feat: Qwen3 Reranker support

[giladgd]

Description of change

• feat: Qwen3 Reranker support
• fix: handle HuggingFace rate limit response
• fix: adapt to llama.cpp breaking changes

The new Qwen3 Reranker support only works with recent models converted with llama.cpp release b6578 or later.
Here are prequantized models you can use right away:

Model	URI	Size
Qwen3 Reranker 0.6B	hf:giladgd/Qwen3-Reranker-0.6B-GGUF:Q8_0	639.2MB
Qwen3 Reranker 4B	hf:giladgd/Qwen3-Reranker-4B-GGUF:Q4_K_M	2.5GB
Qwen3 Reranker 8B	hf:giladgd/Qwen3-Reranker-8B-GGUF:Q4_K_M	4.7GB

Pull-Request Checklist

• Code is up-to-date with the master branch
• npm run format to apply eslint formatting
• npm run test passes with this change
• This pull request links relevant issues as Fixes #0000
• There are new or updated unit tests validating the change
• Documentation has been updated to reflect this change
• The new commits and pull request title follow conventions explained in pull request guidelines (PRs that do not follow this convention will not be merged)

[ido-pluto]

LGTM

[github-actions]

🎉 This PR is included in version 3.14.0 🎉

The release is available on:

• v3.14.0
• npm package (@latest dist-tag)
• GitHub release
• v3.14.0

Your semantic-release bot 📦🚀