fix: remove author name from agent system prompts to prevent unintended language inference #634
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
The author name "Named by [YeonGyu Kim]" in the Sisyphus role section causes LLMs to sometimes infer Korean language output, even when the user's locale is en-US. This happens because the model sees a Korean name in the system prompt and may interpret it as a signal to respond in Korean. Removing the author attribution from the runtime prompt fixes this issue. The attribution is preserved in README, LICENSE, and package.json. Co-Authored-By: Claude Opus 4.5 <[email protected]>
Contributor
|
All contributors have signed the CLA. Thank you! ✅ |
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
There was a problem hiding this comment.
Your free trial has ended. If you'd like to continue receiving code reviews, you can add a payment method here.
![cubic-dev-ai[bot]](https://avatars.githubusercontent.com/in/1082092?s=60&v=4){kind=small}
Contributor
Author
|
I have read the CLA Document and I hereby sign the CLA |
Owner
|
Kinda funny you made pr with cc |
Contributor
Author
Haha because omo didn't work with cc yesterday, and OpenAI models are too slow, so I temporarily switch back. |
kdcokenny
pushed a commit
that referenced
this pull request
Jan 13, 2026
kdcokenny
pushed a commit
that referenced
this pull request
Jan 13, 2026
The author name "Named by [YeonGyu Kim]" in the Sisyphus role section causes LLMs to sometimes infer Korean language output, even when the user's locale is en-US. This happens because the model sees a Korean name in the system prompt and may interpret it as a signal to respond in Korean. Removing the author attribution from the runtime prompt fixes this issue. The attribution is preserved in README, LICENSE, and package.json. Co-authored-by: Claude Opus 4.5 <[email protected]>
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.
Problem
The Sisyphus agent system prompt includes the line:
This causes LLMs to sometimes infer Korean language output, even when the user's system locale is
en-US. The model sees a Korean name in the system prompt and interprets it as a signal to respond in Korean.Example output (unintended Korean):
Solution
Remove the author attribution from the runtime system prompts in:
src/agents/sisyphus.tssrc/agents/orchestrator-sisyphus.tsThe author attribution is preserved in:
Changes
Named by [YeonGyu Kim](https://github.com/code-yeongyu).fromSISYPHUS_ROLE_SECTIONORCHESTRATOR_SISYPHUS_SYSTEM_PROMPTTest Plan
🤖 Generated with Claude Code
Summary by cubic
Removed the author attribution from Sisyphus system prompts to prevent unintended Korean responses. Ensures the agent replies in the user’s expected language based on locale.
Written for commit e77369b. Summary will update on new commits.