Merge pull request 'feat(nevo): backfill leaked preamble + ratio gold-set benchmark (#86)' (#91) from worktree-task86-nevo-backfill-benchmark into main

mcp-server/src/legal_mcp/services/db.py

@@ -619,6 +619,12 @@ ALTER TABLE case_law ADD COLUMN IF NOT EXISTS practice_area TEXT DEFAULT '';
 ALTER TABLE case_law ADD COLUMN IF NOT EXISTS appeal_subtype TEXT DEFAULT '';
 ALTER TABLE case_law ADD COLUMN IF NOT EXISTS headnote TEXT DEFAULT '';
     -- chair-editable abstract shown in search results.
+ALTER TABLE case_law ADD COLUMN IF NOT EXISTS nevo_ratio TEXT DEFAULT '';
+    -- The Nevo editorial מיני-רציו block, captured at ingest *before* it is
+    -- stripped from the body (#86.3). Kept separate from `headnote` (which is
+    -- our own abstract) so it can serve as a free professional gold-set for
+    -- benchmarking halacha-extraction recall/precision. Empty when the source
+    -- is not a Nevo export or carries no mini-ratio.
 ALTER TABLE case_law ADD COLUMN IF NOT EXISTS source_type TEXT DEFAULT '';
     -- 'court_ruling' | 'appeals_committee'
 
@@ -3263,7 +3269,7 @@ async def update_case_law(case_law_id: UUID, **fields) -> dict | None:
     """
     allowed = {
         "case_number", "case_name", "court", "date", "practice_area", "appeal_subtype",
-        "subject_tags", "summary", "headnote", "key_quote", "source_url",
+        "subject_tags", "summary", "headnote", "nevo_ratio", "key_quote", "source_url",
         "source_type", "precedent_level", "is_binding", "district", "chair_name",
         "proceeding_type", "citation_formatted",
     }

mcp-server/src/legal_mcp/services/extractor.py

@@ -362,12 +362,24 @@ _NEVO_MARKERS = ("ספרות:", "חקיקה שאוזכרה:", "מיני-רציו
 # preamble: bibliography + מיני-רציו). Two families:
 #   - ועדת ערר / district openings (בפנינו / הערר שבנדון / ...)
 #   - COURT-RULING openings (#86.1): a פסק-דין header or the authoring judge's
-#     line ("השופט/ת X:", "כב' השופט", "הנשיא"). Without these, Nevo court
-#     judgments — exactly the ones carrying a מיני-רציו — slipped through unstripped
-#     (e.g. בג"ץ 1764/05), risking that the extractor reads Nevo's answer key.
+#     line. Without these, Nevo court judgments — exactly the ones carrying a
+#     מיני-רציו — slipped through unstripped (e.g. בג"ץ 1764/05).
+#
+# #86.2 hardening — two over-strip bugs found while backfilling:
+#   1. ``פסק-דין`` headers are often markdown-wrapped (``**פסק  דין**``); the old
+#      ``^פסק[- ]דין`` required the keyword to be the very first char of the line
+#      and allowed only one separator, so it missed the header and fell through
+#      to a citation 32K deep (עמ"נ 50567-07-21). We now tolerate leading
+#      markdown/whitespace and 0-3 separators.
+#   2. Bare ``השופט``/``הנשיא`` matched *citations* ("השופט מ' חשין, פסקה 23"),
+#      stripping real decision body. The authoring-judge line ends with a COLON
+#      ("השופט י' עמית:"); citations use a comma. We now require the colon.
 _DECISION_START = re.compile(
-    r"^(בפנינו|לפנינו|לפניי|הערר שבנדון|ועדת הערר לתכנון|רקע עובדתי|עסקינן|"
-    r"פסק[- ]דין|פסק[- ]דינו|כב(?:וד)?['׳]?\s*השופט|המשנה לנשיא|הנשיא|השופט)",
+    r"^[ \t>*_#]{0,6}(?:"
+    r"בפנינו|לפנינו|לפניי|הערר שבנדון|ועדת הערר לתכנון|רקע עובדתי|עסקינן|"
+    r"פסק[ \t\-]{0,3}די(?:ן|נו)|"  # פסק-דין / פסק דין / **פסק  דין** header (final-nun ן vs דינו)
+    r"(?:כב(?:וד)?['׳\"]?\s*)?(?:ה?שופט[ת]?|ה?נשיא[ה]?|המשנה לנשיא)\s+[^\n,]{1,40}:"  # author line → colon
+    r")",
     re.MULTILINE,
 )
 
@@ -388,3 +400,41 @@ def strip_nevo_preamble(text: str) -> str:
         logger.debug("Stripped %d chars of Nevo preamble", m.start())
         return stripped
     return text
+
+
+_RATIO_MARKER = "מיני-רציו:"
+
+
+def extract_nevo_ratio(text: str) -> str:
+    """Return the Nevo מיני-רציו block (editorial holdings summary), or ''.
+
+    The mini-ratio is Nevo's own headnote — a concise, professionally-written
+    list of the holdings. We capture it *before* :func:`strip_nevo_preamble`
+    discards it, to serve as a free gold-set for benchmarking how well our
+    halacha extractor covers the real holdings (#86.3).
+
+    The block runs from the ``מיני-רציו:`` marker to whichever comes first:
+    the decision body (``_DECISION_START``) or the next preamble marker
+    (bibliography / legislation). Returns '' when there is no mini-ratio.
+    """
+    if not text:
+        return ""
+    start = text.find(_RATIO_MARKER)
+    if start == -1:
+        return ""
+    body = text[start + len(_RATIO_MARKER):]
+
+    # End at the earliest of: decision body start, or a following preamble
+    # marker (ספרות: / חקיקה שאוזכרה: / ...). Both are measured relative to
+    # the ratio body so we never run past it into the judgment itself.
+    end = len(body)
+    dm = _DECISION_START.search(body)
+    if dm:
+        end = min(end, dm.start())
+    for marker in _NEVO_MARKERS:
+        if marker == _RATIO_MARKER:
+            continue
+        pos = body.find(marker)
+        if pos != -1:
+            end = min(end, pos)
+    return body[:end].strip()

mcp-server/src/legal_mcp/services/ingest.py

@@ -158,9 +158,14 @@ async def ingest_document(
         except Exception as e:
             await progress("failed", 100, f"כשל בחילוץ טקסט: {e}")
             raise
-        raw_text = extractor.strip_nevo_preamble((raw_text or "")).strip()
+        raw_text = (raw_text or "")
     else:
-        raw_text = (text or "").strip()
+        raw_text = (text or "")
+    # Capture the Nevo מיני-רציו (editorial holdings summary) BEFORE stripping
+    # it out — it is a free professional gold-set for benchmarking halacha
+    # extraction (#86.3). Stored on the case_law row below once we have its id.
+    nevo_ratio = extractor.extract_nevo_ratio(raw_text)
+    raw_text = extractor.strip_nevo_preamble(raw_text).strip()
     if not raw_text:
         await progress("failed", 100, "לא נמצא טקסט בקובץ")
         raise ValueError("no extractable text in file")
@@ -180,6 +185,13 @@ async def ingest_document(
     )
     case_law_id = UUID(str(record["id"]))
 
+    # Persist the captured mini-ratio (best-effort; never block ingest on it).
+    if nevo_ratio:
+        try:
+            await db.update_case_law(case_law_id, nevo_ratio=nevo_ratio)
+        except Exception as e:  # noqa: BLE001 — additive metadata, non-fatal
+            logger.warning("could not store nevo_ratio for %s: %s", case_law_id, e)
+
     try:
         stored_chunks = await _chunk_embed_store(case_law_id, raw_text, page_offsets, page_count, progress)
         await db.mark_indexed(case_law_id)

mcp-server/tests/test_nevo_preamble.py

@@ -55,3 +55,64 @@ def test_markers_past_400_chars_still_detected():
     text = header + _PREAMBLE + "השופטת ע' ארבל:\n\nגוף ההחלטה..."
     out = ex.strip_nevo_preamble(text)
     assert out.startswith("השופטת ע' ארבל:")
+
+
+# ── extract_nevo_ratio (#86.3 gold-set capture) ──
+
+def test_extract_ratio_returns_block_before_body():
+    text = _PREAMBLE + "השופט ס' ג'ובראן:\n\nגוף ההחלטה..."
+    ratio = ex.extract_nevo_ratio(text)
+    assert "העותרים לא הוכיחו טעם מיוחד" in ratio
+    assert "המחוקק הגביל את הזמן" in ratio
+    # must not bleed into the judgment body
+    assert "גוף ההחלטה" not in ratio
+    assert "השופט ס' ג'ובראן" not in ratio
+
+
+def test_extract_ratio_stops_at_following_marker():
+    # ratio first, then a bibliography marker AFTER it
+    text = (
+        "מיני-רציו:\n* עיקרון אחד בלבד.\n\n"
+        "פסקי דין שאוזכרו:\nבג\"ץ 1/00\n\n"
+        "פסק-דין\nגוף..."
+    )
+    ratio = ex.extract_nevo_ratio(text)
+    assert "עיקרון אחד בלבד" in ratio
+    assert "פסקי דין שאוזכרו" not in ratio
+    assert "בג\"ץ 1/00" not in ratio
+
+
+def test_extract_ratio_empty_when_no_marker():
+    assert ex.extract_nevo_ratio("פסק דין\nהשופט כהן: ...") == ""
+    assert ex.extract_nevo_ratio("") == ""
+
+
+# ── #86.2 over-strip regressions ──
+
+def test_citation_judge_line_is_not_a_decision_start():
+    # "השופט מ' חשין, פסקה 23" is a CITATION (comma, no colon) — must NOT be
+    # treated as the decision opening, or 32K of real body gets stripped.
+    body = (
+        "**פסק דין**\n\n"
+        "שני ערעורים לפניי. כפי שנפסק מפי כבוד \n\n"
+        "השופט מ' חשין, פסקה 23 (להלן עניין קהתי), יש לבחון...\n"
+    )
+    text = _PREAMBLE + body
+    out = ex.strip_nevo_preamble(text)
+    assert out.startswith("**פסק דין**")
+    assert "השופט מ' חשין, פסקה" in out  # citation kept inside body
+    assert "מיני-רציו" not in out
+
+
+def test_markdown_wrapped_pdin_header_is_stripped():
+    text = _PREAMBLE + "**פסק  דין**\n\nשני ערעוריה הנדונים..."
+    out = ex.strip_nevo_preamble(text)
+    assert out.startswith("**פסק  דין**")
+    assert "מיני-רציו" not in out
+
+
+def test_author_line_with_colon_still_strips():
+    text = _PREAMBLE + "כב' השופטת ד' ברק-ארז:\n\nגוף ההחלטה..."
+    out = ex.strip_nevo_preamble(text)
+    assert out.startswith("כב' השופטת ד' ברק-ארז:")
+    assert "מיני-רציו" not in out

scripts/SCRIPTS.md

@@ -36,6 +36,8 @@
 | `multimodal_backfill.py` | python | Backfill voyage-multimodal-3 page embeddings על מסמכי תיקים קיימים. idempotent (skips by default), forces `MULTIMODAL_ENABLED=true` ל-run, רץ מהקונטיינר. שלב C — ראה `docs/voyage-upgrades-plan.md` | ידני per-case (`python multimodal_backfill.py 8174-24 8137-24`) |
 | `backfill_chunk_pages.py` | python | Backfill `page_number` ב-`document_chunks` קיימים. legacy chunker לא tracked עמודים → `page_number=NULL` חוסם boost של multimodal hybrid (text+image join על אותו עמוד). re-extracts כל PDF (re-OCR אם צריך, ~$0.0015/page), מחשב page_offsets, ומעדכן chunks. idempotent | ידני per-case (`python backfill_chunk_pages.py 8174-24 8137-24`) |
 | `rechunk_legacy_precedents.py` | python | **#57** — re-chunk + re-embed פסיקה שהוטמעה לפני תיקון ה-chunker (#55). בוחר כל `case_law` עם chunk זעיר (`length(trim(content))<50` — טביעת-האצבע של ה-chunker הישן) ומריץ `ingest.reindex_case_law` (re-chunk+re-embed מ-`full_text` שמור בלבד — ללא re-OCR/LLM, feedback_no_reocr_retrofit; idempotent DELETE-then-INSERT). idempotent ברמת-הבאטץ' (שואב מחדש את הסט המושפע בכל ריצה). דגל `--limit N`. רץ עם venv של mcp-server (`cd mcp-server && .venv/bin/python ../scripts/rechunk_legacy_precedents.py`) | חד-פעמי — מיגרציית-נתונים של פסיקה legacy (תוקן 2026-06-03) |
+| `backfill_nevo_preamble.py` | python | **#86.2** — מיגרציית-נתונים: חיתוך preamble/רציו של נבו שדלף לפסיקה שהוטמעה לפני תיקון #86.1. מאתר כל `case_law` ש-`strip_nevo_preamble(full_text)` עדיין מקצר (דליפה היסטורית), ומבצע: (1) לכידת ה-מיני-רציו ל-`case_law.nevo_ratio` (gold-set ל-#86.3); (2) שכתוב `full_text` החתוך + חישוב-מחדש של `content_hash`; (3) `reindex_case_law` (re-chunk+embed, ללא re-OCR/LLM); (4) **סימון (לא מחיקה)** הלכות ש-`supporting_quote` שלהן בתוך ה-preamble שהוסר → `pending_review` + quality_flag `nevo_preamble_leak`. **שומר-בטיחות:** שורות עם keep%<`--min-keep` (ברירת-מחדל 60) מוחרגות מ-`--apply` כחשד over-strip (אלא אם `--include-suspicious`). **dry-run כברירת-מחדל**; `--apply` כותב backup JSON + manifest CSV ל-`data/audit/` תחילה. idempotent. רץ עם venv של mcp-server. **chair-gated** (לאמת manifest לפני apply) | מיגרציית-נתונים — dry-run בוצע (19 פסקים, 27 הלכות מזוהמות); apply ממתין לאישור |
+| `nevo_ratio_benchmark.py` | python | **#86.3** — מדידת איכות חילוץ-הלכות מול ה-מיני-רציו של נבו (gold-set מקצועי חינמי). לכל פסק עם `nevo_ratio` (או נגזר מ-`full_text` אם טרם בוצע backfill): LLM-judge מקומי (`claude_session`, אפס עלות) ממפה סמנטית את הלכות-המערכת מול הלכות-נבו ומפיק **recall** (כיסוי הלכות-נבו), **precision** (אחוז הלכותינו הממופות), **granularity** (יחס פירוק — איתות over-extraction ל-#81.5). `--case <num>` / `--all [--limit N]` / `--model` / `--out`. כותב CSV ל-`data/audit/`. רץ עם venv של mcp-server (דורש Claude CLI מקומי). אומת על בג"ץ 1764/05: recall 0.875, precision 1.0, granularity 1.75x | ידני — מדידת-איכות (CI/ad-hoc) |
 | `audit_corpus_integrity.py` | python | בדיקה תקופתית של עקביות הקורפוס — 3 בדיקות SQL read-only על `case_law` ו-`cases`: (A) `external_upload` עם prefix פנימי `ערר`/`בל"מ`; (B) `internal_committee` חסר `chair_name`/`district`; (C) `cases.practice_area` מחוץ ל-{`rishuy_uvniya`, `betterment_levy`, `compensation_197`, `''`}. כותב log מצטבר ל-`data/logs/corpus_integrity_audit.log` ובמצב הפרות שולח wakeup ל-CEO ב-Paperclip (best-effort, רק אם `PAPERCLIP_API_URL`+`PAPERCLIP_API_KEY` מוגדרים). דגל: `--no-notify`. Idempotent, יוצא 0. **Cron יומי 07:00**: `0 7 * * * /home/chaim/legal-ai/mcp-server/.venv/bin/python /home/chaim/legal-ai/scripts/audit_corpus_integrity.py` | `0 7 * * *` (cron) |
 | `backfill_legal_arguments.py` | python | Backfill `legal_arguments` לתיקים עם `claims` קיימים (TaskMaster #36). מקבץ פרופוזיציות גולמיות לטיעונים משפטיים מובחנים (~6-12 לכל צד) דרך `argument_aggregator.aggregate_claims_to_arguments` (Claude CLI). תומך `--dry-run`/`--apply`/`--force`/`--case <num>...`. **חייב לרוץ מהמכונה המקומית** (לא קונטיינר) — `claude_session` דורש Claude CLI | ידני per-case (`python scripts/backfill_legal_arguments.py --apply --case 1017-03-26`) |
 | `upload_blam_decisions.py` | python | חד-פעמי (2026-05-26) — העלאת 2 החלטות בל"מ ל-`case_law` (8126/24 סופר נוח, 8047/23 הרנון) דרך `ingest_internal_decision` ישיר, עוקף MCP server שטרם נטען מחדש אחרי הוספת `proceeding_type`. **לא להריץ שוב** | חד-פעמי — להעביר ל-`.archive/` בהזדמנות |

scripts/backfill_nevo_preamble.py

@@ -0,0 +1,240 @@
+#!/usr/bin/env python3
+"""#86.2 — backfill: strip leaked Nevo preamble/ratio from already-ingested rulings.
+
+Court rulings ingested BEFORE the #86.1 fix kept their Nevo preamble
+(bibliography + מיני-רציו) because the old ``_DECISION_START`` regex only
+matched ועדת-ערר openings, not ``פסק-דין``/judge openings. For those rows the
+preamble is baked into the stored ``full_text`` AND into the chunks — and the
+מיני-רציו (Nevo's editorial answer-key) may have leaked into extracted
+halachot, contaminating the corpus.
+
+This script finds every case_law row whose stored ``full_text`` would still be
+shortened by the CURRENT ``strip_nevo_preamble`` (i.e. a pre-fix leak), and:
+
+  1. captures the מיני-רציו into ``case_law.nevo_ratio`` (gold-set for #86.3),
+     unless that column is already populated;
+  2. rewrites ``full_text`` to the stripped body + recomputes ``content_hash``;
+  3. re-chunks + re-embeds via ``ingest.reindex_case_law`` (no re-OCR, no LLM);
+  4. flags — never deletes — halachot whose supporting_quote lives entirely in
+     the removed preamble region: review_status -> 'pending_review' plus a
+     'nevo_preamble_leak' quality_flag, so the chair can re-judge them (#84).
+
+DRY-RUN BY DEFAULT. ``--apply`` performs the migration and first writes a JSON
+backup + CSV manifest to ``data/audit/`` (per the code-protocol data-migration
+rule). Idempotent: a re-run finds nothing because stripped rows no longer match.
+
+Run with the MCP server venv (config loads ~/.env / Infisical for POSTGRES +
+VOYAGE, same as the live MCP tools):
+
+    cd ~/legal-ai/mcp-server
+    .venv/bin/python ../scripts/backfill_nevo_preamble.py            # dry-run
+    .venv/bin/python ../scripts/backfill_nevo_preamble.py --apply    # migrate
+    .venv/bin/python ../scripts/backfill_nevo_preamble.py --limit 3  # smoke
+"""
+from __future__ import annotations
+
+import argparse
+import asyncio
+import csv
+import json
+import sys
+from datetime import datetime, timezone
+from pathlib import Path
+
+from legal_mcp.services import db, ingest
+from legal_mcp.services.extractor import extract_nevo_ratio, strip_nevo_preamble
+from legal_mcp.services.halacha_quality import normalize_text
+
+REPO_ROOT = Path(__file__).resolve().parent.parent
+AUDIT_DIR = REPO_ROOT / "data" / "audit"
+
+# Safety: a clean strip removes only the Nevo preamble (a small head). If the
+# strip would discard more than this fraction of the document, treat it as a
+# suspected over-strip (a citation/heading false-match) and DO NOT auto-apply
+# — surface it for manual review instead. Destroying real decision body is
+# far worse than leaving a preamble in place.
+DEFAULT_MIN_KEEP_PCT = 60
+
+
+async def _scan(conn, limit: int | None) -> list[dict]:
+    """Return rows whose stored full_text still carries a Nevo preamble."""
+    rows = await conn.fetch(
+        "SELECT id, case_number, full_text, nevo_ratio "
+        "FROM case_law WHERE full_text <> '' ORDER BY case_number"
+    )
+    hits: list[dict] = []
+    for r in rows:
+        full = r["full_text"] or ""
+        stripped = strip_nevo_preamble(full)
+        if stripped == full:
+            continue  # no leak (already clean, or never had a preamble)
+        removed = full[: len(full) - len(stripped)]
+        ratio = extract_nevo_ratio(full)
+        keep_pct = round(100 * len(stripped) / len(full)) if full else 0
+        hits.append({
+            "id": r["id"],
+            "case_number": r["case_number"],
+            "full_text": full,
+            "stripped": stripped,
+            "removed": removed,
+            "ratio": ratio,
+            "keep_pct": keep_pct,
+            "had_ratio_stored": bool((r["nevo_ratio"] or "").strip()),
+        })
+        if limit and len(hits) >= limit:
+            break
+    return hits
+
+
+async def _contaminated_halachot(conn, case_law_id, removed: str) -> list[dict]:
+    """Halachot whose supporting_quote sits entirely inside the removed preamble."""
+    norm_removed = normalize_text(removed)
+    if not norm_removed:
+        return []
+    rows = await conn.fetch(
+        "SELECT id, halacha_index, supporting_quote, review_status, quality_flags "
+        "FROM halachot WHERE case_law_id = $1",
+        case_law_id,
+    )
+    bad = []
+    for r in rows:
+        q = normalize_text(r["supporting_quote"] or "")
+        if len(q) >= 20 and q in norm_removed:
+            bad.append(dict(r))
+    return bad
+
+
+async def main(args: argparse.Namespace) -> int:
+    ts = datetime.now(timezone.utc).strftime("%Y%m%dT%H%M%SZ")
+    pool = await db.get_pool()
+    async with pool.acquire() as conn:
+        hits = await _scan(conn, args.limit)
+        for h in hits:
+            h["contaminated"] = await _contaminated_halachot(conn, h["id"], h["removed"])
+
+    # Partition into safe (auto-appliable) vs suspicious (manual review).
+    for h in hits:
+        h["suspicious"] = h["keep_pct"] < args.min_keep
+    safe = [h for h in hits if not h["suspicious"]]
+    suspicious = [h for h in hits if h["suspicious"]]
+
+    n = len(hits)
+    total_contam = sum(len(h["contaminated"]) for h in hits)
+    print(f"leaked rulings found: {n}  (contaminated halachot: {total_contam}; "
+          f"safe: {len(safe)}, suspicious<{args.min_keep}%: {len(suspicious)})", flush=True)
+    for h in hits:
+        print(
+            f"  {'⚠ ' if h['suspicious'] else '  '}{h['case_number']}: "
+            f"keep {h['keep_pct']}%, -{len(h['removed']):,} preamble chars, "
+            f"ratio={len(h['ratio'])} chars, "
+            f"{len(h['contaminated'])} contaminated halachot"
+            + ("" if h["ratio"] else "  [no mini-ratio]")
+            + ("  [ratio already stored]" if h["had_ratio_stored"] else ""),
+            flush=True,
+        )
+    if suspicious:
+        print(f"\n⚠ {len(suspicious)} ruling(s) below {args.min_keep}% keep — "
+              "EXCLUDED from --apply (suspected over-strip). Review manually or "
+              "pass --include-suspicious to force.", flush=True)
+
+    if not hits:
+        print("nothing to backfill — corpus clean ✓", flush=True)
+        return 0
+
+    apply_set = hits if args.include_suspicious else safe
+
+    # Always write a manifest (dry-run included) for the audit trail.
+    AUDIT_DIR.mkdir(parents=True, exist_ok=True)
+    manifest = AUDIT_DIR / f"nevo-backfill-manifest-{ts}.csv"
+    with manifest.open("w", encoding="utf-8", newline="") as f:
+        w = csv.writer(f)
+        w.writerow(["case_law_id", "case_number", "keep_pct", "preamble_chars",
+                    "ratio_chars", "contaminated_halachot", "suspicious", "applied"])
+        for h in hits:
+            will_apply = args.apply and (not h["suspicious"] or args.include_suspicious)
+            w.writerow([h["id"], h["case_number"], h["keep_pct"], len(h["removed"]),
+                        len(h["ratio"]), len(h["contaminated"]), h["suspicious"], will_apply])
+    print(f"manifest: {manifest}", flush=True)
+
+    if not args.apply:
+        print("\nDRY-RUN — no changes written. Re-run with --apply to migrate.", flush=True)
+        return 0
+
+    # Backup the BEFORE state before mutating anything.
+    backup = AUDIT_DIR / f"nevo-backfill-backup-{ts}.json"
+    with backup.open("w", encoding="utf-8") as f:
+        json.dump([
+            {
+                "id": str(h["id"]),
+                "case_number": h["case_number"],
+                "full_text": h["full_text"],
+                "ratio": h["ratio"],
+                "contaminated": [
+                    {"id": str(c["id"]), "halacha_index": c["halacha_index"],
+                     "review_status": c["review_status"],
+                     "quality_flags": list(c["quality_flags"] or [])}
+                    for c in h["contaminated"]
+                ],
+            }
+            for h in apply_set
+        ], f, ensure_ascii=False, indent=2)
+    print(f"backup: {backup}", flush=True)
+
+    n_apply = len(apply_set)
+    ok, failed = 0, []
+    for i, h in enumerate(apply_set, 1):
+        cid, cn = h["id"], h["case_number"]
+        try:
+            async with pool.acquire() as conn:
+                async with conn.transaction():
+                    # 1+2: rewrite full_text + content_hash; store ratio if absent.
+                    await conn.execute(
+                        "UPDATE case_law SET full_text = $2, content_hash = $3 WHERE id = $1",
+                        cid, h["stripped"], db._content_hash(h["stripped"]),
+                    )
+                    if h["ratio"] and not h["had_ratio_stored"]:
+                        await conn.execute(
+                            "UPDATE case_law SET nevo_ratio = $2 WHERE id = $1",
+                            cid, h["ratio"],
+                        )
+                    # 4: flag (never delete) contaminated halachot.
+                    for c in h["contaminated"]:
+                        flags = list(c["quality_flags"] or [])
+                        if "nevo_preamble_leak" not in flags:
+                            flags.append("nevo_preamble_leak")
+                        await conn.execute(
+                            "UPDATE halachot SET review_status = 'pending_review', "
+                            "quality_flags = $2 WHERE id = $1",
+                            c["id"], flags,
+                        )
+            # 3: reindex outside the txn (its own DELETE-then-INSERT + embeddings).
+            res = await ingest.reindex_case_law(cid)
+            ok += 1
+            print(f"[{i}/{n_apply}] OK  {cn}: -> {res['chunks']} chunks, "
+                  f"{len(h['contaminated'])} halachot flagged", flush=True)
+        except Exception as e:  # noqa: BLE001 — per-row, keep going
+            failed.append((cn, str(e)))
+            print(f"[{i}/{n_apply}] FAIL {cn}: {e}", flush=True)
+
+    print(f"\nDONE — {ok}/{n_apply} migrated, {len(failed)} failed"
+          + (f", {len(suspicious)} suspicious skipped" if suspicious and not args.include_suspicious else ""),
+          flush=True)
+    for cn, e in failed:
+        print(f"  FAILED {cn}: {e}", flush=True)
+    return 0 if not failed else 1
+
+
+if __name__ == "__main__":
+    ap = argparse.ArgumentParser(description=__doc__,
+                                 formatter_class=argparse.RawDescriptionHelpFormatter)
+    ap.add_argument("--apply", action="store_true",
+                    help="perform the migration (default: dry-run)")
+    ap.add_argument("--limit", type=int, default=None,
+                    help="process only the first N leaked rulings")
+    ap.add_argument("--min-keep", type=int, default=DEFAULT_MIN_KEEP_PCT,
+                    help=f"min%% of doc that must remain after strip to auto-apply "
+                         f"(default {DEFAULT_MIN_KEEP_PCT}); lower = suspected over-strip")
+    ap.add_argument("--include-suspicious", action="store_true",
+                    help="force --apply on rows below --min-keep (use with care)")
+    args = ap.parse_args()
+    sys.exit(asyncio.run(main(args)))

scripts/nevo_ratio_benchmark.py

@@ -0,0 +1,173 @@
+#!/usr/bin/env python3
+"""#86.3 — benchmark halacha-extraction quality against Nevo's מיני-רציו gold-set.
+
+Nevo's editorial מיני-רציו is a free, professionally-written list of a ruling's
+holdings. By comparing the halachot WE extracted against it we get an honest,
+zero-cost measurement of extraction quality per ruling:
+
+  * recall      — fraction of Nevo's holdings that our halachot cover
+  * precision   — fraction of our halachot that map to a Nevo holding
+  * granularity — our_count / nevo_holding_count (over-decomposition signal,
+                  the #81.5 concern: e.g. 14 ours vs 4 Nevo = 3.5x)
+
+The gold-truth ratio is read from ``case_law.nevo_ratio`` (populated by
+``backfill_nevo_preamble.py`` / ingest). For rulings not yet backfilled it
+falls back to computing the ratio on-the-fly from the stored ``full_text``,
+so the harness works before and after the migration.
+
+An LLM-as-judge (local ``claude_session``, zero API cost) does the semantic
+mapping — string overlap can't tell "same holding, different words" from a
+genuinely new holding. The judge is asked to count, not to rewrite.
+
+Run with the MCP server venv (needs the local ``claude`` CLI):
+
+    cd ~/legal-ai/mcp-server
+    .venv/bin/python ../scripts/nevo_ratio_benchmark.py --case 'בג"ץ 1764/05'
+    .venv/bin/python ../scripts/nevo_ratio_benchmark.py --all --limit 5
+    .venv/bin/python ../scripts/nevo_ratio_benchmark.py --all   # full corpus
+"""
+from __future__ import annotations
+
+import argparse
+import asyncio
+import csv
+import json
+import sys
+from datetime import datetime, timezone
+from pathlib import Path
+
+from legal_mcp.services import claude_session, db
+from legal_mcp.services.extractor import extract_nevo_ratio
+
+REPO_ROOT = Path(__file__).resolve().parent.parent
+AUDIT_DIR = REPO_ROOT / "data" / "audit"
+
+_JUDGE_SYSTEM = (
+    "אתה בוחן-איכות משפטי. נתונים לך (א) רשימת ההלכות (מיני-רציו) שכתב עורך נבו "
+    "עבור פסק-דין — אמת-המידה; (ב) רשימת ההלכות שמערכת אוטומטית חילצה מאותו "
+    "פסק-דין. משימתך: למפות סמנטית בין השתיים (אותו עיקרון משפטי בניסוח שונה = "
+    "התאמה), ולספור. החזר JSON בלבד, ללא טקסט נוסף."
+)
+
+
+def _judge_prompt(ratio: str, ours: list[str]) -> str:
+    ours_block = "\n".join(f"{i}. {s}" for i, s in enumerate(ours, 1)) or "(אין)"
+    return (
+        f"מיני-רציו של נבו (אמת-מידה):\n{ratio}\n\n"
+        f"ההלכות שחולצו על-ידי המערכת ({len(ours)}):\n{ours_block}\n\n"
+        "החזר JSON עם המפתחות:\n"
+        '{"nevo_holdings": <מספר העקרונות הנפרדים במיני-רציו>,\n'
+        ' "covered": <כמה מעקרונות נבו מכוסים ע"י לפחות הלכה אחת שלנו>,\n'
+        ' "ours_total": <מספר ההלכות שלנו>,\n'
+        ' "ours_mapped": <כמה מההלכות שלנו ממופות לעיקרון נבו כלשהו>,\n'
+        ' "notes": "<עד 2 משפטים: מה הוחמץ / מה עודף>"}'
+    )
+
+
+async def _bench_one(row: dict, model: str | None) -> dict:
+    cn = row["case_number"]
+    ratio = (row.get("nevo_ratio") or "").strip() or extract_nevo_ratio(row.get("full_text") or "")
+    result = {"case_number": cn, "nevo_holdings": 0, "covered": 0,
+              "ours_total": 0, "ours_mapped": 0, "recall": None,
+              "precision": None, "granularity": None, "notes": "", "error": ""}
+    if not ratio:
+        result["error"] = "no mini-ratio"
+        return result
+
+    halachot = await db.list_halachot(case_law_id=row["id"], limit=500)
+    ours = [h["rule_statement"] for h in halachot
+            if h.get("review_status") in ("approved", "published", "pending_review")
+            and (h.get("rule_statement") or "").strip()]
+    result["ours_total"] = len(ours)
+    if not ours:
+        result["error"] = "no extracted halachot"
+        return result
+
+    try:
+        verdict = await claude_session.query_json(
+            _judge_prompt(ratio, ours), system=_JUDGE_SYSTEM, model=model, effort="low",
+        )
+    except Exception as e:  # noqa: BLE001
+        result["error"] = f"judge failed: {e}"
+        return result
+    if not isinstance(verdict, dict):
+        result["error"] = "judge returned non-dict"
+        return result
+
+    nh = int(verdict.get("nevo_holdings") or 0)
+    cov = int(verdict.get("covered") or 0)
+    ot = int(verdict.get("ours_total") or len(ours))
+    om = int(verdict.get("ours_mapped") or 0)
+    result.update({
+        "nevo_holdings": nh, "covered": cov, "ours_total": ot, "ours_mapped": om,
+        "recall": round(cov / nh, 3) if nh else None,
+        "precision": round(om / ot, 3) if ot else None,
+        "granularity": round(ot / nh, 2) if nh else None,
+        "notes": str(verdict.get("notes") or "")[:300],
+    })
+    return result
+
+
+async def main(args: argparse.Namespace) -> int:
+    pool = await db.get_pool()
+    async with pool.acquire() as conn:
+        if args.case:
+            rows = await conn.fetch(
+                "SELECT id, case_number, nevo_ratio, full_text FROM case_law "
+                "WHERE case_number = $1", args.case,
+            )
+        else:
+            # rulings that have (or can derive) a ratio
+            rows = await conn.fetch(
+                "SELECT id, case_number, nevo_ratio, full_text FROM case_law "
+                "WHERE nevo_ratio <> '' OR full_text LIKE '%מיני-רציו:%' "
+                "ORDER BY case_number"
+            )
+    rows = [dict(r) for r in rows]
+    if args.limit:
+        rows = rows[: args.limit]
+    if not rows:
+        print("no rulings with a mini-ratio found", flush=True)
+        return 0
+
+    print(f"benchmarking {len(rows)} ruling(s)...", flush=True)
+    results = []
+    for i, row in enumerate(rows, 1):
+        res = await _bench_one(row, args.model)
+        results.append(res)
+        if res["error"]:
+            print(f"[{i}/{len(rows)}] {res['case_number']}: SKIP ({res['error']})", flush=True)
+        else:
+            print(f"[{i}/{len(rows)}] {res['case_number']}: "
+                  f"recall={res['recall']} precision={res['precision']} "
+                  f"granularity={res['granularity']}x "
+                  f"(nevo={res['nevo_holdings']}, ours={res['ours_total']})", flush=True)
+
+    scored = [r for r in results if r["recall"] is not None]
+    if scored:
+        avg = lambda k: round(sum(r[k] for r in scored) / len(scored), 3)  # noqa: E731
+        print(f"\n=== {len(scored)} scored — mean recall={avg('recall')} "
+              f"precision={avg('precision')} granularity={avg('granularity')}x ===", flush=True)
+
+    ts = datetime.now(timezone.utc).strftime("%Y%m%dT%H%M%SZ")
+    AUDIT_DIR.mkdir(parents=True, exist_ok=True)
+    out = Path(args.out) if args.out else AUDIT_DIR / f"nevo-ratio-benchmark-{ts}.csv"
+    with out.open("w", encoding="utf-8", newline="") as f:
+        w = csv.DictWriter(f, fieldnames=list(results[0].keys()))
+        w.writeheader()
+        w.writerows(results)
+    print(f"report: {out}", flush=True)
+    return 0
+
+
+if __name__ == "__main__":
+    ap = argparse.ArgumentParser(description=__doc__,
+                                 formatter_class=argparse.RawDescriptionHelpFormatter)
+    g = ap.add_mutually_exclusive_group(required=True)
+    g.add_argument("--case", help="benchmark a single case_number")
+    g.add_argument("--all", action="store_true", help="benchmark all rulings with a mini-ratio")
+    ap.add_argument("--limit", type=int, default=None, help="cap the number of rulings")
+    ap.add_argument("--model", default=None, help="judge model (default: CLI session default)")
+    ap.add_argument("--out", default=None, help="output CSV path (default: data/audit/)")
+    args = ap.parse_args()
+    sys.exit(asyncio.run(main(args)))