How to stream from a Strands Agent Graph

[flowconic]

Has anyone been able to get an Agent Graph to stream the response back?

We are implementing a workflow approach and explored the task, workflow and graph approaches, but we have not been able to get a graph to stream back as a graph doesn't seem to come with the same streaming ability as an Agent?

The reason we are looking at tasks and Graphs is to setup parallel processing of some agents, and then aggregating to a final node which we want to be the one which streams a response back.

e.g. The example posted on Strands 1.0 documentation for a graph is below.

from strands import Agent
from strands.multiagent import GraphBuilder, Swarm

# Create a swarm of research agents
research_agents = [
    Agent(name="medical_researcher", system_prompt="You are a medical research specialist..."),
    Agent(name="technology_researcher", system_prompt="You are a technology research specialist..."),
    Agent(name="economic_researcher", system_prompt="You are an economic research specialist...")
]
research_swarm = Swarm(research_agents)

# Create a single agent node too
analyst = Agent(system_prompt="Analyze the provided research.")

# Create a graph with the swarm as a node
builder = GraphBuilder()
builder.add_node(research_swarm, "research_team")
builder.add_node(analyst, "analysis")
builder.add_edge("research_team", "analysis")

graph = builder.build()

result = graph("Research the impact of AI on healthcare and create a comprehensive report")

# Access the results
print(f"\n{result}")

but graph doesn't expose the same stream_async as an Agent.

import asyncio
from strands import Agent
from strands_tools import calculator

# Initialize our agent without a callback handler
agent = Agent(
    tools=[calculator],
    callback_handler=None
)

# Async function that iterators over streamed agent events
async def process_streaming_response():
    agent_stream = agent.stream_async("Calculate 2+2")
    async for event in agent_stream:
        print(event)

# Run the agent
asyncio.run(process_streaming_response())

Any suggestions would be appreciated.