Module●Since v0.0
agent
Agent management and creation for the CLI.
Attributes
attributeattributeattributeattributeattributeattributeattributeattribute
OutputFormat: Literal['text', 'json']
Accepted internal output modes for CLI subcommands.
COLORS: dict
App color scheme.
config: RunnableConfig
console
settings
logger
DEFAULT_AGENT_NAME: str
The default agent name used when no -a flag is provided.
REQUIRE_COMPACT_TOOL_APPROVAL: bool
When True, compact_conversation requires HITL approval like other gated tools.
Functions
functionfunctionfunctionfunctionfunctionfunctionfunctionfunctionfunctionfunctionfunctionfunctionfunctionfunction
get_default_coding_instructions
Get the default coding agent instructions.
These are the immutable base instructions that cannot be modified by the agent. Long-term memory (AGENTS.md) is handled separately by the middleware.
get_glyphs
Get the glyph set for the current charset mode.
get_default_working_dir
Get the default working directory for a given sandbox provider.
list_subagents
List subagents from user and/or project directories.
Scans for subagent definitions in the provided directories. Project subagents override user subagents with the same name.
check_url_safety
Check a URL for suspicious Unicode and domain spoofing patterns.
detect_dangerous_unicode
Detect deceptive or hidden Unicode code points in text.
format_warning_detail
Join safety warnings into a display string with overflow indicator.
render_with_unicode_markers
Render hidden Unicode characters as explicit markers.
Example output: abc<U+202E RIGHT-TO-LEFT OVERRIDE>def.
strip_dangerous_unicode
Remove known dangerous/invisible Unicode characters from text.
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.
list_agents
List all available agents.
reset_agent
Reset an agent to default or copy from another agent.
get_system_prompt
Get the base system prompt for the agent.
Loads the base system prompt template from system_prompt.md and
interpolates dynamic sections (model identity, working directory,
skills path, execution mode).
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).
Classes
classclass
MCPServerInfo
Metadata for a connected MCP server and its tools.
LocalContextMiddleware
Inject local context (git state, project structure, etc.) into the system prompt.
Runs a bash detection script via backend.execute() on first interaction
and again after each summarization event, stores the result in state, and
appends it to the system prompt on every model call.
Because the script runs inside the backend, it works for both local shells and remote sandboxes.