+Gitea, Netronome, and Statuspage. It creates one database and one login role
+per service. Per-service standalone databases were removed after the
+migration (Sep 2026); Penpot stays on its own compose PostgreSQL (archived,
+not part of the shared instance).
 
 ## Compatibility baseline
 
-| Service   | Current application | Current standalone PostgreSQL | Common PostgreSQL 15                                                                 |
-| --------- | ------------------- | ----------------------------: | ------------------------------------------------------------------------------------ |
-| Authentik | 2025.10.2           |                            15 | Supported (Authentik requires 14+)                                                   |
-| Gitea     | 1.27.3              |                            14 | Supported (Gitea requires 12+)                                                       |
-| Netronome | 0.14.0              |                            17 | Validate in staging; upstream's example uses 17 but no 17-only feature is documented |
-| Penpot    | 2.17.2              |                            15 | Supported by the official deployment                                                 |
+| Service    | Current application | Shared PostgreSQL 17                   |
+| ---------- | ------------------- | -------------------------------------- |
+| Authentik  | 2025.10.x           | Supported (Authentik requires 14+)     |
+| Gitea      | 1.27.3              | Supported (Gitea requires 12+)         |
+| Netronome  | 0.14.0              | Supported (upstream's example uses 17) |
+| Statuspage | custom              | Supported                              |
 
-PostgreSQL 15 is the conservative common major. A major-version downgrade or
-change must use a logical dump/restore; changing only the image tag while
-keeping a data directory is not supported. Back up and migrate one application
-at a time, starting with Netronome because its current standalone deployment
-uses PostgreSQL 17.
+A major-version change must use a logical dump/restore; changing only the
+image tag while keeping a data directory is not supported.
 
 For Compose, copy `.env.example` to `.env`, set all passwords, and start it with
 `docker compose -f shared-compose.yaml up -d`. This file is intentionally not

postgres/initdb/01-create-databases.sh

@@ -5,12 +5,12 @@ set -euo pipefail
 : "${GITEA_DB_PASSWORD:?GITEA_DB_PASSWORD is required}"
 : "${NETRONOME_DB_PASSWORD:?NETRONOME_DB_PASSWORD is required}"
 : "${PENPOT_DB_PASSWORD:?PENPOT_DB_PASSWORD is required}"
+: "${STATUSPAGE_DB_PASSWORD:?STATUSPAGE_DB_PASSWORD is required}"
 
 create_role_and_database() {
   local role="$1"
   local database="$2"
   local password="$3"
-
   psql --username "$POSTGRES_USER" --dbname postgres \
     -v role="$role" -v database="$database" -v password="$password" \
     <<'SQL'
@@ -25,3 +25,4 @@ create_role_and_database authentik authentik "$AUTHENTIK_DB_PASSWORD"
 create_role_and_database gitea gitea "$GITEA_DB_PASSWORD"
 create_role_and_database netronome netronome "$NETRONOME_DB_PASSWORD"
 create_role_and_database penpot penpot "$PENPOT_DB_PASSWORD"
+create_role_and_database statuspage statuspage "$STATUSPAGE_DB_PASSWORD"

postgres/k8s/postgres.yaml

@@ -60,11 +60,23 @@ spec:
               command: ["pg_isready", "-U", "postgres", "-d", "postgres"]
             initialDelaySeconds: 10
             periodSeconds: 10
+          startupProbe:
+            exec:
+              command: ["pg_isready", "-U", "postgres", "-d", "postgres"]
+            failureThreshold: 30
+            periodSeconds: 10
           livenessProbe:
             exec:
               command: ["pg_isready", "-U", "postgres", "-d", "postgres"]
             initialDelaySeconds: 30
             periodSeconds: 20
+          resources:
+            requests:
+              memory: "512Mi"
+              cpu: "500m"
+            limits:
+              memory: "2Gi"
+              cpu: "2000m"
       volumes:
         - name: postgres-data
           persistentVolumeClaim:

postgres/shared-compose.yaml

@@ -1,6 +1,6 @@
 services:
   postgres:
-    image: postgres:15.19-alpine
+    image: postgres:17.11-alpine
     container_name: homelab-postgres
     restart: unless-stopped
     env_file:

prometheus-stack/k8s/cert-manager-alerts.yaml

@@ -0,0 +1,43 @@
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: cert-manager
+  namespace: prometheus
+  labels:
+    release: prometheus-stack
+spec:
+  groups:
+    - name: cert-manager
+      rules:
+        - alert: CertManagerCertNotReady
+          expr: certmanager_certificate_ready_status{condition="False"} == 1
+          for: 10m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Certificate {{ $labels.exported_namespace }}/{{ $labels.name }} is not ready"
+            description: "Certificate has been failing for more than 10 minutes. Check Challenges/Orders in that namespace."
+        - alert: CertManagerCertExpirySoon
+          expr: certmanager_certificate_expiration_timestamp_seconds - time() < 86400 * 14
+          for: 1h
+          labels:
+            severity: warning
+          annotations:
+            summary: "Certificate {{ $labels.exported_namespace }}/{{ $labels.name }} expires in less than 14 days"
+            description: "Renewal should have happened automatically. Check cert-manager logs if it persists."
+        - alert: CertManagerCertExpiryCritical
+          expr: certmanager_certificate_expiration_timestamp_seconds - time() < 86400 * 7
+          for: 1h
+          labels:
+            severity: critical
+          annotations:
+            summary: "Certificate {{ $labels.exported_namespace }}/{{ $labels.name }} expires in less than 7 days"
+            description: "Manual intervention likely needed: cmctl status certificate {{ $labels.name }} -n {{ $labels.exported_namespace }}."
+        - alert: CertManagerHittingRateLimits
+          expr: sum by (exported_namespace) (rate(certmanager_http_acme_client_request_count{status=~"429.*"}[10m])) > 0
+          for: 15m
+          labels:
+            severity: warning
+          annotations:
+            summary: "cert-manager is hitting ACME rate limits"
+            description: "Back off manual issuance retries and check failed Orders/Challenges."

prometheus-stack/k8s/certificates.yaml

@@ -0,0 +1,28 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: grafana-prod-tls
+  namespace: prometheus
+spec:
+  secretName: grafana-prod-tls
+  dnsNames:
+    - grafana.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: prometheus
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

prometheus-stack/k8s/ingress.yaml

@@ -16,9 +16,7 @@ spec:
         - name: prometheus-stack-grafana
           port: 80
   tls:
-    certResolver: letsencrypt
-    domains:
-      - main: grafana.forust.xyz
+    secretName: grafana-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -34,3 +32,5 @@ spec:
       services:
         - name: prometheus-stack-grafana
           port: 80
+  tls:
+    secretName: internal-wildcard-tls

reloader/k8s/namespace.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: reloader

renovate.json

@@ -1,14 +1,43 @@
 {
   "$schema": "https://docs.renovatebot.com/renovate-schema.json",
   "extends": ["config:recommended"],
-  "enabledManagers": ["docker-compose", "kubernetes", "helm-values"],
+  "enabledManagers": ["dockerfile", "docker-compose", "kubernetes", "helm-values", "custom.regex"],
   "helm-values": {
     "managerFilePatterns": ["/k8s/.+values\\.ya?ml$/"]
   },
   "kubernetes": {
     "managerFilePatterns": ["/k8s/.+\\.ya?ml$/"]
   },
+  "customManagers": [
+    {
+      "customType": "regex",
+      "description": "singlesource: playwright npm version pinned in npx command (k8s + compose)",
+      "fileMatch": ["^edu_master/k8s/playwright\\.yaml$", "^edu_master/compose\\.yaml$"],
+      "matchStrings": ["playwright@(?<currentValue>\\d+\\.\\d+\\.\\d+)"],
+      "datasourceTemplate": "npm",
+      "depNameTemplate": "playwright"
+    },
+    {
+      "customType": "regex",
+      "description": "singlesource: PLAYWRIGHT_VERSION file",
+      "fileMatch": ["^edu_master/PLAYWRIGHT_VERSION$"],
+      "matchStrings": ["^(?<currentValue>\\d+\\.\\d+\\.\\d+)$"],
+      "datasourceTemplate": "pypi",
+      "depNameTemplate": "playwright"
+    }
+  ],
   "packageRules": [
+    {
+      "description": "singlesource playwright - use whichever version is found, keep docker+pypi+npm in sync",
+      "matchPackageNames": ["playwright", "mcr.microsoft.com/playwright"],
+      "groupName": "playwright singlesource",
+      "groupSlug": "playwright"
+    },
+    {
+      "description": "playwright must not automerge - version skew breaks WS handshake (checker.py:1523 vs playwright.yaml:20)",
+      "matchPackageNames": ["playwright", "mcr.microsoft.com/playwright"],
+      "automerge": false
+    },
     {
       "description": "Keep private homelab images unchanged",
       "matchDatasources": ["docker"],

renovate/config.js

@@ -1,6 +1,6 @@
 module.exports = {
   platform: 'gitea',
-  endpoint: process.env.RENOVATE_ENDPOINT,
+  endpoint: process.env.RENOVATE_ENDPOINT || 'https://gitea.forust.xyz/api/v1',
   enabledManagers: ['docker-compose', 'kubernetes', 'helm-values'],
   'helm-values': {
     managerFilePatterns: ['/k8s/.+values\\.ya?ml$/'],

renovate/k8s/configmap.yaml

@@ -7,7 +7,7 @@ data:
   config.js: |
     module.exports = {
       platform: 'gitea',
-      endpoint: process.env.RENOVATE_ENDPOINT,
+      endpoint: process.env.RENOVATE_ENDPOINT || 'https://gitea.forust.xyz/api/v1',
       enabledManagers: ['docker-compose', 'kubernetes', 'helm-values'],
       'helm-values': {
         managerFilePatterns: ['/k8s/.+values\\.ya?ml$/'],

searxng/k8s/certificates.yaml

@@ -0,0 +1,29 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: searxng-prod-tls
+  namespace: searxng
+spec:
+  secretName: searxng-prod-tls
+  dnsNames:
+    - s.forust.xyz
+    - search.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: searxng
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

searxng/k8s/ingress.yaml

@@ -16,7 +16,7 @@ spec:
         - name: searxng-service
           port: 8080
   tls:
-    certResolver: letsencrypt
+    secretName: searxng-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -32,3 +32,5 @@ spec:
       services:
         - name: searxng-service
           port: 8080
+  tls:
+    secretName: internal-wildcard-tls

termix/k8s/certificates.yaml

@@ -0,0 +1,28 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: termix-prod-tls
+  namespace: termix
+spec:
+  secretName: termix-prod-tls
+  dnsNames:
+    - termix.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: termix
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

termix/k8s/ingress.yaml

@@ -16,7 +16,7 @@ spec:
         - name: termix-service
           port: 8080
   tls:
-    certResolver: letsencrypt
+    secretName: termix-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -32,3 +32,5 @@ spec:
       services:
         - name: termix-service
           port: 8080
+  tls:
+    secretName: internal-wildcard-tls

traefik/k8s/certificates.yaml

@@ -0,0 +1,28 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: dashboard-prod-tls
+  namespace: traefik
+spec:
+  secretName: dashboard-prod-tls
+  dnsNames:
+    - traefik.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: traefik
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

traefik/k8s/ingress.yaml

@@ -17,7 +17,7 @@ spec:
         - name: api@internal
           kind: TraefikService
   tls:
-    certResolver: letsencrypt
+    secretName: dashboard-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -33,3 +33,5 @@ spec:
       services:
         - name: api@internal
           kind: TraefikService
+  tls:
+    secretName: internal-wildcard-tls

traefik/k8s/traefik-values.yaml

@@ -31,7 +31,7 @@ deployment:
 
 providers:
   kubernetesIngress:
-    enabled: false
+    enabled: true
   kubernetesCRD:
     enabled: true
   kubernetesGateway:
@@ -121,21 +121,7 @@ persistence:
   size: 100Mi
   path: /data
 
-certificatesResolvers:
-  letsencrypt-staging:
-    acme:
-      email: bobrovod@national.shitposting.agency
-      storage: /data/letsencrypt/acme.json
-      caServer: https://acme-staging-v02.api.letsencrypt.org/directory
-      httpChallenge:
-        entryPoint: web
-  letsencrypt:
-    acme:
-      email: bobrovod@national.shitposting.agency
-      storage: /data/letsencrypt/acme.json
-      caServer: https://acme-v02.api.letsencrypt.org/directory
-      httpChallenge:
-        entryPoint: web
+# No certificatesResolvers: public TLS comes from cert-manager.
 
 volumes:
   - name: traefik-dynamic

uptime-kuma/k8s/certificates.yaml

@@ -0,0 +1,28 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: uptime-kuma-prod-tls
+  namespace: uptime-kuma
+spec:
+  secretName: uptime-kuma-prod-tls
+  dnsNames:
+    - uptime.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: uptime-kuma
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

uptime-kuma/k8s/ingress.yaml

@@ -16,7 +16,7 @@ spec:
         - name: uptime-kuma-service
           port: 3001
   tls:
-    certResolver: letsencrypt
+    secretName: uptime-kuma-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -32,3 +32,5 @@ spec:
       services:
         - name: uptime-kuma-service
           port: 3001
+  tls:
+    secretName: internal-wildcard-tls

userbot/k8s/base/internal-certificate.yaml

@@ -0,0 +1,15 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: userbot
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

userbot/k8s/base/kustomization.yaml

@@ -4,4 +4,5 @@ kind: Kustomization
 resources:
   - userbots.yaml
   - panel.yaml
+  - internal-certificate.yaml
   - common-config.yaml

userbot/k8s/base/panel.yaml

@@ -262,3 +262,5 @@ spec:
       services:
         - name: userbot-panel
           port: 8080
+  tls:
+    secretName: internal-wildcard-tls

vaultwarden/k8s/certificates.yaml

@@ -0,0 +1,28 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: vaultwarden-prod-tls
+  namespace: vaultwarden
+spec:
+  secretName: vaultwarden-prod-tls
+  dnsNames:
+    - vw.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: vaultwarden
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

vaultwarden/k8s/ingress.yaml

@@ -13,7 +13,7 @@ spec:
         - name: vaultwarden-service
           port: 80
   tls:
-    certResolver: letsencrypt
+    secretName: vaultwarden-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -29,3 +29,5 @@ spec:
       services:
         - name: vaultwarden-service
           port: 80
+  tls:
+    secretName: internal-wildcard-tls

vpn/xui/k8s/certificates.yaml

@@ -0,0 +1,28 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: xray-prod-tls
+  namespace: xui
+spec:
+  secretName: xray-prod-tls
+  dnsNames:
+    - xray.forust.xyz
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: internal-wildcard-tls
+  namespace: xui
+spec:
+  secretName: internal-wildcard-tls
+  dnsNames:
+    - "*.workstation.internal"
+    - "*.gigaforust.internal"
+    - workstation.internal
+    - gigaforust.internal
+  issuerRef:
+    name: internal-ca
+    kind: ClusterIssuer

vpn/xui/k8s/ingress.yaml

@@ -12,6 +12,9 @@ spec:
       services:
         - name: xui-service
           port: 30379
+  tls:
+    secretName: internal-wildcard-tls
+
 ---
 # Public panel access (optional).
 # Realistic, but intentionally disabled: the panel has its own login,
@@ -58,7 +61,7 @@ spec:
         - name: xui-service
           port: 10000
   tls:
-    certResolver: letsencrypt
+    secretName: xray-prod-tls
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -79,3 +82,5 @@ spec:
       services:
         - name: xui-service
           port: 10000
+  tls:
+    secretName: internal-wildcard-tls