From 7b4794211de22585d7aeb04e29a7332c95970ca2 Mon Sep 17 00:00:00 2001
From: beatzaplenty <wayne.bennett@live.com>
Date: Wed, 29 Jul 2026 13:53:02 +1000
Subject: [PATCH] fix(gc-hosts): fix pve1 PATH and discovery sudo prompts

Two bugs:

1. Dynamic discovery used BatchMode=yes for the pct/qm list SSH call, which
   silently suppressed any sudo password prompt and returned empty output.
   Fix: split SSH_OPTS into SSH_OPTS (BatchMode, for gc) and SSH_QUERY_OPTS
   (no BatchMode, for discovery) so sudo can prompt when needed.

2. pve1 gc used a non-login SSH session which doesn't source /etc/profile,
   so nix-collect-garbage was never on PATH. The Nix installer registers
   itself via /etc/profile.d/nix-daemon.sh which only runs in login shells.
   Fix: use "bash -l -c 'nix-collect-garbage -d'" instead.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 scripts/gc-hosts.sh | 29 +++++++++++++++++------------
 1 file changed, 17 insertions(+), 12 deletions(-)

diff --git a/scripts/gc-hosts.sh b/scripts/gc-hosts.sh
index 3a87cd0..e884ad9 100755
--- a/scripts/gc-hosts.sh
+++ b/scripts/gc-hosts.sh
@@ -14,8 +14,8 @@
 # "nix-collect-garbage -d" if sudo needs a password — still collects
 # unreferenced store paths and old nixos-user profile generations, but leaves
 # old system generations in place.
-# pve1: runs "nix-collect-garbage -d" as the login user (no system generations
-# on a non-NixOS host).
+# pve1: runs "bash -l -c nix-collect-garbage -d" as the login user so
+# /etc/profile is sourced and the Nix daemon's PATH is set up automatically.
 #
 # Usage (from repo root):
 #   bash scripts/gc-hosts.sh [--dry-run]
@@ -30,7 +30,12 @@ source scripts/lib/nix-eval.sh 2>/dev/null || true
 : "${MAX_JOBS:=8}"
 : "${NIXOS_USER:=nixos}"
 : "${PVE1_SSH_USER:=${PROXMOX_SSH_USER:-wayne}}"
+
+# GC connections use BatchMode — no interactive prompts, just succeed or fail.
 SSH_OPTS=(-o StrictHostKeyChecking=no -o BatchMode=yes -o ConnectTimeout=10)
+# Discovery connections do NOT use BatchMode so that sudo can prompt if needed
+# (pct/qm list require root access on Proxmox).
+SSH_QUERY_OPTS=(-o StrictHostKeyChecking=no -o ConnectTimeout=10)
 
 DRY_RUN=0
 for arg in "$@"; do
@@ -44,7 +49,7 @@ done
 
 # ORDERED_HOSTS: names in display/execution order.
 # HOST_TARGET[name]: SSH target string (user@host).
-# HOST_TYPE[name]: "nixos" (try sudo gc, fallback user) | "nix" (user gc only).
+# HOST_TYPE[name]: "nixos" (try sudo gc, fallback user) | "nix" (login-shell gc).
 declare -a  ORDERED_HOSTS=()
 declare -A  HOST_TARGET=()
 declare -A  HOST_TYPE=()
@@ -78,10 +83,10 @@ if ! hostname_map="$(
   echo "  warning: flake eval failed — skipping dynamic host discovery" >&2
 fi
 
-# Get names of all currently running guests from pve1.
-if ssh "${SSH_OPTS[@]}" "${PVE1_SSH_USER}@${PVE1_HOST}" "true" 2>/dev/null; then
+# SSH_QUERY_OPTS (no BatchMode) so sudo can prompt if wayne's sudo needs a password.
+if ssh "${SSH_QUERY_OPTS[@]}" "${PVE1_SSH_USER}@${PVE1_HOST}" "true" 2>/dev/null; then
   running_guests="$(
-    ssh "${SSH_OPTS[@]}" "${PVE1_SSH_USER}@${PVE1_HOST}" bash <<'REMOTE'
+    ssh "${SSH_QUERY_OPTS[@]}" "${PVE1_SSH_USER}@${PVE1_HOST}" bash <<'REMOTE'
       { sudo pct list 2>/dev/null | awk 'NR>1 && $2=="running" { print $NF }';
         sudo qm  list 2>/dev/null | awk 'NR>1 && $3=="running" { print $2  }'; } | sort -u
 REMOTE
@@ -95,7 +100,7 @@ REMOTE
       | jq -r --arg g "$guest" '.[$g] // empty' 2>/dev/null || true)"
     [[ -z "$hostname" ]] && continue
 
-    # Exclude nix-cache and any target whose hostname is already in our list.
+    # Exclude nix-cache and any hostname already in the list.
     case "$hostname" in nix-cache) continue ;; esac
     if [[ -n "${_SEEN_HOSTNAMES[$hostname]+_}" ]]; then continue; fi
 
@@ -121,7 +126,7 @@ if [[ "$DRY_RUN" -eq 1 ]]; then
       echo "  ssh ${SSH_OPTS[*]} $target 'sudo -n nix-collect-garbage -d'"
       echo "  # fallback: ssh ... $target 'nix-collect-garbage -d'"
     else
-      echo "  ssh ${SSH_OPTS[*]} $target '. /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh && nix-collect-garbage -d'"
+      echo "  ssh ${SSH_OPTS[*]} $target 'bash -l -c nix-collect-garbage -d'"
     fi
   done
   exit 0
@@ -147,10 +152,10 @@ gc_one() {
       echo "ok(user)"; return
     fi
   else
-    # Non-NixOS node: BatchMode SSH doesn't source the Nix daemon profile, so
-    # nix-collect-garbage won't be on PATH unless we source it explicitly.
-    local nix_profile='. /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh 2>/dev/null || true'
-    if ssh "${SSH_OPTS[@]}" "$target" "$nix_profile && nix-collect-garbage -d" \
+    # Non-NixOS node: use a login shell so /etc/profile is sourced and the
+    # Nix daemon's bin dir is on PATH (set up by /etc/profile.d/nix-daemon.sh
+    # which the Nix installer adds to /etc/profile).
+    if ssh "${SSH_OPTS[@]}" "$target" "bash -l -c 'nix-collect-garbage -d'" \
         >>"$logfile" 2>>"$logfile"; then
       echo "ok"; return
     fi