Day 18 Theory — State, Sessions, Persistence and Memory

Lesson Overview

This is the applied companion for Day 18. Read DAY_18_THEORY.md first for the beginner-first teaching of State, Sessions, Persistence and Memory. Then use the real service-desk-day-18/ project to trace, run, debug, and explain the concept.

Service Desk Alignment

Day 18 adds State, Sessions, Persistence and Memory to the running Service Desk. Start with session_manager.py, agent.py, storage.py, serializer.py, models.py, then follow imports and tests to identify the actual runtime path.

Why This Topic Matters

The theory chapter explains why State, Sessions, Persistence and Memory is needed. Here the goal is evidence: identify where the capability is implemented, what observable behavior changes, and how the repository proves both success and failure behavior.

System Architecture

This is a repository surface map, not a claim that modules call each other in the displayed order. The modules are ranked by relevance to today's theory.

graph LR
    T[Day 18: State, Sessions, Persistence and Memory]
    T --> M1[session_manager.py]
    T --> M2[agent.py]
    T --> M3[storage.py]
    T --> M4[serializer.py]
    T --> M5[models.py]

Follow imports and tests to discover the actual runtime flow.

Repository Implementation Map

Use the real Day 18 repository, not a fabricated sample, to connect theory to implementation.

Theory concepts to locate:

• Why agents need explicit state
• State is not the same as memory
• In-memory state versus durable state
• Session identity

Most relevant implementation modules first:

• service_desk/session_manager.py
• service_desk/agent.py
• service_desk/storage.py
• service_desk/serializer.py
• service_desk/models.py

Follow imports/calls from the relevant module and confirm behavior in tests. Record input → mechanism → observable output/state → failure evidence.

Code Walkthrough & Mechanics

Read session_manager.py, agent.py, storage.py, serializer.py, models.py with these theory sections beside you:

• Why agents need explicit state — locate its implementation and evidence.
• State is not the same as memory — locate its implementation and evidence.
• In-memory state versus durable state — locate its implementation and evidence.
• Session identity — locate its implementation and evidence.
• Conversation history is only one kind of state — locate its implementation and evidence.

For each concept identify the real function/class/protocol boundary, its input/state, its observable result, and the assertion in tests/test_state_persistence.py that proves the behavior. If a concept has no implementation or evidence, record that as a gap rather than inventing one.

Common Mistakes & Debugging Guidance

Use the theory—not generic timeout or .env advice—to decide what can fail today.

Failure lens: revisit Session identity, Conversation history is only one kind of state.

• Reproduce the smallest case that violates one of those expectations.
• Trace the real Day 18 modules until you find the first incorrect state/output/decision.
• Use tests/test_state_persistence.py as executable evidence.
• Add a regression test if the failure is not already represented.
• Fix the smallest responsible boundary and rerun the relevant test before the full suite.

Your debugging explanation must name the topic-specific invariant that failed, not merely say “an exception occurred.”

Practical Lab Instructions

1. Summarize these theory ideas before opening the implementation:
   • Why agents need explicit state
   • State is not the same as memory
   • In-memory state versus durable state
   • Session identity
2. Inspect the most relevant real Day 18 modules first:
   • service_desk/session_manager.py
   • service_desk/agent.py
   • service_desk/storage.py
   • service_desk/serializer.py
   • service_desk/models.py
3. Inspect the automated evidence:
   • tests/test_state_persistence.py
4. Establish the baseline:

   cd service-desk-day-18
   PYTHONPATH=. pytest tests/test_state_persistence.py -q
   

5. Trace one theory concept through the actual nested modules and tests.
6. Run one success case and record input → mechanism → observable result.
7. Exercise one topic-specific failure/boundary case and name the invariant that protects the system.
8. Re-run the relevant tests and explain theory → implementation → evidence.

Done when: another student can reproduce your trace without relying on an invented sample.

Key Takeaways

1. Be able to explain Why agents need explicit state and point to its implementation/evidence in Day 18.
2. Be able to explain State is not the same as memory and point to its implementation/evidence in Day 18.
3. Be able to explain In-memory state versus durable state and point to its implementation/evidence in Day 18.

Knowledge Check & Scenario Questions

1. Concept: Using Why agents need explicit state, explain the engineering problem Day 18 is solving without naming a framework as the answer.
2. Mechanism: How does State is not the same as memory appear in the real project? Start from service_desk/session_manager.py and name the observable state/output/event that changes.
3. Failure: For In-memory state versus durable state, describe one incorrect implementation or boundary condition and the evidence you would expect in tests/test_state_persistence.py.
4. Design review: Which assumption in today's design would you verify before reusing this implementation in a different production system?

Official References

• SQLite Official Documentation: https://www.sqlite.org/docs.html
• LangGraph Persistence & Checkpointers: https://langchain-ai.github.io/langgraph/concepts/persistence/