legal-ai/mcp-server/tests/test_research_md_chair_position.py

"""Chair-position round-trip in analysis-and-research.md.

Regression cover for the reader/writer asymmetry that made "עמדת ועדת הערר"
appear to save on threshold claims and then vanish on refresh: the writer
matched the label anywhere on a line, the reader only at the start of one, and
the analyst agent writes threshold claims as a bullet list
("- **עמדת ועדת הערר:**") while it writes issues flush-left.

The invariant these tests pin down: whatever update_chair_position writes,
parse() must read back — for every label form that appears in the corpus.
"""

from __future__ import annotations

from pathlib import Path

import pytest

from legal_mcp.services import research_md


BULLETED = """# ניתוח משפטי — ערר 1069-04-26
תאריך: 2026-08-02

## 5. טענות סף

### ס-1 — אי-מילוי תנאי ההפקדה
- **טענה (claim):** התכנית אושרה מבלי שמולאו תנאי ההפקדה.
- **שאלה משפטית:** האם הסטת התנאים פוגמת בחוקיות?
- **עמדת ועדת הערר:** [ימולא ע"י יו"ר הוועדה]

### ס-2 — זכות עמידה
- **טענה (claim):** לעוררים אין אינטרס מוגן.
- **עמדת ועדת הערר:** [ימולא ע"י יו"ר הוועדה]

## 6. סוגיות להכרעה

### סוגיה 1: סמכות לפי 62א(א)(11)

**ניתוח:**
- הכלל החל: ...

**עמדת ועדת הערר:** [ימולא ע"י יו"ר הוועדה]

---
"""


@pytest.fixture()
def analysis_file(tmp_path: Path) -> Path:
    path = tmp_path / "analysis-and-research.md"
    path.write_text(BULLETED, encoding="utf-8")
    return path


def _positions(path: Path) -> dict[str, str]:
    parsed = research_md.parse(path)
    items = parsed["threshold_claims"] + parsed["issues"]
    return {item["id"]: item["chair_position"] for item in items}


# ── the reported bug ────────────────────────────────────────────


def test_bulleted_threshold_position_survives_a_reload(analysis_file: Path) -> None:
    """The bug as chaim hit it: saved on a threshold claim, gone on refresh."""
    research_md.update_chair_position(analysis_file, "threshold_1", "עמדתנו היא שהטענה נדחית.")

    assert _positions(analysis_file)["threshold_1"] == "עמדתנו היא שהטענה נדחית."


def test_flush_left_issue_position_still_round_trips(analysis_file: Path) -> None:
    """The surface that already worked must keep working."""
    research_md.update_chair_position(analysis_file, "issue_1", "יש לקבל את הערר בנקודה זו.")

    assert _positions(analysis_file)["issue_1"] == "יש לקבל את הערר בנקודה זו."


def test_bulleted_threshold_fields_are_parsed_at_all(analysis_file: Path) -> None:
    """Bulleted labels were invisible to the reader — the whole claim looked empty."""
    threshold = research_md.parse(analysis_file)["threshold_claims"]

    labels = [f["label"] for f in threshold[0]["fields"]]
    assert "טענה (claim)" in labels
    assert "שאלה משפטית" in labels
    # the chair field is surfaced separately, never as a regular field
    assert not any(research_md._is_chair_label(label) for label in labels)


# ── writer/reader agreement on content boundaries ───────────────


def test_position_containing_markdown_is_not_truncated(analysis_file: Path) -> None:
    """The old writer stopped the field at the first '*' and swallowed the rest."""
    text = 'העמדה כוללת **הדגשה** וגם קו --- באמצע\nושורה שנייה.'
    research_md.update_chair_position(analysis_file, "issue_1", text)

    assert _positions(analysis_file)["issue_1"] == text


def test_update_does_not_touch_sibling_subsections(analysis_file: Path) -> None:
    research_md.update_chair_position(analysis_file, "threshold_1", "ראשונה")
    research_md.update_chair_position(analysis_file, "threshold_2", "שנייה")

    positions = _positions(analysis_file)
    assert positions["threshold_1"] == "ראשונה"
    assert positions["threshold_2"] == "שנייה"
    assert positions["issue_1"] == ""


def test_closing_rule_and_bullet_marker_are_preserved(analysis_file: Path) -> None:
    """An update must not restructure the file the analyst produced."""
    research_md.update_chair_position(analysis_file, "threshold_1", "עמדה")
    research_md.update_chair_position(analysis_file, "issue_1", "עמדה")
    content = analysis_file.read_text(encoding="utf-8")

    assert "- **עמדת ועדת הערר:**" in content
    assert content.rstrip().endswith("---")


def test_clearing_a_position_restores_the_placeholder(analysis_file: Path) -> None:
    research_md.update_chair_position(analysis_file, "threshold_1", "עמדה")
    research_md.update_chair_position(analysis_file, "threshold_1", "")

    assert _positions(analysis_file)["threshold_1"] == ""
    assert research_md.CHAIR_POSITION_PLACEHOLDERS[0] in analysis_file.read_text(
        encoding="utf-8"
    )


def test_repeated_saves_do_not_accumulate_blocks(analysis_file: Path) -> None:
    for text in ("ראשון", "שני", "שלישי"):
        research_md.update_chair_position(analysis_file, "threshold_1", text)

    content = analysis_file.read_text(encoding="utf-8")
    assert content.count(f"**{research_md.CHAIR_POSITION_LABEL}:**") == 3
    assert _positions(analysis_file)["threshold_1"] == "שלישי"


# ── decorated and duplicated labels ─────────────────────────────


def test_decorated_label_is_updated_not_duplicated(tmp_path: Path) -> None:
    """'עמדת ועדת הערר (הכוונת יו"ר 24.6)' appears in the corpus (8125-09-24)."""
    path = tmp_path / "a.md"
    path.write_text(
        "## 6. סוגיות להכרעה\n\n"
        "### סוגיה 1: כותרת\n\n"
        '**עמדת ועדת הערר (הכוונת יו"ר 24.6):** [ימולא ע"י יו"ר הוועדה]\n',
        encoding="utf-8",
    )

    research_md.update_chair_position(path, "issue_1", "עמדה מעודכנת")

    content = path.read_text(encoding="utf-8")
    assert content.count(research_md.CHAIR_POSITION_LABEL) == 1
    assert _positions(path)["issue_1"] == "עמדה מעודכנת"


def test_duplicate_labels_read_back_the_one_that_was_written(tmp_path: Path) -> None:
    """An H3 covering several issues (1033-02-25) must not read a sibling's text."""
    path = tmp_path / "a.md"
    path.write_text(
        "## 6. סוגיות להכרעה\n\n"
        "### סוגיות 4–6: מקובצות\n\n"
        "**עמדת ועדת הערר:** ראשונה\n\n"
        "**עמדת ועדת הערר:** אחרונה\n",
        encoding="utf-8",
    )

    research_md.update_chair_position(path, "issue_1", "העמדה הנכונה")

    assert _positions(path)["issue_1"] == "העמדה הנכונה"


# ── read-after-write guard ──────────────────────────────────────


def test_update_returns_the_persisted_value(analysis_file: Path) -> None:
    result = research_md.update_chair_position(analysis_file, "threshold_1", "  עמדה  ")

    assert result["saved"] is True
    assert result["position"] == "עמדה"


def test_a_write_the_parser_cannot_read_back_is_reported_as_failure(
    analysis_file: Path, monkeypatch: pytest.MonkeyPatch
) -> None:
    """Regression guard: the bug hid behind a success response for months."""
    monkeypatch.setattr(
        research_md, "_stored_chair_position", lambda *_args: "משהו אחר"
    )

    with pytest.raises(RuntimeError, match="לא נקראה בחזרה"):
        research_md.update_chair_position(analysis_file, "threshold_1", "עמדה")


# ── downstream consumers see the recovered positions ────────────


def test_chair_directions_count_bulleted_positions(analysis_file: Path) -> None:
    """extract_chair_directions feeds legal-writer; it under-reported before."""
    research_md.update_chair_position(analysis_file, "threshold_1", "עמדה")

    directions = research_md.extract_chair_directions(analysis_file)
    assert directions["filled_count"] == 1
    assert directions["status"] == "partial"
    filled = [t for t in directions["threshold_claims"] if t["direction"]]
    assert [t["id"] for t in filled] == ["threshold_1"]


# ── the real corpus ─────────────────────────────────────────────


CORPUS = sorted(
    Path("/home/chaim/legal-ai/data/cases").glob(
        "*/documents/research/analysis-and-research.md"
    )
)


@pytest.mark.skipif(not CORPUS, reason="case corpus not present on this host")
@pytest.mark.parametrize("source", CORPUS, ids=lambda p: p.parts[-4])
def test_every_corpus_subsection_round_trips(source: Path, tmp_path: Path) -> None:
    sentinel = "עמדת-בדיקה — **הדגשה** ו---קו\nושורה שנייה."
    before = _positions(source)

    for section_id in before:
        working = tmp_path / f"{section_id}.md"
        working.write_text(source.read_text(encoding="utf-8"), encoding="utf-8")

        research_md.update_chair_position(working, section_id, sentinel)
        after = _positions(working)

        assert after[section_id] == sentinel, f"{source.parts[-4]} {section_id}"
        untouched = {k: v for k, v in after.items() if k != section_id}
        assert untouched == {k: v for k, v in before.items() if k != section_id}