LangGraph adds typed response schemas for interrupts, making human-in-the-loop type-safe

LangChain · x · 2026-10-01

LangChain shipped a new LangGraph feature: interrupts now support typed response schemas. When an agent pauses for human input, developers define what a valid response looks like:

The docs also detail the interrupt mechanism: the interrupt() function can pause graph execution anywhere, with the checkpointer persisting state and threadid acting as a cursor to resume later, including from error states. Human-in-the-loop, but (type) safe.

Original post →

More from coding & agent

coding & agent channel →