Returns a decision: auto (allow), approve (needs human review), or block (deny).

    Args:
        action_type: The kind of operation (e.g. "read_file", "send_email", "delete").
        target: The system being acted upon (e.g. "filesystem", "stripe", "database").
        params: Arbitrary parameters for the operation.
        description: Optional human-readable description.
        agent_id: Optional identifier for the agent performing the action.
    

    Each action dict should have: action_type, target,
    and optionally params, description, agent_id.

    Args:
        actions: List of action dicts to evaluate.
    

    The new policy takes effect immediately for all subsequent evaluations.

    Args:
        yaml_content: YAML string containing the policy rules.
    

    Returns just the risk level and approval requirement — lighter than evaluate_action.

    Args:
        action_type: The kind of operation.
        target: The system being acted upon.