changelog.d/139.md

@@ -0,0 +1,3 @@
+### Fixed
+
+- `rig forgejo-runner install`, `rig runner install` and `rig users apply` refuse with a named remedy when root's `PATH` carries no `/usr/sbin`, instead of dying on `useradd: command not found` after prompting for a token (#139)

commands/forgejo-runner-install.sh

@@ -17,6 +17,8 @@ set -euo pipefail
 HERE="$(cd "$(dirname "$(readlink -f "${BASH_SOURCE[0]}")")" && pwd)"
 # shellcheck source=SCRIPTDIR/lib/forgejo-runner-config.sh
 . "$HERE/lib/forgejo-runner-config.sh"
+# shellcheck source=SCRIPTDIR/lib/admin-path.sh
+. "$HERE/lib/admin-path.sh"
 
 log()  { printf 'rig-forgejo-runner: %s\n' "$*"; }
 warn() { printf 'rig-forgejo-runner: WARNING: %s\n' "$*" >&2; }
@@ -202,6 +204,10 @@ fi
 
 # --- guards ----------------------------------------------------------------
 [ "$(id -u)" -eq 0 ] || die "must run as root"
+# Root is not enough: the admin binaries must also be reachable (#139). This
+# sits beside the root check so identity and capability are asserted together,
+# and BEFORE any prompt or download — a token typed for a doomed run is waste.
+require_admin_bins useradd
 if [ -r /etc/os-release ]; then
   # Sourced in a subshell: os-release defines VERSION (e.g. "13 (trixie)"),
   # which would clobber this script's $VERSION.

commands/lib/admin-path.sh

@@ -0,0 +1,29 @@
+#!/usr/bin/env bash
+# admin-path.sh — assert the admin binaries are REACHABLE, not merely that we
+# are root.
+#
+# Being uid 0 and being able to find useradd are different facts, and rig
+# asserted only the first. `su` without `-`, sudo with a sanitised secure_path,
+# and several container images all hand you a root shell whose PATH carries no
+# /usr/sbin — which is where useradd, usermod and groupadd live on Debian. The
+# result was a bare `useradd: command not found` naming a line number inside a
+# versioned install root, emitted AFTER a registration token had been read off
+# the operator's terminal (#139).
+#
+# It REFUSES rather than repairing PATH itself. A command that quietly prepends
+# /usr/sbin teaches the operator nothing and leaves a misconfigured host
+# misconfigured; the same reason bootstrap refuses rather than guessing. The
+# message carries the fix so the refusal costs one paste, not an investigation.
+
+# require_admin_bins <bin>... — die unless every one resolves on PATH.
+require_admin_bins() {
+  local missing=() b
+  for b in "$@"; do
+    command -v "$b" >/dev/null 2>&1 || missing+=("$b")
+  done
+  [ "${#missing[@]}" -eq 0 ] && return 0
+  # Names the REMEDY, not this script: the operator typed a `rig ...` command,
+  # and echoing the internal path back at them is the unhelpful half of the
+  # original `useradd: command not found`.
+  die "cannot find ${missing[*]} on PATH — it lives in /usr/sbin, which this root shell does not carry (a 'su' without '-' does this, and so do some container images). Re-run the same rig command with: PATH=/usr/sbin:/sbin:\$PATH"
+}

commands/runner-install.sh

@@ -9,6 +9,8 @@ set -euo pipefail
 HERE="$(cd "$(dirname "$(readlink -f "${BASH_SOURCE[0]}")")" && pwd)"
 # shellcheck source=SCRIPTDIR/lib/runner-config.sh
 . "$HERE/lib/runner-config.sh"
+# shellcheck source=SCRIPTDIR/lib/admin-path.sh
+. "$HERE/lib/admin-path.sh"
 
 log()  { printf 'rig-runner: %s\n' "$*"; }
 warn() { printf 'rig-runner: WARNING: %s\n' "$*" >&2; }
@@ -85,6 +87,10 @@ VERSION="${VERSION#v}"
 
 # --- guards ----------------------------------------------------------------
 [ "$(id -u)" -eq 0 ] || die "must run as root"
+# Root is not enough: the admin binaries must also be reachable (#139). This
+# sits beside the root check so identity and capability are asserted together,
+# and BEFORE any prompt or download — a token typed for a doomed run is waste.
+require_admin_bins useradd
 if [ -r /etc/os-release ]; then
   # Sourced in a subshell: os-release defines VERSION (e.g. "13 (trixie)"),
   # which would clobber this script's $VERSION.

commands/users-apply.sh

@@ -11,6 +11,8 @@ set -euo pipefail
 HERE="$(cd "$(dirname "$(readlink -f "${BASH_SOURCE[0]}")")" && pwd)"
 # shellcheck source=SCRIPTDIR/lib/users-config.sh
 . "$HERE/lib/users-config.sh"
+# shellcheck source=SCRIPTDIR/lib/admin-path.sh
+. "$HERE/lib/admin-path.sh"
 
 log()  { printf 'rig-users: %s\n' "$*"; }
 warn() { printf 'rig-users: WARNING: %s\n' "$*" >&2; }
@@ -136,6 +138,10 @@ done <<< "$PARSED"
 
 # --- guards ------------------------------------------------------------------
 [ "$(id -u)" -eq 0 ] || die "must run as root"
+# Root is not enough: the admin binaries must also be reachable (#139). This
+# sits beside the root check so identity and capability are asserted together,
+# and BEFORE any prompt or download — a token typed for a doomed run is waste.
+require_admin_bins useradd usermod
 
 # Identity management gates its INVOKER, not just its uid: %rig's sudoers rule
 # is binary-scoped but not argument-scoped, so without this gate a rig-role

test/cli.sh

@@ -3334,6 +3334,46 @@ check "ci-box: its install.sh does not register" 1 "" \
 check "ci-box: bootstrap-tenant does not read the staging dir" 1 "" \
   grep -q 'docs/templates' "$ROOT/commands/bootstrap-tenant.sh"
 
+# --- admin binaries must be reachable, not just root (#139) ------------------
+# Being root and being able to FIND the admin binaries are different facts, and
+# rig asserted only the first. `su` without `-`, sudo with a sanitised
+# secure_path, and several container images all give a root shell whose PATH
+# carries no /usr/sbin — where useradd lives. Reported from a real ci-box:
+#
+#   root@ci-forgejo-box:/home/dev# rig forgejo-runner install --instance …
+#   forgejo runner registration token:
+#   …/forgejo-runner-install.sh: line 250: useradd: command not found
+#
+# Note where it died: AFTER reading a registration token off the operator's
+# terminal. A secret typed for a run that could never succeed is the avoidable
+# half of the bug, so the refusal has to come before the prompt.
+#
+# The root check fires first and correctly, so these stub `id -u` to 0 — the
+# idiom the bootstrap --undo block above already uses — to reach the preflight.
+ADMPATH_DIR="$(mktemp -d)"
+mkdir -p "$ADMPATH_DIR/bin"
+# shellcheck disable=SC2016 # the body is shell source being written, not expanded
+printf '#!/usr/bin/env bash\nif [ "${1:-}" = -u ]; then printf "0\\n"; else exec /usr/bin/id "$@"; fi\n' \
+  > "$ADMPATH_DIR/bin/id"
+chmod +x "$ADMPATH_DIR/bin/id"
+# A PATH with the stub and the ordinary bindirs, but deliberately no /usr/sbin.
+SBINLESS="$ADMPATH_DIR/bin:/usr/local/bin:/usr/bin:/bin"
+adm_run() { env PATH="$SBINLESS" "$@" 2>&1; }
+adm_prompted() {  # did it read a token before refusing?
+  adm_run "$@" | grep -qi 'registration token:'
+}
+check "preflight: forgejo-runner install refuses a PATH with no /usr/sbin" 1 "useradd" \
+  adm_run "$ROOT/commands/forgejo-runner-install.sh" --instance https://f.example.com
+check "preflight: …and names PATH as the cause, not just the missing binary" 1 "PATH" \
+  adm_run "$ROOT/commands/forgejo-runner-install.sh" --instance https://f.example.com
+check "preflight: …and refuses BEFORE prompting for a token" 1 "" \
+  adm_prompted "$ROOT/commands/forgejo-runner-install.sh" --instance https://f.example.com
+check "preflight: the GitHub runner installer refuses too" 1 "useradd" \
+  adm_run "$ROOT/commands/runner-install.sh" --repo o/r
+check "preflight: users apply refuses before it converges anything" 1 "useradd" \
+  adm_run "$ROOT/commands/users-apply.sh" --file /dev/null
+rm -rf "$ADMPATH_DIR"
+
 # --- rig forgejo-runner (#109) ----------------------------------------------
 FR="$ROOT/commands/forgejo-runner-install.sh"
 check "forgejo-runner: bare subcommand shows usage, exit 2" 2 "usage:" "$ROOT/bin/rig" forgejo-runner