langchain-ai/docs
1
0
Fork 0
mirror of https://github.com/langchain-ai/docs.git synced 2026-07-22 04:15:25 -04:00
Code Issues 490 Packages Projects Releases Wiki Activity

[GH-ISSUE #1802] Regarding the tool execution sequence of interrupt_on in subagent #233

New Issue
Open
opened 2026-02-17 17:19:27 -05:00 by yindo · 0 comments
yindo commented 2026-02-17 17:19:27 -05:00
Owner
Copy Link
Copy Source

Originally created by @gsmini on GitHub (Dec 9, 2025).
Original GitHub issue: https://github.com/langchain-ai/docs/issues/1802

When I was configuring the execution sequence of interrupt_on in the main agent of subgent according to the documentation（https://docs.langchain.com/oss/python/deepagents/human-in-the-loop#subagent-interrupts）, I found that it was different from what was described in the documentation. The document states that the interrupt_on configuration in subgent will override the configuration in main agent, but in reality, this is not the case. For example, the configuration in main agent is

interrupt_on={
            "send_email": False
        },

The configuration in the subagent is

  "interrupt_on": {
        "send_email": True
    }

When I call it:

data = agent.invoke({"messages": [{"role": "user", "content": "Send an email to `admin@gmail.com` with the subject "Meeting" and the content: "Please attend the meeting the day after tomorrow.""}]},
                        config=config)

This code will not trigger the send_email tool.

It will only take effect when the configuration is reversed

Originally created by @gsmini on GitHub (Dec 9, 2025). Original GitHub issue: https://github.com/langchain-ai/docs/issues/1802 When I was configuring the execution sequence of interrupt_on in the main agent of subgent according to the documentation（https://docs.langchain.com/oss/python/deepagents/human-in-the-loop#subagent-interrupts）, I found that it was different from what was described in the documentation. The document states that the interrupt_on configuration in subgent will override the configuration in main agent, but in reality, this is not the case. For example, the configuration in main agent is ``` interrupt_on={ "send_email": False }, ``` The configuration in the subagent is ``` "interrupt_on": { "send_email": True } ``` When I call it: ``` data = agent.invoke({"messages": [{"role": "user", "content": "Send an email to `admin@gmail.com` with the subject "Meeting" and the content: "Please attend the meeting the day after tomorrow.""}]}, config=config) ``` This code will not trigger the send_email tool. It will only take effect when the configuration is reversed
yindo added the external label 2026-02-17 17:19:27 -05:00
yindo changed title from Regarding the tool execution sequence of interrupt_on in subagent to [GH-ISSUE #1802] Regarding the tool execution sequence of interrupt_on in subagent 2026-06-05 17:25:48 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
deepagents
docs-infra
external
external
help wanted
integration
internal
internal
javascript
js/ts
langchain
langgraph
langsmith
needs-title
pull-request
Mirrored from GitHub Pull Request
 python
reference
No Label external
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/docs#233
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?