Assistant message multi model support

[Ravikumarchavva]

What happened?

I was building custom Agent and chat completion client, and i found that UserMessage have content type supporting both text and Image type but for AssitantMessage only supporting text for content. What if assistant produces image? I am in a situation that agent need to analyse its own produced image.

How to tackle this? is their any working going on to support this? or we only need it subclass it and change content type? same thing for CreateResult, FunctionExecutionResult.

Which packages was the bug in?

Python Core (autogen-core)

AutoGen library version.

Python dev (main branch)

Other library version.

No response

Model used

gemini-2.5-image-preview

Model provider

Google Gemini

Other model provider

No response

Python version

3.12

.NET version

None

Operating system

Windows