/

LLMs & Reasoning

/

Context Window

Context Window

/ context-window /

The maximum amount of text (tokens) a language model can consider at once, limiting how much conversation history an agent can use.

The maximum amount of text (tokens) a language model can consider at once, limiting how much conversation history an agent can use.

Why it matters

When conversations outgrow the window, agents forget names, repeat questions, and contradict themselves. Long-call simulations expose exactly where memory falls off.

Related — LLMs & Reasoning