Session Context

Goals, plans, and progress for active sessions.

The Session Context Store captures the current state of a conversation: what's been discussed, what the goal is, and what progress has been made. Unlike other stores that accumulate data, session context is a snapshot that gets replaced on each update.

Aspect	Value
Scope	Per session
Persistence	Session lifetime (replaced on update)
Default mode	Always
Supported modes	Always

Basic Usage

1from kern.agent import Agent
2from kern.db.postgres import PostgresDb
3from kern.learn import LearningMachine
4from kern.models.openai import OpenAIResponses
5
6agent = Agent(
7    model=OpenAIResponses(id="gpt-5.2"),
8    db=PostgresDb(db_url="postgresql+psycopg://ai:ai@localhost:5532/ai"),
9    learning=LearningMachine(session_context=True),
10)
11
12# Session tracks what's being discussed
13agent.print_response(
14    "I'm designing a REST API for a todo app. Should I use PUT or PATCH for updates?",
15    user_id="alice@example.com",
16    session_id="api_design",
17)
18
19# Later in the session, context is maintained
20agent.print_response(
21    "What about the delete endpoint?",
22    user_id="alice@example.com",
23    session_id="api_design",
24)

The agent knows the ongoing context about REST API design.

Summary Mode

Default behavior. Captures the essence of the conversation without detailed planning.

1from kern.learn import LearningMachine, SessionContextConfig
2
3agent = Agent(
4    model=OpenAIResponses(id="gpt-5.2"),
5    db=db,
6    learning=LearningMachine(
7        session_context=SessionContextConfig(),
8    ),
9)

What gets captured: what's being worked on, key decisions made, current state, open questions.

Planning Mode

Enable planning to track goals, plan steps, and progress.

1from kern.learn import LearningMachine, SessionContextConfig
2
3agent = Agent(
4    model=OpenAIResponses(id="gpt-5.2"),
5    db=db,
6    learning=LearningMachine(
7        session_context=SessionContextConfig(enable_planning=True),
8    ),
9)
10
11agent.print_response(
12    "Help me deploy a Python app to production. Give me the steps.",
13    user_id="alice@example.com",
14    session_id="deploy_app",
15)
16
17# Later, progress is tracked
18agent.print_response(
19    "Done with step 1. What's next?",
20    user_id="alice@example.com",
21    session_id="deploy_app",
22)

Data Model

Field	Description
`session_id`	Unique session identifier
`user_id`	User this session belongs to
`summary`	What's been discussed
`goal`	What user is trying to accomplish (planning mode)
`plan`	Steps to achieve goal (planning mode)
`progress`	Completed steps (planning mode)
`created_at`	When created
`updated_at`	Last update

Accessing Session Context

1lm = agent.get_learning_machine()
2
3context = lm.session_context_store.get(session_id="api_design")
4if context:
5    print(f"Summary: {context.summary}")
6    if context.goal:
7        print(f"Goal: {context.goal}")
8
9# Debug output
10lm.session_context_store.print(session_id="api_design")

Context Injection

Session context is injected into the system prompt:

1<session_context>
2Summary: Helping user design a REST API for a todo app. Discussed resource naming conventions. Currently exploring HTTP methods for CRUD operations.
3
4Goal: Design complete REST API for todo application
5
6Plan:
7  1. Define resource endpoints
8  2. Choose HTTP methods for each operation
9  3. Design request/response schemas
10  4. Add authentication
11
12Completed:
13  ✓ Define resource endpoints
14</session_context>

When to Use

Session context is essential when:

Message history gets truncated: long conversations lose early context
Sessions are resumed: user returns after a break
Complex multi-step tasks: track progress through long workflows
Handoffs: another agent or human needs to understand the state

Combining with Other Stores

Session context works well alongside user-level stores:

1from kern.learn import LearningMachine, SessionContextConfig
2
3agent = Agent(
4    model=OpenAIResponses(id="gpt-5.2"),
5    db=db,
6    learning=LearningMachine(
7        user_profile=True,                                  # Who the user is
8        session_context=SessionContextConfig(enable_planning=True),  # Current state
9    ),
10)

Long-term user knowledge plus short-term session state.