option b: cleaner flow but hides 'thinking' after answer succeeds.

app.py

@@ -48,13 +48,13 @@ agent = create_sql_agent(llm, db=db, agent_type="openai-tools", verbose=True)
 def handle_user_input(user_query):
     with history:
         st.session_state.messages.append({"role": "user", "content": user_query})
-        st.chat_message("user").write(user_query)
+        #st.chat_message("user").write(user_query)
 
         with st.chat_message("assistant"):
             st_cb = StreamlitCallbackHandler(st.container())
             response = agent.run(user_query, callbacks=[st_cb])
             st.session_state.messages.append({"role": "assistant", "content": response})
-            st.write(response)
+        #    st.write(response) # thinking is only shown transiently this way
 
 
 if "messages" not in st.session_state:
@@ -63,9 +63,10 @@ if "messages" not in st.session_state:
 main = st.container()
 with main:
     history = st.container(height=400)
-    #with history:
-    #    for msg in st.session_state.messages:
-    #        st.chat_message(msg["role"]).write(msg["content"])  
+    # stores all questions and responses, but not the 'thinking'
+    with history:
+        for msg in st.session_state.messages:
+            st.chat_message(msg["role"]).write(msg["content"])  
     if user_query := st.chat_input(placeholder="Ask me about US Protected areas!"):
         handle_user_input(user_query)