Function●Since v0.0

run_non_interactive

Run a single task non-interactively and exit.

The agent is created with interactive=False, which tailors the system prompt for autonomous headless execution (no clarification questions, reasonable assumptions).

Shell access and auto-approval are controlled by --shell-allow-list:

Not set → shell disabled, all other tools auto-approved.
recommended or explicit list → shell enabled, commands gated by allow-list; non-shell tools approved unconditionally.
all → shell enabled, any command allowed, all tools auto-approved.

Note: startup header rendering avoids synchronous LangSmith URL lookups. A background thread resolves the thread URL concurrently and the result is displayed after task completion if available.

run_non_interactive(
  message: str,
  assistant_id: str = 'agent',
  model_name: str | None = None,
  model_params: dict[str, Any] | None = None,
  sandbox_type: str = 'none',
  sandbox_id: str | None = None,
  sandbox_setup: str | None = None,
  *,
  initial_skill: str | None = None,
  profile_override: dict[str, Any] | None = None,
  quiet: bool = False,
  stream: bool = True,
  mcp_config_path: str | None = None,
  no_mcp: bool = False,
  trust_project_mcp: bool = False
) -> int

Parameters

Name	Type	Description
`message`*	`str`	The task/message to execute.
`assistant_id`	`str`	Default:`'agent'` Agent identifier for memory storage.
`model_name`	`str \| None`	Default:`None` Optional model name to use.
`model_params`	`dict[str, Any] \| None`	Default:`None` Extra kwargs from `--model-params` to pass to the model. These override config file values.
`sandbox_type`	`str`	Default:`'none'` Type of sandbox (`'none'`, `'agentcore'`, `'daytona'`, `'langsmith'`, `'modal'`, `'runloop'`).
`sandbox_id`	`str \| None`	Default:`None` Optional existing sandbox ID to reuse.
`sandbox_setup`	`str \| None`	Default:`None` Optional path to setup script to run in the sandbox after creation.
`initial_skill`	`str \| None`	Default:`None` Optional skill name whose `SKILL.md` instructions wrap the user message before sending it to the agent.
`profile_override`	`dict[str, Any] \| None`	Default:`None` Extra profile fields from `--profile-override`. Merged on top of config file profile overrides.
`quiet`	`bool`	Default:`False` When `True`, all console output (headers, status messages, tool notifications, HITL decisions, errors) is redirected to stderr so that only the agent's response text appears on stdout.
`stream`	`bool`	Default:`True` When `True` (default), text chunks are written to stdout as they arrive. When `False`, the full response is buffered and written to stdout in one shot after the agent finishes.
`mcp_config_path`	`str \| None`	Default:`None` Optional path to MCP servers JSON configuration file. Merged on top of auto-discovered configs (highest precedence).
`no_mcp`	`bool`	Default:`False` Disable all MCP tool loading.
`trust_project_mcp`	`bool`	Default:`False` When `True`, allow project-level stdio MCP servers. When `False` (default), project stdio servers are silently skipped.

View source on GitHub

run_non_interactive

Run a single task non-interactively and exit.

The agent is created with interactive=False, which tailors the system prompt for autonomous headless execution (no clarification questions, reasonable assumptions).

Shell access and auto-approval are controlled by --shell-allow-list:

Not set → shell disabled, all other tools auto-approved.
recommended or explicit list → shell enabled, commands gated by allow-list; non-shell tools approved unconditionally.
all → shell enabled, any command allowed, all tools auto-approved.

Note: startup header rendering avoids synchronous LangSmith URL lookups. A background thread resolves the thread URL concurrently and the result is displayed after task completion if available.

run_non_interactive( message: str, assistant_id: str = 'agent', model_name: str | None = None, model_params: dict[str, Any] | None = None, sandbox_type: str = 'none', sandbox_id: str | None = None, sandbox_setup: str | None = None, *, initial_skill: str | None = None, profile_override: dict[str, Any] | None = None, quiet: bool = False, stream: bool = True, mcp_config_path: str | None = None, no_mcp: bool = False, trust_project_mcp: bool = False ) -> int

Parameters

Name	Type	Description
`message`*	`str`	The task/message to execute.
`assistant_id`	`str`	Default:`'agent'` Agent identifier for memory storage.
`model_name`	`str \| None`	Default:`None` Optional model name to use.
`model_params`	`dict[str, Any] \| None`	Default:`None` Extra kwargs from `--model-params` to pass to the model. These override config file values.
`sandbox_type`	`str`	Default:`'none'` Type of sandbox (`'none'`, `'agentcore'`, `'daytona'`, `'langsmith'`, `'modal'`, `'runloop'`).
`sandbox_id`	`str \| None`	Default:`None` Optional existing sandbox ID to reuse.
`sandbox_setup`	`str \| None`	Default:`None` Optional path to setup script to run in the sandbox after creation.
`initial_skill`	`str \| None`	Default:`None` Optional skill name whose `SKILL.md` instructions wrap the user message before sending it to the agent.
`profile_override`	`dict[str, Any] \| None`	Default:`None` Extra profile fields from `--profile-override`. Merged on top of config file profile overrides.
`quiet`	`bool`	Default:`False` When `True`, all console output (headers, status messages, tool notifications, HITL decisions, errors) is redirected to stderr so that only the agent's response text appears on stdout.
`stream`	`bool`	Default:`True` When `True` (default), text chunks are written to stdout as they arrive. When `False`, the full response is buffered and written to stdout in one shot after the agent finishes.
`mcp_config_path`	`str \| None`	Default:`None` Optional path to MCP servers JSON configuration file. Merged on top of auto-discovered configs (highest precedence).
`no_mcp`	`bool`	Default:`False` Disable all MCP tool loading.
`trust_project_mcp`	`bool`	Default:`False` When `True`, allow project-level stdio MCP servers. When `False` (default), project stdio servers are silently skipped.

run_non_interactive

Parameters

LangChain Assistant

Menu

run_non_interactive

Parameters