langchain-ai/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-07-15 12:35:43 -04:00
Code Issues 314 Packages Projects Releases 17 Wiki Activity

[PR #2393] lib: Add interrupt() function #2674

New Issue
Closed
opened 2026-02-20 17:47:23 -05:00 by yindo · 0 comments
yindo commented 2026-02-20 17:47:23 -05:00
Owner
Copy Link
Copy Source

Original Pull Request: https://github.com/langchain-ai/langgraph/pull/2393

State: closed
Merged: Yes

  • This works similarly to the input() function from stdlib
  • calling it in a node interrupts execution
  • invoking the graph with Command(resume=...) will set ... as the return value of interrupt() so that the node can access the "answer" to the "question"
  • This PR also starts the work to control the graph on invoke/stream with Command() input, to be continued in a future PR
    class State(TypedDict):
        my_key: Annotated[str, operator.add]
        market: str

    async def tool_two_node(s: State) -> State:
        if s["market"] == "DE":
            answer = interrupt("Just because...")
        else:
            answer = " all good"
        return {"my_key": answer}

    tool_two_graph = StateGraph(State)
    tool_two_graph.add_node("tool_two", tool_two_node)
    tool_two_graph.add_edge(START, "tool_two")
    tool_two = tool_two_graph.compile()

        tool_two = tool_two_graph.compile(checkpointer=checkpointer)

        # flow: interrupt -> resume with answer
        thread2 = {"configurable": {"thread_id": "2"}}
        # stop when about to enter node
        assert [
            c
            async for c in tool_two.astream(
                {"my_key": "value ⛰️", "market": "DE"}, thread2
            )
        ] == [
            {"__interrupt__": [Interrupt(value="Just because...", when="during")]},
        ]
        # resume with answer
        assert [
            c async for c in tool_two.astream(Command(resume=" my answer"), thread2)
        ] == [
            {"tool_two": {"my_key": " my answer"}},
        ]
**Original Pull Request:** https://github.com/langchain-ai/langgraph/pull/2393 **State:** closed **Merged:** Yes --- - This works similarly to the input() function from stdlib - calling it in a node interrupts execution - invoking the graph with Command(resume=...) will set ... as the return value of interrupt() so that the node can access the "answer" to the "question" - This PR also starts the work to control the graph on invoke/stream with Command() input, to be continued in a future PR ```py class State(TypedDict): my_key: Annotated[str, operator.add] market: str async def tool_two_node(s: State) -> State: if s["market"] == "DE": answer = interrupt("Just because...") else: answer = " all good" return {"my_key": answer} tool_two_graph = StateGraph(State) tool_two_graph.add_node("tool_two", tool_two_node) tool_two_graph.add_edge(START, "tool_two") tool_two = tool_two_graph.compile() tool_two = tool_two_graph.compile(checkpointer=checkpointer) # flow: interrupt -> resume with answer thread2 = {"configurable": {"thread_id": "2"}} # stop when about to enter node assert [ c async for c in tool_two.astream( {"my_key": "value ⛰️", "market": "DE"}, thread2 ) ] == [ {"__interrupt__": [Interrupt(value="Just because...", when="during")]}, ] # resume with answer assert [ c async for c in tool_two.astream(Command(resume=" my answer"), thread2) ] == [ {"tool_two": {"my_key": " my answer"}}, ] ```
yindo added the pull-request label 2026-02-20 17:47:23 -05:00
yindo closed this issue 2026-02-20 17:47:23 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
agents
awaiting author revision
bug
change
chat models
checkpointer
ci
code quality
code quality
dependencies
documentation
drawing
duplicate
enhancement
good first issue
help wanted
invalid
maintainer
meta
missing information
not maintained by langchain
open-swe-auto
open-swe-max
open-swe-max-auto
pending
performance
pull-request
Mirrored from GitHub Pull Request
 question
requires design
sdk
server
stale
studio
tests
type checking
usage question
v0.5
v1.1
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/langgraph#2674
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?