Module 6 — L3.2 Token counting and cost

The code as it stands at the end of this lesson, with the dataset it reads.
The code files are assembled from that lesson's own code blocks, so they
match what the lesson asks you to write. The dataset is the same one the
lesson uses.

The escalation pattern and the token guardrail appear later in the lesson as patches rather than whole functions, so they are not in this snapshot. L3.3 carries the guardrail.

Set up, then run:

  python -m venv .venv
  source .venv/bin/activate      # Windows: .venv\Scripts\activate
  pip install -r requirements.txt
  AUTO_APPROVE=1 python pipeline.py
  # Windows PowerShell: $env:AUTO_APPROVE=1; python pipeline.py

You are not expected to download this to keep up. Type the code out if that
helps you learn it; take this if you would rather read and run it.
