Documentation/docs/managed-agents/compatibility

#Compatibility

Sandbox0 Managed Agents follows the Claude Managed Agents API shape where practical, while using Sandbox0 as the execution backend. This page documents the important compatibility boundaries.

Supported Surface#

AreaStatus
Official Anthropic SDKSupported by setting baseURL to the Sandbox0 Managed Agents API endpoint
Managed Agents beta headerRequired for direct HTTP calls. SDKs set it automatically.
AgentsSupported, including versioned agent definitions
EnvironmentsSupported for type: cloud with package and networking configuration
SessionsSupported with durable status, metadata, agent snapshot, resources, vault ids, usage, and stats
EventsSupported for list, send, and event streaming
FilesSupported for upload, metadata, download, delete, and file-backed message content
Vaults and credentialsSupported for LLM credentials and MCP credentials
Custom skillsSupported through uploaded skill versions
MCP serversSupported for URL MCP servers and vault-backed credentials
GitHub repository resourcesSupported at session creation

Current Differences#

DifferenceSandbox0 behavior
SDK ownershipSandbox0 does not ship a Managed Agents SDK. Use the official Anthropic SDK.
API tokenSDK apiKey is a Sandbox0 API key, not the Anthropic LLM token.
LLM tokenStored in an LLM vault and attached to the session.
Sandbox claimSession creation eagerly claims a sandbox, bootstraps wrapper state, and pauses the sandbox to reduce first-run latency.
Sandbox hard TTLConfigurable at session creation through metadata["sandbox0.managed_agents.hard_ttl_seconds"]; defaults to 3600 seconds and accepts "0" to disable the hard cap.
Engine supportClaude engine only. The LLM endpoint must be Anthropic-compatible.
OpenAI-compatible providersNot supported by the Claude engine. Use a future separate engine.
Anthropic pre-built skillsNot supported. Use Sandbox0 custom skills.
Multi-agent threadsNot implemented in the current backend surface.
Outcomes and memory research previewNot implemented in the current backend surface.
Rate limitsDeployment-specific. Do not assume Anthropic-hosted organization limits apply.

Tool Support#

The Claude wrapper maps Managed Agents tool definitions to Claude Agent SDK options.

Tool typeStatusNotes
agent_toolset_20260401SupportedEnables built-in tools such as bash, file operations, grep/glob, web fetch, and web search through the Claude wrapper
mcp_toolsetSupportedRequires matching mcp_servers entries and vault credentials when the server needs auth
Custom toolsSupportedThe wrapper emits agent.custom_tool_use and waits for user.custom_tool_result

Tool confirmation events are supported. When a tool policy requires confirmation, the session emits session.status_idle with stop_reason.type = "requires_action" and the relevant event ids.

Environment Support#

Only type: cloud environments are accepted today.

Networking options:

Networking typeBehavior
unrestrictedSandbox network mode is allow-all
limitedSandbox network mode is block-all with allowed hosts derived from environment settings, package managers, MCP servers, and session credential bindings

Package managers supported in environment config:

  • apt
  • cargo
  • gem
  • go
  • npm
  • pip

Session Lifecycle Notes#

Sandbox0 stores the session and event log outside the sandbox. Sandbox attachment state is stored outside the sandbox and points at the sandbox and volumes.

ActionBehavior
Create sessionStores durable session truth, claims a sandbox, bootstraps wrapper state, then pauses the sandbox until work starts.
Send user messageEnsures a sandbox is ready, bootstraps wrapper state, starts a run, and appends status events.
InterruptInterrupts the active wrapper run and moves local session truth back toward idle.
DeleteRejects active running sessions. Delete after interrupting and reaching idle.
ArchiveMakes the session read-only for new input events.

Version Drift#

The Managed Agents API is a beta surface. Sandbox0 tracks the official OpenAPI shape, but behavior can differ where Sandbox0 intentionally uses its own runtime, credential, and deployment model.

For application code, prefer SDK methods over hardcoded endpoint paths.

Next Steps#

Overview

Understand how Managed Agents map onto Sandbox0 primitives

Claude SDK

Use the official Anthropic SDK with the Sandbox0 Managed Agents endpoint