feat(routing): 引入多执行池智能调度

将 Worker 发现、路由画像、容量与执行传输抽象为平台无关接口,新增 Kubernetes 和静态容量适配器,并以 shadow 模式接入生产配置。

实现网络与容量评分、路由防抖、池队列、同步 Worker 租约、一次性执行令牌,以及提交状态不明时禁止重复分配的安全语义。

新增 0105 兼容迁移、管理接口、指标、OpenAPI 和回归测试。已执行全量 Go 测试、go vet、OpenAPI、迁移安全、Compose 与 Kustomize 验证。
This commit is contained in:
2026-08-05 22:25:37 +08:00
parent 03c0873649
commit 7786692d32
58 changed files with 4510 additions and 348 deletions
@@ -44,6 +44,7 @@ data:
AI_GATEWAY_WORKER_MIN_REPLICAS_HONGKONG: "1"
AI_GATEWAY_WORKER_MAX_REPLICAS_NINGBO: "2"
AI_GATEWAY_WORKER_MAX_REPLICAS_HONGKONG: "2"
AI_GATEWAY_CAPACITY_POOLS: '[{"id":"ningbo","adapterRef":"ningbo","bootstrapReplicas":1,"minReplicas":1,"maxReplicas":2},{"id":"hongkong","adapterRef":"hongkong","bootstrapReplicas":1,"minReplicas":1,"maxReplicas":2}]'
AI_GATEWAY_WORKER_TARGET_OUTSTANDING_PER_REPLICA: "48"
AI_GATEWAY_WORKER_SCALE_UP_WINDOW_SECONDS: "20"
AI_GATEWAY_WORKER_SCALE_DOWN_STABILIZATION_SECONDS: "600"