Post by Sydney Runkle

📦 New in LangChain 1.1: dynamically triggered context compaction ➗ Select the proportion of the context window at which you'd like to trigger summarization and the fraction you want to retain. 🌐 This uses LangChain's new model profiles, which expose context window sizes so the middleware can trigger at the right threshold for any model. 🧠 In DeepAgents, we've seen success when compacting at 85% and retaining 10%.