fix(moonshot): drop temperature for reasoning models (kimi-k2.5/k2.6) (#29687)

Kimi reasoning models reject every temperature except 1; a request with
temperature=0.2 returns "invalid temperature: only 1 is allowed for this model".
litellm only clamped temperature into [0.3, 1], so any value below 1 still 400'd.

Drop the temperature param entirely for reasoning models (gated on
supports_reasoning, the same signal transform_request already uses) so the model
default is used; the non-reasoning moonshot-v1 models keep the existing clamp.

Co-authored-by: Sameer Kankute <sameer@berri.ai>

litellm/llms/moonshot/chat/transformation.py

@@ -134,11 +134,15 @@ class MoonshotChatConfig(OpenAIGPTConfig):
 
         ##########################################
         # temperature limitations
-        # 1. `temperature` on KIMI API is [0, 1] but OpenAI is [0, 2]
-        # 2. If temperature < 0.3 and n > 1, KIMI will raise an exception.
+        # 1. reasoning models (kimi-k2.5, kimi-k2.6, ...) reject every temperature
+        #    except 1, so the param is dropped and the model's default is used
+        # 2. `temperature` on KIMI API is [0, 1] but OpenAI is [0, 2]
+        # 3. If temperature < 0.3 and n > 1, KIMI will raise an exception.
         #       If we enter this condition, we set the temperature to 0.3 as suggested by Moonshot AI
         ##########################################
-        if "temperature" in optional_params:
+        if supports_reasoning(model=model, custom_llm_provider="moonshot"):
+            optional_params.pop("temperature", None)
+        elif "temperature" in optional_params:
             if optional_params["temperature"] > 1:
                 optional_params["temperature"] = 1
             if optional_params["temperature"] < 0.3 and optional_params.get("n", 1) > 1:

tests/test_litellm/llms/moonshot/test_moonshot_chat_transformation.py

@@ -205,6 +205,42 @@ class TestMoonshotConfig:
             # Temperature should be preserved
             assert result.get("temperature") == temp
 
+    def test_temperature_dropped_for_reasoning_models(self):
+        """Reasoning models (kimi-k2.5, kimi-k2.6) reject any temperature except 1,
+        so the param is dropped rather than clamped. A clamp to 0.3/1 would still
+        400 when the caller passes e.g. 0.5."""
+        config = MoonshotChatConfig()
+
+        with patch(
+            "litellm.llms.moonshot.chat.transformation.supports_reasoning",
+            return_value=True,
+        ):
+            for temp in [0.0, 0.5, 1.0, 1.5]:
+                result = config.map_openai_params(
+                    non_default_params={"temperature": temp},
+                    optional_params={},
+                    model="kimi-k2.5",
+                    drop_params=False,
+                )
+                assert "temperature" not in result
+
+    def test_temperature_clamped_for_non_reasoning_models(self):
+        """Non-reasoning models keep the [0.3, 1] clamp behaviour."""
+        config = MoonshotChatConfig()
+
+        with patch(
+            "litellm.llms.moonshot.chat.transformation.supports_reasoning",
+            return_value=False,
+        ):
+            result = config.map_openai_params(
+                non_default_params={"temperature": 1.5},
+                optional_params={},
+                model="moonshot-v1-8k",
+                drop_params=False,
+            )
+
+        assert result.get("temperature") == 1
+
     def test_tool_choice_required_adds_message(self):
         """Test that tool_choice='required' adds a special message and removes tool_choice"""
         config = MoonshotChatConfig()