Sessions

Product agents use sessions to keep each conversation thread separate and continue it across requests. A stable session_id groups related runs, while user_id associates the thread with the person using your product.

support_agent.py

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIResponses

agent = Agent(
    model=OpenAIResponses(id="gpt-5.4-mini"),
    db=SqliteDb(db_file="tmp/support.db"),
    add_history_to_context=True,
    num_history_runs=3,
)

agent.print_response(
    "My order number is ORD-123.",
    user_id="customer-42",
    session_id="support-thread-7",
)

agent.print_response(
    "Which order are we discussing?",
    user_id="customer-42",
    session_id="support-thread-7",
)

The database stores both runs under support-thread-7. On the second run, add_history_to_context=True loads messages from the same session into the model context.

IDs and Persistence

Value	Purpose	Generation
`run_id`	Identifies one execution	Agno generates a new value for every run unless you provide one
`session_id`	Groups related runs into one thread	Agno generates one when the Agent instance first runs without a supplied value, then reuses it on that instance
`user_id`	Associates a run and session with a user	Your application supplies it, or the agent uses its configured default

An ID labels a run or thread. A configured database provides durable storage.

Persistence and Model Context

Session storage and chat history serve separate purposes:

Configuration	Effect
`db=...`	Persists session records, runs, state, and stored messages
`add_history_to_context=True`	Adds messages from previous runs in the session to the next model request
`num_history_runs=N`	Limits history by run count
`num_history_messages=N`	Limits history by message count
`session_state={...}`	Stores application state with the session

add_history_to_context defaults to False. Configure it when the model needs conversational continuity. See Chat History for message selection and storage controls.

Multi-User Applications

Use IDs from your application instead of sharing one generated session across customers:

Product concept	Agno value
Account or customer	`user_id`
Chat thread, ticket, or workspace conversation	`session_id`
One request and response cycle	`run_id`

A user can have multiple session IDs, such as separate support tickets or chat tabs. Reuse a session ID only for runs that belong to the same thread.

Workflow Sessions

Agent and team sessions store conversational runs and messages. Workflow sessions track pipeline executions with their inputs, outputs, and state. See Workflow Sessions for workflow-specific behavior.

Next Steps

Session Management

Assign IDs and manage agent and team sessions.

History Management

Control which previous messages enter model context.

Session Summaries

Condense long conversations to manage context size.

Get Started

Basics

Advanced

Production

Providers

Other

Additional Resources

IDs and Persistence

Persistence and Model Context

Multi-User Applications

Workflow Sessions

Next Steps

Session Management

History Management

Session Summaries

​IDs and Persistence

​Persistence and Model Context

​Multi-User Applications

​Workflow Sessions

​Next Steps

Session Management

History Management

Session Summaries

IDs and Persistence

Persistence and Model Context

Multi-User Applications

Workflow Sessions

Next Steps