fix: prefix Proxmox commands with sudo for non-root SSH user

PROXMOX_SSH_USER was changed from root to wayne, but all remote pvesh/qm/pct
invocations assumed root. When run as a non-root user these commands fail with
ipcc_send_rec errors because they can't reach the pve-cluster IPC socket.

Adds a global sudo_prefix (empty when PROXMOX_SSH_USER=root, "sudo" otherwise)
and applies it to every remote Proxmox command in the script, including the
duplicate-host heredoc check, pvesh nextid, vmid existence checks, resource
destruction, and all create/start commands. Removes the now-redundant local
sudo_prefix definition that was previously only in the VM image build branch.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

hosts/nixos/home.nix

@@ -19,11 +19,13 @@
       nextcloud-client
       #    vscode
       chromium
+      claude-code
     ];
 
     # Optional: set environment vars
     sessionVariables = {
       EDITOR = "vim";
+      SOPS_AGE_KEY_FILE = "/home/nixos/Nextcloud/Filing Cabinet/keys/nixos-sops-age-key-txt";
     };
 
     file = {

modules/build-types/gui.nix

@@ -18,7 +18,7 @@
   ];
 
   boot.loader.grub.useOSProber = true;
-
+programs.direnv.enable = true;
   services = {
     xserver = {
       enable = true;

modules/common/configuration.nix

@@ -31,6 +31,7 @@
     btop
     git
     gcr
+    jq
   ];
 
   # Secrets shared by every host, decrypted at activation via each host's

modules/platforms/baremetal.nix

@@ -25,4 +25,14 @@
     enable = true;
     enable32Bit = true;
   };
+
+  # The systemd-based initrd (default here since this host has a ZFS root --
+  # see modules/disko/baremetal.nix) locks the root account by default, so
+  # sulogin refuses to hand over a shell if something in the initrd (e.g.
+  # the ZFS pool import) fails and it drops to emergency mode -- confirmed
+  # live: it just loops re-entering the target instead of prompting. This
+  # only affects the pre-switch-root initrd shell, not the installed
+  # system's own login, and is worth the tradeoff on a box already reachable
+  # at the physical console.
+  boot.initrd.systemd.emergencyAccess = true;
 }

scripts/env.sh

@@ -22,7 +22,7 @@
 : "${PVE1_HOST:=pve1.sweet.home}"
 : "${PVE_TEST_HOST:=pve-test.sweet.home}"
 : "${PROXMOX_HOST:=$PVE1_HOST}"
-: "${PROXMOX_SSH_USER:=root}"
+: "${PROXMOX_SSH_USER:=wayne}"
 
 # Where this flake repo lives on the Proxmox node itself.
 # scripts/proxmox/create-proxmox-resource.sh builds images directly on the node

scripts/installer/auto-install.sh

@@ -179,6 +179,24 @@ nixos-install \
     # makes boot stall waiting on the ZFS import. Exporting here (a no-op
     # if the chosen host has no ZFS root, e.g. proxmox-*/linode-*) clears
     # that in-use state so the next import, from any hostid, succeeds.
+    #
+    # Anything still mounted under /mnt -- nixos-install's own leftover
+    # chroot bind mounts for running the target's activation script
+    # (/mnt/dev, /mnt/proc, /mnt/sys, /mnt/run), and disko's own /mnt/boot
+    # ESP mount (modules/disko/baremetal.nix) -- blocks ZFS from unmounting
+    # its root dataset at /mnt, the same way any nested mount blocks
+    # unmounting its parent. Confirmed live: zpool export failed with
+    # "cannot unmount '/mnt': pool or dataset busy" even after handling the
+    # chroot mounts alone, because /mnt/boot was still mounted too. Because
+    # of this script's `set -e`, that killed the script before it ever
+    # reached reboot, silently defeating the whole point of exporting first.
+    # Unmounting everything under /mnt up front (recursively, so nested
+    # mounts like /mnt/dev/pts come along for free) sidesteps needing to
+    # enumerate every mount disko/nixos-install might leave behind.
+    if mountpoint -q /mnt; then
+        umount -R /mnt
+    fi
+
     if [[ -n "$(zpool list -H -o name 2>/dev/null)" ]]; then
         echo "Exporting ZFS pool(s) before reboot..."
         zpool export -a

scripts/proxmox/create-proxmox-resource.sh

@@ -193,6 +193,16 @@ done
 
 ssh_target="${PROXMOX_SSH_USER}@${node}"
 
+# Proxmox tools (pvesh, qm, pct) require root access to the cluster IPC
+# socket. When SSH-ing as a non-root user with sudo, prefix every remote
+# Proxmox command with sudo.
+sudo_prefix=""
+sudo_display=""
+if [[ "$PROXMOX_SSH_USER" != "root" ]]; then
+  sudo_prefix="sudo"
+  sudo_display="sudo "
+fi
+
 remote() {
   if [[ "$dry_run" -eq 1 ]]; then
     echo "[dry-run] ssh ${ssh_target} -- $*"
@@ -214,10 +224,10 @@ cmd_modify() {
 
   echo "Looking up VMID ${vmid} on ${node}..."
   local kind current_cores current_memory disk_key
-  if ssh "$ssh_target" "qm status ${vmid}" >/dev/null 2>&1; then
+  if ssh "$ssh_target" "${sudo_prefix} qm status ${vmid}" >/dev/null 2>&1; then
     kind="vm"
     disk_key="scsi0"
-  elif ssh "$ssh_target" "pct status ${vmid}" >/dev/null 2>&1; then
+  elif ssh "$ssh_target" "${sudo_prefix} pct status ${vmid}" >/dev/null 2>&1; then
     kind="lxc"
     disk_key="rootfs"
   else
@@ -225,8 +235,8 @@ cmd_modify() {
     exit 1
   fi
 
-  local config_cmd="qm config ${vmid}"
+  local config_cmd="${sudo_prefix} qm config ${vmid}"
-  [[ "$kind" == "lxc" ]] && config_cmd="pct config ${vmid}"
+  [[ "$kind" == "lxc" ]] && config_cmd="${sudo_prefix} pct config ${vmid}"
   local current_config
   current_config="$(ssh "$ssh_target" "$config_cmd")"
   current_cores="$(echo "$current_config" | grep -oP '^cores:\s*\K\S+' || echo '?')"
@@ -250,9 +260,9 @@ cmd_modify() {
     exit 1
   fi
 
-  local set_cmd="qm set"
+  local set_cmd="${sudo_prefix} qm set"
-  local resize_cmd="qm resize"
+  local resize_cmd="${sudo_prefix} qm resize"
-  [[ "$kind" == "lxc" ]] && set_cmd="pct set" && resize_cmd="pct resize"
+  [[ "$kind" == "lxc" ]] && set_cmd="${sudo_prefix} pct set" && resize_cmd="${sudo_prefix} pct resize"
 
   if [[ -n "$cores" || -n "$memory" ]]; then
     local args=""
@@ -359,14 +369,15 @@ else
   echo
   echo "==> Checking ${node} for an existing VM/CT identified as '${host}'..."
   ssh_check_status=0
-  existing="$(ssh "$ssh_target" bash -s -- "$host" <<'REMOTE_SCRIPT'
+  existing="$(ssh "$ssh_target" bash -s -- "$host" "$sudo_prefix" <<'REMOTE_SCRIPT'
 target="$1"
-for id in $(qm list 2>/dev/null | awk 'NR>1{print $1}'); do
+sudo_pfx="$2"
-  n="$(qm config "$id" 2>/dev/null | grep -oP '^name:\s*\K\S+' || true)"
+for id in $($sudo_pfx qm list 2>/dev/null | awk 'NR>1{print $1}'); do
+  n="$($sudo_pfx qm config "$id" 2>/dev/null | grep -oP '^name:\s*\K\S+' || true)"
   [[ "$n" == "$target" ]] && echo "vm ${id} ${n}"
 done
-for id in $(pct list 2>/dev/null | awk 'NR>1{print $1}'); do
+for id in $($sudo_pfx pct list 2>/dev/null | awk 'NR>1{print $1}'); do
-  n="$(pct config "$id" 2>/dev/null | grep -oP '^hostname:\s*\K\S+' || true)"
+  n="$($sudo_pfx pct config "$id" 2>/dev/null | grep -oP '^hostname:\s*\K\S+' || true)"
   [[ "$n" == "$target" ]] && echo "lxc ${id} ${n}"
 done
 exit 0
@@ -453,12 +464,12 @@ REMOTE_SCRIPT
       if [[ "$kind" == "vm" ]]; then
         # qm destroy has no --force to stop-then-destroy in one call (pct's
         # does) -- stop explicitly first if it's running.
-        if ssh "$ssh_target" "qm status ${id}" 2>/dev/null | grep -q running; then
+        if ssh "$ssh_target" "${sudo_prefix} qm status ${id}" 2>/dev/null | grep -q running; then
-          ssh "$ssh_target" "qm stop ${id}"
+          ssh "$ssh_target" "${sudo_prefix} qm stop ${id}"
         fi
-        ssh "$ssh_target" "qm destroy ${id} --purge 1"
+        ssh "$ssh_target" "${sudo_prefix} qm destroy ${id} --purge 1"
       else
-        ssh "$ssh_target" "pct destroy ${id} --force 1 --purge 1"
+        ssh "$ssh_target" "${sudo_prefix} pct destroy ${id} --force 1 --purge 1"
       fi
     done
   fi
@@ -487,7 +498,7 @@ if [[ -z "$vmid" ]]; then
     vmid="<next-free-vmid>"
     echo "[dry-run] would ask ${node} for the next free VMID (pvesh get /cluster/nextid)"
   else
-    vmid="$(ssh "$ssh_target" "pvesh get /cluster/nextid" | tr -d '[:space:]')"
+    vmid="$(ssh "$ssh_target" "${sudo_prefix} pvesh get /cluster/nextid" | tr -d '[:space:]')"
     echo "Auto-assigned VMID: ${vmid}"
   fi
 else
@@ -501,8 +512,8 @@ if [[ "$dry_run" -eq 0 ]]; then
   # both. Any success here means something is already using this ID --
   # refuse to go anywhere near it. (Reconfiguring an existing resource is
   # --modify's job, not this one's.)
-  if ssh "$ssh_target" "qm status ${vmid}" >/dev/null 2>&1 \
+  if ssh "$ssh_target" "${sudo_prefix} qm status ${vmid}" >/dev/null 2>&1 \
-    || ssh "$ssh_target" "pct status ${vmid}" >/dev/null 2>&1; then
+    || ssh "$ssh_target" "${sudo_prefix} pct status ${vmid}" >/dev/null 2>&1; then
     echo "ERROR: VMID ${vmid} already exists on ${node}. Refusing to touch an" >&2
     echo "existing resource here -- use --modify to reconfigure it, pick a" >&2
     echo "different --vmid, or omit it to auto-assign." >&2
@@ -702,15 +713,6 @@ REMOTE_SCRIPT
       echo "Built on ${node}: ${remote_path}"
     fi
   else
-    # PROXMOX_SSH_USER defaults to root (env.sh), which needs no sudo and
-    # can't assume it's even installed on a minimal node -- only shell out
-    # through sudo when actually running as a non-root SSH user.
-    sudo_prefix="sudo"
-    sudo_display="sudo "
-    if [[ "$PROXMOX_SSH_USER" == "root" ]]; then
-      sudo_prefix=""
-      sudo_display=""
-    fi
     if [[ "$dry_run" -eq 1 ]]; then
       echo "[dry-run] would build on ${node}: nix build --no-use-registries --no-accept-flake-config${nix_opts_display} \\"
       echo "[dry-run]   .#nixosConfigurations.${flake_target}.config.system.build.diskoImagesScript"
@@ -812,9 +814,9 @@ if [[ "$type" == "lxc" ]]; then
   # hands the whole string to `ssh` as a single command for the *remote*
   # shell to parse -- unquoted, that `;` would be read as a remote
   # command separator and silently truncate this into two commands.
-  create_cmd="pct create ${vmid} ${iso_storage}:vztmpl/${remote_filename} --unprivileged ${unprivileged_flag} --features '${PROXMOX_DEFAULT_LXC_FEATURES}' --rootfs ${storage}:${local_disk_size} --hostname ${name} --cores ${cores} --memory ${memory} --swap ${local_swap} --net0 name=eth0,bridge=${bridge},ip=dhcp"
+  create_cmd="${sudo_prefix} pct create ${vmid} ${iso_storage}:vztmpl/${remote_filename} --unprivileged ${unprivileged_flag} --features '${PROXMOX_DEFAULT_LXC_FEATURES}' --rootfs ${storage}:${local_disk_size} --hostname ${name} --cores ${cores} --memory ${memory} --swap ${local_swap} --net0 name=eth0,bridge=${bridge},ip=dhcp"
   remote "$create_cmd"
-  remote "pct start ${vmid}"
+  remote "${sudo_prefix} pct start ${vmid}"
 else
   echo "==> Creating VM ${vmid} (${name})..."
   # pre-enrolled-keys=0 disables OVMF's Secure Boot key pre-enrollment --
@@ -825,29 +827,29 @@ else
   # without this flag Proxmox never creates the channel it listens on, so
   # `qm guest exec`/`qm agent` and the UI's IP-address display silently
   # never work for any VM this script creates.
-  remote "qm create ${vmid} --name ${name} --memory ${memory} --cores ${cores} \
+  remote "${sudo_prefix} qm create ${vmid} --name ${name} --memory ${memory} --cores ${cores} \
 --net0 virtio,bridge=${bridge} --bios ovmf --machine q35 --scsihw virtio-scsi-pci \
 --efidisk0 ${storage}:1,efitype=4m,pre-enrolled-keys=0 --agent enabled=1"
 
   if [[ "$dry_run" -eq 1 ]]; then
-    echo "[dry-run] ssh ${ssh_target} -- qm importdisk ${vmid} ${remote_path} ${storage}"
+    echo "[dry-run] ssh ${ssh_target} -- ${sudo_display}qm importdisk ${vmid} ${remote_path} ${storage}"
     echo "[dry-run] (would parse the resulting disk identifier from that output)"
-    echo "[dry-run] ssh ${ssh_target} -- qm set ${vmid} --scsi0 ${storage}:<parsed-disk-id>"
+    echo "[dry-run] ssh ${ssh_target} -- ${sudo_display}qm set ${vmid} --scsi0 ${storage}:<parsed-disk-id>"
   else
-    importdisk_output="$(ssh "$ssh_target" "qm importdisk ${vmid} ${remote_path} ${storage}")"
+    importdisk_output="$(ssh "$ssh_target" "${sudo_prefix} qm importdisk ${vmid} ${remote_path} ${storage}")"
     echo "$importdisk_output"
     disk_id="$(echo "$importdisk_output" | grep -oP "(?<=Successfully imported disk as ')[^']+" | sed 's/^unused[0-9]*://')"
     if [[ -z "$disk_id" ]]; then
       echo "ERROR: couldn't parse the imported disk identifier from qm importdisk's output above." >&2
       echo "The VM shell (${vmid}) and imported disk both exist -- finish attaching it by hand:" >&2
-      echo "  ssh ${ssh_target} -- qm set ${vmid} --scsi0 ${storage}:<disk-id-from-output-above>" >&2
+      echo "  ssh ${ssh_target} -- ${sudo_display}qm set ${vmid} --scsi0 ${storage}:<disk-id-from-output-above>" >&2
-      echo "  ssh ${ssh_target} -- qm set ${vmid} --boot order=scsi0" >&2
+      echo "  ssh ${ssh_target} -- ${sudo_display}qm set ${vmid} --boot order=scsi0" >&2
       exit 1
     fi
-    remote "qm set ${vmid} --scsi0 ${disk_id}"
+    remote "${sudo_prefix} qm set ${vmid} --scsi0 ${disk_id}"
   fi
-  remote "qm set ${vmid} --boot order=scsi0"
+  remote "${sudo_prefix} qm set ${vmid} --boot order=scsi0"
-  remote "qm start ${vmid}"
+  remote "${sudo_prefix} qm start ${vmid}"
 fi
 
 echo