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 #5158] feat: post hook - create_react_agent support identical tool call ids #4271

New Issue
Closed
opened 2026-02-20 17:49:56 -05:00 by yindo · 0 comments
yindo commented 2026-02-20 17:49:56 -05:00
Owner
Copy Link
Copy Source

Original Pull Request: https://github.com/langchain-ai/langgraph/pull/5158

State: closed
Merged: No

@sydney-runkle
This fixes #5157.

While working on the fix/tests I have observed that FakeToolCallingModel had no way to "stop producing tool calls" which was working only because the bug existed. (Think about it this way, it would keep producing the same tool call id - over and over, and the router would always assume the tool call is completed, and thus would end the execution).

but I needed to reproduce the above case, without hitting the max graph recursion limit - so I added an optional arg to allow max generations with tool calls.

After fixing the bug, I observed the test test_post_model_hook_with_structured_output fails on max graph recursion due to the above reason, so I took the liberty of fixing that test, resetting the agent/model state such that the two tested modes (invoke vs stream) are independent. I suggest splitting them to two tests though.

As an aside - I do wonder - why even test for tool call completions in the post_model_hook router?
And why does the logic assumed tools->post_model_hook is a possible path?

This probably complicated the logic and is not expected to happen - right?

Without this assumption it could be as simple as the logic in should_continue - if there are any tool_calls route to tools.
Wdyt?

**Original Pull Request:** https://github.com/langchain-ai/langgraph/pull/5158 **State:** closed **Merged:** No --- @sydney-runkle This fixes #5157. While working on the fix/tests I have observed that `FakeToolCallingModel` had no way to "stop producing tool calls" which was working only because the bug existed. (Think about it this way, it would keep producing the same tool call id - over and over, and the router would always assume the tool call is completed, and thus would end the execution). but I needed to reproduce the above case, without hitting the max graph recursion limit - so I added an optional arg to allow max generations with tool calls. After fixing the bug, I observed the test `test_post_model_hook_with_structured_output` fails on max graph recursion due to the above reason, so I took the liberty of fixing that test, resetting the agent/model state such that the two tested modes (invoke vs stream) are independent. I suggest splitting them to two tests though. As an aside - I do wonder - why even test for tool call completions in the `post_model_hook` router? And why does the logic assumed tools->post_model_hook is a possible path? This probably complicated the logic and is not expected to happen - right? Without this assumption it could be as simple as the logic in `should_continue` - if there are any tool_calls route to `tools`. Wdyt?
yindo added the pull-request label 2026-02-20 17:49:56 -05:00
yindo closed this issue 2026-02-20 17:49:56 -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#4271
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?