#!/usr/bin/env bash
# usage: ssh-run.sh <stage>
# Runs one deploy-lib.sh stage on the workstation over SSH.
set -euo pipefail

: "${DEPLOY_HOST:?missing DEPLOY_HOST}"
: "${DEPLOY_USER:?missing DEPLOY_USER}"
: "${DEPLOY_KEY:?missing DEPLOY_SSH_KEY}"

deploy_port="${DEPLOY_PORT:-22}"
deploy_path="${DEPLOY_PATH:-/srv/homelab}"
deploy_path="$(printf '%s' "$deploy_path" | tr -d '\"' | tr -d '\r' | xargs)"

# The private key is written to a per-run directory that is removed on exit, so a
# failed or cancelled job cannot leave deploy credentials in the runner's temp
# directory. Do not use a fixed path: apply-k8s and apply-compose run in parallel.
key_dir="$(mktemp -d "${RUNNER_TEMP:-/tmp}/homelab-deploy-key.XXXXXXXX")"
trap 'rm -rf "$key_dir"' EXIT INT TERM

ssh_key="$key_dir/deploy_key"
printf '%s\n' "$DEPLOY_KEY" > "$ssh_key"
chmod 600 "$ssh_key"

# A connection that died silently used to hang until the job timeout, and the
# stage was never re-run: one flaky TCP session cost a whole 45-minute apply.
# ServerAlive* bounds how long a dead peer goes unnoticed, ConnectTimeout bounds
# setup. Only exit 255 - ssh's own transport failures - is retried. A stage that
# fails on its own merits exits with the remote's status, so a real failure
# still surfaces its own log instead of burning three attempts. The stages are
# declarative applies, so re-running one that had already committed is harmless.
ssh_opts=(
  -i "$ssh_key" -p "$deploy_port"
  -o BatchMode=yes -o StrictHostKeyChecking=accept-new
  -o ConnectTimeout=15
  -o ServerAliveInterval=15 -o ServerAliveCountMax=4
)

rc=0
for attempt in 1 2 3; do
  if [ "$attempt" -gt 1 ]; then
    echo ":: warning::ssh transport failed, retrying (${attempt}/3)"
    sleep $((attempt * 5))
  fi
  rc=0
  ssh "${ssh_opts[@]}" "${DEPLOY_USER}@${DEPLOY_HOST}" \
    env "REPO=$deploy_path" "APPLY_PRUNE=${APPLY_PRUNE:-false}" \
    "DEPLOY_SHA=${DEPLOY_SHA:-}" "DEPLOY_SNAPSHOT_DIR=${DEPLOY_SNAPSHOT_DIR:-}" \
    "STAGE=$1" bash -se <<'EOF' || rc=$?
source "$REPO/.gitea/workflows/deploy-lib.sh"
run_stage "$STAGE"
EOF
  [ "$rc" -eq 0 ] && break
  [ "$rc" -ne 255 ] && break
done

if [ "$rc" -ne 0 ]; then
  echo ":: error::stage $1 failed over ssh (exit $rc)"
fi
exit "$rc"