subagentcontext

Long-running agent sessions (like a Cowork session running for many turns) accumulate tool calls, tool results, and conversation turns that can approach the context window's limit well before the conversation is actually finished.

Strategies include summarizing or compacting older turns, dropping large intermediate tool outputs once they are no longer needed, and being selective about how much of a large file or dataset is read into context at once versus fetched incrementally.

General agentic-session practice; consistent with this repo's own documented practice of scoping reads (e.g. Read tool offset/length) rather than loading entire large files.

created 2026-07-02 08:26:58 · JSON