dongarandClaude Opus 5.5
e351d0a74e
A pure move; behaviour unchanged. - models (L9, L7): llm, catalog, probe, render, render_anthropic, context - log (L7, L6): canonical, views - state (L8): store (was state), reconcile, worker, cancel, dump - knowledge (L10, L6.4): vault, memory - conversation (L5): transport, matrix - execution (L13): ssh (was execution), testing - authority (P3, P4, L4): actions - gitea, oplog, envfile stay at the top until each gains a second module. Every import, monkeypatch target, script and doc reference rewritten. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
35 lines
1.1 KiB
Python
35 lines
1.1 KiB
Python
"""One live benchmark run: the simplest task, through the agent's own
|
|
client wiring, with the test config's driver."""
|
|
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from nisse_core.execution.ssh import SSHHost
|
|
from nisse_core.models.catalog import ModelCatalog
|
|
from nisse_dev.bench.runner import run_task
|
|
from nisse_dev.bench.tasks import load_tasks
|
|
from nisse_dev.config import AgentConfig
|
|
from nisse_dev.loop.build import make_llm_clients
|
|
|
|
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.driver)
|
|
[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
|