A knowledge worker is explaining context-window basics to a teammate.

Answer B is correct. A context window is the bounded amount of information that a model can consider when generating a response. Depending on the Claude interface or implementation, this can include the current user message, earlier messages in the active conversation, system instructions, uploaded documents, tool results, and other supplied content. The capacity is finite and is normally measured in tokens rather than words or pages.

Option A incorrectly defines the context window as only the information the model considers most relevant. Relevance selection or retrieval can determine which materials are placed into the window, but the context window itself is the total bounded processing capacity. Option C incorrectly treats it as unlimited cross-session memory. A model does not automatically receive every previous conversation whenever it responds in a different chat. Any available memory or Project knowledge is a separate feature and must be supplied or retrieved into the active context. Option D is also incorrect because users generally do not configure the context-window size independently for each chat.

When a conversation becomes too long or cluttered, the user may need to summarize essential information, remove irrelevant material, or start a focused new conversation. This preserves relevant context and reduces conflicts between current and obsolete instructions. Anthropic: Context windows