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

Can not get ToolMessage in astream_events if excepiton occures in tool call #945

New Issue
Closed
opened 2026-02-20 17:42:28 -05:00 by yindo · 2 comments
yindo commented 2026-02-20 17:42:28 -05:00
Owner
Copy Link
Copy Source

Originally created by @781574155 on GitHub (Aug 26, 2025).

Originally assigned to: @casparb on GitHub.

Checked other resources

  • This is a bug, not a usage question. For questions, please use the LangChain Forum (https://forum.langchain.com/).
  • I added a clear and detailed title that summarizes the issue.
  • I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example).
  • I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue.

Example Code

async for event in graph.astream_events(input, config=config):
        kind = event["event"]
        if kind == "on_tool_end":
            output = event['data']['output']
            pass

Error Message and Stack Trace (if applicable)

Description

In on_tool_end event, I can get ToolMessage on tool call finish.
However if exception occures, there are an tool message to send to LLM, but I can't get it.

Image

I think we should be able to get ToolMessage on on_tool_end event even exception occures in tool call.

System Info

no

Originally created by @781574155 on GitHub (Aug 26, 2025). Originally assigned to: @casparb on GitHub. ### Checked other resources - [x] This is a bug, not a usage question. For questions, please use the LangChain Forum (https://forum.langchain.com/). - [x] I added a clear and detailed title that summarizes the issue. - [x] I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example). - [x] I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue. ### Example Code ```python async for event in graph.astream_events(input, config=config): kind = event["event"] if kind == "on_tool_end": output = event['data']['output'] pass ``` ### Error Message and Stack Trace (if applicable) ```shell ``` ### Description In `on_tool_end` event, I can get ToolMessage on tool call finish. However if exception occures, there are an tool message to send to LLM, but I can't get it. <img width="1559" height="998" alt="Image" src="https://github.com/user-attachments/assets/a0a70978-d15e-45e8-ba65-59df98d1f503" /> I think we should be able to get ToolMessage on `on_tool_end` event even exception occures in tool call. ### System Info no
yindo added the bugpending labels 2026-02-20 17:42:28 -05:00
yindo closed this issue 2026-02-20 17:42:28 -05:00
yindo commented 2026-02-20 17:42:28 -05:00
Author
Owner
Copy Link
Copy Source

@casparb commented on GitHub (Sep 11, 2025):

Hi @781574155. It is not obvious what you are asking because your code example does not clearly demonstrate the issue, so I'm sorry if I misunderstand:

It seems like you want to capture the ToolMessage that contains the error while streaming. You can use the .astream() API - you'll see the following event if a tool errors:

{'tools': {'messages': [ToolMessage(content='Error: ValueError("...")\n Please fix your mistakes.', ..., status='error')]}}

You should be favoring the .stream() or .astream() APIs instead of.astream_events() API, which is largely unnecessary these days for development. There is also a known bug in core (langchain-ai/langchain#30708) where on_tool_error does not appear in the .astream_events() events stream. If you must use .astream_events() over .astream(), then keep an eye on that PR - a fix is coming soon.

Closing as resolved, reply here if you're still having issues (with a clear, self-contained, minimal example) and I'll reopen.

@casparb commented on GitHub (Sep 11, 2025): Hi @781574155. It is not obvious what you are asking because your code example does not clearly demonstrate the issue, so I'm sorry if I misunderstand: It seems like you want to capture the ToolMessage that contains the error while streaming. You can use the [`.astream()` API](https://docs.langchain.com/oss/python/langgraph/streaming) - you'll see the following event if a tool errors: ```python {'tools': {'messages': [ToolMessage(content='Error: ValueError("...")\n Please fix your mistakes.', ..., status='error')]}} ``` You should be favoring the `.stream()` or `.astream()` APIs instead of`.astream_events()` API, which is largely unnecessary these days for development. There is also a known bug in core (langchain-ai/langchain#30708) where `on_tool_error` does not appear in the `.astream_events()` events stream. If you must use `.astream_events()` over `.astream()`, then keep an eye on that PR - a fix is coming soon. Closing as resolved, reply here if you're still having issues (with a clear, self-contained, minimal example) and I'll reopen.
yindo commented 2026-02-20 17:42:28 -05:00
Author
Owner
Copy Link
Copy Source

@781574155 commented on GitHub (Sep 11, 2025):

Thank you @casparb. https://github.com/langchain-ai/langchain/issues/30708 is what I want to express

@781574155 commented on GitHub (Sep 11, 2025): Thank you @casparb. https://github.com/langchain-ai/langchain/issues/30708 is what I want to express
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 bug pending
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#945
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?