feat(core): experimental in-progress steering hints#18878
feat(core): experimental in-progress steering hints#18878joshualitt wants to merge 1 commit intomainfrom
Conversation
This is a rebase / refactor of: #18783
Summary of ChangesHello @joshualitt, 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 introduces an experimental capability for real-time model steering, allowing users to provide dynamic guidance to the AI agent during complex tasks. It integrates a new lightweight model for efficient hint processing and acknowledgement, updates the model's core instructions to properly handle these hints, and provides a robust testing framework to ensure the feature's reliability. The changes aim to enhance user control and interaction fluidity with the AI agent. Highlights
Changelog
Activity
Using Gemini Code AssistThe 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
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 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
|
There was a problem hiding this comment.
Code Review
This pull request introduces an experimental feature for in-progress steering hints, allowing users to guide the model's execution while a task is running. The implementation is comprehensive, touching the core logic, UI, and agent execution. Key changes include updating the Config class to manage hints, modifying the system prompt to instruct the model on handling these hints, and updating the UI to capture user input as hints during an active task. A new flash-lite-helper utility is introduced for generating quick user acknowledgements, which is a nice UX touch. The feature is also integrated into local and remote agent execution. The addition of a new AppRig test utility and corresponding integration tests demonstrates a high level of quality and thought. The code is well-structured and I have no high or critical severity feedback.
|
Hi there! Thank you for your contribution to Gemini CLI. To improve our contribution process and better track changes, we now require all pull requests to be associated with an existing issue, as announced in our recent discussion and as detailed in our CONTRIBUTING.md. This pull request is being closed because it is not currently linked to an issue. Once you have updated the description of this PR to link an issue (e.g., by adding How to link an issue: Thank you for your understanding and for being a part of our community! |
This is a rebase / refactor of:
#18783