Context editing / compaction
Context editing (sometimes called compaction) is the general practice of programmatically trimming, summarizing, or removing older or less-relevant content from a conversation's context so a long-running session can continue without exceeding the context window.
A common approach
Once context usage crosses a threshold, older tool results or conversation turns are summarized into a shorter form (or dropped entirely if no longer relevant) and replaced in place, freeing budget for new turns while preserving the gist of what came before.
Trade-offs
Summarizing or dropping older context saves budget but risks losing detail the model might need later -- a fact mentioned once early in a session and then discarded can resurface as a gap several turns later if it was compacted away too aggressively. Effective context editing tends to preserve verbatim the pieces most likely to be needed again (decisions made, constraints stated, file paths, IDs) while more freely summarizing narrative or exploratory content that was only useful in the moment.
Phrased generally rather than tied to a specific mirrored document or API field name -- no single canonical doc for this exact term was cited verbatim this session.