fix(langchain): handle parallel usage of the todo tool in planning middleware #34637
+360
−6
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
eyurtsev
changed the title
github-actions
bot
added
fix
eyurtsev
changed the title
github-actions
bot
added
fix
eyurtsev
previously approved these changes
Jan 7, 2026
nomore8797
added a commit
to nomore8797/langchain
that referenced
this pull request
Jan 8, 2026
* test(text-splitters): add edge case tests for CharacterTextSplitter (langchain-ai#34628) * chore(groq): document vision support (langchain-ai#34620) * feat(core): support custom message separator in get_buffer_string() (langchain-ai#34569) * chore(langchain): fix types in test_wrap_model_call (langchain-ai#34573) * fix: handle empty assistant content in Responses API (langchain-ai#34272) (langchain-ai#34296) * fix(openai): raise proper exception `OpenAIRefusalError` on structured output refusal (langchain-ai#34619) * release(openai): 1.1.7 (langchain-ai#34640) * fix(core): fix strict schema generation for functions with optional args (langchain-ai#34599) * test(core): add edge case for empty examples in LengthBasedExampleSelector (langchain-ai#34641) * fix(langchain): handle parallel usage of the todo tool in planning middleware (langchain-ai#34637) The agent should only make a single call to update the todo list at a time. A parallel call doesn't make sense, but also cannot work as there's no obvious reducer to use. On parallel calls of the todo tool, we return ToolMessage containing to guide the LLM to not call the tool in parallel. --------- Co-authored-by: Eugene Yurtsev <[email protected]> * release(langchain): release 1.2.2 (langchain-ai#34643) Release langchain 1.2.2 * fix(langchain): add test to verify version (langchain-ai#34644) verify version in langchain to avoid accidental drift --------- Co-authored-by: Manas karthik <[email protected]> Co-authored-by: Aarav Dugar <[email protected]> Co-authored-by: Chris Papademetrious <[email protected]> Co-authored-by: Christophe Bornet <[email protected]> Co-authored-by: Sujal M H <[email protected]> Co-authored-by: OysterMax <[email protected]> Co-authored-by: ccurme <[email protected]> Co-authored-by: Mohammad Mohtashim <[email protected]> Co-authored-by: Harrison Chase <[email protected]> Co-authored-by: Eugene Yurtsev <[email protected]>
eyurtsev
added a commit
to langchain-ai/deepagents
that referenced
this pull request
Jan 9, 2026
Adds a unit test for an edge case with the todos middleware in langchain that can be triggered by the agent incorrectly issuing parallel calls to the todos middleware. Depends on langchain-ai/langchain#34637
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The agent should only make a single call to update the todo list at a time. A parallel call doesn't make sense, but also cannot work as there's no obvious reducer to use.
On parallel calls of the todo tool, we return ToolMessage containing to guide the LLM to not call the tool in parallel.