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/__init__.py

@@ -17,7 +17,7 @@ from astrai.dataset import (
     StoreFactory,
 )
 from astrai.factory import BaseFactory
-from astrai.inference import InferenceEngine, get_app, run_server, sample
+from astrai.inference import InferenceEngine, build_engine, get_app, run_server, sample
 from astrai.inference.network import ProtocolHandler
 from astrai.inference.runtime.sample import SamplingPipeline
 from astrai.logging import setup_logging
@@ -67,6 +67,7 @@ __all__ = [
     "EncoderConfig",
     "ExecutorFactory",
     "InferenceEngine",
+    "build_engine",
     "LoRAConfig",
     "Pipeline",
     "PipelineConfig",