gps-denied-onboard/scripts/health-check.sh

#!/usr/bin/env bash
# GPS-Denied Onboard — verify the running service stack is healthy.
#
# The companion has no inbound HTTP `/health/*` endpoint (NFT-SEC-05 —
# in-flight egress lockdown). Health is read from the Docker
# HEALTHCHECK status (exec-based `python3 -m gps_denied_onboard.healthcheck`
# per deployment_procedures.md § Health Checks).
#
# Usage:
#   scripts/health-check.sh [--target dev|airborne|operator-workstation]
#                           [--compose-file <path>] [--help]
#
# Defaults:
#   target       = dev
#   compose-file = docker-compose.yml
#
# Exit codes:
#   0 all services healthy (or running with no declared healthcheck)
#   1 at least one service is unhealthy
#   2 at least one service is missing (compose up was not run, or container exited)

set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
REPO_ROOT="$(cd "${SCRIPT_DIR}/.." && pwd)"

usage() {
    cat <<'EOF'
GPS-Denied Onboard — verify the running service stack is healthy.

The companion has no inbound HTTP `/health/*` endpoint (NFT-SEC-05 —
in-flight egress lockdown). Health is read from the Docker HEALTHCHECK
status (exec-based `python3 -m gps_denied_onboard.healthcheck` per
deployment_procedures.md § Health Checks).

Usage:
  scripts/health-check.sh [--target dev|airborne|operator-workstation]
                          [--compose-file <path>] [--help]

Defaults:
  target       = dev
  compose-file = docker-compose.yml

Exit codes:
  0 all services healthy (or running with no declared healthcheck)
  1 at least one service is unhealthy
  2 at least one service is missing (compose up was not run, or container exited)
EOF
    exit 0
}

TARGET="dev"
COMPOSE_FILE=""

while [ $# -gt 0 ]; do
    case "$1" in
        --target)       TARGET="$2"; shift 2 ;;
        --compose-file) COMPOSE_FILE="$2"; shift 2 ;;
        --help|-h)      usage ;;
        *) echo "ERROR: unknown argument: $1" >&2; usage ;;
    esac
done

if [ -z "${COMPOSE_FILE}" ]; then
    case "${TARGET}" in
        dev)                  COMPOSE_FILE="docker-compose.yml" ;;
        airborne)             COMPOSE_FILE="${AIRBORNE_COMPOSE_FILE:-/etc/gps-denied/docker-compose.airborne.yml}" ;;
        operator-workstation) COMPOSE_FILE="docker-compose.yml" ;;
        *) echo "ERROR: invalid --target: ${TARGET}" >&2; exit 64 ;;
    esac
fi

remote_exec=""
if [ -n "${DEPLOY_HOST:-}" ]; then
    if ! ssh -o BatchMode=yes -o ConnectTimeout=5 "${DEPLOY_HOST}" true 2>/dev/null; then
        echo "ERROR: cannot reach 'ssh ${DEPLOY_HOST}' non-interactively." >&2
        exit 64
    fi
    remote_exec="ssh ${DEPLOY_HOST}"
fi

echo "[health-check] target:       ${TARGET}"
echo "[health-check] compose-file: ${COMPOSE_FILE}"

# Format: <service>\t<state>\t<health>
status_lines=$(${remote_exec} docker compose -f "${COMPOSE_FILE}" ps -a \
    --format '{{.Service}}{{"\t"}}{{.State}}{{"\t"}}{{.Health}}' 2>/dev/null \
    || true)

if [ -z "${status_lines}" ]; then
    echo "ERROR: no containers found for ${COMPOSE_FILE}" >&2
    echo "       Did you run scripts/start-services.sh?" >&2
    exit 2
fi

rc=0
printf '%-30s %-12s %-12s\n' SERVICE STATE HEALTH
printf '%-30s %-12s %-12s\n' "------------------------------" "------------" "------------"
while IFS=$'\t' read -r service state health; do
    [ -z "${service}" ] && continue
    if [ -z "${health}" ]; then
        health_display="(none)"
    else
        health_display="${health}"
    fi
    printf '%-30s %-12s %-12s\n' "${service}" "${state}" "${health_display}"
    if [ "${state}" != "running" ]; then
        rc=2
    elif [ -n "${health}" ] && [ "${health}" != "healthy" ]; then
        rc=1
    fi
done <<< "${status_lines}"

case "${rc}" in
    0) echo "[health-check] OK" ;;
    1) echo "[health-check] UNHEALTHY — at least one service failed HEALTHCHECK" >&2 ;;
    2) echo "[health-check] MISSING — at least one service is not running" >&2 ;;
esac
exit "${rc}"