Skip to content

Docs/context compressor#889

Merged
alcholiclg merged 7 commits intomodelscope:mainfrom
vinci-grape:docs/context-compressor
Mar 24, 2026
Merged

Docs/context compressor#889
alcholiclg merged 7 commits intomodelscope:mainfrom
vinci-grape:docs/context-compressor

Conversation

@vinci-grape
Copy link
Collaborator

Change Summary

Related issue number

Checklist

  • The pull request title is a good summary of the changes - it will be used in the changelog
  • Unit tests for the changes exist
  • Run pre-commit install and pre-commit run --all-files before git commit, and passed lint check.
  • Documentation reflects the changes where applicable

Add a new context compression mechanism inspired by opencode's
compaction approach. Features include:
- Token-based overflow detection
- Tool output pruning to reduce context size
- LLM-based conversation summarization

🤖 Generated with [Qoder][https://qoder.com]
@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello, 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 enhances the project's documentation by introducing a dedicated section for memory compression configurations. These new features are designed to improve context management in long conversations and specialized AI tasks, offering various compression methods to optimize performance and resource usage. The update ensures that users have clear guidance on configuring these advanced memory management capabilities.

Highlights

  • New Memory Compression Documentation: Introduced a comprehensive section detailing memory compression configurations, including context_compressor, refine_condenser, and code_condenser.
  • Context Management Features: Documented parameters for context management in long conversations, such as context_limit, prune_protect, prune_minimum, reserved_buffer, and enable_summary.
  • Multilingual Documentation: Updated both English (docs/en/Components/Config.md) and Chinese (docs/zh/Components/config.md) configuration documentation to reflect the new memory compression features.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

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 by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

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 pull request 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.

Footnotes

  1. 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.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request introduces comprehensive documentation for the new memory compression configurations, including context_compressor, refine_condenser, and code_condenser. The added sections in both English and Chinese configuration guides provide clear YAML examples and a descriptive table of supported compressor types. This is a valuable addition that enhances the clarity and usability of the ms-agent configuration for managing long conversations and code generation tasks.

@alcholiclg alcholiclg merged commit 30d4fc1 into modelscope:main Mar 24, 2026
1 of 2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants