import json
import os
import shutil
import subprocess
import sys
from pathlib import Path

import pytest

from infospace_bench import InfospaceError, load_infospace
from infospace_bench.evaluation_io import read_entity_evaluation
from infospace_bench.generation import parse_entity_bundle
from infospace_bench.history import read_metrics_file
from infospace_bench.markdown_adapter import validate_infospace_artifacts
from infospace_bench.semantics import list_entities, list_relations


REPO_ROOT = Path(__file__).resolve().parents[1]
PILOT = REPO_ROOT / "infospaces" / "wealth-vsm-generation-pilot"
FIXTURES = PILOT / "workflows" / "fixtures" / "wealth-vsm-fake-responses.yaml"


def cli_env() -> dict[str, str]:
    env = os.environ.copy()
    env["PYTHONPATH"] = str(REPO_ROOT / "src") + ":/home/worsch/markitect-tool/src"
    return env


def run_cli(*args: str, cwd: Path | None = None) -> subprocess.CompletedProcess[str]:
    return subprocess.run(
        [sys.executable, "-m", "infospace_bench", *args],
        check=False,
        cwd=cwd or REPO_ROOT,
        env=cli_env(),
        text=True,
        capture_output=True,
    )


def copy_pilot(tmp_path: Path) -> Path:
    target = tmp_path / PILOT.name
    shutil.copytree(PILOT, target)
    return target


def test_wealth_vsm_generation_plan_is_explicit_and_assisted() -> None:
    plan = run_cli("workflow", "plan", str(PILOT), "wealth-vsm-extract-entities")
    workflows = run_cli("workflow", "inspect", str(PILOT))

    assert plan.returncode == 0, plan.stderr
    assert workflows.returncode == 0, workflows.stderr

    plan_payload = json.loads(plan.stdout)
    workflow_ids = [
        workflow["id"] for workflow in json.loads(workflows.stdout)["workflows"]
    ]

    assert workflow_ids == [
        "wealth-vsm-extract-entities",
        "wealth-vsm-map-and-analyze",
        "wealth-vsm-evaluate-entities",
    ]
    assert plan_payload["status"] == "planned"
    assert plan_payload["assisted_requests"][0]["stage_id"] == "extract-entities"
    assert plan_payload["stages"][1]["kind"] == "split_entities"
    assert plan_payload["stages"][1]["status"] == "waiting_for_assisted_output"


def test_wealth_vsm_generation_pipeline_runs_with_fixture_adapter(
    tmp_path: Path,
) -> None:
    root = copy_pilot(tmp_path)
    fixture = root / "workflows" / "fixtures" / "wealth-vsm-fake-responses.yaml"

    extraction = run_cli(
        "workflow",
        "run",
        str(root),
        "wealth-vsm-extract-entities",
        "--fixture-responses",
        str(fixture),
    )
    second_extraction = run_cli(
        "workflow",
        "run",
        str(root),
        "wealth-vsm-extract-entities",
        "--fixture-responses",
        str(fixture),
    )
    mapping = run_cli(
        "workflow",
        "run",
        str(root),
        "wealth-vsm-map-and-analyze",
        "--fixture-responses",
        str(fixture),
    )
    evaluation = run_cli(
        "workflow",
        "run",
        str(root),
        "wealth-vsm-evaluate-entities",
        "--fixture-responses",
        str(fixture),
    )
    check = run_cli("check", str(root))
    validation = run_cli("validate", str(root))

    assert extraction.returncode == 0, extraction.stderr
    assert second_extraction.returncode == 0, second_extraction.stderr
    assert mapping.returncode == 0, mapping.stderr
    assert evaluation.returncode == 0, evaluation.stderr
    assert check.returncode == 0, check.stderr
    assert validation.returncode == 0, validation.stderr

    loaded = load_infospace(root)
    artifact_ids = [artifact.id for artifact in loaded.artifacts]
    entities = list_entities(root)
    relations = list_relations(root)
    metrics = read_metrics_file(root / "output" / "metrics" / "metrics.yaml")
    division_eval = read_entity_evaluation(
        root / "output" / "evaluations" / "division-of-labour.md"
    )
    validation_results = validate_infospace_artifacts(root)

    assert artifact_ids.count("entity/division-of-labour.md") == 1
    assert artifact_ids.count("entity/market-extent.md") == 1
    assert "generated/book-1-chapter-03-analysis.md" in artifact_ids
    assert [entity.slug for entity in entities] == [
        "division-of-labour",
        "market-extent",
    ]
    assert relations[0].subject_entity_id == "entity/division-of-labour.md"
    assert relations[0].object_entity_id == "entity/market-extent.md"
    assert division_eval.artifact_id == "entity/division-of-labour.md"
    assert metrics["per_artifact_mean"] == 4.3
    assert all(result.valid for result in validation_results)


def test_entity_bundle_parser_rejects_malformed_and_duplicate_bundles() -> None:
    with pytest.raises(InfospaceError) as missing_h1:
        parse_entity_bundle("## Definition\n\nNo top-level entity heading.")

    with pytest.raises(InfospaceError) as duplicate:
        parse_entity_bundle(
            "# Market Extent\n\n## Definition\n\nOne.\n\n"
            "# Market Extent\n\n## Definition\n\nTwo.\n"
        )

    assert missing_h1.value.code == "invalid_entity_bundle"
    assert duplicate.value.code == "duplicate_entity_bundle_item"


def test_wealth_vsm_generation_docs_capture_scale_up_risks() -> None:
    doc = (REPO_ROOT / "docs" / "wealth-vsm-generation-pipeline.md").read_text(
        encoding="utf-8"
    )
    report = (PILOT / "reports" / "generation-pilot-report.md").read_text(
        encoding="utf-8"
    )

    assert "Legacy pipeline decomposition" in doc
    assert "One-chapter pilot" in doc
    assert "Full corpus scale-up" in doc
    assert "live provider-backed generation" in doc
    assert "one-chapter regeneration" in report
    assert "not the legacy process script" in report