test: add unit tests for ai_provider with mocked LLM responses

[yachikadev]

Description

Added comprehensive unit tests for backend/app/services/ai_provider.py as per issue #212.

• Mocked responses for OpenAI, Groq, and Ollama providers
• Covered success cases, response parsing, fallback behavior, timeout, HTTP errors, and malformed responses
• All tests are fully offline using unittest.mock

Related Issue

Fixes #212

Type of change

• Test addition

Checklist

• I have read CONTRIBUTING.md
• My branch is up to date with main
• I have run pytest -v and all tests pass
• I have not introduced duplicate issues or features
• My PR title follows the format: feat/fix/docs/test: short description
• I have added tests for new features
• No hardcoded secrets or API keys in my code
• This PR is linked to a GSSoC 2026 issue

Screenshots (if frontend change)

N/A (Backend only)

Test evidence

cd backend
pytest tests/test_ai_provider.py -v
All tests passed successfully.

[yachikadev]

Hi @imDarshanGK,

I have added comprehensive unit tests for ai_provider.py as per issue #212.

All tests are passing locally. Please review when possible.

Thank you!

[yachikadev]

Hi @imDarshanGK,

I have been waiting for more than 30 minutes but the Lint workflow is still showing as pending.

Could you please approve or re-run the workflow?

Thank you!