fix(azure/search): reject bool and non-positive max_results for bing_grounding count

Extract a shared _valid_max_results predicate that rejects bools (an int
subclass) and non-positive values, and reuse it from both the connection-mode
request count and the response-side cap so both paths honor the same contract.

litellm/llms/azure/search/transformation.py

@@ -178,6 +178,16 @@ def _citation_results(envelope: _ResponsesEnvelope) -> tuple[SearchResult, ...]:
     return tuple(first_by_url[url] for url in dict.fromkeys(result.url for result in cited))
 
 
+def _valid_max_results(max_results: object) -> int | None:
+    """A positive-int `max_results`, else None. Rejects bools, an `int` subclass, and
+    non-positive values so neither the request-side `count` nor the response-side cap
+    forwards a value the other would silently ignore.
+    """
+    if isinstance(max_results, bool) or not isinstance(max_results, int):
+        return None
+    return max_results if max_results > 0 else None
+
+
 def _requested_max_results(response_kwargs: Mapping[str, object]) -> int | None:
     """The unified `max_results` cap the caller asked for, if any.
 
@@ -188,10 +198,7 @@ def _requested_max_results(response_kwargs: Mapping[str, object]) -> int | None:
     optional_params: Final = response_kwargs.get("optional_params")
     if not isinstance(optional_params, Mapping):
         return None
-    max_results: Final = optional_params.get("max_results")
-    return (
-        max_results if isinstance(max_results, int) and not isinstance(max_results, bool) and max_results > 0 else None
-    )
+    return _valid_max_results(optional_params.get("max_results"))
 
 
 def _capped(results: tuple[SearchResult, ...], max_results: int | None) -> tuple[SearchResult, ...]:
@@ -247,7 +254,7 @@ def _search_tool(optional_params: Mapping[str, object]) -> _BingGroundingTool |
     if connection_id:
         configuration: Final = _SearchConfiguration(
             project_connection_id=connection_id,
-            count=max_results if isinstance(max_results, int) else None,
+            count=_valid_max_results(max_results),
         )
         return _BingGroundingTool(bing_grounding=_BingGroundingParams(search_configurations=(configuration,)))
     location: Final = _UserLocation(country=country.upper()) if isinstance(country, str) else None

tests/test_litellm/llms/azure/search/test_bing_grounding_search_transformation.py

@@ -195,6 +195,24 @@ def test_transform_search_request_connection_mode_omits_count_without_max_result
     assert body["tools"][0]["bing_grounding"]["search_configurations"] == [{"project_connection_id": "conn-id"}]
 
 
+@pytest.mark.parametrize("max_results", [True, False, 0, -1])
+def test_transform_search_request_connection_mode_omits_count_for_invalid_max_results(
+    monkeypatch: pytest.MonkeyPatch, max_results: object
+):
+    monkeypatch.setenv("BING_GROUNDING_MODEL", "gpt-4.1")
+    monkeypatch.setenv("BING_GROUNDING_CONNECTION_ID", "conn-id")
+    body = _config().transform_search_request("q", {"max_results": max_results})
+    assert body["tools"][0]["bing_grounding"]["search_configurations"] == [{"project_connection_id": "conn-id"}]
+
+
+def test_transform_search_response_ignores_invalid_max_results_cap():
+    annotations = [_citation(f"https://example.com/{i}", f"T{i}", 0, 5) for i in range(3)]
+    resp = _config().transform_search_response(
+        _resp(_message_response("claim", annotations)), logging_obj=Mock(), optional_params={"max_results": True}
+    )
+    assert [r.url for r in resp.results] == [f"https://example.com/{i}" for i in range(3)]
+
+
 def test_transform_search_request_joins_list_query(monkeypatch: pytest.MonkeyPatch):
     monkeypatch.setenv("BING_GROUNDING_MODEL", "gpt-4.1")
     assert _config().transform_search_request(["foo", "bar"], {})["input"] == "foo bar"