Fix duplicate-host check reporting false SSH failures

The remote bash script run over SSH ended with a for-loop whose last statement was `[[ "$n" == "$target" ]] && echo ...`. When the last VM/CT checked on the node didn't match --host, that test evaluated false and became the exit status of the whole remote script (1) -- which the wrapper then misreported as "couldn't reach the node", even though SSH connectivity and the check itself were both fine. The actual signal is the script's stdout, not its exit code, so end it with an explicit exit 0. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Merge pull request 'Stop tracking deployment status in the README Hosts table' (#7 ) from remove-deploy-status-from-readme into main
2026-07-20 10:55:53 +00:00 · 2026-07-20 10:51:59 +00:00 · 2026-07-20 10:18:33 +00:00
9 changed files with 78 additions and 155 deletions
@@ -18,22 +18,23 @@ list:

 | Target | Purpose |
 | --- | --- |
-| `linode-minimal` | Minimal NixOS host profile on a Linode VPS (real, deployed) |
-| `proxmox-minimal` | Minimal NixOS host profile on Proxmox (real, deployed — previously the flat `nix-minimal` target) |
+| `linode-minimal` | Minimal NixOS host profile on a Linode VPS |
+| `proxmox-minimal` | Minimal NixOS host profile on Proxmox — previously the flat `nix-minimal` target |
 | `lxc-minimal` | Minimal NixOS host profile in a Proxmox LXC container |
-| `linode-nix-cache` / `proxmox-nix-cache` / `lxc-nix-cache` | Local Nix binary cache and remote builder (`lxc-nix-cache` is the real, deployed one — previously `proxmox-nix-cache`, itself previously the flat `nix-cache` target) |
-| `linode-server` / `proxmox-server` / `lxc-server` | Storage, NFS, backup, and monitoring exporter host (`proxmox-server` is the real, deployed one — previously the flat `server` target) |
-| `linode-docker` / `proxmox-docker` / `lxc-docker` | Docker host for the main container stack (`proxmox-docker` is the real, deployed one — previously the flat `docker` target) |
-| `linode-gui` / `proxmox-gui` / `lxc-gui` | Cinnamon desktop workstation (`proxmox-gui` is the real, deployed one — previously the flat `nixos` target) |
-| `proxmox-pxe-boot` / `lxc-pxe-boot` | HTTP/iPXE boot asset host (`proxmox-pxe-boot` is the real, deployed one — previously the flat `pxe-boot` target) |
-| `linode-tailscale-exit-node` / `proxmox-tailscale-exit-node` / `lxc-tailscale-exit-node` | Tailscale exit node (no deployed target yet; `lxc-tailscale-exit-node` is the one planned for actual use) |
+| `linode-nix-cache` / `proxmox-nix-cache` / `lxc-nix-cache` | Local Nix binary cache and remote builder — previously the flat `nix-cache` target |
+| `linode-server` / `proxmox-server` / `lxc-server` | Storage, NFS, backup, and monitoring exporter host — previously the flat `server` target |
+| `linode-docker` / `proxmox-docker` / `lxc-docker` | Docker host for the main container stack — previously the flat `docker` target |
+| `linode-gui` / `proxmox-gui` / `lxc-gui` | Cinnamon desktop workstation — previously the flat `nixos` target |
+| `proxmox-pxe-boot` / `lxc-pxe-boot` | HTTP/iPXE boot asset host — previously the flat `pxe-boot` target |
+| `linode-tailscale-exit-node` / `proxmox-tailscale-exit-node` / `lxc-tailscale-exit-node` | Tailscale exit node |

-This table is the only place "(real, deployed)" status is tracked — there's
-no separate machine-readable copy to keep in sync. `scripts/create-proxmox-resource.sh`
-guards against creating a same-identity duplicate of an already-deployed host
-by checking the Proxmox node itself (live `qm`/`pct` state) rather than any
-file in this repo, since a static list can't track whether a resource still
-actually exists.
+Which variant of a given buildtype is actually deployed isn't tracked
+anywhere in this repo — that's live infrastructure state, not something a
+committed file can keep accurate, and it changes independently of the code.
+Check the Proxmox node itself, or `/etc/flake-target` on a running host (see
+below), if you need to know what's really out there right now.
+`scripts/create-proxmox-resource.sh`'s duplicate-host guard works the same
+way: it checks the Proxmox node directly rather than any file here.

 Each buildtype's `hosts/<name>/host.nix` carries the per-machine identity
 (hostname, hostId, per-machine secrets, `system.stateVersion`) that must stay
@@ -1,14 +1,22 @@
 #!/usr/bin/env bash
 set -euo pipefail

-script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-# shellcheck source=lib/nix-bootstrap.sh
-source "${script_dir}/lib/nix-bootstrap.sh"
-# shellcheck source=lib/nix-eval.sh
-source "${script_dir}/lib/nix-eval.sh"
+export NIX_CONFIG="${NIX_CONFIG:-}
+experimental-features = nix-command flakes
+accept-flake-config = false
+warn-dirty = false
+"

 MODE="${1:-validate}"

+ensure_nix_profile() {
+  if [ -f /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh ]; then
+    . /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh
+  elif [ -f "$HOME/.nix-profile/etc/profile.d/nix.sh" ]; then
+    . "$HOME/.nix-profile/etc/profile.d/nix.sh"
+  fi
+}
+
 ensure_nix_profile

 if ! command -v nix >/dev/null 2>&1; then
@@ -16,7 +24,8 @@ if ! command -v nix >/dev/null 2>&1; then
  exit 127
 fi

-hosts="$(list_flake_targets .)"
+hosts_json="$(nix eval --json --no-use-registries --no-accept-flake-config .#nixosConfigurations --apply builtins.attrNames)"
+hosts="$(echo "$hosts_json" | jq -r '.[]')"

 echo "Hosts:"
 echo "$hosts"
@@ -35,17 +44,17 @@ fi

 echo
 echo "Checking Nix formatting with nixpkgs-fmt..."
-nix run "${NIX_EVAL_FLAGS[@]}" github:NixOS/nixpkgs/nixos-25.11#nixpkgs-fmt -- --check .
+nix run --no-use-registries --no-accept-flake-config github:NixOS/nixpkgs/nixos-25.11#nixpkgs-fmt -- --check .

 echo
 echo "Running statix lint..."
-nix run "${NIX_EVAL_FLAGS[@]}" github:NixOS/nixpkgs/nixos-25.11#statix -- check .
+nix run --no-use-registries --no-accept-flake-config github:NixOS/nixpkgs/nixos-25.11#statix -- check .

 echo
 echo "Evaluating host toplevel derivations..."
 for host in $hosts; do
  echo "==> $host"
-  nix eval --raw "${NIX_EVAL_FLAGS[@]}" ".#nixosConfigurations.${host}.config.system.build.toplevel.drvPath"
+  nix eval --raw --no-use-registries --no-accept-flake-config ".#nixosConfigurations.${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
@@ -55,21 +64,22 @@ for host in $hosts; do
  case "$host" in
    lxc-*)
      echo "==> $host (tarball)"
-      nix eval --raw "${NIX_EVAL_FLAGS[@]}" ".#nixosConfigurations.${host}.config.system.build.tarball.drvPath"
+      nix eval --raw --no-use-registries --no-accept-flake-config ".#nixosConfigurations.${host}.config.system.build.tarball.drvPath"
      ;;
    proxmox-*)
      echo "==> $host (diskoImagesScript)"
-      nix eval --raw "${NIX_EVAL_FLAGS[@]}" ".#nixosConfigurations.${host}.config.system.build.diskoImagesScript.drvPath"
+      nix eval --raw --no-use-registries --no-accept-flake-config ".#nixosConfigurations.${host}.config.system.build.diskoImagesScript.drvPath"
      ;;
  esac
 done

 echo
 echo "Evaluating buildable packages..."
-packages="$(nix eval --json "${NIX_EVAL_FLAGS[@]}" .#packages.x86_64-linux --apply builtins.attrNames | jq -r '.[]')"
+packages_json="$(nix eval --json --no-use-registries --no-accept-flake-config .#packages.x86_64-linux --apply builtins.attrNames)"
+packages="$(echo "$packages_json" | jq -r '.[]')"
 for pkg in $packages; do
  echo "==> packages.x86_64-linux.${pkg}"
-  nix eval --raw "${NIX_EVAL_FLAGS[@]}" ".#packages.x86_64-linux.${pkg}"
+  nix eval --raw --no-use-registries --no-accept-flake-config ".#packages.x86_64-linux.${pkg}"
 done

 if [[ "$MODE" == "dry-run" ]]; then
@@ -77,16 +87,16 @@ if [[ "$MODE" == "dry-run" ]]; then
  echo "Running dry-run builds for all hosts. This will not create result symlinks."
  for host in $hosts; do
    echo "==> Dry-run build: $host"
-    nix build --dry-run --no-link "${NIX_EVAL_FLAGS[@]}" ".#nixosConfigurations.${host}.config.system.build.toplevel"
+    nix build --dry-run --no-link --no-use-registries --no-accept-flake-config ".#nixosConfigurations.${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.${host}.config.system.build.tarball"
+        nix build --dry-run --no-link --no-use-registries --no-accept-flake-config ".#nixosConfigurations.${host}.config.system.build.tarball"
        ;;
      proxmox-*)
        echo "==> Dry-run build: $host (diskoImagesScript)"
-        nix build --dry-run --no-link "${NIX_EVAL_FLAGS[@]}" ".#nixosConfigurations.${host}.config.system.build.diskoImagesScript"
+        nix build --dry-run --no-link --no-use-registries --no-accept-flake-config ".#nixosConfigurations.${host}.config.system.build.diskoImagesScript"
        ;;
    esac
  done
@@ -95,7 +105,7 @@ if [[ "$MODE" == "dry-run" ]]; then
  echo "Running dry-run builds for all packages."
  for pkg in $packages; do
    echo "==> Dry-run build: packages.x86_64-linux.${pkg}"
-    nix build --dry-run --no-link "${NIX_EVAL_FLAGS[@]}" ".#packages.x86_64-linux.${pkg}"
+    nix build --dry-run --no-link --no-use-registries --no-accept-flake-config ".#packages.x86_64-linux.${pkg}"
  done
 fi

@@ -1,11 +1,19 @@
 #!/usr/bin/env bash
 set -euo pipefail

-script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-# shellcheck source=lib/nix-bootstrap.sh
-source "${script_dir}/lib/nix-bootstrap.sh"
-# shellcheck source=lib/nix-eval.sh
-source "${script_dir}/lib/nix-eval.sh"
+export NIX_CONFIG="${NIX_CONFIG:-}
+experimental-features = nix-command flakes
+accept-flake-config = false
+warn-dirty = false
+"
+
+ensure_nix_profile() {
+  if [ -f /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh ]; then
+    . /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh
+  elif [ -f "$HOME/.nix-profile/etc/profile.d/nix.sh" ]; then
+    . "$HOME/.nix-profile/etc/profile.d/nix.sh"
+  fi
+}

 install_nix_if_missing() {
  if command -v nix >/dev/null 2>&1; then
@@ -71,13 +79,13 @@ if ! command -v jq >/dev/null 2>&1; then
 fi

 echo "Available NixOS hosts:"
-hosts="$(list_flake_targets .)"
+hosts="$(nix eval --json --no-use-registries --no-accept-flake-config .#nixosConfigurations --apply builtins.attrNames | jq -r '.[]')"
 echo "$hosts"

 echo "Evaluating all host toplevel derivations..."
 for host in $hosts; do
  echo "==> Evaluating $host"
-  nix eval --raw "${NIX_EVAL_FLAGS[@]}" ".#nixosConfigurations.${host}.config.system.build.toplevel.drvPath"
+  nix eval --raw --no-use-registries --no-accept-flake-config ".#nixosConfigurations.${host}.config.system.build.toplevel.drvPath"
 done

 echo "Codex setup complete."
@@ -26,8 +26,6 @@ set -euo pipefail
 repo_root="$(cd "$(dirname "$0")/.." && pwd)"
 # shellcheck source=env.sh
 source "${repo_root}/scripts/env.sh"
-# shellcheck source=lib/nix-eval.sh
-source "${repo_root}/scripts/lib/nix-eval.sh"

 sync_keys="${repo_root}/scripts/sync-host-keys.sh"

@@ -242,21 +240,15 @@ platform_prefix="lxc"
 [[ -z "$memory" ]] && memory="$PROXMOX_DEFAULT_MEMORY_MB"

 # --- discover / resolve the flake target from --host --------------------
-# Emits "<target>\t<hostName>" pairs for every ${platform_prefix}-* flake
-# target -- the one source both --list and the --host lookup below read
-# from, so they can never see a different set of targets from each other.
-targets_for_platform() {
-  local target
-  for target in $(list_flake_targets "$repo_root" 2>/dev/null | grep -- "^${platform_prefix}-"); do
-    printf '%s\t%s\n' "$target" "$(flake_target_hostname "$repo_root" "$target")"
-  done
-}
-
 list_hosts() {
  local target hostname
-  while IFS=$'\t' read -r target hostname; do
+  for target in $(nix eval --json --no-use-registries --no-accept-flake-config \
+    "${repo_root}#nixosConfigurations" --apply builtins.attrNames 2>/dev/null \
+    | jq -r --arg p "${platform_prefix}-" '.[] | select(startswith($p))'); do
+    hostname="$(nix eval --raw --no-use-registries --no-accept-flake-config \
+      "${repo_root}#nixosConfigurations.${target}.config.networking.hostName" 2>/dev/null)"
    printf '  %-12s -> %s\n' "$hostname" "$target"
-  done < <(targets_for_platform)
+  done
 }

 if [[ "$do_list" -eq 1 ]]; then
@@ -271,12 +263,16 @@ if [[ -z "$host" ]]; then
 fi

 flake_target=""
-while IFS=$'\t' read -r target hostname; do
-  if [[ "$hostname" == "$host" ]]; then
+for target in $(nix eval --json --no-use-registries --no-accept-flake-config \
+  "${repo_root}#nixosConfigurations" --apply builtins.attrNames \
+  | jq -r --arg p "${platform_prefix}-" '.[] | select(startswith($p))'); do
+  hn="$(nix eval --raw --no-use-registries --no-accept-flake-config \
+    "${repo_root}#nixosConfigurations.${target}.config.networking.hostName")"
+  if [[ "$hn" == "$host" ]]; then
    flake_target="$target"
    break
  fi
-done < <(targets_for_platform)
+done

 if [[ -z "$flake_target" ]]; then
  echo "ERROR: no ${platform_prefix}-* target has hostName '${host}'." >&2
@@ -324,6 +320,7 @@ for id in $(pct list 2>/dev/null | awk 'NR>1{print $1}'); do
  n="$(pct config "$id" 2>/dev/null | grep -oP '^hostname:\s*\K\S+' || true)"
  [[ "$n" == "$target" ]] && echo "lxc ${id} ${n}"
 done
+exit 0
 REMOTE_SCRIPT
  )" || ssh_check_status=$?
  if [[ "$ssh_check_status" -ne 0 ]]; then
@@ -1,20 +0,0 @@
-#!/usr/bin/env bash
-# Shared Nix bootstrap for scripts/codex-setup.sh and
-# scripts/codex-maintenance.sh: the nix.conf settings both need in effect
-# before a single `nix` command runs (flakes enabled, never honor a flake
-# input's own nixConfig, no "dirty tree" warning spam), plus a helper to
-# pull an already-installed Nix's daemon/profile script onto PATH if it
-# isn't there yet. Source this instead of copying it -- see CLAUDE.md.
-export NIX_CONFIG="${NIX_CONFIG:-}
-experimental-features = nix-command flakes
-accept-flake-config = false
-warn-dirty = false
-"
-
-ensure_nix_profile() {
-  if [ -f /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh ]; then
-    . /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh
-  elif [ -f "$HOME/.nix-profile/etc/profile.d/nix.sh" ]; then
-    . "$HOME/.nix-profile/etc/profile.d/nix.sh"
-  fi
-}
@@ -1,36 +0,0 @@
-#!/usr/bin/env bash
-# Shared flake-introspection helpers for scripts/*.sh. Source alongside
-# env.sh:
-#   source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/lib/nix-eval.sh"
-#
-# NIX_EVAL_FLAGS: --no-use-registries so a call here never resolves through
-# the user's global flake registry (every call targets this repo's own
-# flake, or an explicit github: ref, not a registry alias); --no-accept-flake-config
-# so a flake input's own nixConfig (e.g. a dependency's substituters) is
-# never honored -- matches accept-flake-config = false already set repo-wide
-# (see lib/nix-bootstrap.sh / CLAUDE.md). Reuse this array rather than
-# retyping the two flags at each call site.
-declare -a NIX_EVAL_FLAGS=(--no-use-registries --no-accept-flake-config)
-
-# list_flake_targets <flake_ref>
-# Prints the attribute names under <flake_ref>#nixosConfigurations, one per
-# line, e.g.:
-#   list_flake_targets .            # from inside the repo
-#   list_flake_targets "$repo_root" # from anywhere
-list_flake_targets() {
-  local flake_ref="$1"
-  nix eval --json "${NIX_EVAL_FLAGS[@]}" \
-    "${flake_ref}#nixosConfigurations" --apply builtins.attrNames \
-  | jq -r '.[]'
-}
-
-# flake_target_hostname <flake_ref> <target>
-# Prints one nixosConfigurations target's config.networking.hostName.
-# Empty (not an error under set -e) if the target doesn't exist or the
-# eval otherwise fails -- callers that need to distinguish "empty" from
-# "eval failed" should check $? themselves instead of relying on this.
-flake_target_hostname() {
-  local flake_ref="$1" target="$2"
-  nix eval --raw "${NIX_EVAL_FLAGS[@]}" \
-    "${flake_ref}#nixosConfigurations.${target}.config.networking.hostName" 2>/dev/null
-}
@@ -1,30 +0,0 @@
-#!/usr/bin/env bash
-# Shared SSH-host-key / age-conversion helpers for scripts/sync-host-keys.sh
-# and scripts/prepare-host-key.sh -- both generate the same kind of key
-# (ed25519, no passphrase, the sops-nix age-derivation input) and convert it
-# to an age recipient the same way; kept in one place so the two can't
-# drift apart.
-#
-# Uses NIX_OPTS (an array of extra `nix-shell` options -- see env.sh's
-# nix_extra_opts) if the caller has already set it, so a decision to avoid
-# an unreachable nix-cache is reused here instead of probed again. Falls
-# back to no extra options if the caller never sourced env.sh.
-if ! declare -p NIX_OPTS >/dev/null 2>&1; then
-  declare -a NIX_OPTS=()
-fi
-
-# generate_host_ed25519_key <hostname> <keyfile>
-# Writes <keyfile> and <keyfile>.pub. Caller is responsible for refusing to
-# overwrite an existing keyfile -- this always runs ssh-keygen fresh.
-generate_host_ed25519_key() {
-  local hostname="$1" keyfile="$2"
-  nix-shell "${NIX_OPTS[@]}" -p openssh --run \
-    "ssh-keygen -t ed25519 -N '' -C '${hostname}' -f '${keyfile}'" >/dev/null
-}
-
-# ssh_pubkey_to_age <pubkeyfile>
-# Prints the age public key derived from an ed25519 SSH public key file.
-ssh_pubkey_to_age() {
-  local pubkeyfile="$1"
-  nix-shell "${NIX_OPTS[@]}" -p ssh-to-age --run "ssh-to-age -i '${pubkeyfile}'"
-}
@@ -23,10 +23,6 @@
 set -euo pipefail

 repo_root="$(cd "$(dirname "$0")/.." && pwd)"
-# shellcheck source=env.sh
-source "${repo_root}/scripts/env.sh"
-# shellcheck source=lib/ssh-host-keys.sh
-source "${repo_root}/scripts/lib/ssh-host-keys.sh"

 hostname="${1:?usage: scripts/prepare-host-key.sh <hostname>}"
 sops_yaml="${repo_root}/.sops.yaml"
@@ -45,10 +41,9 @@ if [[ -f "$keyfile" ]]; then
  exit 1
 fi

-nix_extra_opts
-generate_host_ed25519_key "$hostname" "$keyfile"
+nix-shell -p openssh --run "ssh-keygen -t ed25519 -N '' -C '${hostname}' -f '${keyfile}'" >/dev/null

-age_pub="$(ssh_pubkey_to_age "${keyfile}.pub")"
+age_pub="$(nix-shell -p ssh-to-age --run "ssh-to-age -i '${keyfile}.pub'")"

 cat <<EOF

@@ -31,10 +31,6 @@ editor="${repo_root}/scripts/lib/sync-host-keys-edit-sops.py"

 # shellcheck source=env.sh
 source "${repo_root}/scripts/env.sh"
-# shellcheck source=lib/nix-eval.sh
-source "${repo_root}/scripts/lib/nix-eval.sh"
-# shellcheck source=lib/ssh-host-keys.sh
-source "${repo_root}/scripts/lib/ssh-host-keys.sh"

 mkdir -p "$keydir"

@@ -122,10 +118,12 @@ EOF
 }

 discover_targets() {
+  nix eval --json --no-use-registries --no-accept-flake-config \
+    "${repo_root}#nixosConfigurations" --apply builtins.attrNames \
+  | jq -r '.[] | select(. != "installer")'
  # installer is the one nixosConfigurations target that doesn't import
  # sops-nix at all (see CLAUDE.md's "Security Notes" -- hardcoded login
  # password instead) -- config.sops.secrets doesn't exist for it.
-  list_flake_targets "$repo_root" | grep -v '^installer$'
 }

 locally_managed_hosts() {
@@ -161,7 +159,7 @@ queue_host_sync() {
      echo "[dry-run] ${host}: would generate host key"
    else
      echo "==> ${host}: generating host key"
-      generate_host_ed25519_key "$host" "$keyfile"
+      nix-shell "${NIX_OPTS[@]}" -p openssh --run "ssh-keygen -t ed25519 -N '' -C '${host}' -f '${keyfile}'" >/dev/null
    fi
  else
    echo "==> ${host}: host key already present"
@@ -172,7 +170,7 @@ queue_host_sync() {
    if [[ "$dry_run" -eq 1 ]]; then
      age_pub="dry-run-placeholder-not-a-real-key"
    else
-      age_pub="$(ssh_pubkey_to_age "${keyfile}.pub")"
+      age_pub="$(nix-shell "${NIX_OPTS[@]}" -p ssh-to-age --run "ssh-to-age -i '${keyfile}.pub'")"
    fi
    add_keys_json="$(jq --arg host "$host" --arg key "$age_pub" \
      '. + [{host: $host, age_key: $key}]' <<<"$add_keys_json")"