refactor: assemble inference engines through a shared composition root

- add build_engine() to astrai.inference.engine as the single load-place-wire path for InferenceEngine, accepting a checkpoint path or live model/tokenizer plus passthrough engine kwargs
- migrate the server lifespan, generate CLI, humaneval/ifeval evals, and all three demos to build_engine; app._create_engine collapses into a direct call
- export build_engine from astrai and astrai.inference
- parameterize the autoregressive demo with --prompt one-shot continuation plus model path and sampling knobs, exiting cleanly on !exit or EOF
- cover the composition root with unit tests for live-object assembly, kwargs passthrough, and argument validation

astrai/inference/__init__.py

@@ -12,7 +12,7 @@ Modules:
   - engine.py:     Facade (InferenceEngine)
 """
 
-from astrai.inference.engine import InferenceEngine
+from astrai.inference.engine import InferenceEngine, build_engine
 from astrai.inference.network import get_app, run_server
 from astrai.inference.runtime.executor import Executor
 from astrai.inference.runtime.sample import sample
@@ -21,6 +21,7 @@ from astrai.inference.task import STOP, GenerationResult, Task, TaskManager, Tas
 
 __all__ = [
     "InferenceEngine",
+    "build_engine",
     "InferenceScheduler",
     "GenerationResult",
     "Executor",