ModelRefs / Conversation History — AI Glossary

Conversation History — AI Glossary

The sequence of prior turns (user and assistant messages) included in the prompt to maintain dialogue coherence. Also called chat history or message history.

Overview

Most chat APIs require the caller to maintain and resend the full conversation history each turn—there is no server-side session state in stateless REST APIs. History management decisions: how many turns to keep, when to summarize old turns, and how to inject retrieved context without exceeding context limits.

Reference details

Topicprompting
Also known aschat history, message history, dialogue history
Last reviewed2026-06-24

Commonly confused with

The history is the data you resend on every request; multi-turn is the property of the interaction that results. Keeping them apart is useful because the problems are different: history is a cost and truncation problem, while multi-turn behaviour is a quality problem — instruction memory, coherence, handling a topic change. Context management is the set of strategies that connect the two.

Continue your research

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

Frequently asked questions

What is Conversation History?

The sequence of prior turns (user and assistant messages) included in the prompt to maintain dialogue coherence.

Is Conversation History the same as chat history?

Yes — chat history, message history, dialogue history are common aliases for Conversation History.

What concepts are related to Conversation History?

Closely related concepts include multi turn, context window, context management.