tests/test_core_speak.py

# tests/test_core_speak.py
"""Plan 4, tâche 4 — bench/core_speak.py : l'évaluation honnête du noyau réel.

Le test charge le VRAI checkpoint fractus (chargement strict, greedy court) :
skippé sans torch (substrat mingw), skippé si le checkpoint est absent.
Le contrat mesuré est le harnais honnête (runs verbatim + taux), pas la
qualité du texte — le checkpoint actuel est de la salade de mots et le test
l'accepte.
"""
import pytest

torch = pytest.importorskip("torch", reason="core_speak nécessite torch")

from bench.core_speak import run_core_speak


def test_core_speak_reports_honestly(tmp_path):
    import pathlib
    ckpt = pathlib.Path(r"C:\Users\PHIL\ZCodeProject\fractus\checkpoints\checkpoints\fractus_1b_latest.pt")
    if not ckpt.exists():
        pytest.skip("checkpoint absent")
    result = run_core_speak(ckpt, ["what is the capital of france"], brain=None, max_new_tokens=6)
    assert len(result["runs"]) == 1
    run = result["runs"][0]
    for key in ("question", "no_cards_output", "with_cards_output", "answer_in_output"):
        assert key in run
    assert isinstance(result["with_cards_answer_rate"], float)