Fix reasoningSummary for gpt-5 series as well

litellm/main.py

@@ -991,17 +991,29 @@ def responses_api_bridge_check(
             mode = "responses"
             model_info["mode"] = mode
 
-    # OpenAI/Azure gpt-5.4+ chat-completions calls that need Responses-only fields
-    # (e.g. reasoning summary) must be bridged. SDKs send ``reasoningSummary`` /
-    # ``reasoning_summary`` alongside ``reasoning_effort``; Chat Completions rejects
-    # those keys, so route when tools+reasoning_effort (original case) or when a
-    # reasoning summary is requested without tools.
+    # OpenAI/Azure GPT-5 chat-completions that need Responses-only fields (e.g.
+    # ``reasoningSummary`` in ``extra_body``) must be bridged; Chat Completions rejects
+    # those keys.
+    #
+    # - gpt-5.4+: tools + reasoning_effort (original) or any reasoning-summary alias.
+    # - Older GPT-5 names (e.g. ``gpt-5``, ``gpt-5.1``): bridge only when a reasoning
+    #   summary alias is present with ``reasoning_effort`` (tools alone stay on chat).
     if (
         custom_llm_provider in ("openai", "azure")
-        and OpenAIGPT5Config.is_model_gpt_5_4_plus_model(model)
-        and reasoning_effort is not None
-        and (tools or reasoning_summary is not None)
         and model_info.get("mode") != "responses"
+        and OpenAIGPT5Config.is_model_gpt_5_model(model)
+        and not OpenAIGPT5Config.is_model_gpt_5_search_model(model)
+        and reasoning_effort is not None
+        and (
+            (
+                OpenAIGPT5Config.is_model_gpt_5_4_plus_model(model)
+                and (tools or reasoning_summary is not None)
+            )
+            or (
+                not OpenAIGPT5Config.is_model_gpt_5_4_plus_model(model)
+                and reasoning_summary is not None
+            )
+        )
     ):
         model_info["mode"] = "responses"
         model = model.replace("responses/", "")

tests/test_litellm/test_main.py

@@ -775,6 +775,42 @@ def test_responses_api_bridge_check_gpt_5_4_reasoning_summary_without_tools_rout
     assert model_info.get("mode") == "responses"
 
 
+def test_responses_api_bridge_check_gpt_5_reasoning_summary_routes_to_responses():
+    """Bare ``gpt-5`` with reasoning_effort + reasoningSummary should bridge (not 5.4+)."""
+    from litellm.main import responses_api_bridge_check
+
+    with patch("litellm.main._get_model_info_helper") as mock_get_model_info:
+        mock_get_model_info.return_value = {"max_tokens": 128000}
+        model_info, model = responses_api_bridge_check(
+            model="gpt-5",
+            custom_llm_provider="openai",
+            tools=None,
+            reasoning_effort="medium",
+            reasoning_summary="auto",
+        )
+
+    assert model == "gpt-5"
+    assert model_info.get("mode") == "responses"
+
+
+def test_responses_api_bridge_check_gpt_5_tools_without_summary_stays_chat():
+    """gpt-5 with tools + reasoning_effort but no summary should stay on chat."""
+    from litellm.main import responses_api_bridge_check
+
+    with patch("litellm.main._get_model_info_helper") as mock_get_model_info:
+        mock_get_model_info.return_value = {"max_tokens": 128000}
+        model_info, model = responses_api_bridge_check(
+            model="gpt-5",
+            custom_llm_provider="openai",
+            tools=[{"type": "function", "function": {"name": "get_capital"}}],
+            reasoning_effort="medium",
+            reasoning_summary=None,
+        )
+
+    assert model == "gpt-5"
+    assert model_info.get("mode") != "responses"
+
+
 @patch("litellm.completion_extras.responses_api_bridge.completion")
 def test_gpt_5_4_responses_bridge_preserves_reasoning_summary_dict(
     mock_responses_completion,
@@ -839,6 +875,42 @@ def test_gpt_5_4_responses_bridge_merges_reasoning_summary_kwarg_without_tools(
     assert "reasoning_summary" not in optional_params
 
 
+@patch("litellm.completion_extras.responses_api_bridge.completion")
+def test_gpt_5_responses_bridge_tools_and_reasoning_summary(
+    mock_responses_completion,
+):
+    """Bare gpt-5 with tools + reasoningSummary should bridge (OpenCode-style)."""
+    mock_responses_completion.return_value = MagicMock()
+
+    import litellm
+
+    litellm.completion(
+        model="gpt-5",
+        messages=[{"role": "user", "content": "ok"}],
+        tools=[
+            {
+                "type": "function",
+                "function": {
+                    "name": "apply_patch",
+                    "parameters": {"type": "object", "properties": {}},
+                },
+            }
+        ],
+        tool_choice="auto",
+        reasoning_effort="medium",
+        reasoningSummary="auto",
+        stream=True,
+        api_key="fake-key",
+    )
+
+    assert mock_responses_completion.called is True
+    optional_params = mock_responses_completion.call_args.kwargs["optional_params"]
+    assert optional_params.get("reasoning_effort") == {
+        "effort": "medium",
+        "summary": "auto",
+    }
+
+
 def test_responses_api_bridge_check_handles_exception():
     """Test that responses_api_bridge_check handles exceptions and still processes responses/ models."""
     from litellm.main import responses_api_bridge_check