Team

​

Parameters

Parameter	Type	Default	Description
members	List[Union[Agent, Team]]	-	List of agents or teams that make up this team
id	Optional[str]	None	Team UUID (autogenerated if not set)
model	Optional[Model]	None	Model to use for the team
name	Optional[str]	None	Name of the team
role	Optional[str]	None	Role of the team within its parent team
respond_directly	bool	False	If True, the team leader won’t process responses from the members and instead will return them directly
determine_input_for_members	bool	True	Set to False if you want to send the run input directly to the member agents
delegate_task_to_all_members	bool	False	If True, the team leader will delegate tasks to all members automatically, without any decision from the team leader
user_id	Optional[str]	None	Default user ID for this team
session_id	Optional[str]	None	Default session ID for this team (autogenerated if not set)
session_state	Optional[Dict[str, Any]]	None	Session state (stored in the database to persist across runs)
add_session_state_to_context	bool	False	Set to True to add the session_state to the context
enable_agentic_state	bool	False	Set to True to give the team tools to update the session_state dynamically
overwrite_db_session_state	bool	False	Set to True to overwrite the session state in the database with the session state provided in the run
cache_session	bool	False	If True, cache the current Team session in memory for faster access
resolve_in_context	bool	True	If True, resolve the session_state, dependencies, and metadata in the user and system messages
description	Optional[str]	None	A description of the Team that is added to the start of the system message
instructions	Optional[Union[str, List[str], Callable]]	None	List of instructions for the team
expected_output	Optional[str]	None	Provide the expected output from the Team
additional_context	Optional[str]	None	Additional context added to the end of the system message
markdown	bool	False	If markdown=true, add instructions to format the output using markdown
add_datetime_to_context	bool	False	If True, add the current datetime to the instructions to give the team a sense of time
add_location_to_context	bool	False	If True, add the current location to the instructions to give the team a sense of location
timezone_identifier	Optional[str]	None	Allows for custom timezone for datetime instructions following the TZ Database format
add_name_to_context	bool	False	If True, add the team name to the instructions
add_member_tools_to_context	bool	True	If True, add the tools available to team members to the context
system_message	Optional[Union[str, Callable, Message]]	None	Provide the system message as a string or function
system_message_role	str	"system"	Role for the system message
additional_input	Optional[List[Union[str, Dict, BaseModel, Message]]]	None	A list of extra messages added after the system message and before the user message
db	Optional[BaseDb]	None	Database to use for this team
memory_manager	Optional[MemoryManager]	None	Memory manager to use for this team
dependencies	Optional[Dict[str, Any]]	None	User provided dependencies
add_dependencies_to_context	bool	False	If True, add the dependencies to the user prompt
knowledge	Optional[Knowledge]	None	Add a knowledge base to the team
knowledge_filters	Optional[Dict[str, Any]]	None	Filters to apply to knowledge base searches
enable_agentic_knowledge_filters	Optional[bool]	False	Let the team choose the knowledge filters
update_knowledge	bool	False	Add a tool that allows the Team to update Knowledge
add_knowledge_to_context	bool	False	If True, add references to the user prompt
knowledge_retriever	Optional[Callable[..., Optional[List[Union[Dict, str]]]]]	None	Retrieval function to get references
references_format	Literal["json", "yaml"]	"json"	Format of the references
share_member_interactions	bool	False	If True, send all member interactions (request/response) during the current run to members that have been delegated a task to
get_member_information_tool	bool	False	If True, add a tool to get information about the team members
search_knowledge	bool	True	Add a tool to search the knowledge base (aka Agentic RAG)
send_media_to_model	bool	True	If False, media (images, videos, audio, files) is only available to tools and not sent to the LLM
store_media	bool	True	If True, store media in the database
store_tool_messages	bool	True	If True, store tool results in the database
store_history_messages	bool	True	If True, store history messages in the database
tools	Optional[List[Union[Toolkit, Callable, Function, Dict]]]	None	A list of tools provided to the Model
tool_choice	Optional[Union[str, Dict[str, Any]]]	None	Controls which (if any) tool is called by the team model
tool_call_limit	Optional[int]	None	Maximum number of tool calls allowed
max_tool_calls_from_history	Optional[int]	None	Maximum number of tool calls from history to keep in context. If None, all tool calls from history are included. If set to N, only the last N tool calls from history are added to the context for memory management
tool_hooks	Optional[List[Callable]]	None	A list of hooks to be called before and after the tool call
pre_hooks	Optional[Union[List[Callable[..., Any]], List[BaseGuardrail]]]	None	Functions called right after team session is loaded, before processing starts
post_hooks	Optional[Union[List[Callable[..., Any]], List[BaseGuardrail]]]	None	Functions called after output is generated but before the response is returned
input_schema	Optional[Type[BaseModel]]	None	Input schema for validating input
output_schema	Optional[Type[BaseModel]]	None	Output schema for the team response
parser_model	Optional[Model]	None	Provide a secondary model to parse the response from the primary model
parser_model_prompt	Optional[str]	None	Provide a prompt for the parser model
output_model	Optional[Model]	None	Provide an output model to parse the response from the team
output_model_prompt	Optional[str]	None	Provide a prompt for the output model
use_json_mode	bool	False	If output_schema is set, sets the response mode of the model
parse_response	bool	True	If True, parse the response
enable_agentic_memory	bool	False	Enable the team to manage memories of the user
enable_user_memories	bool	False	If True, the team creates/updates user memories at the end of runs
add_memories_to_context	Optional[bool]	None	If True, the team adds a reference to the user memories in the response
enable_session_summaries	bool	False	If True, the team creates/updates session summaries at the end of runs
session_summary_manager	Optional[SessionSummaryManager]	None	Session summary manager
add_session_summary_to_context	Optional[bool]	None	If True, the team adds session summaries to the context
add_history_to_context	bool	False	Add messages from the chat history to the messages list sent to the Model. This only applies to the team leader, not the members.
num_history_runs	int	3	Number of historical runs to include in the messages
add_team_history_to_members	bool	False	If True, send the team-level history to the members, not the agent-level history
num_team_history_runs	int	3	Number of historical runs to include in the messages sent to the members
search_session_history	Optional[bool]	False	If True, adds a tool to allow searching through previous sessions
num_history_sessions	Optional[int]	None	Number of past sessions to include in the search
read_team_history	bool	False	If True, adds a tool to allow the team to read the team history (deprecated and will be removed in a future version)
read_chat_history	bool	False	If True, adds a tool to allow the team to read the chat history
metadata	Optional[Dict[str, Any]]	None	Metadata stored with this team
reasoning	bool	False	Enable reasoning for the team
reasoning_model	Optional[Model]	None	Model to use for reasoning
reasoning_agent	Optional[Agent]	None	Agent to use for reasoning
reasoning_min_steps	int	1	Minimum number of reasoning steps
reasoning_max_steps	int	10	Maximum number of reasoning steps
stream	Optional[bool]	None	Stream the response from the Team
stream_events	bool	False	Stream the intermediate steps from the Team
stream_member_events	bool	True	Stream the member events from the Team members
store_events	bool	False	Store the events from the Team
events_to_skip	Optional[List[Union[RunEvent, TeamRunEvent]]]	None	List of events to skip from the Team
store_member_responses	bool	False	Store member agent runs inside the team’s RunOutput
debug_mode	bool	False	Enable debug logs
debug_level	Literal[1, 2]	1	Debug level: 1 = basic, 2 = detailed
show_members_responses	bool	False	Enable member logs - Sets the debug_mode for team and members
retries	int	0	Number of retries to attempt
delay_between_retries	int	1	Delay between retries (in seconds)
exponential_backoff	bool	False	Exponential backoff: if True, the delay between retries is doubled each time
telemetry	bool	True	Log minimal telemetry for analytics

​

Functions

​

run

Run the team. Parameters:

• input (Union[str, List, Dict, Message, BaseModel, List[Message]]): The input to send to the team
• stream (Optional[bool]): Whether to stream the response
• stream_events (Optional[bool]): Whether to stream intermediate steps
• session_id (Optional[str]): Session ID to use
• session_state (Optional[Dict[str, Any]]): Session state to use. By default, merged with the session state in the db.
• user_id (Optional[str]): User ID to use
• retries (Optional[int]): Number of retries to attempt
• audio (Optional[Sequence[Audio]]): Audio files to include
• images (Optional[Sequence[Image]]): Image files to include
• videos (Optional[Sequence[Video]]): Video files to include
• files (Optional[Sequence[File]]): Files to include
• knowledge_filters (Optional[Dict[str, Any]]): Knowledge filters to apply
• add_history_to_context (Optional[bool]): Whether to add history to context
• add_dependencies_to_context (Optional[bool]): Whether to add dependencies to context
• add_session_state_to_context (Optional[bool]): Whether to add session state to context
• dependencies (Optional[Dict[str, Any]]): Dependencies to use for this run
• metadata (Optional[Dict[str, Any]]): Metadata to use for this run
• debug_mode (Optional[bool]): Whether to enable debug mode
• yield_run_response (bool): Whether to yield the run response (only for streaming)

Returns:

• Union[TeamRunOutput, Iterator[Union[RunOutputEvent, TeamRunOutputEvent]]]: Either a TeamRunOutput or an iterator of events, depending on the stream parameter

​

arun

Run the team asynchronously. Parameters:

• input (Union[str, List, Dict, Message, BaseModel, List[Message]]): The input to send to the team
• stream (Optional[bool]): Whether to stream the response
• stream_events (Optional[bool]): Whether to stream intermediate steps
• session_id (Optional[str]): Session ID to use
• session_state (Optional[Dict[str, Any]]): Session state to use. By default, merged with the session state in the db.
• user_id (Optional[str]): User ID to use
• retries (Optional[int]): Number of retries to attempt
• audio (Optional[Sequence[Audio]]): Audio files to include
• images (Optional[Sequence[Image]]): Image files to include
• videos (Optional[Sequence[Video]]): Video files to include
• files (Optional[Sequence[File]]): Files to include
• knowledge_filters (Optional[Dict[str, Any]]): Knowledge filters to apply
• add_history_to_context (Optional[bool]): Whether to add history to context
• add_dependencies_to_context (Optional[bool]): Whether to add dependencies to context
• add_session_state_to_context (Optional[bool]): Whether to add session state to context
• dependencies (Optional[Dict[str, Any]]): Dependencies to use for this run
• metadata (Optional[Dict[str, Any]]): Metadata to use for this run
• debug_mode (Optional[bool]): Whether to enable debug mode
• yield_run_response (bool): Whether to yield the run response (only for streaming)

Returns:

• Union[TeamRunOutput, AsyncIterator[Union[RunOutputEvent, TeamRunOutputEvent]]]: Either a TeamRunOutput or an async iterator of events, depending on the stream parameter

​

print_response

Run the team and print the response. Parameters:

• input (Union[List, Dict, str, Message, BaseModel, List[Message]]): The input to send to the team
• stream (Optional[bool]): Whether to stream the response
• stream_events (Optional[bool]): Whether to stream intermediate steps
• session_id (Optional[str]): Session ID to use
• session_state (Optional[Dict[str, Any]]): Session state to use. By default, merged with the session state in the db.
• user_id (Optional[str]): User ID to use
• show_message (bool): Whether to show the message (default: True)
• show_reasoning (bool): Whether to show reasoning (default: True)
• show_full_reasoning (bool): Whether to show full reasoning (default: False)
• console (Optional[Any]): Console to use for output
• tags_to_include_in_markdown (Optional[Set[str]]): Tags to include in markdown content
• audio (Optional[Sequence[Audio]]): Audio files to include
• images (Optional[Sequence[Image]]): Image files to include
• videos (Optional[Sequence[Video]]): Video files to include
• files (Optional[Sequence[File]]): Files to include
• markdown (Optional[bool]): Whether to format output as markdown
• knowledge_filters (Optional[Dict[str, Any]]): Knowledge filters to apply
• add_history_to_context (Optional[bool]): Whether to add history to context
• dependencies (Optional[Dict[str, Any]]): Dependencies to use for this run
• add_dependencies_to_context (Optional[bool]): Whether to add dependencies to context
• add_session_state_to_context (Optional[bool]): Whether to add session state to context
• metadata (Optional[Dict[str, Any]]): Metadata to use for this run
• debug_mode (Optional[bool]): Whether to enable debug mode

​

aprint_response

Run the team and print the response asynchronously. Parameters:

• input (Union[List, Dict, str, Message, BaseModel, List[Message]]): The input to send to the team
• stream (Optional[bool]): Whether to stream the response
• stream_events (Optional[bool]): Whether to stream intermediate steps
• session_id (Optional[str]): Session ID to use
• session_state (Optional[Dict[str, Any]]): Session state to use. By default, merged with the session state in the db.
• user_id (Optional[str]): User ID to use
• show_message (bool): Whether to show the message (default: True)
• show_reasoning (bool): Whether to show reasoning (default: True)
• show_full_reasoning (bool): Whether to show full reasoning (default: False)
• console (Optional[Any]): Console to use for output
• tags_to_include_in_markdown (Optional[Set[str]]): Tags to include in markdown content
• audio (Optional[Sequence[Audio]]): Audio files to include
• images (Optional[Sequence[Image]]): Image files to include
• videos (Optional[Sequence[Video]]): Video files to include
• files (Optional[Sequence[File]]): Files to include
• markdown (Optional[bool]): Whether to format output as markdown
• knowledge_filters (Optional[Dict[str, Any]]): Knowledge filters to apply
• add_history_to_context (Optional[bool]): Whether to add history to context
• dependencies (Optional[Dict[str, Any]]): Dependencies to use for this run
• add_dependencies_to_context (Optional[bool]): Whether to add dependencies to context
• add_session_state_to_context (Optional[bool]): Whether to add session state to context
• metadata (Optional[Dict[str, Any]]): Metadata to use for this run
• debug_mode (Optional[bool]): Whether to enable debug mode

​

cli_app

Run an interactive command-line interface to interact with the team. Parameters:

• input (Optional[str]): The input to send to the team
• user (str): Name for the user (default: “User”)
• emoji (str): Emoji for the user (default: “:sunglasses:”)
• stream (bool): Whether to stream the response (default: False)
• markdown (bool): Whether to format output as markdown (default: False)
• exit_on (Optional[List[str]]): List of commands to exit the CLI
• **kwargs: Additional keyword arguments

​

acli_app

Run an interactive command-line interface to interact with the team asynchronously. Parameters:

• input (Optional[str]): The input to send to the team
• session_id (Optional[str]): Session ID to use
• user_id (Optional[str]): User ID to use
• user (str): Name for the user (default: “User”)
• emoji (str): Emoji for the user (default: “:sunglasses:”)
• stream (bool): Whether to stream the response (default: False)
• markdown (bool): Whether to format output as markdown (default: False)
• exit_on (Optional[List[str]]): List of commands to exit the CLI
• **kwargs: Additional keyword arguments

​

get_session_summary

Get the session summary for the given session ID. Parameters:

• session_id (Optional[str]): Session ID to use (if not provided, the current session is used)

Returns:

• Session summary for the given session

​

get_user_memories

Get the user memories for the given user ID. Parameters:

• user_id (Optional[str]): User ID to use (if not provided, the current user is used)

Returns:

• Optional[List[UserMemory]]: The user memories

​

add_tool

Add a tool to the team. Parameters:

• tool (Union[Toolkit, Callable, Function, Dict]): The tool to add

​

set_tools

Replace the tools of the team. Parameters:

• tools (List[Union[Toolkit, Callable, Function, Dict]]): The tools to set

​

cancel_run

Cancel a run by run ID. Parameters:

• run_id (str): The run ID to cancel

Returns:

• bool: True if the run was successfully cancelled

​

get_run_output

Get the run output for the given run ID. Parameters:

• run_id (str): The run ID
• session_id (Optional[str]): Session ID to use

Returns:

• Optional[Union[TeamRunOutput, RunOutput]]: The run output

​

get_last_run_output

Get the last run output for the session. Parameters:

• session_id (Optional[str]): Session ID to use (if not provided, the current session is used)

Returns:

• Optional[TeamRunOutput]: The last run output

​

get_session

Get the session for the given session ID. Parameters:

• session_id (Optional[str]): Session ID to use (if not provided, the current session is used)

Returns:

• Optional[TeamSession]: The team session

​

save_session

Save a session to the database. Parameters:

• session (TeamSession): The session to save

​

asave_session

Save a session to the database asynchronously. Parameters:

• session (TeamSession): The session to save

​

delete_session

Delete a session. Parameters:

• session_id (str): Session ID to delete

​

get_session_name

Get the session name for the given session ID. Parameters:

• session_id (Optional[str]): Session ID to use (if not provided, the current session is used)

Returns:

• str: The session name

​

set_session_name

Set the session name. Parameters:

• session_id (Optional[str]): Session ID to use (if not provided, the current session is used)
• autogenerate (bool): Whether to autogenerate the name
• session_name (Optional[str]): The name to set

Returns:

• TeamSession: The updated session

​

get_session_state

Get the session state for the given session ID. Parameters:

• session_id (Optional[str]): Session ID to use (if not provided, the current session is used)

Returns:

• Dict[str, Any]: The session state

​

update_session_state

Update the session state for the given session ID. Parameters:

• session_id (str): Session ID to use
• session_state_updates (Dict[str, Any]): The session state keys and values to update. Overwrites the existing session state.

Returns:

• Dict[str, Any]: The updated session state

​

get_session_metrics

Get the session metrics for the given session ID. Parameters:

• session_id (Optional[str]): Session ID to use (if not provided, the current session is used)

Returns:

• Optional[Metrics]: The session metrics

​

get_chat_history

Get the chat history for the given session ID. Parameters:

• session_id (Optional[str]): Session ID to use (if not provided, the current session is used)

Returns:

• List[Message]: The chat history

​

get_messages_for_session

Get the messages for the given session ID. Parameters:

• session_id (Optional[str]): Session ID to use (if not provided, the current session is used)

Returns:

• List[Message]: The messages for the session