fix: plugin rl overwriting trainer_cls

[NanoCode012]

Description

The trainer_cls is being overwritten always if a plugin is loaded, even if get_trainer_cls returns None.

This is fixed in #2133 but moved here to be merged first.

Fixes https://github.com/axolotl-ai-cloud/axolotl/issues/2693

Motivation and Context

How has this been tested?

Screenshots (if appropriate)

Types of changes

Social Handles (Optional)

Summary by CodeRabbit

• Bug Fixes
  • Improved reliability when selecting a trainer by preventing accidental replacement with an invalid option.

[coderabbitai[bot]]

## Walkthrough

A safety check was added in the `HFRLTrainerBuilder.build` method to ensure that the `trainer_cls` variable is only overwritten if the plugin manager returns a non-None value. This prevents `trainer_cls` from being set to `None` if the plugin does not provide a trainer class, avoiding potential runtime errors.

## Changes

| File(s)                                      | Change Summary                                                                                      |
|----------------------------------------------|-----------------------------------------------------------------------------------------------------|
| src/axolotl/core/trainer_builder.py          | Added a conditional check so that `trainer_cls` is updated only if the plugin manager returns a non-None value. No other logic was changed. |
| tests/core/test_trainer_builder.py            | Added `TestTrainerClsPlugin` class with a test verifying that trainer class is not None when using the Liger plugin, expecting a specific AttributeError. |

## Assessment against linked issues

| Objective                                                                                                   | Addressed | Explanation                                                                                                 |
|-------------------------------------------------------------------------------------------------------------|-----------|-------------------------------------------------------------------------------------------------------------|
| Prevent `trainer_cls` from becoming `None` when the plugin manager returns `None` (#2693)                   | ✅        |                                                                                                             |
| Ensure training does not fail due to missing `get_trainer_cls` in plugins like Liger (#2693)                | ✅        |                                                                                                             |
| Avoid TypeError during trainer setup when using plugins without `get_trainer_cls` (#2693)                   | ✅        |                                                                                                             |

## Poem

> In the code where trainers dwell,  
> A bug appeared, but now all’s well!  
> No more None to cause dismay,  
> The rabbit hops—training’s okay!  
> With a safety check, we leap ahead,  
> 🐇✨ No more errors to dread!

[!NOTE]

⚡️ AI Code Reviews for VS Code, Cursor, Windsurf

CodeRabbit now has a plugin for VS Code, Cursor and Windsurf. This brings AI code reviews directly in the code editor. Each commit is reviewed immediately, finding bugs before the PR is raised. Seamless context handoff to your AI code agent ensures that you can easily incorporate review feedback. Learn more here.

---

[!NOTE]

⚡️ Faster reviews with caching

CodeRabbit now supports caching for code and dependencies, helping speed up reviews. This means quicker feedback, reduced wait times, and a smoother review experience overall. Cached data is encrypted and stored securely. This feature will be automatically enabled for all accounts on May 30th. To opt out, configure Review - Disable Cache at either the organization or repository level. If you prefer to disable all data retention across your organization, simply turn off the Data Retention setting under your Organization Settings. Enjoy the performance boost—your workflow just got faster.

---

📜 Recent review details

Configuration used: CodeRabbit UI Review profile: CHILL Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 1a2790221fbacf0d33ebcbb68bd0d10009bdeb19 and 5d5036a821f44e84b782f836da95b89943a4b33d.

📒 Files selected for processing (1)

• tests/core/test_trainer_builder.py (2 hunks)

⏰ Context from checks skipped due to timeout of 90000ms (6)

• GitHub Check: PyTest from Source Dist (3.11, 2.7.0)
• GitHub Check: PyTest (3.11, 2.7.0)
• GitHub Check: PyTest from Source Dist (3.11, 2.6.0)
• GitHub Check: PyTest (3.11, 2.6.0)
• GitHub Check: PyTest from Source Dist (3.11, 2.5.1)
• GitHub Check: PyTest (3.11, 2.5.1)

🔇 Additional comments (2)

tests/core/test_trainer_builder.py (2)

11-11: LGTM: Required import for RLType added.

This import is necessary for the new test class to specify the RL type configuration.

---

71-93: Great test coverage for the trainer_cls plugin fix!

This test directly addresses the issue mentioned in #2693 where the trainer_cls attribute was being incorrectly overwritten with None when a plugin was loaded. The test effectively verifies that:

1. When a plugin is configured (LigerPlugin)
2. With a specific RL type (RLType.KTO)
3. The trainer_cls is not being set to None

The test validation approach is clever - by checking for a specific AttributeError rather than a TypeError, you're confirming that execution progresses past the point where a None trainer class would cause a different error.

The comments on lines 85-87 clearly explain the test's intention and expected behavior, making it easy for other developers to understand.

✨ Finishing Touches

• [ ] 📝 Generate Docstrings

---

🪧 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>, please review it.
  • Explain this complex logic.
  • 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 explain this code block.
  • @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 gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read src/utils.ts and explain its main purpose.
  • @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.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

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 generate docstrings to generate docstrings for this PR.
• @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this 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.

[codecov[bot]]

Codecov Report

All modified and coverable lines are covered by tests :white_check_mark:

:loudspeaker: Thoughts on this report? Let us know!

[coderabbitai[bot]]

[!NOTE] Generated docstrings for this pull request at https://github.com/axolotl-ai-cloud/axolotl/pull/2698

[NanoCode012]

Confirmed to work by reported author @Rexhaif https://github.com/axolotl-ai-cloud/axolotl/issues/2693#issuecomment-2894221212