Fix ToolNode parallel interrupts aggregation #6629
Open
+195
−16
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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.