Skip to content

Multi-tier framework for evaluating AI agent skills and plugins with quality gates, security scanning, harness compatibility checks, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior. Ships reusable CI templates that bring every check to any repository.

1.1 KB
Raw Blame
# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0

"""Run the packaged Streamlit entry script that the dashboard launcher starts."""

from __future__ import annotations

import sys

import pytest

pytest.importorskip("streamlit")
# st.dataframe otherwise imports these inside AppTest's timed script thread.
pytest.importorskip("pandas")
pytest.importorskip("pyarrow")
from streamlit.testing.v1 import AppTest

from skillevaluator.reporting import dashboard

# A ceiling for cold imports under xdist and coverage; passing runs finish far sooner.
_APP_TIMEOUT_SECONDS = 60


def test_entry_script_runs_dashboard_main(monkeypatch) -> None:
    # AppTest runs the script in this process, so it would otherwise read pytest's argv.
    monkeypatch.setattr(sys, "argv", [str(dashboard._APP)])
    app = AppTest.from_file(str(dashboard._APP), default_timeout=_APP_TIMEOUT_SECONDS).run()
    assert not app.exception
    assert [message.value for message in app.info] == ["Upload JSON evaluation reports to start comparing results."]