build-golden.sh 3.1.0: live-restore on in the golden (fail-closed assertion), GOLDEN_DOCKER_PKGS pins the approved Docker engine set

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0159rPz1ZhFKsS53msqPYxtS

configs/build-golden.sh

@@ -61,7 +61,7 @@ set -euo pipefail
 
 # Script provenance — logged into every bake transcript next to the baked controller tag, so an
 # archive can always be traced to the script that produced it. Bump on any behavior change.
-GOLDEN_SCRIPT_VERSION="3.0.0"
+GOLDEN_SCRIPT_VERSION="3.1.0"
 
 VMID="${1:-9100}"
 TEMPLATE="${2:-local:vztmpl/debian-13-standard_13.1-2_amd64.tar.zst}"
@@ -112,7 +112,15 @@ for i in $(seq 1 30); do
   if pct exec "$VMID" -- getent hosts download.docker.com >/dev/null 2>&1; then break; fi
   sleep 1
 done
-pct exec "$VMID" -- bash -c '
+# v3.1.0 (`11` §5.8): GOLDEN_DOCKER_PKGS pins the APPROVED Docker engine set (the hub's newest Docker release, all six
+# "name=version"); without it the newest stable set is installed and the bake log says so.
+GOLDEN_DOCKER_PKGS="${GOLDEN_DOCKER_PKGS:-}"
+if [[ -n "$GOLDEN_DOCKER_PKGS" ]]; then
+  echo "[golden] Docker engine set PINNED to the approved release: $GOLDEN_DOCKER_PKGS"
+else
+  echo "[golden] WARNING: GOLDEN_DOCKER_PKGS not set — installing the newest stable Docker set, not an approved one"
+fi
+pct exec "$VMID" -- env GOLDEN_DOCKER_PKGS="$GOLDEN_DOCKER_PKGS" bash -c '
   set -e
   export DEBIAN_FRONTEND=noninteractive
   apt-get update -qq
@@ -122,7 +130,12 @@ pct exec "$VMID" -- bash -c '
   echo "deb [signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/debian trixie stable" \
     > /etc/apt/sources.list.d/docker.list
   apt-get update -qq
-  apt-get install -y -qq docker-ce docker-ce-cli containerd.io >/dev/null
+  if [ -n "$GOLDEN_DOCKER_PKGS" ]; then
+    apt-get install -y -qq $GOLDEN_DOCKER_PKGS >/dev/null
+  else
+    apt-get install -y -qq docker-ce docker-ce-cli containerd.io >/dev/null
+  fi
+  dpkg-query -W containerd.io docker-buildx-plugin docker-ce docker-ce-cli docker-ce-rootless-extras docker-compose-plugin 2>/dev/null | sed "s/^/  installed: /"
 '
 echo "[golden] baking daemon.json: classic overlay2 driver (containerd-snapshotter OFF) + log rotation …"
 # containerd-snapshotter (Docker 28+/29 default) keeps the IMAGE content store under
@@ -135,9 +148,12 @@ echo "[golden] baking daemon.json: classic overlay2 driver (containerd-snapshott
 # layout (a container's `df /` reports the single volume, phase-0 spike). Since v3.0.0 /var/lib/docker
 # is a BIND of <volume>/docker rather than the mp0 mount itself, wired immediately below; data-root
 # still needs no override because the path is unchanged. Log caps kill the most common runaway.
+# v3.1.0: "live-restore": true (`09` decision 87) — a Docker engine update then restarts no app (`11` C5). A box made
+# from this golden never needs the agent's one-time live-restore-on step. NEVER removed by a plain restart (R-835).
 pct exec "$VMID" -- bash -c 'mkdir -p /etc/docker; cat > /etc/docker/daemon.json <<JSON
 {
   "features": { "containerd-snapshotter": false },
+  "live-restore": true,
   "log-driver": "json-file",
   "log-opts": { "max-size": "10m", "max-file": "3" }
 }
@@ -175,6 +191,8 @@ pct exec "$VMID" -- bash -c 'systemctl restart docker; sleep 3; docker run --rm
 # Guard: the image store MUST be on the data volume now. /var/lib/containerd holding the images would
 # mean containerd-snapshotter is still on (the split would leave images on the rootfs).
 pct exec "$VMID" -- bash -c 'drv=$(docker info 2>/dev/null | sed -n "s/.*Storage Driver: //p"); [ "$drv" = "overlay2" ] || { echo "[golden] FATAL: storage driver is $drv, expected overlay2 — images would not land on the data volume"; exit 1; }'
+# v3.1.0 ASSERTION: live-restore is ON in the running daemon (decision 87), or the bake fails closed.
+pct exec "$VMID" -- bash -c 'lr=$(docker info --format "{{.LiveRestoreEnabled}}" 2>/dev/null); [ "$lr" = "true" ] && echo "  live-restore: on" || { echo "[golden] FATAL: live-restore is $lr, expected true (decision 87)"; exit 1; }'
 # ASSERTION 1 (RETARGETED v3.0.0, not removed). /var/lib/docker must be a real mount — now the V-c
 # bind of <volume>/docker rather than the mp0 mount itself. Still fails closed on the same failure:
 # if the bind did not take, Docker's data-root silently sits on the OS rootfs and the golden ships