test: refactor tests and fix inference edge cases

- Convert protocol and MoE test classes to plain functions
- Add real server/engine integration and generate_async tests
- Isolate test model per test and use pytest tmp_path
- Reset FastAPI engine state after inference tests
- Fix generate_async StopIteration handling on Python 3.12
- Fix HF adapter MoE dense/shared and Gemma qk_norm mapping
- Correct dev dependency httpx2 to httpx

pyproject.toml

@@ -31,7 +31,7 @@ classifiers = [
 urls = { Homepage = "https://github.com/ViperEkura/AstrAI" }
 
 [project.optional-dependencies]
-dev = ["pytest==9.0.2", "ruff", "httpx2"]
+dev = ["pytest==9.0.2", "ruff", "httpx"]
 flash = ["flash-attn>=2.6"]
 
 [tool.setuptools.packages.find]