Orchestrator requires an llm_factory even if a planner and agents are provided

[strawgate]

The llm_factory on the orchestrator should be optional if you provide a planner and agents (like it is on evaluator optimizer)

    def __init__(
        self,
        llm_factory: Callable[[Agent], AugmentedLLM[MessageParamT, MessageT]],
        planner: AugmentedLLM | None = None,
        available_agents: List[Agent | AugmentedLLM] | None = None,
        plan_type: Literal["full", "iterative"] = "full",
        context: Optional["Context"] = None,
        **kwargs,
    ):
        """
        Args:
            llm_factory: Factory function to create an LLM for a given agent
            planner: LLM to use for planning steps (if not provided, a default planner will be used)
            plan_type: "full" planning generates the full plan first, then executes. "iterative" plans the next step, and loops until success.
            available_agents: List of agents available to tasks executed by this orchestrator
            context: Application context
        """
        super().__init__(context=context, **kwargs)

        self.llm_factory = llm_factory

        self.planner = planner or llm_factory(
            agent=Agent(
                name="LLM Orchestration Planner",
                instruction="""
                You are an expert planner. Given an objective task and a list of MCP servers (which are collections of tools)
                or Agents (which are collections of servers), your job is to break down the objective into a series of steps,
                which can be performed by LLMs with access to the servers or agents.
                """,
            )
        )