Even with 1-million token context windows, an agent running for hours will run out of space or suffer from the "Lost in the Middle" phenomenon (where it ignores instructions in the middle of a huge prompt).
When the context grows too large, the Orchestrator pauses the agent, passes the history to a summarization model, and replaces the massive history block with a dense summary.
# Before Compaction: [Msg1 ... Msg100] (50k tokens) # After Compaction: [Summary_Msg, Msg95... Msg100] (2k tokens)