Merge pull request 'fix(precedents): נרמול case_number עמיד-להתנגשות — מדלג ומתעד, לא קורס (#145)' (#266) from worktree-backfill-citations-run into main

scripts/backfill_precedent_citations.py

@@ -67,7 +67,7 @@ async def main() -> None:
     rows = await _empty_citation_rows(args.limit)
     print(f"רשומות עם citation_formatted ריק: {len(rows)}\n")
 
-    n_pass1 = n_pass2 = n_abstain = 0
+    n_pass1 = n_pass2 = n_abstain = n_errors = 0
     for r in rows:
         cid = r["id"]
         # Pass 1 — deterministic from the stored row (no LLM).
@@ -92,7 +92,13 @@ async def main() -> None:
             print(f"  ? [llm?] {r['case_number']} — would run extractor (dry-run)")
             continue
 
-        res = await precedent_metadata_extractor.extract_and_apply(cid)
+        # One bad row must never abort the batch — log and move on.
+        try:
+            res = await precedent_metadata_extractor.extract_and_apply(cid)
+        except Exception as e:  # noqa: BLE001 — best-effort backfill, reported per-row
+            n_errors += 1
+            print(f"  ✗ [error] {r['case_number']}: {type(e).__name__}: {e}")
+            continue
         record2 = await db.get_case_law(cid)
         new_cit = (record2.get("citation_formatted") or "").strip()
         if new_cit:
@@ -109,7 +115,7 @@ async def main() -> None:
 
     print(
         f"\nסיכום: דטרמיניסטי={n_pass1} · LLM={n_pass2} · "
-        f"נמנע (חסר רכיב)={n_abstain}"
+        f"נמנע (חסר רכיב)={n_abstain} · שגיאות={n_errors}"
         + ("" if args.apply else "   (dry-run — לא נכתב)")
     )