Context Window
The context window is the maximum amount of text, measured in tokens, a language model can take into account in a single request.
Anything beyond that limit is truncated or ignored. A larger window allows more documents, a longer conversation history, or more complete website content to be provided at once.
For an AI agent reading a site to answer a question, a page that's too long or poorly structured risks exceeding this limit or diluting the passages that actually matter.