create_cli_agent

create_cli_agent(
  model: str | BaseChatModel,
  assistant_id: str,

View source on GitHub

interrupt_shell_only

Parameters

Name	Type	Description
`model`*	`str \| BaseChatModel`	LLM model to use (e.g., `'provider:model'`)
`assistant_id`*	`str`	Agent identifier for memory/state storage
`tools`	`Sequence[BaseTool \| Callable \| dict[str, Any]] \| None`	Default:`None`
`sandbox`	`SandboxBackendProtocol \| None`	Default:`None`
`sandbox_type`	`str \| None`	Default:`None`
`system_prompt`	`str \| None`	Default:`None`
`interactive`	`bool`	Default:`True`
`auto_approve`	`bool`	Default:`False`
`interrupt_shell_only`	`bool`	Default:`False`
`shell_allow_list`	`list[str] \| None`	Default:`None`
`enable_ask_user`	`bool`	Default:`True`
`enable_memory`	`bool`	Default:`True`
`enable_skills`	`bool`	Default:`True`
`enable_shell`	`bool`	Default:`True`
`checkpointer`	`BaseCheckpointSaver \| None`	Default:`None`
`mcp_server_info`	`list[MCPServerInfo] \| None`	Default:`None`
`cwd`	`str \| Path \| None`	Default:`None`
`project_context`	`ProjectContext \| None`	Default:`None`
`async_subagents`	`list[AsyncSubAgent] \| None`	Default:`None`

Create a CLI-configured agent with flexible options.

This is the main entry point for creating a Deep Agents Code agent, usable both internally and from external code (e.g., benchmarking frameworks).

Additional tools to provide to agent

Optional sandbox backend for remote execution (e.g., ModalSandbox).

If None, uses local filesystem + shell.

Type of sandbox provider ('agentcore', 'daytona', 'langsmith', 'modal', 'runloop'). Used for system prompt generation.

Override the default system prompt.

If None, generates one based on sandbox_type, assistant_id, and interactive.

When False, the auto-generated system prompt is tailored for headless non-interactive execution. Ignored when system_prompt is provided explicitly.

If True, no tools trigger human-in-the-loop interrupts — all calls (shell execution, file writes/edits, web search, URL fetch) run automatically.

If False, tools pause for user confirmation via the approval menu. See _add_interrupt_on for the full list of gated tools.

If True, all HITL interrupts are disabled; shell commands are validated inline by ShellAllowListMiddleware against the configured allow-list instead.

Used in non-interactive mode with a restrictive shell allow-list to avoid splitting traces into multiple LangSmith runs.

Has no effect when auto_approve is True (interrupts are already disabled) or when shell_allow_list is SHELL_ALLOW_ALL.

Explicit restrictive shell allow-list forwarded from the CLI process. When provided (and interrupt_shell_only is True), used directly instead of reading settings.shell_allow_list (which may not be set in the server subprocess environment).

Enable AskUserMiddleware so the agent can ask clarifying questions.

Disabled in non-interactive mode.

Enable MemoryMiddleware for persistent memory

Enable SkillsMiddleware for custom agent skills

Enable shell execution via LocalShellBackend (only in local mode). When enabled, the execute tool is available.

Optional checkpointer for session persistence. When None, the graph is compiled without a checkpointer.

MCP server metadata to surface in the system prompt.

Override the working directory for the agent's filesystem backend and system prompt.

Explicit project path context for project-sensitive behavior such as project AGENTS.md files, skills, subagents, and MCP trust.

Remote LangGraph deployments to expose as async subagent tools.

Loaded from [async_subagents] in config.toml or passed directly.

LangChain Assistant

Menu

create_cli_agent

Parameters