Refactor to use SpeziLLM, SpeziChat, and Spezi 1.x

[vishnuravi]

Refactor to use SpeziLLM, SpeziChat, and Spezi 1.x

♻️ Current situation & Problem

The current application uses SpeziML, which has now been replaced by SpeziLLM. SpeziLLM provides significant additional functionality and will simplify the code. It also uses a pre-release version of Spezi, and should be migrated to the latest production release.

⚙️ Release Notes

• The application has been upgraded to Spezi 1.x and refactored to use SpeziLLM.
• The chat view has been migrated to SpeziChat, and an option to export the chat as a text file has been added.
• The SettingsView has been recreated, adhering to Apple Design Guidelines and including additional options to switch the OpenAI model used and change the Open AI API key.
• Strings have been migrated to a string catalogue for easier localization.
• Unnecessary files and code have been cleaned up.

📚 Documentation

In-line documentation has been updated.

✅ Testing

• Additional UI tests have been added for the new SettingsView and the HealthGPTView.
• This PR introduces a --mockMode feature flag to allow for UI testing with mock LLM responses.

Code of Conduct & Contributing Guidelines

By submitting creating this pull request, you agree to follow our Code of Conduct and Contributing Guidelines:

• I agree to follow the Code of Conduct and Contributing Guidelines.

[PSchmiedmayer]

Nice; thank you for looking into this @vishnuravi! 🚀

[vishnuravi]

Nice; thank you for looking into this @vishnuravi! 🚀

Was waiting for the bugfix in StanfordSpezi/SpeziLLM#50 to get merged and released to finish this. Should be able to finish now.

[PSchmiedmayer]

Very nice; thanks for all the work here @vishnuravi 🚀

[codecov]

Codecov Report

Attention: Patch coverage is 94.44444% with 13 lines in your changes are missing coverage. Please review.

Project coverage is 92.91%. Comparing base (0d5fee8) to head (132cd49).

Additional details and impacted files

@@            Coverage Diff             @@
##             main      #36      +/-   ##
==========================================
+ Coverage   87.52%   92.91%   +5.40%     
==========================================
  Files          25       24       -1     
  Lines         785      832      +47     
==========================================
+ Hits          687      773      +86     
+ Misses         98       59      -39     

Files	Coverage Δ
...ealthGPT/HealthGPT/HealthDataFetcher+Process.swift	100.00% <100.00%> (ø)
HealthGPT/HealthGPT/HealthDataFetcher.swift	89.75% <100.00%> (-0.33%)	⬇️
HealthGPT/HealthGPT/PromptGenerator.swift	100.00% <100.00%> (ø)
HealthGPT/HealthGPTAppDelegate.swift	100.00% <100.00%> (ø)
HealthGPT/HealthGPTApplication.swift	100.00% <100.00%> (ø)
HealthGPT/HealthGPTStandard.swift	0.00% <ø> (ø)
HealthGPT/Onboarding/Disclaimer.swift	90.33% <ø> (ø)
HealthGPT/Onboarding/OnboardingFlow.swift	82.36% <ø> (ø)
HealthGPT/Onboarding/OpenAIAPIKey.swift	100.00% <100.00%> (ø)
HealthGPT/Onboarding/OpenAIModelSelection.swift	100.00% <100.00%> (ø)
... and 8 more

---

Continue to review full report in Codecov by Sentry.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 0d5fee8...132cd49. Read the comment docs.

[philippzagar]

Thanks @vishnuravi for the update to SpeziLLM, greatly appreciated!
Only had some minor comments and improvement suggestions, no need for a second round of review