Skip to main content

Context

Everything the model can see when it answers. What fills the window, what to do when it runs out, and the two ways of putting outside knowledge in front of a model: retrieval and memory.

📄️Context management and compaction

As an interactive session continues, the message history steadily expands until it threatens to exceed the model's context window. The underlying model cannot decide what to keep or discard when this happens. That responsibility falls entirely to the client harness orchestrating the conversation. How that software manages information at the context boundary determines whether an agent successfully finishes a long task or quietly forgets its original instructions halfway through.