fix think template prepend nothink_prefix #5492
Conversation
There was a problem hiding this comment.
Summary of Changes
Hello @hjh0119, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!
This pull request addresses a bug in the _swift_prepare_inputs function within the LLM template utility. The previous implementation might have incorrectly prepended a no_think_prefix to assistant messages even when the content already contained a <think> block or the no_think_prefix itself. The fix refines this logic, ensuring the prefix is only added when the message content does not already begin with either of these patterns, thereby preventing redundant or erroneous additions and improving the template's behavior during multi-turn SFT training/validation.
Highlights
- Refined Prefix Prepending Logic: Modified the
_swift_prepare_inputsfunction inswift/llm/template/template/utils.pyto correctly handle theno_think_prefix. The condition for prepending theno_think_prefixto assistant messages now checks if the message content starts with either<think>or theno_think_prefixitself, preventing incorrect additions.
Using Gemini Code Assist
The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.
Invoking Gemini
You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.
| Feature | Command | Description |
|---|---|---|
| Code Review | /gemini review |
Performs a code review for the current pull request in its current state. |
| Pull Request Summary | /gemini summary |
Provides a summary of the current pull request in its current state. |
| Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in issue comments and review comments. |
| Help | /gemini help |
Displays a list of available commands. |
Customization
To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.
Limitations & Feedback
Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.
You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.
Footnotes
-
Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩
There was a problem hiding this comment.
Code Review
This pull request addresses a bug in the ThinkingTemplate where no_think_prefix could be repeatedly prepended to an assistant's message. The fix correctly verifies if a message already starts with <think> or no_think_prefix before adding the prefix. While the logic is sound, the implementation could be slightly simplified for improved code clarity.
PR type
PR information
Write the detail information belongs to this PR.
Experiment results
Paste your experiment result here(if needed).