refactor: 大规模模块拆分与代码精简，新增 ai-pipeline/data-contracts 独立 crate

- 新增 aether-ai-pipeline 和 aether-data-contracts crate，将 pipeline 逻辑与数据契约从 gateway 中解耦
- 重构 admin handlers：拆分单体模块为 auth/billing/endpoint/features/model/observability/provider/system 等独立子模块
- 合并 chat/cli 重复代码路径：精简 conversion、finalize、planner 中的 sync/chat/cli 分支
- 重构 scheduler/executor/data 层，引入 facade 模式降低模块间耦合
- 移除冗余的 intent 模块，将 plan_fallback/policy/stream_path/sync_path 迁移至 executor
- 前端适配：调整 admin API 调用和 provider 模型测试对话框

apps/aether-gateway/src/scheduler/affinity.rs

@@ -0,0 +1,23 @@
+use std::time::Duration;
+
+use aether_scheduler_core::{
+    build_scheduler_affinity_cache_key_for_api_key_id, SchedulerAffinityTarget,
+};
+
+use super::state::SchedulerRuntimeState;
+
+pub(crate) const SCHEDULER_AFFINITY_TTL: Duration = Duration::from_secs(300);
+
+pub(crate) fn read_cached_scheduler_affinity_target(
+    state: &(impl SchedulerRuntimeState + ?Sized),
+    api_key_id: &str,
+    api_format: &str,
+    global_model_name: &str,
+) -> Option<SchedulerAffinityTarget> {
+    let cache_key = build_scheduler_affinity_cache_key_for_api_key_id(
+        api_key_id,
+        api_format,
+        global_model_name,
+    )?;
+    state.read_cached_scheduler_affinity_target(&cache_key, SCHEDULER_AFFINITY_TTL)
+}