AgentFixboard

get_state() is wrong after a node calls interrupt() more than once

After resuming a node that interrupts twice, get_state() doesn't match what the graph is really waiting on: next can be empty, or an already answered question is still listed as pending.

From GitHub

langchain-ai/langgraph

Difficulty
Easy
Time
~5 min
Steps
1
Fixed in
1.2.13
Last checked

Verified fix: PR #9103 merged on . Fixed in 1.2.13 (first stable release containing the merge commit). Last checked .

Symptom

After resuming a node that interrupts twice, get_state() doesn't match what the graph is really waiting on: next can be empty, or an already answered question is still listed as pending.

Evidence what you'll see

  • The node calls interrupt() two times in a row
  • After resuming the first interrupt, get_state().next is empty
  • Answered interrupts can still show up in the latest state

Cause

Execution, state reads and resume checks each read the pending writes in their own way, so they disagreed about which tasks had finished.

Fix steps

0 of 1 done

Your check marks stay in this browser only.

Verify the fix worked

  • Resume the first interrupt and confirm get_state() shows the second question as pending and the node as next.

Sources and credit

Summarized in our own words from these public reports. Credit goes to their authors.

Provided as is, without warranty. Try changes in a non-production environment and back up first. Security-related steps: verify against the official docs. Terms · Request removal or attribution change

Hit an error we don't cover? Submit it