fix: generate session titles in the conversation's language, not always English#4683
Closed
dieutx wants to merge 1 commit into
Closed
fix: generate session titles in the conversation's language, not always English#4683dieutx wants to merge 1 commit into
dieutx wants to merge 1 commit into
Conversation
Contributor
Author
|
Closing — can't verify the fix end-to-end on my setup. The prompt change is correct but #4670 may cover this too. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Session titles are always generated in English regardless of the conversation language. A Japanese user chatting in Japanese gets an English title like "Discussion About Python Decorators" instead of something in Japanese.
Companion to #4670 which fixes the same issue for context compression summaries.
Root Cause
The title generator prompt in
agent/title_generator.pyhas no language-matching instruction:The LLM defaults to English.
Fix
Added one line to the prompt:
Same approach as #4670 uses for compression summaries.
Tests