session_summary_limits.py
"""
Session Summary with Limits
============================
Demonstrates how to limit the conversation history sent to the summary model
using `last_n_runs` and `conversation_limit` on SessionSummaryManager.
This is useful for long-running sessions where the full conversation would
exceed the summary model's context window.
"""
from agno.agent.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.openai import OpenAIChat
from agno.session.summary import SessionSummaryManager
# ---------------------------------------------------------------------------
# Setup
# ---------------------------------------------------------------------------
db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
db = PostgresDb(db_url=db_url, session_table="sessions")
# ---------------------------------------------------------------------------
# Option 1: Limit by number of recent runs
# Only the last 5 runs are included when generating the summary.
# ---------------------------------------------------------------------------
summary_manager_by_runs = SessionSummaryManager(
model=OpenAIChat(id="gpt-4o-mini"),
last_n_runs=5,
)
agent_by_runs = Agent(
model=OpenAIChat(id="gpt-4o"),
db=db,
session_id="summary_limit_runs",
session_summary_manager=summary_manager_by_runs,
add_session_summary_to_context=True,
)
# ---------------------------------------------------------------------------
# Option 2: Limit by total number of messages
# At most 20 messages are included when generating the summary.
# ---------------------------------------------------------------------------
summary_manager_by_messages = SessionSummaryManager(
model=OpenAIChat(id="gpt-4o-mini"),
conversation_limit=20,
)
agent_by_messages = Agent(
model=OpenAIChat(id="gpt-4o"),
db=db,
session_id="summary_limit_messages",
session_summary_manager=summary_manager_by_messages,
add_session_summary_to_context=True,
)
# ---------------------------------------------------------------------------
# Run
# ---------------------------------------------------------------------------
if __name__ == "__main__":
# --- Option 1: Limit by runs ---
print("=== Limiting by last_n_runs ===")
agent_by_runs.print_response("Hi, my name is John and I work at Acme Corp")
agent_by_runs.print_response("We are building a new product for data analytics")
agent_by_runs.print_response("The stack is Python, FastAPI, and PostgreSQL")
agent_by_runs.print_response("Our deadline is end of Q2")
agent_by_runs.print_response(
"Can you summarize what you know about me and my project?"
)
summary = agent_by_runs.get_session_summary(session_id="summary_limit_runs")
print("Session summary (by runs):", summary)
# --- Option 2: Limit by message count ---
print("\n=== Limiting by conversation_limit ===")
agent_by_messages.print_response("Hi, my name is Jane and I work at Globex")
agent_by_messages.print_response(
"We are migrating our infrastructure to Kubernetes"
)
agent_by_messages.print_response("The main challenge is stateful services")
agent_by_messages.print_response(
"Can you summarize what you know about me and my project?"
)
summary = agent_by_messages.get_session_summary(session_id="summary_limit_messages")
print("Session summary (by messages):", summary)
Run the Example
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activate
uv venv --python 3.12
.venv\Scripts\activate
Export your OpenAI API key
export OPENAI_API_KEY="your_openai_api_key_here"
$Env:OPENAI_API_KEY="your_openai_api_key_here"
Run PgVector
docker run -d \
-e POSTGRES_DB=ai \
-e POSTGRES_USER=ai \
-e POSTGRES_PASSWORD=ai \
-e PGDATA=/var/lib/postgresql/data/pgdata \
-v pgvolume:/var/lib/postgresql/data \
-p 5532:5432 \
--name pgvector \
agnohq/pgvector:18