Session state and conversation memory

Real apps need memory that survives reloads, multiple users, and budget caps. Streamlit gives you the first tools to learn this properly.

A diary on your nightstand vs a journal app that syncs. Both are memory. One is fragile, one is durable.

st.session_state lives in memory per browser tab. Refresh = gone. For real persistence:

1. Save chat history to a file (json) keyed by user.
2. Save to a database (Supabase, SQLite, Firebase).
3. Use Streamlit's st.experimental_user for SSO-style auth.

Memory strategies from Module 3.4 (full, window, summary, retrieval) all apply here.

Add a 10-message rolling window:

MAX_HISTORY = 20  # 10 user + 10 assistant
if len(st.session_state.messages) > MAX_HISTORY + 1:  # +1 for system
    st.session_state.messages = (
        [st.session_state.messages[0]]  # keep system
        + st.session_state.messages[-MAX_HISTORY:]
    )

Add reset and export:

col1, col2 = st.sidebar.columns(2)
if col1.button("Clear"):
    st.session_state.messages = []
    st.rerun()
if col2.download_button("Export", data=str(st.session_state.messages), file_name="chat.json"):
    pass