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:
- Responses are validated before being passed back to the agent
- UIs can render real response forms instead of raw JSON entry fields
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.
More from coding & agent
- All the Copyright Easter Eggs in That AI Music Video Came From Claude — technollama · 2026-10-01
- ChatGPT Wrote Lyrics, Suno Made Music, Claude Coded a 5,200-Frame Music Video — technollama · 2026-10-01
- New tool makes benchmarking across factory configs trivial, not just models — vikvang1 · 2026-10-01
- Magnitude inference engine hits #1 on HN, claims up to 2x faster local open-model runs than llama.cpp — nickbaumann_ · 2026-10-01
- marimo-lens lets you point at charts and steer your coding agent directly — S_Conradi · 2026-10-01
- Non-coder builds MCP-only medieval trade game played entirely by AI agents — Wainfare · 2026-10-01