LangChain details two context modes for subagents: isolated vs forked
LangChain · x · 2026-09-09
LangChain published "Organizing Context in a Multi-Agent Harness," tackling the hardest part of subagent design: deciding what context to pass in and what to return.
The guide covers two input context modes now supported:
- Isolated: the subagent gets a completely new prompt with no inherited history — best for context isolation and parallel reasoning.
- Forked: the subagent starts exactly where the main agent left off, with a copy of the full message history — best for tasks needing continuity.
It also explains when to use each mode, noting subagents excel at parallelizing work and delegating to specialized agents but are sensitive to context design.
Related event: LangChain Deep Agents Add Subagent Forking to Inherit Full Context(6 posts)→
More from coding & agent
- DeepMind paper: LLMs can't sample randomly on their own, only convert given seeds — rohanpaul_ai · 2026-10-27
- DeepMind paper: LLMs can't sample randomly on their own — pass random numbers from code instead — rohanpaul_ai · 2026-10-27
- BELL: Open-Source Stack Combines Browserbase, Eve, iMessage and Stripe Link for Personal Agents — jeff_weinstein · 2026-10-27
- Legora runs 2,000 parallel agent evals on Modal Sandboxes for legal AI — blelbach · 2026-10-27
- Two engineers rebuilt a FedEx supplier's billing core in 3.5 months vs an estimated 7-8 — alex_verem · 2026-10-27
- GPT-6.1 Terra scores 48 on AA Coding Agent Index at one-third the cost of GPT-5.6 Terra — ArtificialAnlys · 2026-10-27