AgentCore 게이트웨이에서 샘플링 사용

import requests
import json
import sseclient

gateway_url = "https://mygateway-abcdefghij.gateway.bedrock-agentcore.us-west-2.amazonaws.com/mcp"
headers = {
    "Content-Type": "application/json",
    "Accept": "text/event-stream",
    "Authorization": "Bearer YOUR_ACCESS_TOKEN"
}

# Step 1: Initialize with sampling capability
init_response = requests.post(gateway_url, headers=headers, json={
    "jsonrpc": "2.0",
    "id": "init-request",
    "method": "initialize",
    "params": {
        "protocolVersion": "2025-06-18",
        "capabilities": {"sampling": {}},
        "clientInfo": {"name": "my-agent", "version": "1.0.0"}
    }
})
session_id = init_response.headers["Mcp-Session-Id"]
headers["Mcp-Session-Id"] = session_id

# Step 2: Call tool (streaming response)
response = requests.post(gateway_url, headers=headers, json={
    "jsonrpc": "2.0",
    "id": "tool-call-1",
    "method": "tools/call",
    "params": {
        "name": "summarizeDocument",
        "arguments": {"documentId": "doc-789"}
    }
}, stream=True)

# Step 3: Process SSE events
client = sseclient.SSEClient(response)
for event in client.events():
    data = json.loads(event.data)
    if data.get("method") == "sampling/createMessage":
        sampling_id = data["id"]
        print(f"Sampling request: {data['params']['messages']}")

        # Step 4: Invoke your LLM and send result
        llm_result = invoke_your_model(data["params"])  # Your LLM invocation
        requests.post(gateway_url, headers=headers, json={
            "jsonrpc": "2.0",
            "id": sampling_id,
            "result": {
                "model": "claude-sonnet-4-20250514",
                "role": "assistant",
                "content": {"type": "text", "text": llm_result}
            }
        })
    elif "result" in data:
        print(f"Tool result: {data['result']}")
        break

from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client
import asyncio

async def sampling_handler(request):
    """Handle sampling requests from the server by invoking an LLM."""
    messages = request.params.messages
    llm_response = await invoke_your_model(messages, max_tokens=request.params.maxTokens)
    return {
        "model": "claude-sonnet-4-20250514",
        "role": "assistant",
        "content": {"type": "text", "text": llm_response}
    }

async def use_sampling(url, token):
    headers = {"Authorization": f"Bearer {token}"}

    async with streamablehttp_client(url=url, headers=headers) as (
        read_stream, write_stream, _
    ):
        async with ClientSession(
            read_stream, write_stream,
            sampling_handler=sampling_handler
        ) as session:
            await session.initialize()
            result = await session.call_tool(
                name="summarizeDocument",
                arguments={"documentId": "doc-789"}
            )
            print(f"Tool result: {result}")
            return result

asyncio.run(use_sampling(
    url="https://mygateway-abcdefghij.gateway.bedrock-agentcore.us-west-2.amazonaws.com/mcp",
    token="YOUR_ACCESS_TOKEN"
))