Skip to content

Conversation

@osasisorae
Copy link

I updated ToolNode to collect interrupts from every parallel tool execution (sync + async) before bubbling them up because the previous executor only surfaced whichever call finished first.

I added regression coverage for the sync, async, and resume flows because we needed tests that prove all three tool calls halt, resume in order, and return their tool messages.

I ran make format, make lint, test_tool_node.py -k interrupt, and test_tool_node.py -k interrupt' because those hit the files we touched; full make test still requires Docker (Postgres/Redis) if you want to run it.

@vercel
Copy link

vercel bot commented Dec 26, 2025

@osasisorae is attempting to deploy a commit to the LangChain Team on Vercel.

A member of the Team first needs to authorize it.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant