#!/bin/bash
# Checks every 5 minutes if a livekit restart is pending.
# Only restarts when LiveKit reports no participants AND nobody holds a
# signalling connection, so a restart never drops a call.
# Run by: livekit-graceful-restart.timer (systemd)

if [ ! -f /run/livekit-restart-pending ]; then
    exit 0
fi

# Participants LiveKit itself counts, across all rooms. Counting TCP connections
# on :7881 (the old check) only saw clients on the ICE-TCP fallback: signalling
# is on :7880 and media is normally UDP, so most calls looked idle.
METRICS_URL="${LIVEKIT_METRICS_URL:-http://127.0.0.1:6789/metrics}"
if ! METRICS=$(curl -sf --max-time 5 "$METRICS_URL") \
    || ! printf '%s\n' "$METRICS" | grep -q '^livekit_participant_total'; then
    echo "$(date): Livekit restart pending but its metrics are unreadable — assuming a call is active, waiting."
    exit 0
fi
PARTICIPANTS=$(printf '%s\n' "$METRICS" | awk '/^livekit_participant_total/ {s += $NF} END {printf "%d", s}')

# Belt and braces: open signalling WebSockets (a client mid-join may not be a
# participant yet). Count lines (-H drops the header): with a `state` filter ss
# omits the State column, so the old `grep -c ESTAB` was always 0.
SIGNALLING=$(ss -Htn state established '( sport = :7880 )' | wc -l)

if [ "$PARTICIPANTS" -gt 0 ] || [ "$SIGNALLING" -gt 0 ]; then
    echo "$(date): Livekit restart pending but $PARTICIPANTS participant(s), $SIGNALLING signalling connection(s) — waiting."
    exit 0
fi

echo "$(date): No active calls — applying livekit-server restart."
systemctl restart livekit-server
rm -f /run/livekit-restart-pending
echo "$(date): livekit-server restarted successfully."