feat(opencode): added logic to probe loaded models from lmstudio and ollama

[goniz]

What does this PR do?

• Added core logic for enumerating loaded models from Ollama and LMStudio in packages/opencode/src/provider/local/index.ts
• Added debug cli opencode debug provider probe <type: ollama|lmstudio> <url: string>

How did you verify your code works?

[github-actions]

Thanks for your contribution!

This PR doesn't have a linked issue. All PRs must reference an existing issue.

Please:

1. Open an issue describing the bug/feature (if one doesn't exist)
2. Add Fixes #<number> or Closes #<number> to this PR description

See CONTRIBUTING.md for details.

[github-actions]

The following comment was made by an LLM, it may be inaccurate:

Potential Duplicate Found

PR #8359 - feat(opencode): add auto model detection for OpenAI-compatible providers
#8359

Why it might be related:
This PR appears to be related to auto model detection for providers, which overlaps with the current PR's goal of probing/enumerating loaded models from local providers (LMStudio and Ollama). Both PRs deal with automatic model discovery and detection logic within the provider system.

[willie]

Fantastic work, I need this.

[goniz]

Closing in favor of #11951