Only 'execute' is registered by the SDK and CLI backends in practice. 'bash' and 'shell' are legacy names carried over and kept as backwards-compatible aliases.

attribute

settings

attribute

logger

function

create_cli_agent

Create a CLI-configured agent with flexible options.

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

function

build_langsmith_thread_url

Build a full LangSmith thread URL if tracing is configured.

Combines get_langsmith_project_name and fetch_langsmith_project_url into a single convenience helper.

function

create_model

Create a chat model.

Uses init_chat_model for standard providers, or imports a custom BaseChatModel subclass when the provider has a class_path in config.

Supports provider:model format (e.g., 'anthropic:claude-sonnet-4-5') for explicit provider selection, or bare model names for auto-detection.

function

is_shell_command_allowed

Check if a shell command is in the allow-list.

The allow-list matches against the first token of the command (the executable name). This allows read-only commands like ls, cat, grep, etc. to be auto-approved.

When allow_list is the SHELL_ALLOW_ALL sentinel, all non-empty commands are approved unconditionally — dangerous pattern checks are skipped.

SECURITY: For regular allow-lists, this function rejects commands containing dangerous shell patterns (command substitution, redirects, process substitution, etc.) BEFORE parsing, to prevent injection attacks that could bypass the allow-list.

function

dispatch_hook

Fire matching hook commands with payload serialized as JSON on stdin.

The event name is automatically injected into the payload under the "event" key so callers don't need to duplicate it.

The blocking subprocess work is offloaded to a thread so the caller's event loop is never stalled. Matching hooks run concurrently, each with a 5-second timeout. Errors are logged and never propagated.

function

dispatch_hook_fire_and_forget

Schedule dispatch_hook as a background task with a strong reference.

Use this instead of bare create_task(dispatch_hook(...)) to prevent the task from being garbage collected before completion.

Safe to call from sync code as long as an event loop is running.

function

generate_thread_id

Generate a new 8-char hex thread ID.

function

get_checkpointer

Get AsyncSqliteSaver for the global database.

function

print_usage_table

Print a model-usage stats table to a Rich console.

When the session spans multiple models each gets its own row with a totals row appended; single-model sessions show one row.

function

fetch_url

Fetch content from a URL and convert HTML to markdown format.

This tool fetches web page content and converts it to clean markdown text, making it easy to read and process HTML content. After receiving the markdown, you MUST synthesize the information into a natural, helpful response for the user.

function

http_request

Make HTTP requests to APIs and web services.

function

web_search

Search the web using Tavily for current information and documentation.

This tool searches the web and returns relevant results. After receiving results, you MUST synthesize the information into a natural, helpful response for the user.

function

check_url_safety

Check a URL for suspicious Unicode and domain spoofing patterns.

function

detect_dangerous_unicode

Detect deceptive or hidden Unicode code points in text.

function

format_warning_detail

Join safety warnings into a display string with overflow indicator.

function

iter_string_values

Flatten nested dict/list structures into key-path/string pairs.

function

looks_like_url_key

Return whether a key path suggests URL-like content.

function

summarize_issues

Summarize Unicode issues for warning messages.

Deduplicates by code point. When more than max_items unique entries exist, the summary is truncated with a +N more entries suffix.

function

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.

class

FileOpTracker

Collect file operation metrics during a CLI interaction.

class

ModelConfigError

Raised when model configuration or creation fails.

class

SessionStats

Stats accumulated over a single agent turn (or full session).

class

HITLIterationLimitError

Raised when the HITL interrupt loop exceeds _MAX_HITL_ITERATIONS rounds.

class

StreamState

Mutable state accumulated while iterating over the agent stream.

class

ThreadUrlLookupState

Best-effort background LangSmith thread URL lookup state.

Thread safety: the background thread sets url then calls done.set(). Consumers must check done.is_set() before reading url.

Non-interactive execution mode for deepagents CLI.

Provides run_non_interactive which runs a single user task against the agent graph, streams results to stdout, and exits with an appropriate code.

Shell commands are gated by an optional allow-list (--shell-allow-list):

Not set → shell disabled, all other tool calls auto-approved.
recommended or explicit list → shell enabled, commands validated against the list; non-shell tools approved unconditionally.
all → shell enabled, any command allowed, all tools auto-approved.

An optional quiet mode (--quiet / -q) redirects all console output to stderr, leaving stdout exclusively for the agent's response text.

Menu

non_interactive

Attributes

Functions

Classes