rig/commands/forgejo-runner-status.sh

#!/usr/bin/env bash
# rig forgejo-runner status — what is this box's Forgejo runner registered to?
# Read-only: reports what is already on the box. No credential, no network call.
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"

log()  { printf 'rig-forgejo-runner: %s\n' "$*"; }
warn() { printf 'rig-forgejo-runner: WARNING: %s\n' "$*" >&2; }
die()  { printf 'rig-forgejo-runner: ERROR: %s\n' "$1" >&2; exit "${2:-1}"; }

# forgejo_runner_liveness_note <systemctl-state> — what `active` does not cover.
#
# `active` is the strongest health signal this command has, and it proves only
# that a process exists — not that the runner is still asking Forgejo for work.
# A poller can go quiet while the daemon stays up: measured 2026-07-30 (#129,
# #133), a daemon logged "[poller] launched" and never fetched a job dispatched
# four minutes later, while a daemon started fresh claimed that same queued task
# in one second. Both times it read as a label-mapping bug on the forge, which
# is the wrong place to look.
#
# A FUNCTION rather than an inline `if`, because the state boundary is the part
# worth pinning: an absent or inactive unit must say nothing, and a grep over
# the source cannot tell the difference (codex/kimi, !134).
#
# log, not warn: nothing has been DETECTED here. An idle runner with no queued
# jobs is silent in exactly the same way a stalled one is, so there is no signal
# separating them — a warning on every status run would be crying wolf, and warn
# in this file means a drift actually measured (the .runner mode below).
forgejo_runner_liveness_note() {
  [ "${1:-}" = active ] || return 0
  log "          note: 'active' is not proof the runner is fetching jobs — only that the process is up."
  log "          If a job stays queued and its run page says it never started, run"
  log "          'systemctl restart forgejo-runner' and re-read before suspecting the labels."
}

usage() {
  cat <<'EOF'
usage: rig forgejo-runner status [--user <name>]

  --user <name>   unprivileged service user (default: the tenant user `ci`
                  when it exists, else forgejo-runner)

Prints the Forgejo instance this box's runner is registered to, its runner
name, the labels rig recorded when it registered, the install directory, and
the systemd unit and its state.

Reads only the runner's own on-disk config — no token, no network call. The
registration secret that config holds is never printed. Exits 1 when no runner
is installed.
EOF
}

# --- args (validated before the root check, so errors are testable) ---------
RUNNER_USER=""
while [ $# -gt 0 ]; do
  case "$1" in
    --user)
      [ $# -ge 2 ] || die "--user needs a value" 2
      RUNNER_USER="$2"; shift 2 ;;
    -h|--help) usage; exit 0 ;;
    *) die "unknown flag: $1" 2 ;;
  esac
done

if [ -z "$RUNNER_USER" ]; then
  if id -u ci >/dev/null 2>&1; then RUNNER_USER="ci"; else RUNNER_USER="forgejo-runner"; fi
fi

# --- validation ------------------------------------------------------------
[ "$RUNNER_USER" != "root" ] || die "runner user must not be root" 2

# --- guards ----------------------------------------------------------------
[ "$(id -u)" -eq 0 ] || die "must run as root"

id -u "$RUNNER_USER" >/dev/null 2>&1 \
  || die "no runner installed (no ${RUNNER_USER} user on this box)"
USER_HOME="$(getent passwd "$RUNNER_USER" | cut -d: -f6)"
RUNNER_DIR="$USER_HOME/forgejo-runner"
[ -e "$RUNNER_DIR/.runner" ] \
  || die "no runner registered in ${RUNNER_DIR}"

# --- read the runner's own config -------------------------------------------
INSTANCE="$(forgejo_runner_instance "$RUNNER_DIR")"
RUNNER_NAME="$(forgejo_runner_name "$RUNNER_DIR")"

if [ -r "$RUNNER_DIR/.rig-labels" ]; then
  LABELS="$(cat "$RUNNER_DIR/.rig-labels")"
else
  LABELS="(not recorded on this box — see the instance's Actions > Runners)"
fi

UNIT=/etc/systemd/system/forgejo-runner.service
if [ -e "$UNIT" ]; then
  STATE="$(systemctl is-active forgejo-runner 2>/dev/null || true)"
  SERVICE="forgejo-runner.service (${STATE:-unknown})"
else
  SERVICE="(not installed as a service)"
fi

log "instance: ${INSTANCE:-unknown}"
log "name:     ${RUNNER_NAME:-unknown}"
log "labels:   ${LABELS}"
log "dir:      ${RUNNER_DIR}"
log "service:  ${SERVICE}"
forgejo_runner_liveness_note "${STATE:-}"


# status is the only command an operator runs when nothing is obviously wrong,
# which makes it the right place to notice a mode that drifted. It reports and
# does not fix: converging state is `install`'s job, and a read-only verb that
# quietly writes is a worse surprise than a loud warning.
MODE="$(stat -c '%a' "$RUNNER_DIR/.runner" 2>/dev/null || true)"
if [ -n "$MODE" ] && [ "$MODE" != "$FORGEJO_RUNNER_FILE_MODE" ]; then
  warn ".runner is mode ${MODE}, not ${FORGEJO_RUNNER_FILE_MODE} — it holds this runner's registration secret, and every account on this box can read it. Re-run 'rig forgejo-runner install --instance ${INSTANCE:-<url>}' to converge the mode."
fi