"""One live benchmark run: the simplest task, through the agent's own
client wiring, with the test config's executor."""

from pathlib import Path

import pytest

from nisse_dev.agent import make_llm_clients
from nisse_dev.bench.runner import run_task
from nisse_dev.bench.tasks import load_tasks
from nisse_dev.catalog import ModelCatalog
from nisse_dev.config import AgentConfig
from nisse_dev.execution import SSHHost

pytestmark = pytest.mark.integration


def test_the_simplest_task_passes_live(
    live_config: AgentConfig, tmp_path: Path, ssh_host: SSHHost
) -> None:
    catalog = ModelCatalog.discover(live_config.llm_base_url, live_config.llm_token)
    normalized, _ = make_llm_clients(live_config, catalog)
    facts = catalog.facts(live_config.roles.executor)
    [task] = load_tasks(["write-function"])

    record = run_task(
        task, facts, normalized, live_config.tuning, host=ssh_host, workdir=tmp_path
    )

    assert record.fallbacks == []
    assert record.success, (
        f"{record.outcome}: {record.outcome_note}\n{record.check_output}"
    )
    assert record.cost >= 0