commands/bootstrap.sh

@@ -229,7 +229,11 @@ rm -f "$TMP"
 eff="$(sshd -T 2>/dev/null)" || die "sshd -T failed; refusing to claim a hardened box"
 echo "$eff" | grep -qx 'passwordauthentication no' \
   || die "sshd still resolves passwordauthentication=yes — a drop-in is beating ${DROPIN}; check ls /etc/ssh/sshd_config.d/"
-echo "$eff" | grep -qxE 'permitrootlogin (prohibit-password|without-password)' \
+# `no` is accepted because it is the post-`rig users close-root` state —
+# strictly harder than the prohibit-password this script installs. Bootstrap
+# must never read a closed door as a broken one, and it cannot reopen one
+# either: by first-wins its own drop-in loses to 00-rig-users.conf.
+echo "$eff" | grep -qxE 'permitrootlogin (no|prohibit-password|without-password)' \
   || die "sshd still permits root password login — check ls /etc/ssh/sshd_config.d/"
 log "sshd hardening verified (sshd -T: passwordauthentication no)"
 

commands/lib/users-config.sh

@@ -79,8 +79,36 @@ parse_users_file() {
 # read_role_marker <path> — the marker line bootstrap wrote
 # (`role=... class=... host=... join=...`), or nothing when absent. NO policy
 # here: what an absent marker or a given class MEANS is each caller's call
-# (apply notes it, close-root refuses on it) — the lib only reads.
+# (apply notes it, close-root refuses on it) — this reader only reads.
 read_role_marker() {
   [ -r "$1" ] || return 0
   head -n1 "$1"
 }
+
+# assert_marker_human <marker_path> — close-root's marker gate: return 0,
+# silently, only when the marker says class=human; otherwise print the refusal
+# reason on stdout and return 1 (the caller wraps it in its own die). The
+# policy is a pure lib function on purpose: the CLI path sits behind the root
+# check, so the harness proves every refusal HERE, against fixture markers,
+# non-root (repo precedent: parse_users_file, assert_runner_repo).
+assert_marker_human() {
+  local marker
+  marker="$(read_role_marker "$1")"
+  if [ -z "$marker" ]; then
+    # No marker means rig cannot know whether root here is a human's bad habit
+    # or the control plane's automation door — refuse to shut it blind.
+    printf '%s\n' "no /etc/rig/role marker: re-run rig bootstrap so this box knows what it is; refusing to shut the root door blind"
+    return 1
+  fi
+  case "$marker" in
+    *class=human*) return 0 ;;
+    *class=server*)
+      # Root SSH on a server IS the control plane's (Coolify's) automation
+      # identity — closing it severs fleet management. No --force exists.
+      printf '%s\n' "class=server: root here is the control plane's automation identity — closing it severs fleet management"
+      return 1 ;;
+    *)
+      printf '%s\n' "marker names no class (${marker}): re-run rig bootstrap; refusing to shut the root door blind"
+      return 1 ;;
+  esac
+}

commands/users-close-root.sh

@@ -0,0 +1,112 @@
+#!/usr/bin/env bash
+# rig users close-root — shut the human-class root SSH door, once and only
+# once a named admin can already get in. class decides root SSH's fate (#26):
+# on class=human a root login is unattributable noise, so it goes; on
+# class=server root IS the control plane's automation identity, so closing it
+# would sever fleet management — this command refuses there, and no --force
+# exists. Convergent: a second run is a no-op and says so.
+set -euo pipefail
+
+HERE="$(cd "$(dirname "$(readlink -f "${BASH_SOURCE[0]}")")" && pwd)"
+# shellcheck source=SCRIPTDIR/lib/users-config.sh
+. "$HERE/lib/users-config.sh"
+
+log()  { printf 'rig-users: %s\n' "$*"; }
+die()  { printf 'rig-users: ERROR: %s\n' "$1" >&2; exit "${2:-1}"; }
+
+usage() {
+  cat <<'EOF'
+usage: rig users close-root
+
+Shuts the root SSH door: installs /etc/ssh/sshd_config.d/00-rig-users.conf
+carrying exactly `PermitRootLogin no`, which beats bootstrap's drop-in by
+first-wins include order.
+
+Human class ONLY. On class=server, root SSH is the control plane's (Coolify's)
+automation identity — closing it severs fleet management — so close-root
+refuses there, with no --force. It also refuses without a role marker (re-run
+rig bootstrap; never shut the root door blind) and refuses while no rig-admin
+member holds a working authorized_keys (run rig users apply first; never close
+the only door).
+
+Before running, verify your admin login in a SEPARATE session — `ssh
+<admin>@<box>` while this one stays open. Root SSH is the door being welded
+shut; the admin door must be proven, not presumed.
+
+Run as root. Convergent: once root is closed, a re-run is a clean no-op.
+EOF
+}
+
+# --- args (validated before the root check, so errors are testable) ---------
+while [ $# -gt 0 ]; do
+  case "$1" in
+    -h|--help) usage; exit 0 ;;
+    *) die "unknown flag: $1" 2 ;;
+  esac
+done
+
+# --- guards ------------------------------------------------------------------
+[ "$(id -u)" -eq 0 ] || die "must run as root"
+
+# Marker gate — the policy lives in assert_marker_human (lib) so the harness
+# can prove its refusals against fixture markers as non-root; RIG_ROLE_MARKER
+# exists for the same reason: it keeps the command's own gate pointable at
+# fixtures instead of only at the real /etc/rig/role.
+if ! WHY="$(assert_marker_human "${RIG_ROLE_MARKER:-/etc/rig/role}")"; then
+  die "$WHY"
+fi
+
+# Admin-door gate — never close the only door. Root SSH goes away below, so at
+# least one rig-admin member must already hold a non-empty authorized_keys:
+# "verified in a separate session" cannot be automated, but a key at the door
+# can be, and its absence is proof enough to stop.
+ADMIN_OK=0
+while IFS= read -r a; do
+  [ -n "$a" ] || continue
+  h="$(getent passwd "$a" | cut -d: -f6)"
+  if [ -n "$h" ] && [ -s "$h/.ssh/authorized_keys" ]; then ADMIN_OK=1; break; fi
+done < <(getent group rig-admin | cut -d: -f4 | tr ',' '\n')
+[ "$ADMIN_OK" -eq 1 ] \
+  || die "no admin user with a key on this box — run rig users apply first; never close the only door"
+
+# --- the drop-in --------------------------------------------------------------
+# The NAME is the entire mechanism: sshd_config is FIRST-wins ("for each
+# keyword, the first obtained value will be used" — sshd_config(5)), Include
+# expands its glob in lexical order, and '-' (0x2D) sorts before '.' (0x2E),
+# so 00-rig-users.conf is read BEFORE bootstrap's 00-rig.conf and this
+# PermitRootLogin beats its prohibit-password. Rename the file and it silently
+# loses that fight — the harness asserts the comparison the glob makes.
+DROPIN=/etc/ssh/sshd_config.d/00-rig-users.conf
+TMP="$(mktemp)"
+printf 'PermitRootLogin no\n' > "$TMP"
+if cmp -s "$TMP" "$DROPIN" 2>/dev/null; then
+  rm -f "$TMP"
+  log "root already closed; nothing to do"
+  exit 0
+fi
+
+BACKUP=""
+[ -e "$DROPIN" ] && { BACKUP="$(mktemp)"; cp -a "$DROPIN" "$BACKUP"; }
+install -m 0644 "$TMP" "$DROPIN"
+rm -f "$TMP"
+
+# Validate the MERGED config BEFORE bouncing the daemon (the bootstrap shape):
+# on a box whose only door is SSH — exactly what this box is about to become —
+# restarting into a config the daemon refuses to parse leaves no listener and
+# no way back in. Roll back and stop rather than shut the door on a maybe.
+if ! sshd -t 2>/dev/null; then
+  if [ -n "$BACKUP" ]; then cp -a "$BACKUP" "$DROPIN"; else rm -f "$DROPIN"; fi
+  rm -f "$BACKUP"
+  die "sshd rejects the merged config; drop-in rolled back, daemon untouched. Run 'sshd -t' to see which file is bad."
+fi
+rm -f "$BACKUP"
+
+systemctl restart ssh
+
+# Assert the EFFECTIVE config, not the file's existence — a drop-in sorting
+# even earlier would win the first-wins fight silently. `sshd -T` is what the
+# daemon actually resolved.
+eff="$(sshd -T 2>/dev/null)" || die "sshd -T failed; refusing to claim root is closed"
+echo "$eff" | grep -qx 'permitrootlogin no' \
+  || die "sshd still resolves permitrootlogin != no — a drop-in is beating ${DROPIN}; check ls /etc/ssh/sshd_config.d/"
+log "root door closed (sshd -T resolves permitrootlogin no); humans enter as themselves now"

test/cli.sh

@@ -335,6 +335,57 @@ sudoers_at="$(grep -nE 'install .*sudoers\.d/rig-roles' "$ROOT/commands/users-ap
 check "users apply: visudo -c precedes the sudoers install" \
   0 "" test "${visudo_at:-999999}" -lt "${sudoers_at:-0}"
 
+# --- users close-root: the human-class root-door shutter ---------------------
+check "users close-root: --help exits 0"       0 "usage:"       "$ROOT/commands/users-close-root.sh" --help
+check "users close-root: unknown flag exits 2" 2 "unknown flag" "$ROOT/commands/users-close-root.sh" --nope
+# The whole command rests on first-wins + lexical include order: '-' (0x2D)
+# sorts before '.' (0x2E), so 00-rig-users.conf is read before bootstrap's
+# 00-rig.conf and its PermitRootLogin wins. Assert the actual comparison the
+# glob makes, so a renamed drop-in cannot silently lose the fight.
+check "users close-root: drop-in name sorts before bootstrap's" 0 "" \
+  bash -c '[ "00-rig-users.conf" \< "00-rig.conf" ]'
+check "users close-root: drop-in name is the load-bearing one" 0 "" \
+  grep -q "00-rig-users.conf" "$ROOT/commands/users-close-root.sh"
+# Validate-then-apply: `sshd -t` on the merged config must precede the restart —
+# on a box whose only door is SSH (exactly what this box is about to become),
+# bouncing the daemon into a config it refuses to parse leaves no way back in.
+# Match the call, not the word (repo precedent: the repo-guard ordering check);
+# defaults fail closed.
+sshdt_at="$(grep -nE '^[[:space:]]*if ! sshd -t' "$ROOT/commands/users-close-root.sh" | head -n1 | cut -d: -f1)"
+restart_at="$(grep -n 'systemctl restart ssh' "$ROOT/commands/users-close-root.sh" | head -n1 | cut -d: -f1)"
+check "users close-root: sshd -t precedes the ssh restart" \
+  0 "" test "${sshdt_at:-999999}" -lt "${restart_at:-0}"
+# Marker-gate refusals through the sourced lib against fixture markers: the CLI
+# path sits behind the root check, so the gate is a pure lib function on
+# purpose (repo precedent: parse_users_file, assert_runner_repo). The command
+# reads the marker path from RIG_ROLE_MARKER for the same reason — so the gate
+# stays pointable at fixtures.
+marker_gate() { # marker_gate <marker_path>
+  bash -c 'set -euo pipefail
+    . "$1/commands/lib/users-config.sh"
+    assert_marker_human "$2"' _ "$ROOT" "$1"
+}
+MARKER_DIR="$(mktemp -d)"
+printf 'role=workload class=server host=no join=authkey\n' > "$MARKER_DIR/server"
+printf 'role=dev class=human host=yes join=authkey\n'      > "$MARKER_DIR/human"
+check "users close-root: absent marker refuses, names bootstrap as the repair" \
+  1 "no /etc/rig/role marker" marker_gate "$MARKER_DIR/absent"
+check "users close-root: class=server refuses, names the control plane" \
+  1 "control plane" marker_gate "$MARKER_DIR/server"
+check "users close-root: class=human passes the gate" \
+  0 "" marker_gate "$MARKER_DIR/human"
+rm -rf "$MARKER_DIR"
+if [ "$(id -u)" -ne 0 ]; then
+  check "users close-root: refuses non-root" 1 "must run as root" "$ROOT/commands/users-close-root.sh"
+else
+  echo "skip: users close-root non-root refusal (running as root)"
+fi
+# Bootstrap must read the closed door as hardened, not broken: `no` is the
+# post-close-root state, strictly harder than what bootstrap installs. Byte-grep
+# the widened assertion so a revert cannot ship green.
+check "bootstrap: permitrootlogin assertion accepts the closed state" 0 "" \
+  grep -qF "permitrootlogin (no|prohibit-password|without-password)" "$ROOT/commands/bootstrap.sh"
+
 # The dump script ships to control-plane boxes as an embedded heredoc. A syntax
 # error in it would be invisible here and would first surface at 04:00 on a live
 # control plane. Extract it and syntax-check what actually gets written.