#!/bin/sh
# shikane-watchdog: auto-recover shikane from its deadlock bug.
#
# Bug (shikane 1.1.1): if a variant application is discarded mid-way
# (e.g. by a failing DP atomic commit), the daemon gets stuck in
# VariantInProgress/Discarded and keeps logging
#   [WARN shikane::variant] Received invalid input AtomicChangeDone at state Discarded
# `shikanectl reload` does not recover it; a service restart does
# (re-applies the active profile in ~1s).
#
# A healthy daemon's last state-machine line is "VariantApplied".

set -u

unit=shikane
stuck=0

logs3=$(journalctl --user -u "$unit" -q --since "-3min" 2>/dev/null)
[ -z "$logs3" ] && exit 0

latest3=$(printf '%s\n' "$logs3" | grep 'daemon::state_machine' | tail -1)

if [ -n "$latest3" ]; then
    case "$latest3" in
        *VariantApplied*)
            : ;;  # healthy
        *)
            # InProgress/Discarded within the last 3 min: only a deadlock
            # if the WARN signature is present (a legitimate slow transition
            # has no WARN)
            printf '%s\n' "$logs3" | grep -q 'invalid input' && stuck=1
            ;;
    esac
else
    # No state change in the last 3 min — check the last known state
    last10=$(journalctl --user -u "$unit" -q --since "-10min" 2>/dev/null \
        | grep 'daemon::state_machine' | tail -1)
    case "$last10" in
        '' | *VariantApplied*)
            : ;;  # stable and applied, or nothing to check
        *)
            stuck=1 ;;  # stuck in-progress/discarded for >3 min
    esac
fi

if [ "$stuck" -eq 1 ]; then
    echo "shikane-watchdog: shikane stuck, restarting" >&2
    systemctl --user restart "$unit"
fi