feat: Workspace improvements for agents#2761
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
@blocknote/ariakit
@blocknote/code-block
@blocknote/core
@blocknote/mantine
@blocknote/react
@blocknote/server-util
@blocknote/shadcn
@blocknote/xl-ai
@blocknote/xl-docx-exporter
@blocknote/xl-email-exporter
@blocknote/xl-multi-column
@blocknote/xl-odt-exporter
@blocknote/xl-pdf-exporter
commit: |
| When fixing a bug, the following feedback loop should be used. | ||
|
|
||
| 1. Apply a code change that you think will fix the issue. | ||
| 2. Test the change in a browser environment. |
There was a problem hiding this comment.
I think it doesn't always have to be a browser env (I think it is good to clarify the "most minimal test" rule). Like if it can solve it with a unit test that is fine & better
|
|
||
| Before starting up a browser environment, you need to ensure the dev server is running. This can be done by checking if port 5173 is in use. If it isn't, running `vp dev` at the project root will start the server. | ||
|
|
||
| The Playwright CLI should be used for the browser environment. It can be used to navigate to the dev server and programmatically issue mouse clicks/keyboard inputs. If not installed, stop what you're doing and notify the user to install it. |
There was a problem hiding this comment.
ideally we'd link to it's docs so it can discover commands & stuff it can do
There was a problem hiding this comment.
I was thinking since I added the playwright-cli skill it would be able to reference that. Though I'm not 100% sure if skills referencing other skills works.
There was a problem hiding this comment.
The agent should see the frontmatter of each skill as part of the initial system prompt. So I guess it might be able to figure it out.
2 participants
Summary
This PR makes the repo more friendly for AI agents, and should make them more effective.
Rationale
Our workflow is very agent driven these days, so this should streamline things further.
Changes
AGENTS.mdupdated: Now also contains some general context about the project and information about writing/running/updating tests.create-example: Describes how to create a new example.debug-skill: Describes how Claude should go about debugging in a loop of write->test in browser->verify results. Also includes details about how to navigate the playground and editor.playwright-cli: Instructions for using the Playwright CLI. This is meant to supportdebug-skill.AGENTS.md.Impact
N/A
Testing
N/A
Screenshots/Video
N/A
Checklist
Additional Notes
N/A