Merge pull request #38222 from BerriAI/litellm_fix_mantle_reasoning_effort_max

fix(completion_extras): forward reasoning_effort=max through the Responses API bridge

litellm/completion_extras/litellm_responses_transformation/transformation.py

@@ -5,7 +5,7 @@ Handler for transforming /chat/completions api requests to litellm.responses req
 import json
 import os
 from collections.abc import AsyncIterator, Callable, Iterable, Iterator, Mapping, Sequence
-from typing import TYPE_CHECKING, Any, Final, Literal, TypedDict, Union, cast
+from typing import TYPE_CHECKING, Any, Final, Literal, TypedDict, Union, cast, get_args
 
 from openai.types.responses.custom_tool_param import CustomToolParam
 from openai.types.responses.response_input_param import (
@@ -35,6 +35,7 @@ from litellm.responses.sse_output_recovery import (
 )
 from litellm.responses.utils import normalize_responses_api_stream_options
 from litellm.types.llms.openai import (
+    REASONING_EFFORT,
     ChatCompletionAnnotation,
     ChatCompletionReasoningItem,
     ChatCompletionToolCallChunk,
@@ -1113,22 +1114,11 @@ class LiteLLMResponsesTransformationHandler(CompletionTransformationBridge):
             litellm.reasoning_auto_summary or os.getenv("LITELLM_REASONING_AUTO_SUMMARY", "false").lower() == "true"
         )
 
-        # If string is passed, map with optional summary based on flag/env var
-        if reasoning_effort == "none":
-            return Reasoning(effort="none", summary="detailed") if auto_summary_enabled else Reasoning(effort="none")
-        elif reasoning_effort == "high":
-            return Reasoning(effort="high", summary="detailed") if auto_summary_enabled else Reasoning(effort="high")
-        elif reasoning_effort == "xhigh":
-            return Reasoning(effort="xhigh", summary="detailed") if auto_summary_enabled else Reasoning(effort="xhigh")
-        elif reasoning_effort == "medium":
+        if reasoning_effort in get_args(REASONING_EFFORT):
             return (
-                Reasoning(effort="medium", summary="detailed") if auto_summary_enabled else Reasoning(effort="medium")
-            )
-        elif reasoning_effort == "low":
-            return Reasoning(effort="low", summary="detailed") if auto_summary_enabled else Reasoning(effort="low")
-        elif reasoning_effort == "minimal":
-            return (
-                Reasoning(effort="minimal", summary="detailed") if auto_summary_enabled else Reasoning(effort="minimal")
+                Reasoning(effort=reasoning_effort, summary="detailed")
+                if auto_summary_enabled
+                else Reasoning(effort=reasoning_effort)
             )
         return None
 

litellm/types/llms/openai.py

@@ -1840,7 +1840,7 @@ ResponsesAPIStreamingResponse = Annotated[
 ]
 
 
-REASONING_EFFORT = Literal["none", "minimal", "low", "medium", "high", "xhigh"]
+REASONING_EFFORT = Literal["none", "minimal", "low", "medium", "high", "xhigh", "max"]
 
 
 class OpenAIRealtimeStreamSession(TypedDict, total=False):

tests/test_litellm/completion_extras/litellm_responses_transformation/test_completion_extras_litellm_responses_transformation_transformation.py

@@ -2,7 +2,7 @@ import datetime
 import json
 import os
 import unittest
-from typing import TYPE_CHECKING, List, Literal, Optional, Tuple
+from typing import TYPE_CHECKING, Final, List, Literal, Optional, Tuple
 from unittest.mock import ANY, MagicMock, Mock, patch
 
 import httpx
@@ -1585,10 +1585,16 @@ def test_map_reasoning_effort_adds_summary_detailed(monkeypatch):
         assert result_dict["summary"] == "custom_summary"
         print("✓ Dict input is passed through without modification")
 
-        # Test 5: None/unknown values return None
-        result_unknown = handler._map_reasoning_effort("unknown_value")
-        assert result_unknown is None
-        print("✓ Unknown reasoning_effort values return None")
+        # Test 5: every REASONING_EFFORT level reaches the provider, and anything else (a typo, an
+        # unshipped level, "default") is dropped so the request still succeeds at the provider default
+        from litellm.types.llms.openai import Reasoning
+
+        for effort in ("max", "xhigh", "none"):
+            result_passthrough = handler._map_reasoning_effort(effort)
+            assert result_passthrough == Reasoning(effort=effort)
+        for dropped in ("ultra", "hgih", "unknown_value", "", "default"):
+            assert handler._map_reasoning_effort(dropped) is None
+        print("✓ Enumerated levels pass through and unknown ones are dropped")
 
         print(
             "✓ All reasoning_effort behaviors work correctly with flag/env var control"
@@ -2438,6 +2444,32 @@ def test_map_optional_params_preserves_reasoning_summary():
     assert responses_api_request["reasoning"]["summary"] == "detailed"
 
 
+@pytest.mark.parametrize("reasoning_effort", ["max", "high"])
+def test_transform_request_bedrock_mantle_tools_keeps_reasoning_effort(monkeypatch, reasoning_effort):
+    """Regression for reasoning_effort=max being dropped on the chat -> Responses bridge (issue #38084)."""
+    from litellm.completion_extras.litellm_responses_transformation.transformation import (
+        LiteLLMResponsesTransformationHandler,
+    )
+
+    monkeypatch.setattr(litellm, "reasoning_auto_summary", False)
+    monkeypatch.delenv("LITELLM_REASONING_AUTO_SUMMARY", raising=False)
+    handler: Final = LiteLLMResponsesTransformationHandler()
+
+    result: Final = handler.transform_request(
+        model="openai.gpt-5.6-sol",
+        messages=[{"role": "user", "content": "Say pong"}],
+        optional_params={
+            "reasoning_effort": reasoning_effort,
+            "tools": [{"type": "function", "function": {"name": "get_weather", "parameters": {"type": "object"}}}],
+        },
+        litellm_params={"custom_llm_provider": "bedrock_mantle"},
+        headers={},
+        litellm_logging_obj=Mock(),
+    )
+
+    assert result["reasoning"] == {"effort": reasoning_effort}
+
+
 def test_map_optional_params_tool_choice_chat_nested_to_responses_api():
     """Chat tool_choice must become Responses ToolChoiceFunction (top-level name)."""
     from litellm.completion_extras.litellm_responses_transformation.transformation import (

tests/test_litellm/proxy/response_api_endpoints/test_endpoints.py

@@ -1353,6 +1353,8 @@ class TestParseCursorModelVariant:
             ("claude-opus-5-fast", "claude-opus-5", None),
             ("gpt-5.6-sol", "gpt-5.6-sol", None),
             ("foo-thinking-ultra-fast", "foo-thinking-ultra", None),
+            ("gpt-5.6-thinking-max", "gpt-5.6", "max"),
+            ("foo-thinking-mega-fast", "foo-thinking-mega", None),
             ("-thinking-high", "-thinking-high", None),
         ],
     )