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

@@ -5237,6 +5237,50 @@ async def seed_goldset_from_chair(
         return False
 
 
+async def panel_rounds_vs_chair(limit: int = 2000) -> list[dict]:
+    """Read-only join for rubric distillation (#133 / FU-4).
+
+    For every halacha that has BOTH a chair-live gold-set seed (FU-2 — the
+    human keep/drop ground-truth) AND at least one captured panel round (FU-1),
+    return the LATEST round's per-judge votes+reasons+verdict next to the
+    chair's label and the halacha text. These (panel ⋈ chair) pairs are the
+    ONLY signal the distillation may learn from — human ground-truth, never the
+    panel's own votes (echo-chamber guard, INV-LRN1). Purely analytical: reads
+    capture tables, writes nothing."""
+    pool = await get_pool()
+    rows = await pool.fetch(
+        """
+        SELECT g.halacha_id::text AS halacha_id,
+               g.is_holding AS chair_keep, g.tagged_at AS chair_at,
+               h.rule_statement, h.reasoning_summary, h.supporting_quote,
+               h.rule_type, h.quality_flags,
+               pr.question, pr.verdict, pr.applied_action, pr.round_ts,
+               pr.claude_vote, pr.claude_reason,
+               pr.deepseek_vote, pr.deepseek_reason,
+               pr.gemini_vote, pr.gemini_reason
+        FROM halacha_goldset g
+        JOIN halachot h ON h.id = g.halacha_id
+        JOIN LATERAL (
+            SELECT * FROM halacha_panel_rounds r
+            WHERE r.halacha_id = g.halacha_id
+            ORDER BY r.round_ts DESC LIMIT 1
+        ) pr ON true
+        WHERE g.batch = 'chair-live' AND g.is_holding IS NOT NULL
+        ORDER BY g.tagged_at DESC NULLS LAST
+        LIMIT $1
+        """,
+        limit,
+    )
+    out = []
+    for r in rows:
+        d = dict(r)
+        for k in ("chair_at", "round_ts"):
+            if d.get(k) is not None:
+                d[k] = d[k].isoformat()
+        out.append(d)
+    return out
+
+
 async def goldset_tag(
     goldset_id: UUID, *, is_holding: bool | None = None,
     correct_type: str | None = None, quote_complete: bool | None = None,

mcp-server/tests/test_rubric_distill.py

@@ -0,0 +1,87 @@
+"""Tests for #133 / FU-4 — rubric distillation from chair decisions.
+
+Covers the PURE deterministic core (analyze_pairs): given (panel ⋈ chair) pairs
+it must correctly classify the systematic-failure buckets — false-keep (panel
+auto-kept, chair dropped), false-drop, chair-resolved splits — and the per-judge
+disagreement-with-chair rate. Fully OFFLINE (no DB, no LLM). The LLM proposal
+and the report rendering are exercised by the integration smoke run.
+
+The invariant this locks down: the only label compared against is the chair's
+human ruling — never the panel's own votes (echo-chamber guard, INV-LRN1).
+"""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+# the script lives in ../scripts relative to mcp-server/
+sys.path.insert(0, str(Path(__file__).resolve().parents[2] / "scripts"))
+import halacha_rubric_distill as rd  # noqa: E402
+
+
+def _pair(chair, verdict, action, c, ds, gm, rule="כלל כלשהו"):
+    return {
+        "chair_keep": chair, "verdict": verdict, "applied_action": action,
+        "rule_statement": rule,
+        "claude_vote": c, "claude_reason": "rc",
+        "deepseek_vote": ds, "deepseek_reason": "rd",
+        "gemini_vote": gm, "gemini_reason": "rg",
+    }
+
+
+def test_false_keep_detected():
+    """Panel auto-approved but the chair dropped → a false-keep (the costly error)."""
+    a = rd.analyze_pairs([_pair(False, "unanimous_yes", "approved", True, True, True)])
+    assert a["n_false_keep"] == 1
+    assert a["n_false_drop"] == 0
+
+
+def test_nli_cleared_counts_as_keep():
+    a = rd.analyze_pairs([_pair(False, "unanimous_yes", "nli_cleared", True, True, True)])
+    assert a["n_false_keep"] == 1
+
+
+def test_false_drop_detected():
+    a = rd.analyze_pairs([_pair(True, "unanimous_no", "rejected", False, False, False)])
+    assert a["n_false_drop"] == 1
+    assert a["n_false_keep"] == 0
+
+
+def test_split_resolved_counted_not_a_false_decision():
+    """A split escalates to the chair — no auto-decision, so it is neither a
+    false-keep nor a false-drop, but it IS a resolved split (learning signal)."""
+    a = rd.analyze_pairs([_pair(True, "split", "chair", True, False, None)])
+    assert a["n_splits_resolved"] == 1
+    assert a["n_false_keep"] == 0 and a["n_false_drop"] == 0
+
+
+def test_judge_disagreement_rate_vs_chair():
+    """Disagreement is measured against the chair, never against the other judges."""
+    pairs = [
+        _pair(True, "split", "chair", True, False, None),   # claude agree, deepseek disagree
+        _pair(True, "split", "chair", True, False, True),   # claude agree, deepseek disagree, gemini agree
+    ]
+    a = rd.analyze_pairs(pairs)
+    assert a["judge_stats"]["claude"]["disagree_rate"] == 0.0
+    assert a["judge_stats"]["deepseek"]["disagree_rate"] == 1.0
+    # gemini voted once (agree) and abstained once → rate 0.0 over 1 vote
+    assert a["judge_stats"]["gemini"]["voted"] == 1
+    assert a["judge_stats"]["gemini"]["disagree_rate"] == 0.0
+
+
+def test_none_chair_label_ignored():
+    a = rd.analyze_pairs([_pair(None, "split", "chair", True, False, None)])
+    assert a["n_pairs"] == 1  # counted in total …
+    assert a["judge_stats"]["claude"]["voted"] == 0  # … but contributes no signal
+
+
+def test_evidence_capped():
+    pairs = [_pair(False, "unanimous_yes", "approved", True, True, True) for _ in range(40)]
+    a = rd.analyze_pairs(pairs)
+    assert a["n_false_keep"] == 40
+    assert len(a["evidence"]) == rd.MAX_EVIDENCE
+
+
+def test_min_pairs_threshold_is_sane():
+    assert rd.MIN_PAIRS >= 1

scripts/SCRIPTS.md

@@ -63,6 +63,7 @@
 | `curator_apply_pipeline_branch.py` | python | **מקור-אמת לחיווט-הכפתורים של הרמס.** prompt-ה-curator חי רק ב-Paperclip DB (`agents.adapter_config.promptTemplate`). הסקריפט מקדים branch כך שיקיצה עם reason `final_learning_*`/`final_halacha_*` מריצה את ה-pipeline המתאים (HOME/DOTENV/DATA_DIR מוחלטים → DeepSeek+Gemini keys + DATA_DIR נפתרים נכון) ועוצרת, אחרת §A/§B כרגיל. idempotent (מסיר branch קודם). מחיל על שני הסוכנים (CMP+CMPA). `--verify`. **להריץ אחרי reset/יצירה-מחדש של סוכן-curator.** | אחרי reset prompt של curator |
 | `halacha_panel_audit.py` | python | **רשת-ביטחון לפאנל** (selective-prediction monitoring) — דוגם הלכות שאושרו ע"י הפאנל (`reviewer LIKE 'panel:%'`), מריץ עליהן **שוב** את הצבעת-ה-KEEP של 3 השופטים, ומציף כל מקרה שכעת נוטה DROP (false-keep פוטנציאלי). report-only כברירת-מחדל; `--flag` מחזיר את ה-flips ל-`pending_review` לסקירת-יו"ר. `--sample N`/`--seed`. בסיס 2026-06-07: 0/15. מיועד להרצה תקופתית (שבועי). מייבא שופטים מ-`halacha_panel_approve`. **חובה מקומי**. | תקופתי (שבועי) — ניטור |
 | `halacha_panel_calibrate.py` | python | **כיול מדיניות-ההצבעה של הפאנל** (Trust-or-Escalate, ICLR 2025). מריץ את שאלת-ה-KEEP של `halacha_panel_approve` על מדגם-הזהב ומודד מול `is_holding` (הציר-הגס) precision+coverage לכל מדיניות (unanimous/majority) + ספירת false-keep/false-drop. נותן את **אחוז-הטעות בפועל** לבחירת סף-סיכון α. מייבא שופטים מ-`halacha_panel_approve` (מקור-אמת יחיד). read-only, **חובה מקומי**. | ידני — לפני חיווט `--apply` |
+| `halacha_rubric_distill.py` | python | **#133/FU-4 — זיקוק-רובריקה PROPOSE-ONLY.** מצליב `halacha_panel_rounds` (FU-1, הצבעות+נימוקים) מול הכרעות-היו"ר (FU-2, seeds ב-`halacha_goldset` batch `chair-live`) דרך `db.panel_rounds_vs_chair` (read-only), מנתח דטרמיניסטית **כשלים שיטתיים** (false-keep/false-drop, פיצולים-שהוכרעו, שיעור-מחלוקת-עם-היו"ר לכל שופט), ומציע `KEEP_SYSTEM` v2 + exemplars מופשטים (claude_session מקומי, אפס עלות) כ**דוח-diff** ל-`data/learning/rubric-proposal-<ts>.md`. **לעולם לא auto-apply** — אימוץ v2 = עריכה אנושית של הקבוע דרך PR (INV-LRN1); exemplars מופשטים בלבד (INV-LRN5); הסיגנל היחיד = הכרעת-יו"ר, לא הצבעות-פאנל (anti-echo). מתחת ל-12 זוגות → "אין מספיק נתונים". `--no-llm` (סטטיסטיקה בלבד) / `--limit N`. **חובה מקומי**. | תקופתי — אחרי שהצטברו הכרעות-יו"ר על מחלוקות-פאנל |
 | `halacha_rule_role_backfill.py` | python | **INV-DM7** — backfill חד-פעמי: מסווג-מחדש את ההלכות הישנות (`rule_type IN ('binding','persuasive')` — ערכי-סמכות שנשמרו במסווה תפקיד לפני פיצול הצירים) לאחד מחמשת **תפקידי-הכלל** (holding/interpretive/procedural/application/obiter) דרך claude_session המקומי (אפס עלות). **לא נוגע בסמכות** (נגזרת מ-`precedent_level`). `--apply` (ברירת-מחדל dry-run) / `--limit N` / `--concurrency`. כותב backup CSV ל-`data/audit/` תחילה. fail-safe (פריט שנכשל → נשמר ערך ישן). **חובה מקומי** (claude_session). | ידני חד-פעמי אחרי deploy של פיצול-הסמכות |
 | `halacha_batch_reconcile.py` | python | **#82.7** — dedup חוצה-פסקים offline (שמרני, **dry-run בלבד**). dedup-on-insert משווה רק תוך-פסק; כאן סף מחמיר (cosine ≥0.95, `--cosine`) ולא-הרסני: מאתר זוגות הלכות near-duplicate בין פסקים שונים (pgvector `<=>` exact) עם איתות לקסיקלי (Jaccard/Levenshtein) ומדווח ל-CSV ב-`data/audit/` לסקירת היו"ר. לא מדלג/ממזג/מוחק. `--include-pending`. **`--link`** רושם את הזוגות שנמצאו כ-`equivalent_halachot` (parallel authority, #84.2 — קישור-מקביל ברמת-הלכה, **לא** ציטוט; idempotent, לא-הרסני). רץ עם venv של mcp-server. אומת: 800 הלכות → 5 זוגות (קושרו). | ידני — דוח-סקירה / `--link` לקישור |
 | `calibrate_halacha_dedup.py` | python | **#82.1** — כיול ספי ה-dedup הלקסיקלי (#82.3) מול gold-set הניקוי. קורא `halacha-cleanup-manifest-*.csv` (זוגות duplicate↔survivor מתויגי-אדם), טוען טקסט-survivor מה-DB, ו-sweep של (jaccard_min × levenshtein_min) עם P/R/F1, מסמן את נקודת-העבודה המוגדרת. אימת ש-(0.55, 0.70) → **precision 1.0** (אפס false-merge), recall 0.30 — מתאים לאיתות-משני שחוסם auto-approve. `--manifest <path>`. רץ עם venv של mcp-server | חד-פעמי — כיול (בוצע 2026-06-06) |

scripts/halacha_rubric_distill.py

@@ -0,0 +1,227 @@
+#!/usr/bin/env python3
+"""Distil a better panel rubric from the chair's decisions — PROPOSE-ONLY (#133/FU-4).
+
+The 3-judge KEEP panel (halacha_panel_approve.py) escalates every split to the
+chair. FU-1 captured each round's votes+reasons; FU-2 captured the chair's
+keep/drop ruling as a gold seed. This job joins the two — (panel ⋈ chair) — and
+mines SYSTEMATIC failures: a judge that disagrees with the chair on an axis, a
+recurring split the chair resolves the same way (e.g. obiter↔interpretive). It
+then proposes a refined ``KEEP_SYSTEM`` v2 + abstract few-shot exemplars, written
+as a DIFF report for the chair to review.
+
+CRITICAL — this is the ACTIVE-LEARNING signal, not an echo chamber:
+  - The only ground-truth is the chair's human ruling (db.panel_rounds_vs_chair
+    reads the chair-live gold seeds, never the panel's own votes).
+  - The proposal is NEVER auto-applied (INV-LRN1). KEEP_SYSTEM lives in code;
+    adopting v2 is a human edit through a normal PR. This script writes a report
+    to data/learning/ and touches nothing else.
+  - Exemplars stay ABSTRACT patterns, never copied case holdings (INV-LRN5).
+
+    cd ~/legal-ai/mcp-server
+    .venv/bin/python ../scripts/halacha_rubric_distill.py            # propose
+    .venv/bin/python ../scripts/halacha_rubric_distill.py --no-llm   # stats only
+"""
+from __future__ import annotations
+
+import argparse
+import asyncio
+import difflib
+import json
+from datetime import datetime, timezone
+from pathlib import Path
+
+from legal_mcp.services import claude_session, db
+# single source of truth for the rubric under refinement
+from halacha_panel_approve import KEEP_SYSTEM  # noqa: E402
+
+# Below this many chair-resolved pairs the patterns are noise — report and stop.
+MIN_PAIRS = 12
+# Cap evidence shipped to the model / report (keep the prompt + report tight).
+MAX_EVIDENCE = 24
+
+_JUDGES = ("claude", "deepseek", "gemini")
+
+
+def analyze_pairs(pairs: list[dict]) -> dict:
+    """Pure, deterministic mining of the (panel ⋈ chair) pairs — no DB, no LLM.
+
+    Each pair carries the chair's keep/drop (``chair_keep``), the panel verdict
+    + applied action, and each judge's vote+reason. Returns the systematic-
+    failure metrics and a capped bundle of disagreement evidence for the model.
+    """
+    n = len(pairs)
+    judge_stats = {j: {"voted": 0, "agree": 0, "disagree": 0} for j in _JUDGES}
+    false_keep: list[dict] = []   # panel auto-KEPT, chair DROPPED
+    false_drop: list[dict] = []   # panel auto-DROPPED, chair KEPT
+    splits_resolved: list[dict] = []
+    for p in pairs:
+        chair = p.get("chair_keep")
+        if chair is None:
+            continue
+        for j in _JUDGES:
+            v = p.get(f"{j}_vote")
+            if v is None:
+                continue
+            judge_stats[j]["voted"] += 1
+            judge_stats[j]["agree" if bool(v) == bool(chair) else "disagree"] += 1
+        action = (p.get("applied_action") or "").strip()
+        verdict = (p.get("verdict") or "").strip()
+        ev = {
+            "rule_statement": p.get("rule_statement") or "",
+            "verdict": verdict,
+            "applied_action": action,
+            "chair_keep": bool(chair),
+            "reasons": {j: p.get(f"{j}_reason") or "" for j in _JUDGES},
+            "votes": {j: p.get(f"{j}_vote") for j in _JUDGES},
+        }
+        # Panel acted automatically (kept) but the chair disagreed → dangerous.
+        if action in ("approved", "nli_cleared") and chair is False:
+            false_keep.append(ev)
+        elif action == "rejected" and chair is True:
+            false_drop.append(ev)
+        if verdict in ("split", "incomplete"):
+            splits_resolved.append(ev)
+
+    for j in _JUDGES:
+        s = judge_stats[j]
+        s["disagree_rate"] = round(s["disagree"] / s["voted"], 3) if s["voted"] else None
+
+    # Evidence the model needs to see: every false auto-decision (highest value)
+    # then chair-resolved splits, capped.
+    evidence = (false_keep + false_drop + splits_resolved)[:MAX_EVIDENCE]
+    return {
+        "n_pairs": n,
+        "judge_stats": judge_stats,
+        "n_false_keep": len(false_keep),
+        "n_false_drop": len(false_drop),
+        "n_splits_resolved": len(splits_resolved),
+        "evidence": evidence,
+    }
+
+
+def _proposal_prompt(analysis: dict) -> str:
+    """Build the model prompt: current rubric + failure evidence → v2 proposal."""
+    ev_lines = []
+    for i, e in enumerate(analysis["evidence"], 1):
+        votes = ", ".join(f"{j}={e['votes'][j]}" for j in _JUDGES)
+        reasons = " | ".join(f"{j}: {e['reasons'][j]}" for j in _JUDGES if e["reasons"][j])
+        ev_lines.append(
+            f"{i}. הכרעת-יו\"ר: {'שמירה' if e['chair_keep'] else 'דחייה'} | "
+            f"ורדיקט-פאנל: {e['verdict']} ({e['applied_action'] or 'הוסלם'}) | "
+            f"הצבעות: {votes}\n   כלל: {e['rule_statement'][:200]}\n   נימוקי-שופטים: {reasons}"
+        )
+    evidence_block = "\n".join(ev_lines) or "(אין מספיק ראיות-מחלוקת)"
+    return (
+        "להלן רובריקת-ההכרעה הנוכחית של פאנל-שופטים שמסווג 'הלכות' שחולצו מפסיקה "
+        "כראויות-לשמירה (keep) או לא. מצורפים מקרים שבהם השופטים נחלקו או טעו ביחס "
+        "להכרעת-היו\"ר (האמת היחידה). זהה את **דפוסי-הכשל השיטתיים** והצע שיפור מינימלי "
+        "לרובריקה.\n\n"
+        f"## הרובריקה הנוכחית (KEEP_SYSTEM)\n{KEEP_SYSTEM}\n\n"
+        f"## סטטיסטיקת-כשל\n"
+        f"זוגות: {analysis['n_pairs']} | false-keep: {analysis['n_false_keep']} | "
+        f"false-drop: {analysis['n_false_drop']} | פיצולים-שהוכרעו: {analysis['n_splits_resolved']}\n"
+        f"שיעור-מחלוקת-עם-היו\"ר לכל שופט: "
+        + ", ".join(f"{j}={analysis['judge_stats'][j]['disagree_rate']}" for j in _JUDGES)
+        + f"\n\n## ראיות-מחלוקת\n{evidence_block}\n\n"
+        "החזר JSON בלבד (ללא markdown) בסכמה:\n"
+        '{"patterns": ["<דפוס-כשל שיטתי 1>", ...], '
+        '"keep_system_v2": "<נוסח מלא מוצע לרובריקה — מופשט, בר-הכללה, בלי מהות-תיק>", '
+        '"exemplars": [{"pattern":"<תבנית מופשטת>","label":"keep|drop","why":"<קצר>"}]}\n'
+        "אזהרה: ה-exemplars והנוסח חייבים להיות **מופשטים** — אסור להעתיק ניסוח-כלל "
+        "ספציפי או מהות-תיק (INV-LRN5). אם הראיות לא מספיקות לדפוס ברור — החזר "
+        '{"patterns": [], "keep_system_v2": "", "exemplars": []}.'
+    )
+
+
+def _render_report(analysis: dict, proposal: dict | None, ts: str) -> str:
+    js = analysis["judge_stats"]
+    lines = [
+        f"# הצעת-זיקוק לרובריקת-הפאנל (FU-4) — {ts}",
+        "",
+        "> **PROPOSE-ONLY (INV-LRN1).** המסמך הזה הוא הצעה לעיון-היו\"ר בלבד. "
+        "`KEEP_SYSTEM` חי בקוד (`scripts/halacha_panel_approve.py`); אימוץ v2 = "
+        "עריכה אנושית דרך PR רגיל. אף שורת-קוד לא שונתה אוטומטית.",
+        "> הסיגנל היחיד = הכרעת-היו\"ר על מחלוקות-הפאנל (לא הצבעות-הפאנל — echo-chamber).",
+        "",
+        "## סטטיסטיקת-כשל",
+        "",
+        "| מדד | ערך |",
+        "|---|---|",
+        f"| זוגות (panel ⋈ chair) | {analysis['n_pairs']} |",
+        f"| false-keep (פאנל שמר, יו\"ר דחה) | {analysis['n_false_keep']} |",
+        f"| false-drop (פאנל דחה, יו\"ר שמר) | {analysis['n_false_drop']} |",
+        f"| פיצולים שהוכרעו ע\"י היו\"ר | {analysis['n_splits_resolved']} |",
+        "",
+        "### שיעור-מחלוקת-עם-היו\"ר לכל שופט",
+        "",
+        "| judge | voted | disagree | rate |",
+        "|---|---|---|---|",
+    ]
+    for j in _JUDGES:
+        lines.append(f"| {j} | {js[j]['voted']} | {js[j]['disagree']} | {js[j]['disagree_rate']} |")
+    lines.append("")
+
+    if not proposal or not proposal.get("keep_system_v2"):
+        lines += ["## הצעה", "", "_אין דפוס-כשל מובהק / אין מספיק ראיות — לא הוצעה רובריקה חדשה._", ""]
+        return "\n".join(lines)
+
+    patterns = proposal.get("patterns") or []
+    lines += ["## דפוסי-כשל שזוהו", ""]
+    lines += [f"- {p}" for p in patterns] or ["- (—)"]
+    lines += ["", "## diff מוצע ל-KEEP_SYSTEM", "", "```diff"]
+    diff = difflib.unified_diff(
+        KEEP_SYSTEM.replace(". ", ".\n").splitlines(),
+        proposal["keep_system_v2"].replace(". ", ".\n").splitlines(),
+        fromfile="KEEP_SYSTEM (current)", tofile="KEEP_SYSTEM (proposed v2)", lineterm="",
+    )
+    lines += list(diff)
+    lines += ["```", "", "## few-shot exemplars מוצעים (מופשטים — INV-LRN5)", ""]
+    for ex in proposal.get("exemplars") or []:
+        lines.append(f"- **{ex.get('label','')}** — {ex.get('pattern','')} _( {ex.get('why','')} )_")
+    lines += ["", "---", "_להחלת ההצעה: ערוך ידנית את `KEEP_SYSTEM` ופתח PR. אין auto-apply (INV-LRN1)._"]
+    return "\n".join(lines)
+
+
+async def main(args: argparse.Namespace) -> int:
+    pairs = await db.panel_rounds_vs_chair(limit=args.limit or 2000)
+    analysis = analyze_pairs(pairs)
+    print(f"pairs={analysis['n_pairs']} false_keep={analysis['n_false_keep']} "
+          f"false_drop={analysis['n_false_drop']} splits={analysis['n_splits_resolved']}",
+          flush=True)
+
+    if analysis["n_pairs"] < MIN_PAIRS:
+        print(f"insufficient data (<{MIN_PAIRS} chair-resolved pairs) — no proposal. "
+              "Seeds accrue as the chair reviews panel-judged halachot (FU-2).", flush=True)
+        proposal = None
+    elif args.no_llm:
+        proposal = None
+        print("--no-llm: stats only, no rubric proposal.", flush=True)
+    else:
+        try:
+            proposal = await claude_session.query_json(
+                _proposal_prompt(analysis), system=None, tools="",
+            )
+        except Exception as e:
+            print(f"LLM proposal failed ({e}); writing stats-only report.", flush=True)
+            proposal = None
+        if proposal and not isinstance(proposal, dict):
+            proposal = None
+
+    ts = datetime.now(timezone.utc).strftime("%Y%m%dT%H%M%SZ")
+    out_dir = Path(__file__).resolve().parents[1] / "data" / "learning"
+    out_dir.mkdir(parents=True, exist_ok=True)
+    report = _render_report(analysis, proposal, ts)
+    out_path = out_dir / f"rubric-proposal-{ts}.md"
+    out_path.write_text(report, encoding="utf-8")
+    print(f"wrote {out_path}", flush=True)
+    if proposal and proposal.get("keep_system_v2"):
+        print("→ rubric v2 PROPOSED — review the diff and apply via PR if sound (INV-LRN1).",
+              flush=True)
+    return 0
+
+
+if __name__ == "__main__":
+    ap = argparse.ArgumentParser(description="Propose a panel-rubric refinement from chair decisions (FU-4).")
+    ap.add_argument("--limit", type=int, default=0, help="max (panel ⋈ chair) pairs to mine")
+    ap.add_argument("--no-llm", action="store_true", help="deterministic stats only, skip the rubric proposal")
+    raise SystemExit(asyncio.run(main(ap.parse_args())))