What's in the context window
The idea: Each turn the model sees one bundle — system prompt, tool definitions, your files, the whole chat so far, plus room reserved for its reply — and it all must fit in a fixed context window.
What you'll be able to do: You can list what occupies the context window and explain why it's a fixed budget, not memory.
The problem it solves: Why does the assistant sometimes 'forget' what you told it earlier?
Builds on: Context window & KV cache
← The harness: the loop, made real · Next: Managing the context →
All lessons