From 358d82e90e6421a699f88621ffc2b6c6d66e7724 Mon Sep 17 00:00:00 2001
From: Chaim <chaim@marcus-law.co.il>
Date: Sat, 30 May 2026 20:57:27 +0000
Subject: [PATCH] feat(retrieval): require practice_area only for
 internal/cases; enable searchable filter + health visibility (GAP-13, FU-2a)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 mcp-server/src/legal_mcp/services/db.py      | 14 ++++++++++----
 mcp-server/src/legal_mcp/services/metrics.py |  4 ++++
 mcp-server/tests/test_idempotent_ingest.py   |  9 +++++++++
 3 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/mcp-server/src/legal_mcp/services/db.py b/mcp-server/src/legal_mcp/services/db.py
index d2cfedc..632746e 100644
--- a/mcp-server/src/legal_mcp/services/db.py
+++ b/mcp-server/src/legal_mcp/services/db.py
@@ -2735,8 +2735,12 @@ def _compute_searchable(row: dict, has_embedded_chunk: bool) -> bool:
         return False
     if not (row.get("case_name") or "").strip():
         return False
-    if not (row.get("practice_area") or "").strip():
-        return False
+    # practice_area is required only for identifier-keyed corpora (internal
+    # committee decisions, active cases). External precedents (e.g. בג"ץ) are
+    # legitimately cross-domain and may have no single practice_area.
+    if (row.get("source_kind") or "") != "external_upload":
+        if not (row.get("practice_area") or "").strip():
+            return False
     if not (row.get("source_kind") or "").strip():
         return False
     tags = row.get("subject_tags") or []
@@ -3272,8 +3276,9 @@ async def search_precedent_library_semantic(
     halacha_filters = [
         "h.review_status IN ('approved', 'published')",
         f"cl.source_kind = '{source_kind}'",
+        "cl.searchable = true",
     ]
-    chunk_filters = [f"cl.source_kind = '{source_kind}'"]
+    chunk_filters = [f"cl.source_kind = '{source_kind}'", "cl.searchable = true"]
     h_params: list = [query_embedding, limit]
     c_params: list = [query_embedding, limit]
     h_idx = 3
@@ -3508,8 +3513,9 @@ async def search_precedent_library_lexical(
     halacha_filters = [
         "h.review_status IN ('approved', 'published')",
         f"cl.source_kind = '{source_kind}'",
+        "cl.searchable = true",
     ]
-    chunk_filters = [f"cl.source_kind = '{source_kind}'"]
+    chunk_filters = [f"cl.source_kind = '{source_kind}'", "cl.searchable = true"]
     # $1 = query, $2 = limit. Filters append starting at $3.
     h_params: list = [query, limit]
     c_params: list = [query, limit]
diff --git a/mcp-server/src/legal_mcp/services/metrics.py b/mcp-server/src/legal_mcp/services/metrics.py
index ce43dda..c32b4f5 100644
--- a/mcp-server/src/legal_mcp/services/metrics.py
+++ b/mcp-server/src/legal_mcp/services/metrics.py
@@ -123,6 +123,9 @@ async def get_dashboard() -> dict:
         total_corpus = await conn.fetchval("SELECT COUNT(*) FROM style_corpus")
         total_patterns = await conn.fetchval("SELECT COUNT(*) FROM style_patterns")
         total_case_law = await conn.fetchval("SELECT COUNT(*) FROM case_law")
+        non_searchable_case_law = await conn.fetchval(
+            "SELECT COUNT(*) FROM case_law WHERE NOT searchable"
+        )
 
         # QA summary
         qa_total = await conn.fetchval("SELECT COUNT(DISTINCT case_id) FROM qa_results")
@@ -154,6 +157,7 @@ async def get_dashboard() -> dict:
             "style_corpus": total_corpus,
             "style_patterns": total_patterns,
             "case_law_entries": total_case_law,
+            "non_searchable_case_law": non_searchable_case_law,
         },
         "cases_by_status": cases_by_status,
         "qa": {
diff --git a/mcp-server/tests/test_idempotent_ingest.py b/mcp-server/tests/test_idempotent_ingest.py
index 04b5f08..a78b754 100644
--- a/mcp-server/tests/test_idempotent_ingest.py
+++ b/mcp-server/tests/test_idempotent_ingest.py
@@ -70,6 +70,15 @@ def test_compute_searchable_false_without_core_fields():
     assert db._compute_searchable(row, has_embedded_chunk=True) is False
 
 
+def test_compute_searchable_external_allows_empty_practice_area():
+    # External precedents (e.g. בג"ץ) are cross-domain — empty practice_area
+    # must NOT disqualify them, as long as the rest of the contract holds.
+    row = _complete_row()
+    row["source_kind"] = "external_upload"
+    row["practice_area"] = ""
+    assert db._compute_searchable(row, has_embedded_chunk=True) is True
+
+
 # ── ingest wires in recompute_searchable (both types) ──────────────────
 def test_ingest_calls_recompute_searchable(monkeypatch, tmp_path):
     calls = {"recompute": [], "meta": [], "hal": []}