langchain-ai/docs
1
0
Fork 0
mirror of https://github.com/langchain-ai/docs.git synced 2026-07-22 20:35:34 -04:00
Code Issues 490 Packages Projects Releases Wiki Activity

[GH-ISSUE #474] [langgraph-platform]: issue w/ interrupt double texting example #57

New Issue
Open
opened 2026-02-17 17:19:05 -05:00 by yindo · 1 comment
yindo commented 2026-02-17 17:19:05 -05:00
Owner
Copy Link
Copy Source

Originally created by @mUser-ai on GitHub (Sep 1, 2025).
Original GitHub issue: https://github.com/langchain-ai/docs/issues/474

Issue with current documentation:

When following the documentation on Interrupt concurrent, the expected behavior is that partial outputs from interrupted runs are preserved and shown (example below):

================================ Human Message =================================
what's the weather in sf?
================================== Ai Message ==================================
[{'id': 'toolu_01MjNtVJwEcpujRGrf3x6Pih', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
...
================================== Ai Message ==================================
The search provides a convenient overview...

However, in practice, I see the following behavior:

================================ Human Message ================================
what's the weather in sf?
================================ Human Message ================================
what's the weather in nyc?
================================== Ai Message ================================
Name: my_agent
Tool Calls:
weather_tool (call_l9teq416Wbc8tz2w0G40VgCk)
Args: location: SF
weather_tool (call_XjuoiC39FTUPKRfhd6TAzRqw)
Args: location: New York
================================= Tool Message ================================
Name: weather_tool
The weather in SF is windy.
================================= Tool Message ================================
Name: weather_tool
The weather in New York is sunny.
...

Please clarify in the "Interrupt concurrent" documentation:

  • Should partial outputs from interrupted runs be preserved?
  • If not, is the example in the docs outdated or misleading?
  • If yes, guidance on how to properly capture and display these intermediate results would be very helpful.

Idea or request for content:

No response

Originally created by @mUser-ai on GitHub (Sep 1, 2025). Original GitHub issue: https://github.com/langchain-ai/docs/issues/474 ### Issue with current documentation: When following the documentation on [Interrupt concurrent](https://docs.langchain.com/langgraph-platform/interrupt-concurrent), the expected behavior is that partial outputs from interrupted runs are preserved and shown (example below): ================================ Human Message ================================= what's the weather in sf? ================================== Ai Message ================================== [{'id': 'toolu_01MjNtVJwEcpujRGrf3x6Pih', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}] ... ================================== Ai Message ================================== The search provides a convenient overview... However, in practice, I see the following behavior: ================================ Human Message ================================ what's the weather in sf? ================================ Human Message ================================ what's the weather in nyc? ================================== Ai Message ================================ Name: my_agent Tool Calls: weather_tool (call_l9teq416Wbc8tz2w0G40VgCk) Args: location: SF weather_tool (call_XjuoiC39FTUPKRfhd6TAzRqw) Args: location: New York ================================= Tool Message ================================ Name: weather_tool The weather in SF is windy. ================================= Tool Message ================================ Name: weather_tool The weather in New York is sunny. ... Please clarify in the "Interrupt concurrent" documentation: - Should partial outputs from interrupted runs be preserved? - If not, is the example in the docs outdated or misleading? - If yes, guidance on how to properly capture and display these intermediate results would be very helpful. ### Idea or request for content: _No response_
yindo added the external label 2026-02-17 17:19:05 -05:00
yindo commented 2026-02-17 17:19:05 -05:00
Author
Owner
Copy Link
Copy Source

@isahers1 commented on GitHub (Sep 10, 2025):

Hi @mUser-ai , the interrupt concurrent will only save values up to the last checkpoint - so the data from a node that is in the middle of running will not be saved in the checkpoint history. As you can see in the example, the first run goes Human -> AI -> Tool and then gets interrupted while the AI is finalizing it's response (you normally would see Human -> AI -> Tool -> AI), and the partial response from the AI is not visible. The second run then kicks off and works as normal: Human -> AI -> Tool -> AI. Let me know if you have more questions!

@isahers1 commented on GitHub (Sep 10, 2025): Hi @mUser-ai , the interrupt concurrent will only save values up to the last checkpoint - so the data from a node that is in the middle of running will not be saved in the checkpoint history. As you can see in the example, the first run goes Human -> AI -> Tool and then gets interrupted while the AI is finalizing it's response (you normally would see Human -> AI -> Tool -> AI), and the partial response from the AI is not visible. The second run then kicks off and works as normal: Human -> AI -> Tool -> AI. Let me know if you have more questions!
yindo changed title from [langgraph-platform]: issue w/ interrupt double texting example to [GH-ISSUE #474] [langgraph-platform]: issue w/ interrupt double texting example 2026-06-05 17:24:50 -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#57
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?