new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

LangChain & LangGraph · all subjects

human-in-the-loop & interrupts

1 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

interrupt_on parameter for human-in-the-loop pausing

interrupt_on is a configuration parameter that enables human-in-the-loop pausing in LangGraph by specifying which nodes or conditions should trigger an interrupt. When a graph execution reaches an interrupt point, the run transitions to 'input-required' state, allowing external systems to inspect state and provide resumption commands. The Agent Server supports native A2A interrupt handling with command resumption via `message/stream` and `message/send` endpoints.

Give your agent this brain