fix: Allow LLM request to override the model used in the generate content async method in LiteLLM

Merge https://github.com/google/adk-python/pull/3066

Close #3065

Co-authored-by: Raman Mangla <ramanmangla@google.com>
PiperOrigin-RevId: 825880794

tests/unittests/models/test_litellm.py

@@ -549,6 +549,53 @@ async def test_generate_content_async(mock_acompletion, lite_llm_instance):
   )
 
 
+@pytest.mark.asyncio
+async def test_generate_content_async_with_model_override(
+    mock_acompletion, lite_llm_instance
+):
+  llm_request = LlmRequest(
+      model="overridden_model",
+      contents=[
+          types.Content(
+              role="user", parts=[types.Part.from_text(text="Test prompt")]
+          )
+      ],
+  )
+
+  async for response in lite_llm_instance.generate_content_async(llm_request):
+    assert response.content.role == "model"
+    assert response.content.parts[0].text == "Test response"
+
+  mock_acompletion.assert_called_once()
+
+  _, kwargs = mock_acompletion.call_args
+  assert kwargs["model"] == "overridden_model"
+  assert kwargs["messages"][0]["role"] == "user"
+  assert kwargs["messages"][0]["content"] == "Test prompt"
+
+
+@pytest.mark.asyncio
+async def test_generate_content_async_without_model_override(
+    mock_acompletion, lite_llm_instance
+):
+  llm_request = LlmRequest(
+      model=None,
+      contents=[
+          types.Content(
+              role="user", parts=[types.Part.from_text(text="Test prompt")]
+          )
+      ],
+  )
+
+  async for response in lite_llm_instance.generate_content_async(llm_request):
+    assert response.content.role == "model"
+
+  mock_acompletion.assert_called_once()
+
+  _, kwargs = mock_acompletion.call_args
+  assert kwargs["model"] == "test_model"
+
+
 @pytest.mark.asyncio
 async def test_generate_content_async_adds_fallback_user_message(
     mock_acompletion, lite_llm_instance