fix(retrieval): scope search_decisions by domain — derive from case, block only on undeterminable case (GAP-12, INV-RET1)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

mcp-server/src/legal_mcp/tools/search.py

@@ -7,7 +7,7 @@ import logging
 import time
 from uuid import UUID
 
-from legal_mcp.services import db, embeddings, hybrid_search, telemetry
+from legal_mcp.services import db, embeddings, hybrid_search, practice_area as pa, telemetry
 
 logger = logging.getLogger(__name__)
 
@@ -30,7 +30,9 @@ async def search_decisions(
         appeal_subtype: סוג ערר לסינון (building_permit/betterment_levy/compensation_197)
         case_number: אם סופק, ה-practice_area/subtype יוסקו אוטומטית מהתיק
     """
-    # Auto-resolve practice_area from case_number if available
+    # Auto-resolve practice_area from case_number if available (GAP-12 / INV-RET1):
+    # explicit practice_area wins; otherwise derive from the case so the search is
+    # scoped to the case's legal domain. Case-less search stays cross-domain.
     resolved_case_id: UUID | None = None
     if case_number and not practice_area:
         case = await db.get_case_by_number(case_number)
@@ -42,6 +44,22 @@ async def search_decisions(
             except (KeyError, ValueError, TypeError):
                 resolved_case_id = None
 
+            # Case row had no practice_area — fall back to deriving from the
+            # case-number prefix (1xxx/8xxx/9xxx). Returns "" for unknown prefixes.
+            if not practice_area:
+                practice_area = pa.derive_domain_practice_area(case_number)
+
+            # Still undeterminable: a case is present but we cannot scope the
+            # search to its domain. This is a data anomaly — BLOCK rather than
+            # silently running a cross-domain search for a specific case.
+            if not practice_area:
+                return (
+                    f"שגיאה: לא ניתן לקבוע את התחום המשפטי (practice_area) של תיק "
+                    f"{case_number}. לתיק אין practice_area מוגדר ולא ניתן להסיק אותו "
+                    f"ממספר התיק. זוהי אנומליית נתונים — נא להגדיר את ה-practice_area "
+                    f"של התיק (למשל דרך case_update) לפני הרצת חיפוש מסונן לתיק זה."
+                )
+
     if not practice_area:
         logger.warning(
             "search_decisions called without practice_area filter — "