Overview
FlowsAgent extends BaseAgent with Pipecat Flows for structured conversation flows. It manages a FlowManager for node-based conversations with functions, transitions, and actions.
On first activation the flow starts at build_initial_node(). Subsequent activations resume from build_resume_node().
Requires the flows extra:
uv add "pipecat-ai-subagents[flows]"Imported from pipecat_subagents.agents.flows_agent:Configuration
Inherits all parameters fromBaseAgent.
str
required
Unique name for this agent.
Any
required
The context aggregator pair for managing LLM conversation context, forwarded
to
FlowManager.ContextStrategyConfig | None
default:"None"
Optional context strategy forwarded to
FlowManager. See
ContextStrategyConfig.list[FlowsFunctionSchema | FlowsDirectFunction] | None
default:"None"
Optional list of functions available at every node, forwarded to
FlowManager. Methods decorated with
@tool are automatically
included as global functions.bool
default:"False"
Whether the agent starts active. Defaults to
False.tuple[str, ...] | None
default:"()"
Bridge configuration. Defaults to an empty tuple (bridged, accepting all
bridges).
Properties
Inherits all properties fromBaseAgent.
flow_manager
FlowManager instance, available after the pipeline task is created.
Abstract Methods
build_llm
LLMService instance.
build_initial_node
NodeConfig describing the first node of the flow.
Methods
build_resume_node
flow_manager.state. Defaults to restarting from the initial node.
Returns: A NodeConfig for the resumption point.
on_activated
build_initial_node(). On subsequent calls, sets the node from build_resume_node().