#!/usr/bin/env bash
# Run both official suites against the currently served model (or $1).
set -euo pipefail
WS="${AGENTPTB_WORKSPACE:-/mnt/pvc/users/simon/agentptb/runs/grok/workspace}"
MODEL="${1:-$WS/outputs/soup-85-s80/weights}"
N="${2:-40}"
"$WS/scripts/wait_api.sh"
"$WS/scripts/launch_eval.sh" tb2 "$MODEL" "$N"
"$WS/scripts/launch_eval.sh" swe "$MODEL" "$N"