用户指令 → MiniMax LLM (任务规划) → Pi05 VLA (动作执行) → LIBERO仿真
               ↑                                              ↓
         MCP视觉理解 ← ─────────── 场景图像 ←──────────────────┘

AGENT_TOOLS = [
    {
        "name": "execute_task",
        "description": "Execute a manipulation task using the robot arm.",
        "input_schema": {
            "type": "object",
            "properties": {
                "task": {
                    "type": "string",
                    "description": "A manipulation task instruction"
                }
            },
            "required": ["task"]
        }
    },
    {
        "name": "get_scene_info",
        "description": "Capture camera image and use VLM to analyze the current scene.",
        "input_schema": {
            "type": "object",
            "properties": {},
            "required": []
        }
    }
]

from anthropic import Anthropic

client = Anthropic(
    base_url="https://api.minimaxi.com/anthropic",
    api_key=api_key,
    default_headers={"Authorization": f"Bearer {api_key}"}
)

response = client.messages.create(
    model="MiniMax-M2.1",
    max_tokens=4096,
    system=system_prompt,
    messages=conversation_history,
    tools=AGENT_TOOLS
)

from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client

server_params = StdioServerParameters(
    command="uvx",
    args=["minimax-coding-plan-mcp", "-y"],
    env={
        "MINIMAX_API_KEY": api_key,
        "MINIMAX_API_HOST": "https://api.minimaxi.com"
    }
)

async with stdio_client(server_params) as (read, write):
    async with ClientSession(read, write) as session:
        await session.initialize()
        result = await session.call_tool("understand_image", {
            "image_source": image_path,
            "prompt": "Verify if the task was completed successfully."
        })