feat: add nixos@nixos workstation SSH key to all hosts

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Rcq7iXrN9eYUTUEWrbWqyX

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
@@ -76,6 +77,7 @@
     openssh.authorizedKeys.keys = [
       vars.adminSshKey
       "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICMJhrfFayLBG+gWtO6oAvgambw5nWWgztiTFEaaaVRH debian@surface"
+      "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGygkCljN6uKpdJbHTOQtn8ZnH+wKXDLAwrDFbLrE/65 nixos@nixos"
     ];
   };
 

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/codex-maintenance.sh

@@ -16,6 +16,14 @@
 #
 # --dry-run: adds `nix build --dry-run --no-link` for whatever scope is
 # active (changed-files scope by default, full scope under --full-check).
+#
+# Per-host/per-package eval and dry-run build calls run concurrently (see
+# scripts/lib/nix-parallel.sh) since they're independent of each other.
+# Concurrency defaults to core count capped by available memory (~1GB/job)
+# rather than plain core count, since each concurrent `nix eval` evaluates a
+# whole NixOS system closure and can OOM a small/memory-constrained CI
+# runner otherwise; override via NIX_PARALLEL_JOBS if a runner has more (or
+# less) room than that estimate assumes.
 set -euo pipefail
 
 script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
@@ -23,6 +31,8 @@ script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 source "${script_dir}/lib/nix-bootstrap.sh"
 # shellcheck source=lib/nix-eval.sh
 source "${script_dir}/lib/nix-eval.sh"
+# shellcheck source=lib/nix-parallel.sh
+source "${script_dir}/lib/nix-parallel.sh"
 
 repo_root="$(cd "${script_dir}/.." && pwd)"
 cd "$repo_root"
@@ -246,66 +256,64 @@ echo
 if [[ ${#hosts[@]} -eq 0 ]]; then
   echo "No hosts affected by changed files; skipping host eval."
 else
-  echo "Evaluating host toplevel derivations (${scope_desc})..."
+  echo "Evaluating host toplevel derivations (${scope_desc}, up to ${NIX_PARALLEL_JOBS} at a time)..."
+  # lxc-* hosts deploy via a directly pct-restore-able tarball instead of
+  # nixos-install (see docs/auto-installer.md); proxmox-* hosts can
+  # alternatively be built as a standalone disk image (see
+  # docs/proxmox-images.md). Both are otherwise-unvalidated buildable
+  # surface, easy to silently break without this.
+  declare -a host_eval_jobs=()
   for host in "${hosts[@]}"; do
-    echo "==> $host"
-    nix eval --raw "${NIX_EVAL_FLAGS[@]}" ".#nixosConfigurations.${host}.config.system.build.toplevel.drvPath"
-
-    # lxc-* hosts deploy via a directly pct-restore-able tarball instead of
-    # nixos-install (see docs/auto-installer.md); proxmox-* hosts can
-    # alternatively be built as a standalone disk image (see
-    # docs/proxmox-images.md). Both are otherwise-unvalidated buildable
-    # surface, easy to silently break without this.
+    host_eval_jobs+=("${host}${NIX_PARALLEL_SEP}.#nixosConfigurations.${host}.config.system.build.toplevel.drvPath")
     case "$host" in
       lxc-*)
-        echo "==> $host (tarball)"
-        nix eval --raw "${NIX_EVAL_FLAGS[@]}" ".#nixosConfigurations.${host}.config.system.build.tarball.drvPath"
+        host_eval_jobs+=("${host} (tarball)${NIX_PARALLEL_SEP}.#nixosConfigurations.${host}.config.system.build.tarball.drvPath")
         ;;
       proxmox-*)
-        echo "==> $host (diskoImagesScript)"
-        nix eval --raw "${NIX_EVAL_FLAGS[@]}" ".#nixosConfigurations.${host}.config.system.build.diskoImagesScript.drvPath"
+        host_eval_jobs+=("${host} (diskoImagesScript)${NIX_PARALLEL_SEP}.#nixosConfigurations.${host}.config.system.build.diskoImagesScript.drvPath")
         ;;
     esac
   done
+  run_nix_parallel host_eval_jobs eval --raw "${NIX_EVAL_FLAGS[@]}"
 fi
 
 echo
 if ! $eval_packages; then
   echo "No packages affected by changed files; skipping package eval."
 else
-  echo "Evaluating buildable packages..."
+  echo "Evaluating buildable packages (up to ${NIX_PARALLEL_JOBS} at a time)..."
+  declare -a package_eval_jobs=()
   for pkg in "${all_packages[@]}"; do
-    echo "==> packages.x86_64-linux.${pkg}"
-    nix eval --raw "${NIX_EVAL_FLAGS[@]}" ".#packages.x86_64-linux.${pkg}"
+    package_eval_jobs+=("packages.x86_64-linux.${pkg}${NIX_PARALLEL_SEP}.#packages.x86_64-linux.${pkg}")
   done
+  run_nix_parallel package_eval_jobs eval --raw "${NIX_EVAL_FLAGS[@]}"
 fi
 
 if $dry_run; then
   echo
-  echo "Running dry-run builds for the active scope. This will not create result symlinks."
+  echo "Running dry-run builds for the active scope (up to ${NIX_PARALLEL_JOBS} at a time). This will not create result symlinks."
+  declare -a host_build_jobs=()
   for host in "${hosts[@]:-}"; do
-    echo "==> Dry-run build: $host"
-    nix build --dry-run --no-link "${NIX_EVAL_FLAGS[@]}" ".#nixosConfigurations.${host}.config.system.build.toplevel"
-
+    host_build_jobs+=("Dry-run build: ${host}${NIX_PARALLEL_SEP}.#nixosConfigurations.${host}.config.system.build.toplevel")
     case "$host" in
       lxc-*)
-        echo "==> Dry-run build: $host (tarball)"
-        nix build --dry-run --no-link "${NIX_EVAL_FLAGS[@]}" ".#nixosConfigurations.${host}.config.system.build.tarball"
+        host_build_jobs+=("Dry-run build: ${host} (tarball)${NIX_PARALLEL_SEP}.#nixosConfigurations.${host}.config.system.build.tarball")
         ;;
       proxmox-*)
-        echo "==> Dry-run build: $host (diskoImagesScript)"
-        nix build --dry-run --no-link "${NIX_EVAL_FLAGS[@]}" ".#nixosConfigurations.${host}.config.system.build.diskoImagesScript"
+        host_build_jobs+=("Dry-run build: ${host} (diskoImagesScript)${NIX_PARALLEL_SEP}.#nixosConfigurations.${host}.config.system.build.diskoImagesScript")
         ;;
     esac
   done
+  run_nix_parallel host_build_jobs build --dry-run --no-link "${NIX_EVAL_FLAGS[@]}"
 
   if $eval_packages; then
     echo
     echo "Running dry-run builds for packages."
+    declare -a package_build_jobs=()
     for pkg in "${all_packages[@]}"; do
-      echo "==> Dry-run build: packages.x86_64-linux.${pkg}"
-      nix build --dry-run --no-link "${NIX_EVAL_FLAGS[@]}" ".#packages.x86_64-linux.${pkg}"
+      package_build_jobs+=("Dry-run build: packages.x86_64-linux.${pkg}${NIX_PARALLEL_SEP}.#packages.x86_64-linux.${pkg}")
     done
+    run_nix_parallel package_build_jobs build --dry-run --no-link "${NIX_EVAL_FLAGS[@]}"
   fi
 fi
 

scripts/codex-setup.sh

@@ -68,6 +68,7 @@ cat > "$HOME/.config/nix/nix.conf" <<'EOF'
 experimental-features = nix-command flakes
 accept-flake-config = false
 warn-dirty = false
+build-users-group =
 EOF
 
 echo "Nix version:"

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
@@ -30,7 +30,7 @@
 # (from this checkout's own `origin` remote) the first time it doesn't
 # find it, installing build tooling via scripts/codex-setup.sh, then
 # `git pull`s it before every subsequent build.
-: "${PROXMOX_REMOTE_REPO_DIR:=/root/nixos}"
+: "${PROXMOX_REMOTE_REPO_DIR:=/home/${PROXMOX_SSH_USER}/nixos}"
 
 # Storage pool names -- Proxmox's own stock-install defaults, but this
 # varies a lot by setup (ZFS pool name, custom LVM-thin volume, etc.).

scripts/installer/auto-install.sh

@@ -1,17 +1,20 @@
 #!/usr/bin/env nix-shell
-#!nix-shell -i bash -p jq disko nixos-install-tools
+#!nix-shell -i bash -p jq disko nixos-install-tools zfs
 # shellcheck shell=bash
 # The only genuinely external tools this script calls directly: `jq`
-# (parsing the `nix eval` host list) and `disko`/`nixos-install` (the
-# install itself). Everything disko shells out to internally
-# (parted/sgdisk/mkfs.*/zfs/...) is self-contained -- disko's own
-# generated scripts hardcode absolute Nix store paths for those, they
+# (parsing the `nix eval` host list), `disko`/`nixos-install` (the
+# install itself), and `zpool` (exporting a ZFS root pool before reboot,
+# see the comment above that call below). Everything disko shells out to
+# internally (parted/sgdisk/mkfs.*/zfs/...) is self-contained -- disko's
+# own generated scripts hardcode absolute Nix store paths for those, they
 # don't rely on this script's PATH at all (confirmed by inspecting a
 # generated system.build.formatScript). The built installer image
-# (modules/installer/common.nix) already has all three in
-# environment.systemPackages, so this nix-shell wrapper is a fast no-op
-# there; it's what makes the script also work standalone (e.g. run
-# directly from a checkout on a stock ISO), where they aren't.
+# (modules/installer/common.nix, plus the upstream
+# installation-cd-minimal.nix it imports via iso.nix) already has all
+# four in environment.systemPackages, so this nix-shell wrapper is a
+# fast no-op there; it's what makes the script also work standalone
+# (e.g. run directly from a checkout on a stock ISO), where they aren't
+# guaranteed.
 set -eux
 
 set -euo pipefail
@@ -162,5 +165,42 @@ nixos-install \
     # /etc/ssh/ssh_host_ed25519_key. Nothing NixOS-managed ever cleans this
     # up on its own since it was written imperatively, not declaratively.
     rm -rf /root/host-keys
+
+    # disko's --mode ...,mount left any ZFS root pool imported (that's what
+    # let nixos-install write into /mnt). If we reboot with it still
+    # imported, it isn't just "not exported" -- it's stamped with *this*
+    # live installer environment's hostid, which almost never matches the
+    # target's own networking.hostId (see hosts/*/host.nix; the installer
+    # itself sets none). modules/services/zfs/enable-service.nix and
+    # modules/common/configuration.nix both set boot.zfs.forceImportRoot =
+    # false deliberately (the safe option per that setting's own docs), so
+    # the freshly-installed system's first real boot sees a pool "in use by
+    # another system" and refuses to import it without -f -- which is what
+    # 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
+    fi
+
     sleep 10
     reboot

scripts/lib/nix-parallel.sh

@@ -0,0 +1,95 @@
+#!/usr/bin/env bash
+# Shared parallel-nix-invocation helper for scripts/codex-maintenance.sh.
+# Source alongside nix-eval.sh:
+#   source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/lib/nix-parallel.sh"
+#
+# The per-host/per-package `nix eval`/`nix build --dry-run` calls in
+# codex-maintenance.sh are independent of each other, so running them one at
+# a time leaves most cores idle for most of the sweep -- run_nix_parallel
+# fans a batch of them out across up to NIX_PARALLEL_JOBS processes instead.
+
+# NIX_PARALLEL_JOBS: how many `nix` invocations run_nix_parallel runs at
+# once. Defaults to core count capped by available memory (~1GB/job,
+# floor 1) rather than plain `nproc` -- each concurrent `nix eval` here
+# evaluates a whole NixOS system closure from scratch, and on a small/
+# memory-constrained CI runner, `nproc` concurrent evals can OOM-kill each
+# other (confirmed empirically: on a 4GB/6-core box, 5-6 concurrent evals
+# started getting killed while 3-4 ran clean and were still ~2x faster than
+# serial). Override via env if a given machine/CI runner has room to spare
+# or needs a tighter cap.
+default_nix_parallel_jobs() {
+  local cores mem_avail_kb mem_cap
+  cores="$(nproc 2>/dev/null || echo 4)"
+  mem_avail_kb="$(awk '/^MemAvailable:/ {print $2}' /proc/meminfo 2>/dev/null)"
+  if [[ -z "$mem_avail_kb" ]]; then
+    echo "$cores"
+    return
+  fi
+  mem_cap=$((mem_avail_kb / 1024 / 1024))
+  ((mem_cap < 1)) && mem_cap=1
+  ((mem_cap < cores)) && echo "$mem_cap" || echo "$cores"
+}
+NIX_PARALLEL_JOBS="${NIX_PARALLEL_JOBS:-$(default_nix_parallel_jobs)}"
+
+# Separator between a job's label and its flake attr in the arrays
+# run_nix_parallel takes -- a control character so it can't collide with
+# anything a label or attr path would plausibly contain.
+NIX_PARALLEL_SEP=$'\x1f'
+
+# run_nix_parallel <jobs_array_name> <nix subcommand + flags...>
+#
+# jobs_array_name: name of an already-populated bash array whose entries are
+# "<label>${NIX_PARALLEL_SEP}<attr>" pairs, e.g.
+#   jobs=("proxmox-docker${NIX_PARALLEL_SEP}.#nixosConfigurations.proxmox-docker...drvPath")
+# Remaining args are passed to `nix` before the attr, e.g.:
+#   run_nix_parallel jobs eval --raw "${NIX_EVAL_FLAGS[@]}"
+#   run_nix_parallel jobs build --dry-run --no-link "${NIX_EVAL_FLAGS[@]}"
+#
+# Prints "==> <label>" followed by that job's stdout+stderr for every job,
+# in submission order (not completion order) so a run stays readable and
+# diffable across invocations even though the work itself doesn't finish in
+# that order. Returns non-zero if any job failed, only after every job has
+# finished and been printed -- same "surface everything, then fail" contract
+# a `set -e` caller gets, just parallelized instead of stopping at the first
+# failure.
+run_nix_parallel() {
+  local -n jobs_ref="$1"
+  shift
+  local -a nix_args=("$@")
+
+  local n=${#jobs_ref[@]}
+  [[ $n -eq 0 ]] && return 0
+
+  local tmp_dir
+  tmp_dir="$(mktemp -d)"
+
+  local i=0 running=0
+  for job in "${jobs_ref[@]}"; do
+    local attr="${job#*"${NIX_PARALLEL_SEP}"}"
+    printf '%s\n' "${job%%"${NIX_PARALLEL_SEP}"*}" >"${tmp_dir}/${i}.label"
+    (
+      if nix "${nix_args[@]}" "$attr" >"${tmp_dir}/${i}.out" 2>&1; then
+        echo 0 >"${tmp_dir}/${i}.status"
+      else
+        echo 1 >"${tmp_dir}/${i}.status"
+      fi
+    ) &
+    i=$((i + 1))
+    running=$((running + 1))
+    if ((running >= NIX_PARALLEL_JOBS)); then
+      wait -n
+      running=$((running - 1))
+    fi
+  done
+  wait
+
+  local failed=0 j
+  for ((j = 0; j < n; j++)); do
+    echo "==> $(cat "${tmp_dir}/${j}.label")"
+    cat "${tmp_dir}/${j}.out"
+    [[ "$(cat "${tmp_dir}/${j}.status")" -ne 0 ]] && failed=1
+  done
+
+  rm -rf "$tmp_dir"
+  return $failed
+}

scripts/proxmox/configure-nix-cache-client.sh

@@ -6,27 +6,31 @@
 #
 # This is the non-NixOS equivalent of modules/nix-cache/client.nix +
 # modules/nix-cache/remote-builder-client.nix -- those two only apply to
-# hosts built from this flake. A plain Debian box with Nix installed
-# (single- or multi-user install, nix-daemon running) has no NixOS module
-# system to pick that config up, so this edits /etc/nix/nix.conf by hand
-# instead. Run this ON the target Debian machine, as root.
+# hosts built from this flake. A plain Debian box with Nix installed has no
+# NixOS module system to pick that config up, so this edits nix.conf by hand.
+#
+# Two modes depending on who runs it:
+#
+#   root (multi-user / daemon install):
+#     Writes /etc/nix/nix.conf, /etc/ssh/ssh_known_hosts, restarts nix-daemon.
+#     Requires /etc/nix/nix.conf to already exist (i.e. nix-daemon is set up).
+#     Run as: sudo ./configure-nix-cache-client.sh [options]
+#
+#   non-root (single-user install):
+#     Writes ~/.config/nix/nix.conf, ~/.ssh/known_hosts. No daemon to restart.
+#     Run as: ./configure-nix-cache-client.sh [options]
 #
 # The values below mirror variables.nix / modules/nix-cache/client.nix in
 # this repo -- update both if nix-cache is ever rebuilt with a new host
 # key or the cache signing key is rotated (see docs/nix-cache.md).
 #
-# REMOTE_BUILDER_KEY defaults to this machine's own default root SSH
-# identity (matches modules/nix-cache/remote-builder-client.nix's
-# convention for real NixOS clients: authenticate as nixremote with the
-# host's own default key, added individually to
-# vars.remoteBuilderAuthorizedKeys, rather than a separately-named or
-# shared keypair) -- generate one with
-# `ssh-keygen -t ed25519 -N '' -f /root/.ssh/id_ed25519` if this machine
-# doesn't have one yet, then add its .pub to vars.remoteBuilderAuthorizedKeys
-# and rebuild nix-cache.
+# REMOTE_BUILDER_KEY defaults to the running user's default SSH identity
+# (root: /root/.ssh/id_ed25519, other user: ~/.ssh/id_ed25519). That key
+# must be listed in vars.remoteBuilderAuthorizedKeys in this repo and
+# nix-cache rebuilt before remote building works.
 #
 # Usage:
-#   sudo ./configure-nix-cache-client.sh [--dry-run] [--no-remote-builder] [--no-restart]
+#   ./configure-nix-cache-client.sh [--dry-run] [--no-remote-builder] [--no-restart]
 #
 # Env overrides (defaults match variables.nix):
 #   NIX_CACHE_HOST, NIX_CACHE_HOST_KEY, REMOTE_BUILDER_USER, REMOTE_BUILDER_KEY
@@ -36,17 +40,28 @@ set -euo pipefail
 : "${NIX_CACHE_HOST:=nix-cache}"
 : "${NIX_CACHE_HOST_KEY:=ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIPeWgMsdaiz4axT/deFc1+0B5bN+GX/NOeW9bbQ0c/IT lxc-nix-cache}"
 : "${REMOTE_BUILDER_USER:=nixremote}"
-: "${REMOTE_BUILDER_KEY:=/root/.ssh/id_ed25519}"
 
 CACHE_PUB_KEY="cache.local-1:usoWYanY3Kpq2+kDIS2nhWoLZiRxanmdysdzqCFBHW4="
 FALLBACK_URL="https://cache.nixos.org/"
 FALLBACK_PUB_KEY="cache.nixos.org-1:6NCHdD59X431o0gWypbMrAURkbJ16ZPMQFGspcDShjY="
 
-NIX_CONF="/etc/nix/nix.conf"
-KNOWN_HOSTS="/etc/ssh/ssh_known_hosts"
 MARKER_BEGIN="# BEGIN nix-cache client config (configure-nix-cache-client.sh)"
 MARKER_END="# END nix-cache client config"
 
+# Mode: root uses system-wide paths and restarts the daemon; non-root uses
+# user-level paths and has no daemon to restart.
+if [[ "$EUID" -eq 0 ]]; then
+  install_mode="multi"
+  NIX_CONF="/etc/nix/nix.conf"
+  KNOWN_HOSTS="/etc/ssh/ssh_known_hosts"
+  : "${REMOTE_BUILDER_KEY:=/root/.ssh/id_ed25519}"
+else
+  install_mode="single"
+  NIX_CONF="${XDG_CONFIG_HOME:-$HOME/.config}/nix/nix.conf"
+  KNOWN_HOSTS="$HOME/.ssh/known_hosts"
+  : "${REMOTE_BUILDER_KEY:=$HOME/.ssh/id_ed25519}"
+fi
+
 dry_run=0
 with_remote_builder=1
 restart_daemon=1
@@ -57,7 +72,7 @@ for arg in "$@"; do
     --no-remote-builder) with_remote_builder=0 ;;
     --no-restart) restart_daemon=0 ;;
     -h|--help)
-      sed -n '2,20p' "$0"
+      sed -n '2,37p' "$0"
       exit 0
       ;;
     *)
@@ -67,21 +82,22 @@ for arg in "$@"; do
   esac
 done
 
-if [[ "$dry_run" -eq 0 && "$EUID" -ne 0 ]]; then
-  echo "ERROR: must run as root (writes $NIX_CONF and, unless --no-remote-builder, $KNOWN_HOSTS)." >&2
-  exit 1
-fi
-
 if ! command -v nix >/dev/null 2>&1; then
   echo "ERROR: no 'nix' binary on PATH -- install the Nix package manager first." >&2
   exit 1
 fi
 
-if [[ ! -f "$NIX_CONF" ]]; then
+if [[ "$install_mode" == "multi" && ! -f "$NIX_CONF" ]]; then
   echo "ERROR: $NIX_CONF not found -- expected an existing multi-user Nix install." >&2
   exit 1
 fi
 
+# Single-user: create the config file if it doesn't exist yet.
+if [[ "$install_mode" == "single" && "$dry_run" -eq 0 ]]; then
+  mkdir -p "$(dirname "$NIX_CONF")"
+  [[ -f "$NIX_CONF" ]] || touch "$NIX_CONF"
+fi
+
 builder_line=""
 if [[ "$with_remote_builder" -eq 1 ]]; then
   if [[ -f "$REMOTE_BUILDER_KEY" ]]; then
@@ -117,7 +133,7 @@ fi
 block="${block}
 $MARKER_END"
 
-echo "== nix.conf block to install =="
+echo "== nix.conf block to install ($NIX_CONF) =="
 echo "$block"
 echo "================================"
 
@@ -159,7 +175,8 @@ if [[ "$with_remote_builder" -eq 1 ]]; then
   fi
 fi
 
-if [[ "$dry_run" -eq 0 && "$restart_daemon" -eq 1 ]]; then
+# Only restart the daemon for multi-user installs -- single-user has no daemon.
+if [[ "$dry_run" -eq 0 && "$restart_daemon" -eq 1 && "$install_mode" == "multi" ]]; then
   if command -v systemctl >/dev/null 2>&1 && systemctl is-active --quiet nix-daemon 2>/dev/null; then
     systemctl restart nix-daemon
     echo "Restarted nix-daemon to pick up the new config."

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 ${vmid}"
-  [[ "$kind" == "lxc" ]] && config_cmd="pct config ${vmid}"
+  local config_cmd="${sudo_prefix} qm 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 resize_cmd="qm resize"
-  [[ "$kind" == "lxc" ]] && set_cmd="pct set" && resize_cmd="pct resize"
+  local set_cmd="${sudo_prefix} qm set"
+  local resize_cmd="${sudo_prefix} qm resize"
+  [[ "$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 $1}'); do
-  n="$(qm config "$id" 2>/dev/null | grep -oP '^name:\s*\K\S+' || true)"
+sudo_pfx="$2"
+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 $1}'); do
-  n="$(pct config "$id" 2>/dev/null | grep -oP '^hostname:\s*\K\S+' || true)"
+for id in $($sudo_pfx pct list 2>/dev/null | awk 'NR>1{print $1}'); do
+  n="$($sudo_pfx pct config "$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 ${id}" 2>/dev/null | grep -q running; then
-          ssh "$ssh_target" "qm stop ${id}"
+        if ssh "$ssh_target" "${sudo_prefix} qm status ${id}" 2>/dev/null | grep -q running; then
+          ssh "$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 ${vmid}" >/dev/null 2>&1 \
-    || ssh "$ssh_target" "pct status ${vmid}" >/dev/null 2>&1; then
+  if ssh "$ssh_target" "${sudo_prefix} qm status ${vmid}" >/dev/null 2>&1 \
+    || ssh "$ssh_target" "${sudo_prefix} pct status ${vmid}" >/dev/null 2>&1; then
     echo "ERROR: VMID ${vmid} already exists on ${node}. Refusing to touch an" >&2
     echo "existing resource here -- use --modify to reconfigure it, pick a" >&2
     echo "different --vmid, or omit it to auto-assign." >&2
@@ -672,11 +683,11 @@ if [[ "$image_already_remote" -eq 0 && -z "$local_image" ]]; then
       # hands the result to the remote shell to re-split, which would
       # otherwise scatter NIX_EXTRA_OPTS (itself several space-separated,
       # %q-quoted tokens) across the wrong positional parameters below.
-      printf -v remote_cmd 'bash -s -- %q %q %q %q %q' \
-        "$remote_repo_dir" "$flake_target" "$remote_dir" "$remote_filename" "$NIX_EXTRA_OPTS"
+      printf -v remote_cmd 'bash -s -- %q %q %q %q %q %q' \
+        "$remote_repo_dir" "$flake_target" "$remote_dir" "$remote_filename" "$NIX_EXTRA_OPTS" "$sudo_prefix"
       ssh "$ssh_target" "$remote_cmd" <<'REMOTE_SCRIPT'
 set -euo pipefail
-repo_dir="$1"; target="$2"; dest_dir="$3"; dest_name="$4"; nix_extra_opts_str="$5"
+repo_dir="$1"; target="$2"; dest_dir="$3"; dest_name="$4"; nix_extra_opts_str="$5"; sudo_pfx="$6"
 declare -a NIX_OPTS=()
 [[ -n "$nix_extra_opts_str" ]] && eval "NIX_OPTS=(${nix_extra_opts_str})"
 cd "$repo_dir"
@@ -694,23 +705,14 @@ if [[ -z "$built" ]]; then
   echo "ERROR: no tarball found under result-${target}/tarball after build." >&2
   exit 1
 fi
-mkdir -p "$dest_dir"
-cp "$built" "${dest_dir}/${dest_name}"
+$sudo_pfx mkdir -p "$dest_dir"
+$sudo_pfx cp "$built" "${dest_dir}/${dest_name}"
 echo "Built and staged: ${dest_dir}/${dest_name}"
 REMOTE_SCRIPT
       local_image="$remote_path"
       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.${flake_target}.config.system.build.diskoImagesScript"
@@ -728,7 +730,7 @@ REMOTE_SCRIPT
         "$remote_repo_dir" "$flake_target" "$remote_dir" "$remote_filename" "$NIX_EXTRA_OPTS" "$sudo_prefix"
       ssh "$ssh_target" "$remote_cmd" <<'REMOTE_SCRIPT'
 set -euo pipefail
-repo_dir="$1"; target="$2"; dest_dir="$3"; dest_name="$4"; nix_extra_opts_str="$5"; sudo_prefix="$6"
+repo_dir="$1"; target="$2"; dest_dir="$3"; dest_name="$4"; nix_extra_opts_str="$5"; sudo_pfx="$6"
 declare -a NIX_OPTS=()
 [[ -n "$nix_extra_opts_str" ]] && eval "NIX_OPTS=(${nix_extra_opts_str})"
 cd "$repo_dir"
@@ -737,7 +739,7 @@ ensure_nix_profile
 nix build --no-use-registries --no-accept-flake-config "${NIX_OPTS[@]}" \
   ".#nixosConfigurations.${target}.config.system.build.diskoImagesScript" \
   --out-link "result-${target}"
-$sudo_prefix "./result-${target}" \
+$sudo_pfx "./result-${target}" \
   --pre-format-files "host-keys/${target}_ssh_host_ed25519_key" /etc/ssh/ssh_host_ed25519_key \
   --pre-format-files "host-keys/${target}_ssh_host_ed25519_key.pub" /etc/ssh/ssh_host_ed25519_key.pub \
   --build-memory 2048
@@ -746,8 +748,8 @@ if [[ -z "$built" ]]; then
   echo "ERROR: no .raw image found in ${repo_dir} after build." >&2
   exit 1
 fi
-mkdir -p "$dest_dir"
-mv "$built" "${dest_dir}/${dest_name}"
+$sudo_pfx mkdir -p "$dest_dir"
+$sudo_pfx mv "$built" "${dest_dir}/${dest_name}"
 echo "Built and staged: ${dest_dir}/${dest_name}"
 REMOTE_SCRIPT
       local_image="$remote_path"
@@ -812,9 +814,9 @@ if [[ "$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} -- qm set ${vmid} --boot order=scsi0" >&2
+      echo "  ssh ${ssh_target} -- ${sudo_display}qm set ${vmid} --scsi0 ${storage}:<disk-id-from-output-above>" >&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 "qm start ${vmid}"
+  remote "${sudo_prefix} qm set ${vmid} --boot order=scsi0"
+  remote "${sudo_prefix} qm start ${vmid}"
 fi
 
 echo