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,
     )

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

@@ -96,10 +96,13 @@ async def precedent_library_list(
     precedent_level: str = "",
     source_type: str = "",
     search: str = "",
-    source_kind: str = "external_upload",
+    source_kind: str = "",
     limit: int = 100,
 ) -> str:
-    """רשימה של פסיקה בקורפוס הסמכותי, עם פילטרים."""
+    """רשימה של פסיקה בקורפוס הסמכותי, עם פילטרים.
+
+    source_kind ריק (ברירת מחדל) = כל הקורפוס, כולל החלטות ועדות ערר.
+    """
     rows = await precedent_library.list_precedents(
         practice_area=practice_area,
         court=court,
@@ -266,8 +269,9 @@ async def search_precedent_library(
     subject_tag: str = "",
     limit: int = 10,
     include_halachot: bool = True,
+    source_kind: str = "",
 ) -> str:
-    """חיפוש סמנטי בקורפוס הפסיקה הסמכותית.
+    """חיפוש סמנטי בקורפוס הפסיקה הסמכותית — פסקי דין **והחלטות ועדות ערר**.
 
     מחזיר תוצאות מעורבות: הלכות (rule-level, מאושרות בלבד) + קטעי טקסט
     (passage-level). הלכות מקבלות boost קל בדירוג כי הן מזוקקות מראש.
@@ -282,6 +286,9 @@ async def search_precedent_library(
         subject_tag: סינון לפי תגית נושא (לדוגמה "מועד_קביעת_שומה").
         limit: מספר תוצאות מקסימלי.
         include_halachot: האם לכלול הלכות (ברירת מחדל: כן).
+        source_kind: ריק (ברירת מחדל) = כל הקורפוס — פסקי דין והחלטות ועדות
+            ערר יחד. "external_upload" = פסקי בתי משפט בלבד;
+            "internal_committee" = החלטות ועדות ערר בלבד.
 
     Returns: רשימה מדורגת. כל פריט הוא {"type": "halacha"|"passage", "score", ...}.
     """
@@ -299,6 +306,7 @@ async def search_precedent_library(
         subject_tag=subject_tag,
         limit=limit,
         include_halachot=include_halachot,
+        source_kind=source_kind,
     )
     # X11 Phase 2 (#154): attach the incoming-citation authority breakdown so the
     # research agent can WEIGH and ARGUE authority ("הלכה שאומצה ב-N החלטות ועדת-ערר")

mcp-server/tests/test_source_kind_selector.py

@@ -0,0 +1,67 @@
+"""#232 — the source_kind selector must not silently hide a corpus.
+
+`search_precedent_library` defaulted to source_kind='external_upload' all the
+way down the stack, so 104 appeals-committee decisions (29% of the corpus)
+were unreachable through the entry point the writing agents actually call.
+These tests pin the selector semantics; the end-to-end retrieval check lives
+in scripts/test_retrieval_by_name.py (needs a live DB).
+"""
+
+import pytest
+
+from legal_mcp.services.db import _source_kind_clause
+
+
+def test_empty_selector_means_no_filter():
+    """'' and 'all' must produce no predicate — the whole corpus."""
+    assert _source_kind_clause("") == ""
+    assert _source_kind_clause("all") == ""
+    assert _source_kind_clause("  ") == ""
+
+
+def test_named_kinds_produce_equality_predicate():
+    assert _source_kind_clause("internal_committee", "cl.") == (
+        "cl.source_kind = 'internal_committee'"
+    )
+    assert _source_kind_clause("external_upload") == "source_kind = 'external_upload'"
+
+
+def test_all_committees_expands_to_both_shapes():
+    """Committee decisions live under two historical shapes — cover both."""
+    clause = _source_kind_clause("all_committees", "cl.")
+    assert "cl.source_kind = 'internal_committee'" in clause
+    assert "cl.source_type = 'appeals_committee'" in clause
+    assert clause.startswith("(") and clause.endswith(")")
+
+
+def test_unknown_selector_raises_rather_than_reaching_sql():
+    """The value is f-string-interpolated, so the whitelist is the guard."""
+    with pytest.raises(ValueError, match="source_kind"):
+        _source_kind_clause("'; DROP TABLE case_law; --")
+    with pytest.raises(ValueError):
+        _source_kind_clause("internal")
+
+
+def test_default_of_the_search_entry_points_is_whole_corpus():
+    """A regression guard on the defaults themselves — this is the bug."""
+    import inspect
+
+    from legal_mcp.services import hybrid_search, precedent_library
+    from legal_mcp.services import db as db_mod
+    from legal_mcp.tools import precedent_library as plib_tool
+
+    for fn in (
+        db_mod.search_precedent_library_semantic,
+        db_mod.search_precedent_library_lexical,
+        db_mod.list_external_case_law,
+        hybrid_search.search_precedent_library_hybrid,
+        precedent_library.search_library,
+        precedent_library.list_precedents,
+        plib_tool.search_precedent_library,
+        plib_tool.precedent_library_list,
+    ):
+        default = inspect.signature(fn).parameters["source_kind"].default
+        assert default == "", (
+            f"{fn.__module__}.{fn.__qualname__} defaults source_kind to "
+            f"{default!r} — that hides a corpus from every caller (#232)"
+        )

web/app.py

@@ -6992,7 +6992,7 @@ async def precedent_library_list(
     precedent_level: str = "",
     source_type: str = "",
     search: str = "",
-    source_kind: str = "external_upload",
+    source_kind: str = "",
     limit: int = 100,
     offset: int = 0,
 ):
@@ -7020,6 +7020,7 @@ async def precedent_library_search(
     subject_tag: str = "",
     limit: int = 10,
     include_halachot: bool = True,
+    source_kind: str = "",
 ):
     if not q or len(q.strip()) < 2:
         return {"items": [], "count": 0}
@@ -7032,6 +7033,7 @@ async def precedent_library_search(
         subject_tag=subject_tag,
         limit=limit,
         include_halachot=include_halachot,
+        source_kind=source_kind,
     )
     return {"items": results, "count": len(results)}