From 8c19ee9d72ec15389ab7e168020ed2085ddb8dcd Mon Sep 17 00:00:00 2001
From: beatzaplenty <wayne.bennett@live.com>
Date: Mon, 27 Jul 2026 05:42:32 +1000
Subject: [PATCH] fix(sops): hard-fail on missing admin key and expand literal
 ~ in key path

SOPS_AGE_KEY_FILE was set in hosts/nixos/home.nix sessionVariables with a
literal ~ that Home Manager injects as-is into the environment.  In bash,
tilde expansion does not happen inside double-quoted variable references, so
DEFAULT_SOPS_AGE_KEY_FILE resolved to ~/... literally and the -s file-existence
check in ensure_admin_decrypt_key silently failed.  The script then generated
a brand-new age key (to ~/... relative to the repo root) while the real admin
key at ~/.config/sops/age/keys.txt went untouched -- making it appear the key
was lost when it was actually still intact.

Fix the home.nix root cause by using config.home.homeDirectory so the path
is fully resolved.  Add tilde expansion in ensure_admin_decrypt_key as a
belt-and-suspenders guard for any caller whose environment has the same issue.

Also replace the auto-generate-a-new-key fallback with a hard failure: auto-
generating a new admin key is never useful (it cannot decrypt existing secrets)
and created serious confusion about whether the original key was lost.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 hosts/nixos/home.nix              |  2 +-
 scripts/secrets/sync-host-keys.sh | 41 ++++++++++++-------------------
 2 files changed, 17 insertions(+), 26 deletions(-)

diff --git a/hosts/nixos/home.nix b/hosts/nixos/home.nix
index 64b8b7f..65702e6 100644
--- a/hosts/nixos/home.nix
+++ b/hosts/nixos/home.nix
@@ -27,7 +27,7 @@
     # Optional: set environment vars
     sessionVariables = {
       EDITOR = "vim";
-      SOPS_AGE_KEY_FILE = "~/.config/sops/age/keys.txt";
+      SOPS_AGE_KEY_FILE = "${config.home.homeDirectory}/.config/sops/age/keys.txt";
     };
 
     file = {
diff --git a/scripts/secrets/sync-host-keys.sh b/scripts/secrets/sync-host-keys.sh
index 512929e..3a57373 100755
--- a/scripts/secrets/sync-host-keys.sh
+++ b/scripts/secrets/sync-host-keys.sh
@@ -85,6 +85,10 @@ ensure_admin_decrypt_key() {
   fi
 
   local key_file="$DEFAULT_SOPS_AGE_KEY_FILE"
+  # Expand a leading ~ that survived variable substitution without tilde
+  # expansion (happens when SOPS_AGE_KEY_FILE or XDG_CONFIG_HOME is set with
+  # a literal ~ in the caller's environment).
+  key_file="${key_file/#~\//$HOME/}"
 
   if [[ -s "$key_file" ]]; then
     echo "Found existing sops age key at ${key_file}."
@@ -93,36 +97,23 @@ ensure_admin_decrypt_key() {
 
   if [[ "$dry_run" -eq 1 ]]; then
     echo "[dry-run] No sops age decryption key found (checked \$SOPS_AGE_KEY, \$SOPS_AGE_KEY_FILE, ${key_file})."
-    echo "[dry-run] Would generate a new one here -- continuing the dry run without one; any"
-    echo "[dry-run] 'would re-encrypt' output below couldn't actually run for real yet."
+    echo "[dry-run] Continuing dry run without one -- any 'would re-encrypt' output below"
+    echo "[dry-run] couldn't actually run for real until a key is present."
     return
   fi
 
-  echo "No sops age decryption key found (checked \$SOPS_AGE_KEY, \$SOPS_AGE_KEY_FILE, ${key_file})."
-  echo "Generating a new one at ${key_file}..."
-  mkdir -p "$(dirname "$key_file")"
-  nix-shell "${NIX_OPTS[@]}" -p age --run "age-keygen -o '${key_file}'" 2>&1 | grep -v "^Public key:" || true
-  local new_pub
-  new_pub="$(age_pubkey_from_identity_file "$key_file")"
+  cat >&2 <<EOF
+No sops age decryption key found (checked \$SOPS_AGE_KEY, \$SOPS_AGE_KEY_FILE, ${key_file}).
 
-  cat <<EOF
+Place your admin age private key at ${key_file}, or set SOPS_AGE_KEY (inline
+key) or SOPS_AGE_KEY_FILE (path to a different key file) and re-run.
 
-A brand-new age key was just generated -- it cannot decrypt anything that
-already exists in secrets/*.yaml, since nothing was ever encrypted for it.
-That trust can't be bootstrapped automatically (nobody can decrypt a file
-for a recipient that didn't exist when it was last encrypted).
-
-To actually use this key:
-  1. Have someone who currently CAN decrypt replace the &admin entry in
-     .sops.yaml with this public key:
-       ${new_pub}
-  2. They re-encrypt every secrets/*.yaml:
-       sops updatekeys --yes secrets/common.yaml
-       sops updatekeys --yes secrets/nix-cache.yaml
-       sops updatekeys --yes secrets/server.yaml
-  3. Re-run this script.
-
-Exiting without making any other changes.
+If the key is truly missing (not just mislocated), this is a manual recovery
+situation -- generating a brand-new admin key won't help, since it cannot
+decrypt anything already encrypted for the old one.  Each secrets/*.yaml is
+also encrypted for its respective host key(s), so a running deployed host can
+still decrypt what it needs -- but the admin key is required for re-encryption
+(e.g. adding new recipients via sops updatekeys).
 EOF
   exit 1
 }