AgentSkillsCN

agentuity-cli-cloud-sandbox-create

创建用于多次执行的交互式沙箱。需要身份验证。用于Agentuity云平台操作

SKILL.md
--- frontmatter
name: agentuity-cli-cloud-sandbox-create
description: Create an interactive sandbox for multiple executions. Requires authentication. Use for Agentuity cloud platform operations
version: "0.0.110"
license: Apache-2.0
allowed-tools: "Bash(agentuity:*)"
metadata:
  command: "agentuity cloud sandbox create"
  tags: "slow requires-auth"

Cloud Sandbox Create

Create an interactive sandbox for multiple executions

Prerequisites

  • Authenticated with agentuity auth login
  • Organization context required (--org-id or default org)

Usage

bash
agentuity cloud sandbox create [options]

Options

OptionTypeRequiredDefaultDescription
--memorystringYes-Memory limit (e.g., "500Mi", "1Gi")
--cpustringYes-CPU limit in millicores (e.g., "500m", "1000m")
--diskstringYes-Disk limit (e.g., "500Mi", "1Gi")
--networkbooleanYes-Enable outbound network access
--idleTimeoutstringYes-Idle timeout before sandbox is reaped (e.g., "10m", "1h")
--envarrayYes-Environment variables (KEY=VALUE)
--filearrayYes-Files to create in sandbox (sandbox-path:local-path)
--snapshotstringYes-Snapshot ID or tag to restore from
--dependencyarrayYes-Apt packages to install (can be specified multiple times)

Examples

Create a sandbox with default settings:

bash
bunx @agentuity/cli cloud sandbox create

Create a sandbox with resource limits:

bash
bunx @agentuity/cli cloud sandbox create --memory 1Gi --cpu 1000m

Create a sandbox with network and custom timeout:

bash
bunx @agentuity/cli cloud sandbox create --network --idle-timeout 30m

Create a sandbox with a specific environment variable:

bash
bunx @agentuity/cli cloud sandbox create --env KEY=VAL

Output

Returns JSON object:

json
{
  "sandboxId": "string",
  "status": "string",
  "stdoutStreamUrl": "string",
  "stderrStreamUrl": "string"
}
FieldTypeDescription
sandboxIdstringUnique sandbox identifier
statusstringCurrent sandbox status
stdoutStreamUrlstringURL to the stdout output stream
stderrStreamUrlstringURL to the stderr output stream