Trying to save space

[ericcurtin]

tiny is is not so tiny, it's 600M

Summary by Sourcery

Refactor the 040-serve.bats system test to dynamically derive model and quadlet container names, replace hard-coded references, and update assertions to support the smollm:135m model.

Enhancements:

• Parameterize the model name and quadlet file name in the Bats system tests instead of using hard-coded values
• Switch the test model from 'tiny' to 'smollm:135m' to reflect updated model sizing

Tests:

• Update output assertions to reference dynamic variables for quadlet file name, mount line, and environment settings
• Adjust error-case invocation to use the parameterized model variable

[sourcery-ai]

Reviewer's Guide

Refactored the system test to parameterize the model and quadlet file names with dynamic variables instead of using hardcoded ‘tiny’ values.

File-Level Changes

Change	Details	Files
Introduce dynamic model and quadlet variables	Defined model="smollm:135m" at the top of the test Added quadlet="$model.container" variable Replaced hardcoded model references in run_ramalama commands with ${model} Updated assertions to reference $quadlet dynamically	test/system/040-serve.bats
Remove hardcoded tiny/tinyllama.container usages	Deleted literal 'tiny' and 'tinyllama.container' references Replaced rm tinyllama.container with rm $quadlet Adjusted the bogus-generate test to invoke serve on $model instead of 'tiny'	test/system/040-serve.bats

---

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

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[gemini-code-assist]

Summary of Changes

Hello @ericcurtin, 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 focuses on internal code organization and enhancing test robustness. It refactors a common utility function into a dedicated module and updates system tests to be more flexible with model naming conventions, ensuring better maintainability and reliability.

Highlights

• Code Refactoring: The should_colorize utility function has been moved from ramalama/chat.py to ramalama/model.py. This centralizes common utility functions, improving code organization and promoting reusability.
• Test Improvements: The system tests for ramalama serve --generate=quadlet in test/system/040-serve.bats have been updated. The tests now use a more specific model name (smollm:135m) and dynamically derive the generated quadlet filename, making them more robust and adaptable to different model naming conventions.

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. ↩

[gemini-code-assist]

Code Review

This pull request refactors the should_colorize function and updates system tests to use dynamic variables. One assertion in test/system/040-serve.bats needs a correction to accurately reflect the expected output.

[sourcery-ai]

Hey @ericcurtin - I've reviewed your changes - here's some feedback:

• The second quadlet‐generation assertion uses $quadlet.container, which double‐appends .container—it should just use $quadlet like the first assertion.
• Wrap $quadlet in quotes for run cat and rm commands (e.g. run cat "$quadlet") to safely handle any model names with spaces or special characters.

Prompt for AI Agents

Please address the comments from this code review:
## Overall Comments
- The second quadlet‐generation assertion uses `$quadlet.container`, which double‐appends `.container`—it should just use `$quadlet` like the first assertion.
- Wrap `$quadlet` in quotes for `run cat` and `rm` commands (e.g. `run cat "$quadlet"`) to safely handle any model names with spaces or special characters.

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[rhatdan]

LGTM