#!/usr/bin/env bash
# Full evaluation (T5.5): trained model + all baselines through the same
# parse_answer + ts_metrics pipeline → reports/eval-YYYYMMDD.md
#
# Usage:
#   scripts/run_eval.sh                   # trivial baselines only (CPU, fast)
#   scripts/run_eval.sh --model           # include the trained model (GPU)
set -euo pipefail
cd "$(dirname "$0")/.."

export PYTHONPATH=src
.venv/bin/python -m tsmm.eval.report \
  --synth data/eval_synth.jsonl \
  --real data/eval_real.jsonl \
  --report_dir reports \
  --judge_backend "${JUDGE_BACKEND:-stub}" \
  "$@"