LangChain adds ScaleDown models for managing long-running agent context

LangChain has released a langchain-scaledown integration and LangSmith LLM Gateway support for ScaleDown's constrained decoding models.

The integration ships three middlewares for LangChain and Deep Agents that summarize old history, compress large tool results, and extract structured data.

ScaleDown reports its models are 200x faster and 467x cheaper than frontier models on these narrow tasks.