o4-mini model support

[KanikaChoudhary1312]

Hi Team,

I'm currently working with Azure OpenAI models and have recently deployed the new o4-mini model. I'm trying to test the Web Agent flow in Autogen Studio using this model. In my team_config, I've set the model_client to use o4-mini, but I encounter a connection error when running it.

I noticed that autogen-ext doesn’t explicitly list o4-mini as a supported model. Could this be the reason for the error? If so, is the recommended approach to register it as a custom_model_client instead? Just want to confirm the best practice for integrating newly deployed Azure models in Autogen Studio.

  {
    "provider": "autogen_agentchat.agents.UserProxyAgent",
    "component_type": "agent",
    "version": 1,
    "component_version": 1,
    "description": "An agent that can represent a human user through an input function.",
    "label": "UserProxyAgent",
    "config": {
      "name": "user_proxy",
      "description": "a human user that should be consulted only when the assistant_agent is unable to verify the information provided by the websurfer_agent"
    }
  }
],
"model_client": {
  "provider": "autogen_ext.models.openai.AzureOpenAIChatCompletionClient",
  "component_type": "model",
  "version": 1,
  "component_version": 1,
  "description": "GPT-o4-mini",
  "label": "o4-mini",
  "config": {
    "model": "o4-mini",
    "api_key": "<key>",
    "azure_endpoint": "<endpoint>",
    "azure_deployment": "o4-mini",
    "reasoning_effort": "medium",
    "api_version": "<apiversion>",
    "model_info": {
      "vision": "False",
      "function_calling": "True",
      "json_output": "True",
      "family": "ModelFamily.O3",
      "structured_output": "True"
    }
  }
},
"termination_condition": {
  "provider": "autogen_agentchat.base.OrTerminationCondition",
  "component_type": "termination",
  "version": 1,
  "component_version": 1,
  "label": "OrTerminationCondition",
  "config": {
    "conditions": [
      {
        "provider": "autogen_agentchat.conditions.MaxMessageTermination",
        "component_type": "termination",
        "version": 1,
        "component_version": 1,
        "description": "Terminate the conversation after a maximum number of messages have been exchanged.",
        "label": "MaxMessageTermination",
        "config": {
          "max_messages": 20,
          "include_agent_event": false
        }
      },
      {
        "provider": "autogen_agentchat.conditions.TextMentionTermination",
        "component_type": "termination",
        "version": 1,
        "component_version": 1,
        "description": "Terminate the conversation if a specific text is mentioned.",
        "label": "TextMentionTermination",
        "config": {
          "text": "TERMINATE"
        }
      }
    ]
  }
},
"selector_prompt": "You are the cordinator of role play game. The following roles are available:\n{roles}. Given a task, the websurfer_agent will be tasked to address it by browsing the web and providing information.  The assistant_agent will be tasked with verifying the information provided by the websurfer_agent and summarizing the information to present a final answer to the user. If the task  needs assistance from a human user (e.g., providing feedback, preferences, or the task is stalled), you should select the user_proxy role to provide the necessary information.\n\nRead the following conversation. Then select the next role from {participants} to play. Only return the role.\n\n{history}\n\nRead the above conversation. Then select the next role from {participants} to play. Only return the role.",
"allow_repeated_speaker": false,
"max_selector_attempts": 3

}
}
Thanks for the help

[KanikaChoudhary1312]

I guess I found the answer : after keeping "family": "unknown", it works. Thanks

[ekzhu]

The model info should have been added in the latest version of autogen. Just update the library