server: auto-create tank ZFS pool on first boot if data disk is blank

A fresh proxmox-server deploy has a blank scsi1 disk, so
zfs-import-tank.service spun 60 s then failed with no pool found.
Add zfs-init-tank.service that runs before the import: exits immediately
if the pool already exists, imports it if it exists but isn't imported
yet, or creates it on /dev/disk/by-id/scsi-*drive-scsi1 (Proxmox's
virtio-scsi naming for the second disk) with all required NFS datasets
if the disk is blank.

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

hosts/nixos/home.nix

@@ -20,6 +20,7 @@
       #    vscode
       chromium
       claude-code
+      fish
     ];
 
     # Optional: set environment vars

modules/build-types/server.nix

@@ -1,12 +1,74 @@
-{ vars, lib, ... }:
+{ vars, lib, pkgs, ... }:
 
+let
+  poolName = lib.removePrefix "/" vars.storageRoot;
+
+  # For each NFS share subpath, generate every ancestor path so ZFS datasets
+  # are created parent-first.  e.g. "docker/config" → ["docker" "docker/config"]
+  ancestors = path:
+    let parts = lib.splitString "/" path;
+    in lib.imap1 (i: _: lib.concatStringsSep "/" (lib.take i parts)) parts;
+
+  poolDatasets = lib.unique (
+    lib.concatMap (share: ancestors share.subpath) (lib.attrValues vars.nfsShares)
+  );
+in
 {
   imports = [
     ../beszel/enable-agent.nix
     ../services/zfs/enable-service.nix
   ];
 
-  boot.zfs.extraPools = [ (lib.removePrefix "/" vars.storageRoot) ];
+  boot.zfs.extraPools = [ poolName ];
+
+  # On a fresh image deploy the data disk (scsi1) starts blank — no pool
+  # exists yet, so zfs-import-tank.service would spin for 60 s and fail.
+  # This service runs first: if the pool is already present it exits instantly;
+  # otherwise it creates it (with all required datasets) so the standard
+  # import service finds it ready on the very first boot.
+  systemd.services."zfs-init-${poolName}" = {
+    description = "Initialize '${poolName}' ZFS pool on first boot if not present";
+    wantedBy = [ "zfs-import-${poolName}.service" ];
+    before = [ "zfs-import-${poolName}.service" ];
+    after = [ "systemd-udev-settle.service" ];
+    unitConfig.DefaultDependencies = false;
+    serviceConfig = {
+      Type = "oneshot";
+      RemainAfterExit = true;
+    };
+    path = [ pkgs.zfs_unstable ];
+    script = ''
+      # Already imported — nothing to do.
+      if zpool list "${poolName}" >/dev/null 2>&1; then
+        exit 0
+      fi
+
+      # Pool exists on a device but not yet imported — let the standard
+      # zfs-import-${poolName}.service handle it normally.
+      if zpool import -d /dev/disk/by-id -N "${poolName}" 2>/dev/null; then
+        exit 0
+      fi
+
+      # No pool found at all.  Create it on the Proxmox data disk (scsi1),
+      # which appears as /dev/disk/by-id/scsi-*drive-scsi1 inside the VM.
+      DATA_DISK=""
+      for candidate in /dev/disk/by-id/scsi-*drive-scsi1; do
+        [[ "$candidate" == *-part* ]] && continue
+        [ -b "$candidate" ] && DATA_DISK="$candidate" && break
+      done
+
+      if [ -z "$DATA_DISK" ]; then
+        echo "zfs-init-${poolName}: no data disk found (expected /dev/disk/by-id/scsi-*drive-scsi1)" >&2
+        exit 1
+      fi
+
+      echo "zfs-init-${poolName}: creating pool on $DATA_DISK"
+      zpool create -f "${poolName}" "$DATA_DISK"
+      ${lib.concatMapStrings (ds: ''
+        zfs create "${poolName}/${ds}"
+      '') poolDatasets}
+    '';
+  };
 
   systemd.services.nfs-server = {
     after = [ "zfs-mount.service" ];

modules/common/configuration.nix

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

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

@@ -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/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

@@ -683,11 +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"
@@ -705,8 +705,8 @@ 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="$remote_path"
@@ -730,7 +730,7 @@ REMOTE_SCRIPT
         "$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"
@@ -739,7 +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/${target}_ssh_host_ed25519_key.pub" /etc/ssh/ssh_host_ed25519_key.pub \
   --build-memory 2048
@@ -748,8 +748,8 @@ if [[ -z "$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"