Hi,
I’m running level_3_agent example script with minimal changes (only changed model to point to Ollama instance). When runnning the code, it outputs everything fine but ends up just short of the final response. I see Message block, tool calls block, message block, then multiple resasoning steps, then final tool calls. There is no output message
Code:
memory = Memory(
model=Ollama(id="qwen3:8b", host="http://localhost:11434"),
db=SqliteMemoryDb(table_name="user_memories", db_file="tmp/agent.db"),
delete_memories=True,
clear_memories=True,
)
agent = Agent(
model=Ollama(id="qwen3:8b", host="http://localhost:11434"),
tools=[
ReasoningTools(add_instructions=True),
YFinanceTools(stock_price=True, analyst_recommendations=True, company_info=True, company_news=True),
],
user_id="ava",
instructions=[
"Use tables to display data.",
"Include sources in your response.",
"Only include the report in your response. No other text.",
],
memory=memory,
enable_agentic_memory=True,
markdown=True,
)
if __name__ == "__main__":
agent.print_response(
"My favorite stocks are NVIDIA and TSLA",
stream=True,
show_full_reasoning=False,
stream_intermediate_steps=False,
)
agent.print_response(
"Can you compare my favorite stocks?",
stream=False,
show_full_reasoning=False,
stream_intermediate_steps=False,
)
Terminal output in Powershell Windows:
In the previous level 2 example script. it also exhibited similar behavior. I had to change the agent.print_response() call to be two calls:
response = agent.run("What is Agno?")
pprint_run_response(response, markdown=True)
Then I get the output. Running agent.print_response("What is Agno?, stream=True)
doesn’t work either