langchain-ai/docs
1
0
Fork 0
mirror of https://github.com/langchain-ai/docs.git synced 2026-07-23 04:45:23 -04:00
Code Issues 490 Packages Projects Releases Wiki Activity

[GH-ISSUE #2119] [langgraph]: The example below is not reasonable #268

New Issue
Open
opened 2026-02-17 17:19:31 -05:00 by yindo · 0 comments
yindo commented 2026-02-17 17:19:31 -05:00
Owner
Copy Link
Copy Source

Originally created by @wangtong198 on GitHub (Jan 6, 2026).
Original GitHub issue: https://github.com/langchain-ai/docs/issues/2119

Type of issue

issue / bug

Language

Python

Description

In this first execution, it specifies that the agent should interrupt before node_a, and also interrupt after node_b and node_c.

graph.invoke(
    inputs,
    interrupt_before=["node_a"],  
    interrupt_after=["node_b", "node_c"],  
    config=config,
)

However, in the second execution:

result_2 = graph.invoke(
    None,  # ← Pass None to resume from the current checkpoint
    config=config
)

If you do not re-specify interrupt_after=["B"] or interrupt_after=["C"], the agent will not interrupt again. This means that during the second run, you must explicitly set interrupt_after=["B"] (or similar) for interruption to occur.
Therefore, setting interrupt_after=["B", "C"] in the first invocation is effectively ignored or ineffective, because those settings do not persist across invocations.

In other words, interruption configurations are not automatically carried forward — they must be redeclared in each .invoke() call if needed.

Originally created by @wangtong198 on GitHub (Jan 6, 2026). Original GitHub issue: https://github.com/langchain-ai/docs/issues/2119 ### Type of issue issue / bug ### Language Python ### Description In this first execution, it specifies that the agent should interrupt before node_a, and also interrupt after node_b and node_c. ```python graph.invoke( inputs, interrupt_before=["node_a"], interrupt_after=["node_b", "node_c"], config=config, ) ``` However, in the second execution: ```python result_2 = graph.invoke( None, # ← Pass None to resume from the current checkpoint config=config ) ``` If you do not re-specify interrupt_after=["B"] or interrupt_after=["C"], the agent will not interrupt again. This means that during the second run, you must explicitly set interrupt_after=["B"] (or similar) for interruption to occur. Therefore, **setting interrupt_after=["B", "C"] in the first invocation is effectively ignored or ineffective, because those settings do not persist across invocations.** In other words, interruption configurations are not automatically carried forward — they must be redeclared in each .invoke() call if needed.
yindo added the langgraphexternal labels 2026-02-17 17:19:31 -05:00
yindo changed title from [langgraph]: The example below is not reasonable to [GH-ISSUE #2119] [langgraph]: The example below is not reasonable 2026-06-05 17:25:58 -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 langgraph
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#268
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?