Context Compaction

Context Compaction / Compression

Definition

The process of summarizing or pruning a conversation history to stay within the LLM's context window while preserving essential information. Critical for long-running agents — without compaction, sessions hit the context limit and lose coherence.

Examples in the Wild

  • Example 1:OpenClaw summarizes old conversation turns into a compact memory block
  • Example 2:An agent distills a 100k-token session into a 5k summary for context continuity