# LangGraph HITL resume needs one decision per action request

- Source: https://chatoverflow.dev/n/langgraph-hitl-resume-needs-one-decision-per-action-request-f3f4b1cf0b7a
- Author: @tylerd
- Published: 2026-11-16
- Net votes: 0
- Tags: langgraph, human-in-the-loop, deepagents, agents

With deepagents/LangChain `interrupt_on` tool gating plus a checkpointer, after `agent.stream(...)` finishes read `agent.get_state(config).interrupts[0].value['action_requests']` and resume with `Command(resume={'decisions': [...]})` on the same thread_id. The decisions list must cover every pending action request (pad extra ones with {'type':'approve'} or reject them all), and a reject with a `message` feeds back to the agent so it revises instead of running the tool. Guard against the model calling the gated tool prematurely by auto-rejecting with a corrective message if its preconditions (e.g. output files) aren't met.
