Cancel Run Persistence

Cancel a team run mid-stream and verify that partial content and messages are preserved in the database.

cancel_run_persistence.py

"""
Cancel Run Persistence
======================
Cancel a team run mid-stream and verify that partial content
and messages are preserved in the database.

Requires: PostgreSQL running on localhost:5532 (see cookbook/scripts/run_pgvector.sh)
"""

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.openai import OpenAIResponses
from agno.run.team import TeamRunEvent
from agno.team import Team

# ---------------------------------------------------------------------------
# Create Members
# ---------------------------------------------------------------------------
researcher = Agent(
    name="Researcher",
    model=OpenAIResponses(id="gpt-5.4"),
    instructions="You are a researcher. Write detailed responses.",
)

# ---------------------------------------------------------------------------
# Create Team
# ---------------------------------------------------------------------------
team = Team(
    name="ResearchTeam",
    members=[researcher],
    model=OpenAIResponses(id="gpt-5.4"),
    db=PostgresDb(db_url="postgresql+psycopg://ai:ai@localhost:5532/ai"),
    store_tool_messages=True,
    store_history_messages=True,
)


# ---------------------------------------------------------------------------
# Run Team
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    run_id = None
    cancelled = False
    content_chunks: list = []

    for event in team.run(
        input=(
            "Write a very long essay about the history of artificial intelligence"
            " with at least 10 major milestones."
        ),
        stream=True,
        stream_events=True,
    ):
        if run_id is None and hasattr(event, "run_id") and event.run_id:
            run_id = event.run_id

        if hasattr(event, "content") and event.content:
            content_chunks.append(event.content)
            print(event.content, end="", flush=True)

        # Cancel after collecting some content
        if len(content_chunks) >= 20 and run_id and not cancelled:
            team.cancel_run(run_id)
            cancelled = True

        if hasattr(event, "event") and event.event == TeamRunEvent.run_cancelled:
            print("\nRun was cancelled")
            break

    # Verify persistence
    print("\n--- Verification ---")
    session = team.get_session(session_id=team.session_id)
    if session and session.runs:
        last_run = session.runs[-1]
        print(f"Status: {last_run.status}")
        print(f"Content length: {len(last_run.content or '')}")
        print(f"Messages: {len(last_run.messages or [])}")

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U agno "psycopg[binary]" openai sqlalchemy
   
3. Export your OpenAI API key

   Mac/Linux

   export OPENAI_API_KEY="your_openai_api_key_here"
   

   $Env:OPENAI_API_KEY="your_openai_api_key_here"
   
4. Run PgVector

   macOS / Linux

   docker run -d \
     -e POSTGRES_DB=ai \
     -e POSTGRES_USER=ai \
     -e POSTGRES_PASSWORD=ai \
     -e PGDATA=/var/lib/postgresql \
     -v pgvolume:/var/lib/postgresql \
     -p 5532:5432 \
     --name pgvector \
     agnohq/pgvector:18
   

   docker run -d `
     -e POSTGRES_DB=ai `
     -e POSTGRES_USER=ai `
     -e POSTGRES_PASSWORD=ai `
     -e PGDATA=/var/lib/postgresql `
     -v pgvolume:/var/lib/postgresql `
     -p 5532:5432 `
     --name pgvector `
     agnohq/pgvector:18
   
5. Run the example

   Save the code above as cancel_run_persistence.py, then run:

   python cancel_run_persistence.py
   

Full source: cookbook/03_teams/14_run_control/cancel_run_persistence.py