WorkflowSession

WorkflowSession Attributes

Parameter	Type	Default	Description
`session_id`	`str`	Required	Session UUID - this is the workflow_session_id that gets set on agents/teams
`user_id`	`Optional[str]`	`None`	ID of the user interacting with this workflow
`workflow_id`	`Optional[str]`	`None`	ID of the workflow that this session is associated with
`workflow_name`	`Optional[str]`	`None`	Workflow name
`runs`	`Optional[List[WorkflowRunOutput]]`	`None`	List of all workflow runs in the session
`session_data`	`Optional[Dict[str, Any]]`	`None`	Session Data: session_name, session_state, images, videos, audio
`workflow_data`	`Optional[Dict[str, Any]]`	`None`	Workflow configuration and metadata
`metadata`	`Optional[Dict[str, Any]]`	`None`	Metadata stored with this workflow session
`created_at`	`Optional[int]`	`None`	The unix timestamp when this session was created
`updated_at`	`Optional[int]`	`None`	The unix timestamp when this session was last updated

WorkflowSession Methods

`upsert_run(run: WorkflowRunOutput)`

Adds a WorkflowRunOutput to the runs list. If a run with the same run_id already exists, it updates the existing run.

`get_run(run_id: str) -> Optional[WorkflowRunOutput]`

Retrieves a specific workflow run by its run_id.

`get_workflow_history(num_runs: Optional[int] = None) -> List[Tuple[str, str]]`

Gets workflow history as structured data (input, response pairs).

num_runs: Number of recent runs to include. If None, returns all available history.

Returns a list of tuples containing (input, response) pairs from completed workflow runs only.

`get_workflow_history_context(num_runs: Optional[int] = None) -> Optional[str]`

Gets formatted workflow history context for steps.

num_runs: Number of recent runs to include. If None, returns all available history.

Returns a formatted string containing the workflow history wrapped in <workflow_history_context> tags, suitable for providing context to workflow steps.

`get_messages(...) -> List[Message]`

Returns the messages belonging to the session that fit the given criteria. Note: Either agent_id or team_id must be provided, but not both. Parameters:

agent_id (Optional[str]): The ID of the agent to get the messages for
team_id (Optional[str]): The ID of the team to get the messages for
last_n_runs (Optional[int]): The number of runs to return messages from, counting from the latest. Defaults to all runs
limit (Optional[int]): The number of messages to return, counting from the latest. Defaults to all messages
skip_roles (Optional[List[str]]): Skip messages with these roles
skip_statuses (Optional[List[RunStatus]]): Skip messages with these statuses
skip_history_messages (bool): Skip messages that were tagged as history in previous runs. Defaults to True
skip_member_messages (bool): Skip messages created by members of the team. Defaults to True

Returns:

List[Message]: The messages for the session

`get_chat_history(last_n_runs: Optional[int] = None) -> List[WorkflowChatInteraction]`

Return a list of WorkflowChatInteraction objects containing the input and output for each run in the session. Parameters:

last_n_runs (Optional[int]): Number of recent runs to include. If None, all runs will be considered

Returns:

List[WorkflowChatInteraction]: The chat history for the session as a list of input/output interactions

`to_dict() -> Dict[str, Any]`

Converts the WorkflowSession to a dictionary for storage, serializing runs to dictionaries.

`from_dict(data: Mapping[str, Any]) -> Optional[WorkflowSession]`

Creates a WorkflowSession from a dictionary, deserializing runs from dictionaries back to WorkflowRunOutput objects.

Agno SDK Reference

AgentOS API Reference

WorkflowSession