#!/usr/bin/env bash
# Which running workers are serving code older than the file on disk.
#
# Python loads a worker module once, at process start. Editing the file afterwards changes nothing
# until that process restarts, and nothing in the stage output says so: the stage completes, the
# counters read 116/116, and the result is what the OLD code produced. On 2026-08-12 this ate a full
# vision + identity + reconcile cycle — the bbox fix was committed 16 minutes after the worker that
# was supposed to apply it had already started.
#
# Run this before any stage run that is meant to prove a code change.
# Exits non-zero if anything is stale, so it can gate a script.
set -uo pipefail
cd "$(dirname "$0")"

stale=0
# `ps -o lstart` is always exactly five fields: "Wed Aug 12 13:20:00 2026". Read them positionally
# rather than trying to split the line with a regex.
while read -r pid _dow mon day time year cmd; do
    mod=$(grep -oP '(?:worker_\w+|session_manager)(?=:app)' <<<"$cmd" | head -1)
    [ -n "$mod" ] && [ -f "$mod.py" ] || continue
    p_epoch=$(date -d "$mon $day $time $year" +%s 2>/dev/null) || continue
    f_epoch=$(stat -c %Y "$mod.py")
    if [ "$f_epoch" -gt "$p_epoch" ]; then
        printf 'STALE  %-22s pid %-7s edited %dm after it started\n' \
               "$mod.py" "$pid" "$(( (f_epoch - p_epoch) / 60 ))"
        stale=1
    else
        printf 'ok     %-22s pid %s\n' "$mod.py" "$pid"
    fi
done < <(ps -eo pid,lstart,cmd | grep -E 'uvicorn (worker_|session_manager)' | grep -v grep)

if [ "$stale" -ne 0 ]; then
    echo
    echo "Restart the stale ones before trusting a stage result. Window numbers:"
    tmux list-windows -t manga-workers -F '  #{window_index} #{window_name}' 2>/dev/null \
        || echo "  (tmux session manga-workers is not running; ./start_workers.sh)"
fi
exit "$stale"