tests/test_cli.py

# tests/test_cli.py
from pathlib import Path

from fractus_vorax.agent import cli

CSV_CONTENT = (
    "question,answer\n"
    "what is the capital of france,paris\n"
    "what is the capital of spain,madrid\n"
    "what is the capital of japan,tokyo\n"
    "who wrote hamlet,william shakespeare\n"
)


def _make_csv(tmp_path):
    p = tmp_path / "cap.csv"
    p.write_text(CSV_CONTENT, encoding="utf-8")
    return p


def test_ingest_then_ask_end_to_end(tmp_path, capsys):
    csv = _make_csv(tmp_path)
    brain_dir = tmp_path / "brain"
    n = cli.ingest(csv, brain_dir, D=2048, seed=0, kn_cache=tmp_path / "kn")
    assert n == 4
    assert (brain_dir / "meta.json").exists()
    assert (tmp_path / "kn" / "cap.kn" / "manifest.json").exists()  # l'artefact .kn existe

    lines = cli.ask("what is the capital of japan", brain_dir, k=1)
    out = "\n".join(lines)
    assert "tokyo" in out
    assert "[CARTE]" in out
    assert "=>" in out  # format v2 : FAIT {statement} => {context} (remplace RÉP:)
    print(out)
    captured = capsys.readouterr()
    assert "tokyo" in captured.out


def test_ask_empty_brain(tmp_path):
    lines = cli.ask("anything", tmp_path / "nope", k=1)
    assert lines == ["[CARTE] LACUNES: aucune trace (brain vide ou absent)"]


def test_status_reports_counts(tmp_path, capsys):
    csv = _make_csv(tmp_path)
    cli.ingest(csv, tmp_path / "brain", D=2048, seed=0, kn_cache=tmp_path / "kn")
    s = cli.status(tmp_path / "brain")
    assert "4" in s


def test_main_subcommands(tmp_path, capsys):
    csv = _make_csv(tmp_path)
    brain = tmp_path / "brain"
    assert cli.main(["ingest", str(csv), "--brain", str(brain), "--D", "2048", "--kn-cache", str(tmp_path / "kn")]) == 0
    assert cli.main(["ask", "who wrote hamlet", "--brain", str(brain), "--k", "1"]) == 0
    assert "william shakespeare" in capsys.readouterr().out
    assert cli.main(["status", "--brain", str(brain)]) == 0


def test_ingest_recompiles_when_source_changes(tmp_path):
    csv = tmp_path / "cap.csv"
    csv.write_text(
        "question,answer\nwhat is the capital of france,paris\nwho wrote hamlet,william shakespeare\n",
        encoding="utf-8",
    )
    brain = tmp_path / "brain"
    cli.ingest(csv, brain, D=2048, seed=0, kn_cache=tmp_path / "kn")
    # Source éditée : 3 QA nouvelles — le cache .kn doit être invalidé puis recompilé.
    csv.write_text(
        "question,answer\nwhat color is the sky,blue\nwhat sound does a cow make,moo\nwhat is two plus two,four\n",
        encoding="utf-8",
    )
    cli.ingest(csv, brain, D=2048, seed=0, kn_cache=tmp_path / "kn")
    out = "\n".join(cli.ask("what sound does a cow make", brain, k=1))
    assert "moo" in out  # réponse uniquement présente dans les nouvelles lignes


def test_ingest_reuses_cache_when_source_unchanged(tmp_path):
    csv = _make_csv(tmp_path)
    kn_dir = tmp_path / "kn" / "cap.kn"
    cli.ingest(csv, tmp_path / "brain", D=2048, seed=0, kn_cache=tmp_path / "kn")
    mtime = (kn_dir / "atoms.tsv.gz").stat().st_mtime_ns
    cli.ingest(csv, tmp_path / "brain2", D=2048, seed=0, kn_cache=tmp_path / "kn")
    assert (kn_dir / "atoms.tsv.gz").stat().st_mtime_ns == mtime  # pas de recompilation


def test_main_missing_source_clean_error(tmp_path, capsys):
    rc = cli.main(["ingest", str(tmp_path / "nope.csv"), "--brain", str(tmp_path / "b")])
    assert rc == 1
    out = capsys.readouterr().out
    assert any(line.startswith("[VORAX] ERREUR:") for line in out.splitlines())