Merge pull request #15465 from kowyo/kowyo/fix-ollama-think

fix(ollama/chat): correctly map reasoning_effort to think in requests

litellm/llms/ollama/chat/transformation.py

@@ -184,9 +184,12 @@ class OllamaChatConfig(BaseConfig):
             ):
                 if value.get("json_schema") and value["json_schema"].get("schema"):
                     optional_params["format"] = value["json_schema"]["schema"]
-            ### FUNCTION CALLING LOGIC ###
             if param == "reasoning_effort" and value is not None:
-                optional_params["think"] = True
+                if model.startswith("gpt-oss"):
+                    optional_params["think"] = value
+                else:
+                    optional_params["think"] = True
+            ### FUNCTION CALLING LOGIC ###
             if param == "tools":
                 ## CHECK IF MODEL SUPPORTS TOOL CALLING ##
                 try:
@@ -281,6 +284,7 @@ class OllamaChatConfig(BaseConfig):
         stream = optional_params.pop("stream", False)
         format = optional_params.pop("format", None)
         keep_alive = optional_params.pop("keep_alive", None)
+        think = optional_params.pop("think", None)
         function_name = optional_params.pop("function_name", None)
         litellm_params["function_name"] = function_name
         tools = optional_params.pop("tools", None)
@@ -344,6 +348,8 @@ class OllamaChatConfig(BaseConfig):
             data["tools"] = tools
         if keep_alive is not None:
             data["keep_alive"] = keep_alive
+        if think is not None:
+            data["think"] = think
 
         return data
 

litellm/llms/ollama/completion/transformation.py

@@ -180,7 +180,10 @@ class OllamaConfig(BaseConfig):
             elif param == "stop":
                 optional_params["stop"] = value
             elif param == "reasoning_effort" and value is not None:
-                optional_params["think"] = True
+                if model.startswith("gpt-oss"):
+                    optional_params["think"] = value
+                else:
+                    optional_params["think"] = True
             elif param == "response_format" and isinstance(value, dict):
                 if value["type"] == "json_object":
                     optional_params["format"] = "json"
@@ -412,6 +415,7 @@ class OllamaConfig(BaseConfig):
         stream = optional_params.pop("stream", False)
         format = optional_params.pop("format", None)
         images = optional_params.pop("images", None)
+        think = optional_params.pop("think", None)
         data = {
             "model": model,
             "prompt": ollama_prompt,
@@ -425,6 +429,8 @@ class OllamaConfig(BaseConfig):
             data["images"] = [
                 _convert_image(convert_to_ollama_image(image)) for image in images
             ]
+        if think is not None:
+            data["think"] = think
 
         return data
 

litellm/llms/ollama_chat.py

@@ -59,6 +59,7 @@ def get_ollama_response(  # noqa: PLR0915
     stream = optional_params.pop("stream", False)
     format = optional_params.pop("format", None)
     keep_alive = optional_params.pop("keep_alive", None)
+    think = optional_params.pop("think", None)
     function_name = optional_params.pop("function_name", None)
     tools = optional_params.pop("tools", None)
 
@@ -98,6 +99,8 @@ def get_ollama_response(  # noqa: PLR0915
         data["tools"] = tools
     if keep_alive is not None:
         data["keep_alive"] = keep_alive
+    if think is not None:
+        data["think"] = think
     ## LOGGING
     logging_obj.pre_call(
         input=None,