Agent Sandbox:Create an AgenticBucket Volume

Storage configuration

The fields of agenticBucketVolumeConfig correspond to the Python SDK parameters as follows:

Mount configuration

mountConfig stores the Alibaba Cloud Resource Name (ARN) of the RAM role required for the mount. The corresponding Python SDK parameter is mount_config, which is of the models.CreateVolumeInputMountConfig type.

An AgenticBucket Volume does not support mountConfig.vpcConfig.

The role configuration is stored when the volume is created, and is reused when a Sandbox mounts the volume. For more information about how to create a role and the role selection rules, see Configure a RAM role.

Environment variables

The example in this topic reads the following environment variables. Configure the access credentials as described in the SDK instructions above, and set the other parameters in the creation example.

Creation example

In a terminal in which the access credentials are configured, set the following parameters and replace the placeholders with actual values. For the value of each variable, see Environment variables.

export SANDBOX_REGION_ID="<REGION>"
export SANDBOX_ENDPOINT="sandbox.${SANDBOX_REGION_ID}.aliyuncs.com"

export SANDBOX_TEAM_ID="<TEAM-ID>"
export SANDBOX_ROLE_ARN="acs:ram::<ACCOUNT-UID>:role/<ROLE-NAME>"
export SANDBOX_VOLUME_NAME="<VOLUME-NAME>"

export AGENTIC_BUCKET_NAME="<AGENTIC-BUCKET-FULL-NAME>"
export BUCKET_SPACE_NAME="<BUCKET-SPACE-FULL-NAME>"
export OSS_ENDPOINT="https://oss-<REGION>-internal.aliyuncs.com"

Save the following code as 10_create_agentic_bucket_volume.py:

import os

from alibabacloud_sandbox20260820 import models
from alibabacloud_sandbox20260820.client import Client as SandboxClient
from alibabacloud_tea_openapi import utils_models as open_api_models


def require_env(name: str) -> str:
    value = os.environ.get(name, "").strip()
    if not value:
        raise RuntimeError(f"Missing environment variable: {name}")
    return value


config = open_api_models.Config(
    access_key_id=require_env("ALIBABA_CLOUD_ACCESS_KEY_ID"),
    access_key_secret=require_env("ALIBABA_CLOUD_ACCESS_KEY_SECRET"),
    security_token=os.environ.get("ALIBABA_CLOUD_SECURITY_TOKEN"),
    region_id=require_env("SANDBOX_REGION_ID"),
    endpoint=require_env("SANDBOX_ENDPOINT"),
)

pop_client = SandboxClient(config)

response = pop_client.create_volume(
    models.CreateVolumeRequest(
        body=models.CreateVolumeInput(
            team_id=require_env("SANDBOX_TEAM_ID"),
            volume_name=require_env("SANDBOX_VOLUME_NAME"),
            mount_config=models.CreateVolumeInputMountConfig(
                role=require_env("SANDBOX_ROLE_ARN"),
            ),
            agentic_bucket_volume_config=models.AgenticBucketVolumeConfig(
                agentic_bucket=require_env("AGENTIC_BUCKET_NAME"),
                bucket_name=require_env("BUCKET_SPACE_NAME"),
                bucket_path="/",
                endpoint=require_env("OSS_ENDPOINT"),
                read_only=False,
            ),
        )
    )
)

if response.body is None or response.body.volume is None:
    raise RuntimeError("CreateVolume did not return a volume")

volume = response.body.volume
print(f"request_id={response.body.request_id}")
print(f"volume_id={volume.volume_id}")
print(f"volume_name={volume.volume_name}")
print(f"storage_class={volume.storage_class}")
print(f"status={volume.status}")

In the same terminal, create the AgenticBucket Volume:

python 10_create_agentic_bucket_volume.py

A successful creation only indicates that the volume configuration is stored. To verify that the mount works, create a Sandbox and mount the volume by name as described in Mount an AgenticBucket Volume. Then confirm that files can be read and written.