fix(retrieval): 104 החלטות ועדות-ערר היו בלתי-נראות בחיפוש — סינון ולא דירוג (#232)

`search_precedent_library` — הכלי שסוכני הכתיבה קוראים לו בפועל — לא חשף
`source_kind` כלל, וכל שכבה מתחתיו נפלה לברירת-מחדל `external_upload`.
התוצאה: `WHERE cl.source_kind = 'external_upload'` חתך 104 החלטות ועדות-ערר
(29% מהקורפוס) עוד לפני הדירוג. ערר (חיפה) 83/16 — האסמכתה הישירה ביותר
בקורפוס לטענת-סף ס-2 ב-1069-04-26 — לא הוחזרה גם בשאילתה כמעט-מילולית.

ההיפותזה שנרשמה ב-#232 (הטיית verified/cite_count מדירה החלטות חדשות)
**נבדקה ונפסלה**: כיסוי ה-verified כמעט זהה בשני הקורפוסים (55% מול 49%),
ותקרת-ההטיה 0.22 לא הסבירה פער מול התאמה כמעט-מילולית. הסיבה הייתה סינום
קשיח, לא דירוג.

מה שונה
- `_source_kind_clause()` — הגדרה אחת לאוצר-המילים של הסלקטור (G2), במקום
  שכפולו בכל אתר חיפוש/רשימה. `""`/`"all"` = כל הקורפוס; סלקטור לא-מוכר
  מרים ValueError במקום להגיע ל-SQL (הערך מוזרק ב-f-string, אז ה-whitelist
  הוא גם מה ששומר על זה בטוח).
- ברירת-המחדל בכל שרשרת-החיפוש והרשימה: `""` = הקורפוס כולו.
- `search_precedent_library` + `precedent_library_list` חושפים `source_kind`
  לסינון מפורש; `/api/precedent-library/search` מקבל אותו גם הוא כדי ש-UI
  ו-MCP לא יתפצלו.
- נרמול מפריד במספר-תיק: `83/16` ו-`83-16` מחזירים את אותה שורה.

אימות מול ה-DB החי — 4/4 החלטות ועדה חוזרות במקום **1** בשאילתה בלשון
הלכה מאושרת (83-16, 1029-18, 1085-23, 1094-09-19 פדילה). 83/16 עלתה
ל-0.711 מול 0.663 של 3213/97 שחסמה אותה קודם. רשימת-הקורפוס: 259 → 386.

invariants: G1 (נרמול במקור, לא תיקון-תסמין בקריאה) · G2 (הגדרה אחת
לסלקטור; UI ו-MCP על אותו מסלול) · §6 (סלקטור שגוי מתפוצץ, לא נבלע)

טסטים: 5 חדשים (tests/test_source_kind_selector.py), אחד מהם נועל את
ברירות-המחדל של 8 נקודות-הכניסה — זה בדיוק הבאג. 514 עוברים.

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

@@ -5324,21 +5324,19 @@ async def list_external_case_law(
     search: str = "",
     limit: int = 100,
     offset: int = 0,
-    source_kind: str = "external_upload",
+    source_kind: str = "",
 ) -> list[dict]:
     """List chair-uploaded precedents, with simple filters.
 
+    source_kind="" (default) = the whole corpus — court rulings *and*
+    appeals-committee decisions. The old ``external_upload`` default hid
+    every committee decision from a plain listing (#232).
     source_kind="all_committees" expands to: source_kind='internal_committee'
     OR (source_kind='external_upload' AND source_type='appeals_committee').
     """
     pool = await get_pool()
-    if source_kind == "all_committees":
-        conditions = [
-            "(source_kind = 'internal_committee' OR "
-            "(source_kind = 'external_upload' AND source_type = 'appeals_committee'))"
-        ]
-    else:
-        conditions = [f"source_kind = '{source_kind}'"]
+    sk_clause = _source_kind_clause(source_kind)
+    conditions = [sk_clause] if sk_clause else []
     params: list = []
     idx = 1
     if practice_area:
@@ -5358,13 +5356,19 @@ async def list_external_case_law(
         params.append(source_type)
         idx += 1
     if search:
+        # Case-number separator normalisation (#232, trap 2): committee numbers
+        # are stored hyphenated ("83-16") while people write them with a slash
+        # ("83/16"). Fold both sides to '/' so either form finds the row —
+        # matching at the point of comparison rather than asking every caller
+        # to guess the stored form.
         conditions.append(
             f"(case_number ILIKE ${idx} OR case_name ILIKE ${idx} "
-            f"OR summary ILIKE ${idx} OR headnote ILIKE ${idx})"
+            f"OR summary ILIKE ${idx} OR headnote ILIKE ${idx} "
+            f"OR replace(case_number, '-', '/') ILIKE replace(${idx}, '-', '/'))"
         )
         params.append(f"%{search}%")
         idx += 1
-    where_sql = " AND ".join(conditions)
+    where_sql = " AND ".join(conditions) if conditions else "TRUE"
     params.extend([limit, offset])
     sql = f"""
         SELECT id, case_number, case_name, court, date, practice_area,
@@ -7775,6 +7779,45 @@ async def list_corroboration_for_halacha(halacha_id: UUID) -> list[dict]:
     ]
 
 
+#: Accepted ``source_kind`` selectors. ``""``/``"all"`` mean *no filter* —
+#: the whole corpus, court rulings and appeals-committee decisions alike.
+_SOURCE_KIND_SELECTORS = frozenset(
+    {"", "all", "all_committees", "external_upload", "internal_committee", "cited_only"}
+)
+
+
+def _source_kind_clause(source_kind: str, column_prefix: str = "") -> str:
+    """Return the SQL predicate for a ``source_kind`` selector, or "" for none.
+
+    Single definition for every caller (G2) — the selector vocabulary was
+    previously restated at each search/list site, which is how the
+    ``external_upload`` default silently hid 104 appeals-committee
+    decisions from ``search_precedent_library`` (#232).
+
+    ``column_prefix`` is the table alias plus dot (e.g. ``"cl."``) or "" when
+    the query selects from ``case_law`` directly.
+
+    Raises ValueError on an unknown selector rather than interpolating it —
+    the value reaches SQL by f-string, so the whitelist is also what keeps
+    that safe.
+    """
+    sk = (source_kind or "").strip()
+    if sk not in _SOURCE_KIND_SELECTORS:
+        raise ValueError(
+            f"source_kind לא מוכר: {source_kind!r}. "
+            f"ערכים חוקיים: {sorted(_SOURCE_KIND_SELECTORS - {''})} או '' (הכל)"
+        )
+    if sk in ("", "all"):
+        return ""
+    p = column_prefix
+    if sk == "all_committees":
+        return (
+            f"({p}source_kind = 'internal_committee' OR "
+            f"({p}source_kind = 'external_upload' AND {p}source_type = 'appeals_committee'))"
+        )
+    return f"{p}source_kind = '{sk}'"
+
+
 async def search_precedent_library_semantic(
     query_embedding: list[float],
     practice_area: str = "",
@@ -7785,14 +7828,15 @@ async def search_precedent_library_semantic(
     subject_tag: str = "",
     limit: int = 10,
     include_halachot: bool = True,
-    source_kind: str = "external_upload",
+    source_kind: str = "",
     district: str = "",
     chair_name: str = "",
 ) -> list[dict]:
-    """Semantic search over precedents filtered by source_kind.
+    """Semantic search over precedents, optionally filtered by source_kind.
 
-    source_kind='external_upload'  → court rulings (default)
-    source_kind='internal_committee' → appeals-committee decisions
+    source_kind=''                   → the whole corpus (default, #232)
+    source_kind='external_upload'    → court rulings only
+    source_kind='internal_committee' → appeals-committee decisions only
 
     Returns merged halachot + chunks. Halachot are pre-distilled rules, so
     they get a small score boost. Only ``approved`` / ``published`` halachot
@@ -7800,12 +7844,15 @@ async def search_precedent_library_semantic(
     of halacha review status.
     """
     pool = await get_pool()
+    sk_clause = _source_kind_clause(source_kind, "cl.")
     halacha_filters = [
         "h.review_status <> 'rejected'",  # #153: include background; rank verified higher
-        f"cl.source_kind = '{source_kind}'",
         "cl.searchable = true",
     ]
-    chunk_filters = [f"cl.source_kind = '{source_kind}'", "cl.searchable = true"]
+    chunk_filters = ["cl.searchable = true"]
+    if sk_clause:
+        halacha_filters.append(sk_clause)
+        chunk_filters.append(sk_clause)
     h_params: list = [query_embedding, limit]
     c_params: list = [query_embedding, limit]
     h_idx = 3
@@ -8017,7 +8064,7 @@ async def search_precedent_library_lexical(
     appeal_subtype: str = "",
     is_binding: bool | None = None,
     subject_tag: str = "",
-    source_kind: str = "external_upload",
+    source_kind: str = "",
     district: str = "",
     chair_name: str = "",
     limit: int = 30,
@@ -8043,12 +8090,15 @@ async def search_precedent_library_lexical(
         return []
 
     pool = await get_pool()
+    sk_clause = _source_kind_clause(source_kind, "cl.")
     halacha_filters = [
         "h.review_status <> 'rejected'",  # #153: include background; rank verified higher
-        f"cl.source_kind = '{source_kind}'",
         "cl.searchable = true",
     ]
-    chunk_filters = [f"cl.source_kind = '{source_kind}'", "cl.searchable = true"]
+    chunk_filters = ["cl.searchable = true"]
+    if sk_clause:
+        halacha_filters.append(sk_clause)
+        chunk_filters.append(sk_clause)
     # $1 = query, $2 = limit. Filters append starting at $3.
     h_params: list = [query, limit]
     c_params: list = [query, limit]

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

@@ -98,15 +98,16 @@ async def search_precedent_library_hybrid(
     is_binding: bool | None = None,
     subject_tag: str = "",
     include_halachot: bool = True,
-    source_kind: str = "external_upload",
+    source_kind: str = "",
     district: str = "",
     chair_name: str = "",
     max_per_case_law: int = 2,
 ) -> list[dict]:
     """Hybrid wrapper for precedent-library search.
 
-    source_kind='external_upload'    → court rulings (default)
-    source_kind='internal_committee' → appeals-committee decisions
+    source_kind=''                   → the whole corpus (default, #232)
+    source_kind='external_upload'    → court rulings only
+    source_kind='internal_committee' → appeals-committee decisions only
     max_per_case_law: MMR-style diversity cap — at most N hits per
         case_law_id in the final ranked list (default 2). Prevents a
         single precedent from monopolizing the result list when many of

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

@@ -477,7 +477,7 @@ async def list_precedents(
     precedent_level: str = "",
     source_type: str = "",
     search: str = "",
-    source_kind: str = "external_upload",
+    source_kind: str = "",
     limit: int = 100,
     offset: int = 0,
 ) -> list[dict]:
@@ -503,12 +503,18 @@ async def search_library(
     subject_tag: str = "",
     limit: int = 10,
     include_halachot: bool = True,
+    source_kind: str = "",
 ) -> list[dict]:
     """Semantic search merging halachot (rule-level) and chunks (passage-level).
 
     Only ``approved`` / ``published`` halachot are returned, per chair-review
     policy. Chunks are returned regardless of halacha review status.
 
+    ``source_kind=""`` (default) covers the whole corpus — court rulings and
+    appeals-committee decisions together. It used to be hard-wired to
+    ``external_upload`` here, which made 104 committee decisions
+    unreachable through this entry point (#232).
+
     When ``VOYAGE_RERANK_ENABLED`` is set, results are passed through
     voyage rerank-2 (cross-encoder). The +0.05 halacha boost from
     ``search_precedent_library_semantic`` is preserved before rerank
@@ -529,4 +535,5 @@ async def search_library(
         is_binding=is_binding,
         subject_tag=subject_tag,
         include_halachot=include_halachot,
+        source_kind=source_kind,
     )