---
type: "raw_signal"
id: "building-long-running-agents-with-scaledown-and-deep-98e484"
slug: "building-long-running-agents-with-scaledown-and-deep-98e484"
title: "Building Long-Running Agents with ScaleDown and Deep Agents"
description: "LangChain announced a `langchain-scaledown` integration for LangChain and Deep Agents, adding middleware for summarizing older conversation history, compressing tool results, and extracting structured data."
retrieval_nugget: "LangChain announced a `langchain-scaledown` integration for LangChain and Deep Agents, adding middleware for summarizing older conversation history, compressing tool results, and extracting structured data."
observed_at: "2026-10-13"
record_date: "2026-10-13"
date_kind: "observed_at"
why_it_matters: "Source: https://www.langchain.com/blog/building-long-running-agents-with-scaledown-and-deep-agents"
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "langchain.com"
topics: []
entities: ["LangChain","ScaleDown","LangSmith","Deep Agents","langchain-scaledown"]
related_patterns: []
source_url: "https://www.langchain.com/blog/building-long-running-agents-with-scaledown-and-deep-agents"
source_urls: ["https://www.langchain.com/blog/building-long-running-agents-with-scaledown-and-deep-agents"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:building-long-running-agents-with-scaledown-and-deep-98e484"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/building-long-running-agents-with-scaledown-and-deep-98e484/","markdown":"https://newruntime.com/signals/building-long-running-agents-with-scaledown-and-deep-98e484.md","json":"https://newruntime.com/signals/building-long-running-agents-with-scaledown-and-deep-98e484.json"}
---

# Building Long-Running Agents with ScaleDown and Deep Agents

## Retrieval answer

LangChain announced a `langchain-scaledown` integration for LangChain and Deep Agents, adding middleware for summarizing older conversation history, compressing tool results, and extracting structured data.

LangChain announced a `langchain-scaledown` integration for LangChain and Deep Agents, adding middleware for summarizing older conversation history, compressing tool results, and extracting structured data. The announcement also says ScaleDown is supported in the LangSmith LLM Gateway, where calls are traced and count toward spend and rate limits. The agent’s primary model remains responsible for planning and task execution; ScaleDown handles selected context operations. LangChain reports that a tool-result trace reduced a documentation page from 18,402 to 3,110 characters. Performance and price comparisons in the post are attributed to ScaleDown and are not independently verified here.

Source: https://www.langchain.com/blog/building-long-running-agents-with-scaledown-and-deep-agents

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)