#!/usr/bin/env bash
# swap.sh — run frank-dragoon on the candidate env through a transient systemd
# drop-in (the fleet's A/B law: restart the SERVICE with a different
# FRANK_DRAGOON_ENV_FILE, never a scratch port — one iGPU holds one server).
#
#   swap.sh candidate   install the drop-in, restart, print the boot ledger
#   swap.sh restore     retire the drop-in (moved, never deleted), restart back
#                       onto the repo env, print the boot ledger
set -euo pipefail

UNIT=frank-dragoon
DROP=/etc/systemd/system/$UNIT.service.d/v2abl.conf
ENVF=/tmp/frank-dragoon-v2abl.env
LOG=/home/dank/logs/frank_dragoon.log

ledger() {
    echo "--- boot ledger (kv pool / weights / mtp / clamp)"
    grep -aiE "kv pool|KV budget|checkpoint:|n-gram|vision|pinned|memory:|clamp|warn|error|MTP|prompt cache|version" \
        "$LOG" | head -30
}

case "${1:-}" in
  candidate)
    [ -f "$ENVF" ] || { echo "missing $ENVF" >&2; exit 1; }
    sudo mkdir -p "$(dirname "$DROP")"
    printf '[Service]\nEnvironment=FRANK_DRAGOON_ENV_FILE=%s\n' "$ENVF" \
        | sudo tee "$DROP" >/dev/null
    sudo systemctl daemon-reload
    # the census window masks the unit; a masked unit cannot be started
    sudo systemctl unmask "$UNIT" 2>/dev/null || true
    sudo systemctl restart "$UNIT"
    echo "--- waiting for the listener (load is minutes; the listener opens after the full load)"
    for _ in $(seq 1 120); do
        curl -sf -m 5 -o /dev/null "http://127.0.0.1:7770/health" && break
        sleep 5
    done
    systemctl is-active "$UNIT"
    curl -s -m 5 http://127.0.0.1:7770/v1/models | head -c 300; echo
    ledger
    ;;
  restore)
    if [ -f "$DROP" ]; then
        sudo mv "$DROP" "/tmp/v2abl.conf.retired-$(date +%s)"
        sudo systemctl daemon-reload
    fi
    sudo systemctl unmask "$UNIT" 2>/dev/null || true
    sudo systemctl restart "$UNIT"
    for _ in $(seq 1 120); do
        curl -sf -m 5 -o /dev/null "http://127.0.0.1:7770/health" && break
        sleep 5
    done
    systemctl is-active "$UNIT"
    curl -s -m 5 http://127.0.0.1:7770/v1/models | head -c 300; echo
    ledger
    ;;
  *) echo "usage: $0 candidate|restore" >&2; exit 2 ;;
esac