Merge pull request 'Fix proxmox remote build bootstrap' (#16) from fix-proxmox-remote-build-bootstrap into main

Reviewed-on: #16

scripts/codex-setup.sh

@@ -41,6 +41,17 @@ warn-dirty = false
 build-users-group = nixbld
 EOF
 
+    # The official installer's single-user root path still shells out to
+    # `sudo` to create /nix even though it already knows it's running as
+    # root -- confirmed live against a sudo-less minimal Debian/Proxmox
+    # node, where it fails with "sudo: not found" and prints this exact
+    # mkdir/chown as the manual fix. Pre-create it so that branch of the
+    # installer is skipped entirely.
+    if [ ! -d /nix ]; then
+      mkdir -m 0755 /nix
+      chown root /nix
+    fi
+
     sh <(curl -L https://nixos.org/nix/install) --no-daemon
   else
     sh <(curl -L https://nixos.org/nix/install) --no-daemon

scripts/create-proxmox-resource.sh

@@ -524,7 +524,7 @@ ensure_remote_repo() {
   echo
   echo "==> Ensuring ${remote_repo_dir} exists and is current on ${node}..."
   if [[ "$dry_run" -eq 1 ]]; then
-    echo "[dry-run] would ensure ${remote_repo_dir} exists on ${node} (clone + scripts/codex-setup.sh if missing, git pull if present)"
+    echo "[dry-run] would ensure ${remote_repo_dir} exists on ${node} (clone if missing, git pull if present), and would verify/bootstrap build tooling there (scripts/codex-setup.sh) if \`nix\` isn't already on PATH"
     return
   fi
 
@@ -542,6 +542,33 @@ ensure_remote_repo() {
     fi
     echo "Not present -- cloning from ${origin_url}..."
     ssh "$ssh_target" "git clone '${origin_url}' '${remote_repo_dir}'"
+  fi
+
+  # Trivial check, run every time (not just right after a fresh clone) --
+  # confirmed live: a first bootstrap can clone the repo successfully and
+  # still leave the node without a working `nix` (e.g. the node had no
+  # `sudo`, which the Nix installer's root path depends on -- see the fix
+  # in scripts/codex-setup.sh), and a later run with the repo already
+  # present would otherwise never retry it. Sources
+  # scripts/lib/nix-bootstrap.sh's ensure_nix_profile first -- a
+  # single-user Nix install typically only gets sourced into login shells,
+  # and ssh's non-interactive command execution is neither, so a
+  # freshly-installed `nix` still wouldn't be on PATH here without it.
+  #
+  # Just `nix` today -- the only thing the remote build commands below
+  # actually invoke -- but a list (not a single hardcoded check) so a
+  # future remote step needing another tool can add itself here instead of
+  # growing a parallel check.
+  local remote_required_cmds=(nix)
+  local tooling_check_cmd="cd '${remote_repo_dir}' && . scripts/lib/nix-bootstrap.sh && ensure_nix_profile"
+  local cmd
+  for cmd in "${remote_required_cmds[@]}"; do
+    tooling_check_cmd="${tooling_check_cmd} && command -v ${cmd}"
+  done
+
+  if ssh "$ssh_target" "$tooling_check_cmd" >/dev/null 2>&1; then
+    echo "Build tooling already present on ${node}."
+  else
     echo "==> Bootstrapping build tooling on ${node} (scripts/codex-setup.sh)..."
     ssh "$ssh_target" "cd '${remote_repo_dir}' && bash scripts/codex-setup.sh"
   fi
@@ -625,6 +652,11 @@ repo_dir="$1"; target="$2"; dest_dir="$3"; dest_name="$4"; nix_extra_opts_str="$
 declare -a NIX_OPTS=()
 [[ -n "$nix_extra_opts_str" ]] && eval "NIX_OPTS=(${nix_extra_opts_str})"
 cd "$repo_dir"
+# A single-user Nix install only gets sourced into login shells; this ssh
+# session is neither, so `nix` wouldn't otherwise be on PATH here even
+# right after a successful install.
+. scripts/lib/nix-bootstrap.sh
+ensure_nix_profile
 NIXOS_HOST_KEYS_DIR="$(pwd)/host-keys" nix build --impure \
   --no-use-registries --no-accept-flake-config "${NIX_OPTS[@]}" \
   ".#nixosConfigurations.${target}.config.system.build.tarball" \
@@ -672,6 +704,8 @@ repo_dir="$1"; target="$2"; dest_dir="$3"; dest_name="$4"; nix_extra_opts_str="$
 declare -a NIX_OPTS=()
 [[ -n "$nix_extra_opts_str" ]] && eval "NIX_OPTS=(${nix_extra_opts_str})"
 cd "$repo_dir"
+. scripts/lib/nix-bootstrap.sh
+ensure_nix_profile
 nix build --no-use-registries --no-accept-flake-config "${NIX_OPTS[@]}" \
   ".#nixosConfigurations.${target}.config.system.build.diskoImagesScript" \
   --out-link "result-${target}"