OpenAI o1 support

[Hk669]

Why are these changes needed?

the o1 preview and o1 series models doesnt support the same API parameters (Limitations) as the other openai models, so added a helper function in the OpenAIClient that tackles this issue and can be run in the agentic workflow.

tested with the two agent run (with o1-preview) with a question from simple-bench, and it runs perfectly on my side.

Related issue number

Checks

• I've included any doc changes needed for https://docs.ag2.ai/. See https://docs.ag2.ai/docs/contributor-guide/documentation to build and test documentation locally.
• I've added tests (if relevant) corresponding to the changes introduced in this PR.
• I've made sure all auto checks have passed.

[marklysze]

I'd like to propose adding documentation regarding o1 separately when we do the documentation updates. I think a table showing supported features and models/clients would be beneficial.

[marklysze]

Outstanding, if we can put documentation in a separate PR, is testing this with o1. If that's a dependency then we'll need to get that tested first.

Here's sample code to run against this branch to test o1:

altmodel_llm_config = {
    # o1 full model
    "config_list": [
        {
            "api_type": "openai",
            "model": "o1-2024-12-17",
            "max_tokens": 8192,
            "cache_seed": None,
        }
    ]
}

altmodel_llm_config_other = {
    # Leave this as 4o-mini
    "config_list": [{"api_type": "openai", "model": "gpt-4o-mini", "stream": False, "cache_seed": None}]
}

from autogen import (
    AFTER_WORK,
    AfterWorkOption,
    SwarmAgent,
    SwarmResult,
    initiate_swarm_chat,
)


def must_call_me() -> SwarmResult:
    """A must call function, absolutely call it."""
    return SwarmResult(values="This must call me function ran.", agent=emma)


jack = SwarmAgent(
    "Jack",
    llm_config=altmodel_llm_config,
    system_message="List the steps required to solve this.",
    is_termination_msg=lambda x: True if "FINISH" in x["content"] else False,
)
emma = SwarmAgent(
    "Emma",
    llm_config=altmodel_llm_config_other,
    system_message="Use the steps to answer the question.",
    is_termination_msg=lambda x: True if "FINISH" in x["content"] else False,
)

jack.register_hand_off([AFTER_WORK(emma)])
emma.register_hand_off(AFTER_WORK(AfterWorkOption.TERMINATE))

result, messages, last_agent = initiate_swarm_chat(
    initial_agent=jack,
    agents=[jack, emma],
    messages=[
        "Peter needs CPR from his best friend Paul, the only person around. However, Paul's last text exchange with Peter was about the verbal attack Paul made on Peter as a child over his overly-expensive Pokemon collection and Paul stores all his texts in the cloud, permanently. Paul will [ _ ] help Peter.\nA. probably not\nB. definitely\nC. half-heartedly\nD. not\nE. pretend to\nF. ponder deeply over whether to"
    ],
    after_work=AFTER_WORK(AfterWorkOption.TERMINATE),
)

[Hk669]

LGTM. thanks @marklysze