fix(core): fix trim_messages misclassification of per-message token_counter#18
Open
LennyMalcolm0 wants to merge 5 commits into
Open
fix(core): fix trim_messages misclassification of per-message token_counter#18LennyMalcolm0 wants to merge 5 commits into
trim_messages misclassification of per-message token_counter#18LennyMalcolm0 wants to merge 5 commits into
Conversation
|
AI review failed to complete. Please retry. |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes : langchain-ai#35629
I replaced the brittle
annotation is BaseMessagecheck intrim_messageswithget_type_hints()to resolve annotations to live types where possible andissubclass()to correctly matchBaseMessageand its subclasses. This should fix misclassification for subclass annotations likeHumanMessage, string/forward-reference annotations, and common cases involving postponed annotation evaluation. I also added atoken_counter_is_per_messageflag as an explicit escape hatch for lambdas and unannotated callables where auto-detection cannot work. Also added regression tests covering:BaseMessageannotationget_num_tokens_from_messagesCloned from langchain-ai#35630 for DevAsign stress testing.