#!/usr/bin/env python3
"""Run a single benchmark for quick smoke tests.

Usage:
    python bash/run_single.py bigcodebench --limit 1
    python bash/run_single.py bfcl_v3 --limit 5 --model MODEL --api-url URL
"""
import sys
from pathlib import Path

sys.path.insert(0, str(Path(__file__).parent))
import run as run_mod
from evalscope import run_task

if len(sys.argv) < 2:
    print('Usage: python bash/run_single.py <dataset_name> [--limit N] [--model M] [--api-url U]')
    sys.exit(1)

dataset_name = sys.argv[1]
limit = None
for i, arg in enumerate(sys.argv):
    if arg == '--limit' and i + 1 < len(sys.argv):
        v = sys.argv[i + 1]
        limit = None if v.lower() in ('none', 'all') else int(v)
    elif arg == '--model' and i + 1 < len(sys.argv):
        run_mod.MODEL = sys.argv[i + 1]
    elif arg == '--api-url' and i + 1 < len(sys.argv):
        run_mod.API_URL = sys.argv[i + 1]

if dataset_name not in run_mod.DATASET_CONFIGS:
    raise SystemExit(f'{dataset_name} not in config')

run_mod.LIMIT = limit
ds_cfg = run_mod.DATASET_CONFIGS[dataset_name]
task_cfg = run_mod.build_task_config(
    dataset_name=dataset_name,
    ds_cfg=ds_cfg,
    batch_size=4,
    enable_thinking=run_mod.ENABLE_THINKING,
    seed=run_mod.SEED,
    run_idx=0,
)
print(f'Running {dataset_name} with limit={limit}')
run_task(task_cfg)
print('Done.')