Type Your Message Models

A chat message is a small, fixed shape - and the shape is exactly where the bugs hide. Model it as a dataclass with type hints.

Validator

⏱ 0:00

IDLE — checks run live as you type commands; submit when done

01Requirements

live checks

4 steps

01
Create the source directory
Keep the library code separate from the tests - src layout makes imports unambiguous.
mkdir -p ~/ai-lab/src
02
Write the message model
A dataclass generates the constructor for you. The role is a str and the content is a str - say so in the annotations.
echo 'from dataclasses import dataclass\n\n@dataclass\nclass Message:\n role: str\n content: str' > ~/ai-lab/src/messages.py
03
Add a helper function
The arrow annotation tells a reader - and your editor - what the function returns. Typing is documentation that cannot go stale.
echo '\ndef user_message(text: str) -> Message:\n return Message(role="user", content=text)' >> ~/ai-lab/src/messages.py
04
Verify and submit
cat the module, then submit for validation.
cat ~/ai-lab/src/messages.py

0 of 3 revealed

Take a hint without losing the lab — each one points at the thing to look at, not at the answer.

guides, never solves

Tell me what you're stuck on — I'll nudge, not solve. Which requirement are you looking at?

saved locally in this browser

learner@lab — ubuntu:24.04

Session is disposable

↑/↓ recalls commands · Ctrl+Enter submits · type help for the command list

← Previous lab

Write a Pytest Suite

Python

Next lab →

Set a Token Budget

LLM Fundamentals