fix: using ollama provider for ollama llama4 model

[nathanfallet]

Hello, thank you for the project!

Just spotted a small mistake when trying to use OllamaModels.Meta.LLAMA_4; It's configured with LLMProvider.Meta instead of LLMProvider.Ollama, which makes it unusable (throws a IllegalArgumentException: Model not supported by Ollama). So I fixed it!

---

Type of the change

• New feature
• Bug fix
• Documentation fix

Checklist for all pull requests

• The pull request has a description of the proposed change
• I read the Contributing Guidelines before opening the pull request
• The pull request uses develop as the base branch
• Tests for the changes have been added (N/A)
• All new and existing tests passed

Additional steps for pull requests adding a new feature

• An issue describing the proposed change exists
• The pull request includes a link to the issue
• The change was discussed and approved in the issue
• Docs have been added / updated

[Rizzen]

@nathanfallet could you please rebase your branch onto latest dev? I worried about failing Qodana check

[nathanfallet]

Done. Thank you!
But since it is a very small change, it must not break any build I guess.

[nathanfallet]

Starting from version 2023.2 release versions of Qodana Linters require connection to Qodana Cloud.
To continue using Qodana, please ensure you have an access token and provide the token as the QODANA_TOKEN environment variable.
Obtain your token by registering at https://qodana.cloud
For more details, please visit: https://www.jetbrains.com/help/qodana/cloud-quickstart.html
We also offer Community versions as an alternative. You can find them here: https://www.jetbrains.com/help/qodana/linters.html
✗ Qodana exited with code 1

I'm not a Qodana expert, but looking at the logs it looks like it's a token issue more than an issue with the changes itself