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

astrai/inference/engine.py

@@ -156,9 +156,8 @@ class InferenceEngine:
         async def _agen():
             loop = asyncio.get_event_loop()
             while True:
-                try:
-                    token = await loop.run_in_executor(None, next, sync_gen)
-                except StopIteration:
+                token = await loop.run_in_executor(None, next, sync_gen, None)
+                if token is None:
                     break
                 yield token