Add max_prompt_tokens
#202
Merged
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
Contributor
There was a problem hiding this comment.
Summary of Changes
Hello @chenyushuo, 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 reintroduces and properly implements the max_prompt_tokens configuration to manage the length of input prompts for language models. The changes ensure that prompts are truncated to fit within the model's context window, improving stability and preventing errors related to overly long inputs. It also establishes a default maximum model length and intelligently derives related token limits, making the system more robust in handling various model configurations.
Highlights
- Re-enabling
max_prompt_tokens: Themax_prompt_tokensparameter, previously marked as deprecated, has been fully re-enabled and integrated into the model configuration and inference process. - Dynamic
max_model_lendetermination: New logic has been introduced to dynamically determine themax_model_lenby attempting to retrieve it from the model's tokenizer. If unsuccessful, a new defaultMAX_MODEL_LENconstant of 4096 is used. - Automatic token limit adjustments: The system now automatically adjusts
max_prompt_tokensto bemax_model_len - 1andmax_response_tokensto bemax_model_lenif they are not explicitly set or exceed the model's maximum length, ensuring token limits are always within bounds. - Explicit prompt truncation: Prompts are now explicitly tokenized and truncated from the left side based on the
max_prompt_tokenssetting before being passed to the VLLM engine for generation, preventing input prompts from exceeding the model's context window.
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. ↩
Contributor
There was a problem hiding this comment.
Code Review
This pull request introduces support for max_prompt_tokens to handle prompt truncation. The changes are mostly in the configuration handling and the vLLM model wrapper. My review identifies a high-severity issue with silent error handling that could mask problems, and a couple of medium-severity issues related to code duplication and a potentially unused parameter, which could affect maintainability and clarity.
Collaborator
Author
|
/unittest-all |
Summary
Tests
Github Test Reporter by CTRF 💚 |
pan-x-c
approved these changes
Aug 20, 2025
yaochaorui
pushed a commit
to yaochaorui/Trinity-RFT
that referenced
this pull request
Aug 27, 2025
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.
Description
[Please describe the background, purpose, changes made, and how to test this PR]
Checklist
Please check the following items before code is ready to be reviewed.