Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
将 LangGraph 状态和检查点与 BeeOS 原生工具、MCP 或持久 OpenAPI 任务结合
langchain-beeos 返回标准 LangChain 工具，可以直接传给 LangGraph 的
ToolNode：
import os
from langgraph.prebuilt import ToolNode
from langchain_beeos import BeeOSToolkit
with BeeOSToolkit(
instance_id=os.environ["BEEOS_INSTANCE_ID"],
include_tools={"beeos_computer_info", "beeos_mobile_info"},
) as toolkit:
beeos_node = ToolNode(toolkit.get_tools())
# Build, compile, and invoke the graph while the toolkit remains open.
include_tools、固定目标 ID 和修改权限范围限定能力。检查点可以
恢复图状态，但不能在恢复运行时静默扩大可用的 BeeOS 工具或权限。
pip install langgraph langchain-mcp-adapters
import os
from langchain.agents import create_agent
from langchain_mcp_adapters.client import MultiServerMCPClient
async def build_agent():
agent_id = os.environ["BEEOS_AGENT_ID"]
client = MultiServerMCPClient(
{
"beeos": {
"transport": "http",
"url": f"https://mcp.beeos.ai/{agent_id}/mcp",
"headers": {
"Authorization": f"Bearer {os.environ['BEEOS_API_KEY']}"
},
}
}
)
tools = await client.get_tools()
return create_agent(os.environ["LLM_MODEL"], tools)
taskId 存入图状态。后续节点轮询，或由 webhook 恢复图。这样 LangGraph checkpoint 与 BeeOS task 持久性可以协作，而不是一直占用一个 MCP 请求。
import os
import httpx
async def create_beeos_task(state: dict) -> dict:
headers = {"Authorization": f"Bearer {os.environ['BEEOS_API_KEY']}"}
body = {
"message": state["phone_task"],
"idempotency_key": state["run_id"],
}
async with httpx.AsyncClient(base_url="https://openapi.beeos.ai") as client:
response = await client.post(
f"/api/v1/agents/{state['agent_id']}/tasks",
headers=headers,
json=body,
)
response.raise_for_status()
return {"beeos_task": response.json()}