#!/usr/bin/env bash
# recover-uno-q.sh — recover an APESS Uno Q node after a sudden USB/adb
# disconnect. Run this from the host (Mac) once the board is physically back.
#
# A disconnect drops the adb tunnels, kills held-shell services, and can leave
# llama wedged — none of it self-heals (see memory: unoq-disconnect-recovery).
# This re-establishes every hop and verifies it by ENDPOINT, not by pgrep.
#
#   ./recover-uno-q.sh <adb-serial> [cloud-shim-port]
#
# Steps: reconnect adb → re-tunnel (8080 gateway out, shim port back) → ensure
# the on-board supervisor is running (it restarts llama + daemon) → health-check
# gateway, llama, and board→shim reachability.
set -uo pipefail

SERIAL="${1:?usage: recover-uno-q.sh <adb-serial> [cloud-shim-port]}"
SHIM_PORT="${2:-8090}"
SUPERVISOR="/home/arduino/zeroclaw-supervisor.sh"
a() { adb -s "$SERIAL" "$@"; }

echo "==> [1/5] reconnect adb"
adb kill-server  >/dev/null 2>&1 || true
adb start-server >/dev/null 2>&1 || true
for _ in $(seq 1 15); do
  [ "$(a get-state 2>/dev/null || true)" = "device" ] && break
  sleep 1
done
[ "$(a get-state 2>/dev/null || true)" = "device" ] \
  || { echo "    board $SERIAL not found — a physical re-plug is required"; exit 1; }
echo "    device up"

echo "==> [2/5] re-establish tunnels (out :8080 gateway, back :$SHIM_PORT shim)"
a forward tcp:8080 tcp:8080 >/dev/null
a reverse "tcp:$SHIM_PORT" "tcp:$SHIM_PORT" >/dev/null
echo "    forward :8080 · reverse :$SHIM_PORT"

echo "==> [3/5] ensure on-board supervisor is running"
if a shell "test -x $SUPERVISOR" 2>/dev/null; then
  # Bracket the pattern so the pgrep's own shell (whose args contain the
  # supervisor path) doesn't self-match and skip the launch.
  a shell "pgrep -f '[z]eroclaw-supervisor.sh' >/dev/null 2>&1 \
    || (setsid nohup $SUPERVISOR >/dev/null 2>&1 < /dev/null &)" >/dev/null 2>&1
  echo "    supervisor ensured (restarts llama + daemon on death/wedge)"
else
  echo "    WARN: $SUPERVISOR not on board — falling back to a one-shot daemon start"
  a shell 'pkill -f "zeroclaw daemon" 2>/dev/null; sleep 1; \
    cd /home/arduino && TMPDIR=/tmp setsid nohup ./zeroclaw daemon >> zc-daemon.log 2>&1 < /dev/null &' >/dev/null 2>&1
fi

echo "==> [4/5] wait for board services (endpoint, not pgrep)"
for _ in $(seq 1 20); do
  a shell 'curl -sf --max-time 3 http://127.0.0.1:8080/health >/dev/null' 2>/dev/null \
    && { echo "    gateway :8080 healthy"; break; }
  sleep 3
done
a shell 'curl -sf --max-time 3 http://127.0.0.1:8083/health >/dev/null' 2>/dev/null \
  && echo "    llama :8083 healthy" \
  || echo "    llama :8083 still warming (cold GGUF load is 3–5 min)"

echo "==> [5/5] verify cloud shim reachable from the board"
a shell "curl -sf --max-time 4 http://127.0.0.1:$SHIM_PORT/v1/models >/dev/null" 2>/dev/null \
  && echo "    board can reach cloud shim :$SHIM_PORT" \
  || echo "    WARN: shim unreachable from board — is it running on the host?"

echo "==> recovery complete for $SERIAL"