[aiapienthusiast]

Adds Cheaper Inference as an LLM provider.
It uses the same pattern as #8 (Atlas Cloud).
Cheaper Inference is an OpenAI-compatible LLM gateway.
One API key gives access to models from several labs.

ChatCheaperInference extends ChatOpenAI and only sets the base URL, the API key env var and the provider name.

Changes

• windows_use/providers/cheaper_inference/ — new ChatCheaperInference class.
  • Base URL: https://api.cheaperinference.com/v1.
  • Key: CHEAPER_INFERENCE_API_KEY. Optional base URL override: CHEAPER_INFERENCE_API_BASE.
  • Default model: gpt-5.4-mini.
• windows_use/providers/__init__.py — export ChatCheaperInference.
• windows_use/cli/registry.py — provider, models, API key flag and display name.
• windows_use/cli/setup.py — create_llm branch and env var map entry.
• README.md — provider table row and a short usage example.
• tests/unit/providers/test_cheaper_inference.py — client defaults and CLI registry entries.

Testing

• pytest tests/unit/providers tests/unit/test_openai_events.py tests/unit/test_llm_events.py — 11 passed.
• ruff check and ruff format --check on the changed files — pass.
• create_llm("cheaper_inference", "gpt-5.4-mini") returns ChatCheaperInference with the expected base URL.
• I ran the tests on Linux, so the package __init__ imports that need Windows (comtypes) were stubbed. The full suite was not run.