feat: add native LLaMA.cpp local provider support

[it-education-md]

Related Issue

Closes #333

Description

This PR adds native LLaMA.cpp support as a dedicated Local Model provider in Settings.

It includes:

• LLaMA.cpp provider entry in Local Models (selection/default/save/reset flow)
• llama-server integration with /v1/health and /v1/models
• backend platform compatibility mapping (llama.cpp -> openai-compatible-model)
• model suggestion updates + tests
• docs updates for Local Model / Quick Start

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).
• No frontend/UI changes in this PR.

Evidence:

• pnpm -s eslint src/pages/Agents/Models.tsx (pass)
• cd backend && uv run pytest tests/app/model/test_model_platform.py tests/app/component/test_model_suggestions.py -q (pass)
• Manual verification with local llama-server:
  • /v1/health reachable
  • /v1/models returns model list
  • Save + set default in Settings > Models > Local > LLaMA.cpp works
  • Screenshot attached

Video recording:

eigent-llamacpp.mp4

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

[bytecii]

Did some refactoring and tested on ollama

@it-education-md can you help to test on the llama.cpp again to see whether it works? if there is no other issue I will approve and merge the PR. Thanks.

[it-education-md]

@it-education-md can you help to test on the llama.cpp again to see whether it works? if there is no other issue I will approve and merge the PR. Thanks.

Sure, checking now.

[it-education-md]

Screencast.from.2026-03-02.06-18-18.mp4

@bytecii Cool, it worked for me!