ModelRefs / Context Management — AI Glossary

Context Management — AI Glossary

Strategies for organizing, trimming, and summarizing conversation history and retrieved context to fit within the model's context window.

Overview

Context management includes sliding window (drop oldest turns), summarization (compress old turns via the model), importance scoring (keep high-relevance turns), and RAG injection (replace retrieved chunks at the relevant turn). Critical for long-running agents and multi-session applications where history exceeds context limits.

Reference details

Topic	prompting
Last reviewed	2026-06-24

Example: Every strategy loses something

A sliding window drops the oldest turns, so the model forgets what was agreed early. Summarisation compresses them and loses the exact wording a later turn depends on. Importance scoring keeps what it judges relevant and is wrong sometimes. There is no lossless option — the decision is which loss you can tolerate.

Commonly confused with

Context management is not memory. It decides what to re-send within the window on each call; memory implies persistent state the model can retrieve later. Systems that appear to remember across sessions are doing retrieval, not remembering.

When to use it

Reach for it when:

Conversations or agent runs outlive the context window
Cost scales with history and history keeps growing
Some early context is genuinely load-bearing and must survive

Reach for something else when:

Short interactions that comfortably fit — the machinery adds failure modes
Summarising content you will later need verbatim
Trimming before measuring which turns actually matter

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Context Management — AI Glossary.

Frequently asked questions

What is Context Management?