feat(llm): Introduce type safety checks

[Prajna1999]

Issue #1079

Summary

• Before: Liberal type safety in LLM calls.
• Now: Introduces strict type safety for LLM calls.

• New Features

  • Added strongly typed configuration for text, speech-to-text, and text-to-speech models.
  • Improved speech-to-speech language validation and standardized language formatting.
  • Audio responses now provide signed URLs for playback.

• Bug Fixes

  • Improved compatibility with varied configuration formats across model providers.
  • Preserved explicitly configured temperature values, including zero.
  • Improved tracing and evaluation reliability for typed model settings.
  • Improved validation and handling of proxy and provider configuration values.

Checklist

Before submitting a pull request, please ensure that you mark these task.

• Ran fastapi run --reload app/main.py or docker compose up in the repository root and test.
• If you've fixed a bug or added code that is tested and has test cases.

Notes

Please add here if any other information is required for the reviewer.

Summary by CodeRabbit

• New Features

  • Added distinct configuration types for text, speech-to-text, and text-to-speech.
  • Added language alias support and normalized speech-to-speech language codes.
  • Audio responses now provide accessible signed URLs when available.
  • Added automatic audio-provider selection when none is specified.

• Bug Fixes

  • Improved compatibility with saved and typed configuration data.
  • Standardized provider parameter handling and omitted unnecessary defaults.

• Tests

  • Expanded coverage for audio, language validation, configuration, and serialization.