fix(langchain): handle malformed LLM response in LLMToolSelectorMiddleware #34375
+77
−1
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
…eware Add validation in `_process_selection_response` to check that the LLM response contains a valid 'tools' list before processing. Previously, if the LLM returned a malformed response (missing 'tools' key or null value), a cryptic `KeyError: 'tools'` was raised. Now raises a clear `ValueError` with actionable guidance suggesting the user try a model with better structured output support. Fixes langchain-ai#34358
github-actions
bot
added
langchain
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Summary
_process_selection_responseto check that the LLM response contains a validtoolslist before processingValueErrorwith actionable guidance instead of crypticKeyError: 'tools'Root Cause
When using
with_structured_output(), some models may not strictly follow the schema and could return responses without the expectedtoolskey. The previous code directly accessedresponse["tools"]without validation, causing intermittentKeyErrorfailures.Test Plan
test_malformed_response_missing_tools_key- verifiesValueErroris raised whentoolskey is missingtest_malformed_response_null_tools- verifiesValueErroris raised whentoolsisNoneFixes #34358