heavy-duty-watcher/scripts/health-check.sh
grok-reviewer-andresmgsl 8d6f902209 Harden watcher: shared config, dual forge backends, safer discovery
- Add scripts/lib/common.sh (ORG/BOT/FORGE_BACKEND, logging, process_running)
- discover.sh: dedupe review-requested+assignee PRs; JSON+summary formats
- discover.sh: FORGE_BACKEND=forgejo via Forgejo API + stoke token
- Fix poll-loop process detection (basename, not install path)
- health-check: jq-safe JSON; backend-aware auth (gh or stoke)
- install-live: require rsync/jq/tmux; soft-warn missing gh/stoke
- self-test.sh offline smoke; restore/poll-once use shared config
- Docs: Forgejo table, watcher.env, OPERATIONS troubleshooting
2026-07-22 23:23:33 +00:00

140 lines
4.2 KiB
Bash
Executable file

#!/usr/bin/env bash
# Health check for the heavy-duty org watcher. Exit 0=ok, 1=degraded, 2=down.
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
# shellcheck source=lib/common.sh
source "${SCRIPT_DIR}/lib/common.sh"
HEALTH_LOG="${LOG_DIR}/health.log"
mkdir -p "${LOG_DIR}"
NOW_EPOCH="$(date -u +%s)"
NOW_ISO="$(utc_now)"
STATUS="ok"
ISSUES=()
ok() { ISSUES+=("OK: $1"); }
warn() { STATUS="degraded"; ISSUES+=("WARN: $1"); }
fail() { STATUS="down"; ISSUES+=("FAIL: $1"); }
# --- auth ---
case "${FORGE_BACKEND}" in
github)
if command -v gh >/dev/null 2>&1 && gh api user --jq .login >/dev/null 2>&1; then
LOGIN="$(gh api user --jq .login 2>/dev/null || echo unknown)"
ok "gh authenticated as ${LOGIN}"
if [[ -n "${BOT_LOGIN}" && "${LOGIN}" != "${BOT_LOGIN}" ]]; then
warn "gh login ${LOGIN} != expected BOT_LOGIN ${BOT_LOGIN}"
fi
else
fail "gh not authenticated"
fi
;;
forgejo)
if command -v stoke >/dev/null 2>&1 && stoke auth status 2>/dev/null | grep -q 'Login:'; then
LOGIN="$(stoke auth status 2>/dev/null | awk '/^Login:/{print $2; exit}')"
ok "stoke authenticated as ${LOGIN:-unknown}"
else
fail "stoke not authenticated (FORGE_BACKEND=forgejo)"
fi
;;
esac
# --- tmux ---
ACTIVE_TMUX=""
if command -v tmux >/dev/null 2>&1; then
if tmux has-session -t "${TMUX_SESSION}" 2>/dev/null; then
ACTIVE_TMUX="${TMUX_SESSION}"
elif tmux has-session -t "${LEGACY_TMUX}" 2>/dev/null; then
ACTIVE_TMUX="${LEGACY_TMUX}"
warn "using legacy tmux session ${LEGACY_TMUX} (prefer ${TMUX_SESSION})"
fi
else
warn "tmux not installed"
fi
if [[ -n "${ACTIVE_TMUX}" ]]; then
ok "tmux session ${ACTIVE_TMUX} exists"
if tmux list-windows -t "${ACTIVE_TMUX}" -F '#{window_name}' 2>/dev/null | grep -Eqx 'poll-loop'; then
ok "tmux window poll-loop present"
else
warn "tmux window poll-loop missing"
fi
else
fail "tmux session missing (run scripts/restore.sh)"
fi
if process_running 'poll-loop\.sh'; then
ok "poll-loop.sh process running"
else
fail "poll-loop.sh process not running"
fi
# --- state ---
if [[ -f "${STATE_FILE}" ]]; then
if command -v jq >/dev/null 2>&1; then
LAST_POLL="$(jq -r '.last_poll_at // empty' "${STATE_FILE}" 2>/dev/null || true)"
SCOPE="$(jq -r '.scope // .repo // "unknown"' "${STATE_FILE}" 2>/dev/null || echo unknown)"
ok "scope: ${SCOPE}"
if [[ -n "${LAST_POLL}" && "${LAST_POLL}" != "null" ]]; then
if LAST_EPOCH="$(date -u -d "${LAST_POLL}" +%s 2>/dev/null)"; then
AGE_MIN=$(( (NOW_EPOCH - LAST_EPOCH) / 60 ))
if (( AGE_MIN > STALE_POLL_MINUTES )); then
warn "last_poll_at is ${AGE_MIN}m old (${LAST_POLL})"
else
ok "last_poll_at fresh (${AGE_MIN}m ago: ${LAST_POLL})"
fi
else
ok "last_poll_at present (${LAST_POLL})"
fi
else
warn "state.json has no last_poll_at"
fi
SUMMARY="$(jq -r '.last_poll_summary // "n/a"' "${STATE_FILE}" 2>/dev/null || echo n/a)"
ok "last_poll_summary: ${SUMMARY}"
else
warn "jq missing; cannot parse state.json details"
fi
else
fail "state.json missing"
fi
[[ -f "${WATCHER_DIR}/POLL_INSTRUCTIONS.md" ]] && ok "POLL_INSTRUCTIONS.md present" || fail "POLL_INSTRUCTIONS.md missing"
# --- write health JSON via jq (safe escaping) ---
RESULT_JSON="${LOG_DIR}/health-latest.json"
if command -v jq >/dev/null 2>&1; then
jq -n \
--arg t "${NOW_ISO}" \
--arg s "${STATUS}" \
--arg backend "${FORGE_BACKEND}" \
--arg org "${ORG}" \
--args \
'{
checked_at: $t,
status: $s,
backend: $backend,
org: $org,
issues: $ARGS.positional
}' -- "${ISSUES[@]}" > "${RESULT_JSON}"
else
echo "{\"checked_at\":\"${NOW_ISO}\",\"status\":\"${STATUS}\",\"issues\":[]}" > "${RESULT_JSON}"
fi
watcher_log "${HEALTH_LOG}" "status=${STATUS} | $(IFS=' ; '; echo "${ISSUES[*]}")"
if command -v jq >/dev/null 2>&1 && [[ -f "${STATE_FILE}" ]]; then
tmp="$(mktemp)"
jq --arg t "${NOW_ISO}" --arg s "${STATUS}" \
'.health = {last_check_at: $t, status: $s}' "${STATE_FILE}" > "${tmp}" \
&& mv "${tmp}" "${STATE_FILE}"
fi
echo "status=${STATUS}"
printf '%s\n' "${ISSUES[@]}"
case "${STATUS}" in
ok) exit 0 ;;
degraded) exit 1 ;;
*) exit 2 ;;
esac