FIX: MultiModalMessage in gemini with openai sdk error occured (#6440)

## Why are these changes needed?

Multimodal message fill context with other routine. However current
`_set_empty_to_whitespace` is fill with context.
So, error occured.

And, I checked `multimodal_user_transformer_funcs` and I found it, in
this routine, context must not be empty.
Now remove the `_set_empty_to_whitespace` when multimodal message,
<!-- Please give a short summary of the change and the problem this
solves. -->

## Related issue number

Closes #6439 

## Checks

- [ ] I've included any doc changes needed for
<https://microsoft.github.io/autogen/>. See
<https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md> to
build and test documentation locally.
- [x] I've added tests (if relevant) corresponding to the changes
introduced in this PR.
- [x] I've made sure all auto checks have passed.

Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>

Author: SongChiYoung

python/packages/autogen-ext/src/autogen_ext/models/openai/_message_transform.py

@@ -379,7 +379,7 @@ def assistant_condition(message: LLMMessage, context: Dict[str, Any]) -> str:
 
 user_transformer_funcs_gemini: Dict[str, List[Callable[[LLMMessage, Dict[str, Any]], Dict[str, Any]]]] = {
     "text": single_user_transformer_funcs + [_set_empty_to_whitespace],
-    "multimodal": multimodal_user_transformer_funcs + [_set_empty_to_whitespace],
+    "multimodal": multimodal_user_transformer_funcs,
 }
 
 

python/packages/autogen-ext/tests/models/test_openai_model_client.py

@@ -7,6 +7,8 @@
 
 import httpx
 import pytest
+from autogen_agentchat.agents import AssistantAgent
+from autogen_agentchat.messages import MultiModalMessage
 from autogen_core import CancellationToken, FunctionCall, Image
 from autogen_core.models import (
     AssistantMessage,
@@ -2459,4 +2461,28 @@ def test_find_model_family() -> None:
     assert _find_model_family("openai", "error") == ModelFamily.UNKNOWN
 
 
+@pytest.mark.asyncio
+@pytest.mark.parametrize(
+    "model",
+    [
+        "gpt-4.1-nano",
+        "gemini-1.5-flash",
+        "claude-3-5-haiku-20241022",
+    ],
+)
+async def test_multimodal_message_test(
+    model: str, openai_client: OpenAIChatCompletionClient, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    # Test that the multimodal message is converted to the correct format
+    img = Image.from_base64(
+        "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAIAAACQd1PeAAAADElEQVR4nGP4z8AAAAMBAQDJ/pLvAAAAAElFTkSuQmCC"
+    )
+    multi_modal_message = MultiModalMessage(content=["Can you describe the content of this image?", img], source="user")
+
+    ocr_agent = AssistantAgent(
+        name="ocr_agent", model_client=openai_client, system_message="""You are a helpful agent."""
+    )
+    _ = await ocr_agent.run(task=multi_modal_message)
+
+
 # TODO: add integration tests for Azure OpenAI using AAD token.