#!/bin/bash
# cayce-urgent-watch (r21 → r33) — política de DMs del operador:
#   DM inmediato SOLO si:
#     · kill switch activado o fuga detectada
#     · sitio/servicio público caído >15 min (no rollbacks que se recuperan)
#     · backup fallido 2 días seguidos
#     · gasto de Gemini por encima del umbral
#   Todo lo demás (initiative, rollbacks recuperados, ciclos, publicaciones,
#   rechazos, merges CODEOWNERS) va SOLO al resumen diario de las 23:50 UTC.
#   Ciclos pausados a propósito (p.ej. promo) no generan alertas.
#   Dedup por tipo de incidente + sujeto (24 h). Tope: 3 DMs urgentes/día;
#   a partir de ahí, una línea en el resumen diario (.dm-deferred.log).
# DRYRUN=1 imprime qué haría sin enviar ni contar.
DEDUP=/srv/cayce-core/.dm-dedup.json
DOWNST=/srv/cayce-core/.critical-down.json
COUNTF=/srv/cayce-core/.dm-urgent-count.json
DEFER=/srv/cayce-core/.dm-deferred.log
USAGE=${LLM_USAGE_LOG:-/srv/cayce-core/.llm-usage.jsonl}
GEMINI_MAX_USD=${GEMINI_MAX_USD:-1.0}
export TTL_MS=$((24 * 3600 * 1000))
DRY=${DRYRUN:-0}

dm_urgente() {  # $1 clave (tipo:sujeto), $2 mensaje
  python3 - "$1" "$2" "$DEDUP" "$TTL_MS" "$COUNTF" "$DEFER" "$DRY" <<'PY'
import json, sys, subprocess, datetime, os
key, msg, dedup, ttl, countf, defer, dry = sys.argv[1:8]
ttl, dry = int(ttl), int(dry)
st = {}
try: st = json.load(open(dedup))
except Exception: pass
now = datetime.datetime.utcnow().timestamp() * 1000
if now - st.get(key, 0) < ttl:
    print(f"[urgent] DM dedup ({key}) — ya alertado en <24h"); sys.exit(0)
cnt = {}
today = datetime.datetime.utcnow().date().isoformat()
try: cnt = json.load(open(countf))
except Exception: pass
n = cnt.get(today, 0)
sup = ""
for l in open("/srv/cayce-nostr/.env"):
    if l.startswith("SUPERVISOR_NPUB_HEX="): sup = l.strip().split("=",1)[1]
if not sup:
    print("[urgent] sin supervisor — solo log"); sys.exit(0)
if n >= 3:
    with open(defer, "a") as f:
        f.write(f"{datetime.datetime.utcnow().isoformat()} DEFERIDO (tope 3/dia) {key}: {msg}\n")
    print(f"[urgent] TOPE 3/dia alcanzado — diferido al resumen diario ({key})")
    sys.exit(0)
if dry:
    print(f"[urgent] DRYRUN: enviaria DM ({key}): {msg[:100]}")
    sys.exit(0)
subprocess.run(["curl","-s","-m","20","-X","POST","http://127.0.0.1:3011/dm",
    "-H","Content-Type: application/json","-d",json.dumps({"to_hex":sup,"content":msg})],
    capture_output=True)
st[key] = now
cnt[today] = n + 1
json.dump(st, open(dedup, "w"))
json.dump(cnt, open(countf, "w"))
print(f"[urgent] DM enviado ({key}) — {cnt[today]}/3 hoy")
PY
}

# 1) kill switch manual o fuga: PUBLISH_OFF sin violación reciente del watcher,
#    o violación del relay-watcher (fuga) en la última hora.
if [ -f /srv/cayce-core/PUBLISH_OFF ]; then
  SIG=$(head -c 9 /srv/cayce-core/PUBLISH_OFF 2>/dev/null)
  AGE=$(( $(date -u +%s) - $(stat -c %Y /srv/cayce-core/PUBLISH_OFF 2>/dev/null || echo 0) ))
  if [ "$SIG" != "autodeploy" ] || [ "$AGE" -ge 600 ]; then
    V=$(sudo -n -u postgres psql -d cayce -tAc "SELECT count(*) FROM guard_rejections WHERE type='watcher_violation' AND ts > now() - interval '15 minutes'" 2>/dev/null || echo 1)
    [ "$V" = "0" ] && dm_urgente "killswitch:manual" "URGENTE: PUBLISH_OFF activo (kill switch MANUAL) — publicación en draft global. Sin violación del watcher que lo explique."
  fi
fi
FUGA=$(sudo -n -u postgres psql -d cayce -tAc "SELECT count(*) FROM guard_rejections WHERE type='watcher_violation' AND ts > now() - interval '60 minutes'" 2>/dev/null || echo 0)
[ "$FUGA" != "0" ] && dm_urgente "fuga:watcher" "URGENTE: $FUGA violaciones del watcher en 60 min — posible fuga de publicación. PUBLISH_OFF recomendado."

# 2) servicios críticos caídos >15 min (estado persistente de primera caída)
while IFS=: read -r TAG UNIT MINS; do
  [ "$TAG" = "DOWN" ] && dm_urgente "down:$UNIT" "URGENTE: servicio crítico caído ${MINS} min: $UNIT"
done < <(python3 - "$DOWNST" <<'PY'
import json, subprocess, sys, time
UNITS = ["cayce-nostr.service","hardcap-backend.service","hardcap-frontend.service",
         "cayce-bitcoinhotels.service","postgresql@18-main.service","caddy.service"]
st = {}
try: st = json.load(open(sys.argv[1]))
except Exception: pass
now = time.time()
for u in UNITS:
    active = subprocess.run(["systemctl","is-active",u], capture_output=True, text=True).stdout.strip() == "active"
    if active:
        st.pop(u, None)
    else:
        st.setdefault(u, now)
        if now - st[u] > 15*60:
            print(f"DOWN:{u}:{int((now-st[u])/60)}")
json.dump(st, open(sys.argv[1], "w"))
PY
)

# 3) backup fallido 2 días seguidos (r33: un fallo puntual no es urgente)
if systemctl is-failed cayce-backup.service >/dev/null 2>&1; then
  FAILS=$(journalctl -u cayce-backup.service --since "48 hours ago" --no-pager 2>/dev/null | grep -c "Failed with result")
  if [ "${FAILS:-0}" -ge 2 ]; then
    dm_urgente "backup:2días" "URGENTE: cayce-backup fallido ${FAILS} veces en 48h — revisar /var/backups/cayce y el journal."
  else
    echo "[urgent] backup failed hoy ($FAILS en 48h <2) — va al resumen diario"
  fi
fi

# 4) gasto de Gemini hoy > umbral (tokens reales)
read -r COST CALLS TIN TOUT < <(python3 - "$USAGE" <<'PY'
import json, sys, os, datetime
rin = float(os.environ.get("GEMINI_USD_PER_MTOK_IN", "0.15"))
rout = float(os.environ.get("GEMINI_USD_PER_MTOK_OUT", "0.60"))
today = datetime.datetime.utcnow().date().isoformat()
IN = OUT_ = CALLS = 0
if os.path.exists(sys.argv[1]):
    for line in open(sys.argv[1]):
        try:
            d = json.loads(line)
            if d.get("ts","")[:10] == today:
                CALLS += 1; IN += d.get("in",0); OUT_ += d.get("out",0)
        except Exception: pass
print(f"{IN/1e6*rin + OUT_/1e6*rout:.4f} {CALLS} {IN} {OUT_}")
PY
)
if python3 -c "exit(0 if float('${COST:-0}') > float('$GEMINI_MAX_USD') else 1)" 2>/dev/null; then
  dm_urgente "gasto:gemini" "URGENTE: gasto Gemini de hoy \$${COST} (> \$${GEMINI_MAX_USD}) — ${CALLS} llamadas, ${TIN} in / ${TOUT} out tokens."
fi

# r33: lo que YA NO manda DM (solo resumen diario de 23:50):
#   · ciclos mudos / pausados a propósito (promo hoy) — el resumen diario ya
#     trae la sección "Ciclos: piezas producidas"
#   · merges que tocan CODEOWNERS — el resumen diario (sección 3) lista los
#     merges del día; la sección 3b lista los PRs abiertos
#   · rollbacks recuperados — el autodeploy usa dm_once (un aviso por
#     incidente) y el resumen diario lista los deploys/rollbacks del journal

logger -t cayce-urgent-watch "tick ok (gemini=\$${COST:-0})"
