add model selection backend support

[chinmaychahar]

Summary

Add backend support for user-selectable LLM models (Issue - #87).

• Dynamic model discovery via GET /models endpoint
• Optional model field on POST /generate-note to override the server default
• preferred_model persisted in user settings (MongoDB)
• Graceful fallback to server default when provider API is unreachable

Testing

• I have tested these changes locally
• I have run all relevant automated tests
• I have verified this does not break existing workflows
• For changes that can be tested in UI, I have included screenshots or gif animations of the changes.

How I Tested

• I ran make test and all backend tests pass
• Added new test file backend/tests/llm_providers/test_model_selection.py
• Verified GET /models endpoint returns expected shape via test client
• Verified preferred_model field persists and returns correctly in user settings endpoints

[linux-foundation-easycla]

The committers listed above are authorized under a signed CLA.

• ✅ login: chinmaychahar / name: chinmaychahar (2864580)

[jspada200]

Great start @chinmaychahar ! I approved the pipeline to run. Let me know if you have any issues with the automated pipelines.

[chinmaychahar]

Thanks! I'll take a look at the failing tests

[chinmaychahar]

I removed the server-side caching, made sens that the frontend query cache handles that already, let me know if anything else needs changing

[jspada200]

Looks good to me! I wish the openai API had a better way to filter the models but it looks like the only way is the way you did it! This PR looks good, just needs to have the pipeline resolved

[chinmaychahar]

Thanks! I'll take an action idea to fix the current code format failure. And then get started on the frontend changes if there are no other comments