fix(vector): address PR review round 12 — bool guard + strict doc_id validation

- _group_int_doc_ids: use type(value) is not int instead of isinstance,
  since bool is an int subclass and would otherwise stringify to
  "True"/"False" and corrupt legacy payloads on backfill.
- Replace doc_id.isdigit() guards in 5 boundary sites
  (api/visualization, auth/viz_routes, search/context note/news_item/
  deck_card branches) with a shared is_valid_nextcloud_doc_id helper
  that rejects "0", leading zeros, and Unicode digit classes
  (superscripts, Arabic-Indic, Devanagari) which pass isdigit() but
  cannot be valid MySQL AUTO_INCREMENT IDs.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

tests/unit/utils/test_validation.py

@@ -0,0 +1,54 @@
+"""Unit tests for shared boundary validators."""
+
+import pytest
+
+from nextcloud_mcp_server.utils.validation import is_valid_nextcloud_doc_id
+
+
+@pytest.mark.unit
+@pytest.mark.parametrize(
+    "value",
+    [
+        "1",
+        "42",
+        "1234567890",
+        "9999999999999999999",
+    ],
+)
+def test_accepts_positive_ascii_integers(value):
+    """Any positive ASCII integer (no leading zero) is a valid doc_id."""
+    assert is_valid_nextcloud_doc_id(value) is True
+
+
+@pytest.mark.unit
+@pytest.mark.parametrize(
+    "value,reason",
+    [
+        ("", "empty string"),
+        ("0", "MySQL AUTO_INCREMENT starts at 1"),
+        ("01", "leading zero"),
+        ("00", "leading zeros"),
+        ("-1", "negative"),
+        ("+1", "explicit sign"),
+        ("1.0", "float-like"),
+        (" 1", "leading whitespace"),
+        ("1 ", "trailing whitespace"),
+        ("1\n", "trailing newline"),
+        ("abc", "alphabetic"),
+        ("1a", "trailing letter"),
+        ("a1", "leading letter"),
+        # Unicode digit classes that pass str.isdigit() but are not ASCII.
+        # `²` (U+00B2) is a superscript and would slip past the old guard.
+        ("²", "Unicode superscript-2"),
+        # `٢` (U+0662) Arabic-Indic digit two — passes both isdigit() and
+        # isdecimal(), so only an explicit ASCII regex catches it.
+        ("٢", "Arabic-Indic digit two"),
+        # `१` (U+0967) Devanagari digit one — same story.
+        ("१", "Devanagari digit one"),
+        # Mixed ASCII + Unicode digits.
+        ("1٢", "mixed ASCII + Arabic-Indic"),
+    ],
+)
+def test_rejects_invalid_doc_ids(value, reason):
+    """Reject empty/zero/leading-zero/non-ASCII/non-digit inputs."""
+    assert is_valid_nextcloud_doc_id(value) is False, f"should reject: {reason}"

tests/unit/vector/test_qdrant_client.py

@@ -678,6 +678,36 @@ def test_group_int_doc_ids_skips_float_and_warns(caplog):
     assert "99" in msg
 
 
+@pytest.mark.unit
+def test_group_int_doc_ids_skips_bool_and_warns(caplog):
+    """A bool doc_id is not stringified to "True"/"False"; it logs and skips.
+
+    ``isinstance(True, int)`` is ``True`` because ``bool`` is a subclass of
+    ``int`` in Python, so a naive ``isinstance(value, int)`` guard would let
+    a boolean payload through and write ``str(True)`` → ``"True"`` into
+    Qdrant. Producers never write bools, but the strict ``type(value) is
+    int`` guard ensures any future producer bug surfaces as a WARNING and is
+    not silently stringified.
+    """
+    bool_point = SimpleNamespace(id=33, payload={"doc_id": True})
+    int_point = SimpleNamespace(id=42, payload={"doc_id": 7})
+
+    with caplog.at_level("WARNING", logger="nextcloud_mcp_server.vector.qdrant_client"):
+        by_value, scanned = _group_int_doc_ids([bool_point, int_point])
+
+    # Only the int point made it into by_value — "True" is *not* a key.
+    assert by_value == {"7": [42]}
+    assert "True" not in by_value
+    assert "False" not in by_value
+    assert scanned == 2
+
+    warnings = [r for r in caplog.records if r.levelname == "WARNING"]
+    assert len(warnings) == 1
+    msg = warnings[0].getMessage()
+    assert "bool" in msg
+    assert "33" in msg
+
+
 @pytest.mark.unit
 def test_group_int_doc_ids_handles_str_and_missing_silently(caplog):
     """str / missing doc_id payloads are skipped without warning.