fix(deploy): reject destructive per-file pruning before apply

Reviewed-on: https://gitea.forust.xyz/forust/homelab/pulls/91

.gitea/tests/deploy-validation.sh

@@ -0,0 +1,80 @@
+#!/usr/bin/env bash
+# Local regressions only: kubectl is mocked and Docker is used for config parsing.
+set -euo pipefail
+repo="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
+scratch="$(mktemp -d)"
+trap 'rm -rf "$scratch"' EXIT
+
+mkdir -p "$scratch/repo/app" "$scratch/repo/postgres" "$scratch/repo/netbird" "$scratch/repo/renovate"
+git -C "$scratch/repo" init -q
+for file in app/compose.yaml postgres/shared-compose.yaml netbird/client.compose.yaml renovate/renovate-compose.yaml; do
+  touch "$scratch/repo/$file"
+done
+git -C "$scratch/repo" add .
+# shellcheck source=../workflows/compose-lint.sh
+source "$repo/.gitea/workflows/compose-lint.sh"
+actual="$(cd "$scratch/repo" && compose_files)"
+expected=$'app/compose.yaml\nnetbird/client.compose.yaml\npostgres/shared-compose.yaml\nrenovate/renovate-compose.yaml'
+[ "$actual" = "$expected" ] || { echo 'Compose discovery missed a file' >&2; exit 1; }
+
+cat >"$scratch/compose.yaml" <<'YAML'
+services:
+  example:
+    image: busybox:1.37.0
+    environment:
+      REQUIRED: ${HOMELAB_TEST_REQUIRED:?required for this regression}
+YAML
+unset HOMELAB_TEST_REQUIRED
+if validate_compose_file "$scratch/compose.yaml" >"$scratch/config.log" 2>&1; then
+  echo 'Full Compose validation accepted a missing variable' >&2
+  exit 1
+fi
+grep -q 'required for this regression' "$scratch/config.log"
+HOMELAB_TEST_REQUIRED=present validate_compose_file "$scratch/compose.yaml"
+
+cat >"$scratch/resources.json" <<'JSON'
+{"kind":"List","items":[
+  {"kind":"Deployment","metadata":{"namespace":"app"},"spec":{"template":{"spec":{
+    "containers":[{"envFrom":[{"secretRef":{"name":"credentials"}},{"secretRef":{"name":"optional","optional":true}}],"env":[{"valueFrom":{"secretKeyRef":{"name":"credentials","key":"password"}}}]}],
+    "initContainers":[{"envFrom":[{"secretRef":{"name":"init"}}]}],
+    "imagePullSecrets":[{"name":"registry"}],
+    "volumes":[{"secret":{"secretName":"mounted"}},{"projected":{"sources":[{"secret":{"name":"projected"}},{"secret":{"name":"optional-projected","optional":true}}]}}]
+  }}}},
+  {"kind":"CronJob","metadata":{},"spec":{"jobTemplate":{"spec":{"template":{"spec":{"containers":[{"envFrom":[{"secretRef":{"name":"cron"}}]}]}}}}}},
+  {"kind":"IngressRoute","metadata":{"namespace":"app"},"spec":{"tls":{"secretName":"controller-issued-tls"}}}
+]}
+JSON
+actual="$(jq -r -f "$repo/.gitea/workflows/secret-references.jq" "$scratch/resources.json" | sort)"
+expected=$'app credentials\napp init\napp mounted\napp projected\napp registry\ndefault cron'
+[ "$actual" = "$expected" ] || { echo "Unexpected Secret references: $actual" >&2; exit 1; }
+
+REPO="$repo"
+# shellcheck source=../workflows/deploy-lib.sh
+source "$repo/.gitea/workflows/deploy-lib.sh"
+K8S_MANIFESTS=("$scratch/resources.json")
+KUSTOMIZE_APPS=()
+# No live cluster access. Reject credentials in app even if they exist elsewhere.
+kubectl() {
+  case "$1" in
+    create) cat "$scratch/resources.json" ;;
+    get)
+      if [ "$3" = credentials ] && [ "$5" = app ]; then
+        return 1
+      fi
+      return 0
+      ;;
+    *) echo "Unexpected kubectl invocation: $*" >&2; return 1 ;;
+  esac
+}
+if check_referenced_secrets >"$scratch/secrets.log"; then
+  echo 'Namespace-scoped Secret check accepted a missing Secret' >&2
+  exit 1
+fi
+grep -q 'MISSING OR UNREADABLE: app/credentials' "$scratch/secrets.log"
+# API/rendering errors must not produce an empty reference list and pass.
+kubectl() { return 1; }
+if check_referenced_secrets >"$scratch/secrets.log"; then
+  echo 'Secret check accepted a failed manifest render' >&2
+  exit 1
+fi
+printf '%s\n' 'Deploy validation regressions passed.'

.gitea/workflows/ci.yaml

@@ -88,7 +88,7 @@ jobs:
         shell: bash
         run: |
           set -euo pipefail
-          tools_dir="$(bash .gitea/workflows/install-ci-tools.sh shellcheck)"
+          tools_dir="$(bash .gitea/workflows/install-ci-tools.sh shellcheck jq)"
           export PATH="$tools_dir:$PATH"
           mapfile -t scripts < <(
             git ls-files '*.sh' ':(glob)**/*.bash'
@@ -98,6 +98,7 @@ jobs:
             exit 0
           fi
           shellcheck --external-sources --source-path=SCRIPTDIR --severity=style "${scripts[@]}"
+          bash .gitea/tests/deploy-validation.sh
 
   lint-prettier:
     runs-on: [self-hosted, linux, arch, homelab]

.gitea/workflows/compose-lint.sh

@@ -21,8 +21,7 @@
 # All committed Compose files, including the ones deploy never starts.
 compose_files() {
   git ls-files \
-    '*/compose.yaml' '*/compose.yml' 'compose.yaml' 'compose.yml' \
+    '*compose.yaml' '*compose.yml'
-    '*/docker-compose.yaml' '*/docker-compose.yml'
 }
 
 # Prints the flags that turn `docker compose config` into the general check.

.gitea/workflows/deploy-lib.sh

@@ -31,6 +31,16 @@ warn() {
   echo "WARNING: $*" >&2
 }
 
+# Prune needs the complete desired set in one invocation. Per-file pruning
+# treats resources from the other files as absent and can delete them.
+check_prune_mode() {
+  if [ "$APPLY_PRUNE" = "true" ]; then
+    echo "ERROR: APPLY_PRUNE=true is unsupported by the per-file deploy loop." >&2
+    echo "Disable it; remove obsolete resources explicitly after review." >&2
+    return 1
+  fi
+}
+
 collect_k8s() {
   git -C "$REPO" ls-files -- "$1" \
     | grep -E '\.ya?ml$' \
@@ -686,27 +696,53 @@ stage_preflight() {
   git -C "$REPO" reset --hard "$target"
 }
 
+# Required pod Secrets, scoped to the resource namespace. TLS route Secrets are
+# created by cert-manager and are not prerequisites for applying a Certificate.
+check_referenced_secrets() {
+  local m k objects refs extracted ns name
+  local missing=()
+  refs=""
+  for m in ${K8S_MANIFESTS[@]+"${K8S_MANIFESTS[@]}"}; do
+    objects="$(kubectl create --dry-run=client --validate=false -f "$m" -o json)" || return 1
+    extracted="$(printf '%s' "$objects" | jq -r -f "$REPO/.gitea/workflows/secret-references.jq")" || return 1
+    refs+="$extracted"$'\n'
+  done
+  for k in ${KUSTOMIZE_APPS[@]+"${KUSTOMIZE_APPS[@]}"}; do
+    objects="$(kubectl kustomize "$k" | kubectl create --dry-run=client --validate=false -f - -o json)" || return 1
+    extracted="$(printf '%s' "$objects" | jq -r -f "$REPO/.gitea/workflows/secret-references.jq")" || return 1
+    refs+="$extracted"$'\n'
+  done
+  while read -r ns name; do
+    [ -n "${name:-}" ] || continue
+    if kubectl get secret "$name" -n "$ns" -o name >/dev/null 2>&1; then
+      echo "  ok: $ns/$name"
+    else
+      echo "  MISSING OR UNREADABLE: $ns/$name"
+      missing+=("$ns/$name")
+    fi
+  done < <(printf '%s' "$refs" | sort -u)
+  if [ "${#missing[@]}" -gt 0 ]; then
+    echo "ERROR: required pod Secrets are missing or unreadable:"
+    printf '  - %s\n' "${missing[@]}"
+    echo "Create them in the listed namespaces from the service's secret example."
+    return 1
+  fi
+}
+
 stage_validate() {
+  check_prune_mode || return 1
   cd "$REPO"
   select_manifests
   local m k cf
-  # Compose .env files and secret files are gitignored by design, so the
+  # The deploy host has the local .env and secret files. Resolve them here so
-  # workstation never has real values for the inactive stacks. This stage only
+  # missing configuration fails before either apply job changes workloads.
-  # runs the full check on active stacks; the general structure check for every
+  # CI keeps the structure-only check for inactive stacks.
-  # committed Compose file (active or not) lives in the ci workflow, which has no
-  # .env at all.
-  #
-  # Active stacks are still validated with interpolation and env-file resolution
-  # off, so required-variable guards (:?) and missing local files do not fail the
-  # deploy. Normalization and consistency checks stay enabled.
   # shellcheck source=compose-lint.sh
   source "$REPO/.gitea/workflows/compose-lint.sh"
-  local compose_validate_flags=()
-  mapfile -t compose_validate_flags < <(compose_safe_flags)
   log "Validate compose stacks"
   for cf in ${COMPOSE_STACKS[@]+"${COMPOSE_STACKS[@]}"}; do
     echo "  config: $cf"
-    validate_compose_file "$cf" ${compose_validate_flags[@]+"${compose_validate_flags[@]}"}
+    validate_compose_file "$cf"
   done
   log "Validate k8s manifests (kubectl dry-run=client)"
   for m in ${K8S_MANIFESTS[@]+"${K8S_MANIFESTS[@]}"}; do
@@ -724,48 +760,20 @@ stage_validate() {
   done
   log "Checking referenced Secrets exist"
   echo "  (deploy never applies *secret*.yaml; create missing ones manually)"
-  local ref_secrets=() missing_secrets=() all_secrets s
+  check_referenced_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:' "${K8S_MANIFESTS[@]}" 2>/dev/null || true
-      } | grep -E 'name:' | sed -E 's/.*name:[[:space:]]*//' | tr -d '"'"'"' "'"'" | sed -E 's/[[:space:]]*#.*//' | awk 'NF' | sort -u || true
-    )
-  fi
-  all_secrets="$(kubectl get secrets -A --no-headers -o custom-columns=:metadata.name 2>/dev/null || true)"
-  for s in ${ref_secrets[@]+"${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
 }
 
 stage_apply_k8s() {
+  check_prune_mode || return 1
   cd "$REPO"
   select_manifests >/dev/null
-  local ns_files=() other_files=() m k prune_opts=()
+  local ns_files=() other_files=() m k
   for m in ${K8S_MANIFESTS[@]+"${K8S_MANIFESTS[@]}"}; do
     case "$m" in
       */namespace.y?ml) ns_files+=("$m") ;;
       *) other_files+=("$m") ;;
     esac
   done
-  if [ "$APPLY_PRUNE" = "true" ]; then
-    prune_opts=(--prune -l app.kubernetes.io/managed-by=homelab-deploy)
-  fi
 
   # Record what is about to change, and publish it for the verify job, before
   # the first apply. Both are fatal on failure: see snapshot_dir.
@@ -790,7 +798,7 @@ stage_apply_k8s() {
   if [ "${#other_files[@]}" -gt 0 ]; then
     log "Applying resources (${#other_files[@]} files, our images pinned to digests)"
     for m in "${other_files[@]}"; do
-      if ! render_pinned <"$m" | kubectl apply "${prune_opts[@]}" -f -; then
+      if ! render_pinned <"$m" | kubectl apply -f -; then
         echo "ERROR: apply failed for ${m#"$REPO"/}" >&2
         exit 1
       fi

.gitea/workflows/install-ci-tools.sh

@@ -120,6 +120,15 @@ install_shellcheck() {
   rm -rf "$tmp"
 }
 
+install_jq() {
+  if at_version jq "${JQ_VERSION}"; then
+    return 0
+  fi
+  fetch "https://github.com/jqlang/jq/releases/download/jq-${JQ_VERSION}/jq-linux-${goarch}" \
+    "$BIN_DIR/jq"
+  chmod 0755 "$BIN_DIR/jq"
+}
+
 install_uv() {
   if at_version uv "${UV_VERSION}"; then
     return 0
@@ -236,6 +245,7 @@ for tool in "${wanted[@]}"; do
   case "$tool" in
     kubeconform) install_kubeconform ;;
     shellcheck) install_shellcheck ;;
+    jq) install_jq ;;
     actionlint) install_actionlint ;;
     prettier) install_prettier ;;
     ruff) install_ruff ;;

.gitea/workflows/secret-references.jq

@@ -0,0 +1,13 @@
+# kubectl emits a List for files containing multiple resources.
+(if .kind == "List" then .items[] else . end)
+| (.metadata.namespace // "default") as $ns
+| [
+    (.. | objects
+      | (.secretRef? // empty), (.secretKeyRef? // empty), (.secret? // empty)
+      | select(.optional != true)
+      | .name // .secretName // empty),
+    (.. | objects | .imagePullSecrets[]?.name)
+  ]
+| unique[]
+| select(. != null and . != "")
+| "\($ns) \(.)"

.gitea/workflows/tool-versions.env

@@ -31,3 +31,6 @@ UV_VERSION="0.12.17"
 # so the tree that gets tested is the tree that gets built. Renovate keeps this
 # in step with the Dockerfile's node: tag via the "node runtime" group.
 NODE_VERSION="22.23.3"
+
+# Secret-reference regression tests parse rendered Kubernetes objects.
+JQ_VERSION="1.8.1"

adguardhome/k8s/adguard.yaml

@@ -51,6 +51,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: adguard-deployment
   namespace: adguard
 spec:
@@ -64,8 +66,6 @@ spec:
     metadata:
       labels:
         app: adguard
-      annotations:
-        reloader.stakater.com/auto: "true"
     spec:
       containers:
         - name: adguard

authentik/k8s/authentik.yaml

@@ -27,6 +27,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: authentik-server-deployment
   namespace: authentik
 spec:
@@ -63,6 +65,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: authentik-worker-deployment
   namespace: authentik
 spec:

cfddns/k8s/deployment.yaml

@@ -1,6 +1,8 @@
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: cfddns
   labels:
     app: cfddns

checkmk/k8s/checkmk.yaml

@@ -17,6 +17,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: checkmk-deployment
   namespace: checkmk
 spec:

cloudflared/k8s/deployment.yaml

@@ -1,6 +1,8 @@
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: cloudflared
   labels:
     app: cloudflared

converters/k8s/convertx.yaml

@@ -13,6 +13,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: convertx-deployment
   namespace: converters
 spec:

edu_master/k8s/session-keeper.yaml

@@ -1,6 +1,8 @@
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: session-keeper
   namespace: edu-master
   labels:

edu_master/k8s/webinar-checker.yaml

@@ -1,6 +1,8 @@
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: webinar-checker
   namespace: edu-master
   labels:

gitea/k8s/gitea.yaml

@@ -17,6 +17,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: gitea-deployment
   namespace: gitea
 spec:

glance/k8s/glance.yaml

@@ -13,6 +13,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: glance-deployment
   namespace: glance
 spec:

homarr/k8s/homarr.yaml

@@ -13,6 +13,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: homarr-deployment
   namespace: homarr
 spec:

immich/k8s/immich.yaml

@@ -14,6 +14,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: immich-deployment
   namespace: immich
   labels:

immich/k8s/machine-learning.yaml

@@ -14,6 +14,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: immich-machine-learning-deployment
   namespace: immich
   labels:

immich/k8s/valkey.yaml

@@ -17,6 +17,8 @@ spec:
 apiVersion: apps/v1
 kind: StatefulSet
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: immich-valkey
   namespace: immich
   labels:

kener/k8s/kener.yaml

@@ -13,6 +13,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: kener-deployment
   namespace: kener
 spec:

metube/k8s/metube.yaml

@@ -13,6 +13,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: metube-deployment
   namespace: metube
 spec:

n8n/k8s/n8n.yaml

@@ -13,6 +13,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: n8n-deployment
   namespace: n8n
 spec:

netbird/k8s/netbird.yaml

@@ -32,6 +32,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: netbird-server-deployment
   namespace: netbird
 spec:
@@ -126,6 +128,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: netbird-dashboard-deployment
   namespace: netbird
 spec:

netbox/k8s/netbox.yaml

@@ -14,6 +14,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: netbox-deployment
   namespace: netbox
   labels:
@@ -118,6 +120,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: netbox-worker-deployment
   namespace: netbox
   labels:

netbox/k8s/valkey.yaml

@@ -17,6 +17,8 @@ spec:
 apiVersion: apps/v1
 kind: StatefulSet
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: netbox-valkey
   namespace: netbox
   labels:

netronome/k8s/netronome.yaml

@@ -14,6 +14,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: netronome-deployment
   namespace: netronome
   labels:

reloader/k8s/reloader-values.yaml

@@ -1,11 +1,17 @@
 # Pinned chart: stakater/reloader 2.2.17 (app v1.4.22).
 # Deployed by the deploy workflow, namespace reloader.
 # Restarts pods when a ConfigMap or Secret they consume changes. Opt-in per workload
-# via the reloader.stakater.com/auto: "true" pod annotation; watchGlobally because
+# via the reloader.stakater.com/auto: "true" workload annotation; watchGlobally because
 # the workloads that need it are spread across a few dozen namespaces.
 
 reloader:
   watchGlobally: true
+  # Only opted-in workloads are restarted. Keep scheduled jobs on their schedule.
+  autoReloadAll: false
+  ignoreJobs: true
+  ignoreCronJobs: true
+  # Change pod-template annotations rather than injecting STAKATER_* env vars.
+  reloadStrategy: annotations
 
   deployment:
     replicas: 1

searxng/k8s/searxng.yaml

@@ -13,6 +13,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: searxng-deployment
   namespace: searxng
 spec:

termix/k8s/termix.yaml

@@ -13,6 +13,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: termix-deployment
   namespace: termix
 spec:

vaultwarden/k8s/vaultwarden.yaml

@@ -13,6 +13,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: vaultwarden-deployment
   namespace: vaultwarden
 spec:

vpn/xui/k8s/xui.yaml

@@ -20,6 +20,8 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+    reloader.stakater.com/auto: "true"
   name: xui-deployment
   namespace: xui
 spec: