get --runtime-args back

[ilopezluna]

Address #515

Revert removal of --runtime-args as its being used by users, so when I removed in here I broke their workflows.

[gemini-code-assist]

Summary of Changes

Hello @ilopezluna, 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 addresses a critical user workflow issue by reintroducing the ability to pass raw runtime flags to the inference backends. It integrates this functionality across the CLI commands and backend configuration, ensuring that users can customize model runtime behavior as needed. The change restores previously broken workflows and enhances the flexibility of model deployment and configuration.

Highlights

• Reintroduction of --runtime-args: The --runtime-args functionality, previously removed, has been reinstated to support existing user workflows. This allows users to pass raw runtime flags directly to the inference engine.
• CLI Command Updates: Both docker model compose up and docker model configure commands now support the --runtime-flags option. The configure command also accepts flags after a -- separator.
• Backend Configuration Integration: The BackendConfiguration struct now includes a RuntimeFlags field, and these flags are correctly passed to both LlamaCpp and vLLM inference backends during configuration.
• Dynamic Mode Detection: The scheduler now automatically detects and sets the backend mode to Embedding if the --embeddings flag is present within the provided runtime flags.

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 by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

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 pull request 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 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. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

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 reintroduces the --runtime-args flag for the compose up command and adds support for passing runtime arguments to the configure command. The changes span across command definitions, backend configurations, and documentation to support passing these flags down to the inference engines. The implementation correctly handles parsing flags from both a raw string and a string slice. I've found one critical issue where swapped arguments in an error message formatting call would lead to a panic. Otherwise, the changes look good and include necessary tests and documentation updates.

[sourcery-ai]

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

Prompt for AI Agents

Please address the comments from this code review:

## Individual Comments

### Comment 1
<location> `cmd/cli/commands/configure.go:44` </location>
<code_context>
+		RunE: func(cmd *cobra.Command, args []string) error {
</code_context>

<issue_to_address>
**issue (bug_risk):** Runtime flags slice includes the model name and likely the literal "--"

Here `opts.RuntimeFlags = args[1:]` will still include the literal "--" when present (e.g. `docker model configure foo -- --embeddings` yields `RuntimeFlags = ["--", "--embeddings"]`). To avoid depending on positional slicing and to drop "--" explicitly, consider mirroring the `Args` logic and using `cmd.ArgsLenAtDash()`: treat `args[:argsBeforeDash]` as the model (length 1) and `args[argsBeforeDash+1:]` as runtime flags.
</issue_to_address>

### Comment 2
<location> `cmd/cli/commands/compose.go:99` </location>
<code_context>
+				if err := desktopClient.ComposeUp(ctx, compose.UpRequest{
</code_context>

<issue_to_address>
**suggestion (bug_risk):** Error formatting string and logging call have minor issues and inconsistent formatting

The new `configErrFmtString` has a double space before `"and runtime-flags"`, and the `_ = sendErrorf(...)` line appears mis-indented compared to gofmt output. Also, the format string now has three verbs (`%s`, `%d`, `%s`); please ensure both `sendErrorf` and `fmt.Errorf` pass exactly three matching arguments.
</issue_to_address>

---

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.}

[sourcery-ai]

issue (bug_risk): Runtime flags slice includes the model name and likely the literal "--"

Here opts.RuntimeFlags = args[1:] will still include the literal "--" when present (e.g. docker model configure foo -- --embeddings yields RuntimeFlags = ["--", "--embeddings"]). To avoid depending on positional slicing and to drop "--" explicitly, consider mirroring the Args logic and using cmd.ArgsLenAtDash(): treat args[:argsBeforeDash] as the model (length 1) and args[argsBeforeDash+1:] as runtime flags.