feat: Add custom AI system prompt functionality#33
Conversation
This commit introduces a new feature that allows users to customize the AI's system prompt. A settings modal has been added to the UI, which can be accessed via a "Settings" button. Inside the modal, users can input a custom system prompt, which is then saved to `localStorage` for persistence. A "Reset to Default" button is also available to restore the original prompt. The AI generation logic has been updated to use the custom prompt, allowing for more flexible and user-defined mind-map generation. A Playwright test has been added to ensure the functionality of the settings modal, including saving and loading the custom prompt from `localStorage` and verifying that the AI uses the custom prompt when generating new nodes. Finally, the `__pycache__` directory has been added to the `.gitignore` file to prevent Python cache files from being committed to the repository. Co-authored-by: coderdevang <85845460+coderdevang@users.noreply.github.com>
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
This feature adds a settings modal that allows users to customize the AI's system prompt.
localStorageand persists across sessions.__pycache__directory has been added to the.gitignorefile.This change is a small, high-value feature that does not break any existing functionality. It gives users more control over the AI's behavior and allows for a more personalized experience.
PR created automatically by Jules for task 16786742967922085289 started by @coderdevang