"""Explicit experimental repin and historical-source provenance contracts."""

import hashlib
import json
from pathlib import Path
import subprocess
import sys

ROOT = Path(__file__).resolve().parents[2]
sys.path.insert(0, str(ROOT / "tests/validation"))
import pytest
from source_provenance import (HistoryUnavailable, checkout_provenance, historical_sha256,
                               historical_tree)
import re100_helpers
import run_jet_circle_cv

ORIGIN = "47b05bc8abfc957fe876b0c63bdb386e3c6cbaa5"


def test_manifests_match_their_recorded_source_and_preserve_origin():
    """Historical evidence integrity: each manifest describes the tree of its own commit."""
    try:
        names = historical_tree(ROOT, ORIGIN)
    except HistoryUnavailable as error:
        pytest.skip(f"historical integrity NOT checked: {error}")
    for group, hashes_key, revision_key in (
        ("dfg_re100", "production_sha256", "commit"),
        ("jet_circle_cv", "files", "revision"),
    ):
        manifest = json.loads(
            (
                ROOT / "tests/validation/data" / group / "source_manifest.json"
            ).read_text()
        )
        assert manifest[revision_key] == ORIGIN
        assert set(manifest[hashes_key]) == set(names)
        assert manifest["source_origin_commits"][-1] == ORIGIN
        assert (
            manifest["historical_checkpoints"]["production"]
            == "d79e3f6f0a424f5bcc3a1a6d610313e49daf97a2"
        )
        assert "not inherited from d79" in manifest["experiment"]
        assert historical_sha256(ROOT, ORIGIN, manifest[hashes_key]) == manifest[hashes_key]
    assert re100_helpers.PIN == run_jet_circle_cv.PIN == ORIGIN


def test_runtime_checkout_identity_is_separate_from_source_origin(tmp_path):
    subprocess.run(["git", "init", "-q", str(tmp_path)], check=True)
    (tmp_path / "test.txt").write_text("tracked\n")
    subprocess.run(["git", "-C", str(tmp_path), "add", "test.txt"], check=True)
    subprocess.run(
        [
            "git",
            "-C",
            str(tmp_path),
            "-c",
            "user.name=Test",
            "-c",
            "user.email=test@example.invalid",
            "commit",
            "-qm",
            "fixture",
        ],
        check=True,
    )
    expected = subprocess.check_output(
        ["git", "-C", str(tmp_path), "rev-parse", "HEAD"], text=True
    ).strip()
    assert checkout_provenance(tmp_path) == dict(
        checkout_revision=expected, checkout_dirty=False
    )
    (tmp_path / "test.txt").write_text("changed\n")
    assert checkout_provenance(tmp_path) == dict(
        checkout_revision=expected, checkout_dirty=True
    )


def test_historical_check_rejects_tampering_and_reports_missing_history(tmp_path):
    with pytest.raises(HistoryUnavailable):
        historical_sha256(tmp_path, ORIGIN, ["src/x.py"])  # not a repository
    with pytest.raises(HistoryUnavailable):
        historical_sha256(ROOT, "0" * 40, ["src/x.py"])  # commit absent
    manifest = json.loads(
        (ROOT / "tests/validation/data/dfg_re100/source_manifest.json").read_text())
    name = sorted(manifest["production_sha256"])[0]
    try:
        actual = historical_sha256(ROOT, ORIGIN, [name])
    except HistoryUnavailable as error:
        pytest.skip(f"historical integrity NOT checked: {error}")
    assert actual != {name: "0" * 64}  # a tampered digest would not match