fix: sanitize surrogate characters in messages before sending to LLM#4987
Open
graydeon wants to merge 1 commit intoAider-AI:mainfrom
Open
fix: sanitize surrogate characters in messages before sending to LLM#4987graydeon wants to merge 1 commit intoAider-AI:mainfrom
graydeon wants to merge 1 commit intoAider-AI:mainfrom
Conversation
On Windows systems with certain locales (e.g. Chinese edition), file content or console input can contain surrogate characters that cause UnicodeEncodeError when httpx tries to JSON-encode the outgoing LLM request. Add sanitize_for_utf8() that recursively walks the message structure and replaces surrogates with the Unicode replacement character before passing messages to litellm.completion(). Fixes Aider-AI#3460
|
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Fixes #3460 — On Windows with certain locales (e.g. Chinese edition), file content or console input can contain surrogate characters (
\udcb0) that causeUnicodeEncodeErrorwhen httpx tries to JSON-encode the outgoing request to the LLM provider.Adds
sanitize_for_utf8()that recursively walks the message structure and replaces any surrogates with the Unicode replacement character, applied insend_completion()right before messages are passed tolitellm.completion().Test plan
TestSanitizeForUtf8test class with 4 tests covering surrogates in strings, nested message structures, non-surrogate Unicode preservation, and non-string passthroughpytest tests/basic/test_models.py— all 27 tests pass