chore(deps): update renovate/renovate docker tag to v44.102.0

.gitea/workflows/ci.yaml

@@ -7,10 +7,6 @@ on:
   pull_request:
   workflow_dispatch:
 
-concurrency:
-  group: ci-${{ github.ref }}
-  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
-
 env:
   REGISTRY: gcr.forust.xyz
 
@@ -19,7 +15,7 @@ jobs:
     runs-on: [self-hosted, linux, arch, homelab]
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
+        uses: actions/checkout@v4
 
       - name: Check formatting with Prettier
         shell: bash
@@ -35,24 +31,32 @@ jobs:
             exit 0
           fi
 
-          prettier --check --ignore-unknown "${prettier_files[@]}"
+          docker run --rm \
+            -v "$PWD:/work" \
+            -w /work \
+            node:22-alpine \
+            sh -lc 'npx --yes prettier@3 --check --ignore-unknown "$@"' sh "${prettier_files[@]}"
 
   lint-ruff:
     runs-on: [self-hosted, linux, arch, homelab]
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
+        uses: actions/checkout@v4
 
       - name: Lint Python with Ruff
         shell: bash
         run: |
-          ruff check .
+          docker run --rm \
+            -v "$PWD:/work" \
+            -w /work \
+            ghcr.io/astral-sh/ruff:latest \
+            check .
 
   lint-yaml:
     runs-on: [self-hosted, linux, arch, homelab]
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
+        uses: actions/checkout@v4
 
       - name: Lint YAML syntax
         shell: bash
@@ -68,13 +72,17 @@ jobs:
             exit 0
           fi
 
-          yamllint -c .yamllint "${yaml_files[@]}"
+          docker run --rm \
+            -v "$PWD:/work" \
+            -w /work \
+            cytopia/yamllint:latest \
+            -c .yamllint "${yaml_files[@]}"
 
   lint-dockerfiles:
     runs-on: [self-hosted, linux, arch, homelab]
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
+        uses: actions/checkout@v4
 
       - name: Lint Dockerfiles
         shell: bash
@@ -88,13 +96,18 @@ jobs:
             exit 0
           fi
 
-          hadolint -c .hadolint.yaml "${dockerfiles[@]}"
+          docker run --rm \
+            -v "$PWD:/work" \
+            -w /work \
+            --entrypoint hadolint \
+            hadolint/hadolint:latest-debian \
+            -c .hadolint.yaml "${dockerfiles[@]}"
 
   validate:
     runs-on: [self-hosted, linux, arch, homelab]
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
+        uses: actions/checkout@v4
 
       - name: Validate Kubernetes manifests
         shell: bash
@@ -109,7 +122,10 @@ jobs:
             exit 0
           fi
 
-          kubeconform \
+          docker run --rm \
+            -v "$PWD:/work" \
+            -w /work \
+            ghcr.io/yannh/kubeconform:latest \
             -strict \
             -ignore-missing-schemas \
             -summary \
@@ -123,7 +139,7 @@ jobs:
       services: ${{ steps.services.outputs.services }}
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
+        uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
@@ -214,10 +230,7 @@ jobs:
                 for tag in "${tags[@]}"; do
                   build_args+=(-t "${image}:${tag}")
                 done
-                docker build \
+                docker build "${build_args[@]}" dtek_notif
-                  --cache-from "type=registry,ref=${image}:buildcache" \
-                  --cache-to "type=registry,ref=${image}:buildcache,mode=max" \
-                  "${build_args[@]}" dtek_notif
                 for tag in "${tags[@]}"; do
                   docker push "${image}:${tag}"
                 done
@@ -237,10 +250,7 @@ jobs:
                 for tag in "${tags[@]}"; do
                   build_args+=(-t "${image}:${tag}")
                 done
-                docker build \
+                docker build "${build_args[@]}" errorpages
-                  --cache-from "type=registry,ref=${image}:buildcache" \
-                  --cache-to "type=registry,ref=${image}:buildcache,mode=max" \
-                  "${build_args[@]}" errorpages
                 for tag in "${tags[@]}"; do
                   docker push "${image}:${tag}"
                 done
@@ -270,10 +280,7 @@ jobs:
                   for tag in "${tags[@]}"; do
                     build_args+=(-t "${image}:${tag}")
                   done
-                  docker build \
+                  docker build "${build_args[@]}" "$context"
-                    --cache-from "type=registry,ref=${image}:buildcache" \
-                    --cache-to "type=registry,ref=${image}:buildcache,mode=max" \
-                    "${build_args[@]}" "$context"
                   for tag in "${tags[@]}"; do
                     docker push "${image}:${tag}"
                   done
@@ -302,10 +309,7 @@ jobs:
                   for tag in "${tags[@]}"; do
                     build_args+=(-t "${image}:${tag}")
                   done
-                  docker build \
+                  docker build "${build_args[@]}" -f "homepages/Dockerfile.${service}" homepages
-                    --cache-from "type=registry,ref=${image}:buildcache" \
-                    --cache-to "type=registry,ref=${image}:buildcache,mode=max" \
-                    "${build_args[@]}" -f "homepages/Dockerfile.${service}" homepages
                   for tag in "${tags[@]}"; do
                     docker push "${image}:${tag}"
                   done
@@ -336,10 +340,7 @@ jobs:
                   for tag in "${tags[@]}"; do
                     build_args+=(-t "${image}:${tag}")
                   done
-                  docker build \
+                  docker build "${build_args[@]}" "$context"
-                    --cache-from "type=registry,ref=${image}:buildcache" \
-                    --cache-to "type=registry,ref=${image}:buildcache,mode=max" \
-                    "${build_args[@]}" "$context"
                   for tag in "${tags[@]}"; do
                     docker push "${image}:${tag}"
                   done
@@ -347,3 +348,23 @@ 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@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

@@ -1,9 +1,6 @@
 name: deploy
 
 on:
-  push:
-    branches:
-      - main
   workflow_dispatch:
 
 concurrency:
@@ -22,6 +19,9 @@ 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
@@ -57,170 +57,59 @@ jobs:
           fi
 
           git -C "$repo" fetch origin main
-
-          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
-          }
 
+          # 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
           collect_k8s() {
-            git ls-files -- "$1" \
+            find "$1" -type f \( -name '*.yaml' -o -name '*.yml' \) \
-              | grep -E '\.ya?ml$' \
+              ! -path '*/routing/*' ! -path '*/overlays/*' \
-              | grep -Ev '/routing/|/overlays/' \
+              ! -name 'kustomization.y*ml' ! -name '*.example.y*ml' \
-              | grep -Ev '(^|/)(kustomization\.ya?ml|.*\.example\.ya?ml|.*values\.ya?ml|patch-.*\.ya?ml)$' \
+              ! -name '*values.y*ml' ! -name 'patch-*.y*ml' \
-              | grep -Ev '(^|/)[^/]*secret[^/]*\.ya?ml$' \
               | sort
           }
 
           collect_k8s_inactive() {
-            collect_k8s "$1" \
+            find "$1" -type f \( -name '*.yaml' -o -name '*.yml' \) \
-              | grep -E '(^|/)namespace\.ya?ml$|/routing/'
+              \( -name 'namespace.y*ml' -o -path '*/routing/*' \) \
+              ! -path '*/overlays/*' ! -name '*.example.y*ml' \
+              | sort
           }
 
-          kustomize_overlay() {
+          mapfile -t compose_stacks < <(
-            if [ -f "$1/overlays/prod/kustomization.yaml" ]; then
+            find "$repo" -type f \( -name 'compose.yaml' -o -name 'compose.yml' \) | sort
-              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
           )
 
-          k8s_manifests=()
+          mapfile -t k8s_manifests < <(
-          kustomize_apps=()
+            for kd in $(find "$repo" -type d -name k8s ! -path '*/.git/*' | sort); do
-          for kd_rel in "${k8s_dirs[@]}"; do
+              if [ -f "$kd/active" ]; then
-            kd="$repo/$kd_rel"
+                collect_k8s "$kd"
-            if is_disabled "$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+=("$overlay")
               else
-                while IFS= read -r f; do
+                collect_k8s_inactive "$kd"
-                  [ -n "$f" ] && k8s_manifests+=("$repo/$f")
-                done < <(collect_k8s "$kd_rel" || true)
               fi
-            else
+            done
-              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=client) =="
+          echo "== Validate k8s manifests (kubectl dry-run) =="
           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=()
@@ -241,63 +130,19 @@ jobs:
             echo "  namespaces first: ${ns_files[*]}"
             kubectl apply -f "${ns_files[@]}"
           fi
-          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 --timeout 10m
-          fi
-          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
-            helm upgrade --install loki grafana/loki \
-              --version 7.3.0 \
-              --namespace prometheus \
-              --values "$repo/loki/k8s/loki-values.yaml" \
-              --wait --timeout 10m
-            helm upgrade --install alloy grafana/alloy \
-              --version 1.12.1 \
-              --namespace prometheus \
-              --values "$repo/loki/k8s/alloy-values.yaml" \
-              --wait --timeout 10m
-          fi
-
           if [ "${#other_files[@]}" -gt 0 ]; then
             echo "  resources: ${other_files[*]}"
             kubectl apply "${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
-            echo "  compose: $cf"
+            dir=$(dirname "$cf")
+            if [ -f "$dir/k8s/active" ]; then
+              echo "  skip (k8s-managed): $dir"
+              continue
+            fi
+            echo "  compose: $dir"
             if grep -Eq '^\s+pull_policy:\s*build\b' "$cf"; then
               docker compose -f "$cf" build
               docker compose -f "$cf" push

.gitea/workflows/renovate-ci.yaml

@@ -12,7 +12,7 @@ jobs:
     runs-on: [self-hosted, linux, arch, homelab]
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
+        uses: actions/checkout@v4
 
       - name: Validate Renovate Compose draft
         shell: bash
@@ -48,5 +48,5 @@ jobs:
           docker run --rm \
             -v "$PWD:/work" \
             -w /work \
-            renovate/renovate:44.103.0 \
+            renovate/renovate:44.83.2 \
             renovate-config-validator renovate.json

.gitea/workflows/renovate-run.yaml

@@ -1,69 +0,0 @@
-name: renovate-run
-
-on:
-  workflow_dispatch:
-    inputs:
-      repositories:
-        description: "Repositories to scan (comma-separated)"
-        required: false
-        default: "forust/homelab"
-      log_level:
-        description: "Renovate log level"
-        required: false
-        default: "info"
-        type: choice
-        options:
-          - info
-          - debug
-      dry_run:
-        description: "Plan only, do not open or update PRs"
-        required: false
-        default: false
-        type: boolean
-
-concurrency:
-  group: renovate-run
-  cancel-in-progress: false
-
-jobs:
-  run-renovate:
-    runs-on: [self-hosted, linux, arch, homelab]
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
-
-      - name: Validate Renovate config
-        shell: bash
-        run: |
-          set -euo pipefail
-          docker run --rm \
-            -v "$PWD/renovate/config.js:/opt/renovate/config.js:ro" \
-            -e RENOVATE_CONFIG_FILE=/opt/renovate/config.js \
-            renovate/renovate:44.103.0 \
-            renovate-config-validator
-
-      - name: Run Renovate
-        shell: bash
-        env:
-          RENOVATE_TOKEN: ${{ secrets.RENOVATE_TOKEN }}
-          RENOVATE_GITHUB_COM_TOKEN: ${{ secrets.RENOVATE_GITHUB_COM_TOKEN }}
-          RENOVATE_REPOSITORIES: ${{ inputs.repositories }}
-          RENOVATE_DRY_RUN: ${{ inputs.dry_run && 'full' || '' }}
-          LOG_LEVEL: ${{ inputs.log_level }}
-        run: |
-          set -euo pipefail
-
-          : "${RENOVATE_TOKEN:?missing RENOVATE_TOKEN secret — add a renovate-bot PAT in repo/org Actions secrets}"
-
-          docker run --rm \
-            -v "$PWD/renovate/config.js:/opt/renovate/config.js:ro" \
-            -e RENOVATE_PLATFORM=gitea \
-            -e RENOVATE_ENDPOINT=https://gitea.forust.xyz/api/v1 \
-            -e RENOVATE_TOKEN="$RENOVATE_TOKEN" \
-            -e RENOVATE_GITHUB_COM_TOKEN="${RENOVATE_GITHUB_COM_TOKEN:-}" \
-            -e RENOVATE_REPOSITORIES="${RENOVATE_REPOSITORIES:-forust/homelab}" \
-            -e RENOVATE_DRY_RUN="${RENOVATE_DRY_RUN:-}" \
-            -e RENOVATE_CONFIG_FILE=/opt/renovate/config.js \
-            -e RENOVATE_BASE_DIR=/tmp/renovate \
-            -e LOG_LEVEL="${LOG_LEVEL:-info}" \
-            renovate/renovate:44.103.0

.github/workflows/ci.yaml

@@ -0,0 +1,370 @@
+name: ci
+
+on:
+  push:
+    branches:
+      - "**"
+  pull_request:
+  workflow_dispatch:
+
+env:
+  REGISTRY: gcr.forust.xyz
+
+jobs:
+  lint-prettier:
+    runs-on: [self-hosted, linux, arch, homelab]
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Check formatting with Prettier
+        shell: bash
+        run: |
+          mapfile -t prettier_files < <(
+            git ls-files \
+              | grep -E '\.(md|json|ya?ml|html|css)$' \
+              | grep -Ev '^(\.docs/|\.zed/|errorpages/html/|homepages/(forust_files|xdfnx_files)/)'
+          )
+
+          if [ "${#prettier_files[@]}" -eq 0 ]; then
+            echo "No Prettier-managed files found."
+            exit 0
+          fi
+
+          docker run --rm \
+            -v "$PWD:/work" \
+            -w /work \
+            node:22-alpine \
+            sh -lc 'npx --yes prettier@3 --check --ignore-unknown "$@"' sh "${prettier_files[@]}"
+
+  lint-ruff:
+    runs-on: [self-hosted, linux, arch, homelab]
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Lint Python with Ruff
+        shell: bash
+        run: |
+          docker run --rm \
+            -v "$PWD:/work" \
+            -w /work \
+            ghcr.io/astral-sh/ruff:latest \
+            check .
+
+  lint-yaml:
+    runs-on: [self-hosted, linux, arch, homelab]
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Lint YAML syntax
+        shell: bash
+        run: |
+          mapfile -t yaml_files < <(
+            git ls-files '*.yaml' '*.yml' \
+              ':!node_modules/**' \
+              ':!**/.venv/**'
+          )
+
+          if [ "${#yaml_files[@]}" -eq 0 ]; then
+            echo "No YAML files found."
+            exit 0
+          fi
+
+          docker run --rm \
+            -v "$PWD:/work" \
+            -w /work \
+            cytopia/yamllint:latest \
+            -c .yamllint "${yaml_files[@]}"
+
+  lint-dockerfiles:
+    runs-on: [self-hosted, linux, arch, homelab]
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Lint Dockerfiles
+        shell: bash
+        run: |
+          mapfile -t dockerfiles < <(
+            git ls-files ':(glob)**/Dockerfile' ':(glob)**/Dockerfile.*'
+          )
+
+          if [ "${#dockerfiles[@]}" -eq 0 ]; then
+            echo "No Dockerfiles found."
+            exit 0
+          fi
+
+          docker run --rm \
+            -v "$PWD:/work" \
+            -w /work \
+            --entrypoint hadolint \
+            hadolint/hadolint:latest-debian \
+            -c .hadolint.yaml "${dockerfiles[@]}"
+
+  validate:
+    runs-on: [self-hosted, linux, arch, homelab]
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Validate Kubernetes manifests
+        shell: bash
+        run: |
+          mapfile -t manifests < <(
+            git ls-files ':(glob)**/k8s/**/*.yaml' ':(glob)**/k8s/**/*.yml' \
+              | grep -Ev '(^|/)(kustomization\.ya?ml|.*\.example\.ya?ml|.*values\.ya?ml|patch-.*\.ya?ml)$'
+          )
+
+          if [ "${#manifests[@]}" -eq 0 ]; then
+            echo "No Kubernetes manifests found."
+            exit 0
+          fi
+
+          docker run --rm \
+            -v "$PWD:/work" \
+            -w /work \
+            ghcr.io/yannh/kubeconform:latest \
+            -strict \
+            -ignore-missing-schemas \
+            -summary \
+            "${manifests[@]}"
+
+  build:
+    needs: [lint-prettier, lint-ruff, lint-yaml, lint-dockerfiles, validate]
+    if: github.event_name != 'pull_request' && (github.ref_name == 'main' || github.ref_name == 'dev')
+    runs-on: [self-hosted, linux, arch, homelab]
+    outputs:
+      services: ${{ steps.services.outputs.services }}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Detect changed docker-built services
+        id: services
+        shell: bash
+        run: |
+          base="${{ github.event.before }}"
+          if [ -z "$base" ] || [ "$base" = "0000000000000000000000000000000000000000" ]; then
+            base="$(git rev-list --max-parents=0 HEAD)"
+          fi
+
+          mapfile -t changed_files < <(git diff --name-only "$base" "${GITHUB_SHA}")
+
+          services=()
+
+          add_service() {
+            local name="$1"
+            local seen=0
+            for existing in "${services[@]}"; do
+              if [ "$existing" = "$name" ]; then
+                seen=1
+                break
+              fi
+            done
+            if [ "$seen" -eq 0 ]; then
+              services+=("$name")
+            fi
+          }
+
+          for file in "${changed_files[@]}"; do
+            case "$file" in
+              dtek_notif/*)
+                add_service dtek_notif
+                ;;
+              errorpages/*)
+                add_service errorpages
+                ;;
+              userbot/*)
+                add_service userbot
+                ;;
+              homepages/*)
+                add_service homepages
+                ;;
+              edu_master/phpsessid-bot/*|edu_master/webinar-checker/*|edu_master/compose.yaml)
+                add_service edu_master
+                ;;
+            esac
+          done
+
+          if [ "${#services[@]}" -eq 0 ]; then
+            echo "No docker-built services changed."
+            echo "services=" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+
+          printf '%s\n' "${services[@]}" | tee /tmp/services.txt
+          echo "services=$(paste -sd, /tmp/services.txt)" >> "$GITHUB_OUTPUT"
+
+      - name: Log in to registry
+        if: steps.services.outputs.services != ''
+        shell: bash
+        run: |
+          echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login "${REGISTRY}" \
+            -u "${{ secrets.REGISTRY_USERNAME }}" \
+            --password-stdin
+
+      - name: Build and push changed images
+        if: steps.services.outputs.services != ''
+        shell: bash
+        run: |
+          IFS=, read -r -a services <<< "${{ steps.services.outputs.services }}"
+
+          for service in "${services[@]}"; do
+            case "$service" in
+              dtek_notif)
+                image="${REGISTRY}/forust/dtek-notif"
+                tags=("latest")
+                case "${GITHUB_REF_NAME}" in
+                  main)
+                    tags+=("main" "prod")
+                    ;;
+                  dev)
+                    tags+=("dev")
+                    ;;
+                esac
+                build_args=()
+                for tag in "${tags[@]}"; do
+                  build_args+=(-t "${image}:${tag}")
+                done
+                docker build "${build_args[@]}" dtek_notif
+                for tag in "${tags[@]}"; do
+                  docker push "${image}:${tag}"
+                done
+                ;;
+              errorpages)
+                image="${REGISTRY}/forust/error-pages"
+                tags=("latest")
+                case "${GITHUB_REF_NAME}" in
+                  main)
+                    tags+=("main" "prod")
+                    ;;
+                  dev)
+                    tags+=("dev")
+                    ;;
+                esac
+                build_args=()
+                for tag in "${tags[@]}"; do
+                  build_args+=(-t "${image}:${tag}")
+                done
+                docker build "${build_args[@]}" errorpages
+                for tag in "${tags[@]}"; do
+                  docker push "${image}:${tag}"
+                done
+                ;;
+              userbot)
+                tags=("latest")
+                case "${GITHUB_REF_NAME}" in
+                  main)
+                    tags+=("main" "prod")
+                    ;;
+                  dev)
+                    tags+=("dev")
+                    ;;
+                esac
+                for target in runtime panel; do
+                  case "$target" in
+                    runtime)
+                      context="userbot"
+                      image="${REGISTRY}/forust/userbot"
+                      ;;
+                    panel)
+                      context="userbot/panel"
+                      image="${REGISTRY}/forust/userbot-panel"
+                      ;;
+                  esac
+                  build_args=()
+                  for tag in "${tags[@]}"; do
+                    build_args+=(-t "${image}:${tag}")
+                  done
+                  docker build "${build_args[@]}" "$context"
+                  for tag in "${tags[@]}"; do
+                    docker push "${image}:${tag}"
+                  done
+                done
+                ;;
+              homepages)
+                for service in forust xdfnx; do
+                  case "$service" in
+                    forust)
+                      image="${REGISTRY}/forust/forust-homepage"
+                      ;;
+                    xdfnx)
+                      image="${REGISTRY}/forust/xdfnx-homepage"
+                      ;;
+                  esac
+                  tags=("latest")
+                  case "${GITHUB_REF_NAME}" in
+                    main)
+                      tags+=("main" "prod")
+                      ;;
+                    dev)
+                      tags+=("dev")
+                      ;;
+                  esac
+                  build_args=()
+                  for tag in "${tags[@]}"; do
+                    build_args+=(-t "${image}:${tag}")
+                  done
+                  docker build "${build_args[@]}" -f "homepages/Dockerfile.${service}" homepages
+                  for tag in "${tags[@]}"; do
+                    docker push "${image}:${tag}"
+                  done
+                done
+                ;;
+              edu_master)
+                for service in session-keeper webinar-checker; do
+                  case "$service" in
+                    session-keeper)
+                      context="edu_master/phpsessid-bot"
+                      image="${REGISTRY}/forust/session-keeper"
+                      ;;
+                    webinar-checker)
+                      context="edu_master/webinar-checker"
+                      image="${REGISTRY}/forust/webinar-checker"
+                      ;;
+                  esac
+                  tags=("latest")
+                  case "${GITHUB_REF_NAME}" in
+                    main)
+                      tags+=("main" "prod")
+                      ;;
+                    dev)
+                      tags+=("dev")
+                      ;;
+                  esac
+                  build_args=()
+                  for tag in "${tags[@]}"; do
+                    build_args+=(-t "${image}:${tag}")
+                  done
+                  docker build "${build_args[@]}" "$context"
+                  for tag in "${tags[@]}"; do
+                    docker push "${image}:${tag}"
+                  done
+                done
+                ;;
+            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@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

.github/workflows/deploy.yaml

@@ -0,0 +1,161 @@
+name: deploy
+
+on:
+  workflow_dispatch:
+
+concurrency:
+  group: deploy-main
+  cancel-in-progress: false
+
+jobs:
+  redeploy:
+    runs-on: [self-hosted, linux, arch, homelab, prod]
+    steps:
+      - name: Redeploy workstation
+        shell: bash
+        env:
+          DEPLOY_HOST: ${{ secrets.DEPLOY_HOST }}
+          DEPLOY_PORT: ${{ secrets.DEPLOY_PORT }}
+          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: ${{ vars.APPLY_PRUNE }}
+        run: |
+          set -euo pipefail
+
+          : "${DEPLOY_HOST:?missing DEPLOY_HOST}"
+          : "${DEPLOY_USER:?missing DEPLOY_USER}"
+          : "${DEPLOY_KEY:?missing DEPLOY_SSH_KEY}"
+
+          deploy_port="${DEPLOY_PORT:-22}"
+          deploy_path="${DEPLOY_PATH:-/srv/homelab}"
+
+          ssh_key="$RUNNER_TEMP/deploy_key"
+          mkdir -p "$RUNNER_TEMP"
+          printf '%s\n' "$DEPLOY_KEY" > "$ssh_key"
+          chmod 600 "$ssh_key"
+
+          ssh_opts=(
+            -i "$ssh_key"
+            -p "$deploy_port"
+            -o BatchMode=yes
+            -o StrictHostKeyChecking=accept-new
+          )
+
+          ssh "${ssh_opts[@]}" "${DEPLOY_USER}@${DEPLOY_HOST}" \
+            "DEPLOY_PATH=$(printf '%q' \"$deploy_path\") APPLY_PRUNE=$(printf '%q' \"${APPLY_PRUNE:-false}\") bash -se" <<'EOF'
+          set -euo pipefail
+
+          repo="${DEPLOY_PATH:-/srv/homelab}"
+
+          if [ ! -d "$repo/.git" ]; then
+            echo "Repository not found at $repo"
+            exit 1
+          fi
+
+          git -C "$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
+          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' \
+              | 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
+          }
+
+          mapfile -t compose_stacks < <(
+            find "$repo" -type f \( -name 'compose.yaml' -o -name 'compose.yml' \) | sort
+          )
+
+          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"
+              else
+                collect_k8s_inactive "$kd"
+              fi
+            done
+          )
+
+          echo "== Validate compose stacks =="
+          for cf in "${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) =="
+          for m in "${k8s_manifests[@]}"; do
+            echo "  apply --dry-run=client $m"
+            kubectl apply --dry-run=client -f "$m" >/dev/null
+          done
+
+          echo "== Applying Kubernetes manifests =="
+          ns_files=()
+          other_files=()
+          for m in "${k8s_manifests[@]}"; do
+            case "$m" in
+              */namespace.y?ml) ns_files+=("$m") ;;
+              *) other_files+=("$m") ;;
+            esac
+          done
+
+          prune_opts=()
+          if [ "${APPLY_PRUNE:-false}" = "true" ]; then
+            prune_opts=(--prune -l app.kubernetes.io/managed-by=homelab-deploy)
+          fi
+
+          if [ "${#ns_files[@]}" -gt 0 ]; then
+            echo "  namespaces first: ${ns_files[*]}"
+            kubectl apply -f "${ns_files[@]}"
+          fi
+          if [ -f "$repo/prometheus-stack/k8s/active" ]; then
+            echo "== Upgrading kube-prometheus-stack =="
+            helm upgrade --install prometheus-stack prometheus-community/kube-prometheus-stack \
+              --namespace prometheus \
+              --version 86.2.3 \
+              --values "$repo/prometheus-stack/k8s/grafana-values.yaml" \
+              --wait
+          fi
+
+          if [ "${#other_files[@]}" -gt 0 ]; then
+            echo "  resources: ${other_files[*]}"
+            kubectl apply "${prune_opts[@]}" -f "${other_files[@]}"
+          fi
+
+          echo "== Redeploying docker compose stacks =="
+          for cf in "${compose_stacks[@]}"; do
+            dir=$(dirname "$cf")
+            if [ -f "$dir/k8s/active" ]; then
+              echo "  skip (k8s-managed): $dir"
+              continue
+            fi
+            echo "  compose: $dir"
+            if grep -Eq '^\s+pull_policy:\s*build\b' "$cf"; then
+              docker compose -f "$cf" build
+              docker compose -f "$cf" push
+            fi
+            docker compose -f "$cf" up -d --pull always --remove-orphans
+          done
+          EOF

.gitignore

@@ -104,10 +104,6 @@ temp/*
 # kubernetes
 */k8s/*secret*
 !*/k8s/*secret*.example
-**/k8s/*secret*
-!**/k8s/*secret*.example
-# Local-only tweaks, not for upstream
-prometheus-stack/k8s/grafana-values.yaml
 traefik/k8s/local-tls.yaml
 converters/k8s/config.yaml
 convertx/k8s/config.yaml

adguardhome/k8s/adguard.yaml

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

adguardhome/k8s/certificate.yaml

@@ -1,12 +0,0 @@
-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(`dns.forust.xyz`)
+    - match: Host(`adguard.forust.xyz`) || Host(`dns.forust.xyz`)
       kind: Rule
       middlewares:
         - name: crowdsec-bouncer
@@ -15,13 +15,13 @@ spec:
       services:
         - name: adguard-service
           port: 3000
-    - match: (Host(`dns.forust.xyz`)) && PathPrefix(`/dns-query`)
+    - match: (Host(`adguard.forust.xyz`) || Host(`dns.forust.xyz`)) && PathPrefix(`/dns-query`)
       kind: Rule
       services:
         - name: adguard-service
           port: 3000
   tls:
-    secretName: adguard-certs
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -42,5 +42,3 @@ spec:
       services:
         - name: adguard-service
           port: 3000
-  tls:
-    secretName: internal-wildcard-tls

adguardhome/k8s/internal-certificate.yaml

@@ -1,15 +0,0 @@
-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/authentik.yaml

@@ -41,7 +41,7 @@ spec:
     spec:
       containers:
         - name: authentik-server
-          image: ghcr.io/goauthentik/server:2026.8.3
+          image: ghcr.io/goauthentik/server:2026.8.2
           args: ["server"]
           envFrom:
             - configMapRef:
@@ -75,7 +75,7 @@ spec:
     spec:
       containers:
         - name: authentik-worker
-          image: ghcr.io/goauthentik/server:2026.8.3
+          image: ghcr.io/goauthentik/server:2026.8.2
           args: ["worker"]
           securityContext:
             runAsUser: 0

authentik/k8s/certificates.yaml

@@ -1,28 +0,0 @@
-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:
-    secretName: authentik-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -32,5 +32,3 @@ spec:
       services:
         - name: authentik-server-service
           port: 9000
-  tls:
-    secretName: internal-wildcard-tls

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

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

cert-manager/k8s/clusterissuer.yaml

@@ -1,29 +0,0 @@
-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

@@ -1,30 +0,0 @@
------BEGIN CERTIFICATE-----
-MIIFFjCCAv6gAwIBAgIUetKpTfEDOn2985FFMu6G26itT+wwDQYJKoZIhvcNAQEN
-BQAwIzEhMB8GA1UEAxMYaG9tZWxhYiBpbnRlcm5hbCByb290IENBMB4XDTI2MDky
-MzEyNDA0N1oXDTM2MDkyMDEyNDA0N1owIzEhMB8GA1UEAxMYaG9tZWxhYiBpbnRl
-cm5hbCByb290IENBMIICIjANBgkqhkiG9w0BAQEFAAOCAg8AMIICCgKCAgEAvmNP
-ZCOoD8NtNuYJKVXBlTPjX7D7sJCSK5neH7ZbYV5+lmUlEErY8Mik7j37V5k5NfpF
-Ig85pOjP7RckTPz5V6ek3yaN40s4AL053sN5ZPauDVYjalaEHTgj5sEMqlLACQWI
-yZmJOZspZykae8dIpQnqCoFpRT4FurJ78v4a0ylnFVLMQn/lyCHedwTjkEdtYWYr
-ccJy8vQwqkzs/rWvEH1lDqZhennLOrmcCjfonG7D/pruMn4z+6E28p4+ejkRrI6x
-luak3KnpT1XMeHtgU21hiRGaMDBchHMFgAhnY1qosymKenXvfTZItwgjZbwa1hJI
-GAiDm+jQDKMjzRZ3rH6Xfc0auUcykNz73PpNu1NGm78nndXwCXcXn1LFKNQJ+r1U
-sJiyAmUZmXVn4aM4OMf2F38k7wTYIKg7nRGaUkNeKDlNkjA4HvgWw+jwO1KmdHQ/
-mOem1rosDWHRK01wg+Gga9mQCnhNhxglg3t/UeSic6uOaRsvaz4qkzHq8MbCujVz
-DpKQjqdikYOAXZOs4KlBLWrS7NaK4NzfSD02pBUErh54ruJfY/bWz9KyXzBD/lQZ
-VUTKyvUVB0bkVHEdf1jJmX3H4IZRQSF5JPqOBotW6bJI5fEGNBvj9Zxy4nm2WWGz
-yyP3uWsQz8U/Wdx9nXZLHInTZBsvgLYtKUAWA30CAwEAAaNCMEAwDgYDVR0PAQH/
-BAQDAgKkMA8GA1UdEwEB/wQFMAMBAf8wHQYDVR0OBBYEFEkKm2rxPaK6+O9WD80z
-BLC6F9QsMA0GCSqGSIb3DQEBDQUAA4ICAQAnFyHz97Umf5VIu+dKTJid7C73VugJ
-TIar/xJBs/4CxP+znBxhJjXygRoyIfzoVGWcB2ZSL//vL78Qlts79K/Imc9a4RFF
-wMvCxsRXAEQ4TpeWi3ophPNcs4rhsP+gQKQFtnyKP9519bqpfxp0bTqwOV2o18fn
-za7rlQViiEnNV58j7CVoM9+mJvVVfBEX1Km+GyJL9GadzbIQ7FxClVJZefCbft93
-zHVk9gDOw8ys1XGSR2OUCyCLinXO6mqS16CmBb2MAKXq/YyH7E0N8iotAPGtfA8V
-M/0ddy947rY0xCrtECfWwvGQpJS7NRv/Z9b2jCfXrI5LXmL2nfQRg0y9GE4Vjwr+
-WxtGU5jOeFt0jQ+xRzcgG0Op+qK3x55l5LSo2hOcOVYbiHxcHEJFgwNi1ADeBFwb
-q/HdysfURSOghqjIpMMAUabBp+DBUg2EUF7pIaUqbdqExFYcr9EYisEMiNsmKmN+
-8ZbcOeerFKDQj+t/R0bFXa7UBn2UWsjI8zlR74aa2kLDXwtyz/XlO/FlYm66eBFo
-2/eYUSeU+S4ej+wUAs/dvjF7f190/DUQGuwOTlLTahqWDztmhCk7qzbECu56CwKT
-E5Ect2P72UleYwdblkVOVd352AmiwEzdOaziIRrPh8uenEknH6JBYPO3mjk7cCg+
-GPGcNIBctjdXhg==
------END CERTIFICATE-----

cert-manager/k8s/internal-ca.yaml

@@ -1,33 +0,0 @@
-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

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

checkmk/k8s/certificates.yaml

@@ -1,28 +0,0 @@
-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:
-    secretName: checkmk-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRouteTCP
@@ -48,5 +48,3 @@ spec:
       services:
         - name: checkmk-service
           port: 5000
-  tls:
-    secretName: internal-wildcard-tls

cloudflared/k8s/.gitignore

@@ -1 +0,0 @@
-secret.yaml

cloudflared/k8s/deployment.yaml

@@ -1,37 +0,0 @@
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: cloudflared
-  labels:
-    app: cloudflared
-spec:
-  replicas: 1
-  selector:
-    matchLabels:
-      app: cloudflared
-  template:
-    metadata:
-      labels:
-        app: cloudflared
-    spec:
-      containers:
-        - name: cloudflared
-          image: cloudflare/cloudflared:2026.9.1
-          imagePullPolicy: IfNotPresent
-          args:
-            - tunnel
-            - --no-autoupdate
-            - run
-          env:
-            - name: TUNNEL_TOKEN
-              valueFrom:
-                secretKeyRef:
-                  name: cloudflared-secrets
-                  key: TUNNEL_TOKEN
-          resources:
-            requests:
-              memory: "32Mi"
-              cpu: "30m"
-            limits:
-              memory: "128Mi"
-              cpu: "200m"

cloudflared/k8s/secret.yaml.example

@@ -1,7 +0,0 @@
-apiVersion: v1
-kind: Secret
-metadata:
-  name: cloudflared-secrets
-type: Opaque
-stringData:
-  TUNNEL_TOKEN: your_tunnel_token_here

converters/k8s/certificates.yaml

@@ -1,42 +0,0 @@
-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:
-    secretName: convertx-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -31,9 +31,6 @@ spec:
       services:
         - name: convertx-service
           port: 3000
-  tls:
-    secretName: internal-wildcard-tls
-
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -50,7 +47,7 @@ spec:
         - name: bentopdf-service
           port: 8080
   tls:
-    secretName: bentopdf-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -66,5 +63,3 @@ spec:
       services:
         - name: bentopdf-service
           port: 8080
-  tls:
-    secretName: internal-wildcard-tls

crowdsec/k8s/crowdsec-values.yaml

@@ -1,102 +1,57 @@
 container_runtime: containerd
-
 agent:
-  acquisition: []
-  additionalAcquisition:
-    - labels:
-        type: traefik
-      limit: 1000
-      query: |
-        {namespace="traefik"}
-      source: loki
-      url: http://loki.prometheus.svc.cluster.local:3100/
-      wait_for_ready: 30s
   env:
     - name: COLLECTIONS
-      value: crowdsecurity/traefik crowdsecurity/base-http-scenarios
+      value: "crowdsecurity/traefik crowdsecurity/base-http-scenarios"
     - name: DISABLE_COLLECTIONS
-      value: crowdsecurity/sshd
+      value: "crowdsecurity/linux crowdsecurity/sshd"
-  metrics:
+
-    enabled: true
+  acquisition:
-    serviceMonitor:
+    - namespace: traefik
-      additionalLabels:
+      podName: "*traefik*"
-        release: prometheus-stack
+      program: traefik
-      enabled: true
+      poll_without_inotify: true
-  # Static machine identity: agent pods mount pre-created LAPI credentials
+
-  # (Secret crowdsec-agent-credentials, key local_api_credentials.yaml)
-  # at the exact path the agent entrypoint expects. Together with the
-  # patched register-init (enforced by janitor-cronjob.yaml) the agent
-  # never calls `cscli lapi register` in steady state, so pod names,
-  # restarts and reboots can no longer break it.
-  extraVolumes:
-    - name: static-creds
-      secret:
-        secretName: crowdsec-agent-credentials
-        items:
-          - key: local_api_credentials.yaml
-            path: local_api_credentials.yaml
-  extraVolumeMounts:
-    - name: static-creds
-      mountPath: /tmp_config/local_api_credentials.yaml
-      subPath: local_api_credentials.yaml
-      readOnly: true
   resources:
-    limits:
-      cpu: 200m
-      memory: 500Mi
     requests:
       cpu: 50m
       memory: 100Mi
-
+    limits:
-config:
+      cpu: 200m
-  parsers:
+      memory: 500Mi
-    s02-enrich:
-      mobile-whitelist.yaml: |
-        name: forust/mobile-whitelist
-        description: "Whitelist SWAN/4ka mobile network"
-        whitelist:
-          reason: "Mobile IP whitelist"
-          cidr:
-            - "84.245.64.0/18"
-
-  postoverflows:
-    s01-whitelist:
-      home-dynamic-ip.yaml: |
-        name: forust/home-dynamic-ip
-        description: "Whitelist home dynamic IP"
-        whitelist:
-          reason: "Home dynamic IP"
-          expression:
-            - evt.Overflow.Alert.Source.IP in LookupHost("ddns.forust.xyz")
 
 lapi:
   env:
     - name: COLLECTIONS
-      value: crowdsecurity/traefik crowdsecurity/base-http-scenarios
+      value: "crowdsecurity/traefik crowdsecurity/base-http-scenarios"
     - name: DISABLE_COLLECTIONS
-      value: crowdsecurity/linux crowdsecurity/sshd
+      value: "crowdsecurity/linux crowdsecurity/sshd"
-  metrics:
+  service:
-    enabled: true
+    type: ClusterIP
-    serviceMonitor:
-      additionalLabels:
-        release: prometheus-stack
-      enabled: true
   persistentVolume:
-    config:
-      enabled: true
-      size: 100Mi
-      storageClassName: local-path-retain
     data:
       enabled: true
-      size: 1Gi
       storageClassName: local-path-retain
+      size: 1Gi
+    config:
+      enabled: true
+      storageClassName: local-path-retain
+      size: 100Mi
+  storeLAPICscliCredentialsInSecret: true
   resources:
-    limits:
-      cpu: 400m
-      memory: 500Mi
     requests:
       cpu: 50m
       memory: 150Mi
-  service:
+    limits:
-    type: ClusterIP
+      cpu: 400m
-  storeLAPICscliCredentialsInSecret: true
+      memory: 500Mi
+
+metrics:
+  enabled: true
+  serviceMonitor:
+    additionalLabels:
+      release: prometheus-stack
+    enabled: true
+    interval: 30s
+    scrapeTimeout: 10s
+    namespace: prometheus

crowdsec/k8s/grafana-dashboards.yaml

@@ -1,32 +0,0 @@
-apiVersion: v1
-data:
-  crowdsec-overview.json: "{\n  \"__inputs\": [\n    {\n      \"name\": \"DS_PROMETHEUS\",\n      \"label\": \"Prometheus\",\n      \"description\": \"\",\n      \"type\": \"datasource\",\n      \"pluginId\": \"prometheus\",\n      \"pluginName\": \"Prometheus\"\n    }\n  ],\n  \"__requires\": [\n    {\n      \"type\": \"grafana\",\n      \"id\": \"grafana\",\n      \"name\": \"Grafana\",\n      \"version\": \"8.1.2\"\n    },\n    {\n      \"type\": \"panel\",\n      \"id\": \"graph\",\n      \"name\": \"Graph (old)\",\n      \"version\": \"\"\n    },\n    {\n      \"type\": \"datasource\",\n      \"id\": \"prometheus\",\n      \"name\": \"Prometheus\",\n      \"version\": \"1.0.0\"\n    },\n    {\n      \"type\": \"panel\",\n      \"id\": \"stat\",\n      \"name\": \"Stat\",\n      \"version\": \"\"\n    },\n    {\n      \"type\": \"panel\",\n      \"id\": \"timeseries\",\n      \"name\": \"Time series\",\n      \"version\": \"\"\n    }\n  ],\n  \"annotations\": {\n    \"list\": [\n      {\n        \"builtIn\": 1,\n        \"datasource\": \"-- Grafana --\",\n        \"enable\": true,\n        \"hide\": true,\n        \"iconColor\": \"rgba(0, 211, 255, 1)\",\n        \"name\": \"Annotations & Alerts\",\n        \"target\": {\n          \"limit\": 100,\n          \"matchAny\": false,\n          \"tags\": [],\n          \"type\": \"dashboard\"\n        },\n        \"type\": \"dashboard\"\n      }\n    ]\n  },\n  \"editable\": true,\n  \"gnetId\": null,\n  \"graphTooltip\": 0,\n  \"id\": null,\n  \"links\": [],\n  \"panels\": [\n    {\n      \"collapsed\": false,\n      \"datasource\": null,\n      \"gridPos\": {\n        \"h\": 1,\n        \"w\": 24,\n        \"x\": 0,\n        \"y\": 0\n      },\n      \"id\": 24,\n      \"panels\": [],\n      \"title\": \"Summary\",\n      \"type\": \"row\"\n    },\n    {\n      \"cacheTimeout\": null,\n      \"datasource\": \"${DS_PROMETHEUS}\",\n      \"fieldConfig\": {\n        \"defaults\": {\n          \"color\": {\n            \"mode\": \"thresholds\"\n          },\n          \"mappings\": [\n            {\n              \"options\": {\n                \"match\": \"null\",\n                \"result\": {\n                  \"text\": \"N/A\"\n                }\n              },\n              \"type\": \"special\"\n            }\n          ],\n          \"thresholds\": {\n            \"mode\": \"absolute\",\n            \"steps\": [\n              {\n                \"color\": \"#E02F44\",\n                \"value\": null\n              },\n              {\n                \"color\": \"#E02F44\",\n                \"value\": 10\n              },\n              {\n                \"color\": \"#299c46\",\n                \"value\": 10\n              }\n            ]\n          },\n          \"unit\": \"none\"\n        },\n        \"overrides\": []\n      },\n      \"gridPos\": {\n        \"h\": 8,\n        \"w\": 6,\n        \"x\": 0,\n        \"y\": 1\n      },\n      \"id\": 2,\n      \"interval\": null,\n      \"links\": [],\n      \"maxDataPoints\": 100,\n      \"options\": {\n        \"colorMode\": \"background\",\n        \"graphMode\": \"none\",\n        \"justifyMode\": \"auto\",\n        \"orientation\": \"horizontal\",\n        \"reduceOptions\": {\n          \"calcs\": [\n            \"lastNotNull\"\n          ],\n          \"fields\": \"\",\n          \"values\": false\n        },\n        \"text\": {},\n        \"textMode\": \"auto\"\n      },\n      \"pluginVersion\": \"8.1.2\",\n      \"targets\": [\n        {\n          \"exemplar\": true,\n          \"expr\": \"count(cs_info)\",\n          \"interval\": \"\",\n          \"legendFormat\": \"\",\n          \"refId\": \"A\"\n        }\n      ],\n      \"timeFrom\": null,\n      \"timeShift\": null,\n      \"title\": \"Running Crowdsec\",\n      \"transparent\": true,\n      \"type\": \"stat\"\n    },\n    {\n      \"aliasColors\": {},\n      \"bars\": false,\n      \"dashLength\": 10,\n      \"dashes\": false,\n      \"datasource\": \"${DS_PROMETHEUS}\",\n      \"decimals\": 1,\n      \"fieldConfig\": {\n        \"defaults\": {\n          \"links\": []\n        },\n        \"overrides\": []\n      },\n      \"fill\": 1,\n      \"fillGradient\": 0,\n      \"gridPos\": {\n        \"h\": 8,\n        \"w\": 18,\n        \"x\": 6,\n        \"y\": 1\n      },\n      \"hiddenSeries\": false,\n      \"id\": 8,\n      \"legend\": {\n        \"alignAsTable\": true,\n        \"avg\": false,\n        \"current\": false,\n        \"max\": false,\n        \"min\": false,\n        \"rightSide\": true,\n        \"show\": true,\n        \"sort\": \"total\",\n        \"sortDesc\": true,\n        \"total\": true,\n        \"values\": true\n      },\n      \"lines\": true,\n      \"linewidth\": 1,\n      \"nullPointMode\": \"null\",\n      \"options\": {\n        \"alertThreshold\": true\n      },\n      \"percentage\": false,\n      \"pluginVersion\": \"8.1.2\",\n      \"pointradius\": 2,\n      \"points\": false,\n      \"renLine truncated
-kind: ConfigMap
-metadata:
-  labels:
-    app.kubernetes.io/managed-by: manual
-    grafana_dashboard: "1"
-  name: crowdsec-crowdsec-overview
-  namespace: prometheus
----
-apiVersion: v1
-data:
-  crowdsec-lapi-metrics.json: "{\n  \"__inputs\": [\n    {\n      \"name\": \"DS_PROMETHEUS\",\n      \"label\": \"Prometheus\",\n      \"description\": \"\",\n      \"type\": \"datasource\",\n      \"pluginId\": \"prometheus\",\n      \"pluginName\": \"Prometheus\"\n    }\n  ],\n  \"__requires\": [\n    {\n      \"type\": \"panel\",\n      \"id\": \"bargauge\",\n      \"name\": \"Bar gauge\",\n      \"version\": \"\"\n    },\n    {\n      \"type\": \"grafana\",\n      \"id\": \"grafana\",\n      \"name\": \"Grafana\",\n      \"version\": \"8.1.2\"\n    },\n    {\n      \"type\": \"datasource\",\n      \"id\": \"prometheus\",\n      \"name\": \"Prometheus\",\n      \"version\": \"1.0.0\"\n    }\n  ],\n  \"annotations\": {\n    \"list\": [\n      {\n        \"builtIn\": 1,\n        \"datasource\": \"-- Grafana --\",\n        \"enable\": true,\n        \"hide\": true,\n        \"iconColor\": \"rgba(0, 211, 255, 1)\",\n        \"name\": \"Annotations & Alerts\",\n        \"target\": {\n          \"limit\": 100,\n          \"matchAny\": false,\n          \"tags\": [],\n          \"type\": \"dashboard\"\n        },\n        \"type\": \"dashboard\"\n      }\n    ]\n  },\n  \"editable\": true,\n  \"gnetId\": null,\n  \"graphTooltip\": 0,\n  \"id\": null,\n  \"iteration\": 1655915193937,\n  \"links\": [],\n  \"panels\": [\n    {\n      \"collapsed\": false,\n      \"datasource\": null,\n      \"gridPos\": {\n        \"h\": 1,\n        \"w\": 24,\n        \"x\": 0,\n        \"y\": 0\n      },\n      \"id\": 10,\n      \"panels\": [],\n      \"title\": \"Agents\",\n      \"type\": \"row\"\n    },\n    {\n      \"datasource\": \"${DS_PROMETHEUS}\",\n      \"fieldConfig\": {\n        \"defaults\": {\n          \"color\": {\n            \"mode\": \"thresholds\"\n          },\n          \"mappings\": [],\n          \"thresholds\": {\n            \"mode\": \"absolute\",\n            \"steps\": [\n              {\n                \"color\": \"green\",\n                \"value\": null\n              },\n              {\n                \"color\": \"red\",\n                \"value\": 80\n              }\n            ]\n          }\n        },\n        \"overrides\": []\n      },\n      \"gridPos\": {\n        \"h\": 8,\n        \"w\": 12,\n        \"x\": 0,\n        \"y\": 1\n      },\n      \"id\": 2,\n      \"options\": {\n        \"displayMode\": \"gradient\",\n        \"orientation\": \"vertical\",\n        \"reduceOptions\": {\n          \"calcs\": [\n            \"lastNotNull\"\n          ],\n          \"fields\": \"\",\n          \"values\": false\n        },\n        \"showUnfilled\": false,\n        \"text\": {}\n      },\n      \"pluginVersion\": \"8.1.2\",\n      \"repeat\": \"query0\",\n      \"repeatDirection\": \"h\",\n      \"targets\": [\n        {\n          \"exemplar\": false,\n          \"expr\": \"sum(rate(cs_lapi_request_duration_seconds_bucket{endpoint=\\\"/v1/watchers/login\\\", instance=\\\"$lapi\\\"}[$__rate_interval])) by (le)\",\n          \"format\": \"heatmap\",\n          \"interval\": \"\",\n          \"legendFormat\": \"{{le}}\",\n          \"refId\": \"A\"\n        }\n      ],\n      \"title\": \"Agents Login\",\n      \"type\": \"heatmap\"\n    },\n    {\n      \"datasource\": \"${DS_PROMETHEUS}\",\n      \"fieldConfig\": {\n        \"defaults\": {\n          \"color\": {\n            \"mode\": \"thresholds\"\n          },\n          \"mappings\": [],\n          \"thresholds\": {\n            \"mode\": \"absolute\",\n            \"steps\": [\n              {\n                \"color\": \"green\",\n                \"value\": null\n              }\n            ]\n          },\n          \"unit\": \"none\"\n        },\n        \"overrides\": []\n      },\n      \"gridPos\": {\n        \"h\": 8,\n        \"w\": 12,\n        \"x\": 12,\n        \"y\": 1\n      },\n      \"id\": 6,\n      \"options\": {\n        \"displayMode\": \"gradient\",\n        \"orientation\": \"auto\",\n        \"reduceOptions\": {\n          \"calcs\": [\n            \"lastNotNull\"\n          ],\n          \"fields\": \"\",\n          \"values\": false\n        },\n        \"showUnfilled\": false,\n        \"text\": {}\n      },\n      \"pluginVersion\": \"8.1.2\",\n      \"targets\": [\n        {\n          \"exemplar\": true,\n          \"expr\": \"sum(rate(cs_lapi_request_duration_seconds_bucket{endpoint=\\\"/v1/watchers/login\\\"}[$__rate_interval])) by (le)\",\n          \"format\": \"heatmap\",\n          \"interval\": \"\",\n          \"legendFormat\": \"{{le}}\",\n          \"refId\": \"A\"\n        }\n      ],\n      \"title\": \"Heartbeat\",\n      \"type\": \"heatmap\"\n    },\n    {\n      \"collapsed\": false,\n      \"datasource\": null,\n      \"gridPos\": {\n        \"h\": 1,\n        \"w\": 24,\n        \"x\": 0,\n        \"y\": 9\n      },\n      \"id\": 12,\n      \"panels\": [],\n      \"title\": \"Decisions\",\n      \"type\": \"row\"\n    },\n    {\n      \"datasource\": \"${DS_PROMETHEUS}\",\n  Line truncated
-kind: ConfigMap
-metadata:
-  labels:
-    app.kubernetes.io/managed-by: manual
-    grafana_dashboard: "1"
-  name: crowdsec-crowdsec-lapi-metrics
-  namespace: prometheus
----
-apiVersion: v1
-data:
-  crowdsec-insight.json: "{\n  \"__inputs\": [\n    {\n      \"name\": \"DS_PROMETHEUS\",\n      \"label\": \"Prometheus\",\n      \"description\": \"\",\n      \"type\": \"datasource\",\n      \"pluginId\": \"prometheus\",\n      \"pluginName\": \"Prometheus\"\n    }\n  ],\n  \"__requires\": [\n    {\n      \"type\": \"panel\",\n      \"id\": \"bargauge\",\n      \"name\": \"Bar gauge\",\n      \"version\": \"\"\n    },\n    {\n      \"type\": \"panel\",\n      \"id\": \"gauge\",\n      \"name\": \"Gauge\",\n      \"version\": \"\"\n    },\n    {\n      \"type\": \"grafana\",\n      \"id\": \"grafana\",\n      \"name\": \"Grafana\",\n      \"version\": \"8.1.2\"\n    },\n    {\n      \"type\": \"datasource\",\n      \"id\": \"prometheus\",\n      \"name\": \"Prometheus\",\n      \"version\": \"1.0.0\"\n    },\n    {\n      \"type\": \"panel\",\n      \"id\": \"stat\",\n      \"name\": \"Stat\",\n      \"version\": \"\"\n    }\n  ],\n  \"annotations\": {\n    \"list\": [\n      {\n        \"builtIn\": 1,\n        \"datasource\": \"-- Grafana --\",\n        \"enable\": true,\n        \"hide\": true,\n        \"iconColor\": \"rgba(0, 211, 255, 1)\",\n        \"name\": \"Annotations & Alerts\",\n        \"target\": {\n          \"limit\": 100,\n          \"matchAny\": false,\n          \"tags\": [],\n          \"type\": \"dashboard\"\n        },\n        \"type\": \"dashboard\"\n      }\n    ]\n  },\n  \"editable\": true,\n  \"gnetId\": null,\n  \"graphTooltip\": 0,\n  \"id\": null,\n  \"iteration\": 1655915159751,\n  \"links\": [],\n  \"panels\": [\n    {\n      \"collapsed\": true,\n      \"datasource\": null,\n      \"gridPos\": {\n        \"h\": 1,\n        \"w\": 24,\n        \"x\": 0,\n        \"y\": 0\n      },\n      \"id\": 22,\n      \"panels\": [\n        {\n          \"cacheTimeout\": null,\n          \"datasource\": \"${DS_PROMETHEUS}\",\n          \"fieldConfig\": {\n            \"defaults\": {\n              \"color\": {\n                \"mode\": \"thresholds\"\n              },\n              \"mappings\": [\n                {\n                  \"options\": {\n                    \"match\": \"null\",\n                    \"result\": {\n                      \"text\": \"N/A\"\n                    }\n                  },\n                  \"type\": \"special\"\n                }\n              ],\n              \"thresholds\": {\n                \"mode\": \"absolute\",\n                \"steps\": [\n                  {\n                    \"color\": \"green\",\n                    \"value\": null\n                  },\n                  {\n                    \"color\": \"red\",\n                    \"value\": 80\n                  }\n                ]\n              },\n              \"unit\": \"dateTimeAsIso\"\n            },\n            \"overrides\": []\n          },\n          \"gridPos\": {\n            \"h\": 9,\n            \"w\": 5,\n            \"x\": 2,\n            \"y\": 1\n          },\n          \"id\": 2,\n          \"interval\": null,\n          \"links\": [],\n          \"maxDataPoints\": 100,\n          \"options\": {\n            \"colorMode\": \"none\",\n            \"graphMode\": \"none\",\n            \"justifyMode\": \"auto\",\n            \"orientation\": \"horizontal\",\n            \"reduceOptions\": {\n              \"calcs\": [\n                \"lastNotNull\"\n              ],\n              \"fields\": \"\",\n              \"values\": false\n            },\n            \"text\": {},\n            \"textMode\": \"auto\"\n          },\n          \"pluginVersion\": \"8.1.2\",\n          \"targets\": [\n            {\n              \"exemplar\": true,\n              \"expr\": \"(process_start_time_seconds{instance=\\\"$instance\\\"})*1000\",\n              \"interval\": \"\",\n              \"legendFormat\": \"{{instance}}\",\n              \"refId\": \"A\"\n            }\n          ],\n          \"timeFrom\": null,\n          \"timeShift\": null,\n          \"title\": \"Up since\",\n          \"type\": \"stat\"\n        },\n        {\n          \"datasource\": \"${DS_PROMETHEUS}\",\n          \"fieldConfig\": {\n            \"defaults\": {\n              \"displayName\": \"\",\n              \"mappings\": [],\n              \"thresholds\": {\n                \"mode\": \"absolute\",\n                \"steps\": [\n                  {\n                    \"color\": \"green\",\n                    \"value\": null\n                  }\n                ]\n              },\n              \"unit\": \"decbytes\"\n            },\n            \"overrides\": []\n          },\n          \"gridPos\": {\n            \"h\": 9,\n            \"w\": 5,\n            \"x\": 7,\n            \"y\": 1\n          },\n          \"id\": 4,\n          \"options\": {\n            \"orientation\": \"auto\",\n            \"reduceOptions\": {\n              \"calcs\": [\n                \"mean\"\n              ],\n              \"fields\": \"\",\n              \"values\": false\n            },\Line truncated
-kind: ConfigMap
-metadata:
-  labels:
-    app.kubernetes.io/managed-by: manual
-    grafana_dashboard: "1"
-  name: crowdsec-crowdsec-insight
-  namespace: prometheus

crowdsec/k8s/janitor-cronjob.yaml

@@ -1,195 +0,0 @@
-# CrowdSec self-healing: static machine identity + enforcement loops.
-#
-# Problem it fixes: the chart's agent init container runs
-#   `cscli lapi register --machine "$POD_NAME" ...`
-# unconditionally. Credentials live in an emptyDir, the machine row lives
-# in LAPI's persistent DB. Any init re-run for an already-known pod name
-# (kubelet restart, node reboot) dies with
-#   403 Forbidden: user '<pod>' already exist
-# and the DaemonSet pod sticks in Init forever. Every DS restart also
-# leaves an orphan machine row that is never cleaned.
-#
-# Design (name-independent):
-#   * Agent identity is a STATIC machine `crowdsec-agent-workstation`
-#     whose password lives in Secret `crowdsec-agent-credentials`
-#     (created once, manually - like all other secrets in this repo).
-#     The secret is mounted into agent pods at
-#     /tmp_config/local_api_credentials.yaml (see extraVolumeMounts in
-#     crowdsec-values.yaml), which is exactly the path the agent's main
-#     container copies into place at startup.
-#   * The DS init command is patched (strategic merge, by container name)
-#     to SKIP registration when that file exists, keeping the legacy
-#     register path only as fallback. Detection marker in the patched
-#     command: `[ -s /tmp_config`.
-#   * This CronJob enforces the desired state hourly, so recovery is
-#     automatic even after `helm upgrade` reverts the DS patch or the
-#     LAPI database is wiped:
-#       1. patch DS init if it still has the unconditional register
-#          (no-op otherwise - no restart churn);
-#       2. prune machines with no heartbeat for 2h (orphan hygiene);
-#       3. ensure the static machine exists, recreating it with the
-#          Secret password if missing (agent retry loops reconnect
-#          on their own - same name + same password);
-#       4. prune bouncer entries idle for 30d.
-#
-# Manual apply (crowdsec/k8s is NOT managed by deploy.yaml):
-#   kubectl apply -f crowdsec/k8s/janitor-cronjob.yaml
-# Force a run:
-#   kubectl create job -n crowdsec --from=cronjob/crowdsec-janitor janitor-now
-#
-# Helm upgrades: the janitor's strategic patch puts the DS field under
-# the `kubectl-patch` field manager, so a plain `helm upgrade` FAILS
-# with an SSA conflict on initContainers[].command. Procedure:
-#   1. revert init to chart state (kills the conflict):
-#        helm template crowdsec crowdsec/crowdsec --version <ver> \
-#          -n crowdsec -f crowdsec/k8s/crowdsec-values.yaml > /tmp/r.yaml
-#        python3 -c "import yaml,json; ..." # build revert patch from
-#        the rendered DaemonSet init command, then
-#        kubectl patch ds crowdsec-agent -n crowdsec \
-#          --type strategic -p "\$(cat /tmp/revert_patch.json)"
-#   2. helm upgrade --install crowdsec ... (no --force needed)
-#   3. janitor-now right away (upgrade reverts init; new pods would
-#      sit in Init until the next hourly run otherwise).
-#
-# One-time bootstrap (order matters):
-#   1. Create Secret + static machine (see commands in chat).
-#   2. Apply this file, trigger janitor-now, wait for agent 1/1.
-#   3. One-time orphan cleanup:
-#        kubectl exec -n crowdsec deploy/crowdsec-lapi -- \
-#          cscli machines prune --duration 1h --force
-#   4. Only then `helm upgrade` crowdsec with the extraVolumes values.
-#      Upgrade reverts the DS patch; trigger janitor-now right after it
-#      (otherwise new pods sit in Init until the next hourly run, then
-#      self-heal anyway).
-#
-# Password rotation: update the Secret, delete the machine
-# (`cscli machines delete crowdsec-agent-workstation`), trigger
-# janitor-now (recreates it), then `kubectl rollout restart
-# ds/crowdsec-agent -n crowdsec` (agent reads the file at startup only).
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: crowdsec-janitor
-  namespace: crowdsec
-  labels:
-    app.kubernetes.io/part-of: crowdsec
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: Role
-metadata:
-  name: crowdsec-janitor
-  namespace: crowdsec
-  labels:
-    app.kubernetes.io/part-of: crowdsec
-rules:
-  - apiGroups: [""]
-    resources: ["pods"]
-    verbs: ["get", "list"]
-  - apiGroups: [""]
-    resources: ["pods/exec"]
-    verbs: ["create"]
-  - apiGroups: ["apps"]
-    resources: ["daemonsets"]
-    verbs: ["get", "patch"]
-  # `kubectl exec deploy/<name>` resolves deploy -> replicaset -> pod,
-  # which needs read access to these (exec itself is pods/exec above).
-  - apiGroups: ["apps"]
-    resources: ["deployments", "replicasets"]
-    verbs: ["get", "list"]
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: RoleBinding
-metadata:
-  name: crowdsec-janitor
-  namespace: crowdsec
-  labels:
-    app.kubernetes.io/part-of: crowdsec
-subjects:
-  - kind: ServiceAccount
-    name: crowdsec-janitor
-    namespace: crowdsec
-roleRef:
-  kind: Role
-  name: crowdsec-janitor
-  apiGroup: rbac.authorization.k8s.io
----
-apiVersion: batch/v1
-kind: CronJob
-metadata:
-  name: crowdsec-janitor
-  namespace: crowdsec
-  labels:
-    app.kubernetes.io/part-of: crowdsec
-spec:
-  schedule: "17 * * * *"
-  concurrencyPolicy: Forbid
-  successfulJobsHistoryLimit: 3
-  failedJobsHistoryLimit: 3
-  jobTemplate:
-    spec:
-      activeDeadlineSeconds: 300
-      template:
-        metadata:
-          labels:
-            app.kubernetes.io/part-of: crowdsec
-        spec:
-          serviceAccountName: crowdsec-janitor
-          restartPolicy: OnFailure
-          containers:
-            - name: janitor
-              # Same image the chart itself uses for registration jobs;
-              # IfNotPresent so it works while the node is offline
-              # (layer cached from the chart install).
-              image: alpine/kubectl:latest
-              imagePullPolicy: IfNotPresent
-              env:
-                - name: AGENT_PASSWORD
-                  valueFrom:
-                    secretKeyRef:
-                      name: crowdsec-agent-credentials
-                      key: password
-              command:
-                - /bin/sh
-                - -c
-                - |
-                  set -eu
-                  LAPI_EXEC="kubectl exec -n crowdsec deploy/crowdsec-lapi --"
-                  echo "== 1. enforce patched agent init =="
-                  CUR=$(kubectl get ds crowdsec-agent -n crowdsec \
-                    -o jsonpath='{.spec.template.spec.initContainers[0].command[2]}')
-                  case "$CUR" in
-                    *'-s /tmp_config'*)
-                      echo "init already patched"
-                      ;;
-                    *)
-                      echo "patching init"
-                      WAIT='until nc "$LAPI_HOST" "$LAPI_PORT" -z'
-                      WAIT="$WAIT; do echo waiting for lapi to start; sleep 5; done"
-                      LINK='ln -s /staging/etc/crowdsec /etc/crowdsec'
-                      REG='cscli lapi register --machine "$USERNAME"'
-                      REG="$REG -u \"\$LAPI_URL\" --token \"\$REGISTRATION_TOKEN\""
-                      CREDS=/tmp_config/local_api_credentials.yaml
-                      CMD="$WAIT; $LINK; [ -s $CREDS ] || {"
-                      CMD="$CMD $REG && cp"
-                      CMD="$CMD /etc/crowdsec/local_api_credentials.yaml $CREDS; }"
-                      ESC=$(printf '%s' "$CMD" | sed 's/"/\\"/g')
-                      PATCH='{"spec":{"template":{"spec":{"initContainers":'
-                      PATCH=$PATCH'[{"name":"wait-for-lapi-and-register",'
-                      PATCH=$PATCH'"command":["sh","-c","'$ESC'"]}]}}}}'
-                      kubectl patch ds crowdsec-agent -n crowdsec \
-                        --type strategic -p "$PATCH"
-                      ;;
-                  esac
-                  echo "== 2. prune orphan machines (no heartbeat for 2h) =="
-                  $LAPI_EXEC cscli machines prune --duration 2h --force
-                  echo "== 3. ensure static machine exists =="
-                  if $LAPI_EXEC cscli machines inspect \
-                    crowdsec-agent-workstation >/dev/null 2>&1; then
-                    echo "static machine present"
-                  else
-                    echo "recreating static machine"
-                    $LAPI_EXEC cscli machines add crowdsec-agent-workstation \
-                      --password "$AGENT_PASSWORD" --force
-                  fi
-                  echo "== 4. prune stale bouncers (no pull for 30d) =="
-                  $LAPI_EXEC cscli bouncers prune -d 720h --force

crowdsec/k8s/network-policy.yaml

@@ -25,10 +25,3 @@ spec:
       ports:
         - protocol: TCP
           port: 8080
-    - from:
-        - namespaceSelector:
-            matchLabels:
-              kubernetes.io/metadata.name: prometheus
-      ports:
-        - protocol: TCP
-          port: 6060

dockmon/k8s/certificates.yaml

@@ -1,28 +0,0 @@
-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:
-    secretName: dockmon-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -43,5 +43,3 @@ 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:
-    secretName: downtify-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -33,5 +33,3 @@ spec:
       services:
         - name: downtify-service
           port: 8000
-  tls:
-    secretName: internal-wildcard-tls

edu_master/PLAYWRIGHT_VERSION

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

edu_master/compose.yaml

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

edu_master/k8s/alerts.yaml

@@ -1,77 +0,0 @@
-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

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

edu_master/k8s/secrets.yaml.example

@@ -21,8 +21,6 @@ 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

@@ -1,15 +0,0 @@
-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

@@ -1,16 +0,0 @@
-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

@@ -47,10 +47,6 @@ 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

@@ -2,11 +2,8 @@ FROM python:3.11-slim
 
 WORKDIR /app
 
-# renovate: datasource=pypi depName=playwright versioning=pep440
+# Install dependencies
-ARG PLAYWRIGHT_VERSION=1.56.0
+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"
-
-# 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

@@ -1,15 +1,12 @@
-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
@@ -51,106 +48,6 @@ 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'
@@ -700,66 +597,59 @@ 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 asyncio.timeout(60):
+        async with async_playwright() as p:
-            async with async_playwright() as p:
+            browser = await p.chromium.connect(PLAYWRIGHT_WS)
-                browser = await asyncio.wait_for(p.chromium.connect(PLAYWRIGHT_WS), timeout=15)
+            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()
+
                 try:
-                    context_browser = await browser.new_context(user_agent=USER_AGENT)
+                    await page.goto(DIARY_URL, wait_until='domcontentloaded')
-                    await context_browser.add_cookies(
+                    await page.wait_for_selector('table.calendar', timeout=10000)
-                        [{'name': 'PHPSESSID', 'value': phpsessid, 'domain': 'edu.edu.vn.ua', 'path': '/'}]
+                    await page.wait_for_timeout(1500)
-                    )
-                    page = await context_browser.new_page()
 
-                    try:
+                    table_html = await page.evaluate("""
-                        await asyncio.wait_for(page.goto(DIARY_URL, wait_until='domcontentloaded'), timeout=30)
+                        () => {
-                        await page.wait_for_selector('table.calendar', timeout=10000)
+                            const t = document.querySelector('table.calendar');
-                        await page.wait_for_timeout(1500)
+                            return t ? t.outerHTML : null;
-
+                        }
-                        table_html = await page.evaluate("""
+                    """)
-                            () => {
+                    if not table_html:
-                                const t = document.querySelector('table.calendar');
+                        logger.error('table.calendar not found in DOM')
-                                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):
+                    # Debug: save HTML for troubleshooting
-                            await asyncio.wait_for(page.close(), timeout=5)
+                    with contextlib.suppress(Exception), open('/tmp/diary_debug.html', 'w', encoding='utf-8') as f:  # noqa: S108
-                        with contextlib.suppress(Exception):
+                        f.write(table_html)
-                            await asyncio.wait_for(context_browser.close(), timeout=5)
+
+                    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 page.close()
-                        await asyncio.wait_for(browser.close(), timeout=5)
+                    await context_browser.close()
-    except TimeoutError:
+            finally:
-        logger.error('Diary fetch timed out (60s)')
+                await browser.close()
-        return None
     except Exception as e:
         logger.error(f'Playwright error in diary fetch: {e}')
         return None
@@ -1041,55 +931,48 @@ 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 asyncio.timeout(60):
+        async with async_playwright() as p:
-            async with async_playwright() as p:
+            browser = await p.chromium.connect(PLAYWRIGHT_WS)
-                browser = await asyncio.wait_for(p.chromium.connect(PLAYWRIGHT_WS), timeout=15)
+            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()
+
                 try:
-                    context_browser = await browser.new_context(user_agent=USER_AGENT)
+                    await page.goto(SCHEDULE_URL, wait_until='domcontentloaded')
-                    await context_browser.add_cookies(
+                    await page.wait_for_selector('table.schedule-table', timeout=10000)
-                        [{'name': 'PHPSESSID', 'value': phpsessid, 'domain': 'edu.edu.vn.ua', 'path': '/'}]
+                    await page.wait_for_timeout(1500)
-                    )
-                    page = await context_browser.new_page()
 
-                    try:
+                    table_html = await page.evaluate("""
-                        await asyncio.wait_for(page.goto(SCHEDULE_URL, wait_until='domcontentloaded'), timeout=30)
+                        () => {
-                        await page.wait_for_selector('table.schedule-table', timeout=10000)
+                            const t = document.querySelector('table.schedule-table');
-                        await page.wait_for_timeout(1500)
+                            return t ? t.outerHTML : null;
-
+                        }
-                        table_html = await page.evaluate("""
+                    """)
-                            () => {
+                    if not table_html:
-                                const t = document.querySelector('table.schedule-table');
+                        logger.error('table.schedule-table not found in DOM')
-                                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
-                    finally:
+
-                        with contextlib.suppress(Exception):
+                    debug_path = os.path.join(tempfile.gettempdir(), 'schedule_debug.html')
-                            await asyncio.wait_for(page.close(), timeout=5)
+                    with contextlib.suppress(Exception), open(debug_path, 'w', encoding='utf-8') as f:
-                        with contextlib.suppress(Exception):
+                        f.write(table_html)
-                            await asyncio.wait_for(context_browser.close(), timeout=5)
+
+                    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 page.close()
-                        await asyncio.wait_for(browser.close(), timeout=5)
+                    await context_browser.close()
-    except TimeoutError:
+            finally:
-        logger.error('Schedule fetch timed out (60s)')
+                await browser.close()
-        return None
     except Exception as e:
         logger.error(f'Playwright error in schedule fetch: {e}')
         return None
@@ -1602,13 +1485,10 @@ 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:
@@ -1622,88 +1502,78 @@ async def check_webinars_job(context: ContextTypes.DEFAULT_TYPE):
     content = ''
 
     try:
-        async with asyncio.timeout(90):
+        async with async_playwright() as p:
-            async with async_playwright() as p:
+            # Connect to remote Playwright service
-                # Connect to remote Playwright service
+            browser = await p.chromium.connect(PLAYWRIGHT_WS)
-                browser = await asyncio.wait_for(p.chromium.connect(PLAYWRIGHT_WS), timeout=15)
+
+            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()
 
                 try:
-                    # Create browser context with user agent
+                    # Navigate to webinar page
-                    context_browser = await browser.new_context(user_agent=USER_AGENT)
+                    await page.goto(WEBINAR_URL, wait_until='domcontentloaded')
 
-                    # Add PHPSESSID cookie
+                    # Wait for the table to load
-                    await context_browser.add_cookies(
+                    await page.wait_for_selector('#meetings table', timeout=10000)
-                        [{'name': 'PHPSESSID', 'value': phpsessid, 'domain': 'edu.edu.vn.ua', 'path': '/'}]
+                    await page.wait_for_timeout(2000)
-                    )
 
-                    # Create new page
+                    # Get page content
-                    page = await context_browser.new_page()
+                    content = await page.content()
 
-                    try:
+                    # Check if "no webinar" message is present
-                        # Navigate to webinar page
+                    if NO_WEBINAR_MARKER not in content:
-                        await asyncio.wait_for(page.goto(WEBINAR_URL, wait_until='domcontentloaded'), timeout=30)
+                        logger.info('!!! WEBINAR FOUND !!!')
 
-                        # Wait for the table to load
+                        # Extract webinar details from table rows
-                        await page.wait_for_selector('#meetings table', timeout=10000)
+                        rows = page.locator('#meetings table tbody tr')
-                        await page.wait_for_timeout(2000)
+                        count = await rows.count()
 
-                        # Get page content
+                        for i in range(count):
-                        content = await page.content()
+                            row = rows.nth(i)
+                            text = await row.inner_text()
 
-                        # Check if "no webinar" message is present
+                            if NO_WEBINAR_MARKER not in text:
-                        if NO_WEBINAR_MARKER not in content:
+                                # Extract name (topic) from first column
-                            logger.info('!!! WEBINAR FOUND !!!')
+                                name_elem = row.locator('td').nth(0)
+                                name = await name_elem.inner_text()
+                                name = name.strip()
 
-                            # Extract webinar details from table rows
+                                # Extract join URL from fourth column
-                            rows = page.locator('#meetings table tbody tr')
+                                url_elem = row.locator('td').nth(3).locator('a[href*="/webinar/join/"]').first
-                            count = await rows.count()
+                                url = await url_elem.get_attribute('href')
 
-                            for i in range(count):
+                                if name and url:
-                                row = rows.nth(i)
+                                    current_webinars.append({'name': name, 'url': url, 'text': text.strip()})
-                                text = await row.inner_text()
+                                    logger.info(f'Found webinar: {name} -> {url}')
+                    else:
+                        logger.info('No webinars found (expected message present)')
 
-                                if NO_WEBINAR_MARKER not in text:
+                except Exception as e:
-                                    # Extract name (topic) from first column
+                    logger.error(f'Error checking page: {e}. Saving content for debug.')
-                                    name_elem = row.locator('td').nth(0)
+                    # If page content is available, save it on error
-                                    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)
-
-                finally:
                     with contextlib.suppress(Exception):
-                        await asyncio.wait_for(browser.close(), timeout=5)
+                        if page and not content:
+                            content = await page.content()
+
+                    return None
+                finally:
+                    await page.close()
+                    await context_browser.close()
+
+            finally:
+                await browser.close()
 
-    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) ---
@@ -1767,7 +1637,6 @@ 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)
 
 
@@ -1811,8 +1680,6 @@ 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

@@ -1,29 +0,0 @@
-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: gitea/gitea:1.27.3
+          image: docker.gitea.com/gitea:1.27.3
           envFrom:
             - configMapRef:
                 name: gitea-config

gitea/k8s/ingress.yaml

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

glance/k8s/certificates.yaml

@@ -1,29 +0,0 @@
-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:
-    secretName: glance-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -35,9 +35,6 @@ spec:
       services:
         - name: glance-service
           port: 8080
-  tls:
-    secretName: internal-wildcard-tls
-
 ---
 apiVersion: traefik.io/v1alpha1
 kind: Middleware

headscale/k8s/routing/certificates.yaml

@@ -1,41 +0,0 @@
-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:
-    secretName: headscale-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -64,7 +64,7 @@ spec:
         - name: headplane-external
           port: 3000
   tls:
-    secretName: headplane-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -90,9 +90,6 @@ spec:
       services:
         - name: headscale-server-external
           port: 9090
-  tls:
-    secretName: internal-wildcard-tls
-
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -113,5 +110,3 @@ spec:
       services:
         - name: headplane-external
           port: 3000
-  tls:
-    secretName: internal-wildcard-tls

homepages/k8s/certificates.yaml

@@ -1,42 +0,0 @@
-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:
-    secretName: forust-homepage-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -34,9 +34,6 @@ spec:
       services:
         - name: forust-homepage-service
           port: 80
-  tls:
-    secretName: internal-wildcard-tls
-
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -56,7 +53,7 @@ spec:
         - name: xdfnx-homepage-service
           port: 80
   tls:
-    secretName: xdfnx-homepage-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -72,5 +69,3 @@ 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:
-    secretName: kener-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -32,5 +32,3 @@ spec:
       services:
         - name: kener-service
           port: 3000
-  tls:
-    secretName: internal-wildcard-tls

loki/k8s/alloy-values.yaml

@@ -1,57 +0,0 @@
-# Pinned chart: grafana/alloy 1.12.1 (app v1.19.2).
-# Install (deferred to deploy task, namespace prometheus):
-#   helm upgrade --install alloy grafana/alloy --version 1.12.1 \
-#     --namespace prometheus --values loki/k8s/alloy-values.yaml --wait
-# DaemonSet ships k8s pod logs (API-tailed, no hostPath mounts) to Loki.
-# Scope phase 1: k8s only, compose leftovers out.
-
-controller:
-  type: daemonset
-  resources:
-    requests:
-      memory: "128Mi"
-      cpu: "50m"
-    limits:
-      memory: "512Mi"
-      cpu: "500m"
-
-image:
-  tag: "v1.19.2"
-
-alloy:
-  configMap:
-    create: true
-    content: |
-      discovery.kubernetes "pods" {
-        role = "pod"
-      }
-
-      discovery.relabel "pods" {
-        targets = discovery.kubernetes.pods.targets
-
-        rule {
-          source_labels = ["__meta_kubernetes_namespace"]
-          target_label  = "namespace"
-        }
-
-        rule {
-          source_labels = ["__meta_kubernetes_pod_name"]
-          target_label  = "pod"
-        }
-
-        rule {
-          source_labels = ["__meta_kubernetes_pod_container_name"]
-          target_label  = "container"
-        }
-      }
-
-      loki.source.kubernetes "pods" {
-        targets    = discovery.relabel.pods.output
-        forward_to = [loki.write.default.receiver]
-      }
-
-      loki.write "default" {
-        endpoint {
-          url = "http://loki-gateway.prometheus.svc.cluster.local/loki/api/v1/push"
-        }
-      }

loki/k8s/loki-values.yaml

@@ -1,97 +0,0 @@
-# Pinned chart: grafana/loki 7.3.0 (app 3.6.12).
-# Install (deferred to deploy task, namespace prometheus):
-#   helm upgrade --install loki grafana/loki --version 7.3.0 \
-#     --namespace prometheus --values loki/k8s/loki-values.yaml --wait
-# SingleBinary, filesystem storage on local-path-retain, 14d retention.
-# No IngressRoute: Loki is cluster-internal, queried via Grafana datasource.
-
-deploymentMode: SingleBinary
-
-loki:
-  # Multitenancy off: single-node homelab, gateway + Alloy + Grafana talk to one tenant.
-  auth_enabled: false
-  image:
-    tag: "3.6.12"
-  commonConfig:
-    # Single replica: default RF=3 would require 3 ingesters and fail all writes.
-    replication_factor: 1
-  storage:
-    type: filesystem
-  schemaConfig:
-    configs:
-      - from: "2024-04-01"
-        store: tsdb
-        object_store: filesystem
-        schema: v13
-        index:
-          prefix: index_
-          period: 24h
-  compactor:
-    retention_enabled: true
-    delete_request_store: filesystem
-  limits_config:
-    retention_period: 336h
-  rulerConfig:
-    wal:
-      dir: /var/loki/ruler-wal
-    storage:
-      type: local
-      local:
-        directory: /var/loki/rules
-
-singleBinary:
-  replicas: 1
-  persistence:
-    enabled: true
-    size: 20Gi
-    storageClass: local-path-retain
-  resources:
-    requests:
-      memory: "512Mi"
-      cpu: "200m"
-    limits:
-      memory: "2Gi"
-      cpu: "1000m"
-
-# Zeroed: unused in SingleBinary mode (chart validation requires it).
-write:
-  replicas: 0
-read:
-  replicas: 0
-backend:
-  replicas: 0
-
-gateway:
-  replicas: 1
-  resources:
-    requests:
-      memory: "64Mi"
-      cpu: "50m"
-    limits:
-      memory: "256Mi"
-      cpu: "300m"
-
-monitoring:
-  serviceMonitor:
-    enabled: true
-    labels:
-      release: prometheus-stack
-    interval: 15s
-  rules:
-    enabled: true
-    namespace: prometheus
-    labels:
-      release: prometheus-stack
-
-# Disabled: memcached caches don't fit a memory-tight single node.
-# SingleBinary works without them (slower repeated queries, fine at homelab scale).
-resultsCache:
-  enabled: false
-chunksCache:
-  enabled: false
-
-# Disabled: synthetic canary traffic + helm test pod, noise on a single node.
-lokiCanary:
-  enabled: false
-test:
-  enabled: false

metube/k8s/certificates.yaml

@@ -1,28 +0,0 @@
-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:
-    secretName: metube-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -31,5 +31,3 @@ spec:
       services:
         - name: metube-service
           port: 8081
-  tls:
-    secretName: internal-wildcard-tls

n8n/compose.yaml

@@ -1,6 +1,6 @@
 services:
   n8n:
-    image: docker.n8n.io/n8nio/n8n:2.40.3
+    image: docker.n8n.io/n8nio/n8n:2.40.2
     container_name: n8n
     restart: unless-stopped
     environment:

n8n/k8s/ingress.yaml

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

n8n/k8s/internal-certificate.yaml

@@ -1,15 +0,0 @@
-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

n8n/k8s/n8n.yaml

@@ -27,7 +27,7 @@ spec:
     spec:
       containers:
         - name: n8n
-          image: docker.n8n.io/n8nio/n8n:2.40.3
+          image: docker.n8n.io/n8nio/n8n:2.40.2
           envFrom:
             - configMapRef:
                 name: n8n-config

netronome/k8s/certificates.yaml

@@ -1,28 +0,0 @@
-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:
-    secretName: netronome-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -32,5 +32,3 @@ spec:
       services:
         - name: netronome-service
           port: 7575
-  tls:
-    secretName: internal-wildcard-tls

nextcloud/k8s/routing/certificates.yaml

@@ -1,28 +0,0 @@
-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:
-    secretName: nextcloud-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -38,29 +38,26 @@ spec:
       services:
         - name: nextcloud-apache
           port: 11000
-  # ---
+# ---
-  # Nextcloud AIO
+# Nextcloud AIO
-  # apiVersion: traefik.io/v1alpha1
+# apiVersion: traefik.io/v1alpha1
-  # kind: IngressRoute
+# kind: IngressRoute
-  # metadata:
+# metadata:
-  #   name: naio-prod
+#   name: naio-prod
-  #   namespace: nextcloud
+#   namespace: nextcloud
-  # spec:
+# spec:
-  #   entryPoints:
+#   entryPoints:
-  # - websecure
+# - websecure
-  # routes:
+# routes:
-  #   - match: Host(`naio.forust.xyz`)
+#   - match: Host(`naio.forust.xyz`)
-  #     kind: Rule
+#     kind: Rule
-  #     services:
+#     services:
-  #       - name: nextcloud-aio
+#       - name: nextcloud-aio
-  #         port: 8888
+#         port: 8888
-  #         scheme: https
+#         scheme: https
-  #         serversTransport: insecure-transport
+#         serversTransport: insecure-transport
-  # tls:
+# tls:
-  #   certResolver: letsencrypt
+#   certResolver: letsencrypt
-  tls:
-    secretName: internal-wildcard-tls
-
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -78,5 +75,3 @@ spec:
           port: 8888
           scheme: https
           serversTransport: insecure-transport
-  tls:
-    secretName: internal-wildcard-tls

portainer/k8s/certificates.yaml

@@ -1,28 +0,0 @@
-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:
-    secretName: portainer-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -32,5 +32,3 @@ spec:
       services:
         - name: portainer-service
           port: 9000
-  tls:
-    secretName: internal-wildcard-tls

postgres/.env.example

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

postgres/README.md

@@ -1,22 +1,23 @@
 # Shared PostgreSQL
 
-This directory contains the shared PostgreSQL 17 deployment for Authentik,
+This directory contains a PostgreSQL 15 deployment draft for Authentik, Gitea,
-Gitea, Netronome, and Statuspage. It creates one database and one login role
+Netronome, and Penpot. It creates one database and one login role per service;
-per service. Per-service standalone databases were removed after the
+it does not migrate existing data or change application connection settings.
-migration (Sep 2026); Penpot stays on its own compose PostgreSQL (archived,
-not part of the shared instance).
 
 ## Compatibility baseline
 
-| Service    | Current application | Shared PostgreSQL 17                   |
+| Service   | Current application | Current standalone PostgreSQL | Common PostgreSQL 15                                                                 |
-| ---------- | ------------------- | -------------------------------------- |
+| --------- | ------------------- | ----------------------------: | ------------------------------------------------------------------------------------ |
-| Authentik  | 2025.10.x           | Supported (Authentik requires 14+)     |
+| Authentik | 2025.10.2           |                            15 | Supported (Authentik requires 14+)                                                   |
-| Gitea      | 1.27.3              | Supported (Gitea requires 12+)         |
+| Gitea     | 1.27.3              |                            14 | Supported (Gitea requires 12+)                                                       |
-| Netronome  | 0.14.0              | Supported (upstream's example uses 17) |
+| Netronome | 0.14.0              |                            17 | Validate in staging; upstream's example uses 17 but no 17-only feature is documented |
-| Statuspage | custom              | Supported                              |
+| Penpot    | 2.17.2              |                            15 | Supported by the official deployment                                                 |
 
-A major-version change must use a logical dump/restore; changing only the
+PostgreSQL 15 is the conservative common major. A major-version downgrade or
-image tag while keeping a data directory is not supported.
+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.
 
 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="$password" \
     <<'SQL'
@@ -25,4 +25,3 @@ create_role_and_database authentik authentik "$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

@@ -60,23 +60,11 @@ 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:17.11-alpine
+    image: postgres:15.19-alpine
     container_name: homelab-postgres
     restart: unless-stopped
     env_file:

prometheus-stack/alertmanager.yaml

@@ -1,10 +1,5 @@
 route:
   receiver: default
-  routes:
-    - receiver: "null"
-      matchers:
-        - alertname="Watchdog"
 
 receivers:
   - name: default
-  - name: "null"

prometheus-stack/k8s/alertmanager-config.example.yaml

@@ -1,6 +1,3 @@
-templates:
-  - "/etc/alertmanager/config/telegram.tmpl"
-
 route:
   receiver: telegram
   group_by:
@@ -10,10 +7,10 @@ route:
   group_interval: 5m
   repeat_interval: 12h
   routes:
-    - receiver: "null"
+    - receiver: null
       matchers:
         - alertname="InfoInhibitor"
-    - receiver: "null"
+    - receiver: null
       matchers:
         - alertname="Watchdog"
 
@@ -38,5 +35,4 @@ receivers:
         chat_id: REPLACE_WITH_TELEGRAM_CHAT_ID
         parse_mode: HTML
         send_resolved: true
-        message: '{{ template "telegram.forust.message" . }}'
+  - name: null
-  - name: "null"

prometheus-stack/k8s/alertmanager-telegram.tmpl

@@ -1,44 +0,0 @@
-{{- define "telegram.forust.message" -}}
-{{- $statusEmoji := "🚨" -}}
-{{- if ne .Status "firing" -}}{{- $statusEmoji = "✅" -}}{{- end -}}
-{{- $count := len .Alerts.Firing -}}
-{{- if eq .Status "resolved" -}}{{- $count = len .Alerts.Resolved -}}{{- end -}}
-{{ $statusEmoji }} <b>{{ .Status | toUpper }} ({{ $count }})</b>
-{{- range .Alerts }}
-
-<b>{{ .Labels.alertname }}</b>
-{{- $sev := .Labels.severity }}
-{{- if eq $sev "critical" }} 🔥 critical
-{{- else if eq $sev "warning" }} ⚠️ warning
-{{- else if eq $sev "info" }} ℹ️ info
-{{- else if $sev }} • {{ $sev }}
-{{- end }}
-{{- if .Annotations.description }}
-
-<i>{{ .Annotations.description }}</i>
-{{- end }}
-{{- if .Labels.namespace }}
-📦 Namespace: <code>{{ .Labels.namespace }}</code>
-{{- end }}
-{{- if .Labels.pod }}
-📦 Pod: <code>{{ .Labels.pod }}</code>
-{{- end }}
-{{- if .Labels.container }}
-🐳 Container: <code>{{ .Labels.container }}</code>
-{{- end }}
-{{- if .Labels.node }}
-🖥 Node: <code>{{ .Labels.node }}</code>
-{{- end }}
-{{- if .Labels.instance }}
-🖥 Instance: <code>{{ .Labels.instance }}</code>
-{{- end }}
-{{- if .Labels.job }}
-🔧 Job: <code>{{ .Labels.job }}</code>
-{{- end }}
-{{- if eq .Status "firing" }}
-🕐 Since: <code>{{ .StartsAt | date "2006-01-02 15:04 MST" }}</code>
-{{- else }}
-🕐 Resolved: <code>{{ .EndsAt | date "2006-01-02 15:04 MST" }}</code>
-{{- end }}
-{{- end }}
-{{- end }}

prometheus-stack/k8s/alerts.yaml

@@ -66,21 +66,3 @@ spec:
           annotations:
             summary: "Node memory pressure"
             description: "Node {{ $labels.instance }} has used more than 90% of memory for 15 minutes."
-
-        - alert: LokiDown
-          expr: kube_statefulset_status_replicas_unavailable{statefulset="loki"} > 0 or kube_deployment_status_replicas_unavailable{deployment="loki-gateway"} > 0
-          for: 10m
-          labels:
-            severity: warning
-          annotations:
-            summary: "Loki is down"
-            description: "Loki in namespace {{ $labels.namespace }} has unavailable replicas for more than 10 minutes. Logs are not queryable."
-
-        - alert: AlloyDown
-          expr: kube_daemonset_status_number_unavailable{daemonset="alloy"} > 0
-          for: 10m
-          labels:
-            severity: warning
-          annotations:
-            summary: "Alloy is down"
-            description: "Alloy DaemonSet in namespace {{ $labels.namespace }} has {{ $value }} unavailable pods for more than 10 minutes. Pod logs are not being shipped to Loki."

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

@@ -1,43 +0,0 @@
-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

@@ -1,28 +0,0 @@
-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/grafana-values.yaml

@@ -14,11 +14,8 @@ grafana:
 
   persistence:
     enabled: true
-    # Matches live PVC (10Gi/local-path). Retain migration is a separate task
+    storageClassName: local-path-retain
-    # with data migration (see storage-audit doc); do NOT change SC/size here
+    size: 20Gi
-    # without migrating, helm upgrade fails on immutable PVC fields.
-    storageClassName: local-path
-    size: 10Gi
 
   ingress:
     enabled: false
@@ -26,12 +23,6 @@ grafana:
   service:
     port: 80
 
-  additionalDataSources:
-    - name: Loki
-      type: loki
-      url: http://loki-gateway.prometheus.svc.cluster.local
-      access: proxy
-
 prometheus:
   prometheusSpec:
     retention: 60d
@@ -39,8 +30,7 @@ prometheus:
     storageSpec:
       volumeClaimTemplate:
         spec:
-          # Matches live PVC, see note on grafana.persistence above.
+          storageClassName: "local-path-retain"
-          storageClassName: "local-path"
           accessModes:
             - ReadWriteOnce
           resources:
@@ -58,13 +48,12 @@ alertmanager:
     storage:
       volumeClaimTemplate:
         spec:
-          # Matches live PVC (20Gi), see note on grafana.persistence above.
+          storageClassName: local-path-retain
-          storageClassName: local-path
           accessModes:
             - ReadWriteOnce
           resources:
             requests:
-              storage: 20Gi
+              storage: 10Gi
 
 defaultRules:
   disabled:

prometheus-stack/k8s/ingress.yaml

@@ -12,11 +12,14 @@ spec:
       middlewares:
         - name: crowdsec-bouncer
           namespace: crowdsec
+        - name: "security-chain@file"
       services:
         - name: prometheus-stack-grafana
           port: 80
   tls:
-    secretName: grafana-prod-tls
+    certResolver: letsencrypt
+    domains:
+      - main: grafana.forust.xyz
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -32,5 +35,3 @@ spec:
       services:
         - name: prometheus-stack-grafana
           port: 80
-  tls:
-    secretName: internal-wildcard-tls

prometheus-stack/k8s/traefik-alerts.yaml

@@ -42,7 +42,7 @@ spec:
         - alert: TraefikServiceHighLatency
           expr: |
             histogram_quantile(0.95,
-              sum(rate(traefik_service_request_duration_seconds_bucket{service!~"xui-xui-service-.*"}[5m])) by (le, service)) > 2
+              sum(rate(traefik_service_request_duration_seconds_bucket[5m])) by (le, service)) > 2
           for: 5m
           labels:
             severity: warning

reloader/k8s/namespace.yaml

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

renovate.json

@@ -1,43 +1,11 @@
 {
   "$schema": "https://docs.renovatebot.com/renovate-schema.json",
   "extends": ["config:recommended"],
-  "enabledManagers": ["dockerfile", "docker-compose", "kubernetes", "helm-values", "custom.regex"],
+  "enabledManagers": ["docker-compose", "kubernetes"],
-  "helm-values": {
-    "managerFilePatterns": ["/k8s/.+values\\.ya?ml$/"]
-  },
   "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/README.md

@@ -24,25 +24,12 @@ The `renovate/k8s/active` marker makes the normal deployment workflow include
 the namespace, ConfigMap, and CronJob. The Secret is intentionally excluded
 from Git and must be applied separately after every new cluster.
 
-Run it immediately instead of waiting for the six-hour schedule.
+Run it immediately instead of waiting for the six-hour schedule:
-
-Two options, both use the same `renovate/config.js`:
 
 ```sh
 kubectl create job --from=cronjob/renovate renovate-manual-$(date +%s) -n renovate
 ```
 
-or the `renovate-run` Actions workflow (Actions tab → `renovate-run` →
-Run workflow). It runs `renovate/renovate:44.103.0` on the self-hosted
-runner via Docker. Required Actions secrets (repo or org settings):
-
-- `RENOVATE_TOKEN` — renovate-bot PAT (repository + issue read/write).
-- `RENOVATE_GITHUB_COM_TOKEN` — optional, for changelogs and GitHub rate limits.
-
-Inputs: `repositories` (default `forust/homelab`), `log_level`
-(`info`/`debug`). Only one run at a time (concurrency group
-`renovate-run`), same as the CronJob `Forbid` policy.
-
 Inspect runs with:
 
 ```sh

renovate/config.js

@@ -1,10 +1,7 @@
 module.exports = {
   platform: 'gitea',
-  endpoint: process.env.RENOVATE_ENDPOINT || 'https://gitea.forust.xyz/api/v1',
+  endpoint: process.env.RENOVATE_ENDPOINT,
-  enabledManagers: ['docker-compose', 'kubernetes', 'helm-values'],
+  enabledManagers: ['docker-compose', 'kubernetes'],
-  'helm-values': {
-    managerFilePatterns: ['/k8s/.+values\\.ya?ml$/'],
-  },
   kubernetes: {
     managerFilePatterns: ['/k8s/.+\\.ya?ml$/'],
   },

renovate/k8s/configmap.yaml

@@ -7,11 +7,8 @@ data:
   config.js: |
     module.exports = {
       platform: 'gitea',
-      endpoint: process.env.RENOVATE_ENDPOINT || 'https://gitea.forust.xyz/api/v1',
+      endpoint: process.env.RENOVATE_ENDPOINT,
-      enabledManagers: ['docker-compose', 'kubernetes', 'helm-values'],
+      enabledManagers: ['docker-compose', 'kubernetes'],
-      'helm-values': {
-        managerFilePatterns: ['/k8s/.+values\\.ya?ml$/'],
-      },
       kubernetes: {
         managerFilePatterns: ['/k8s/.+\\.ya?ml$/'],
       },
@@ -25,10 +22,7 @@ data:
       dependencyDashboard: true,
       prCreation: 'immediate',
       labels: ['dependencies', 'automated'],
-      extends: [
+      extends: ['config:recommended', ':dependencyDashboard'],
-        'config:recommended',
-        ':dependencyDashboard',
-      ],
       packageRules: [
         {
           description: 'Do not update private homelab images',

renovate/k8s/cronjob.yaml

@@ -16,7 +16,7 @@ spec:
           restartPolicy: Never
           containers:
             - name: renovate
-              image: renovate/renovate:44.106.0
+              image: renovate/renovate:44.102.0
               env:
                 - name: RENOVATE_PLATFORM
                   value: gitea

renovate/renovate-compose.yaml

@@ -1,6 +1,6 @@
 services:
   renovate:
-    image: renovate/renovate:44.103.0
+    image: renovate/renovate:44.83.2
     container_name: renovate
     restart: "no"
     env_file:

searxng/k8s/certificates.yaml

@@ -1,29 +0,0 @@
-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:
-    secretName: searxng-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -32,5 +32,3 @@ spec:
       services:
         - name: searxng-service
           port: 8080
-  tls:
-    secretName: internal-wildcard-tls

termix/k8s/certificates.yaml

@@ -1,28 +0,0 @@
-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:
-    secretName: termix-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -32,5 +32,3 @@ spec:
       services:
         - name: termix-service
           port: 8080
-  tls:
-    secretName: internal-wildcard-tls

traefik/k8s/certificates.yaml

@@ -1,28 +0,0 @@
-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:
-    secretName: dashboard-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -33,5 +33,3 @@ 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: true
+    enabled: false
   kubernetesCRD:
     enabled: true
   kubernetesGateway:
@@ -121,7 +121,21 @@ persistence:
   size: 100Mi
   path: /data
 
-# No certificatesResolvers: public TLS comes from cert-manager.
+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
 
 volumes:
   - name: traefik-dynamic

uptime-kuma/k8s/certificates.yaml

@@ -1,28 +0,0 @@
-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:
-    secretName: uptime-kuma-prod-tls
+    certResolver: letsencrypt
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
@@ -32,5 +32,3 @@ spec:
       services:
         - name: uptime-kuma-service
           port: 3001
-  tls:
-    secretName: internal-wildcard-tls

userbot/k8s/base/internal-certificate.yaml

@@ -1,15 +0,0 @@
-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