refactor: 重构 inference 模块架构，引入设计模式并分组文件

- 新增 protocol.py 协议层，Template Method 模式消除流/非流分支 45% 重复
- SSEBuilder 统一 SSE 构造，StopChecker 独立 stop_sequence 检测
- AnthropicHandler 追踪已产出文本，修复 stop 时重复 delta
- server.py 路由从约 100 行缩减至 3 行
- 拆分为 core/（cache/executor/scheduler/task）和 api/（protocol/server）
- 外部保持二级导入路径（from astrai.inference import Name）
- 删除所有分隔线注释，代码按语义自然分组

astrai/inference/core/__init__.py

@@ -0,0 +1,28 @@
+"""Inference core: cache, executor, scheduler, task management."""
+
+from astrai.inference.core.cache import (
+    CacheView,
+    PagedCache,
+    PagePool,
+    PrefixCache,
+    TaskTable,
+    page_hash,
+)
+from astrai.inference.core.executor import Executor
+from astrai.inference.core.scheduler import InferenceScheduler
+from astrai.inference.core.task import STOP, Task, TaskManager, TaskStatus
+
+__all__ = [
+    "CacheView",
+    "PagedCache",
+    "PagePool",
+    "PrefixCache",
+    "TaskTable",
+    "page_hash",
+    "Executor",
+    "InferenceScheduler",
+    "STOP",
+    "Task",
+    "TaskManager",
+    "TaskStatus",
+]