fix(o_series_transformation.py): fix optional param check for o-serie… (#8787)

* fix(o_series_transformation.py): fix optional param check for o-series models

o3-mini and o-1 do not support parallel tool calling

* fix(utils.py): support 'drop_params' for 'thinking' param across models

allows switching to older claude versions (or non-anthropic models) and param to be safely dropped

* fix: fix passing thinking param in optional params

allows dropping thinking_param where not applicable

* test: update old model

* fix(utils.py): fix linting errors

* fix(main.py): add param to acompletion

tests/llm_translation/test_openai.py

@@ -338,3 +338,18 @@ def test_openai_max_retries_0(mock_get_openai_client):
 
     mock_get_openai_client.assert_called_once()
     assert mock_get_openai_client.call_args.kwargs["max_retries"] == 0
+
+
+@pytest.mark.parametrize("model", ["o1", "o1-preview", "o1-mini", "o3-mini"])
+def test_o1_parallel_tool_calls(model):
+    litellm.completion(
+        model=model,
+        messages=[
+            {
+                "role": "user",
+                "content": "foo",
+            }
+        ],
+        parallel_tool_calls=True,
+        drop_params=True,
+    )