Skip to content

Don't pull image when doing ramalama --help call #1589

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

Merged
merged 1 commit into from
Jun 24, 2025

Conversation

rhatdan
Copy link
Member

@rhatdan rhatdan commented Jun 23, 2025

Fixes: #1587

Summary by Sourcery

Add a nopull option to the image selection logic and apply it in the CLI so that running ramalama --help (or other non-runtime invocations) no longer triggers a container image pull.

Bug Fixes:

  • Prevent unnecessary image pull when calling ramalama --help

Enhancements:

  • Introduce a nopull parameter to accel_image to bypass pulling the container image
  • Invoke accel_image with nopull=True when setting the CLI’s default --image value

Copy link
Contributor

sourcery-ai bot commented Jun 23, 2025

Reviewer's Guide

This PR prevents image pulls during the --help invocation by adding a nopull flag to the accel_image function (which alters its version-selection logic) and passing nopull=True to it in the CLI's default --image argument.

Sequence diagram for CLI argument parsing with nopull flag

sequenceDiagram
    actor User
    participant CLI as ramalama.cli
    participant AccelImage as accel_image
    User->>CLI: ramalama --help
    CLI->>AccelImage: accel_image(CONFIG, nopull=True)
    AccelImage-->>CLI: image string (no pull)
    CLI-->>User: Help output
Loading

Class diagram for updated accel_image function signature and usage

classDiagram
    class accel_image {
        +str accel_image(config: Config, nopull=False)
    }
    class Config
    ramalama.cli --|> accel_image : uses
    ramalama.cli : --image default=accel_image(CONFIG, nopull=True)
Loading

File-Level Changes

Change Details Files
Introduce nopull parameter to accel_image and update its pull logic
  • Extend accel_image signature to accept a nopull boolean flag
  • Modify conditional to skip attempt_to_use_versioned when nopull is true
ramalama/common.py
Use nopull flag when computing default CLI image
  • Update --image default to call accel_image(CONFIG, nopull=True)
ramalama/cli.py

Possibly linked issues


Tips and commands

Interacting with Sourcery

  • Trigger a new review: Comment @sourcery-ai review on the pull request.
  • Continue discussions: Reply directly to Sourcery's review comments.
  • Generate a GitHub issue from a review comment: Ask Sourcery to create an
    issue from a review comment by replying to it. You can also reply to a
    review comment with @sourcery-ai issue to create an issue from it.
  • Generate a pull request title: Write @sourcery-ai anywhere in the pull
    request title to generate a title at any time. You can also comment
    @sourcery-ai title on the pull request to (re-)generate the title at any time.
  • Generate a pull request summary: Write @sourcery-ai summary anywhere in
    the pull request body to generate a PR summary at any time exactly where you
    want it. You can also comment @sourcery-ai summary on the pull request to
    (re-)generate the summary at any time.
  • Generate reviewer's guide: Comment @sourcery-ai guide on the pull
    request to (re-)generate the reviewer's guide at any time.
  • Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
    pull request to resolve all Sourcery comments. Useful if you've already
    addressed all the comments and don't want to see them anymore.
  • Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
    request to dismiss all existing Sourcery reviews. Especially useful if you
    want to start fresh with a new review - don't forget to comment
    @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

  • Enable or disable review features such as the Sourcery-generated pull request
    summary, the reviewer's guide, and others.
  • Change the review language.
  • Add, remove or edit custom review instructions.
  • Adjust other review settings.

Getting Help

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.

Summary of Changes

Hello @rhatdan, 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!

I've implemented a change to prevent the ramalama CLI from attempting to pull container images when the --help command is executed. This improves the responsiveness of the help command by avoiding unnecessary network operations, addressing a reported issue where ramalama --help would trigger an image pull.

Highlights

  • Prevent Image Pull on Help: I've modified the ramalama CLI's --image argument default to pass a nopull=True flag to the accel_image function. This ensures that image pulling is bypassed when --help is invoked, improving the responsiveness of the command.
  • Introduce nopull Parameter: I've added a new nopull boolean parameter to the accel_image function in ramalama/common.py. This parameter, defaulting to False, allows callers to explicitly prevent image pull attempts.
  • Conditional Image Versioning: I've updated the accel_image logic to short-circuit the attempt_to_use_versioned call if the nopull flag is set. This effectively prevents network operations for image checks when nopull is active.
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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 is currently in preview and 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 to provide feedback.

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

  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

@sourcery-ai sourcery-ai bot left a comment

Choose a reason for hiding this comment

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

Hey @rhatdan - I've reviewed your changes and they look great!


Sourcery is free for open source - if you like our reviews please consider sharing them ✨
Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.

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 effectively resolves the issue of ramalama --help triggering an unnecessary image pull. The approach of adding a nopull flag to accel_image is clean and well-targeted. The changes in both cli.py and common.py are correct and work together to implement the fix.

My main feedback is to enhance test coverage for the new logic path to ensure its robustness and prevent future regressions. I've added a comment with details on this.

Overall, this is a solid contribution that improves the user experience.

@@ -650,7 +650,7 @@ def accel_image(config: Config) -> str:
return "registry.redhat.io/rhelai1/ramalama-vllm"

vers = minor_release()
if attempt_to_use_versioned(config.engine, image, vers, True):
if nopull or attempt_to_use_versioned(config.engine, image, vers, True):
Copy link
Contributor

Choose a reason for hiding this comment

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

medium

The new logic path introduced by the nopull flag is not covered by existing unit tests. To ensure the correctness of this change and prevent future regressions, please consider adding a test case to test/unit/test_common.py that verifies the behavior when nopull=True.

The test should:

  1. Call accel_image(config, nopull=True).
  2. Assert that the returned image name has the correct version tag.
  3. Assert that attempt_to_use_versioned is not called, for example by using mock.assert_not_called().

@ericcurtin ericcurtin merged commit fd71bac into containers:main Jun 24, 2025
20 of 21 checks passed
@ktdreyer
Copy link
Contributor

Thanks Eric & Dan!

I proposed a small improvement here: #1611

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.

ramalama --help pulls a large image before printing anything
3 participants