refactor: split infer core into subpackages by concern

- Eliminate core/ directory into cache/, runtime/, network/ subpackages plus flat modules
- Split cache.py (647 lines) into cache/{buffer,strategy,pool}.py by layer
- Add explicit ContiguousStrategy, make AllocationStrategy a real ABC
- Move TaskCacheState to cache/strategy.py, drop string forward references
- Rename api/ to network/, server.py to app.py
- Move sample.py into runtime/ alongside executor and graph
- Simplify TaskCacheManager.__init__ to single pool param
- Expose pool.strategy and pool.req_pool as public properties
- Fix KVCache import in attention_backend.py (TYPE_CHECKING guard)
- Fix steady-state decode reading uninitialized position_ids on first step

astrai/inference/network/__init__.py

@@ -0,0 +1,39 @@
+"""Inference API: protocol handler, stop checker, tool parsers, and FastAPI server.
+
+``app`` is no longer a module-level global. Use :func:`get_app` to access the
+lazy singleton FastAPI instance.
+"""
+
+from astrai.inference.network.app import (
+    AnthropicMessage,
+    ChatCompletionRequest,
+    ChatMessage,
+    FunctionDef,
+    MessagesRequest,
+    ToolDef,
+    get_app,
+    run_server,
+)
+from astrai.inference.network.protocol import GenContext, ProtocolHandler, StopChecker
+from astrai.inference.network.tool_parser import (
+    BaseToolParser,
+    SimpleJsonToolParser,
+    ToolParserFactory,
+)
+
+__all__ = [
+    "ProtocolHandler",
+    "StopChecker",
+    "GenContext",
+    "BaseToolParser",
+    "SimpleJsonToolParser",
+    "ToolParserFactory",
+    "AnthropicMessage",
+    "ChatCompletionRequest",
+    "ChatMessage",
+    "FunctionDef",
+    "ToolDef",
+    "MessagesRequest",
+    "get_app",
+    "run_server",
+]