LangGraph.js shipped @langchain/[email protected] on 2026-09-25 (with @langchain/[email protected] and Vue/Svelte twins). useStream's "enqueue" multitask strategy can set queue: "server" so queued runs hit backend Runs REST instead of an in-memory client queue—surviving reloads, visible across sessions, with server-side cancelQueued/clearQueue. Default remains queue: "local"; custom AgentServerAdapter transports are unsupported. For frontends that need durable, collaborative agent queues.

Key Takeaways

  • ✓Shipped: langgraph-sdk 1.12.0 + react/vue/svelte 1.2.0
  • ✓Opt in with queue: "server" on useStream enqueue; local remains default
  • ✓Backend must implement Runs REST create/list/cancel endpoints
  • ✓Docs: useStream React howto + npm package
  • ✓Not supported with custom AgentServerAdapter transports
LangGraph.js SDK 1.12.0: useStream enqueue can use durable server-side run queues across reloads/sessions
🖼️Official Media
Click to view high-res
⚡

Key Decision Metrics at a Glance

TL;DR Verdict
🏆 Benchmark RankRank
See how it ranks on the leaderboard
Full Leaderboard→
💰 Cost & PlansCompare
API & Subscription
Compare Plans↗
🛠️ Ecosystem & IDERules
LangGraph · LangGraphJS · useStream
Setup IDE Rules↗
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

⚔️ Compare Model→💰 Compare plans & limits↗
🔗

Project Links & Resources

Direct Access
Direct access to official project resources and documentation
🐙
GitHub Release @langchain/[email protected]
github.com/langchain-ai/langgraphjs/releases/tag/%40langchain%2Flanggraph-sdk%401.12.0
↗
🐙
GitHub Release @langchain/[email protected]
github.com/langchain-ai/langgraphjs/releases/tag/%40langchain%2Freact%401.2.0
↗
📖
useStream React howto
langchain-ai.github.io/langgraphjs/cloud/how-tos/use_stream_react/
↗
📖
LangGraph.js docs home
langchain-ai.github.io/langgraphjs/
↗
📖
npm @langchain/langgraph-sdk
www.npmjs.com/package/@langchain/langgraph-sdk
↗
📖
npm @langchain/react
www.npmjs.com/package/@langchain/react
↗
🐙
PR #2848 server-side enqueue queue
github.com/langchain-ai/langgraphjs/pull/2848
↗
🔬

In-Depth Technical Analysis

Core Background & Industry Pain Points

Agent chat UIs often enqueue multitask submissions in the browser only—so reloads drop the queue, tabs diverge, and collaborators cannot cancel. Cloud LangGraph already exposes Runs REST; frontends still treated enqueue as a local toy.

Architecture Highlights & Internals

langgraph-sdk 1.12.0 adds queue: "server" for useStream's enqueue strategy, persisting runs via Runs REST create/list/cancel. Default stays local. React/Vue/Svelte 1.2.0 ship in lockstep. Custom AgentServerAdapter transports are unsupported.

Authoritative Benchmarks & Measured Scores

No public queue throughput numbers. Validate cross-tab visibility after reload and server-side cancel; backends lacking Runs REST should fail closed.

Developer Hands-on Guide

Install sdk 1.12.0 + react 1.2.0, set queue: "server", implement Runs REST, follow the useStream React howto.

Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

⚔️ Launch VS Compare→💳 View Plans↗
Up NextLangChain.js @langchain/openai 1.6.0: explicit prompt cache options + content-block breakpoints
Read Now→