agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Why it matters
Separating the context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → needed for one action from the state needed to continue a workstream is a directly copyable answer to context rot on long-horizon tasks; the orchestrator here cannot execute or edit, only dispatch threads that return structured episodes.
