Merge pull request 'feat(learning): מטא-דאטה מלא להחלטות-פנימיות בקליטה + חילוץ-הלכות אוטומטי' (#165) from worktree-internal-decision-metadata into main

scripts/final_halacha_pipeline.py

@@ -6,6 +6,8 @@ runs THIS single deterministic command (the 3-judge panel uses local DeepSeek+Ge
 keys + the local claude CLI, so it can't run inside the container).
 
 Steps:
+  [0] precedent_extract_halachot → extract the halachot the DECISION ITSELF states
+      (its own case_law row), so they aren't left pending. Idempotent.
   [1] extract_internal_citations(chair) → links the citation graph for the chair's
       decisions (idempotent; ON CONFLICT DO NOTHING).
   [2] corroboration_rebuild → builds the citation-treatment signal and applies the
@@ -35,6 +37,19 @@ sys.path.insert(0, str(Path(__file__).resolve().parent))
 
 from legal_mcp.services import corroboration, db  # noqa: E402
 from legal_mcp.tools.citations import extract_internal_citations  # noqa: E402
+from legal_mcp.tools.precedent_library import precedent_extract_halachot  # noqa: E402
+
+
+async def _decision_law_row(case_number: str) -> dict | None:
+    """The case's own decision row in case_law (internal_committee), if enrolled."""
+    pool = await db.get_pool()
+    async with pool.acquire() as conn:
+        r = await conn.fetchrow(
+            "SELECT id, halacha_extraction_status FROM case_law WHERE case_number = $1 "
+            "AND source_kind = 'internal_committee' ORDER BY created_at DESC LIMIT 1",
+            case_number,
+        )
+    return dict(r) if r else None
 
 
 async def main(args: argparse.Namespace) -> int:
@@ -45,8 +60,26 @@ async def main(args: argparse.Namespace) -> int:
         return 1
     chair = case.get("chair_name") or "דפנה תמיר"
 
+    # [0] extract the halachot the decision ITSELF states (its own row in case_law) —
+    # so they are not left pending. Idempotent: skip when already completed or on dry-run.
+    row = await _decision_law_row(case_number)
+    if not row:
+        print(f"[0/4] ההחלטה {case_number} אינה ב-case_law עדיין — דילוג על חילוץ-הלכות")
+    elif row.get("halacha_extraction_status") == "completed":
+        print(f"[0/4] חילוץ-הלכות מההחלטה — דולג (כבר completed)")
+    elif args.dry_run:
+        print(f"[0/4] חילוץ-הלכות מההחלטה — מדולג (dry-run)")
+    else:
+        print(f"[0/4] precedent_extract_halachot (החלטה {case_number})…", flush=True)
+        try:
+            raw0 = await precedent_extract_halachot(str(row["id"]))
+            d0 = json.loads(raw0).get("data", {})
+            print(f"  ✓ status={d0.get('status')} stored={d0.get('stored', d0.get('extracted'))}")
+        except Exception as e:
+            print(f"  ⚠ halacha extraction failed (non-fatal): {e}")
+
     # [1] citation graph
-    print(f"[1/3] extract_internal_citations (chair={chair})…", flush=True)
+    print(f"[1/4] extract_internal_citations (chair={chair})…", flush=True)
     raw = await extract_internal_citations(chair_name=chair, limit=0)
     try:
         d = json.loads(raw).get("data", {})
@@ -57,9 +90,9 @@ async def main(args: argparse.Namespace) -> int:
 
     # [2] corroboration signal + policy (whole corpus backfill) — skipped on dry-run
     if args.dry_run:
-        print("[2/3] corroboration_rebuild — מדולג (dry-run)")
+        print("[2/4] corroboration_rebuild — מדולג (dry-run)")
     else:
-        print("[2/3] corroboration_rebuild (backfill)…", flush=True)
+        print("[2/4] corroboration_rebuild (backfill)…", flush=True)
         try:
             cr = await corroboration.build_all()
             print(f"  ✓ {cr}")
@@ -68,7 +101,7 @@ async def main(args: argparse.Namespace) -> int:
 
     # [3] three-judge halacha panel
     apply = not args.dry_run
-    print(f"[3/3] halacha_panel_approve {'--apply' if apply else '(dry-run)'} "
+    print(f"[3/4] halacha_panel_approve {'--apply' if apply else '(dry-run)'} "
           f"(Opus+DeepSeek+Gemini)…", flush=True)
     import halacha_panel_approve as hpa
     rc = await hpa.main(Namespace(limit=args.limit, concurrency=6, apply=apply))

web/app.py

@@ -3387,6 +3387,33 @@ def _committee_chair_for_case(case: dict, case_number: str) -> str:
     return COMMITTEE_CHAIR_BY_PREFIX.get(case_number[:1], COMMITTEE_CHAIR_DEFAULT)
 
 
+def _party_name(parties) -> str:
+    """First party's display name from a list of {name|party_name} dicts or strings."""
+    if isinstance(parties, list) and parties:
+        p = parties[0]
+        if isinstance(p, dict):
+            return (p.get("name") or p.get("party_name") or "").strip()
+        return str(p).strip()
+    return ""
+
+
+def _build_internal_citation(
+    case: dict, case_number: str, chair_name: str, proceeding_type: str, district: str,
+) -> str:
+    """Deterministic uniform citation for OUR committee decisions — the Gemini metadata
+    extractor targets external rulings and returns nothing for internal ones, so we build
+    it from the case record instead. E.g.:
+    'ועדת ערר מחוזית לתכנון ובניה ירושלים, בל"מ 8126-03-25 פלוני נ' הוועדה המקומית (יו"ר עו"ד דפנה תמיר)'."""
+    appellant = _party_name(case.get("appellants"))
+    respondent = _party_name(case.get("respondents"))
+    parties = f" {appellant} נ' {respondent}" if (appellant and respondent) else (
+        f" {appellant}" if appellant else "")
+    proc = proceeding_type or "ערר"
+    chair_clause = f' (יו"ר עו"ד {chair_name})' if chair_name else ""
+    return (f"ועדת ערר מחוזית לתכנון ובניה {district}, {proc} {case_number}"
+            f"{parties}{chair_clause}").strip()
+
+
 async def _enroll_final_in_library(
     case: dict, case_number: str, final_text: str, chair_name: str,
 ) -> dict:
@@ -3404,12 +3431,23 @@ async def _enroll_final_in_library(
     if not final_text.strip():
         out["error"] = "no final text extracted"
         return out
+
+    # Deterministic metadata from the case record — the Gemini metadata extractor is
+    # tuned for EXTERNAL rulings and returns no_metadata for internal decisions, so we
+    # populate proceeding_type / date / tags / summary / citation ourselves (no LLM).
+    district = "ירושלים"
+    proceeding_type = (case.get("proceeding_type") or "ערר").strip()
+    decision_date = case.get("decision_date") or case.get("hearing_date")
+    subject_tags = case.get("subject_categories") or []
+    summary = (case.get("subject") or case.get("title") or "").strip()
     try:
         res = await int_svc.ingest_internal_decision(
             case_number=case_number, case_name=case.get("title", ""),
-            decision_date=case.get("decision_date"), chair_name=chair_name,
-            district="ירושלים", practice_area=case.get("practice_area", ""),
-            appeal_subtype=case.get("appeal_subtype", ""), text=final_text,
+            decision_date=decision_date, chair_name=chair_name,
+            district=district, practice_area=case.get("practice_area", ""),
+            appeal_subtype=case.get("appeal_subtype", ""),
+            proceeding_type=proceeding_type, subject_tags=subject_tags,
+            summary=summary, text=final_text,
         )
     except Exception as e:
         logger.warning("library enrollment failed for %s: %s", case_number, e)
@@ -3421,6 +3459,21 @@ async def _enroll_final_in_library(
     if not case_law_id:
         return out
 
+    # Build the uniform citation deterministically (Gemini won't, for internal rows).
+    try:
+        citation = _build_internal_citation(
+            case, case_number, chair_name, proceeding_type, district)
+        pool = await db.get_pool()
+        async with pool.acquire() as conn:
+            await conn.execute(
+                "UPDATE case_law SET citation_formatted = $2 "
+                "WHERE id = $1 AND COALESCE(citation_formatted, '') = ''",
+                UUID(case_law_id), citation,
+            )
+        out["citation"] = citation
+    except Exception as e:
+        logger.warning("citation build failed for %s: %s", case_number, e)
+
     # The precedents this decision cites → link to the library; flag the ones not found.
     try:
         await cit_tools.extract_internal_citations(case_law_id=case_law_id, limit=0)