Related Issue

Closes #1645

Description

Adds Nebius Token Factory as a BYOK LLM provider using its OpenAI-compatible API.

This PR:

• Adds Nebius Token Factory to the provider list with default host https://api.tokenfactory.nebius.com/v1.
• Enables model discovery through /models.
• Maps the backend nebius provider alias to openai-compatible-model.
• Adds frontend and backend tests for the provider config and alias handling.
• Updates BYOK and quick start documentation.

Testing Evidence (REQUIRED)

• I have included human-verified testing evidence in this PR.
• This PR includes frontend/UI changes, and I attached screenshot(s) or screen recording(s).
• [x ] No frontend/UI changes in this PR.

Targeted validation passed:

• PATH="/opt/homebrew/opt/node@22/bin:$PATH" ./node_modules/.bin/vitest run test/unit/lib/llm.test.ts
  • Passed.
• cd backend && uv run pytest tests/app/model/test_model_platform.py tests/app/controller/test_model_controller.py tests/app/model/test_chat.py -q
  • Passed: 38 passed.
• Live Nebius Token Factory smoke test:
  • /v1/models returned available models.
  • /v1/chat/completions returned OK with meta-llama/Llama-3.3-70B-Instruct.

Broader suite status:

• Full frontend Vitest suite runs, but has existing unrelated failures: 453 passed, 69 failed, 5 skipped, 6 errors.
• Full backend pytest suite runs, but has existing unrelated failures: 441 passed, 2 failed, 10 skipped.
• The unrelated backend failures are task-lock setup errors in test_mcp_agent_creation and test_new_agent_model_creation.

What is the purpose of this pull request?

• Bug fix
• New Feature
• Documentation update
• Other

Contribution Guidelines Acknowledgement

• I have read and agree to the Eigent Contribution Guideline