#!/usr/bin/env python3
"""One-time backfill: recover the rule ROLE for pre-split halachot (INV-DM7).

Before the authority/role split, the extractor stored ``rule_type='binding'``
for higher-court sources and ``'persuasive'`` for committee sources — i.e. it
recorded the source's AUTHORITY in the role field. Those 276 rows therefore have
NO genuine role. This script re-classifies each into one of the five real roles
(holding/interpretive/procedural/application/obiter) using the same local
claude_session judge the gold-set trusts (zero API cost), and writes it back to
``halachot.rule_type``.

authority is NOT touched — it is derived from ``case_law.precedent_level`` at
read time and was never stored.

    cd ~/legal-ai/mcp-server
    .venv/bin/python ../scripts/halacha_rule_role_backfill.py --limit 5   # smoke (dry)
    .venv/bin/python ../scripts/halacha_rule_role_backfill.py --apply     # full backfill

Local-only (claude_session needs the local CLI, not the container).
"""
from __future__ import annotations

import argparse
import asyncio
import csv
import sys
from datetime import datetime, timezone
from pathlib import Path
from uuid import UUID

from legal_mcp.services import claude_session, db

REPO_ROOT = Path(__file__).resolve().parent.parent
AUDIT_DIR = REPO_ROOT / "data" / "audit"

VALID_ROLES = {"holding", "interpretive", "procedural", "application", "obiter"}

SYSTEM = (
    "אתה משפטן בכיר המסווג 'הלכות' שחולצו מפסיקה לפי **סוג הכלל** בלבד "
    "(אל תסווג מחייב/משכנע — דרגת-המחייבות נגזרת אוטומטית מזהות הערכאה). "
    "בחר ערך אחד מתוך:\n"
    "- holding — עיקרון מהותי שהיה הכרחי להכרעה (ratio; מבחן Wambaugh).\n"
    "- interpretive — פרשנות הוראת-חוק/מונח/תכנית.\n"
    "- procedural — סדר-דין: סמכות/מועדים/זכות-עמידה/מיצוי/נטל.\n"
    "- application — החלה תלוית-עובדות על נסיבות התיק (לרוב לא-הלכה בת-הכללה).\n"
    "- obiter — אמרת-אגב שלא הוכרעה.\n"
    'החזר JSON בלבד: {"role": "<אחד מהחמישה>"}. ללא markdown, ללא הסבר.'
)


def _prompt(row: dict) -> str:
    return (
        f"מקור: {row.get('case_number') or ''} "
        f"(precedent_level={row.get('precedent_level') or ''}).\n"
        f"סיווג ישן (סמכות, להתעלם): {row.get('rule_type')}.\n\n"
        f"ניסוח הכלל:\n{row.get('rule_statement') or ''}\n\n"
        f"היגיון:\n{row.get('reasoning_summary') or ''}\n\n"
        f"ציטוט תומך:\n{row.get('supporting_quote') or ''}"
    )


async def _classify(row: dict) -> str | None:
    """Return the role for one row, or None on failure (caller keeps old value)."""
    try:
        raw = await claude_session.query_json(_prompt(row), system=SYSTEM)
    except Exception as e:  # noqa: BLE001 — log and skip, never crash the batch
        print(f"  ! {row['id']}: judge error ({e}) — skipped", flush=True)
        return None
    role = ""
    if isinstance(raw, dict):
        role = str(raw.get("role") or "").strip().lower()
    if role not in VALID_ROLES:
        print(f"  ? {row['id']}: invalid role {role!r} — skipped", flush=True)
        return None
    return role


async def _fetch_legacy_rows() -> list[dict]:
    pool = await db.get_pool()
    rows = await pool.fetch(
        "SELECT h.id, h.rule_type, h.rule_statement, h.reasoning_summary, "
        "       h.supporting_quote, cl.case_number, cl.precedent_level "
        "FROM halachot h LEFT JOIN case_law cl ON cl.id = h.case_law_id "
        "WHERE h.rule_type IN ('binding','persuasive') "
        "ORDER BY h.case_law_id, h.halacha_index"
    )
    return [dict(r) for r in rows]


def _backup(rows: list[dict]) -> Path:
    ts = datetime.now(timezone.utc).strftime("%Y%m%dT%H%M%SZ")
    AUDIT_DIR.mkdir(parents=True, exist_ok=True)
    out = AUDIT_DIR / f"halacha-rule-role-backfill-backup-{ts}.csv"
    with out.open("w", encoding="utf-8", newline="") as f:
        w = csv.writer(f)
        w.writerow(["id", "old_rule_type", "case_number", "precedent_level"])
        for r in rows:
            w.writerow([r["id"], r["rule_type"], r.get("case_number") or "",
                        r.get("precedent_level") or ""])
    return out


async def main(args: argparse.Namespace) -> int:
    rows = await _fetch_legacy_rows()
    if args.limit:
        rows = rows[: args.limit]
    print(f"legacy binding/persuasive rows to reclassify: {len(rows)}", flush=True)
    if not rows:
        return 0

    backup = _backup(rows)
    print(f"backup written → {backup}", flush=True)

    pool = await db.get_pool()
    changed = skipped = 0
    sem = asyncio.Semaphore(args.concurrency)

    async def _one(row: dict):
        nonlocal changed, skipped
        async with sem:
            role = await _classify(row)
        if role is None:
            skipped += 1
            return
        old = row["rule_type"]
        print(f"  {row.get('case_number') or '':<14} {old:>10} → {role}", flush=True)
        if args.apply and role != old:
            await pool.execute(
                "UPDATE halachot SET rule_type = $2, updated_at = now() WHERE id = $1",
                row["id"], role,
            )
        changed += 1

    # process in chunks to bound concurrent CLI subprocesses
    for i in range(0, len(rows), args.concurrency):
        await asyncio.gather(*(_one(r) for r in rows[i : i + args.concurrency]))

    mode = "APPLIED" if args.apply else "DRY-RUN (no writes)"
    print(f"\n{mode}: {changed} reclassified, {skipped} skipped (kept old).", flush=True)
    if not args.apply:
        print("re-run with --apply to write changes.", flush=True)
    return 0


if __name__ == "__main__":
    ap = argparse.ArgumentParser(description=__doc__,
                                 formatter_class=argparse.RawDescriptionHelpFormatter)
    ap.add_argument("--apply", action="store_true", help="write changes (default: dry-run)")
    ap.add_argument("--limit", type=int, default=0, help="only first N rows (smoke test)")
    ap.add_argument("--concurrency", type=int, default=4, help="parallel judge calls")
    sys.exit(asyncio.run(main(ap.parse_args())))