session_context_summary.py
"""
Session Context: Summary Mode
=============================
Session Context tracks the current conversation's state:
- What's been discussed
- Key decisions made
- Important context
Summary mode provides lightweight tracking - a running summary without goal/plan structure.
Compare with: 3b_session_context_planning.py for goal-oriented tracking.
"""
from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.learn import LearningMachine
from agno.models.openai import OpenAIResponses
# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
db = PostgresDb(db_url="postgresql+psycopg://ai:ai@localhost:5532/ai")
# Summary mode: Just tracks what's been discussed, no planning overhead.
# Good for general conversations where you want continuity without structure.
agent = Agent(
model=OpenAIResponses(id="gpt-5.5"),
db=db,
instructions="Be very concise. Give brief answers in 1-2 sentences.",
learning=LearningMachine(session_context=True),
markdown=True,
)
# ---------------------------------------------------------------------------
# Run Demo
# ---------------------------------------------------------------------------
if __name__ == "__main__":
user_id = "session@example.com"
session_id = "api_design"
# Turn 1: Start discussion
print("\n" + "=" * 60)
print("TURN 1: Start discussion")
print("=" * 60 + "\n")
agent.print_response(
"I'm designing a REST API for a todo app. PUT or PATCH for updates?",
user_id=user_id,
session_id=session_id,
stream=True,
)
agent.learning_machine.session_context_store.print(session_id=session_id)
# Turn 2: Follow-up
print("\n" + "=" * 60)
print("TURN 2: Follow-up question")
print("=" * 60 + "\n")
agent.print_response(
"What URL structure for that endpoint?",
user_id=user_id,
session_id=session_id,
stream=True,
)
agent.learning_machine.session_context_store.print(session_id=session_id)
# Turn 3: Test recall
print("\n" + "=" * 60)
print("TURN 3: Test context recall")
print("=" * 60 + "\n")
agent.print_response(
"What did we decide?",
user_id=user_id,
session_id=session_id,
stream=True,
)
agent.learning_machine.session_context_store.print(session_id=session_id)
Run the Example
1
Set up your virtual environment
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 openai psycopg-binary sqlalchemy
3
Export your OpenAI API key
export OPENAI_API_KEY="your_openai_api_key_here"
$Env:OPENAI_API_KEY="your_openai_api_key_here"
4
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
5
Run the example
Save the code above as
session_context_summary.py, then run:python session_context_summary.py