nodeLLMCompressHistory

inline fun <T> AIAgentSubgraphBuilderBase<*, *>.nodeLLMCompressHistory(name: String? = null, strategy: HistoryCompressionStrategy = HistoryCompressionStrategy.WholeHistory, retrievalModel: LLModel? = null, preserveMemory: Boolean = true): AIAgentNodeDelegate<T, T>(source)

A node that compresses the current LLM prompt (message history) into a summary, replacing messages with a TLDR.

Parameters

name

Optional node name.

strategy

Determines which messages to include in compression.

retrievalModel

An optional LLModel that will be used for retrieval of the facts from memory. By default, the same model will be used as the current one in the agent's strategy.

preserveMemory

Specifies whether to retain message memory after compression.