Fixes sessions that stopped at 200K tokens with a 1M-context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → error (now compacts and continues), multi-agentUsing several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.Full definition → MCP connection timing, and duplicate SubagentStop agent hookA script the harness runs automatically at a fixed point in an agent's loop — before a tool call, after an edit, on session start.Full definition → runs. Adds idle-hold flags for self-hosted runners.
Terms in this piece · Glossary
context compaction — Summarizing an agent's earlier conversation to free room in the context window so a long session can keep going.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.
agent hook — A script the harness runs automatically at a fixed point in an agent's loop — before a tool call, after an edit, on session start.
