Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fixed bug with additional 'c:' prefix for --workDir #668

Closed
wants to merge 1 commit into from

Conversation

Mannilie
Copy link

@Mannilie Mannilie commented Sep 14, 2024

Changes

  • Removed the 'c:' prefix from the --workDir path for Windows hosts.

Related Issues

Successful Workflow Run Link

PRs don't have access to secrets so you will need to provide a link to a successful run of the workflows from your own
repo.

Checklist

  • Read the contribution guide and accept the
    code of conduct
  • Docs (If new inputs or outputs have been added or changes to behavior that should be documented. Please make a PR
    in the documentation repo)
  • Readme (updated or not needed)
  • Tests (added, updated or not needed)

Summary by CodeRabbit

  • New Features

    • Improved compatibility of the Docker command for cross-platform usage by removing the hardcoded C: prefix from the workspace path.
  • Bug Fixes

    • Enhanced flexibility in workspace path configuration, allowing for better adaptability across different environments.

Copy link

Cat Gif

Copy link

coderabbitai bot commented Sep 14, 2024

Walkthrough

Walkthrough

The changes involve modifying the --workdir option in the docker run command within the src/model/docker.ts file. The original implementation used a hardcoded Windows-specific path prefix (c:) for the dockerWorkspacePath. The updated code removes this prefix, enabling the path to be utilized directly, thereby enhancing compatibility across different environments.

Changes

File Change Summary
src/model/docker.ts Modified the --workdir option to remove the hardcoded c: prefix from dockerWorkspacePath.

Poem

In a world where paths may roam,
A rabbit hops to find a home.
With docker now more free to play,
No c: to bind, just hop away!
Flexibility in every stride,
A workspace path, our joyful guide! 🐇✨

Tip

OpenAI O1 model for chat
  • We have deployed OpenAI's latest O1 model for chat.
  • OpenAI claims that this model has superior reasoning capabilities than their GPT-4o model.
  • Please share any feedback with us in the discussions post.

Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL

Commits

Files that changed from the base of the PR and between 461ecf7 and a4fdbf8.

Files selected for processing (1)
  • src/model/docker.ts (1 hunks)
Additional comments not posted (1)
src/model/docker.ts (1)

103-103: LGTM!

The removal of the hardcoded c: prefix from the --workdir option aligns with the PR objective and fixes the reported bug. The dockerWorkspacePath is now used directly, making the code more flexible and adaptable to different environments or configurations.

The change improves the compatibility of the Docker command with various setups without altering its overall functionality.


Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

Share
Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>.
    • Generate unit testing code for this file.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai generate unit testing code for this file.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai generate interesting stats about this repository and render them as a table.
    • @coderabbitai show all the console.log statements in this repository.
    • @coderabbitai read src/utils.ts and generate unit testing code.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

@AndrewKahr
Copy link
Member

What seems a little odd about this is in v2, it was hardcoded to c:/github/workspace which nobody seemed to have any issues with. We currently have a Windows 11 runner building successfully on V4 without touching the workdir variable, so maybe there's another variable at play?

Here's the v3 commit with the changes for reference: 3032a4a

@Mannilie
Copy link
Author

Hey @AndrewKahr, I agree.
It does seem weird but as I understand, the path should be relative as opposed to absolute for the --workDir argument.

Unless I'm missing something, even in the action items you've written, I believe we're on the same page that it should definitely be omitted from the command.
image

@AndrewKahr
Copy link
Member

It was instructed to leave out the drive letter because the variable was shared between Linux and Windows, so the Windows function would prepend the c: portion while the Linux one doesn't prepend the c:. So at the action level, it is still technically absolute pathing with an assumption of a c drive in the container for Windows containers. And at the docker level, it is supposed to be absolute.

This sounds like you could be hitting a path conversion error based on the shell that's being used: docker/cli#2204
https://stackoverflow.com/questions/40213524/using-absolute-path-with-docker-run-command-not-working

This makes the fix tricky since people with self-hosted runners may be using different ENV vars/shell types on their runners.

@Mannilie
Copy link
Author

@AndrewKahr thanks for pointing me in the right direction with this!

Happy to report that I managed to find the fix to the issue. If anyone runs into this issue, the solution is quite simple.
I noticed that on Dockers Desktop there's an option to utilize both Linux Containers and Windows Containers.

By default, my machine was set to Linux Containers which is not which causes the following error:
image

When you switch it to Windows Containers:
image

The docker service should spin up without any errors:
image

Thanks again for your help @AndrewKahr , can happily close this ticket! 😄

@webbertakken
Copy link
Member

@AndrewKahr do we have a suggested approach for a PR, or recommended values for those variables on self-hosted? Perhaps we can get a quick win by streamlining this.

Related:

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.

3 participants