chore(release): v3.26.2

Co-authored-by: Codex <noreply@openai.com>
fix(openai): keep turn rate limits scoped to the request
2026-11-07 00:05:49 +00:00 · 2026-10-14 16:16:30 +08:00 · 2026-10-14 16:01:49 +08:00 · 2026-10-14 15:54:47 +08:00 · 2026-10-14 14:30:58 +08:00 · 2026-10-14 13:50:51 +08:00
856 changed files with 61702 additions and 31152 deletions
@@ -6,7 +6,7 @@
 ## 清单与处理器

 - `publisher` 与机器短名 `name` 派生插件 ID，`displayName` 用于展示；复制示例后同时调整扩展项 ID 与注册结果
- `contributes` 每种能力最多一项，普通贡献项可省略派生 ID、能力版本和固定阶段；中间件必须声明版本 `3` 并显式选择阶段。自定义完整扩展项 ID 属于自己的插件命名空间，运行注册与规范化清单一致
+- `contributes` 每种能力最多一项，普通贡献项可省略派生 ID、能力版本和固定阶段；中间件必须声明版本 `4` 并显式选择阶段，上游适配器必须声明版本 `2`。自定义完整扩展项 ID 属于自己的插件命名空间，运行注册与规范化清单一致
 - 作者清单用 `Manifest::from_author_slice` 规范化，不手写 `package`、固定阶段或重复注册；CLI 生成平台、协议与资源摘要，版本范围不能使用全版本通配
 - 安装后宿主会按 `configurationSchema` 准备默认配置，配置完整即可启用；默认绑定的空范围不限制请求。需要业务参数时声明真实必填项，通过 `secretFields` 声明敏感字段，不依赖用户再走一遍自建安装向导
 - Rust 插件只依赖公开 `gateway-plugin-sdk`；需要异步会话辅助时开启 `io`，使用 `PluginSession` 管理握手、回调关联、流控、取消和关闭
@@ -177,8 +177,6 @@ jobs:
          host_path = "backend/crates/gateway-plugin/runtime/plugin-host-compatibility.json"
          host = JSON.parse(File.read(host_path))
          abort "Invalid plugin host compatibility declaration: #{host_path}" unless host["schema_version"] == 2
-          # 保留旧更新器可解析的传输格式，实际支持范围仍取自当前宿主合同。
-          host = host.merge("schema_version" => 1, "permissions" => [])
          # 清单只依赖版本与兼容声明，平台归档和镜像消费同一份封口结果。
          manifest = {
            "schema_version" => 1,
@@ -21,7 +21,7 @@

 ## 快速预览

-无需部署，打开 [快速预览服务](https://codex-proxy-rs.ainz.cc) 即可体验管理端的系统概览、账号分组、代理管理与用量统计
+无需部署即可体验管理端的系统概览、账号分组、代理管理与用量统计：

 | 登录信息 | 默认值 |
 | --- | --- |
@@ -53,8 +53,7 @@ curl -fsSL https://raw.githubusercontent.com/zyycn/codex-proxy-rs/main/deploy/in
 [安装脚本](deploy/install.sh) 默认安装到当前目录下的 `codex-proxy-rs/`，下载同一正式 Release 的部署文件，
 自动生成密码、设置目录权限并启动服务

-完成后会显示访问地址和管理员密码，请保存密码，再按下方步骤
-[添加账号与客户端密钥](#添加账号与客户端密钥)
+完成后保存显示的访问地址和管理员密码，再[登录管理端](#登录管理端)并[添加账号与客户端密钥](#添加账号与客户端密钥)

 可在执行 `bash install.sh` 时传入环境变量：

@@ -303,7 +303,7 @@ dependencies = [
 "lru",
 "percent-encoding",
 "regex-lite",
- "sha2 0.11.0",
+ "sha2",
 "tracing",
 "url",
 ]
@@ -325,7 +325,7 @@ dependencies = [
 "hmac",
 "http",
 "percent-encoding",
- "sha2 0.11.0",
+ "sha2",
 "time",
 "tracing",
 ]
@@ -358,7 +358,7 @@ dependencies = [
 "md-5",
 "pin-project-lite",
 "sha1 0.11.0",
- "sha2 0.11.0",
+ "sha2",
 "tracing",
 ]

@@ -877,7 +877,7 @@ dependencies = [
 "gateway-plugin-sdk",
 "hex",
 "serde_json",
- "sha2 0.11.0",
+ "sha2",
 "tar",
 "tempfile",
 "thiserror",
@@ -1681,6 +1681,7 @@ dependencies = [
 "gateway-core",
 "heck",
 "hex",
+ "hkdf",
 "prettyplease",
 "quote",
 "rand_core 0.6.4",
@@ -1688,7 +1689,7 @@ dependencies = [
 "semver",
 "serde",
 "serde_json",
- "sha2 0.11.0",
+ "sha2",
 "subtle",
 "syn 3.0.6",
 "tempfile",
@@ -1719,7 +1720,7 @@ dependencies = [
 "secrecy",
 "serde",
 "serde_json",
- "sha2 0.11.0",
+ "sha2",
 "thiserror",
 "tokio",
 "tokio-tungstenite 0.29.0",
@@ -1745,12 +1746,11 @@ dependencies = [
 "futures",
 "futures-timer",
 "http",
- "http-body",
 "http-body-util",
 "semver",
 "serde",
 "serde_json",
- "sha2 0.11.0",
+ "sha2",
 "thiserror",
 "tracing",
 "url",
@@ -1790,7 +1790,7 @@ dependencies = [
 "serde_ignored",
 "serde_json",
 "serde_path_to_error",
- "sha2 0.11.0",
+ "sha2",
 "tar",
 "tempfile",
 "thiserror",
@@ -1831,7 +1831,7 @@ dependencies = [
 "semver",
 "serde",
 "serde_json",
- "sha2 0.11.0",
+ "sha2",
 "sqlx",
 "tar",
 "tempfile",
@@ -1859,6 +1859,7 @@ dependencies = [
 name = "gateway-protocol"
 version = "0.0.0"
 dependencies = [
+ "http",
 "httpdate",
 "memchr",
 "serde",
@@ -1887,7 +1888,7 @@ dependencies = [
 "secrecy",
 "serde",
 "serde_json",
- "sha2 0.11.0",
+ "sha2",
 "sqlx",
 "tempfile",
 "thiserror",
@@ -1980,9 +1981,9 @@ dependencies = [

 [[package]]
 name = "h2"
-version = "0.4.19"
+version = "0.4.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ef8e5e5a340588f4452631496976cf8636d4a7ecf600239fdc27615d2530bc16"
+checksum = "7d29020232d6aa3fb1daca64c1127cf662cf97f254ae16c18c05b8ab635fc118"
 dependencies = [
 "atomic-waker",
 "bytes",
@@ -2446,9 +2447,9 @@ dependencies = [

 [[package]]
 name = "jsonschema"
-version = "0.58.4"
+version = "0.58.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5761b0ca0a31464030d7c2a98087fde3124ebb5e09b5a112cdb815f03b8ee150"
+checksum = "f622c574a29fb3034a0a90645afee194dfedc75fc124228801b6e77041075bd1"
 dependencies = [
 "ahash",
 "bytecount",
@@ -2474,18 +2475,18 @@ dependencies = [

 [[package]]
 name = "jsonschema-regex"
-version = "0.58.5"
+version = "0.58.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "854e9e22c420535035e95eed240cbfb4a5f4b7da74d122d63144e0c31926dbfd"
+checksum = "a968fffd387b2ab005bf00c1851f5d26e90df05b6f7ad609ed0d620033cca5e7"
 dependencies = [
 "regex-syntax",
 ]

 [[package]]
 name = "jsonschema-value"
-version = "0.58.5"
+version = "0.58.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4e3bfac11ac357ec620880025757d38c67da8fd5b9ef5024d19f0f360002b4ca"
+checksum = "39b7670345e5ce87371339d13705dbb9276b7e3e934bbe1efa2c6734a1f65a96"
 dependencies = [
 "ahash",
 "bytecount",
@@ -2525,6 +2526,15 @@ version = "0.2.186"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "68ab91017fe16c622486840e4c83c9a37afeff978bd239b5293d61ece587de66"

+[[package]]
+name = "libredox"
+version = "0.1.25"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "61ff90caf6077a803a240f62fdbe88645a890bbca49ef8174c3cb0404362171d"
+dependencies = [
+ "libc",
+]
+
 [[package]]
 name = "libsqlite3-sys"
 version = "0.37.0"
@@ -2842,6 +2852,24 @@ dependencies = [
 "libc",
 ]

+[[package]]
+name = "objc2-core-foundation"
+version = "0.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2a180dd8642fa45cdb7dd721cd4c11b1cadd4929ce112ebd8b9f5803cc79d536"
+dependencies = [
+ "bitflags",
+]
+
+[[package]]
+name = "objc2-system-configuration"
+version = "0.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7216bd11cbda54ccabcab84d523dc93b858ec75ecfb3a7d89513fa22464da396"
+dependencies = [
+ "objc2-core-foundation",
+]
+
 [[package]]
 name = "once_cell"
 version = "1.21.4"
@@ -2930,7 +2958,7 @@ dependencies = [
 "elliptic-curve",
 "primefield",
 "primeorder",
- "sha2 0.11.0",
+ "sha2",
 ]

 [[package]]
@@ -3262,6 +3290,7 @@ dependencies = [
 "native-tls",
 "openssl",
 "openssl-sys",
+ "regex",
 "reqwest",
 "roxmltree",
 "rustls",
@@ -3271,7 +3300,7 @@ dependencies = [
 "semver",
 "serde",
 "serde_json",
- "sha2 0.11.0",
+ "sha2",
 "subtle",
 "tar",
 "tempfile",
@@ -3313,7 +3342,7 @@ dependencies = [
 "semver",
 "serde",
 "serde_json",
- "sha2 0.11.0",
+ "sha2",
 "thiserror",
 "tokio",
 "tracing",
@@ -3373,9 +3402,9 @@ dependencies = [

 [[package]]
 name = "quinn-proto"
-version = "0.11.16"
+version = "0.11.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2f4bfc015262b9df63c8845072ce59068853ff5872180c2ce2f13038b970e560"
+checksum = "a9746dbde176634f4f2f1faf2404e30a31b2bc1e9cafb5329c95d8177a18c9fc"
 dependencies = [
 "bytes",
 "getrandom 0.4.3",
@@ -3559,9 +3588,9 @@ dependencies = [

 [[package]]
 name = "referencing"
-version = "0.58.5"
+version = "0.58.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "590efadb0a669f1712c1e3ab810a55d4c3d20d0127c455f7236dd0710aba0346"
+checksum = "558f3855529c0a7e78a48e409fa653456e55f1b167eab4109c16a255b7727e3f"
 dependencies = [
 "ahash",
 "fluent-uri",
@@ -3576,9 +3605,9 @@ dependencies = [

 [[package]]
 name = "regex"
-version = "1.13.0"
+version = "1.13.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2a0e75113e14dc5acb068cd0786884f214f1312650a3d36d269f5c4f3cdee8a2"
+checksum = "f020237b6c8eed93db2e2cb53c00c60a8e1bc73da7d073199a1180401450218d"
 dependencies = [
 "aho-corasick",
 "memchr",
@@ -4024,17 +4053,6 @@ version = "1.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bbfa15b3dddfee50a0fff136974b3e1bde555604ba463834a7eb7deb6417705d"

-[[package]]
-name = "sha2"
-version = "0.10.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a7507d819769d01a365ab707794a4084392c824f54a7a6a7862f8c3d0892b283"
-dependencies = [
- "cfg-if",
- "cpufeatures 0.2.17",
- "digest 0.10.7",
-]
-
 [[package]]
 name = "sha2"
 version = "0.11.0"
@@ -4155,8 +4173,7 @@ dependencies = [
 [[package]]
 name = "sqlx"
 version = "0.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "378620ccc25c62c89d8be1c819e76a88d59bdcc3304733330788948e619bfd71"
+source = "git+https://github.com/transact-rs/sqlx?rev=f1e94ec34dd5f11ad6488a3a8ac7988439a3f757#f1e94ec34dd5f11ad6488a3a8ac7988439a3f757"
 dependencies = [
 "sqlx-core",
 "sqlx-macros",
@@ -4168,8 +4185,7 @@ dependencies = [
 [[package]]
 name = "sqlx-core"
 version = "0.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "05b44e85bf579a8eeb4ceaa77a3a523baf2bf0e9bac7e40f405d537b5d2d5ccb"
+source = "git+https://github.com/transact-rs/sqlx?rev=f1e94ec34dd5f11ad6488a3a8ac7988439a3f757#f1e94ec34dd5f11ad6488a3a8ac7988439a3f757"
 dependencies = [
 "base64 0.22.1",
 "bytes",
@@ -4192,7 +4208,7 @@ dependencies = [
 "rustls",
 "serde",
 "serde_json",
- "sha2 0.10.9",
+ "sha2",
 "smallvec",
 "thiserror",
 "tokio",
@@ -4206,8 +4222,7 @@ dependencies = [
 [[package]]
 name = "sqlx-macros"
 version = "0.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bd2b84f2bc39a5705ef27ec785a11c934a41bbd4a24941e257927cddc26b60bf"
+source = "git+https://github.com/transact-rs/sqlx?rev=f1e94ec34dd5f11ad6488a3a8ac7988439a3f757#f1e94ec34dd5f11ad6488a3a8ac7988439a3f757"
 dependencies = [
 "proc-macro2",
 "quote",
@@ -4219,8 +4234,7 @@ dependencies = [
 [[package]]
 name = "sqlx-macros-core"
 version = "0.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fb8d96de5fdc85a5c4ec813432b523ec637e80ba98f046555f75f7908ddac7c3"
+source = "git+https://github.com/transact-rs/sqlx?rev=f1e94ec34dd5f11ad6488a3a8ac7988439a3f757#f1e94ec34dd5f11ad6488a3a8ac7988439a3f757"
 dependencies = [
 "cfg-if",
 "dotenvy",
@@ -4231,7 +4245,7 @@ dependencies = [
 "quote",
 "serde",
 "serde_json",
- "sha2 0.10.9",
+ "sha2",
 "sqlx-core",
 "sqlx-mysql",
 "sqlx-postgres",
@@ -4245,8 +4259,7 @@ dependencies = [
 [[package]]
 name = "sqlx-mysql"
 version = "0.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "90b8020fe17c5f2c245bfa2505d7ef59c5604839527c740266ad2214acebea27"
+source = "git+https://github.com/transact-rs/sqlx?rev=f1e94ec34dd5f11ad6488a3a8ac7988439a3f757#f1e94ec34dd5f11ad6488a3a8ac7988439a3f757"
 dependencies = [
 "bitflags",
 "byteorder",
@@ -4263,7 +4276,7 @@ dependencies = [
 "percent-encoding",
 "serde",
 "sha1 0.11.0",
- "sha2 0.11.0",
+ "sha2",
 "sqlx-core",
 "thiserror",
 "tracing",
@@ -4273,8 +4286,7 @@ dependencies = [
 [[package]]
 name = "sqlx-postgres"
 version = "0.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "87a2bdd6e83f6b3ea525ca9fee568030508b58355a43d0b2c1674d5f79dcd65e"
+source = "git+https://github.com/transact-rs/sqlx?rev=f1e94ec34dd5f11ad6488a3a8ac7988439a3f757#f1e94ec34dd5f11ad6488a3a8ac7988439a3f757"
 dependencies = [
 "atoi",
 "base64 0.22.1",
@@ -4297,7 +4309,7 @@ dependencies = [
 "rand 0.10.2",
 "serde",
 "serde_json",
- "sha2 0.11.0",
+ "sha2",
 "smallvec",
 "sqlx-core",
 "stringprep",
@@ -4310,8 +4322,7 @@ dependencies = [
 [[package]]
 name = "sqlx-sqlite"
 version = "0.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "488e99c397a62007e4229aec669a179816339afc6d2620ca6fa420dbee2e982c"
+source = "git+https://github.com/transact-rs/sqlx?rev=f1e94ec34dd5f11ad6488a3a8ac7988439a3f757#f1e94ec34dd5f11ad6488a3a8ac7988439a3f757"
 dependencies = [
 "atoi",
 "chrono",
@@ -4996,9 +5007,9 @@ checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"

 [[package]]
 name = "uuid"
-version = "1.26.1"
+version = "1.27.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2ef6dac1e96601b4fb3acccccff2139741fcb757cb9a36089bf5be91cfb285ce"
+checksum = "97277d36b9c3ace13e58fa6e753f8b0bbbf302a18dd193240d70f9e29681059a"
 dependencies = [
 "getrandom 0.4.3",
 "js-sys",
@@ -5183,6 +5194,12 @@ name = "whoami"
 version = "2.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "998767ef88740d1f5b0682a9c53c24431453923962269c2db68ee43788c5a40d"
+dependencies = [
+ "libc",
+ "libredox",
+ "objc2-system-configuration",
+ "web-sys",
+]

 [[package]]
 name = "winapi"
@@ -5530,9 +5547,9 @@ dependencies = [

 [[package]]
 name = "zeroize"
-version = "1.9.0"
+version = "1.9.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e13c156562582aa81c60cb29407084cdb54c4164760106ab78e6c5b0858cf64e"
+checksum = "e13084392c5e4bc371903e2935a5eaeed24905a7511356b883835e18a78f6879"
 dependencies = [
 "zeroize_derive",
 ]
@@ -59,3 +59,5 @@ panic = "abort"
 [patch.crates-io]
 # Upstream SOCKS IPv6 fix; remove once a release includes hyperium/hyper-util#302.
 hyper-util = { git = "https://github.com/hyperium/hyper-util", rev = "191b1acf0a6b18e807e4abf5a6d4a7c47979ecd6" }
+# 固定上游 BEGIN 取消回滚修复，避免未结束事务复用；见 transact-rs/sqlx#4394
+sqlx = { git = "https://github.com/transact-rs/sqlx", rev = "f1e94ec34dd5f11ad6488a3a8ac7988439a3f757" }
@@ -93,7 +93,7 @@ async fn execute(
        Some(plugin_runtime.clone()),
        Some(plugin_runtime.observer_registry()),
        Some(plugin_runtime.policy_registry()),
-        Some(plugin_runtime.middleware_registry()),
+        Some(plugin_runtime.execution_registry()),
    );
    let management = ManagementPorts::new(&store, providers.admin.clone(), core.snapshot_control());
    or_shutdown!(plugin_runtime, management.bind(&plugin_runtime));
@@ -110,7 +110,7 @@ async fn execute(
        providers.admin,
        std::sync::Arc::new(gateway_host::pricing::ModelsDevPricing),
    );
-    let mut services = gateway_admin::service::Registry::new(service_middleware(
+    let mut services = gateway_admin::public_service::Registry::new(service_middleware(
        core.snapshots(),
        &plugin_runtime,
    ));
@@ -72,11 +72,11 @@ impl ManagementPorts {
 pub(super) fn service_middleware(
    snapshots: RuntimeSnapshotHandle,
    runtime: &PluginRuntime,
-) -> gateway_admin::service::PlanSource {
-    let middleware = runtime.middleware_registry();
+) -> gateway_admin::public_service::PlanSource {
+    let middleware = runtime.execution_registry();
    Arc::new(move || {
        let snapshot = snapshots.snapshot_for_diagnostics()?;
-        middleware.resolve(snapshot.extensions()?)
+        middleware.middleware(snapshot.extensions()?)
    })
 }

@@ -1,4 +1,4 @@
-//! 服务模式完成全部组装后交给 Host 监听，并在请求和 Worker 排空后关闭插件
+//! 服务模式完成全部组装后交给 Host 监听，并在停止监听与 Worker 收尾后关闭插件

 use gateway_host::ConfigError;

@@ -28,7 +28,7 @@ pub async fn run() -> Result<(), BootstrapError> {
        Some(plugin_runtime.clone()),
        Some(plugin_runtime.observer_registry()),
        Some(plugin_runtime.policy_registry()),
-        Some(plugin_runtime.middleware_registry()),
+        Some(plugin_runtime.execution_registry()),
        Some(plugin_runtime.frontend_authentication_registry()),
    );
    let management = ManagementPorts::new(&store, providers.admin.clone(), core.snapshot_control());
@@ -56,6 +56,12 @@ pub async fn run() -> Result<(), BootstrapError> {
        plugin_runtime,
        gateway_host::plugin_distribution::HttpPluginDistribution::new(plugin_http)
    ));
+    let analytics_worker = or_shutdown!(
+        plugin_runtime,
+        store.request_analytics_worker(std::sync::Arc::new(
+            gateway_admin::ProviderUsageBillingProjector::new(providers.admin.clone()),
+        ))
+    );
    let mut admin = or_shutdown!(
        plugin_runtime,
        gateway_admin::initialize_with_plugin_accounts(
@@ -122,14 +128,14 @@ pub async fn run() -> Result<(), BootstrapError> {
    )
    .with_middleware({
        let snapshots = core.snapshots();
-        let middleware = plugin_runtime.middleware_registry();
+        let middleware = plugin_runtime.execution_registry();
        move |snapshot| {
            if let Some(snapshot) = snapshot {
-                return middleware.resolve(snapshot.extensions()?);
+                return middleware.middleware(snapshot.extensions()?);
            }
            // 数据面未就绪时，管理与诊断路由仍可使用发布候选中的插件
            let diagnostic = snapshots.snapshot_for_diagnostics()?;
-            middleware.resolve(diagnostic.extensions()?)
+            middleware.middleware(diagnostic.extensions()?)
        }
    });
    let http_dispatcher = api.dispatcher();
@@ -142,6 +148,7 @@ pub async fn run() -> Result<(), BootstrapError> {
    );

    let mut plan = store.take_worker_contributions();
+    plan.push(analytics_worker);
    plan.push(or_shutdown!(
        plugin_runtime,
        gateway_host::retention::worker(store.retention())
@@ -79,18 +79,25 @@ fn core_value_owners_do_not_depend_on_execution_or_routing() {
            path if path.starts_with("policy/") => {
                Some(&["account", "identity", "policy", "validation"])
            }
-            "settings/values.rs" | "settings/compiled.rs" => {
-                Some(&["account", "concurrency", "identity", "metering", "policy"])
-            }
+            path if path.starts_with("settings/") => Some(&[
+                "account",
+                "concurrency",
+                "identity",
+                "metering",
+                "policy",
+                "settings",
+            ]),
            path if path.starts_with("account/") => Some(&["account", "identity", "validation"]),
            _ => None,
        };
        let Some(allowed) = allowed else { continue };
        let source = fs::read_to_string(root.join(&relative)).expect("read core source");
        let syntax = syn::parse_file(&source).expect("parse core source");
-        let mut references = CrateReferences::default();
+        let mut references = CrateReferences::in_module(&relative);
        references.visit_file(&syntax);
-        for dependency in references.0 {
+        // 相对路径中的 self 指向当前 owner，不是跨 owner 依赖
+        references.owners.remove(&references.module_path[0]);
+        for dependency in references.owners {
            assert!(
                allowed.contains(&dependency.as_str()),
                "{} must not depend on crate::{dependency}",
@@ -100,49 +107,155 @@ fn core_value_owners_do_not_depend_on_execution_or_routing() {
    }
 }

+#[test]
+fn core_owner_paths_form_a_dag() {
+    let root = backend_root().join("crates/gateway-core/src");
+    let mut graph = BTreeMap::<String, BTreeSet<String>>::new();
+    for relative in super::rust_files(&root) {
+        if relative == Path::new("lib.rs") {
+            continue;
+        }
+        let mut references = CrateReferences::in_module(&relative);
+        let owner = references.module_path[0].clone();
+        let source = fs::read_to_string(root.join(&relative)).expect("read core source");
+        references.visit_file(&syn::parse_file(&source).expect("parse core source"));
+        references.owners.remove(&owner);
+        graph.entry(owner).or_default().extend(references.owners);
+    }
+    for owner in graph.keys() {
+        let mut pending = graph[owner].iter().cloned().collect::<Vec<_>>();
+        let mut visited = BTreeSet::new();
+        while let Some(dependency) = pending.pop() {
+            assert_ne!(
+                &dependency, owner,
+                "Core owner dependency cycle reaches {owner}"
+            );
+            if visited.insert(dependency.clone())
+                && let Some(next) = graph.get(&dependency)
+            {
+                pending.extend(next.iter().cloned());
+            }
+        }
+    }
+}
+
+#[test]
+fn core_reference_scan_resolves_groups_reexports_and_relative_paths() {
+    let syntax = syn::parse_file(
+        r#"
+        pub use crate::{engine::AttemptContext, settings::SettingsValues as Values};
+        use super::super::runtime as publication;
+        use self::compiled::Value;
+        // crate::ignored::Comment
+        const EXAMPLE: &str = "crate::ignored::Literal";
+        "#,
+    )
+    .expect("parse reference fixture");
+    let mut references = CrateReferences::in_module(Path::new("routing/snapshot.rs"));
+    references.visit_file(&syntax);
+    assert_eq!(
+        references.owners,
+        BTreeSet::from([
+            "engine".to_owned(),
+            "settings".to_owned(),
+            "runtime".to_owned(),
+            "routing".to_owned(),
+        ])
+    );
+}
+
 #[derive(Default)]
-struct CrateReferences(BTreeSet<String>);
+struct CrateReferences {
+    owners: BTreeSet<String>,
+    module_path: Vec<String>,
+}

 impl<'ast> Visit<'ast> for CrateReferences {
    fn visit_path(&mut self, path: &'ast syn::Path) {
-        let mut segments = path.segments.iter();
-        if segments
-            .next()
-            .is_some_and(|segment| segment.ident == "crate")
-            && let Some(owner) = segments.next()
-        {
-            self.0.insert(owner.ident.to_string());
-        }
+        self.record(
+            &path
+                .segments
+                .iter()
+                .map(|part| part.ident.to_string())
+                .collect::<Vec<_>>(),
+        );
        syn::visit::visit_path(self, path);
    }

    fn visit_item_use(&mut self, item: &'ast syn::ItemUse) {
-        self.use_tree(&item.tree, false);
+        self.use_tree(&item.tree, &mut Vec::new());
    }
 }

 impl CrateReferences {
-    fn use_tree(&mut self, tree: &syn::UseTree, crate_root: bool) {
+    fn in_module(relative: &Path) -> Self {
+        let mut module = relative
+            .with_extension("")
+            .components()
+            .map(|part| {
+                part.as_os_str()
+                    .to_str()
+                    .expect("UTF-8 module path")
+                    .to_owned()
+            })
+            .collect::<Vec<_>>();
+        if module.last().is_some_and(|part| part == "mod") {
+            module.pop();
+        }
+        Self {
+            owners: BTreeSet::new(),
+            module_path: module,
+        }
+    }
+
+    fn record(&mut self, path: &[String]) {
+        let Some(first) = path.first() else { return };
+        let owner = if first == "crate" {
+            path.get(1).cloned()
+        } else if first == "self" || first == "super" {
+            let mut module = self.module_path.clone();
+            let mut rest = path;
+            while rest
+                .first()
+                .is_some_and(|part| part == "super" || part == "self")
+            {
+                if rest[0] == "super" {
+                    module.pop();
+                }
+                rest = &rest[1..];
+            }
+            module.first().or_else(|| rest.first()).cloned()
+        } else {
+            None
+        };
+        if let Some(owner) = owner {
+            self.owners.insert(owner);
+        }
+    }
+
+    fn use_tree(&mut self, tree: &syn::UseTree, prefix: &mut Vec<String>) {
        match tree {
-            syn::UseTree::Path(path) if crate_root => {
-                self.0.insert(path.ident.to_string());
+            syn::UseTree::Path(path) => {
+                prefix.push(path.ident.to_string());
+                self.use_tree(&path.tree, prefix);
+                prefix.pop();
            }
-            syn::UseTree::Name(name) if crate_root => {
-                self.0.insert(name.ident.to_string());
+            syn::UseTree::Name(name) => {
+                prefix.push(name.ident.to_string());
+                self.record(prefix);
+                prefix.pop();
            }
-            syn::UseTree::Rename(rename) if crate_root => {
-                self.0.insert(rename.ident.to_string());
+            syn::UseTree::Rename(rename) => {
+                prefix.push(rename.ident.to_string());
+                self.record(prefix);
+                prefix.pop();
            }
-            syn::UseTree::Path(path) => self.use_tree(&path.tree, path.ident == "crate"),
            syn::UseTree::Group(group) => {
                for item in &group.items {
-                    self.use_tree(item, crate_root);
+                    self.use_tree(item, prefix);
                }
            }
-            syn::UseTree::Glob(_) if crate_root => {
-                self.0.insert("*".to_owned());
-            }
-            _ => {}
+            syn::UseTree::Glob(_) => self.record(prefix),
        }
    }
 }
@@ -221,7 +334,7 @@ const ADAPTER_PUBLIC_MODULES: &[(&str, &[&str])] = &[
        "crates/providers/openai",
        &["config", "credential", "transport"],
    ),
-    ("crates/providers/xai", &["credential", "transport"]),
+    ("crates/providers/xai", &["transport"]),
 ];

 /// 不对应单一生产模块、而是校验 crate/workspace 整体契约的根级测试场景
@@ -76,11 +76,6 @@ fn config_loader_should_reject_missing_runtime_data_dir() {
    assert!(parse_config(&config).is_err());
 }

-#[test]
-fn config_loader_should_inject_connection_passwords_into_urls() {
-    parse_config(&valid_config()).expect("Store validates password injection into both URLs");
-}
-
 #[test]
 fn config_loader_should_apply_only_explicit_topology_overrides() {
    let invalid = valid_config()
@@ -28,11 +28,8 @@ cpr-plugin package \

 资源映射相对于作者清单所在目录解析。输出包括完整插件 ID、版本和目标 triple 命名的 `.tar.gz` 及 `.sha256`；归档根目录直接包含 `plugin.json`、可执行文件和已声明资源，不包含开发依赖

-作者清单可省略普通贡献项的 `id`、`version` 和固定阶段；`middleware` 必须显式声明版本 `4`，
-并从 `http`、`websocket`、`service`、`request`、`attempt` 中选择挂载阶段；`upstream_adapter` 必须显式声明版本 `2`。
-CLI 与 SDK 的 `Manifest::from_author_slice`、`PluginBuilder::from_json` 共用规范化入口；归档中的
-`plugin.json` 写入补全后的贡献项字段，不保留另一份作者声明。
-完整规则见 [SDK 清单](../../crates/gateway-plugin/sdk/docs/manifest.md)
+作者清单的省略规则、能力版本和挂载阶段见 [SDK 扩展项声明](../../crates/gateway-plugin/sdk/docs/manifest.md#扩展项简写)。
+CLI 与 SDK 的 `Manifest::from_author_slice`、`PluginBuilder::from_json` 共用规范化入口，归档只保留补全字段后的 `plugin.json`

 支持 `x86_64-unknown-linux-gnu`、`aarch64-unknown-linux-gnu` 和 `aarch64-apple-darwin`。
 完整开发示例在独立仓库 `codex-proxy-plugins` 的 `examples/workbench`，可通过[子模块](../../../docs/development.md#源码联调)检出；本工具不负责源码构建、上传或启用插件
@@ -21,6 +21,7 @@ futures = "0.3.32"
 gateway-core = { path = "../gateway-core" }
 heck = "0.5.0"
 hex = "0.4.3"
+hkdf = "0.13.0"
 rand_core = { version = "0.6.4", features = ["getrandom"] }
 serde = { version = "1.0.228", features = ["derive"] }
 serde_json = { version = "1.0.150", features = ["arbitrary_precision", "preserve_order"] }
@@ -281,7 +281,6 @@ impl BackupTask {
                .await?;
            }
            None => {
-                let _ = self.dump.cleanup_staging(&record.id).await;
                self.fail_task(record, code::PG_DUMP_FAILED, "导出进程中断，暂存归档不完整")
                    .await?;
            }
@@ -307,7 +306,8 @@ impl BackupTask {
            && record.sha256.as_deref() == Some(remote.sha256.as_str())
        {
            let now = Utc::now();
-            self.repository
+            if self
+                .repository
                .transition_status(
                    &record.id,
                    status_transition(BackupStatus::Uploading, BackupStatus::Completed)?,
@@ -315,7 +315,11 @@ impl BackupTask {
                    now,
                )
                .await
-                .map_err(repo_error)?;
+                .map_err(repo_error)?
+                .is_some()
+            {
+                self.cleanup_staging(&record.id).await;
+            }
            return Ok(());
        }
        match self.dump.inspect_staging(&record.id).await? {
@@ -455,9 +459,7 @@ impl BackupTask {
            now,
            cancellation,
        )
-        .await?;
-        let _ = self.dump.cleanup_staging(&record.id).await;
-        Ok(())
+        .await
    }

    /// 上传 + 远端校验，内部完成终态迁移
@@ -489,11 +491,13 @@ impl BackupTask {
            )
            .await
        {
-            let _ = store.delete_object(&config, &record.object_key).await;
-            self.fail_task(
+            self.fail_uploaded_task(
                record,
-                error.code(),
-                format!("上传到对象存储失败：{}", error.message()),
+                &config,
+                BackupError::new(
+                    error.code(),
+                    format!("上传到对象存储失败：{}", error.message()),
+                ),
            )
            .await?;
            return Ok(());
@@ -518,6 +522,7 @@ impl BackupTask {
                        size_bytes,
                        "备份完成"
                    );
+                    self.cleanup_staging(&record.id).await;
                }
            }
            Ok(Some(remote)) => {
@@ -530,16 +535,19 @@ impl BackupTask {
                    sha256_matches,
                    "备份远端对象校验不一致"
                );
-                let _ = store.delete_object(&config, &record.object_key).await;
-                self.fail_task(
+                self.fail_uploaded_task(
                    record,
-                    code::REMOTE_VERIFICATION_FAILED,
-                    match (size_matches, sha256_matches) {
-                        (false, true) => "远端对象大小不一致",
-                        (true, false) => "远端对象 sha256 校验值不一致",
-                        (false, false) => "远端对象大小和 sha256 校验值均不一致",
-                        (true, true) => "远端对象校验状态异常",
-                    },
+                    &config,
+                    BackupError::new(
+                        code::REMOTE_VERIFICATION_FAILED,
+                        match (size_matches, sha256_matches) {
+                            (false, true) => "远端对象大小不一致",
+                            (true, false) => "远端对象 sha256 校验值不一致",
+                            (false, false) => "远端对象大小和 sha256 校验值均不一致",
+                            (true, true) => "远端对象校验状态异常",
+                        }
+                        .to_owned(),
+                    ),
                )
                .await?;
            }
@@ -553,11 +561,13 @@ impl BackupTask {
                .await?;
            }
            Err(error) => {
-                let _ = store.delete_object(&config, &record.object_key).await;
-                self.fail_task(
+                self.fail_uploaded_task(
                    record,
-                    error.code(),
-                    format!("远端对象校验失败：{}", error.message()),
+                    &config,
+                    BackupError::new(
+                        error.code(),
+                        format!("远端对象校验失败：{}", error.message()),
+                    ),
                )
                .await?;
            }
@@ -565,6 +575,24 @@ impl BackupTask {
        Ok(())
    }

+    /// 清理失败并入原终态，后续清理沿用备份记录的到期策略
+    async fn fail_uploaded_task(
+        &self,
+        record: &BackupRecord,
+        config: &BackupStorageConfig,
+        mut error: BackupError,
+    ) -> Result<(), WorkerTaskError> {
+        if let Err(cleanup) = self
+            .object_store
+            .delete_object(config, &record.object_key)
+            .await
+        {
+            error =
+                error.with_cleanup_failure("DeleteObject", &cleanup, record.expires_at.is_some());
+        }
+        self.fail_task(record, error.code(), error.message()).await
+    }
+
    /// 把活跃任务写入失败终态并清理暂存
    async fn fail_task(
        &self,
@@ -596,10 +624,16 @@ impl BackupTask {
            )
            .await
            .map_err(repo_error)?;
-        let _ = self.dump.cleanup_staging(&record.id).await;
+        self.cleanup_staging(&record.id).await;
        Ok(())
    }

+    async fn cleanup_staging(&self, backup_id: &str) {
+        if let Err(error) = self.dump.cleanup_staging(backup_id).await {
+            warn!(backup_id, error = %error, "清理备份暂存失败");
+        }
+    }
+
    /// 执行一小批到期保留清理：先处理 `expires_at` 已到期的记录，再按天数/份数清理计划备份
    async fn run_retention_batch(&self, now: DateTime<Utc>) -> Result<(), WorkerTaskError> {
        let settings = self.repository.load_settings().await.map_err(repo_error)?;
@@ -20,7 +20,7 @@ pub mod backup;
 pub mod freeze_recovery;
 pub mod model;
 pub mod ports;
-pub mod service;
+pub mod public_service;
 mod use_case;
 pub use use_case::plugins::{PluginDistributionPorts, PluginManagementService, PluginsService};

@@ -35,7 +35,7 @@ pub use use_case::{
    client_keys::ClientKeyService,
    credentials::{CredentialsService, ProviderCredentials},
    import_tasks::ImportTasksService,
-    observability::ObservabilityService,
+    observability::{ObservabilityService, ProviderUsageBillingProjector},
    proxies::ProxiesService,
    settings::SettingsService,
    system::SystemService,
@@ -205,7 +205,7 @@ pub enum AdminConfigError {
 #[derive(Clone)]
 pub struct AdminServices {
    timezone: gateway_core::time::DeploymentTimeZone,
-    public_services: Arc<service::Registry>,
+    public_services: Arc<public_service::Registry>,
    plugins: Arc<PluginsService>,
    plugin_management: Arc<PluginManagementService>,
    proxies: Arc<dyn ProxiesService>,
@@ -219,7 +219,8 @@ pub struct AdminServices {
    settings: Arc<dyn SettingsService>,
    system: Arc<dyn SystemService>,
    credentials: Arc<CredentialsService>,
-    plugin_accounts: Arc<dyn PluginAccountAccess>,
+    // Runtime 只持有 Weak，这个强引用保障账号端口与 Admin 服务同寿命
+    _plugin_accounts: Arc<dyn PluginAccountAccess>,
    backups: Arc<dyn BackupService>,
    import_tasks: Arc<dyn ImportTasksService>,
 }
@@ -230,7 +231,7 @@ impl AdminServices {
        self.timezone
    }

-    pub fn public_services(&self) -> Arc<service::Registry> {
+    pub fn public_services(&self) -> Arc<public_service::Registry> {
        self.public_services.clone()
    }

@@ -254,12 +255,6 @@ impl AdminServices {
        self.key_usage.as_ref()
    }

-    /// 取得账号服务的共享句柄；后台编排（冻结恢复 worker）需要持有 Arc
-    #[must_use]
-    pub fn accounts_handle(&self) -> Arc<dyn AccountsService> {
-        Arc::clone(&self.accounts)
-    }
-
    #[must_use]
    pub fn proxies(&self) -> &dyn ProxiesService {
        self.proxies.as_ref()
@@ -309,12 +304,6 @@ impl AdminServices {
        self.credentials.as_ref()
    }

-    /// Runtime 只持有该窄端口的 Weak；AdminBundle 保持实际生命周期
-    #[must_use]
-    pub fn plugin_accounts_handle(&self) -> Arc<dyn PluginAccountAccess> {
-        Arc::clone(&self.plugin_accounts)
-    }
-
    #[must_use]
    pub fn backups(&self) -> &dyn BackupService {
        self.backups.as_ref()
@@ -342,7 +331,7 @@ impl AdminBundle {
 /// 组合根提供给控制面的运行能力；与配置和存储端口分别传入
 pub struct AdminRuntimePorts {
    pub timezone: gateway_core::time::DeploymentTimeZone,
-    pub service_middleware: service::PlanSource,
+    pub service_middleware: public_service::PlanSource,
    pub plugin_preparation: Arc<dyn ports::plugins::PluginPreparation>,
    pub plugin_management: Arc<dyn ports::plugin_management::PluginManagement>,
    pub published_snapshot: gateway_core::runtime::RuntimeSnapshotHandle,
@@ -416,9 +405,7 @@ async fn initialize_inner(
    let registry = providers;

    let auth = Arc::new(DefaultAuthService::new(
-        config.default_username,
-        config.session_ttl_minutes,
-        config.session_absolute_ttl_minutes,
+        &config,
        client_config.session_ttl_minutes,
        store.auth(),
        client_key_verifier.clone(),
@@ -452,11 +439,14 @@ async fn initialize_inner(
        plugin_inspector.clone(),
    ));
    let system = Arc::new(DefaultSystemService::new(system, system_preflight));
+    let observations: Arc<dyn ports::store::ObservabilityStore> = Arc::new(
+        use_case::observability::CachedObservabilityStore::new(store.observability()),
+    );
    let key_usage = Arc::new(use_case::key_usage::DefaultKeyUsageService::new(
        auth.clone(),
        client_key_verifier,
        store.client_keys(),
-        store.observability(),
+        observations.clone(),
        system.clone(),
        timezone,
    ));
@@ -477,7 +467,7 @@ async fn initialize_inner(
        registry.clone(),
        pricing_source,
    );
-    let mut public_services = service::Registry::new(service_middleware);
+    let mut public_services = public_service::Registry::new(service_middleware);
    public_services.register_settings(&settings)?;
    let services = AdminServices {
        timezone,
@@ -517,7 +507,7 @@ async fn initialize_inner(
        )),
        client_distribution: Arc::new(DefaultClientDistributionService::new(client_distribution)),
        observability: Arc::new(DefaultObservabilityService::new(
-            store.observability(),
+            observations.clone(),
            store.accounts(),
            store.settings(),
            registry.clone(),
@@ -526,7 +516,7 @@ async fn initialize_inner(
        settings,
        system,
        credentials,
-        plugin_accounts,
+        _plugin_accounts: plugin_accounts,
        import_tasks,
        backups,
    };
@@ -66,7 +66,7 @@ pub struct AccountGroupCapacity {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct AccountGroupUsage {
    pub today_usd: DecimalAmount,
-    /// 当前 usage retention 窗口内、按请求发生时 routing group 快照归属的累计成本
+    /// 当前 usage retention 窗口内、当前组成员实际完成请求的累计成本
    pub retained_total_usd: DecimalAmount,
 }

@@ -126,6 +126,16 @@ pub struct AccountGroupPage {
    pub page_size: u16,
 }

+/// 分组选择器使用的轻量分页结果
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct AccountGroupOptionsPage {
+    pub config_revision: Revision,
+    pub items: Vec<AccountGroupRef>,
+    pub total: u64,
+    pub page: u32,
+    pub page_size: u16,
+}
+
 /// 创建账号分组
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct CreateAccountGroup {
@@ -146,9 +146,9 @@ pub struct AccountUsage {
    pub success_count: u64,
    pub input_tokens: Option<u64>,
    pub output_tokens: Option<u64>,
-    pub cached_tokens: Option<u64>,
-    pub cache_write_tokens: Option<u64>,
-    pub reasoning_tokens: Option<u64>,
+    pub cached_input_tokens: Option<u64>,
+    pub cache_write_input_tokens: Option<u64>,
+    pub reasoning_output_tokens: Option<u64>,
    pub image_input_tokens: Option<u64>,
    pub image_output_tokens: Option<u64>,
    pub image_request_count: u64,
@@ -0,0 +1,65 @@
+//! 统计投影的新鲜度、覆盖范围与预计算费用合同
+
+use chrono::{DateTime, Utc};
+
+use super::observability::{DecimalAmount, RequestMetricPoint, UsageOverview};
+
+/// 数据可见性状态，不以缺失投影冒充零统计
+#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
+pub enum AnalyticsState {
+    Ready,
+    #[default]
+    Building,
+    Lagging,
+    Stale,
+}
+
+impl AnalyticsState {
+    #[must_use]
+    pub const fn as_str(self) -> &'static str {
+        match self {
+            Self::Ready => "ready",
+            Self::Building => "building",
+            Self::Lagging => "lagging",
+            Self::Stale => "stale",
+        }
+    }
+}
+
+/// 与统计结果在同一读取快照内取得的覆盖和版本事实
+#[derive(Debug, Clone, Default, PartialEq, Eq)]
+pub struct AnalyticsMetadata {
+    pub coverage_start: Option<DateTime<Utc>>,
+    pub coverage_end: Option<DateTime<Utc>>,
+    pub generated_at: DateTime<Utc>,
+    pub lag_seconds: u64,
+    pub state: AnalyticsState,
+    pub percentiles_approximate: bool,
+    pub schema_version: u32,
+    pub histogram_version: u32,
+    /// 派生数据版本供缓存判断失效，不作为源事务提交顺序
+    pub generation: u64,
+}
+
+/// 单次请求经 Provider 费用合同确认后可累加的 USD 情景金额
+#[derive(Debug, Clone, Default, PartialEq, Eq)]
+pub struct UsageBillingProjection {
+    pub standard_amount: Option<DecimalAmount>,
+    pub no_cache_amount: Option<DecimalAmount>,
+}
+
+/// 时间桶内的情景费用，未知金额不改写为零
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct UsageProjectedCostPoint {
+    pub bucket_start: DateTime<Utc>,
+    pub standard_amount: Option<DecimalAmount>,
+    pub no_cache_amount: Option<DecimalAmount>,
+}
+
+/// 同一数据库快照内的完整洞察输入
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct UsageInsightsObservation {
+    pub overview: UsageOverview,
+    pub trend: Vec<RequestMetricPoint>,
+    pub costs: Vec<UsageProjectedCostPoint>,
+}
@@ -76,18 +76,23 @@ impl std::fmt::Debug for LoginCommand {
    }
 }

-/// 登录成功后返回的会话事实
+/// 登录或刷新后仅向当前浏览器交付的会话凭据
 #[derive(Clone, PartialEq, Eq)]
-pub struct LoginResult {
+pub struct SessionGrant {
    pub session_id: String,
+    pub refresh_token: Option<String>,
    pub session: AuthSession,
 }

-impl std::fmt::Debug for LoginResult {
+impl std::fmt::Debug for SessionGrant {
    fn fmt(&self, formatter: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
        formatter
-            .debug_struct("LoginResult")
+            .debug_struct("SessionGrant")
            .field("session_id", &"[REDACTED]")
+            .field(
+                "refresh_token",
+                &self.refresh_token.as_ref().map(|_| "[REDACTED]"),
+            )
            .field("session", &self.session)
            .finish()
    }
@@ -138,12 +143,41 @@ impl std::fmt::Debug for ChangePassword {
    }
 }

-/// 会话有效期与管理员续期上限；没有上限字段的旧会话保持固定有效期
+/// 访问有效期与逻辑会话；没有续期凭据的会话保持固定期限
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct AuthSession {
    pub subject: SessionSubject,
    pub expires_at: DateTime<Utc>,
    pub absolute_expires_at: Option<DateTime<Utc>>,
+    pub renewal: Option<SessionRenewal>,
+}
+
+/// 长效登录的凭据摘要与续期窗口；访问到期不删除整段登录
+#[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
+#[serde(deny_unknown_fields)]
+pub struct SessionRenewal {
+    pub expires_at: DateTime<Utc>,
+    pub access_digest: [u8; 32],
+    pub refresh_digest: [u8; 32],
+    pub previous: Option<SessionRefreshReplay>,
+}
+
+/// 仅保存上一代摘要及派生盐；响应丢失时须持有上一代凭据才能重建同一响应
+#[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
+#[serde(deny_unknown_fields)]
+pub struct SessionRefreshReplay {
+    pub digest: [u8; 32],
+    pub salt: [u8; 32],
+    pub expires_at: DateTime<Utc>,
+}
+
+impl AuthSession {
+    #[must_use]
+    pub fn retained_until(&self) -> DateTime<Utc> {
+        self.renewal
+            .as_ref()
+            .map_or(self.expires_at, |renewal| renewal.expires_at)
+    }
 }

 /// 安全审计事件类型
@@ -474,6 +474,26 @@ impl BackupError {
    pub fn message(&self) -> &str {
        &self.message
    }
+
+    /// 清理失败附加到原始终态，不覆盖上传失败或主动取消的分类
+    #[must_use]
+    pub fn with_cleanup_failure(
+        mut self,
+        stage: &'static str,
+        error: &Self,
+        retry_on_expiration: bool,
+    ) -> Self {
+        let recovery = if retry_on_expiration {
+            "等待备份到期清理"
+        } else {
+            "未安排自动重试"
+        };
+        self.message.push_str(&format!(
+            "；清理阶段 {stage} 失败（{}），{recovery}",
+            error.code()
+        ));
+        self
+    }
 }

 /// 构造稳定错误码常量
@@ -4,6 +4,7 @@ use std::num::{NonZeroU16, NonZeroU64};

 pub mod account_groups;
 pub mod accounts;
+pub mod analytics;
 pub mod audit;
 pub mod auth;
 pub mod backup;
@@ -5,6 +5,10 @@ use std::{num::NonZeroU16, str::FromStr};
 use chrono::{DateTime, TimeDelta, Utc};

 use super::AdminModelError;
+pub use super::analytics::{
+    AnalyticsMetadata, AnalyticsState, UsageBillingProjection, UsageInsightsObservation,
+    UsageProjectedCostPoint,
+};

 /// 观测记录查询的页大小，由 HTTP、管理用例和存储端口共同使用
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
@@ -48,7 +52,7 @@ impl CalendarPeriod {
 }

 /// 外部观测查询的 UTC 时间范围
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
 pub struct TimeRange {
    pub start: DateTime<Utc>,
    pub end: DateTime<Utc>,
@@ -89,7 +93,7 @@ impl TimeRange {
 }

 /// 请求结果状态
-#[derive(Debug, Clone, PartialEq, Eq)]
+#[derive(Debug, Clone, PartialEq, Eq, Hash)]
 pub enum RequestOutcome {
    Running,
    Succeeded,
@@ -100,7 +104,7 @@ pub enum RequestOutcome {
 }

 /// 未知但有界的请求结果值；私有字段禁止绕过 [`RequestOutcome::new`] 构造
-#[derive(Debug, Clone, PartialEq, Eq)]
+#[derive(Debug, Clone, PartialEq, Eq, Hash)]
 pub struct OtherRequestOutcome(String);

 impl RequestOutcome {
@@ -151,7 +155,7 @@ impl OtherRequestOutcome {
 }

 /// 用量记录过滤条件
-#[derive(Debug, Clone, Default, PartialEq, Eq)]
+#[derive(Debug, Clone, Default, PartialEq, Eq, Hash)]
 pub struct UsageFilter {
    pub client_api_key_ref: Option<String>,
    pub request_id: Option<String>,
@@ -177,6 +181,32 @@ pub struct UsageQuery {
    pub page_size: ObservabilityPageSize,
 }

+/// Admin 确定概览的数量、趋势粒度及最近请求筛选，Store 只执行该选择
+#[derive(Debug, Clone, PartialEq, Eq, Hash)]
+pub struct DashboardQuery {
+    pub range: TimeRange,
+    pub granularity: Granularity,
+    pub account_limit: u16,
+    pub recent_request_limit: u16,
+    pub recent_request_filter: UsageFilter,
+}
+
+impl DashboardQuery {
+    #[must_use]
+    pub fn new(range: TimeRange) -> Self {
+        Self {
+            range,
+            granularity: Granularity::for_range(range),
+            account_limit: 4,
+            recent_request_limit: 10,
+            recent_request_filter: UsageFilter {
+                outcome: Some(RequestOutcome::Succeeded),
+                ..UsageFilter::default()
+            },
+        }
+    }
+}
+
 /// 运维错误过滤条件
 #[derive(Debug, Clone, Default, PartialEq, Eq)]
 pub struct OpsErrorFilter {
@@ -204,7 +234,7 @@ pub struct OpsErrorQuery {
 }

 /// 用量诊断维度
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
 pub enum DiagnosticDimension {
    Provider,
    Model,
@@ -337,8 +367,8 @@ pub struct ProviderBillingInput {
    pub service_tier: Option<String>,
    pub input_tokens: Option<u64>,
    pub output_tokens: Option<u64>,
-    pub cached_tokens: Option<u64>,
-    pub cache_write_tokens: Option<u64>,
+    pub cached_input_tokens: Option<u64>,
+    pub cache_write_input_tokens: Option<u64>,
    pub total: CurrencyCost,
 }

@@ -354,8 +384,8 @@ pub struct UsageCalculatedBillingFact {
    pub service_tier: Option<String>,
    pub input_tokens: Option<u64>,
    pub output_tokens: Option<u64>,
-    pub cached_tokens: Option<u64>,
-    pub cache_write_tokens: Option<u64>,
+    pub cached_input_tokens: Option<u64>,
+    pub cache_write_input_tokens: Option<u64>,
    pub total: CurrencyCost,
 }

@@ -382,7 +412,7 @@ pub struct CalculatedBillingBreakdown {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct ImageBillingBreakdown {
    pub input_tokens: u64,
-    pub cached_tokens: u64,
+    pub cached_input_tokens: u64,
    pub input_amount: CurrencyCost,
    pub cache_read_amount: CurrencyCost,
    pub input_price_per_million: CurrencyCost,
@@ -428,9 +458,9 @@ pub struct RequestMetrics {
    pub caller_error_count: u64,
    pub input_tokens: u64,
    pub output_tokens: u64,
-    pub cached_tokens: u64,
-    pub cache_write_tokens: u64,
-    pub reasoning_tokens: u64,
+    pub cached_input_tokens: u64,
+    pub cache_write_input_tokens: u64,
+    pub reasoning_output_tokens: u64,
    pub total_tokens: u64,
    pub first_token_latency_sum_ms: u64,
    pub first_token_latency_count: u64,
@@ -470,13 +500,37 @@ pub struct AttemptMetrics {
 }

 /// 时间序列粒度
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
 pub enum Granularity {
    FifteenMinutes,
    Hour,
    Day,
 }

+impl Granularity {
+    /// 管理趋势按范围选择粒度，费用校验与请求指标必须使用同一策略
+    #[must_use]
+    pub fn for_range(range: TimeRange) -> Self {
+        let seconds = range.end.signed_duration_since(range.start).num_seconds();
+        if seconds <= 2 * 24 * 60 * 60 {
+            Self::FifteenMinutes
+        } else if seconds <= 31 * 24 * 60 * 60 {
+            Self::Hour
+        } else {
+            Self::Day
+        }
+    }
+
+    #[must_use]
+    pub const fn seconds(self) -> i64 {
+        match self {
+            Self::FifteenMinutes => 15 * 60,
+            Self::Hour => 60 * 60,
+            Self::Day => 24 * 60 * 60,
+        }
+    }
+}
+
 /// 一段时间桶内的请求指标
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct RequestMetricPoint {
@@ -506,9 +560,9 @@ pub struct AccountModelUsage {
    pub success_count: u64,
    pub input_tokens: Option<u64>,
    pub output_tokens: Option<u64>,
-    pub cached_tokens: Option<u64>,
-    pub cache_write_tokens: Option<u64>,
-    pub reasoning_tokens: Option<u64>,
+    pub cached_input_tokens: Option<u64>,
+    pub cache_write_input_tokens: Option<u64>,
+    pub reasoning_output_tokens: Option<u64>,
    pub image_input_tokens: Option<u64>,
    pub image_output_tokens: Option<u64>,
    pub image_request_count: u64,
@@ -541,9 +595,9 @@ pub struct DashboardAccountUsage {
    pub success_count: u64,
    pub input_tokens: Option<u64>,
    pub output_tokens: Option<u64>,
-    pub cached_tokens: Option<u64>,
-    pub cache_write_tokens: Option<u64>,
-    pub reasoning_tokens: Option<u64>,
+    pub cached_input_tokens: Option<u64>,
+    pub cache_write_input_tokens: Option<u64>,
+    pub reasoning_output_tokens: Option<u64>,
    pub image_input_tokens: Option<u64>,
    pub image_output_tokens: Option<u64>,
    pub image_request_count: u64,
@@ -578,7 +632,7 @@ pub struct DashboardRuntimeSlots {
 pub struct DashboardTotals {
    pub request_count: u64,
    pub input_tokens: u64,
-    pub cached_tokens: u64,
+    pub cached_input_tokens: u64,
    pub total_tokens: u64,
    pub billing_usd: Option<DecimalAmount>,
 }
@@ -586,16 +640,18 @@ pub struct DashboardTotals {
 /// 仪表盘所需的当前区间事实及全历史累计
 #[derive(Debug, Clone, PartialEq)]
 pub struct DashboardObservation {
+    pub analytics: AnalyticsMetadata,
    pub range: TimeRange,
    pub totals: DashboardTotals,
    pub provider_accounts: AccountPoolMetrics,
+    pub runtime_slots: Option<DashboardRuntimeSlots>,
    pub trend: Vec<RequestMetricPoint>,
    pub account_usage: Vec<DashboardAccountUsage>,
    pub recent_requests: Vec<UsageListRecord>,
 }

 /// 使用记录表格的窄读模型
-#[derive(Debug, Clone, PartialEq, Eq)]
+#[derive(Debug, Clone, PartialEq)]
 pub struct UsageListRecord {
    pub client_api_key_name: Option<String>,
    pub id: String,
@@ -606,9 +662,9 @@ pub struct UsageListRecord {
    pub provider_account_ref: Option<String>,
    pub provider_account_name: Option<String>,
    pub provider_account_email: Option<String>,
-    /// 账号当前备注，按内部账号 ID 关联，不属于请求历史快照
+    /// 请求选号时冻结的账号备注，未采集时保持未知
    pub provider_account_notes: Option<String>,
-    /// 账号当前套餐，不属于请求历史快照
+    /// 请求选号时冻结的账号套餐
    pub provider_account_plan_type: Option<String>,
    pub provider_account_plan_type_display: Option<String>,
    pub provider_account_authentication_kind: Option<String>,
@@ -618,9 +674,9 @@ pub struct UsageListRecord {
    pub service_tier: Option<String>,
    pub input_tokens: Option<u64>,
    pub output_tokens: Option<u64>,
-    pub cached_tokens: Option<u64>,
-    pub cache_write_tokens: Option<u64>,
-    pub reasoning_tokens: Option<u64>,
+    pub cached_input_tokens: Option<u64>,
+    pub cache_write_input_tokens: Option<u64>,
+    pub reasoning_output_tokens: Option<u64>,
    pub image_input_tokens: Option<u64>,
    pub image_output_tokens: Option<u64>,
    pub total_tokens: Option<u64>,
@@ -636,6 +692,13 @@ pub struct UsageListRecord {
    pub first_text_ms: Option<u64>,
    pub first_token_ms: Option<u64>,
    pub provider_processing_ms: Option<u64>,
+    pub upstream_response_ms: Option<u64>,
+    pub upstream_api_overhead_ms: Option<f64>,
+    pub upstream_engine_ms: Option<f64>,
+    pub upstream_engine_iapi_ttft_ms: Option<f64>,
+    pub upstream_engine_service_ttft_ms: Option<f64>,
+    pub upstream_engine_iapi_tbt_ms: Option<f64>,
+    pub upstream_engine_service_tbt_ms: Option<f64>,
    pub latency_ms: Option<u64>,
    pub admission_decision_ms: Option<u64>,
    pub account_selection_wait_ms: Option<u64>,
@@ -651,7 +714,7 @@ pub struct UsageListRecord {
 }

 /// 一次完整模型请求的公共观测记录
-#[derive(Debug, Clone, PartialEq, Eq)]
+#[derive(Debug, Clone, PartialEq)]
 pub struct UsageRecord {
    pub id: String,
    pub client_api_key_ref: String,
@@ -692,9 +755,9 @@ pub struct UsageRecord {
    pub retry_after_ms: Option<u64>,
    pub input_tokens: Option<u64>,
    pub output_tokens: Option<u64>,
-    pub cached_tokens: Option<u64>,
-    pub cache_write_tokens: Option<u64>,
-    pub reasoning_tokens: Option<u64>,
+    pub cached_input_tokens: Option<u64>,
+    pub cache_write_input_tokens: Option<u64>,
+    pub reasoning_output_tokens: Option<u64>,
    pub image_input_tokens: Option<u64>,
    pub image_output_tokens: Option<u64>,
    pub total_tokens: Option<u64>,
@@ -710,6 +773,13 @@ pub struct UsageRecord {
    pub first_text_ms: Option<u64>,
    pub first_token_ms: Option<u64>,
    pub provider_processing_ms: Option<u64>,
+    pub upstream_response_ms: Option<u64>,
+    pub upstream_api_overhead_ms: Option<f64>,
+    pub upstream_engine_ms: Option<f64>,
+    pub upstream_engine_iapi_ttft_ms: Option<f64>,
+    pub upstream_engine_service_ttft_ms: Option<f64>,
+    pub upstream_engine_iapi_tbt_ms: Option<f64>,
+    pub upstream_engine_service_tbt_ms: Option<f64>,
    pub latency_ms: Option<u64>,
    pub admission_decision_ms: Option<u64>,
    pub account_selection_wait_ms: Option<u64>,
@@ -730,7 +800,7 @@ pub struct UsageRecord {
 }

 /// 用量分页结果
-#[derive(Debug, Clone, PartialEq, Eq)]
+#[derive(Debug, Clone, PartialEq)]
 pub struct UsagePage {
    pub items: Vec<UsageListRecord>,
    pub current_page: u32,
@@ -765,9 +835,9 @@ pub struct UsageAttempt {
    pub message: Option<String>,
    pub input_tokens: Option<u64>,
    pub output_tokens: Option<u64>,
-    pub cached_tokens: Option<u64>,
-    pub cache_write_tokens: Option<u64>,
-    pub reasoning_tokens: Option<u64>,
+    pub cached_input_tokens: Option<u64>,
+    pub cache_write_input_tokens: Option<u64>,
+    pub reasoning_output_tokens: Option<u64>,
    pub total_tokens: Option<u64>,
    pub cost_source: Option<String>,
    pub cost_amount: Option<DecimalAmount>,
@@ -776,7 +846,7 @@ pub struct UsageAttempt {
 }

 /// 一条请求及其全部尝试
-#[derive(Debug, Clone, PartialEq, Eq)]
+#[derive(Debug, Clone, PartialEq)]
 pub struct UsageDetail {
    pub trace: Option<serde_json::Value>,
    pub related_requests: Vec<serde_json::Value>,
@@ -797,6 +867,7 @@ pub struct ProviderObservation {
 /// 用量总览
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct UsageOverview {
+    pub analytics: AnalyticsMetadata,
    pub range: TimeRange,
    pub requests: RequestMetrics,
    pub attempts: AttemptMetrics,
@@ -813,6 +884,7 @@ pub struct UsageSummary {
 /// 诊断聚合结果，分母包含截取展示项之前的全部匹配请求
 #[derive(Debug, Clone, Default, PartialEq, Eq)]
 pub struct DiagnosticsObservation {
+    pub analytics: AnalyticsMetadata,
    pub total_request_count: u64,
    pub items: Vec<DiagnosticObservation>,
 }
@@ -936,7 +1008,7 @@ pub struct TrendSummary {
    pub request_count: u64,
    pub input_tokens: u64,
    pub output_tokens: u64,
-    pub cached_tokens: u64,
+    pub cached_input_tokens: u64,
    pub total_tokens: u64,
    pub service_failure_count: u64,
    pub average_latency_ms: Option<u64>,
@@ -954,6 +1026,7 @@ pub struct TrendSummary {
 /// 趋势结果；API 再决定图表标签与数字格式
 #[derive(Debug, Clone, PartialEq)]
 pub struct Trend {
+    pub analytics: AnalyticsMetadata,
    pub kind: TrendKind,
    pub points: Vec<TrendPoint>,
    pub summary: TrendSummary,
@@ -1069,7 +1142,7 @@ pub struct DashboardPeriodMetrics {
    pub request_count: u64,
    pub input_tokens: u64,
    pub output_tokens: u64,
-    pub cached_tokens: u64,
+    pub cached_input_tokens: u64,
    pub total_tokens: u64,
    pub cached_token_rate: f64,
    pub observed_cached_token_rate: Option<f64>,
@@ -1159,7 +1232,7 @@ pub struct UsageInsightsCostPoint {
    pub bucket_start: DateTime<Utc>,
    pub input_tokens: u64,
    pub output_tokens: u64,
-    pub cached_tokens: u64,
+    pub cached_input_tokens: u64,
    pub total_tokens: u64,
    pub estimated_cost: Option<DecimalAmount>,
    pub standard_cost: Option<DecimalAmount>,
@@ -1184,7 +1257,7 @@ pub struct UsageInsightsCost {
    pub cache_hit_request_rate: Option<f64>,
    pub input_tokens: u64,
    pub output_tokens: u64,
-    pub cached_tokens: u64,
+    pub cached_input_tokens: u64,
    pub total_tokens: u64,
    pub points: Vec<UsageInsightsCostPoint>,
    pub costs: Vec<CurrencyCost>,
@@ -1194,6 +1267,7 @@ pub struct UsageInsightsCost {
 /// 用量洞察的完整用例结果；API 只负责标签、时区与字符串格式化
 #[derive(Debug, Clone, PartialEq)]
 pub struct UsageInsights {
+    pub analytics: AnalyticsMetadata,
    pub granularity: Granularity,
    pub health: UsageInsightsHealth,
    pub performance: UsageInsightsPerformance,
@@ -1229,6 +1303,7 @@ pub struct DiagnosticsItem {
 /// 诊断结果
 #[derive(Debug, Clone, PartialEq)]
 pub struct DiagnosticsResult {
+    pub analytics: AnalyticsMetadata,
    pub dimension: DiagnosticDimension,
    pub items: Vec<DiagnosticsItem>,
 }
@@ -15,7 +15,7 @@ pub struct QuotaForecastUsage {
    pub tokens: u64,
    pub input_tokens: u64,
    pub output_tokens: u64,
-    pub cached_tokens: u64,
+    pub cached_input_tokens: u64,
    pub missing_token_count: u64,
    pub known_cost_count: u64,
    pub unavailable_cost_count: u64,
@@ -35,7 +35,9 @@ impl QuotaForecastUsage {
            tokens: self.tokens.checked_sub(baseline.tokens)?,
            input_tokens: self.input_tokens.checked_sub(baseline.input_tokens)?,
            output_tokens: self.output_tokens.checked_sub(baseline.output_tokens)?,
-            cached_tokens: self.cached_tokens.checked_sub(baseline.cached_tokens)?,
+            cached_input_tokens: self
+                .cached_input_tokens
+                .checked_sub(baseline.cached_input_tokens)?,
            missing_token_count: self
                .missing_token_count
                .checked_sub(baseline.missing_token_count)?,
@@ -140,7 +142,7 @@ pub fn select_forecast_sample(
    };
    history.push(current);
    // 重置边界不在查询起点时，从首个新观测重新计数，避免把旧周期累计带入总量
-    let mut cycle_baseline = interrupted.then(|| &history[0]);
+    let cycle_baseline = interrupted.then(|| &history[0]);
    let mut anchors: Vec<&QuotaForecastPoint> = Vec::new();
    let mut high_water: Option<&QuotaForecastPoint> = None;
    for point in &history {
@@ -153,9 +155,9 @@ pub fn select_forecast_sample(
                if previous.used_percent - point.used_percent <= 1.0 {
                    continue;
                }
+                // 同窗口回落不能证明周期重置，只重建采样并保留已记录累计
                sample.discontinuous = true;
                anchors.clear();
-                cycle_baseline = Some(point);
            }
        }
        high_water = Some(point);
@@ -45,12 +45,12 @@ pub use gateway_core::account::RotationStrategy;
 /// 运行设置的共同值；版本、Provider 画像更新和数据库秘密由外层类型拥有
 #[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
 pub struct RuntimeSettingsValues {
+    pub codex_privacy_policy: gateway_core::settings::privacy::CodexPrivacyPolicy,
    pub request_location_enabled: bool,
    pub request_location: gateway_core::account::RequestLocation,
    pub refresh_margin_seconds: u64,
    pub refresh_concurrency: u32,
    pub max_concurrent_per_account: u32,
-    pub request_interval_ms: u64,
    pub max_waiting_per_key: u32,
    pub max_waiting_per_account: u32,
    pub concurrency_wait_timeout_seconds: u32,
@@ -211,10 +211,6 @@ impl RuntimeSettingsValues {
                "refresh_margin_seconds",
            ),
            (self.refresh_concurrency > 0, "refresh_concurrency"),
-            (
-                i64::try_from(self.request_interval_ms).is_ok(),
-                "request_interval_ms",
-            ),
        ] {
            if !valid {
                return Err(field);
@@ -1,7 +1,7 @@
 //! 插件管理页面、资源访问与授权回调的运行时端口

 use async_trait::async_trait;
-use gateway_core::runtime::extensions::ExtensionSetReference;
+use gateway_core::routing::extensions::ExtensionSetReference;

 use crate::model::{
    AdminError,
@@ -26,7 +26,7 @@ use crate::model::{
        PluginCompatibilityRequirements, PluginSource,
    },
 };
-use gateway_core::runtime::extensions::ExtensionSetReference;
+use gateway_core::routing::extensions::ExtensionSetReference;

 /// Admin 准备完整候选并保活到提交后的发布结束；进程状态不能代替持久启用状态
 #[async_trait]
@@ -175,12 +175,13 @@ pub trait PluginDistribution: Send + Sync {
 /// Runtime 只解释插件包格式；安装事务与来源选择归 Admin
 #[async_trait]
 pub trait PluginPackageInspector: Send + Sync {
-    /// 可解析但版本范围未经宿主承诺的诊断，不决定启动资格
+    /// 完整校验包并返回版本范围诊断；校验失败与可加载但未经宿主承诺的提醒分开
    async fn compatibility_warning(
        &self,
-        _archive: Arc<[u8]>,
-        _expected_sha256: String,
+        archive: Arc<[u8]>,
+        expected_sha256: String,
    ) -> Result<Option<String>, AdminError> {
+        self.inspect(archive, Some(expected_sha256)).await?;
        Ok(None)
    }

@@ -130,6 +130,32 @@ struct ProviderAdminDiagnostic {
 /// 运行时资源通知只在事务成功后发生
 #[async_trait]
 pub trait ProviderAdmin: Send + Sync {
+    fn compile_privacy_policy(
+        &self,
+        _policy: &gateway_core::settings::privacy::CodexPrivacyPolicy,
+    ) -> Result<
+        Arc<dyn gateway_core::settings::privacy::CompiledPrivacyPolicy>,
+        gateway_core::settings::privacy::PrivacyError,
+    > {
+        Err(gateway_core::settings::privacy::PrivacyError {
+            rule_index: 0,
+            reason: "Provider 不支持隐私策略",
+        })
+    }
+
+    fn preview_privacy_policy(
+        &self,
+        _request: gateway_core::settings::privacy::PrivacyPreviewRequest,
+    ) -> Result<
+        gateway_core::settings::privacy::PrivacyPreviewResult,
+        gateway_core::settings::privacy::PrivacyError,
+    > {
+        Err(gateway_core::settings::privacy::PrivacyError {
+            rule_index: 0,
+            reason: "Provider 不支持隐私策略",
+        })
+    }
+
    /// 只读内置价目；没有本地计价能力的 Provider 返回空目录
    fn pricing_catalog(&self) -> crate::model::pricing::ProviderPricingCatalog {
        Default::default()
@@ -6,14 +6,14 @@ use std::{collections::BTreeMap, net::IpAddr, sync::Arc, time::Duration};

 use async_trait::async_trait;
 use chrono::{DateTime, Utc};
-use futures::stream::BoxStream;

 use super::backup::BackupStorePorts;
 use crate::model::{
    MutationContext, Revision,
    account_groups::{
-        AccountGroupListQuery, AccountGroupMemberFact, AccountGroupMutation, AccountGroupPage,
-        DeleteAccountGroup, NewAccountGroup, SetAccountGroupEnabled, UpdateAccountGroup,
+        AccountGroupListQuery, AccountGroupMemberFact, AccountGroupMutation,
+        AccountGroupOptionsPage, AccountGroupPage, DeleteAccountGroup, NewAccountGroup,
+        SetAccountGroupEnabled, UpdateAccountGroup,
    },
    accounts::{
        AccountListQuery, AccountPage, AccountPageItem, AccountRuntimeSnapshot,
@@ -27,9 +27,10 @@ use crate::model::{
        UpdateClientKey, UpdateClientKeyBudgetLimits,
    },
    observability::{
-        DashboardObservation, DashboardRuntimeSlots, DiagnosticDimension, DiagnosticsObservation,
-        OpsErrorPage, OpsErrorQuery, RequestMetricPoint, TimeRange, UsageCalculatedBillingFact,
-        UsageDetail, UsageFilter, UsageOverview, UsagePage, UsageQuery,
+        DashboardObservation, DashboardQuery, DiagnosticDimension, DiagnosticsObservation,
+        Granularity, OpsErrorPage, OpsErrorQuery, RequestMetricPoint, TimeRange,
+        UsageBillingProjection, UsageCalculatedBillingFact, UsageDetail, UsageFilter,
+        UsageInsightsObservation, UsageOverview, UsagePage, UsageQuery,
    },
    provider_credentials::{
        AuthorizationCommit, CredentialDetails, CredentialImportCommit, CredentialImportResult,
@@ -293,12 +294,12 @@ pub trait AuthStore: Send + Sync {

    async fn store_session(&self, session_id: &str, session: &AuthSession) -> AdminStoreResult<()>;

-    /// 只延长仍存在且匹配的会话；并发续期返回当前值，已退出或过期时不重建
-    async fn renew_session(
+    /// 原子替换或撤销仍匹配的会话并返回当前值；过期或退出后不重新创建
+    async fn compare_exchange_session(
        &self,
        session_id: &str,
        expected: &AuthSession,
-        expires_at: chrono::DateTime<chrono::Utc>,
+        replacement: Option<&AuthSession>,
    ) -> AdminStoreResult<Option<AuthSession>>;

    async fn delete_session(&self, session_id: &str) -> AdminStoreResult<Option<AuthSession>>;
@@ -385,6 +386,11 @@ pub trait AccountGroupStore: Send + Sync {
        query: AccountGroupListQuery,
    ) -> AdminStoreResult<AccountGroupPage>;

+    async fn list_account_group_options(
+        &self,
+        query: AccountGroupListQuery,
+    ) -> AdminStoreResult<AccountGroupOptionsPage>;
+
    async fn load_account_group_members(
        &self,
        group_ids: &[gateway_core::routing::AccountGroupId],
@@ -415,46 +421,50 @@ pub trait AccountGroupStore: Send + Sync {
    ) -> AdminStoreResult<AccountGroupMutation>;
 }

-/// 逐条读取的已计算费用事实；消费结束或丢弃时释放查询资源
-pub type UsageCalculatedBillingStream<'a> =
-    BoxStream<'a, AdminStoreResult<UsageCalculatedBillingFact>>;
+/// 后台投影复用 Admin 与 Provider 的费用规则，Store 不重新解释价格
+pub trait UsageBillingProjector: Send + Sync {
+    fn project(
+        &self,
+        fact: &UsageCalculatedBillingFact,
+    ) -> Result<UsageBillingProjection, crate::model::AdminError>;
+}

 /// 用量、趋势、诊断与运维错误的只读能力
 #[async_trait]
 pub trait ObservabilityStore: Send + Sync {
+    /// 读取实现声明的总预算，缓存等待沿用同一配置，避免外层提前截断
+    fn query_timeout(&self) -> std::time::Duration;
+
+    /// 缓存必须与删除和后台投影提交的版本一致
+    async fn analytics_cache_generation(&self) -> AdminStoreResult<u64>;
+
    /// 返回历史统计区间和指定观测时刻下的实时账号状态
    async fn dashboard_summary(
        &self,
-        range: TimeRange,
+        query: DashboardQuery,
        observed_at: DateTime<Utc>,
    ) -> AdminStoreResult<DashboardObservation>;

-    /// 返回 Dashboard 可选的实时槽位事实
-    ///
-    /// 该状态来自可丢失的运行时存储；无实现或运行时存储不可用时返回 `None`，不影响
-    /// 持久观测数据的读取
-    async fn dashboard_runtime_slots(
+    async fn dashboard_trend(
        &self,
-        _observed_at: DateTime<Utc>,
-    ) -> AdminStoreResult<Option<DashboardRuntimeSlots>> {
-        Ok(None)
-    }
-
-    async fn dashboard_trend(&self, range: TimeRange) -> AdminStoreResult<Vec<RequestMetricPoint>>;
+        range: TimeRange,
+        granularity: Granularity,
+    ) -> AdminStoreResult<Vec<RequestMetricPoint>>;

    async fn usage_trend(
        &self,
        range: TimeRange,
        filter: UsageFilter,
+        granularity: Granularity,
    ) -> AdminStoreResult<Vec<RequestMetricPoint>>;

-    /// 流式返回可由 Provider 重新校验的已计算费用事实，不保证顺序
-    /// 查询及解码错误由流返回；调用方应逐条聚合，避免收集整个区间
-    fn usage_calculated_billing_facts(
+    /// 同一读取快照中的汇总、趋势和已投影情景费用
+    async fn usage_insights_observation(
        &self,
        range: TimeRange,
        filter: UsageFilter,
-    ) -> UsageCalculatedBillingStream<'_>;
+        granularity: Granularity,
+    ) -> AdminStoreResult<UsageInsightsObservation>;

    async fn list_usage_records(&self, query: UsageQuery) -> AdminStoreResult<UsagePage>;

@@ -471,6 +481,7 @@ pub trait ObservabilityStore: Send + Sync {
        range: TimeRange,
        filter: UsageFilter,
        dimension: DiagnosticDimension,
+        limit: u16,
    ) -> AdminStoreResult<DiagnosticsObservation>;

    async fn list_ops_errors(&self, query: OpsErrorQuery) -> AdminStoreResult<OpsErrorPage>;
@@ -8,11 +8,11 @@ use std::{future::Future, sync::Arc};

 use futures::future::BoxFuture;
 use gateway_core::{
-    engine::middleware::FrozenMiddlewarePlan,
-    middleware::{
-        compose,
+    engine::middleware::{
+        FrozenMiddlewarePlan,
        service::{Context, Error, Value},
    },
+    middleware::compose,
 };

 use crate::model::{AdminError, AdminErrorKind};
@@ -2,7 +2,7 @@

 use crate::model::AdminError;
 use futures::future::BoxFuture;
-use gateway_core::middleware::service::{Error, Value};
+use gateway_core::engine::middleware::service::{Error, Value};
 use serde::{Serialize, de::DeserializeOwned};
 use std::{collections::BTreeMap, sync::Arc};

@@ -25,6 +25,13 @@ pub(super) fn register(
        }};
    }
    register!(Load, load, (), ());
+    register!(
+        PreviewPrivacyPolicy,
+        preview_privacy_policy,
+        gateway_core::settings::privacy::PrivacyPreviewRequest,
+        request,
+        request
+    );
    register!(
        Replace,
        replace,
@@ -19,9 +19,9 @@ use crate::{
        AdminError, MutationContext,
        account_groups::{
            AccountGroupAccountSummary, AccountGroupCapacity, AccountGroupListQuery,
-            AccountGroupMemberFact, AccountGroupMutation, AccountGroupPage, AccountGroupRecord,
-            CreateAccountGroup, DeleteAccountGroup, NewAccountGroup, SetAccountGroupEnabled,
-            UpdateAccountGroup,
+            AccountGroupMemberFact, AccountGroupMutation, AccountGroupOptionsPage,
+            AccountGroupPage, AccountGroupRecord, CreateAccountGroup, DeleteAccountGroup,
+            NewAccountGroup, SetAccountGroupEnabled, UpdateAccountGroup,
        },
    },
    ports::store::{AccountGroupStore, AccountRuntimeStore},
@@ -33,6 +33,10 @@ use super::{map_store_error, publish_committed};
 #[async_trait]
 pub trait AccountGroupService: Send + Sync {
    async fn list(&self, query: AccountGroupListQuery) -> Result<AccountGroupPage, AdminError>;
+    async fn list_options(
+        &self,
+        query: AccountGroupListQuery,
+    ) -> Result<AccountGroupOptionsPage, AdminError>;
    async fn create(
        &self,
        context: &MutationContext,
@@ -130,6 +134,16 @@ impl AccountGroupService for DefaultAccountGroupService {
        Ok(page)
    }

+    async fn list_options(
+        &self,
+        query: AccountGroupListQuery,
+    ) -> Result<AccountGroupOptionsPage, AdminError> {
+        self.store
+            .list_account_group_options(query)
+            .await
+            .map_err(|error| map_store_error(error, "account group options"))
+    }
+
    async fn create(
        &self,
        context: &MutationContext,
@@ -0,0 +1,139 @@
+//! 控制面认证端口、会话策略与访问和续期共用的身份校验
+
+use std::{net::IpAddr, sync::Arc};
+
+use async_trait::async_trait;
+use base64::{Engine as _, engine::general_purpose::URL_SAFE_NO_PAD};
+use chrono::{Duration, Utc};
+use gateway_core::engine::execution::ClientKeyVerifier;
+use sha2::{Digest as _, Sha256};
+
+use super::map_store_error;
+use crate::{
+    model::{
+        AdminError,
+        auth::{
+            AuthSession, ChangePassword, LoginCommand, LoginError, SessionGrant, SessionSubject,
+        },
+    },
+    ports::store::AuthStore,
+};
+
+mod service;
+mod session;
+
+/// 所有控制面接口消费同一个会话服务，权限由服务端身份决定
+#[async_trait]
+pub trait AuthService: Send + Sync {
+    async fn change_password(
+        &self,
+        session_id: Option<&str>,
+        command: ChangePassword,
+        source_ip: IpAddr,
+    ) -> Result<(), AdminError>;
+    async fn ensure_default_admin(&self, password: &str) -> Result<bool, AdminError>;
+    async fn session(&self, session_id: Option<&str>) -> Result<Option<AuthSession>, AdminError>;
+    async fn renew_session(
+        &self,
+        refresh_token: Option<&str>,
+        access_token: Option<&str>,
+    ) -> Result<Option<SessionGrant>, AdminError>;
+    async fn resolve_admin_user_id(
+        &self,
+        session_id: Option<&str>,
+    ) -> Result<Option<String>, AdminError>;
+    async fn verify_admin_api_key(&self, key: &str) -> Result<bool, AdminError>;
+    async fn login(
+        &self,
+        command: LoginCommand,
+        source_ip: IpAddr,
+        previous_session_id: Option<&str>,
+    ) -> Result<SessionGrant, LoginError>;
+    async fn logout(&self, session_id: &str) -> Result<(), AdminError>;
+}
+
+const MAX_SESSION_TTL_MINUTES: i64 = 366 * 24 * 60;
+
+pub(crate) struct DefaultAuthService {
+    default_admin_user_id: String,
+    admin_access_ttl: Duration,
+    admin_session_ttl: Duration,
+    admin_session_absolute_ttl: Duration,
+    key_session_ttl: Duration,
+    store: Arc<dyn AuthStore>,
+    verifier: Arc<dyn ClientKeyVerifier>,
+}
+
+impl DefaultAuthService {
+    #[must_use]
+    pub(crate) fn new(
+        config: &crate::AdminConfig,
+        key_session_ttl_minutes: u64,
+        store: Arc<dyn AuthStore>,
+        verifier: Arc<dyn ClientKeyVerifier>,
+    ) -> Self {
+        let admin_session_ttl = session_ttl(config.session_ttl_minutes);
+        Self {
+            default_admin_user_id: config.default_username.clone(),
+            // 访问凭据最多有效 24 小时，较短的不活动期限也要留出续期窗口
+            admin_access_ttl: Duration::hours(24).min(admin_session_ttl / 4),
+            admin_session_ttl,
+            admin_session_absolute_ttl: session_ttl(config.session_absolute_ttl_minutes),
+            key_session_ttl: session_ttl(key_session_ttl_minutes),
+            store,
+            verifier,
+        }
+    }
+
+    async fn load_live_session(&self, id: &str) -> Result<Option<AuthSession>, AdminError> {
+        let Some(session) = self
+            .store
+            .load_session(id)
+            .await
+            .map_err(|error| map_store_error(error, "authentication session"))?
+        else {
+            return Ok(None);
+        };
+        if session.retained_until() <= Utc::now()
+            || session
+                .absolute_expires_at
+                .is_some_and(|expiry| expiry <= Utc::now())
+        {
+            return Ok(None);
+        }
+        let valid = match &session.subject {
+            SessionSubject::Admin {
+                admin_user_id,
+                credential_fingerprint,
+            } => self
+                .store
+                .load_password_hash(admin_user_id)
+                .await
+                .map_err(|error| map_store_error(error, "administrator session"))?
+                .is_some_and(|hash| password_fingerprint(&hash) == *credential_fingerprint),
+            SessionSubject::Key { client_key_id } => self
+                .store
+                .client_key_enabled(client_key_id)
+                .await
+                .map_err(|error| map_store_error(error, "session key"))?,
+        };
+        if !valid {
+            let _ = self.store.delete_session(id).await;
+            return Ok(None);
+        }
+        Ok(Some(session))
+    }
+}
+
+fn session_ttl(minutes: u64) -> Duration {
+    Duration::minutes(
+        i64::try_from(minutes)
+            .unwrap_or(MAX_SESSION_TTL_MINUTES)
+            .clamp(1, MAX_SESSION_TTL_MINUTES),
+    )
+}
+
+// 指纹只绑定已加盐的密码哈希，不把密码或原始哈希复制到 Redis 会话
+fn password_fingerprint(password_hash: &str) -> String {
+    URL_SAFE_NO_PAD.encode(Sha256::digest(password_hash.as_bytes()))
+}
@@ -1,93 +1,35 @@
-//! 控制面登录、会话恢复与身份校验的唯一 owner
+//! 管理员和 Key 的登录、退出、密码策略与会话访问

-use std::{net::IpAddr, sync::Arc, time::Duration as StdDuration};
+use std::{net::IpAddr, time::Duration as StdDuration};

 use argon2::{Argon2, PasswordHash, PasswordHasher, PasswordVerifier};
 use async_trait::async_trait;
 use base64::{Engine as _, engine::general_purpose::URL_SAFE_NO_PAD};
-use chrono::{Duration, Utc};
-use gateway_core::engine::execution::ClientKeyVerifier;
+use chrono::Utc;
 use rand_core::{OsRng, RngCore as _};
-use sha2::{Digest, Sha256};
 use subtle::ConstantTimeEq as _;
 use uuid::Uuid;

+use super::{
+    AuthService, DefaultAuthService, password_fingerprint,
+    session::{self, Credential, storage_id},
+};
 use crate::{
    model::{
        AdminError, AdminErrorKind,
        auth::{
            AdminAuditEvent, AuditActorKind, AuthSession, ChangePassword, LoginCommand, LoginError,
-            LoginResult, SessionSubject,
+            SessionGrant, SessionSubject,
        },
    },
-    ports::store::AuthStore,
+    use_case::map_store_error,
 };

-use super::map_store_error;
-
-/// 所有控制面接口消费同一个会话服务，权限由服务端身份决定
-#[async_trait]
-pub trait AuthService: Send + Sync {
-    async fn change_password(
-        &self,
-        session_id: Option<&str>,
-        command: ChangePassword,
-        source_ip: IpAddr,
-    ) -> Result<(), AdminError>;
-    async fn ensure_default_admin(&self, password: &str) -> Result<bool, AdminError>;
-    async fn session(&self, session_id: Option<&str>) -> Result<Option<AuthSession>, AdminError>;
-    async fn renew_session(
-        &self,
-        session_id: Option<&str>,
-    ) -> Result<Option<AuthSession>, AdminError>;
-    async fn resolve_admin_user_id(
-        &self,
-        session_id: Option<&str>,
-    ) -> Result<Option<String>, AdminError>;
-    async fn verify_admin_api_key(&self, key: &str) -> Result<bool, AdminError>;
-    async fn login(
-        &self,
-        command: LoginCommand,
-        source_ip: IpAddr,
-        previous_session_id: Option<&str>,
-    ) -> Result<LoginResult, LoginError>;
-    async fn logout(&self, session_id: &str) -> Result<(), AdminError>;
-}
-
-const MAX_SESSION_TTL_MINUTES: i64 = 366 * 24 * 60;
 const LOGIN_WINDOW: StdDuration = StdDuration::from_secs(60);
 const LOGIN_ATTEMPTS_PER_SOURCE: u32 = 10;
 const LOGIN_ATTEMPTS_GLOBAL: u32 = 200;

-pub(crate) struct DefaultAuthService {
-    default_admin_user_id: String,
-    admin_session_ttl: Duration,
-    admin_session_absolute_ttl: Duration,
-    key_session_ttl: Duration,
-    store: Arc<dyn AuthStore>,
-    verifier: Arc<dyn ClientKeyVerifier>,
-}
-
 impl DefaultAuthService {
-    #[must_use]
-    pub(crate) fn new(
-        default_admin_user_id: impl Into<String>,
-        admin_session_ttl_minutes: u64,
-        admin_session_absolute_ttl_minutes: u64,
-        key_session_ttl_minutes: u64,
-        store: Arc<dyn AuthStore>,
-        verifier: Arc<dyn ClientKeyVerifier>,
-    ) -> Self {
-        Self {
-            default_admin_user_id: default_admin_user_id.into(),
-            admin_session_ttl: session_ttl(admin_session_ttl_minutes),
-            admin_session_absolute_ttl: session_ttl(admin_session_absolute_ttl_minutes),
-            key_session_ttl: session_ttl(key_session_ttl_minutes),
-            store,
-            verifier,
-        }
-    }
-
    fn auth_audit(&self, action: &str, admin_user_id: &str) -> AdminAuditEvent {
        AdminAuditEvent {
            id: format!("audit_{}", Uuid::now_v7().simple()),
@@ -228,50 +170,23 @@ impl AuthService for DefaultAuthService {
    }

    async fn session(&self, session_id: Option<&str>) -> Result<Option<AuthSession>, AdminError> {
-        let Some(session_id) = session_id.filter(|value| !value.is_empty()) else {
+        let Some(raw) = session_id.filter(|value| !value.is_empty()) else {
            return Ok(None);
        };
-        let Some(session) = self
-            .store
-            .load_session(session_id)
-            .await
-            .map_err(|error| map_store_error(error, "authentication session"))?
-        else {
+        let Some(session) = self.load_live_session(storage_id(raw)).await? else {
            return Ok(None);
        };
-        if session.expires_at <= Utc::now()
-            || session
-                .absolute_expires_at
-                .is_some_and(|expiry| expiry <= Utc::now())
-        {
-            // Redis 的 TTL 负责过期清理，避免旧读取删除另一个请求刚续期的会话
+        if session.expires_at <= Utc::now() {
            return Ok(None);
        }
-        if let SessionSubject::Admin {
-            admin_user_id,
-            credential_fingerprint,
-        } = &session.subject
-        {
-            let password_hash = self
-                .store
-                .load_password_hash(admin_user_id)
-                .await
-                .map_err(|error| map_store_error(error, "administrator session"))?;
-            if password_hash
-                .is_none_or(|hash| password_fingerprint(&hash) != *credential_fingerprint)
-            {
-                let _ = self.store.delete_session(session_id).await;
+        if let Some(renewal) = &session.renewal {
+            let Some(credential) = Credential::parse(raw).filter(|value| !value.refresh) else {
+                return Ok(None);
+            };
+            if !credential.owns(renewal) {
                return Ok(None);
            }
-        }
-        if let SessionSubject::Key { client_key_id } = &session.subject
-            && !self
-                .store
-                .client_key_enabled(client_key_id)
-                .await
-                .map_err(|error| map_store_error(error, "session key"))?
-        {
-            let _ = self.store.delete_session(session_id).await;
+        } else if Credential::parse(raw).is_some() {
            return Ok(None);
        }
        Ok(Some(session))
@@ -279,33 +194,25 @@ impl AuthService for DefaultAuthService {

    async fn renew_session(
        &self,
-        session_id: Option<&str>,
-    ) -> Result<Option<AuthSession>, AdminError> {
-        let Some(session_id) = session_id else {
-            return Ok(None);
-        };
-        let Some(session) = self.session(Some(session_id)).await? else {
-            return Ok(None);
-        };
-        // Key 与升级前的会话保留原有期限，不能凭续期获得新的最长登录窗口
-        let Some(absolute) = session
-            .absolute_expires_at
-            .filter(|_| matches!(session.subject, SessionSubject::Admin { .. }))
-        else {
-            return Ok(Some(session));
-        };
-        let now = Utc::now();
-        let expires_at = (now + self.admin_session_ttl).min(absolute);
-        let interval = (self.admin_session_ttl / 4).min(Duration::minutes(1));
-        if expires_at <= session.expires_at
-            || session.expires_at - now > self.admin_session_ttl - interval
-        {
-            return Ok(Some(session));
+        refresh_token: Option<&str>,
+        access_token: Option<&str>,
+    ) -> Result<Option<SessionGrant>, AdminError> {
+        if let Some(refresh) = refresh_token {
+            return self.refresh(refresh).await;
        }
-        self.store
-            .renew_session(session_id, &session, expires_at)
-            .await
-            .map_err(|error| map_store_error(error, "authentication session renewal"))
+        // Key 与升级前的单凭据仅返回仍有效的原会话，不授予新的续期能力
+        let Some(session) = self
+            .session(access_token)
+            .await?
+            .filter(|session| session.renewal.is_none())
+        else {
+            return Ok(None);
+        };
+        Ok(Some(SessionGrant {
+            session_id: access_token.unwrap_or_default().to_owned(),
+            refresh_token: None,
+            session,
+        }))
    }

    async fn resolve_admin_user_id(
@@ -346,7 +253,7 @@ impl AuthService for DefaultAuthService {
        command: LoginCommand,
        source_ip: IpAddr,
        previous_session_id: Option<&str>,
-    ) -> Result<LoginResult, LoginError> {
+    ) -> Result<SessionGrant, LoginError> {
        if let Some(retry_after) = self
            .store
            .consume_login_attempt(
@@ -370,14 +277,31 @@ impl AuthService for DefaultAuthService {
        let now = Utc::now();
        let absolute_expires_at = matches!(subject, SessionSubject::Admin { .. })
            .then_some(now + self.admin_session_absolute_ttl);
-        let session = AuthSession {
-            subject,
-            expires_at: (now + ttl).min(absolute_expires_at.unwrap_or(now + ttl)),
-            absolute_expires_at,
+        let refresh_expiry = (now + ttl).min(absolute_expires_at.unwrap_or(now + ttl));
+        let grant = if let Some(absolute) = absolute_expires_at {
+            session::issue(
+                subject,
+                (now + self.admin_access_ttl).min(refresh_expiry),
+                refresh_expiry,
+                absolute,
+            )
+            .map_err(|_| LoginError::Unavailable)?
+        } else {
+            SessionGrant {
+                session_id: random_session_token(),
+                refresh_token: None,
+                session: AuthSession {
+                    subject,
+                    expires_at: refresh_expiry,
+                    absolute_expires_at: None,
+                    renewal: None,
+                },
+            }
        };
-        let session_id = random_session_token();
+        let session_id = storage_id(&grant.session_id);
+        let session = &grant.session;
        self.store
-            .store_session(&session_id, &session)
+            .store_session(session_id, session)
            .await
            .map_err(|_| LoginError::Unavailable)?;
        if let SessionSubject::Admin { admin_user_id, .. } = &session.subject
@@ -387,26 +311,39 @@ impl AuthService for DefaultAuthService {
                .await
                .is_err()
        {
-            let _ = self.store.delete_session(&session_id).await;
+            let _ = self.store.delete_session(session_id).await;
            return Err(LoginError::Unavailable);
        }
        // 新身份验证成功后才撤销旧会话；撤销失败时不向浏览器提交新会话
        if let Some(previous) = previous_session_id.filter(|value| !value.is_empty())
            && self.logout(previous).await.is_err()
        {
-            let _ = self.store.delete_session(&session_id).await;
+            let _ = self.store.delete_session(session_id).await;
            return Err(LoginError::Unavailable);
        }
-        Ok(LoginResult {
-            session_id,
-            session,
-        })
+        Ok(grant)
    }

    async fn logout(&self, session_id: &str) -> Result<(), AdminError> {
+        let id = storage_id(session_id);
+        let Some(stored) = self
+            .store
+            .load_session(id)
+            .await
+            .map_err(|error| map_store_error(error, "authentication session"))?
+        else {
+            return Ok(());
+        };
+        if let Some(renewal) = &stored.renewal {
+            if !Credential::parse(session_id).is_some_and(|credential| credential.owns(renewal)) {
+                return Ok(());
+            }
+        } else if Credential::parse(session_id).is_some() {
+            return Ok(());
+        }
        let session = self
            .store
-            .delete_session(session_id)
+            .delete_session(id)
            .await
            .map_err(|error| map_store_error(error, "authentication session"))?;
        if let Some(AuthSession {
@@ -423,14 +360,6 @@ impl AuthService for DefaultAuthService {
    }
 }

-fn session_ttl(minutes: u64) -> Duration {
-    Duration::minutes(
-        i64::try_from(minutes)
-            .unwrap_or(MAX_SESSION_TTL_MINUTES)
-            .clamp(1, MAX_SESSION_TTL_MINUTES),
-    )
-}
-
 fn validate_new_password(password: &str) -> Result<(), AdminError> {
    if password.trim().chars().count() < 12
        || password.len() > 1024
@@ -470,8 +399,3 @@ fn valid_admin_api_key_shape(value: &str) -> bool {
        && value.starts_with("admin-")
        && value[6..].bytes().all(|byte| byte.is_ascii_hexdigit())
 }
-
-// 指纹只绑定已加盐的密码哈希，不把密码或原始哈希复制到 Redis 会话
-fn password_fingerprint(password_hash: &str) -> String {
-    URL_SAFE_NO_PAD.encode(Sha256::digest(password_hash.as_bytes()))
-}
@@ -0,0 +1,214 @@
+//! 双凭据会话的签发、摘要校验与短窗口重试，不持久化可直接使用的凭据
+
+use base64::{Engine as _, engine::general_purpose::URL_SAFE_NO_PAD};
+use chrono::{DateTime, Duration, Utc};
+use rand_core::{OsRng, RngCore as _};
+use sha2::{Digest as _, Sha256};
+use subtle::ConstantTimeEq as _;
+
+use super::DefaultAuthService;
+use crate::{
+    model::{
+        AdminError, AdminErrorKind,
+        auth::{AuthSession, SessionGrant, SessionRefreshReplay, SessionRenewal, SessionSubject},
+    },
+    use_case::map_store_error,
+};
+
+const REPLAY_WINDOW: Duration = Duration::seconds(30);
+
+pub(super) struct Credential<'a> {
+    pub id: &'a str,
+    pub secret: &'a str,
+    pub refresh: bool,
+}
+
+impl<'a> Credential<'a> {
+    pub fn parse(value: &'a str) -> Option<Self> {
+        let mut parts = value.split('.');
+        let refresh = match parts.next()? {
+            "a2" => false,
+            "r2" => true,
+            _ => return None,
+        };
+        let id = parts.next()?;
+        let secret = parts.next()?;
+        if parts.next().is_some() || !valid_secret(id) || !valid_secret(secret) {
+            return None;
+        }
+        Some(Self {
+            id,
+            secret,
+            refresh,
+        })
+    }
+
+    pub fn digest(&self) -> [u8; 32] {
+        digest(self.secret)
+    }
+
+    pub fn owns(&self, renewal: &SessionRenewal) -> bool {
+        if self.refresh {
+            matches_digest(&renewal.refresh_digest, &self.digest())
+                || renewal
+                    .previous
+                    .as_ref()
+                    .is_some_and(|previous| matches_digest(&previous.digest, &self.digest()))
+        } else {
+            matches_digest(&renewal.access_digest, &self.digest())
+        }
+    }
+}
+
+fn valid_secret(value: &str) -> bool {
+    value.len() == 43
+        && URL_SAFE_NO_PAD
+            .decode(value)
+            .is_ok_and(|bytes| bytes.len() == 32)
+}
+
+pub(super) fn storage_id(value: &str) -> &str {
+    Credential::parse(value).map_or(value, |credential| credential.id)
+}
+
+fn matches_digest(left: &[u8; 32], right: &[u8; 32]) -> bool {
+    bool::from(left.ct_eq(right))
+}
+
+fn digest(secret: &str) -> [u8; 32] {
+    Sha256::digest(secret.as_bytes()).into()
+}
+
+fn random_bytes() -> [u8; 32] {
+    let mut bytes = [0; 32];
+    OsRng.fill_bytes(&mut bytes);
+    bytes
+}
+
+// 使用标准 HKDF 的独立用途标签；只有盐和摘要留在 Store，重试仍须持有原始凭据
+fn derive(secret: &str, salt: Option<&[u8]>, purpose: &[u8]) -> Result<String, AdminError> {
+    let mut output = [0; 32];
+    hkdf::Hkdf::<Sha256>::new(salt, secret.as_bytes())
+        .expand(purpose, &mut output)
+        .map_err(|_| AdminError::internal("会话凭据派生失败"))?;
+    Ok(URL_SAFE_NO_PAD.encode(output))
+}
+
+fn access_secret(refresh: &str) -> Result<String, AdminError> {
+    derive(refresh, None, b"cpr-session-v2/access")
+}
+
+pub(super) fn issue(
+    subject: SessionSubject,
+    access_expiry: DateTime<Utc>,
+    refresh_expiry: DateTime<Utc>,
+    absolute: DateTime<Utc>,
+) -> Result<SessionGrant, AdminError> {
+    let id = URL_SAFE_NO_PAD.encode(random_bytes());
+    let secret = URL_SAFE_NO_PAD.encode(random_bytes());
+    let session = AuthSession {
+        subject,
+        expires_at: access_expiry,
+        absolute_expires_at: Some(absolute),
+        renewal: Some(SessionRenewal {
+            expires_at: refresh_expiry,
+            access_digest: digest(&access_secret(&secret)?),
+            refresh_digest: digest(&secret),
+            previous: None,
+        }),
+    };
+    grant(&id, &secret, session)
+}
+
+fn grant(id: &str, refresh: &str, session: AuthSession) -> Result<SessionGrant, AdminError> {
+    Ok(SessionGrant {
+        session_id: format!("a2.{id}.{}", access_secret(refresh)?),
+        refresh_token: Some(format!("r2.{id}.{refresh}")),
+        session,
+    })
+}
+
+impl DefaultAuthService {
+    pub(super) async fn refresh(&self, raw: &str) -> Result<Option<SessionGrant>, AdminError> {
+        let Some(credential) = Credential::parse(raw).filter(|value| value.refresh) else {
+            return Ok(None);
+        };
+        let mut current = self.load_live_session(credential.id).await?;
+        // CAS 冲突只重新解释同一请求的凭据，不对并发退出进行补建
+        for _ in 0..3 {
+            let Some(session) = current else {
+                return Ok(None);
+            };
+            let Some(renewal) = &session.renewal else {
+                return Ok(None);
+            };
+            let now = Utc::now();
+            if session.retained_until() <= now
+                || session.absolute_expires_at.is_none_or(|limit| limit <= now)
+            {
+                return Ok(None);
+            }
+            if matches_digest(&renewal.refresh_digest, &credential.digest()) {
+                // 其他标签页已经刷新或客户端重试时复用当前代，避免 Cookie 响应相互覆盖
+                if session.expires_at > now {
+                    return grant(credential.id, credential.secret, session).map(Some);
+                }
+                let absolute = session
+                    .absolute_expires_at
+                    .ok_or_else(|| AdminError::internal("缺少会话最长有效期"))?;
+                let salt = random_bytes();
+                let next_secret =
+                    derive(credential.secret, Some(&salt), b"cpr-session-v2/refresh")?;
+                let refresh_expiry = (now + self.admin_session_ttl).min(absolute);
+                let access_expiry = (now + self.admin_access_ttl).min(refresh_expiry);
+                let replacement = AuthSession {
+                    expires_at: access_expiry,
+                    renewal: Some(SessionRenewal {
+                        expires_at: refresh_expiry,
+                        access_digest: digest(&access_secret(&next_secret)?),
+                        refresh_digest: digest(&next_secret),
+                        previous: Some(SessionRefreshReplay {
+                            digest: credential.digest(),
+                            salt,
+                            expires_at: (now + REPLAY_WINDOW).min(access_expiry),
+                        }),
+                    }),
+                    ..session.clone()
+                };
+                current = self
+                    .store
+                    .compare_exchange_session(credential.id, &session, Some(&replacement))
+                    .await
+                    .map_err(|error| map_store_error(error, "authentication session rotation"))?;
+                if current.as_ref() == Some(&replacement) {
+                    return grant(credential.id, &next_secret, replacement).map(Some);
+                }
+            } else if let Some(previous) = renewal
+                .previous
+                .as_ref()
+                .filter(|previous| matches_digest(&previous.digest, &credential.digest()))
+            {
+                if previous.expires_at > now {
+                    let secret = derive(
+                        credential.secret,
+                        Some(&previous.salt),
+                        b"cpr-session-v2/refresh",
+                    )?;
+                    return grant(credential.id, &secret, session).map(Some);
+                }
+                // 已知上一代在重试窗口外再次使用，原子撤销整个会话
+                current = self
+                    .store
+                    .compare_exchange_session(credential.id, &session, None)
+                    .await
+                    .map_err(|error| map_store_error(error, "authentication session revocation"))?;
+            } else {
+                return Ok(None);
+            }
+        }
+        Err(AdminError::new(
+            AdminErrorKind::Unavailable,
+            "会话正在变更，请重试",
+        ))
+    }
+}
@@ -0,0 +1,371 @@
+//! 凭据变更共享的绑定校验、事务结算、失效与提交后观察
+
+use crate::{
+    model::{
+        AdminError, MutationContext,
+        accounts::DeleteAccounts,
+        provider_credentials::{
+            AuthorizationMutationTarget, CredentialDeletion, CredentialDeletionResult,
+            CredentialDetails, CredentialMutationResult, CredentialRotationCommit,
+            PendingAuthorizationMutation, PreparedAuthorizationCommit,
+            PreparedAuthorizationCredential, PreparedCredentialImport, PreparedCredentialRotation,
+            ProviderQuotaRequest, StartAuthorization,
+        },
+    },
+    ports::{provider::ProviderAdmin, store::AccountStore},
+};
+use gateway_core::{account::ProviderAccountId, routing::ProviderKind, runtime::SnapshotControl};
+
+use super::{map_store_error, publish_committed};
+
+pub(super) async fn publish_credentials_and_observe_quota(
+    provider: &std::sync::Arc<dyn crate::ports::provider::ProviderAdmin>,
+    snapshot: &dyn SnapshotControl,
+    revision: crate::model::Revision,
+    account_ids: &[ProviderAccountId],
+    request_id: &str,
+) -> Result<(), AdminError> {
+    provider.account_facts_changed(account_ids).await;
+    publish_committed(snapshot, revision).await?;
+
+    // 凭据已经提交；额度只是可重建的观察，不能拖住管理请求或回滚提交结果
+    let provider = provider.clone();
+    let account_ids = account_ids.to_vec();
+    let request_id = request_id.to_owned();
+    tokio::spawn(async move {
+        for account_id in account_ids {
+            if let Err(error) = provider
+                .quota(ProviderQuotaRequest {
+                    account_id: account_id.clone(),
+                    refresh: true,
+                    rolling_usage: None,
+                })
+                .await
+            {
+                tracing::warn!(
+                    request_id,
+                    provider = %provider.provider_kind().as_str(),
+                    account_id = %account_id.as_str(),
+                    quota_error = ?error.kind(),
+                    "initial quota observation failed"
+                );
+            }
+        }
+    });
+    Ok(())
+}
+
+pub(super) async fn required_credential(
+    accounts: &dyn AccountStore,
+    provider_kind: &ProviderKind,
+    account_id: &ProviderAccountId,
+    resource: &'static str,
+) -> Result<CredentialDetails, AdminError> {
+    accounts
+        .credential_details(provider_kind, account_id)
+        .await
+        .map_err(|error| map_store_error(error, resource))?
+        .ok_or_else(|| AdminError::not_found("Provider 凭据不存在"))
+}
+
+pub(super) async fn required_plugin_credential(
+    accounts: &dyn AccountStore,
+    account_id: &ProviderAccountId,
+    resource: &'static str,
+) -> Result<CredentialDetails, AdminError> {
+    accounts
+        .credential_details_by_id(account_id)
+        .await
+        .map_err(|error| map_store_error(error, resource))?
+        .ok_or_else(|| AdminError::not_found("Provider 凭据不存在"))
+}
+
+pub(super) async fn import_proxy_binding(
+    proxies: &dyn crate::ports::proxy::ProxyStore,
+    id: Option<&str>,
+) -> Result<Option<crate::ports::proxy::ProxyImportReservation>, AdminError> {
+    let Some(id) = id else { return Ok(None) };
+    let reservation = proxies
+        .reserve_import(id)
+        .await
+        .map_err(|error| map_store_error(error, "proxy"))?;
+    Ok(Some(reservation))
+}
+
+pub(super) async fn pending_authorization(
+    accounts: &dyn AccountStore,
+    proxies: &dyn crate::ports::proxy::ProxyStore,
+    provider_kind: &ProviderKind,
+    command: &StartAuthorization,
+    resource: &'static str,
+) -> Result<PendingAuthorizationMutation, AdminError> {
+    let proxy;
+    let mut proxy_id = None;
+    let target = match &command.reauthorization {
+        Some(account_id) => {
+            proxy = required_credential(accounts, provider_kind, account_id, resource)
+                .await?
+                .credential
+                .outbound_proxy;
+            AuthorizationMutationTarget::Reauthorize {
+                account_id: account_id.clone(),
+            }
+        }
+        None => {
+            use crate::model::proxies::AccountProxySelection;
+            proxy = match &command.outbound_proxy {
+                Some(AccountProxySelection::Url(value)) => Some(value.clone()),
+                Some(AccountProxySelection::Saved(id)) => {
+                    let record = proxies
+                        .get(id)
+                        .await
+                        .map_err(|error| map_store_error(error, "proxy"))?;
+                    proxy_id = Some(record.id);
+                    Some(record.proxy)
+                }
+                Some(AccountProxySelection::Direct) | None => None,
+            };
+            AuthorizationMutationTarget::Create {
+                name: command.name.clone(),
+            }
+        }
+    };
+    Ok(PendingAuthorizationMutation::new(
+        provider_kind.clone(),
+        target,
+        crate::model::provider_credentials::AuthorizationOwnerBinding::from_context(
+            &command.context,
+        ),
+    )
+    .with_outbound_proxy(proxy)
+    .with_outbound_proxy_id(proxy_id))
+}
+
+pub(super) fn validate_prepared_import(
+    provider_kind: &ProviderKind,
+    prepared: &PreparedCredentialImport,
+    _resource: &'static str,
+) -> Result<(), AdminError> {
+    if prepared.provider_kind != *provider_kind
+        || prepared
+            .credentials
+            .iter()
+            .any(|credential| credential.provider_kind != *provider_kind)
+    {
+        return Err(AdminError::conflict("Provider 准备结果与请求范围不一致"));
+    }
+    Ok(())
+}
+
+pub(super) fn validate_prepared_rotation(
+    account: &crate::model::accounts::AccountRecord,
+    prepared: &PreparedCredentialRotation,
+    _resource: &'static str,
+) -> Result<(), AdminError> {
+    validate_prepared_rotation_facts(account, prepared.facts())
+}
+
+pub(super) fn validate_prepared_rotation_facts(
+    account: &crate::model::accounts::AccountRecord,
+    facts: &crate::model::provider_credentials::PreparedCredentialRotationFacts,
+) -> Result<(), AdminError> {
+    if facts.account_id.as_str() != account.id.as_str()
+        || facts.provider_kind != account.provider_kind
+    {
+        return Err(AdminError::conflict("Provider 准备结果与当前凭据不一致"));
+    }
+    Ok(())
+}
+
+pub(super) async fn validate_authorization_commit(
+    provider_kind: &ProviderKind,
+    context: &MutationContext,
+    prepared: PreparedAuthorizationCommit,
+    resource: &'static str,
+) -> Result<PreparedAuthorizationCommit, AdminError> {
+    if prepared.pending.provider_kind() != provider_kind
+        || !prepared.pending.owner_binding().matches_context(context)
+    {
+        let validation_error = AdminError::conflict("OAuth 授权绑定已失效，请重新发起授权");
+        if let Err(error) = prepared.abort().await {
+            tracing::warn!(
+                resource,
+                settlement_error = %error,
+                "OAuth authorization claim release failed after preparation validation"
+            );
+            return Err(error);
+        }
+        return Err(validation_error);
+    }
+    let matches_target = match (prepared.pending.target(), &prepared.credential) {
+        (
+            AuthorizationMutationTarget::Create { .. },
+            PreparedAuthorizationCredential::Create(credential),
+        ) => credential.provider_kind == *provider_kind,
+        (
+            AuthorizationMutationTarget::Reauthorize { account_id },
+            PreparedAuthorizationCredential::Reauthorize(credential),
+        ) => {
+            let facts = credential.facts();
+            facts.provider_kind == *provider_kind && facts.account_id == *account_id
+        }
+        _ => false,
+    };
+    if !matches_target {
+        let validation_error = AdminError::conflict("OAuth 凭据与待提交目标不一致");
+        if let Err(error) = prepared.abort().await {
+            tracing::warn!(
+                resource,
+                settlement_error = %error,
+                "OAuth authorization claim release failed after preparation validation"
+            );
+            return Err(error);
+        }
+        return Err(validation_error);
+    }
+    Ok(prepared)
+}
+
+pub(super) async fn commit_authorization(
+    accounts: &dyn AccountStore,
+    prepared: PreparedAuthorizationCommit,
+    key: crate::model::provider_credentials::AuthorizationReceiptKey,
+    settings: Option<crate::model::accounts::AccountImportSettings>,
+    context: &MutationContext,
+    resource: &'static str,
+) -> Result<crate::model::provider_credentials::AuthorizationCommitResult, AdminError> {
+    if settings.is_some()
+        && matches!(
+            &prepared.credential,
+            PreparedAuthorizationCredential::Reauthorize(_)
+        )
+    {
+        prepared.abort().await?;
+        return Err(AdminError::invalid("重新授权不能修改账号设置"));
+    }
+    let crate::model::provider_credentials::AuthorizationCommitSettlement {
+        command,
+        credential_guard,
+        authorization_guard,
+    } = prepared.into_commit(settings, key);
+    match accounts.commit_authorization(command, context).await {
+        Ok(result) => {
+            if let Some(guard) = credential_guard
+                && result.newly_committed
+            {
+                guard.finish();
+            }
+            if let Some(guard) = authorization_guard
+                && let Err(error) = guard.commit().await
+            {
+                // 账号与回执已经原子提交，Redis 清理失败不能把确定的成功改写为失败
+                tracing::warn!(resource, settlement_error = %error, "authorization committed but pending cleanup failed");
+            }
+            Ok(result)
+        }
+        Err(error) => {
+            drop(credential_guard);
+            if let Some(guard) = authorization_guard
+                && let Err(settlement_error) = guard.abort().await
+            {
+                tracing::warn!(
+                    resource,
+                    store_error = %error,
+                    settlement_error = %settlement_error,
+                    "OAuth authorization claim release failed after Store commit failure"
+                );
+                return Err(settlement_error);
+            }
+            Err(map_store_error(error, resource))
+        }
+    }
+}
+
+pub(super) async fn commit_credential_rotation(
+    accounts: &dyn AccountStore,
+    prepared: PreparedCredentialRotation,
+    settings: Option<crate::model::accounts::UpdateAccount>,
+    context: &MutationContext,
+    resource: &'static str,
+) -> Result<CredentialMutationResult, AdminError> {
+    let (facts, guard) = prepared.into_parts();
+    match accounts
+        .commit_credential_rotation(
+            CredentialRotationCommit {
+                prepared: facts,
+                settings,
+            },
+            context,
+        )
+        .await
+    {
+        Ok(result) => {
+            guard.finish();
+            Ok(result)
+        }
+        Err(error) => {
+            drop(guard);
+            Err(map_store_error(error, resource))
+        }
+    }
+}
+
+pub(super) async fn commit_credential_refresh(
+    accounts: &dyn AccountStore,
+    prepared: PreparedCredentialRotation,
+    context: &MutationContext,
+    resource: &'static str,
+) -> Result<CredentialMutationResult, AdminError> {
+    let (facts, guard) = prepared.into_parts();
+    match accounts
+        .commit_credential_refresh(
+            CredentialRotationCommit {
+                prepared: facts,
+                settings: None,
+            },
+            context,
+        )
+        .await
+    {
+        Ok(result) => {
+            guard.finish();
+            Ok(result)
+        }
+        Err(error) => {
+            drop(guard);
+            Err(map_store_error(error, resource))
+        }
+    }
+}
+
+pub(super) async fn delete_credentials(
+    accounts: &dyn AccountStore,
+    provider: &dyn ProviderAdmin,
+    command: CredentialDeletion,
+    resource: &'static str,
+) -> Result<CredentialDeletionResult, AdminError> {
+    for account_id in &command.account_ids {
+        required_credential(accounts, provider.provider_kind(), account_id, resource).await?;
+    }
+    let account_ids = command.account_ids;
+    let revision = accounts
+        .delete_accounts(
+            DeleteAccounts {
+                account_ids: account_ids
+                    .iter()
+                    .map(|account_id| account_id.as_str().to_owned())
+                    .collect(),
+            },
+            &command.context,
+        )
+        .await
+        .map_err(|error| map_store_error(error, resource))?;
+    for account_id in &account_ids {
+        provider.account_unavailable(account_id).await;
+    }
+    provider.account_facts_changed(&account_ids).await;
+    Ok(CredentialDeletionResult {
+        config_revision: revision,
+        account_ids,
+    })
+}
@@ -0,0 +1,67 @@
+//! 管理端口错误到用例错误的统一分类与来源保留
+
+use crate::model::{AdminError, AdminErrorKind};
+use crate::ports::store::{AdminStoreError, AdminStoreErrorKind};
+
+pub(super) fn map_store_error(error: AdminStoreError, resource: &'static str) -> AdminError {
+    let kind = match error.kind() {
+        AdminStoreErrorKind::Invalid => AdminErrorKind::Invalid,
+        AdminStoreErrorKind::NotFound => AdminErrorKind::NotFound,
+        AdminStoreErrorKind::StaleRevision
+        | AdminStoreErrorKind::DuplicateName
+        | AdminStoreErrorKind::Conflict => AdminErrorKind::Conflict,
+        AdminStoreErrorKind::Unavailable => AdminErrorKind::Unavailable,
+    };
+    let message = match kind {
+        AdminErrorKind::Invalid => "请求参数不合法",
+        AdminErrorKind::NotFound => "请求的资源不存在",
+        AdminErrorKind::Conflict => "当前资源状态冲突，请刷新后重试",
+        AdminErrorKind::Unavailable => "依赖服务暂不可用",
+        _ => "服务内部错误",
+    };
+    AdminError::new(kind, message).with_source(OperationFailure {
+        operation: resource,
+        source: error.into(),
+    })
+}
+
+pub(super) fn map_provider_error(
+    error: crate::ports::provider::ProviderAdminError,
+    resource: &'static str,
+) -> AdminError {
+    use crate::ports::provider::ProviderAdminErrorKind;
+
+    let kind = match error.kind() {
+        ProviderAdminErrorKind::Invalid => AdminErrorKind::Invalid,
+        ProviderAdminErrorKind::Unsupported => AdminErrorKind::Invalid,
+        ProviderAdminErrorKind::NotFound => AdminErrorKind::NotFound,
+        ProviderAdminErrorKind::Conflict => AdminErrorKind::Conflict,
+        ProviderAdminErrorKind::Ambiguous => AdminErrorKind::UpstreamResultUnknown,
+        ProviderAdminErrorKind::Unavailable => AdminErrorKind::Unavailable,
+        ProviderAdminErrorKind::CredentialRefreshRequired => AdminErrorKind::Unavailable,
+        ProviderAdminErrorKind::BadGateway => AdminErrorKind::BadGateway,
+        ProviderAdminErrorKind::Internal => AdminErrorKind::Internal,
+    };
+    let message = match kind {
+        AdminErrorKind::Invalid => "Provider 请求不合法",
+        AdminErrorKind::NotFound => "Provider 资源不存在",
+        AdminErrorKind::Conflict => "Provider 资源状态冲突，请刷新后重试",
+        AdminErrorKind::BadGateway => "上游服务请求失败",
+        AdminErrorKind::UpstreamResultUnknown => "上游执行结果未知，请刷新状态后再决定是否重试",
+        AdminErrorKind::Unavailable => "Provider 服务暂不可用",
+        AdminErrorKind::Internal => "服务内部错误",
+        _ => "Provider 操作失败",
+    };
+    AdminError::new(kind, error.public_message().unwrap_or(message)).with_source(OperationFailure {
+        operation: resource,
+        source: error.into(),
+    })
+}
+
+// 用例的操作名补充端口资源上下文，底层分类与原始原因仍由来源持有
+#[derive(Debug, thiserror::Error)]
+#[error("admin operation failed: {operation}")]
+struct OperationFailure {
+    operation: &'static str,
+    source: gateway_core::error::ErrorSource,
+}
@@ -14,7 +14,9 @@ use crate::{
            KeyUsageOverview, KeyUsageQuery, KeyUsageRecordKind, KeyUsageRecords,
            KeyUsageRecordsQuery,
        },
-        observability::{OpsErrorFilter, OpsErrorQuery, TimeRange, UsageFilter, UsageQuery},
+        observability::{
+            Granularity, OpsErrorFilter, OpsErrorQuery, TimeRange, UsageFilter, UsageQuery,
+        },
        system::SystemVersion,
    },
    ports::store::{ClientKeyStore, ObservabilityStore},
@@ -190,17 +192,23 @@ impl KeyUsageService for DefaultKeyUsageService {
                .ok_or_else(|| AdminError::internal("时间超出支持范围"))?,
            end: now,
        };
-        let (overview, trend, health_points) = futures::try_join!(
-            self.observations.usage_summary(query.range, filter.clone()),
-            self.observations.usage_trend(query.range, filter),
-            self.observations
-                .usage_trend(today, usage_filter(&id, None)),
+        let (observation, health_points) = futures::try_join!(
+            self.observations.usage_insights_observation(
+                query.range,
+                filter,
+                Granularity::for_range(query.range)
+            ),
+            self.observations.usage_trend(
+                today,
+                usage_filter(&id, None),
+                Granularity::for_range(today)
+            ),
        )
        .map_err(|error| map_store_error(error, "key usage overview"))?;
        Ok(Some(KeyUsageOverview {
            key,
-            overview,
-            trend,
+            overview: observation.overview,
+            trend: observation.trend,
            health_timeline: health_timeline_at(&health_points, now, self.timezone)?,
        }))
    }
@@ -19,450 +19,16 @@ pub mod proxies;
 pub mod settings;
 pub mod system;

-use crate::{
-    model::{
-        AdminError, AdminErrorKind, MutationContext,
-        accounts::DeleteAccounts,
-        provider_credentials::{
-            AuthorizationMutationTarget, CredentialDeletion, CredentialDeletionResult,
-            CredentialDetails, CredentialMutationResult, CredentialRotationCommit,
-            PendingAuthorizationMutation, PreparedAuthorizationCommit,
-            PreparedAuthorizationCredential, PreparedCredentialImport, PreparedCredentialRotation,
-            ProviderQuotaRequest, StartAuthorization,
-        },
-    },
-    ports::{
-        provider::ProviderAdmin,
-        store::{AccountStore, AdminStoreError, AdminStoreErrorKind},
-    },
+mod credential_mutation;
+mod error;
+mod publication;
+
+use credential_mutation::{
+    commit_authorization, commit_credential_refresh, commit_credential_rotation,
+    delete_credentials, import_proxy_binding, pending_authorization,
+    publish_credentials_and_observe_quota, required_credential, required_plugin_credential,
+    validate_authorization_commit, validate_prepared_import, validate_prepared_rotation,
+    validate_prepared_rotation_facts,
 };
-use gateway_core::{
-    account::ProviderAccountId,
-    routing::{ConfigRevision, ProviderKind},
-    runtime::SnapshotControl,
-};
-
-fn map_store_error(error: AdminStoreError, resource: &'static str) -> AdminError {
-    let kind = match error.kind() {
-        AdminStoreErrorKind::Invalid => AdminErrorKind::Invalid,
-        AdminStoreErrorKind::NotFound => AdminErrorKind::NotFound,
-        AdminStoreErrorKind::StaleRevision
-        | AdminStoreErrorKind::DuplicateName
-        | AdminStoreErrorKind::Conflict => AdminErrorKind::Conflict,
-        AdminStoreErrorKind::Unavailable => AdminErrorKind::Unavailable,
-    };
-    let message = match kind {
-        AdminErrorKind::Invalid => "请求参数不合法",
-        AdminErrorKind::NotFound => "请求的资源不存在",
-        AdminErrorKind::Conflict => "当前资源状态冲突，请刷新后重试",
-        AdminErrorKind::Unavailable => "依赖服务暂不可用",
-        _ => "服务内部错误",
-    };
-    AdminError::new(kind, message).with_source(OperationFailure {
-        operation: resource,
-        source: error.into(),
-    })
-}
-
-fn map_provider_error(
-    error: crate::ports::provider::ProviderAdminError,
-    resource: &'static str,
-) -> AdminError {
-    use crate::ports::provider::ProviderAdminErrorKind;
-
-    let kind = match error.kind() {
-        ProviderAdminErrorKind::Invalid => AdminErrorKind::Invalid,
-        ProviderAdminErrorKind::Unsupported => AdminErrorKind::Invalid,
-        ProviderAdminErrorKind::NotFound => AdminErrorKind::NotFound,
-        ProviderAdminErrorKind::Conflict => AdminErrorKind::Conflict,
-        ProviderAdminErrorKind::Ambiguous => AdminErrorKind::UpstreamResultUnknown,
-        ProviderAdminErrorKind::Unavailable => AdminErrorKind::Unavailable,
-        ProviderAdminErrorKind::CredentialRefreshRequired => AdminErrorKind::Unavailable,
-        ProviderAdminErrorKind::BadGateway => AdminErrorKind::BadGateway,
-        ProviderAdminErrorKind::Internal => AdminErrorKind::Internal,
-    };
-    let message = match kind {
-        AdminErrorKind::Invalid => "Provider 请求不合法",
-        AdminErrorKind::NotFound => "Provider 资源不存在",
-        AdminErrorKind::Conflict => "Provider 资源状态冲突，请刷新后重试",
-        AdminErrorKind::BadGateway => "上游服务请求失败",
-        AdminErrorKind::UpstreamResultUnknown => "上游执行结果未知，请刷新状态后再决定是否重试",
-        AdminErrorKind::Unavailable => "Provider 服务暂不可用",
-        AdminErrorKind::Internal => "服务内部错误",
-        _ => "Provider 操作失败",
-    };
-    AdminError::new(kind, error.public_message().unwrap_or(message)).with_source(OperationFailure {
-        operation: resource,
-        source: error.into(),
-    })
-}
-
-async fn publish_committed(
-    snapshot: &dyn SnapshotControl,
-    revision: crate::model::Revision,
-) -> Result<(), AdminError> {
-    let revision = ConfigRevision::new(revision.get())
-        .map_err(|_| AdminError::internal("已提交的配置版本不合法"))?;
-    snapshot.publish_committed(revision).await;
-    Ok(())
-}
-
-async fn publish_credentials_and_observe_quota(
-    provider: &std::sync::Arc<dyn crate::ports::provider::ProviderAdmin>,
-    snapshot: &dyn SnapshotControl,
-    revision: crate::model::Revision,
-    account_ids: &[ProviderAccountId],
-    request_id: &str,
-) -> Result<(), AdminError> {
-    provider.account_facts_changed(account_ids).await;
-    publish_committed(snapshot, revision).await?;
-
-    // 凭据已经提交；额度只是可重建的观察，不能拖住管理请求或回滚提交结果
-    let provider = provider.clone();
-    let account_ids = account_ids.to_vec();
-    let request_id = request_id.to_owned();
-    tokio::spawn(async move {
-        for account_id in account_ids {
-            if let Err(error) = provider
-                .quota(ProviderQuotaRequest {
-                    account_id: account_id.clone(),
-                    refresh: true,
-                    rolling_usage: None,
-                })
-                .await
-            {
-                tracing::warn!(
-                    request_id,
-                    provider = %provider.provider_kind().as_str(),
-                    account_id = %account_id.as_str(),
-                    quota_error = ?error.kind(),
-                    "initial quota observation failed"
-                );
-            }
-        }
-    });
-    Ok(())
-}
-
-async fn required_credential(
-    accounts: &dyn AccountStore,
-    provider_kind: &ProviderKind,
-    account_id: &ProviderAccountId,
-    resource: &'static str,
-) -> Result<CredentialDetails, AdminError> {
-    accounts
-        .credential_details(provider_kind, account_id)
-        .await
-        .map_err(|error| map_store_error(error, resource))?
-        .ok_or_else(|| AdminError::not_found("Provider 凭据不存在"))
-}
-
-async fn required_plugin_credential(
-    accounts: &dyn AccountStore,
-    account_id: &ProviderAccountId,
-    resource: &'static str,
-) -> Result<CredentialDetails, AdminError> {
-    accounts
-        .credential_details_by_id(account_id)
-        .await
-        .map_err(|error| map_store_error(error, resource))?
-        .ok_or_else(|| AdminError::not_found("Provider 凭据不存在"))
-}
-
-async fn import_proxy_binding(
-    proxies: &dyn crate::ports::proxy::ProxyStore,
-    id: Option<&str>,
-) -> Result<Option<crate::ports::proxy::ProxyImportReservation>, AdminError> {
-    let Some(id) = id else { return Ok(None) };
-    let reservation = proxies
-        .reserve_import(id)
-        .await
-        .map_err(|error| map_store_error(error, "proxy"))?;
-    Ok(Some(reservation))
-}
-
-async fn pending_authorization(
-    accounts: &dyn AccountStore,
-    proxies: &dyn crate::ports::proxy::ProxyStore,
-    provider_kind: &ProviderKind,
-    command: &StartAuthorization,
-    resource: &'static str,
-) -> Result<PendingAuthorizationMutation, AdminError> {
-    let proxy;
-    let mut proxy_id = None;
-    let target = match &command.reauthorization {
-        Some(account_id) => {
-            proxy = required_credential(accounts, provider_kind, account_id, resource)
-                .await?
-                .credential
-                .outbound_proxy;
-            AuthorizationMutationTarget::Reauthorize {
-                account_id: account_id.clone(),
-            }
-        }
-        None => {
-            use crate::model::proxies::AccountProxySelection;
-            proxy = match &command.outbound_proxy {
-                Some(AccountProxySelection::Url(value)) => Some(value.clone()),
-                Some(AccountProxySelection::Saved(id)) => {
-                    let record = proxies
-                        .get(id)
-                        .await
-                        .map_err(|error| map_store_error(error, "proxy"))?;
-                    proxy_id = Some(record.id);
-                    Some(record.proxy)
-                }
-                Some(AccountProxySelection::Direct) | None => None,
-            };
-            AuthorizationMutationTarget::Create {
-                name: command.name.clone(),
-            }
-        }
-    };
-    Ok(PendingAuthorizationMutation::new(
-        provider_kind.clone(),
-        target,
-        crate::model::provider_credentials::AuthorizationOwnerBinding::from_context(
-            &command.context,
-        ),
-    )
-    .with_outbound_proxy(proxy)
-    .with_outbound_proxy_id(proxy_id))
-}
-
-fn validate_prepared_import(
-    provider_kind: &ProviderKind,
-    prepared: &PreparedCredentialImport,
-    _resource: &'static str,
-) -> Result<(), AdminError> {
-    if prepared.provider_kind != *provider_kind
-        || prepared
-            .credentials
-            .iter()
-            .any(|credential| credential.provider_kind != *provider_kind)
-    {
-        return Err(AdminError::conflict("Provider 准备结果与请求范围不一致"));
-    }
-    Ok(())
-}
-
-fn validate_prepared_rotation(
-    account: &crate::model::accounts::AccountRecord,
-    prepared: &PreparedCredentialRotation,
-    _resource: &'static str,
-) -> Result<(), AdminError> {
-    validate_prepared_rotation_facts(account, prepared.facts())
-}
-
-fn validate_prepared_rotation_facts(
-    account: &crate::model::accounts::AccountRecord,
-    facts: &crate::model::provider_credentials::PreparedCredentialRotationFacts,
-) -> Result<(), AdminError> {
-    if facts.account_id.as_str() != account.id.as_str()
-        || facts.provider_kind != account.provider_kind
-    {
-        return Err(AdminError::conflict("Provider 准备结果与当前凭据不一致"));
-    }
-    Ok(())
-}
-
-async fn validate_authorization_commit(
-    provider_kind: &ProviderKind,
-    context: &MutationContext,
-    prepared: PreparedAuthorizationCommit,
-    resource: &'static str,
-) -> Result<PreparedAuthorizationCommit, AdminError> {
-    if prepared.pending.provider_kind() != provider_kind
-        || !prepared.pending.owner_binding().matches_context(context)
-    {
-        let validation_error = AdminError::conflict("OAuth 授权绑定已失效，请重新发起授权");
-        if let Err(error) = prepared.abort().await {
-            tracing::warn!(
-                resource,
-                settlement_error = %error,
-                "OAuth authorization claim release failed after preparation validation"
-            );
-            return Err(error);
-        }
-        return Err(validation_error);
-    }
-    let matches_target = match (prepared.pending.target(), &prepared.credential) {
-        (
-            AuthorizationMutationTarget::Create { .. },
-            PreparedAuthorizationCredential::Create(credential),
-        ) => credential.provider_kind == *provider_kind,
-        (
-            AuthorizationMutationTarget::Reauthorize { account_id },
-            PreparedAuthorizationCredential::Reauthorize(credential),
-        ) => {
-            let facts = credential.facts();
-            facts.provider_kind == *provider_kind && facts.account_id == *account_id
-        }
-        _ => false,
-    };
-    if !matches_target {
-        let validation_error = AdminError::conflict("OAuth 凭据与待提交目标不一致");
-        if let Err(error) = prepared.abort().await {
-            tracing::warn!(
-                resource,
-                settlement_error = %error,
-                "OAuth authorization claim release failed after preparation validation"
-            );
-            return Err(error);
-        }
-        return Err(validation_error);
-    }
-    Ok(prepared)
-}
-
-async fn commit_authorization(
-    accounts: &dyn AccountStore,
-    prepared: PreparedAuthorizationCommit,
-    key: crate::model::provider_credentials::AuthorizationReceiptKey,
-    settings: Option<crate::model::accounts::AccountImportSettings>,
-    context: &MutationContext,
-    resource: &'static str,
-) -> Result<crate::model::provider_credentials::AuthorizationCommitResult, AdminError> {
-    if settings.is_some()
-        && matches!(
-            &prepared.credential,
-            PreparedAuthorizationCredential::Reauthorize(_)
-        )
-    {
-        prepared.abort().await?;
-        return Err(AdminError::invalid("重新授权不能修改账号设置"));
-    }
-    let crate::model::provider_credentials::AuthorizationCommitSettlement {
-        command,
-        credential_guard,
-        authorization_guard,
-    } = prepared.into_commit(settings, key);
-    match accounts.commit_authorization(command, context).await {
-        Ok(result) => {
-            if let Some(guard) = credential_guard
-                && result.newly_committed
-            {
-                guard.finish();
-            }
-            if let Some(guard) = authorization_guard
-                && let Err(error) = guard.commit().await
-            {
-                // 账号与回执已经原子提交，Redis 清理失败不能把确定的成功改写为失败
-                tracing::warn!(resource, settlement_error = %error, "authorization committed but pending cleanup failed");
-            }
-            Ok(result)
-        }
-        Err(error) => {
-            drop(credential_guard);
-            if let Some(guard) = authorization_guard
-                && let Err(settlement_error) = guard.abort().await
-            {
-                tracing::warn!(
-                    resource,
-                    store_error = %error,
-                    settlement_error = %settlement_error,
-                    "OAuth authorization claim release failed after Store commit failure"
-                );
-                return Err(settlement_error);
-            }
-            Err(map_store_error(error, resource))
-        }
-    }
-}
-
-async fn commit_credential_rotation(
-    accounts: &dyn AccountStore,
-    prepared: PreparedCredentialRotation,
-    settings: Option<crate::model::accounts::UpdateAccount>,
-    context: &MutationContext,
-    resource: &'static str,
-) -> Result<CredentialMutationResult, AdminError> {
-    let (facts, guard) = prepared.into_parts();
-    match accounts
-        .commit_credential_rotation(
-            CredentialRotationCommit {
-                prepared: facts,
-                settings,
-            },
-            context,
-        )
-        .await
-    {
-        Ok(result) => {
-            guard.finish();
-            Ok(result)
-        }
-        Err(error) => {
-            drop(guard);
-            Err(map_store_error(error, resource))
-        }
-    }
-}
-
-async fn commit_credential_refresh(
-    accounts: &dyn AccountStore,
-    prepared: PreparedCredentialRotation,
-    context: &MutationContext,
-    resource: &'static str,
-) -> Result<CredentialMutationResult, AdminError> {
-    let (facts, guard) = prepared.into_parts();
-    match accounts
-        .commit_credential_refresh(
-            CredentialRotationCommit {
-                prepared: facts,
-                settings: None,
-            },
-            context,
-        )
-        .await
-    {
-        Ok(result) => {
-            guard.finish();
-            Ok(result)
-        }
-        Err(error) => {
-            drop(guard);
-            Err(map_store_error(error, resource))
-        }
-    }
-}
-
-async fn delete_credentials(
-    accounts: &dyn AccountStore,
-    provider: &dyn ProviderAdmin,
-    command: CredentialDeletion,
-    resource: &'static str,
-) -> Result<CredentialDeletionResult, AdminError> {
-    for account_id in &command.account_ids {
-        required_credential(accounts, provider.provider_kind(), account_id, resource).await?;
-    }
-    let account_ids = command.account_ids;
-    let revision = accounts
-        .delete_accounts(
-            DeleteAccounts {
-                account_ids: account_ids
-                    .iter()
-                    .map(|account_id| account_id.as_str().to_owned())
-                    .collect(),
-            },
-            &command.context,
-        )
-        .await
-        .map_err(|error| map_store_error(error, resource))?;
-    for account_id in &account_ids {
-        provider.account_unavailable(account_id).await;
-    }
-    provider.account_facts_changed(&account_ids).await;
-    Ok(CredentialDeletionResult {
-        config_revision: revision,
-        account_ids,
-    })
-}
-
-// 用例的操作名补充端口资源上下文，底层分类与原始原因仍由来源持有
-#[derive(Debug, thiserror::Error)]
-#[error("admin operation failed: {operation}")]
-struct OperationFailure {
-    operation: &'static str,
-    source: gateway_core::error::ErrorSource,
-}
+use error::{map_provider_error, map_store_error};
+use publication::publish_committed;
@@ -4,12 +4,10 @@ use std::{
    collections::{BTreeMap, HashMap, btree_map::Entry},
    str::FromStr,
    sync::Arc,
-    time::{Duration as StdDuration, Instant},
 };

 use async_trait::async_trait;
 use chrono::{DateTime, Duration, Utc};
-use futures::TryStreamExt;
 use gateway_core::{account::ProviderAccountId, routing::ProviderKind};

 use crate::{
@@ -17,20 +15,20 @@ use crate::{
        AdminError,
        observability::{
            CostCoverage, CurrencyCost, DashboardAccountUsage, DashboardCapacity,
-            DashboardPeriodMetrics, DashboardResult, DecimalAmount, DiagnosticDimension,
-            DiagnosticsItem, DiagnosticsResult, HealthStatus, HealthTimeline, HealthTimelinePoint,
-            OpsErrorPage, OpsErrorQuery, ProviderBillingInput, RequestMetricPoint, RequestMetrics,
-            TimeRange, Trend, TrendKind, TrendPoint, TrendSummary, UsageBilling,
-            UsageCalculatedBillingFact, UsageDetail, UsageFilter, UsageInsights, UsageInsightsCost,
-            UsageInsightsCostPoint, UsageInsightsHealth, UsageInsightsHealthPoint,
-            UsageInsightsPerformance, UsageInsightsPerformancePoint, UsageOverview, UsagePage,
-            UsageQuery, UsageSummary,
+            DashboardPeriodMetrics, DashboardQuery, DashboardResult, DecimalAmount,
+            DiagnosticDimension, DiagnosticsItem, DiagnosticsResult, Granularity, HealthStatus,
+            HealthTimeline, HealthTimelinePoint, OpsErrorPage, OpsErrorQuery, ProviderBillingInput,
+            RequestMetricPoint, RequestMetrics, TimeRange, Trend, TrendKind, TrendPoint,
+            TrendSummary, UsageBilling, UsageBillingProjection, UsageCalculatedBillingFact,
+            UsageDetail, UsageFilter, UsageInsights, UsageInsightsCost, UsageInsightsCostPoint,
+            UsageInsightsHealth, UsageInsightsHealthPoint, UsageInsightsPerformance,
+            UsageInsightsPerformancePoint, UsageOverview, UsagePage, UsageQuery, UsageSummary,
        },
        provider_credentials::ProviderQuotaRequest,
    },
    ports::{
        provider::{ProviderAdminErrorKind, ProviderAdminRegistry},
-        store::{AccountStore, ObservabilityStore, SettingsStore, UsageCalculatedBillingStream},
+        store::{AccountStore, ObservabilityStore, SettingsStore, UsageBillingProjector},
    },
 };

@@ -39,59 +37,9 @@ use super::{map_provider_error, map_store_error};
 const HEALTH_TIMELINE_SLOT_MINUTES: i64 = 15;
 const HEALTH_TIMELINE_MIN_SAMPLE_SIZE: u64 = 10;
 const HEALTH_TIMELINE_UNAVAILABLE_FAILURE_THRESHOLD: u64 = 3;
-const HEALTH_TIMELINE_STABLE_RELIABILITY: f64 = 99.0;
-const DASHBOARD_QUERY_BUCKET_SECONDS: i64 = 2;
-const DASHBOARD_QUERY_CACHE_RETENTION: StdDuration = StdDuration::from_secs(2);
-
-#[derive(Clone, Copy, PartialEq, Eq, Hash)]
-struct DashboardQueryKey {
-    start: DateTime<Utc>,
-    end_bucket: i64,
-}
-
-impl DashboardQueryKey {
-    fn new(range: TimeRange) -> Self {
-        Self {
-            start: range.start,
-            end_bucket: range
-                .end
-                .timestamp()
-                .div_euclid(DASHBOARD_QUERY_BUCKET_SECONDS),
-        }
-    }
-}
-
-struct DashboardQueryEntry {
-    created_at: Instant,
-    result: Arc<tokio::sync::OnceCell<Result<DashboardResult, AdminError>>>,
-}
-
-#[derive(Default)]
-struct DashboardQueryCache {
-    entries: tokio::sync::Mutex<HashMap<DashboardQueryKey, DashboardQueryEntry>>,
-}
-
-impl DashboardQueryCache {
-    async fn result_cell(
-        &self,
-        key: DashboardQueryKey,
-    ) -> Arc<tokio::sync::OnceCell<Result<DashboardResult, AdminError>>> {
-        let now = Instant::now();
-        let mut entries = self.entries.lock().await;
-        entries.retain(|_, entry| {
-            now.duration_since(entry.created_at) < DASHBOARD_QUERY_CACHE_RETENTION
-        });
-        Arc::clone(
-            &entries
-                .entry(key)
-                .or_insert_with(|| DashboardQueryEntry {
-                    created_at: now,
-                    result: Arc::new(tokio::sync::OnceCell::new()),
-                })
-                .result,
-        )
-    }
-}
+const HEALTH_TIMELINE_STABLE_RELIABILITY: f64 = 95.0;
+mod store_cache;
+pub(crate) use store_cache::CachedObservabilityStore;

 /// API 消费的观测控制面服务
 #[async_trait]
@@ -130,7 +78,6 @@ pub(crate) struct DefaultObservabilityService {
    accounts: Arc<dyn AccountStore>,
    settings: Arc<dyn SettingsStore>,
    providers: ProviderAdminRegistry,
-    dashboard_queries: DashboardQueryCache,
 }

 impl DefaultObservabilityService {
@@ -148,7 +95,6 @@ impl DefaultObservabilityService {
            accounts,
            settings,
            providers,
-            dashboard_queries: DashboardQueryCache::default(),
        }
    }

@@ -157,12 +103,13 @@ impl DefaultObservabilityService {
        range: TimeRange,
    ) -> Result<DashboardResult, AdminError> {
        let observed_at = Utc::now();
-        let (mut observation, settings, runtime_slots) = futures::try_join!(
-            self.store.dashboard_summary(range, observed_at),
+        let (mut observation, settings) = futures::try_join!(
+            self.store
+                .dashboard_summary(DashboardQuery::new(range), observed_at),
            self.settings.load_runtime_settings(),
-            self.store.dashboard_runtime_slots(observed_at),
        )
        .map_err(|error| map_store_error(error, "dashboard"))?;
+        let runtime_slots = observation.runtime_slots;
        self.enrich_list_records(&mut observation.recent_requests);
        self.enrich_dashboard_quotas(&mut observation.account_usage)
            .await;
@@ -184,7 +131,7 @@ impl DefaultObservabilityService {
        let yesterday = dashboard_period_metrics(&observation.trend, yesterday_start, today_start);
        let total_billing_usd = observation.totals.billing_usd.clone();
        let total_cached_token_rate = rate_or_zero(
-            observation.totals.cached_tokens,
+            observation.totals.cached_input_tokens,
            observation.totals.input_tokens,
        );
        let (first_token_latency_sum_ms, first_token_latency_count) = observation
@@ -198,7 +145,11 @@ impl DefaultObservabilityService {
            });
        let average_first_token_latency_ms =
            average(first_token_latency_sum_ms, first_token_latency_count);
-        let trend = trend(TrendKind::Usage, observation.trend.clone())?;
+        let trend = trend(
+            TrendKind::Usage,
+            observation.trend.clone(),
+            observation.analytics.clone(),
+        )?;
        let health_timeline =
            health_timeline_at(&observation.trend, observation.range.end, self.timezone)?;
        let wire_profiles = self
@@ -246,15 +197,12 @@ impl ObservabilityService for DefaultObservabilityService {
        range: TimeRange,
        kind: TrendKind,
    ) -> Result<DashboardResult, AdminError> {
-        let cell = self
-            .dashboard_queries
-            .result_cell(DashboardQueryKey::new(range))
-            .await;
-        let mut result = cell
-            .get_or_init(|| self.load_dashboard_summary(range))
-            .await
-            .clone()?;
-        result.trend = trend(kind, result.observation.trend.clone())?;
+        let mut result = self.load_dashboard_summary(range).await?;
+        result.trend = trend(
+            kind,
+            result.observation.trend.clone(),
+            result.observation.analytics.clone(),
+        )?;
        Ok(result)
    }

@@ -263,12 +211,16 @@ impl ObservabilityService for DefaultObservabilityService {
        range: TimeRange,
        kind: TrendKind,
    ) -> Result<Trend, AdminError> {
-        let points = self
+        let observation = self
            .store
-            .dashboard_trend(range)
+            .usage_insights_observation(
+                range,
+                UsageFilter::default(),
+                Granularity::for_range(range),
+            )
            .await
            .map_err(|error| map_store_error(error, "dashboard trend"))?;
-        trend(kind, points)
+        trend(kind, observation.trend, observation.overview.analytics)
    }

    async fn usage_records(&self, query: UsageQuery) -> Result<UsagePage, AdminError> {
@@ -319,21 +271,23 @@ impl ObservabilityService for DefaultObservabilityService {
        range: TimeRange,
        filter: UsageFilter,
    ) -> Result<UsageInsights, AdminError> {
-        let aggregates = async {
-            futures::try_join!(
-                self.store.usage_summary(range, filter.clone()),
-                self.store.usage_trend(range, filter.clone()),
-            )
-            .map_err(|error| map_store_error(error, "usage insights"))
-        };
-        let ((overview, trend), standard_costs) = futures::try_join!(
-            aggregates,
-            recover_standard_costs(
-                &self.providers,
-                self.store
-                    .usage_calculated_billing_facts(range, filter.clone()),
-            ),
-        )?;
+        let granularity = Granularity::for_range(range);
+        let observation = self
+            .store
+            .usage_insights_observation(range, filter, granularity)
+            .await
+            .map_err(|error| map_store_error(error, "usage insights"))?;
+        let mut standard_costs = UsageCostScenarios::default();
+        for point in observation.costs {
+            if let Some(amount) = point.standard_amount {
+                standard_costs.standard.add(point.bucket_start, amount)?;
+            }
+            if let Some(amount) = point.no_cache_amount {
+                standard_costs.no_cache.add(point.bucket_start, amount)?;
+            }
+        }
+        let overview = observation.overview;
+        let trend = observation.trend;
        build_usage_insights(overview, trend, standard_costs)
    }

@@ -345,7 +299,7 @@ impl ObservabilityService for DefaultObservabilityService {
    ) -> Result<DiagnosticsResult, AdminError> {
        let observation = self
            .store
-            .usage_diagnostics(range, filter, dimension)
+            .usage_diagnostics(range, filter, dimension, 100)
            .await
            .map_err(|error| map_store_error(error, "usage diagnostics"))?;
        let items = observation
@@ -387,7 +341,11 @@ impl ObservabilityService for DefaultObservabilityService {
                }
            })
            .collect::<Vec<_>>();
-        Ok(DiagnosticsResult { dimension, items })
+        Ok(DiagnosticsResult {
+            analytics: observation.analytics,
+            dimension,
+            items,
+        })
    }

    async fn ops_errors(&self, query: OpsErrorQuery) -> Result<OpsErrorPage, AdminError> {
@@ -421,8 +379,9 @@ fn build_usage_insights(
    }

    let requests = &overview.requests;
-    let failed_requests = service_failure_count(requests);
-    let health_requests = requests.success_count.saturating_add(failed_requests);
+    let health_window = HealthWindow::from_metrics(requests);
+    let failed_requests = health_window.failed_requests;
+    let health_requests = health_window.eligible_requests();
    let health = UsageInsightsHealth {
        total_requests: requests.request_count,
        success_requests: requests.success_count,
@@ -440,17 +399,19 @@ fn build_usage_insights(
        points: trend
            .iter()
            .map(|point| {
-                let failed_requests = service_failure_count(&point.metrics);
-                let health_requests = point.metrics.success_count.saturating_add(failed_requests);
+                let health_window = HealthWindow::from_metrics(&point.metrics);
                UsageInsightsHealthPoint {
                    total_requests: point.metrics.request_count,
                    bucket_start: point.bucket_start,
                    success_requests: point.metrics.success_count,
-                    failed_requests,
+                    failed_requests: health_window.failed_requests,
                    cancelled_requests: point.metrics.cancelled_count,
                    incomplete_requests: point.metrics.incomplete_count,
                    caller_error_requests: point.metrics.caller_error_count,
-                    error_rate: rate_or_zero(failed_requests, health_requests),
+                    error_rate: rate_or_zero(
+                        health_window.non_success_requests(),
+                        health_window.eligible_requests(),
+                    ),
                }
            })
            .collect(),
@@ -531,14 +492,14 @@ fn build_usage_insights(
        tier_premium,
        tokens_per_request: rate_or_zero(requests.total_tokens, requests.request_count),
        cost_per_successful_request,
-        cached_token_rate: rate_or_zero(requests.cached_tokens, requests.input_tokens),
+        cached_token_rate: rate_or_zero(requests.cached_input_tokens, requests.input_tokens),
        cache_hit_request_rate: ratio(
            requests.cache_hit_request_count,
            requests.cache_eligible_request_count,
        ),
        input_tokens: requests.input_tokens,
        output_tokens: requests.output_tokens,
-        cached_tokens: requests.cached_tokens,
+        cached_input_tokens: requests.cached_input_tokens,
        total_tokens: requests.total_tokens,
        points: trend
            .iter()
@@ -546,7 +507,7 @@ fn build_usage_insights(
                bucket_start: point.bucket_start,
                input_tokens: point.metrics.input_tokens,
                output_tokens: point.metrics.output_tokens,
-                cached_tokens: point.metrics.cached_tokens,
+                cached_input_tokens: point.metrics.cached_input_tokens,
                total_tokens: point.metrics.total_tokens,
                estimated_cost: usd_cost(&point.costs),
                standard_cost: standard_costs_by_bucket.get(&point.bucket_start).cloned(),
@@ -556,7 +517,7 @@ fn build_usage_insights(
                    usd_cost(&point.costs).as_ref(),
                ),
                cached_token_rate: rate_or_zero(
-                    point.metrics.cached_tokens,
+                    point.metrics.cached_input_tokens,
                    point.metrics.input_tokens,
                ),
                cache_hit_request_rate: ratio(
@@ -569,6 +530,7 @@ fn build_usage_insights(
        coverage: overview.attempts.cost_coverage.clone(),
    };
    Ok(UsageInsights {
+        analytics: overview.analytics,
        granularity,
        health,
        performance,
@@ -618,58 +580,65 @@ struct UsageCostScenarios {
    no_cache: ScenarioCosts,
 }

-async fn recover_standard_costs(
-    providers: &ProviderAdminRegistry,
-    mut facts: UsageCalculatedBillingStream<'_>,
-) -> Result<UsageCostScenarios, AdminError> {
-    let mut scenarios = UsageCostScenarios::default();
-    while let Some(mut fact) = facts
-        .try_next()
-        .await
-        .map_err(|error| map_store_error(error, "usage billing facts"))?
-    {
+/// 在后台投影时恢复费用场景，查询不再逐请求读取计费快照
+pub struct ProviderUsageBillingProjector {
+    providers: ProviderAdminRegistry,
+}
+
+impl ProviderUsageBillingProjector {
+    #[must_use]
+    pub fn new(providers: ProviderAdminRegistry) -> Self {
+        Self { providers }
+    }
+}
+
+impl UsageBillingProjector for ProviderUsageBillingProjector {
+    fn project(
+        &self,
+        fact: &UsageCalculatedBillingFact,
+    ) -> Result<UsageBillingProjection, AdminError> {
        let Ok(provider_kind) = ProviderKind::new(fact.provider_kind.clone()) else {
-            continue;
+            return Ok(UsageBillingProjection::default());
        };
        let input = ProviderBillingInput {
            upstream_model_id: fact.upstream_model_id.clone(),
            service_tier: fact.service_tier.clone(),
            input_tokens: fact.input_tokens,
            output_tokens: fact.output_tokens,
-            cached_tokens: fact.cached_tokens,
-            cache_write_tokens: fact.cache_write_tokens,
+            cached_input_tokens: fact.cached_input_tokens,
+            cache_write_input_tokens: fact.cache_write_input_tokens,
            total: fact.total.clone(),
        };
        let breakdown = match fact
            .breakdown
-            .take()
-            .filter(|b| b.total_amount == input.total)
+            .as_ref()
+            .filter(|breakdown| breakdown.total_amount == input.total)
+            .cloned()
            .map_or_else(
-                || providers.calculated_billing(&provider_kind, &input),
-                |b| Ok(Some(b)),
+                || self.providers.calculated_billing(&provider_kind, &input),
+                |breakdown| Ok(Some(breakdown)),
            ) {
            Ok(breakdown) => breakdown,
-            Err(error) if error.kind() == ProviderAdminErrorKind::Unsupported => continue,
+            Err(error) if error.kind() == ProviderAdminErrorKind::Unsupported => {
+                return Ok(UsageBillingProjection::default());
+            }
            Err(error) => return Err(map_provider_error(error, "usage billing")),
        };
        let Some(breakdown) = breakdown else {
-            continue;
+            return Ok(UsageBillingProjection::default());
        };
        if !breakdown
            .standard_amount
            .currency
            .eq_ignore_ascii_case("USD")
        {
-            continue;
-        }
-        scenarios
-            .standard
-            .add(fact.bucket_start, breakdown.standard_amount.amount.clone())?;
-        if let Some(no_cache_cost) = no_cache_cost(&fact, &breakdown) {
-            scenarios.no_cache.add(fact.bucket_start, no_cache_cost)?;
+            return Ok(UsageBillingProjection::default());
        }
+        Ok(UsageBillingProjection {
+            standard_amount: Some(breakdown.standard_amount.amount.clone()),
+            no_cache_amount: no_cache_cost(fact, &breakdown),
+        })
    }
-    Ok(scenarios)
 }

 fn no_cache_cost(
@@ -680,19 +649,21 @@ fn no_cache_cost(
    let input_tokens = fact
        .input_tokens?
        .checked_sub(image.map_or(0, |i| i.input_tokens))?;
-    let cached_tokens = fact
-        .cached_tokens
+    let cached_input_tokens = fact
+        .cached_input_tokens
        .unwrap_or_default()
-        .checked_sub(image.map_or(0, |i| i.cached_tokens))?
+        .checked_sub(image.map_or(0, |i| i.cached_input_tokens))?
        .min(input_tokens);
-    let cache_write_tokens = fact
-        .cache_write_tokens
+    let cache_write_input_tokens = fact
+        .cache_write_input_tokens
        .unwrap_or_default()
-        .min(input_tokens.saturating_sub(cached_tokens));
+        .min(input_tokens.saturating_sub(cached_input_tokens));
    let input_rate = decimal(&breakdown.input_price_per_million.amount)?;
    let replaced_input_amount = input_rate
        .scaled()
-        .checked_mul(u128::from(cached_tokens.saturating_add(cache_write_tokens)))?
+        .checked_mul(u128::from(
+            cached_input_tokens.saturating_add(cache_write_input_tokens),
+        ))?
        .checked_div(1_000_000)?;
    let mut total = decimal(&breakdown.total_amount.amount)?
        .scaled()
@@ -702,7 +673,7 @@ fn no_cache_cost(
    if let Some(image) = image {
        let image_no_cache = decimal(&image.input_price_per_million.amount)?
            .scaled()
-            .checked_mul(u128::from(image.cached_tokens))?
+            .checked_mul(u128::from(image.cached_input_tokens))?
            .checked_div(1_000_000)?;
        total = total
            .checked_sub(decimal(&image.cache_read_amount.amount)?.scaled())?
@@ -827,8 +798,8 @@ impl DefaultObservabilityService {
                service_tier: record.service_tier.clone(),
                input_tokens: record.input_tokens,
                output_tokens: record.output_tokens,
-                cached_tokens: record.cached_tokens,
-                cache_write_tokens: record.cache_write_tokens,
+                cached_input_tokens: record.cached_input_tokens,
+                cache_write_input_tokens: record.cache_write_input_tokens,
                total: total.clone(),
            };
            if let Ok(Some(breakdown)) = self.providers.calculated_billing(&provider_kind, &input) {
@@ -859,8 +830,8 @@ impl DefaultObservabilityService {
                service_tier: record.service_tier.clone(),
                input_tokens: record.input_tokens,
                output_tokens: record.output_tokens,
-                cached_tokens: record.cached_tokens,
-                cache_write_tokens: record.cache_write_tokens,
+                cached_input_tokens: record.cached_input_tokens,
+                cache_write_input_tokens: record.cache_write_input_tokens,
                total: total.clone(),
            };
            if let Ok(Some(breakdown)) = self.providers.calculated_billing(&provider_kind, &input) {
@@ -949,7 +920,11 @@ pub(super) fn health_timeline_at(
    })
 }

-fn trend(kind: TrendKind, points: Vec<RequestMetricPoint>) -> Result<Trend, AdminError> {
+fn trend(
+    kind: TrendKind,
+    points: Vec<RequestMetricPoint>,
+    analytics: crate::model::analytics::AnalyticsMetadata,
+) -> Result<Trend, AdminError> {
    let mut metrics = RequestMetrics::default();
    let mut coverage = CostCoverage::default();
    let mut costs = BTreeMap::<String, DecimalAmount>::new();
@@ -984,7 +959,7 @@ fn trend(kind: TrendKind, points: Vec<RequestMetricPoint>) -> Result<Trend, Admi
    let service_failure_count = service_failure_count(&metrics);
    let success_rate = ratio(
        metrics.success_count,
-        metrics.success_count.saturating_add(service_failure_count),
+        HealthWindow::from_metrics(&metrics).eligible_requests(),
    );
    let cache_hit_request_rate = ratio(
        metrics.cache_hit_request_count,
@@ -1005,13 +980,14 @@ fn trend(kind: TrendKind, points: Vec<RequestMetricPoint>) -> Result<Trend, Admi
        .filter_map(|point| point.metrics.output_throughput_p50)
        .min();
    Ok(Trend {
+        analytics,
        kind,
        points: points.into_iter().map(trend_point).collect(),
        summary: TrendSummary {
            request_count: metrics.request_count,
            input_tokens: metrics.input_tokens,
            output_tokens: metrics.output_tokens,
-            cached_tokens: metrics.cached_tokens,
+            cached_input_tokens: metrics.cached_input_tokens,
            total_tokens: metrics.total_tokens,
            service_failure_count,
            average_latency_ms,
@@ -1042,12 +1018,18 @@ fn trend_point(point: RequestMetricPoint) -> TrendPoint {
            point.metrics.first_token_latency_sum_ms,
            point.metrics.first_token_latency_count,
        ),
-        cached_token_rate: rate_or_zero(point.metrics.cached_tokens, point.metrics.input_tokens),
+        cached_token_rate: rate_or_zero(
+            point.metrics.cached_input_tokens,
+            point.metrics.input_tokens,
+        ),
        cache_hit_request_rate: ratio(
            point.metrics.cache_hit_request_count,
            point.metrics.cache_eligible_request_count,
        ),
-        success_rate: ratio(point.metrics.success_count, point.metrics.request_count),
+        success_rate: ratio(
+            point.metrics.success_count,
+            HealthWindow::from_metrics(&point.metrics).eligible_requests(),
+        ),
        metrics: point.metrics,
        cost_coverage: point.cost_coverage,
        costs: point.costs,
@@ -1068,11 +1050,13 @@ fn dashboard_period_metrics(
        result.request_count = result.request_count.saturating_add(metrics.request_count);
        result.input_tokens = result.input_tokens.saturating_add(metrics.input_tokens);
        result.output_tokens = result.output_tokens.saturating_add(metrics.output_tokens);
-        result.cached_tokens = result.cached_tokens.saturating_add(metrics.cached_tokens);
+        result.cached_input_tokens = result
+            .cached_input_tokens
+            .saturating_add(metrics.cached_input_tokens);
        result.total_tokens = result.total_tokens.saturating_add(metrics.total_tokens);
    }
-    result.cached_token_rate = rate_or_zero(result.cached_tokens, result.input_tokens);
-    result.observed_cached_token_rate = ratio(result.cached_tokens, result.input_tokens);
+    result.cached_token_rate = rate_or_zero(result.cached_input_tokens, result.input_tokens);
+    result.observed_cached_token_rate = ratio(result.cached_input_tokens, result.input_tokens);
    result
 }

@@ -1089,13 +1073,15 @@ fn add_request_metrics(total: &mut RequestMetrics, value: &RequestMetrics) {
        .saturating_add(value.caller_error_count);
    total.input_tokens = total.input_tokens.saturating_add(value.input_tokens);
    total.output_tokens = total.output_tokens.saturating_add(value.output_tokens);
-    total.cached_tokens = total.cached_tokens.saturating_add(value.cached_tokens);
-    total.cache_write_tokens = total
-        .cache_write_tokens
-        .saturating_add(value.cache_write_tokens);
-    total.reasoning_tokens = total
-        .reasoning_tokens
-        .saturating_add(value.reasoning_tokens);
+    total.cached_input_tokens = total
+        .cached_input_tokens
+        .saturating_add(value.cached_input_tokens);
+    total.cache_write_input_tokens = total
+        .cache_write_input_tokens
+        .saturating_add(value.cache_write_input_tokens);
+    total.reasoning_output_tokens = total
+        .reasoning_output_tokens
+        .saturating_add(value.reasoning_output_tokens);
    total.total_tokens = total.total_tokens.saturating_add(value.total_tokens);
    total.first_token_latency_sum_ms = total
        .first_token_latency_sum_ms
@@ -1143,20 +1129,29 @@ struct HealthWindow {
 }

 impl HealthWindow {
+    fn from_metrics(metrics: &RequestMetrics) -> Self {
+        Self {
+            success_requests: metrics.success_count,
+            failed_requests: service_failure_count(metrics),
+            cancelled_requests: metrics.cancelled_count,
+            incomplete_requests: metrics.incomplete_count,
+            caller_error_requests: metrics.caller_error_count,
+        }
+    }
+
+    // 未完成保留交付终态，但上游失败、超时和进程中断都不能视为服务成功
+    fn non_success_requests(self) -> u64 {
+        self.failed_requests
+            .saturating_add(self.incomplete_requests)
+    }
+
+    fn eligible_requests(self) -> u64 {
+        self.success_requests
+            .saturating_add(self.non_success_requests())
+    }
+
    fn add_metrics(&mut self, metrics: &RequestMetrics) {
-        self.success_requests = self.success_requests.saturating_add(metrics.success_count);
-        self.failed_requests = self
-            .failed_requests
-            .saturating_add(service_failure_count(metrics));
-        self.cancelled_requests = self
-            .cancelled_requests
-            .saturating_add(metrics.cancelled_count);
-        self.incomplete_requests = self
-            .incomplete_requests
-            .saturating_add(metrics.incomplete_count);
-        self.caller_error_requests = self
-            .caller_error_requests
-            .saturating_add(metrics.caller_error_count);
+        self.add_window(Self::from_metrics(metrics));
    }

    fn add_window(&mut self, other: Self) {
@@ -1175,15 +1170,13 @@ impl HealthWindow {
 }

 fn health_status(bucket: HealthWindow, is_future: bool) -> HealthStatus {
-    let eligible_requests = bucket
-        .success_requests
-        .saturating_add(bucket.failed_requests);
+    let eligible_requests = bucket.eligible_requests();
    if is_future {
        HealthStatus::Future
    } else if eligible_requests == 0 {
        HealthStatus::NoData
    } else if bucket.success_requests == 0
-        && bucket.failed_requests >= HEALTH_TIMELINE_UNAVAILABLE_FAILURE_THRESHOLD
+        && bucket.non_success_requests() >= HEALTH_TIMELINE_UNAVAILABLE_FAILURE_THRESHOLD
    {
        HealthStatus::Unavailable
    } else if eligible_requests < HEALTH_TIMELINE_MIN_SAMPLE_SIZE {
@@ -1198,9 +1191,7 @@ fn health_status(bucket: HealthWindow, is_future: bool) -> HealthStatus {
 }

 fn health_reliability(bucket: HealthWindow) -> Option<f64> {
-    let eligible_requests = bucket
-        .success_requests
-        .saturating_add(bucket.failed_requests);
+    let eligible_requests = bucket.eligible_requests();
    (eligible_requests > 0)
        .then(|| bucket.success_requests as f64 / eligible_requests as f64 * 100.0)
 }
@@ -0,0 +1,292 @@
+//! 有界统计缓存：身份和完整筛选参与键，删除版本阻止旧数据复活
+
+use crate::model::observability::*;
+use crate::ports::store::{
+    AdminStoreError, AdminStoreErrorKind, AdminStoreResult, ObservabilityStore,
+};
+use async_trait::async_trait;
+use chrono::{DateTime, Utc};
+use std::{collections::HashMap, future::Future, hash::Hash, sync::Arc, time::Duration};
+use tokio::{sync::Mutex, time::Instant};
+
+const CAPACITY: usize = 64;
+const TTL: Duration = Duration::from_secs(15);
+const MAX_STALE: Duration = Duration::from_secs(60);
+
+type Slot<T> = Arc<Mutex<Option<Cached<T>>>>;
+struct Cached<T> {
+    value: T,
+    created: Instant,
+}
+struct Entry<T> {
+    slot: Slot<T>,
+    touched: Instant,
+}
+struct Cache<K, T> {
+    entries: Mutex<HashMap<K, Entry<T>>>,
+}
+impl<K, T> Default for Cache<K, T> {
+    fn default() -> Self {
+        Self {
+            entries: Mutex::new(HashMap::new()),
+        }
+    }
+}
+
+trait AnalyticsValue: Clone {
+    fn metadata(&mut self) -> &mut AnalyticsMetadata;
+}
+impl AnalyticsValue for DashboardObservation {
+    fn metadata(&mut self) -> &mut AnalyticsMetadata {
+        &mut self.analytics
+    }
+}
+impl AnalyticsValue for UsageOverview {
+    fn metadata(&mut self) -> &mut AnalyticsMetadata {
+        &mut self.analytics
+    }
+}
+impl AnalyticsValue for UsageInsightsObservation {
+    fn metadata(&mut self) -> &mut AnalyticsMetadata {
+        &mut self.overview.analytics
+    }
+}
+impl AnalyticsValue for DiagnosticsObservation {
+    fn metadata(&mut self) -> &mut AnalyticsMetadata {
+        &mut self.analytics
+    }
+}
+
+impl<K: Eq + Hash, T: AnalyticsValue> Cache<K, T> {
+    async fn get<F, Fut>(
+        &self,
+        key: K,
+        store: &dyn ObservabilityStore,
+        ttl: Duration,
+        load: F,
+    ) -> AdminStoreResult<T>
+    where
+        F: FnOnce() -> Fut,
+        Fut: Future<Output = AdminStoreResult<T>>,
+    {
+        // 刷新失败后的同键等待也计入预算，避免串行重试把延迟放大为队列长度倍数
+        tokio::time::timeout(
+            store.query_timeout(),
+            self.get_within_budget(key, store, ttl, load),
+        )
+        .await
+        .map_err(|source| {
+            AdminStoreError::new(
+                AdminStoreErrorKind::Unavailable,
+                "observability cache",
+                "observability cache execution budget is exhausted",
+            )
+            .with_source(source)
+        })?
+    }
+
+    async fn get_within_budget<F, Fut>(
+        &self,
+        key: K,
+        store: &dyn ObservabilityStore,
+        ttl: Duration,
+        load: F,
+    ) -> AdminStoreResult<T>
+    where
+        F: FnOnce() -> Fut,
+        Fut: Future<Output = AdminStoreResult<T>>,
+    {
+        let slot = {
+            let mut entries = self.entries.lock().await;
+            if !entries.contains_key(&key) && entries.len() >= CAPACITY {
+                let oldest = entries
+                    .iter()
+                    .filter(|(_, entry)| Arc::strong_count(&entry.slot) == 1)
+                    .min_by_key(|(_, entry)| entry.touched)
+                    .map(|(_, entry)| entry.touched);
+                if let Some(oldest) = oldest {
+                    entries.retain(|_, entry| entry.touched != oldest);
+                }
+            }
+            if !entries.contains_key(&key) && entries.len() >= CAPACITY {
+                drop(entries);
+                return load().await;
+            }
+            let entry = entries.entry(key).or_insert_with(|| Entry {
+                slot: Arc::new(Mutex::new(None)),
+                touched: Instant::now(),
+            });
+            entry.touched = Instant::now();
+            entry.slot.clone()
+        };
+        // 同键刷新只执行一次；失败不会缓存成成功，也不延长旧结果寿命
+        let mut cached = slot.lock().await;
+        // 等锁期间代次可能推进；取得同键锁后再核对，失败时也不能回用已删除事实
+        let generation = store.analytics_cache_generation().await?;
+        if let Some(entry) = cached.as_mut()
+            && entry.value.metadata().generation == generation
+            && entry.created.elapsed() < ttl
+        {
+            return Ok(with_age(entry.value.clone(), false));
+        }
+        match load().await {
+            Ok(value) => {
+                *cached = Some(Cached {
+                    value: value.clone(),
+                    created: Instant::now(),
+                });
+                Ok(value)
+            }
+            Err(error) => {
+                if ttl == TTL
+                    && error.kind() == AdminStoreErrorKind::Unavailable
+                    && let Some(entry) = cached.as_mut()
+                    && entry.created.elapsed() <= MAX_STALE
+                    && Utc::now()
+                        .signed_duration_since(entry.value.metadata().generated_at)
+                        .to_std()
+                        .unwrap_or_default()
+                        <= MAX_STALE
+                    && entry.value.metadata().state != AnalyticsState::Building
+                    && entry.value.metadata().generation
+                        == store.analytics_cache_generation().await?
+                {
+                    return Ok(with_age(entry.value.clone(), true));
+                }
+                Err(error)
+            }
+        }
+    }
+}
+
+fn with_age<T: AnalyticsValue>(mut value: T, stale: bool) -> T {
+    let metadata = value.metadata();
+    metadata.lag_seconds = metadata.lag_seconds.saturating_add(
+        Utc::now()
+            .signed_duration_since(metadata.generated_at)
+            .num_seconds()
+            .max(0) as u64,
+    );
+    if stale {
+        metadata.state = AnalyticsState::Stale;
+    }
+    value
+}
+
+type UsageKey = (TimeRange, UsageFilter);
+pub(crate) struct CachedObservabilityStore {
+    inner: Arc<dyn ObservabilityStore>,
+    dashboard: Cache<DashboardQuery, DashboardObservation>,
+    summaries: Cache<UsageKey, UsageOverview>,
+    insights: Cache<(UsageKey, Granularity), UsageInsightsObservation>,
+    diagnostics: Cache<(UsageKey, DiagnosticDimension, u16), DiagnosticsObservation>,
+}
+impl CachedObservabilityStore {
+    pub(crate) fn new(inner: Arc<dyn ObservabilityStore>) -> Self {
+        Self {
+            inner,
+            dashboard: Cache::default(),
+            summaries: Cache::default(),
+            insights: Cache::default(),
+            diagnostics: Cache::default(),
+        }
+    }
+}
+
+#[async_trait]
+impl ObservabilityStore for CachedObservabilityStore {
+    fn query_timeout(&self) -> Duration {
+        self.inner.query_timeout()
+    }
+
+    async fn analytics_cache_generation(&self) -> AdminStoreResult<u64> {
+        self.inner.analytics_cache_generation().await
+    }
+    async fn dashboard_summary(
+        &self,
+        query: DashboardQuery,
+        observed_at: DateTime<Utc>,
+    ) -> AdminStoreResult<DashboardObservation> {
+        // 复合概览还包含账号容量和最近请求，保持原有两秒实时刷新上限
+        self.dashboard
+            .get(
+                query.clone(),
+                self.inner.as_ref(),
+                Duration::from_secs(2),
+                || self.inner.dashboard_summary(query, observed_at),
+            )
+            .await
+    }
+    async fn dashboard_trend(
+        &self,
+        range: TimeRange,
+        granularity: Granularity,
+    ) -> AdminStoreResult<Vec<RequestMetricPoint>> {
+        self.inner.dashboard_trend(range, granularity).await
+    }
+    async fn usage_trend(
+        &self,
+        range: TimeRange,
+        filter: UsageFilter,
+        granularity: Granularity,
+    ) -> AdminStoreResult<Vec<RequestMetricPoint>> {
+        self.inner.usage_trend(range, filter, granularity).await
+    }
+    async fn usage_insights_observation(
+        &self,
+        range: TimeRange,
+        filter: UsageFilter,
+        granularity: Granularity,
+    ) -> AdminStoreResult<UsageInsightsObservation> {
+        self.insights
+            .get(
+                ((range, filter.clone()), granularity),
+                self.inner.as_ref(),
+                TTL,
+                || {
+                    self.inner
+                        .usage_insights_observation(range, filter, granularity)
+                },
+            )
+            .await
+    }
+    async fn usage_summary(
+        &self,
+        range: TimeRange,
+        filter: UsageFilter,
+    ) -> AdminStoreResult<UsageOverview> {
+        self.summaries
+            .get((range, filter.clone()), self.inner.as_ref(), TTL, || {
+                self.inner.usage_summary(range, filter)
+            })
+            .await
+    }
+    async fn usage_diagnostics(
+        &self,
+        range: TimeRange,
+        filter: UsageFilter,
+        dimension: DiagnosticDimension,
+        limit: u16,
+    ) -> AdminStoreResult<DiagnosticsObservation> {
+        self.diagnostics
+            .get(
+                ((range, filter.clone()), dimension, limit),
+                self.inner.as_ref(),
+                TTL,
+                || {
+                    self.inner
+                        .usage_diagnostics(range, filter, dimension, limit)
+                },
+            )
+            .await
+    }
+    async fn list_usage_records(&self, query: UsageQuery) -> AdminStoreResult<UsagePage> {
+        self.inner.list_usage_records(query).await
+    }
+    async fn usage_record_detail(&self, request_id: &str) -> AdminStoreResult<UsageDetail> {
+        self.inner.usage_record_detail(request_id).await
+    }
+    async fn list_ops_errors(&self, query: OpsErrorQuery) -> AdminStoreResult<OpsErrorPage> {
+        self.inner.list_ops_errors(query).await
+    }
+}
@@ -2,7 +2,10 @@

 use std::collections::{BTreeMap, BTreeSet};

-use gateway_core::{policy::ClientApiKeyId, routing::AccountGroupId};
+use gateway_core::{
+    policy::ClientApiKeyId,
+    routing::{AccountGroupId, extensions::ExtensionSetReference},
+};
 use secrecy::ExposeSecret;

 use super::PluginsService;
@@ -41,14 +44,11 @@ impl PluginsService {
            .map_err(|error| map_store_error(error, "plugin"))?;
        let warning = match self
            .inspector
-            .inspect(artifact.archive.clone(), Some(digest.to_owned()))
+            .compatibility_warning(artifact.archive, digest.to_owned())
            .await
        {
-            Ok(_) => PackageStatus {
-                warning: self
-                    .inspector
-                    .compatibility_warning(artifact.archive, digest.to_owned())
-                    .await?,
+            Ok(warning) => PackageStatus {
+                warning,
                load_error: None,
            },
            Err(error) if error.kind() == AdminErrorKind::Invalid => PackageStatus {
@@ -368,25 +368,8 @@ impl PluginsService {
            )
            .await
            .map_err(|e| map_store_error(e, "plugin"))?;
-        let prepared = if result.config_revision == candidate_revision
-            && result.instance.revision == candidate_revision
-        {
-            prepared
-        } else {
-            snapshot.config_revision = result.config_revision;
-            snapshot
-                .instances
-                .retain(|item| item.id != result.instance.id);
-            snapshot.instances.push(result.instance.clone());
-            apply_replacements(&mut snapshot, &replacements);
-            self.preparation.prepare(snapshot).await?
-        };
-        self.preparation
-            .activate_state(&prepared, &result.instance)
+        self.publish_instance(snapshot, prepared, &result, &replacements)
            .await?;
-        // prepared 的强引用跨过提交与唯一发布入口，防止候选在被读取之前回收
-        publish_committed(self.snapshots.as_ref(), result.config_revision).await?;
-        drop(prepared);
        Ok(result)
    }

@@ -463,48 +446,45 @@ impl PluginsService {
                    .await);
            }
        };
-        if let Err(error) = self
-            .preparation
-            .migrate_state(&migration_prepared, transition.clone())
-            .await
-        {
-            return Err(self
-                .recover_failed_state_transition(
-                    Some(&transition.id),
-                    &previous,
-                    &previous_state,
-                    disabled_revision,
+        // 迁移开始后的所有提交前失败都走同一恢复出口；提交成功后不再回滚旧配置
+        let committed = async {
+            self.preparation
+                .migrate_state(&migration_prepared, transition.clone())
+                .await?;
+            let mut current = self
+                .store
+                .load_instances()
+                .await
+                .map_err(|error| map_store_error(error, "plugin"))?;
+            if current.config_revision != expected_revision {
+                return Err(AdminError::conflict("迁移期间插件配置已发生变化"));
+            }
+            let candidate_revision = next_revision(expected_revision)?;
+            target.revision = candidate_revision;
+            current.instances.retain(|item| item.id != target.id);
+            current.instances.push(target.clone());
+            current.config_revision = candidate_revision;
+            apply_replacements(&mut current, replacements);
+            let prepared = self.preparation.prepare(current.clone()).await?;
+            let result = self
+                .store
+                .save_instance_replacing(
+                    target,
+                    expected_revision,
+                    PluginStateCommit {
+                        configuration: target_state,
+                        transition_id: Some(transition.id.clone()),
+                    },
+                    replacements,
                    context,
-                    error,
                )
-                .await);
+                .await
+                .map_err(|error| map_store_error(error, "plugin"))?;
+            Ok((current, prepared, result))
        }
-
-        let mut current = self
-            .store
-            .load_instances()
-            .await
-            .map_err(|error| map_store_error(error, "plugin"))?;
-        if current.config_revision != expected_revision {
-            return Err(self
-                .recover_failed_state_transition(
-                    Some(&transition.id),
-                    &previous,
-                    &previous_state,
-                    disabled_revision,
-                    context,
-                    AdminError::conflict("迁移期间插件配置已发生变化"),
-                )
-                .await);
-        }
-        let candidate_revision = next_revision(expected_revision)?;
-        target.revision = candidate_revision;
-        current.instances.retain(|item| item.id != target.id);
-        current.instances.push(target.clone());
-        current.config_revision = candidate_revision;
-        apply_replacements(&mut current, replacements);
-        let prepared = match self.preparation.prepare(current.clone()).await {
-            Ok(prepared) => prepared,
+        .await;
+        let (current, prepared, result) = match committed {
+            Ok(committed) => committed,
            Err(error) => {
                return Err(self
                    .recover_failed_state_transition(
@@ -518,53 +498,9 @@ impl PluginsService {
                    .await);
            }
        };
-        let result = match self
-            .store
-            .save_instance_replacing(
-                target,
-                expected_revision,
-                PluginStateCommit {
-                    configuration: target_state,
-                    transition_id: Some(transition.id.clone()),
-                },
-                replacements,
-                context,
-            )
-            .await
-        {
-            Ok(result) => result,
-            Err(error) => {
-                return Err(self
-                    .recover_failed_state_transition(
-                        Some(&transition.id),
-                        &previous,
-                        &previous_state,
-                        disabled_revision,
-                        context,
-                        map_store_error(error, "plugin"),
-                    )
-                    .await);
-            }
-        };
-        let prepared = if result.config_revision == candidate_revision
-            && result.instance.revision == candidate_revision
-        {
-            prepared
-        } else {
-            current.config_revision = result.config_revision;
-            current
-                .instances
-                .retain(|item| item.id != result.instance.id);
-            current.instances.push(result.instance.clone());
-            apply_replacements(&mut current, replacements);
-            self.preparation.prepare(current).await?
-        };
-        self.preparation
-            .activate_state(&prepared, &result.instance)
+        self.publish_instance(current, prepared, &result, replacements)
            .await?;
-        publish_committed(self.snapshots.as_ref(), result.config_revision).await?;
        drop(migration_prepared);
-        drop(prepared);
        Ok(result)
    }

@@ -615,22 +551,8 @@ impl PluginsService {
                )
                .await
                .map_err(|error| map_store_error(error, "plugin"))?;
-            let prepared = if mutation.config_revision == candidate_revision
-                && mutation.instance.revision == candidate_revision
-            {
-                prepared
-            } else {
-                snapshot.config_revision = mutation.config_revision;
-                snapshot
-                    .instances
-                    .retain(|item| item.id != mutation.instance.id);
-                snapshot.instances.push(mutation.instance.clone());
-                self.preparation.prepare(snapshot).await?
-            };
-            self.preparation
-                .activate_state(&prepared, &mutation.instance)
+            self.publish_instance(snapshot, prepared, &mutation, &[])
                .await?;
-            publish_committed(self.snapshots.as_ref(), mutation.config_revision).await?;
            Ok::<(), AdminError>(())
        }
        .await;
@@ -646,6 +568,35 @@ impl PluginsService {
        }
    }

+    /// 以事务返回的版本激活并发布，候选强引用必须覆盖整个提交后阶段
+    async fn publish_instance(
+        &self,
+        mut snapshot: PluginInstanceSnapshot,
+        prepared: ExtensionSetReference,
+        mutation: &PluginInstanceMutation,
+        replacements: &[PluginInstanceReplacement],
+    ) -> Result<(), AdminError> {
+        let prepared = if mutation.config_revision == snapshot.config_revision
+            && mutation.instance.revision == snapshot.config_revision
+        {
+            prepared
+        } else {
+            snapshot.config_revision = mutation.config_revision;
+            snapshot
+                .instances
+                .retain(|item| item.id != mutation.instance.id);
+            snapshot.instances.push(mutation.instance.clone());
+            apply_replacements(&mut snapshot, replacements);
+            self.preparation.prepare(snapshot).await?
+        };
+        self.preparation
+            .activate_state(&prepared, &mutation.instance)
+            .await?;
+        publish_committed(self.snapshots.as_ref(), mutation.config_revision).await?;
+        drop(prepared);
+        Ok(())
+    }
+
    pub async fn delete_instance(
        &self,
        id: &str,
@@ -2,7 +2,8 @@

 use std::sync::Arc;

-use gateway_core::runtime::{RuntimeSnapshotHandle, extensions::ExtensionSetReference};
+use gateway_core::routing::extensions::ExtensionSetReference;
+use gateway_core::runtime::RuntimeSnapshotHandle;

 use crate::{
    model::{
@@ -0,0 +1,14 @@
+//! 管理事务提交后的运行快照发布入口
+
+use crate::model::AdminError;
+use gateway_core::{routing::ConfigRevision, runtime::SnapshotControl};
+
+pub(super) async fn publish_committed(
+    snapshot: &dyn SnapshotControl,
+    revision: crate::model::Revision,
+) -> Result<(), AdminError> {
+    let revision = ConfigRevision::new(revision.get())
+        .map_err(|_| AdminError::internal("已提交的配置版本不合法"))?;
+    snapshot.publish_committed(revision).await;
+    Ok(())
+}
@@ -22,6 +22,13 @@ use super::{map_store_error, publish_committed};
 /// API 消费的 Runtime settings 管理服务
 #[async_trait]
 pub trait SettingsService: Send + Sync {
+    async fn preview_privacy_policy(
+        &self,
+        _request: gateway_core::settings::privacy::PrivacyPreviewRequest,
+    ) -> Result<gateway_core::settings::privacy::PrivacyPreviewResult, AdminError> {
+        Err(AdminError::invalid("隐私预览不可用"))
+    }
+
    async fn preview_pricing_sync(
        &self,
    ) -> Result<crate::model::pricing::PricingSyncPreview, AdminError>;
@@ -117,6 +124,21 @@ fn validate_settings(command: &ReplaceRuntimeSettings) -> Result<(), AdminError>

 #[async_trait]
 impl SettingsService for DefaultSettingsService {
+    async fn preview_privacy_policy(
+        &self,
+        request: gateway_core::settings::privacy::PrivacyPreviewRequest,
+    ) -> Result<gateway_core::settings::privacy::PrivacyPreviewResult, AdminError> {
+        self.profile_provider("openai")?
+            .preview_privacy_policy(request)
+            .map_err(|error| {
+                AdminError::invalid(format!(
+                    "第 {} 条规则：{}",
+                    error.rule_index + 1,
+                    error.reason
+                ))
+            })
+    }
+
    async fn preview_pricing_sync(
        &self,
    ) -> Result<crate::model::pricing::PricingSyncPreview, AdminError> {
@@ -238,10 +260,12 @@ impl SettingsService for DefaultSettingsService {
            PricingChange::Replace(pricing) => {
                pricing.validate().map_err(AdminError::invalid)?;
                if command.provider == "xai"
-                    && pricing
-                        .bands
-                        .keys()
-                        .any(|band| matches!(band.as_str(), "image" | "flex" | "long_flex"))
+                    && pricing.bands.keys().any(|band| {
+                        matches!(
+                            band.as_str(),
+                            "image" | "flex" | "long_flex" | "ultrafast" | "long_ultrafast"
+                        )
+                    })
                {
                    return Err(AdminError::invalid("xAI 不支持此价格档位"));
                }
@@ -342,6 +366,17 @@ impl SettingsService for DefaultSettingsService {
        mut command: ReplaceRuntimeSettings,
    ) -> Result<RuntimeSettings, AdminError> {
        validate_settings(&command)?;
+        if command.values.codex_privacy_policy != Default::default() {
+            self.profile_provider("openai")?
+                .compile_privacy_policy(&command.values.codex_privacy_policy)
+                .map_err(|error| {
+                    AdminError::invalid(format!(
+                        "第 {} 条规则：{}",
+                        error.rule_index + 1,
+                        error.reason
+                    ))
+                })?;
+        }
        if command
            .request_profile_updates
            .values()
@@ -519,9 +519,16 @@ impl DatabaseDumpPort for FakeDumpPort {

    async fn cleanup_staging(
        &self,
-        _backup_id: &str,
+        backup_id: &str,
    ) -> Result<(), gateway_admin::model::backup::BackupError> {
-        Ok(())
+        match std::fs::remove_file(self.dir.path().join(format!("{backup_id}.dump"))) {
+            Ok(()) => Ok(()),
+            Err(error) if error.kind() == std::io::ErrorKind::NotFound => Ok(()),
+            Err(_) => Err(gateway_admin::model::backup::BackupError::new(
+                gateway_admin::model::backup::code::PG_DUMP_FAILED,
+                "cleanup failed".to_owned(),
+            )),
+        }
    }
 }

@@ -529,6 +536,9 @@ impl DatabaseDumpPort for FakeDumpPort {
 pub(crate) struct FakeObjectStore {
    pub(crate) objects: Mutex<std::collections::HashMap<String, Vec<u8>>>,
    upload_error: Option<BackupError>,
+    head_error: Option<BackupError>,
+    delete_error: Option<BackupError>,
+    connection_error: Option<BackupError>,
 }

 impl FakeObjectStore {
@@ -536,6 +546,9 @@ impl FakeObjectStore {
        Self {
            objects: Mutex::new(std::collections::HashMap::new()),
            upload_error: None,
+            head_error: None,
+            delete_error: None,
+            connection_error: None,
        }
    }

@@ -545,6 +558,21 @@ impl FakeObjectStore {
        self
    }

+    pub(crate) fn fail_head(mut self, code: &'static str) -> Self {
+        self.head_error = Some(BackupError::new(code, "HEAD failed".into()));
+        self
+    }
+
+    pub(crate) fn fail_delete(mut self, code: &'static str) -> Self {
+        self.delete_error = Some(BackupError::new(code, "DELETE failed".into()));
+        self
+    }
+
+    pub(crate) fn fail_connection(mut self, code: &'static str) -> Self {
+        self.connection_error = Some(BackupError::new(code, "DELETE failed".into()));
+        self
+    }
+
    pub(crate) fn object(&self, key: &str) -> Option<Vec<u8>> {
        self.objects.lock().expect("objects").get(key).cloned()
    }
@@ -556,6 +584,14 @@ impl BackupObjectStorePort for FakeObjectStore {
        &self,
        _config: &BackupStorageConfig,
    ) -> Result<ConnectionTestResult, gateway_admin::model::backup::BackupError> {
+        if let Some(error) = &self.connection_error {
+            return Ok(ConnectionTestResult {
+                ok: false,
+                stage: "deleteObject",
+                code: Some(error.code()),
+                message: error.message().into(),
+            });
+        }
        Ok(ConnectionTestResult {
            ok: true,
            stage: "deleteObject",
@@ -590,6 +626,9 @@ impl BackupObjectStorePort for FakeObjectStore {
        _config: &BackupStorageConfig,
        object_key: &str,
    ) -> Result<Option<BackupObjectMetadata>, gateway_admin::model::backup::BackupError> {
+        if let Some(error) = &self.head_error {
+            return Err(error.clone());
+        }
        let Some(content) = self.object(object_key) else {
            return Ok(None);
        };
@@ -606,6 +645,9 @@ impl BackupObjectStorePort for FakeObjectStore {
        _config: &BackupStorageConfig,
        object_key: &str,
    ) -> Result<(), gateway_admin::model::backup::BackupError> {
+        if let Some(error) = &self.delete_error {
+            return Err(error.clone());
+        }
        self.objects.lock().expect("objects").remove(object_key);
        Ok(())
    }
@@ -683,11 +725,11 @@ impl AuthStore for FakeAuthStore {
    ) -> AdminStoreResult<()> {
        Ok(())
    }
-    async fn renew_session(
+    async fn compare_exchange_session(
        &self,
        _: &str,
        _: &gateway_admin::model::auth::AuthSession,
-        _: chrono::DateTime<chrono::Utc>,
+        _: Option<&gateway_admin::model::auth::AuthSession>,
    ) -> AdminStoreResult<Option<gateway_admin::model::auth::AuthSession>> {
        Ok(None)
    }
@@ -55,6 +55,7 @@ async fn backup_task_runs_full_dump_upload_verify_pipeline() {
        .object(&seed.object_key)
        .expect("uploaded object exists");
    assert_eq!(stored.as_slice(), DUMP_CONTENT);
+    assert!(dump.inspect_staging(&seed.id).await.unwrap().is_none());
 }

 #[tokio::test]
@@ -259,3 +260,122 @@ async fn timezone_change_rebases_future_cursor_without_running_old_due_backup()
    task.run_cycle(&CancellationToken::new()).await.unwrap();
    assert!(repository.all_records().is_empty());
 }
+
+#[tokio::test]
+async fn completed_recovery_removes_staging_for_dumping_and_uploading_tasks() {
+    for (status, remote_exists) in [
+        (BackupStatus::Dumping, false),
+        (BackupStatus::Uploading, false),
+        (BackupStatus::Uploading, true),
+    ] {
+        let repository = Arc::new(FakeBackupRepository::new(configured_settings()));
+        let dump = Arc::new(FakeDumpPort::new());
+        let object_store = Arc::new(FakeObjectStore::new());
+        let seed = BackupRecordSeed {
+            id: backup_id("recovery-cleanup"),
+            trigger_kind: BackupTriggerKind::Manual,
+            scheduled_at: None,
+            object_key: "recovery.dump".to_owned(),
+            expires_at: None,
+        };
+        repository.insert_backup_record(seed.clone()).await.unwrap();
+        let artifact = dump
+            .dump(DumpRequest {
+                backup_id: seed.id.clone(),
+                cancellation: CancellationToken::new(),
+            })
+            .await
+            .unwrap();
+        repository.force_status(&seed.id, BackupStatus::Dumping);
+        if status == BackupStatus::Uploading {
+            repository
+                .transition_status(
+                    &seed.id,
+                    gateway_admin::model::backup::BackupStatusTransition::try_new(
+                        BackupStatus::Dumping,
+                        status,
+                    )
+                    .unwrap(),
+                    gateway_admin::ports::backup::StatusTransitionUpdate {
+                        size_bytes: Some(artifact.size_bytes),
+                        sha256: Some(artifact.sha256),
+                        ..Default::default()
+                    },
+                    Utc::now(),
+                )
+                .await
+                .unwrap();
+        }
+        if remote_exists {
+            object_store
+                .objects
+                .lock()
+                .unwrap()
+                .insert(seed.object_key.clone(), DUMP_CONTENT.to_vec());
+        }
+        BackupTask::new(repository.clone(), dump.clone(), object_store)
+            .run_cycle(&CancellationToken::new())
+            .await
+            .unwrap();
+        assert_eq!(repository.all_records()[0].status, BackupStatus::Completed);
+        assert!(
+            dump.inspect_staging(&seed.id).await.unwrap().is_none(),
+            "completed recovery must remove staging: {status:?}"
+        );
+    }
+}
+
+#[tokio::test]
+async fn manual_backup_preserves_primary_and_final_delete_failures() {
+    for (upload_fails, expiring) in [(false, false), (true, false), (false, true)] {
+        let repository = Arc::new(FakeBackupRepository::new(configured_settings()));
+        let dump = Arc::new(FakeDumpPort::new());
+        let store = FakeObjectStore::new().fail_delete(code::S3_PERMISSION_DENIED);
+        let store = Arc::new(if upload_fails {
+            store.fail_upload(code::S3_UPLOAD_FAILED, "上传失败")
+        } else {
+            store.fail_head(code::REMOTE_VERIFICATION_FAILED)
+        });
+        let seed = BackupRecordSeed {
+            id: backup_id("cleanup-failure"),
+            trigger_kind: BackupTriggerKind::Manual,
+            scheduled_at: None,
+            object_key: "codex/cleanup-failure.dump".into(),
+            expires_at: expiring.then(|| Utc::now() + Duration::hours(1)),
+        };
+        repository.insert_backup_record(seed.clone()).await.unwrap();
+        let task = BackupTask::new(repository.clone(), dump.clone(), store.clone());
+        task.run_cycle(&CancellationToken::new()).await.unwrap();
+        let records = repository.all_records();
+        let record = &records[0];
+        assert_eq!(record.status, BackupStatus::Failed);
+        assert_eq!(
+            record.error_code.as_deref(),
+            Some(if upload_fails {
+                code::S3_UPLOAD_FAILED
+            } else {
+                code::REMOTE_VERIFICATION_FAILED
+            })
+        );
+        let message = record.error_message.as_deref().unwrap();
+        assert!(message.contains(if upload_fails {
+            "上传失败"
+        } else {
+            "HEAD failed"
+        }));
+        assert!(message.contains("DeleteObject"));
+        assert!(message.contains(code::S3_PERMISSION_DENIED));
+        assert!(message.contains(if expiring {
+            "等待备份到期清理"
+        } else {
+            "未安排自动重试"
+        }));
+        assert_eq!(store.object(&seed.object_key).is_some(), !upload_fails);
+        assert!(dump.inspect_staging(&seed.id).await.unwrap().is_none());
+        task.run_cycle(&CancellationToken::new()).await.unwrap();
+        assert_eq!(
+            repository.all_records()[0].error_message,
+            record.error_message
+        );
+    }
+}
@@ -70,12 +70,6 @@ fn request_outcome_filter_should_preserve_known_and_bounded_other_values() {
    assert!(RequestOutcome::new("future\nstate").is_err());
 }

-#[test]
-fn time_range_should_accept_exactly_366_days() {
-    let end = Utc::now();
-    assert!(TimeRange::new(end - TimeDelta::days(366), end).is_ok());
-}
-
 #[test]
 fn time_range_should_reject_more_than_366_days() {
    let end = Utc::now();
@@ -176,9 +170,9 @@ fn usage_window_should_not_use_daily_rolling_usage_for_weekly_statistics() {
        success_count: 5,
        input_tokens: Some(100),
        output_tokens: Some(20),
-        cached_tokens: Some(80),
-        cache_write_tokens: Some(0),
-        reasoning_tokens: Some(0),
+        cached_input_tokens: Some(80),
+        cache_write_input_tokens: Some(0),
+        reasoning_output_tokens: Some(0),
        image_input_tokens: Some(0),
        image_output_tokens: Some(0),
        image_request_count: 0,
@@ -115,9 +115,9 @@ fn usage_window(key: &str, group: &str, seconds: u64) -> ProviderQuotaWindow {
            success_count: 0,
            input_tokens: None,
            output_tokens: None,
-            cached_tokens: None,
-            cache_write_tokens: None,
-            reasoning_tokens: None,
+            cached_input_tokens: None,
+            cache_write_input_tokens: None,
+            reasoning_output_tokens: None,
            image_input_tokens: None,
            image_output_tokens: None,
            image_request_count: 0,
@@ -32,9 +32,9 @@ fn window(key: &str, days: u64) -> ProviderQuotaWindow {
            success_count: 10,
            input_tokens: Some(900),
            output_tokens: Some(100),
-            cached_tokens: Some(800),
-            cache_write_tokens: None,
-            reasoning_tokens: None,
+            cached_input_tokens: Some(800),
+            cache_write_input_tokens: None,
+            reasoning_output_tokens: None,
            image_input_tokens: None,
            image_output_tokens: None,
            image_request_count: 0,
@@ -84,7 +84,7 @@ fn samples(quota: &ProviderQuota) -> Vec<QuotaForecastSample> {
                tokens: usage.total_tokens.unwrap_or(0),
                input_tokens: usage.input_tokens.unwrap_or(0),
                output_tokens: usage.output_tokens.unwrap_or(0),
-                cached_tokens: usage.cached_tokens.unwrap_or(0),
+                cached_input_tokens: usage.cached_input_tokens.unwrap_or(0),
                missing_token_count: u64::from(usage.total_tokens.is_none()),
                known_cost_count: if usd.is_some() {
                    usage.cost_coverage.known_count()
@@ -73,14 +73,14 @@ fn snapshot_at_a_block_boundary_keeps_only_three_recent_blocks() {
 }

 #[test]
-fn large_percentage_reversal_restarts_sampling_without_crossing_old_consumption() {
+fn large_percentage_reversal_restarts_only_sampling_without_crossing_old_consumption() {
    let sample = select(
        vec![point(1, 40.0, 100), point(2, 50.0, 200), point(3, 1.0, 210)],
        point(4, 8.0, 280),
    );
    assert_eq!(sample.baseline_percent, 1.0);
    assert_eq!(sample.usage.tokens, 70);
-    assert_eq!(sample.cycle_usage.tokens, 70);
+    assert_eq!(sample.cycle_usage.tokens, 280);
    assert_eq!(sample.sampled_percent, 7.0);
    assert!(!sample.discontinuous);
    let waiting = select(
@@ -90,6 +90,30 @@ fn large_percentage_reversal_restarts_sampling_without_crossing_old_consumption(
    assert!(waiting.discontinuous);
 }

+#[test]
+fn same_window_reversal_preserves_all_recorded_cycle_usage() {
+    let current = point(3, 35.0, 140);
+    let recorded = current.usage.clone();
+    let sample = select(vec![point(1, 32.0, 100), point(2, 30.0, 120)], current);
+    assert_eq!(sample.cycle_usage, recorded);
+    assert_eq!(sample.usage.tokens, 20);
+    assert!((sample.usage.usd - 0.02).abs() < 1e-10);
+    assert!(!sample.discontinuous);
+}
+
+#[test]
+fn small_reversals_after_full_usage_preserve_cycle_totals_and_cumulative_forecasts() {
+    let current = point(3, 99.5, 10_020);
+    let recorded = current.usage.clone();
+    let sample = select(
+        vec![point(1, 100.0, 10_000), point(2, 99.0, 10_010)],
+        current,
+    );
+    assert_eq!(sample.cycle_usage, recorded);
+    assert_eq!(sample.method, QuotaForecastMethod::Cumulative);
+    assert!(!sample.discontinuous);
+}
+
 #[test]
 fn one_point_reversal_is_skipped_without_counting_an_extra_block() {
    let sample = select(
@@ -128,17 +152,41 @@ fn counter_regressions_fail_closed_and_future_points_are_not_used() {
 }

 #[test]
-fn exhausted_history_is_retained_to_detect_a_reset_with_an_unchanged_deadline() {
+fn same_window_recovery_restarts_sampling_but_preserves_recorded_cycle_usage() {
    let sample = select(
        vec![point(1, 100.0, 10_000), point(2, 0.0, 10_000)],
        point(3, 10.0, 10_100),
    );
-    assert_eq!(sample.cycle_usage.tokens, 100);
+    assert_eq!(sample.cycle_usage.tokens, 10_100);
+    assert!((sample.cycle_usage.usd - 10.1).abs() < 1e-10);
    assert_eq!(sample.usage.tokens, 100);
    assert_eq!(sample.sampled_percent, 10.0);
    assert!(!sample.discontinuous);
 }

+#[test]
+fn a_single_non_exhausted_observation_does_not_restart_cycle_usage() {
+    let sample = select(vec![point(1, 100.0, 10_000)], point(2, 0.0, 10_000));
+    assert_eq!(sample.cycle_usage.tokens, 10_000);
+    assert!(sample.discontinuous);
+}
+
+#[test]
+fn repeated_same_window_recoveries_preserve_recorded_cycle_usage() {
+    let sample = select(
+        vec![
+            point(1, 100.0, 10_000),
+            point(2, 0.0, 10_000),
+            point(3, 100.0, 10_100),
+            point(4, 0.0, 10_100),
+        ],
+        point(5, 10.0, 10_200),
+    );
+    assert_eq!(sample.cycle_usage.tokens, 10_200);
+    assert_eq!(sample.usage.tokens, 100);
+    assert!(!sample.discontinuous);
+}
+
 #[test]
 fn changed_window_restarts_cycle_totals_at_first_matching_observation() {
    let sample = select_forecast_sample(
@@ -10,12 +10,13 @@ use async_trait::async_trait;
 use chrono::{DateTime, Duration, Utc};
 use gateway_admin::{
    model::{
-        MutationContext, PageSize, Revision,
+        AdminErrorKind, MutationContext, PageSize, Revision,
        account_groups::{
            AccountGroupAccountSummary, AccountGroupCapacity, AccountGroupColor,
-            AccountGroupListQuery, AccountGroupMemberFact, AccountGroupMutation, AccountGroupPage,
-            AccountGroupRecord, AccountGroupUsage, DeleteAccountGroup, NewAccountGroup,
-            SetAccountGroupEnabled, UpdateAccountGroup,
+            AccountGroupListQuery, AccountGroupMemberFact, AccountGroupMutation,
+            AccountGroupOptionsPage, AccountGroupPage, AccountGroupRecord, AccountGroupRef,
+            AccountGroupUsage, DeleteAccountGroup, NewAccountGroup, SetAccountGroupEnabled,
+            UpdateAccountGroup,
        },
        accounts::AccountRuntimeSnapshot,
        observability::DecimalAmount,
@@ -90,6 +91,62 @@ async fn group_query_service_enriches_only_current_page_members_with_runtime_fac
    );
 }

+#[tokio::test]
+async fn group_options_query_should_skip_member_and_runtime_enrichment() {
+    let groups = Arc::new(FakeGroupStore::default());
+    let runtime = Arc::new(FakeRuntimeStore::default());
+    let service = AdminHarness::new()
+        .account_groups(groups.clone())
+        .account_runtime(runtime.clone())
+        .build()
+        .await;
+
+    let page = service
+        .account_groups()
+        .list_options(AccountGroupListQuery {
+            page: 1,
+            page_size: PageSize::new(20).expect("page size"),
+            search: None,
+            enabled: None,
+        })
+        .await
+        .expect("list account group options");
+
+    assert_eq!(page.items[0].id.as_str(), GROUP_ID);
+    assert!(
+        groups
+            .requested_groups
+            .lock()
+            .expect("requested groups")
+            .is_empty()
+    );
+    assert!(
+        runtime
+            .requested_accounts
+            .lock()
+            .expect("requested accounts")
+            .is_empty()
+    );
+}
+
+#[tokio::test]
+async fn group_options_query_should_preserve_store_failures() {
+    let service = AdminHarness::new().build().await;
+
+    let error = service
+        .account_groups()
+        .list_options(AccountGroupListQuery {
+            page: 1,
+            page_size: PageSize::new(20).expect("page size"),
+            search: None,
+            enabled: None,
+        })
+        .await
+        .expect_err("unavailable options store must fail");
+
+    assert_eq!(error.kind(), AdminErrorKind::Unavailable);
+}
+
 #[derive(Default)]
 struct FakeGroupStore {
    requested_groups: Mutex<Vec<String>>,
@@ -144,6 +201,24 @@ impl AccountGroupStore for FakeGroupStore {
        })
    }

+    async fn list_account_group_options(
+        &self,
+        query: AccountGroupListQuery,
+    ) -> AdminStoreResult<AccountGroupOptionsPage> {
+        Ok(AccountGroupOptionsPage {
+            config_revision: Revision::new(1).expect("revision"),
+            items: vec![AccountGroupRef {
+                id: group_id(),
+                name: "Primary".to_owned(),
+                color: AccountGroupColor::parse("#2563EBFF").expect("color"),
+                enabled: true,
+            }],
+            total: 1,
+            page: query.page,
+            page_size: query.page_size.get(),
+        })
+    }
+
    async fn load_account_group_members(
        &self,
        group_ids: &[AccountGroupId],
@@ -300,7 +375,7 @@ fn unused() -> AdminStoreError {

 #[tokio::test]
 async fn invalid_group_fields_are_rejected_before_store_mutations() {
-    use gateway_admin::model::{AdminErrorKind, MutationActor, account_groups::CreateAccountGroup};
+    use gateway_admin::model::{MutationActor, account_groups::CreateAccountGroup};
    let service = AdminHarness::new()
        .account_groups(Arc::new(FakeGroupStore::default()))
        .build()
@@ -1115,12 +1115,12 @@ impl SettingsStore for StaticSettingsStore {
            rotation_strategy: RotationStrategy::Smart,
            updated_at: Utc::now(),
            values: gateway_admin::model::settings::RuntimeSettingsValues {
+                codex_privacy_policy: Default::default(),
                request_location_enabled: false,
                request_location: Default::default(),
                refresh_margin_seconds: 300,
                refresh_concurrency: 2,
                max_concurrent_per_account: 1,
-                request_interval_ms: 0,
                max_waiting_per_key: 0,
                max_waiting_per_account: 0,
                concurrency_wait_timeout_seconds: 30,
@@ -1538,10 +1538,13 @@ async fn plugin_account_save_rejects_stale_authentication_kind_before_commit() {
    let events = events();
    let provider = FakeProviderAdmin::new("openai", events.clone());
    let store = FakeAccountStore::new("openai", events.clone());
-    let services = accounts_service(provider, store.clone()).await;
+    let access = gateway_admin::initialize_plugin_accounts(
+        ProviderAdminRegistry::new([provider as Arc<dyn ProviderAdmin>]).unwrap(),
+        store.clone(),
+        Arc::new(RecordingPluginAccountPublication(events.clone())),
+    );

-    let error = services
-        .plugin_accounts_handle()
+    let error = access
        .save(
            PreparedPluginAccountSave::Replace {
                facts: plugin_rotation_facts(&account_record("openai")),
@@ -2395,6 +2398,93 @@ async fn quota_forecast_only_queries_the_two_selected_source_windows() {
    );
 }

+#[tokio::test]
+async fn quota_forecast_same_window_reversal_keeps_recorded_usage_in_the_report() {
+    use gateway_admin::model::quota_forecast_sampling::QuotaForecastHistoryPoint;
+
+    for (percents, tokens, expected_tokens, expected_usd) in [
+        ([32.0, 30.0, 35.0], [100, 120, 140], 400, 0.4),
+        (
+            [100.0, 99.0, 99.5],
+            [10_000, 10_010, 10_020],
+            10_070,
+            10.02 / 0.995,
+        ),
+    ] {
+        let now = Utc::now();
+        let observed = now - TimeDelta::minutes(1);
+        let reset = now + TimeDelta::days(1);
+        let provider = FakeProviderAdmin::new("openai", events());
+        provider.set_quota(ProviderQuota {
+            plan_type: Some("pro".to_owned()),
+            observed_at: Some(observed),
+            windows: vec![ProviderQuotaWindow {
+                key: "week".to_owned(),
+                group: "shortTerm".to_owned(),
+                label: "周额度".to_owned(),
+                limit_id: None,
+                limit_name: None,
+                role: None,
+                local_usage_attribution: QuotaLocalUsageAttribution::AccountWide,
+                window_seconds: Some(604_800),
+                used_percent: Some(percents[2]),
+                reset_at: Some(reset),
+                limit_reached: false,
+                local_usage: None,
+                provider_data: None,
+            }],
+            ..empty_quota()
+        });
+        let mut account = account_record("openai");
+        account.created_at = now - TimeDelta::days(7);
+        let store = FakeAccountStore::with_account(account, events());
+        let usage = |requests, tokens| QuotaForecastUsage {
+            request_count: requests,
+            tokens,
+            input_tokens: tokens,
+            known_cost_count: requests,
+            usd: tokens as f64 / 1_000.0,
+            ..Default::default()
+        };
+        *store.quota_forecast_history.lock().unwrap() = QuotaForecastHistory {
+            points: [(3, percents[0], tokens[0]), (2, percents[1], tokens[1])]
+                .into_iter()
+                .enumerate()
+                .map(
+                    |(index, (minutes, percent, tokens))| QuotaForecastHistoryPoint {
+                        started_at: now - TimeDelta::minutes(5),
+                        completed_at: now - TimeDelta::minutes(minutes),
+                        usage: usage(index as u64 + 1, tokens),
+                        provider_observation: ProviderDocument::new(OpaqueProviderData::new(
+                            serde_json::json!({
+                                "percent": percent, "reset": reset.to_rfc3339(), "plan": "pro",
+                            })
+                            .as_object()
+                            .unwrap()
+                            .clone(),
+                        )),
+                    },
+                )
+                .collect(),
+            usage: usage(3, tokens[2]),
+            pending_request_count: 0,
+        };
+        let services = accounts_service(provider, store).await;
+        let result = services
+            .accounts()
+            .quota_forecast(&ProviderAccountId::new("acct_test").unwrap())
+            .await
+            .unwrap();
+        let forecast = &result.forecasts[0];
+        let source = forecast.source.as_ref().unwrap();
+        assert_eq!(source.tokens, Some(tokens[2]));
+        assert!((source.usd.unwrap() - tokens[2] as f64 / 1_000.0).abs() < 1e-10);
+        assert_eq!(forecast.estimated_tokens, Some(expected_tokens));
+        assert!((forecast.estimated_usd.unwrap() - expected_usd).abs() < 1e-10);
+        assert!(forecast.unavailable_reason.is_none());
+    }
+}
+
 #[tokio::test]
 async fn quota_forecast_mid_cycle_sampling_accepts_small_reset_jitter_but_not_a_changed_bucket() {
    use gateway_admin::model::quota_forecast_sampling::QuotaForecastHistoryPoint;
@@ -3028,9 +3118,9 @@ fn quota_local_usage(account_id: &str, total_tokens: u64) -> AccountUsage {
        success_count: 1,
        input_tokens: Some(total_tokens),
        output_tokens: Some(0),
-        cached_tokens: Some(0),
-        cache_write_tokens: Some(0),
-        reasoning_tokens: Some(0),
+        cached_input_tokens: Some(0),
+        cache_write_input_tokens: Some(0),
+        reasoning_output_tokens: Some(0),
        image_input_tokens: Some(0),
        image_output_tokens: Some(0),
        image_request_count: 0,
@@ -1,4 +1,4 @@
-//! 验证管理员认证、密码变更、会话绑定与限流行为
+//! 验证管理员认证、密码变更与限流，提供会话轮换的内存存储辅助

 use std::{collections::BTreeMap, sync::Mutex};

@@ -69,6 +69,7 @@ async fn password_change_obeys_rate_limit_and_rejects_unbound_legacy_sessions()
                admin_user_id: "admin".into(),
                credential_fingerprint: String::new(),
            },
+            renewal: None,
            absolute_expires_at: None,
            expires_at: Utc::now() + TimeDelta::hours(1),
        },
@@ -138,19 +139,24 @@ impl AuthStore for MemoryAuthStore {
        Ok(())
    }

-    async fn renew_session(
+    async fn compare_exchange_session(
        &self,
        session_id: &str,
        expected: &AuthSession,
-        expires_at: chrono::DateTime<chrono::Utc>,
+        replacement: Option<&AuthSession>,
    ) -> AdminStoreResult<Option<AuthSession>> {
        let mut sessions = self.sessions.lock().unwrap();
        if let Some(session) = sessions.get_mut(session_id) {
-            if session.expires_at <= chrono::Utc::now() {
+            if session.retained_until() <= chrono::Utc::now() {
                return Ok(None);
            }
            if session == expected {
-                session.expires_at = expires_at;
+                if let Some(replacement) = replacement {
+                    *session = replacement.clone();
+                } else {
+                    sessions.remove(session_id);
+                    return Ok(None);
+                }
            }
            return Ok(Some(session.clone()));
        }
@@ -190,8 +196,13 @@ impl AuthStore for MemoryAuthStore {
 #[tokio::test]
 async fn successful_login_should_create_expiring_session_and_audit() {
    let store = std::sync::Arc::new(MemoryAuthStore::default());
-    let services = super::AdminHarness::new().auth(store.clone()).build().await;
+    let services = super::AdminHarness::new()
+        .session_ttl_minutes(7 * 24 * 60)
+        .auth(store.clone())
+        .build()
+        .await;

+    let before = Utc::now();
    let result = services
        .auth()
        .login(
@@ -205,6 +216,17 @@ async fn successful_login_should_create_expiring_session_and_audit() {
        .await
        .expect("login");

+    let after = Utc::now();
+    for (expiry, ttl) in [
+        (result.session.expires_at, TimeDelta::hours(24)),
+        (result.session.retained_until(), TimeDelta::days(7)),
+        (
+            result.session.absolute_expires_at.unwrap(),
+            TimeDelta::days(30),
+        ),
+    ] {
+        assert!((before + ttl..=after + ttl).contains(&expiry));
+    }
    assert!(
        services
            .auth()
@@ -293,6 +315,7 @@ async fn expired_sessions_are_rejected_and_store_outages_are_not_treated_as_logo
                credential_fingerprint: String::new(),
                admin_user_id: "admin".to_owned(),
            },
+            renewal: None,
            absolute_expires_at: None,
            expires_at: Utc::now() - TimeDelta::seconds(1),
        },
@@ -362,7 +385,7 @@ async fn failed_rotation_discards_the_new_session_and_leaves_the_old_session_ret
        .await
        .unwrap();
    assert!(!format!("{original:?}").contains(&original.session_id));
-    *store.reject_delete.lock().unwrap() = Some(original.session_id.clone());
+    *store.reject_delete.lock().unwrap() = Some(stored_id(&original.session_id).to_owned());
    assert_eq!(
        services
            .auth()
@@ -391,109 +414,23 @@ async fn failed_rotation_discards_the_new_session_and_leaves_the_old_session_ret
    assert!(store.sessions.lock().unwrap().is_empty());
 }

-#[tokio::test]
-async fn renewal_is_throttled_and_capped_by_the_original_absolute_expiry() {
-    let store = std::sync::Arc::new(MemoryAuthStore::default());
-    let services = super::AdminHarness::new()
-        .auth(store.clone())
-        .session_ttl_minutes(60)
-        .build()
-        .await;
-    let auth = services.auth();
-    let login = auth
-        .login(
-            LoginCommand::Admin {
-                username: None,
-                password: "strong-test-password".into(),
-            },
-            std::net::Ipv4Addr::LOCALHOST.into(),
-            None,
-        )
-        .await
-        .unwrap();
-    assert_eq!(
-        auth.renew_session(Some(&login.session_id)).await.unwrap(),
-        Some(login.session.clone())
-    );
-    let limit = Utc::now() + TimeDelta::minutes(30);
-    {
-        let mut sessions = store.sessions.lock().unwrap();
-        let session = sessions.get_mut(&login.session_id).unwrap();
-        session.expires_at = Utc::now() + TimeDelta::minutes(1);
-        session.absolute_expires_at = Some(limit);
-    }
-    let renewed = auth
-        .renew_session(Some(&login.session_id))
-        .await
-        .unwrap()
-        .unwrap();
-    assert_eq!(renewed.expires_at, limit);
-    assert_eq!(renewed.absolute_expires_at, Some(limit));
-    assert_eq!(
-        auth.renew_session(Some(&login.session_id)).await.unwrap(),
-        Some(renewed)
-    );
+fn stored_id(token: &str) -> &str {
+    token.split('.').nth(1).unwrap_or(token)
 }

-#[tokio::test]
-async fn renewal_never_revives_expired_revoked_or_legacy_sessions() {
-    let store = std::sync::Arc::new(MemoryAuthStore::default());
-    let services = super::AdminHarness::new().auth(store.clone()).build().await;
-    let auth = services.auth();
-    let login = auth
-        .login(
-            LoginCommand::Admin {
-                username: None,
-                password: "strong-test-password".into(),
-            },
-            std::net::Ipv4Addr::LOCALHOST.into(),
-            None,
-        )
-        .await
-        .unwrap();
-    let mut session = login.session.clone();
-    session.absolute_expires_at = None;
-    session.expires_at = Utc::now() + TimeDelta::seconds(30);
-    store
-        .sessions
-        .lock()
-        .unwrap()
-        .insert(login.session_id.clone(), session.clone());
-    assert_eq!(
-        auth.renew_session(Some(&login.session_id)).await.unwrap(),
-        Some(session.clone())
-    );
-    session.expires_at = Utc::now() - TimeDelta::seconds(1);
-    store
-        .sessions
-        .lock()
-        .unwrap()
-        .insert(login.session_id.clone(), session);
-    assert!(
-        auth.renew_session(Some(&login.session_id))
-            .await
-            .unwrap()
-            .is_none()
-    );
-    let mut session = login.session;
-    session.absolute_expires_at = Some(Utc::now() - TimeDelta::seconds(1));
-    store
-        .sessions
-        .lock()
-        .unwrap()
-        .insert(login.session_id.clone(), session);
-    assert!(
-        auth.renew_session(Some(&login.session_id))
-            .await
-            .unwrap()
-            .is_none()
-    );
-    auth.logout(&login.session_id).await.unwrap();
-    assert!(
-        auth.renew_session(Some(&login.session_id))
-            .await
-            .unwrap()
-            .is_none()
-    );
-    assert!(store.sessions.lock().unwrap().is_empty());
+async fn admin_login(
+    auth: &dyn gateway_admin::AuthService,
+) -> gateway_admin::model::auth::SessionGrant {
+    auth.login(
+        LoginCommand::Admin {
+            username: None,
+            password: "strong-test-password".into(),
+        },
+        std::net::Ipv4Addr::LOCALHOST.into(),
+        None,
+    )
+    .await
+    .unwrap()
 }
+
+mod session;
@@ -0,0 +1,268 @@
+//! 验证双凭据续期、响应重试、并发撤销与固定期限边界
+
+use super::super::AdminHarness;
+use super::{MemoryAuthStore, admin_login, stored_id};
+use chrono::{TimeDelta, Utc};
+use gateway_admin::model::auth::AuthSession;
+
+#[tokio::test]
+async fn expired_access_is_restored_by_refresh_and_duplicate_refresh_replays_the_same_grant() {
+    let store = std::sync::Arc::new(MemoryAuthStore::default());
+    let services = AdminHarness::new().auth(store.clone()).build().await;
+    let auth = services.auth();
+    let login = admin_login(auth).await;
+    let refresh = login.refresh_token.as_deref().unwrap();
+    assert!(auth.session(Some(refresh)).await.unwrap().is_none());
+    assert!(
+        auth.renew_session(Some(&login.session_id), None)
+            .await
+            .unwrap()
+            .is_none()
+    );
+    assert!(
+        auth.renew_session(None, Some(&login.session_id))
+            .await
+            .unwrap()
+            .is_none()
+    );
+    assert_eq!(
+        auth.renew_session(Some(refresh), None).await.unwrap(),
+        Some(login.clone())
+    );
+    store
+        .sessions
+        .lock()
+        .unwrap()
+        .get_mut(stored_id(&login.session_id))
+        .unwrap()
+        .expires_at = Utc::now() - TimeDelta::seconds(1);
+    assert!(
+        auth.session(Some(&login.session_id))
+            .await
+            .unwrap()
+            .is_none()
+    );
+    let (first, concurrent) = tokio::join!(
+        auth.renew_session(Some(refresh), None),
+        auth.renew_session(Some(refresh), None)
+    );
+    let first = first.unwrap().unwrap();
+    assert_eq!(concurrent.unwrap().as_ref(), Some(&first));
+    assert_ne!(first.session_id, login.session_id);
+    assert_ne!(first.refresh_token, login.refresh_token);
+    assert_eq!(
+        first.session.absolute_expires_at,
+        login.session.absolute_expires_at
+    );
+    assert!(
+        auth.session(Some(&first.session_id))
+            .await
+            .unwrap()
+            .is_some()
+    );
+    assert_eq!(
+        auth.renew_session(first.refresh_token.as_deref(), None)
+            .await
+            .unwrap(),
+        Some(first.clone())
+    );
+    assert_eq!(
+        auth.renew_session(Some(refresh), None).await.unwrap(),
+        Some(first.clone())
+    );
+    let persisted = format!("{:?}", store.sessions.lock().unwrap());
+    for token in [
+        &first.session_id,
+        first.refresh_token.as_ref().unwrap(),
+        &login.session_id,
+        login.refresh_token.as_ref().unwrap(),
+    ] {
+        assert!(!persisted.contains(token));
+        assert!(!persisted.contains(token.rsplit('.').next().unwrap()));
+    }
+}
+
+#[tokio::test]
+async fn late_refresh_reuse_revokes_the_family_but_unknown_secrets_do_not() {
+    let store = std::sync::Arc::new(MemoryAuthStore::default());
+    let services = AdminHarness::new().auth(store.clone()).build().await;
+    let auth = services.auth();
+    let login = admin_login(auth).await;
+    store
+        .sessions
+        .lock()
+        .unwrap()
+        .get_mut(stored_id(&login.session_id))
+        .unwrap()
+        .expires_at = Utc::now() - TimeDelta::seconds(1);
+    let next = auth
+        .renew_session(login.refresh_token.as_deref(), None)
+        .await
+        .unwrap()
+        .unwrap();
+    let unknown = format!("r2.{}.{}", stored_id(&login.session_id), "A".repeat(43));
+    assert!(
+        auth.renew_session(Some(&unknown), None)
+            .await
+            .unwrap()
+            .is_none()
+    );
+    auth.logout(&unknown).await.unwrap();
+    auth.logout(stored_id(&login.session_id)).await.unwrap();
+    assert!(
+        auth.session(Some(&next.session_id))
+            .await
+            .unwrap()
+            .is_some()
+    );
+    store
+        .sessions
+        .lock()
+        .unwrap()
+        .get_mut(stored_id(&login.session_id))
+        .unwrap()
+        .renewal
+        .as_mut()
+        .unwrap()
+        .previous
+        .as_mut()
+        .unwrap()
+        .expires_at = Utc::now() - TimeDelta::seconds(1);
+    assert!(
+        auth.renew_session(login.refresh_token.as_deref(), None)
+            .await
+            .unwrap()
+            .is_none()
+    );
+    assert!(
+        auth.session(Some(&next.session_id))
+            .await
+            .unwrap()
+            .is_none()
+    );
+    assert!(
+        auth.renew_session(next.refresh_token.as_deref(), None)
+            .await
+            .unwrap()
+            .is_none()
+    );
+}
+
+#[tokio::test]
+async fn refresh_respects_idle_and_absolute_expiry_and_logout_after_access_expiry() {
+    let store = std::sync::Arc::new(MemoryAuthStore::default());
+    let services = AdminHarness::new().auth(store.clone()).build().await;
+    let auth = services.auth();
+    for absolute in [false, true] {
+        let login = admin_login(auth).await;
+        {
+            let mut sessions = store.sessions.lock().unwrap();
+            let session = sessions.get_mut(stored_id(&login.session_id)).unwrap();
+            if absolute {
+                session.absolute_expires_at = Some(Utc::now() - TimeDelta::seconds(1));
+            } else {
+                session.renewal.as_mut().unwrap().expires_at = Utc::now() - TimeDelta::seconds(1);
+            }
+        }
+        assert!(
+            auth.renew_session(login.refresh_token.as_deref(), None)
+                .await
+                .unwrap()
+                .is_none()
+        );
+        assert!(
+            auth.session(Some(&login.session_id))
+                .await
+                .unwrap()
+                .is_none()
+        );
+    }
+    let login = admin_login(auth).await;
+    store
+        .sessions
+        .lock()
+        .unwrap()
+        .get_mut(stored_id(&login.session_id))
+        .unwrap()
+        .expires_at = Utc::now() - TimeDelta::seconds(1);
+    auth.logout(login.refresh_token.as_deref().unwrap())
+        .await
+        .unwrap();
+    assert!(
+        auth.renew_session(login.refresh_token.as_deref(), None)
+            .await
+            .unwrap()
+            .is_none()
+    );
+}
+
+#[tokio::test]
+async fn refreshed_expiry_is_capped_and_store_outages_preserve_the_session() {
+    let store = std::sync::Arc::new(MemoryAuthStore::default());
+    let services = AdminHarness::new().auth(store.clone()).build().await;
+    let auth = services.auth();
+    let login = admin_login(auth).await;
+    let limit = Utc::now() + TimeDelta::minutes(1);
+    {
+        let mut sessions = store.sessions.lock().unwrap();
+        let session = sessions.get_mut(stored_id(&login.session_id)).unwrap();
+        session.absolute_expires_at = Some(limit);
+        session.expires_at = Utc::now() - TimeDelta::seconds(1);
+    }
+    store
+        .unavailable
+        .store(true, std::sync::atomic::Ordering::SeqCst);
+    assert!(
+        auth.renew_session(login.refresh_token.as_deref(), None)
+            .await
+            .is_err()
+    );
+    store
+        .unavailable
+        .store(false, std::sync::atomic::Ordering::SeqCst);
+    let refreshed = auth
+        .renew_session(login.refresh_token.as_deref(), None)
+        .await
+        .unwrap()
+        .unwrap();
+    assert_eq!(refreshed.session.expires_at, limit);
+    assert_eq!(refreshed.session.retained_until(), limit);
+    assert_eq!(refreshed.session.absolute_expires_at, Some(limit));
+}
+
+#[tokio::test]
+async fn fixed_sessions_cannot_acquire_refresh_credentials() {
+    let store = std::sync::Arc::new(MemoryAuthStore::default());
+    let services = AdminHarness::new().auth(store.clone()).build().await;
+    let auth = services.auth();
+    let login = admin_login(auth).await;
+    let fixed = AuthSession {
+        renewal: None,
+        ..login.session
+    };
+    store
+        .sessions
+        .lock()
+        .unwrap()
+        .insert("fixed".into(), fixed.clone());
+    let grant = auth
+        .renew_session(None, Some("fixed"))
+        .await
+        .unwrap()
+        .unwrap();
+    assert_eq!(grant.session, fixed);
+    assert!(grant.refresh_token.is_none());
+    store
+        .sessions
+        .lock()
+        .unwrap()
+        .get_mut("fixed")
+        .unwrap()
+        .expires_at = Utc::now() - TimeDelta::seconds(1);
+    assert!(
+        auth.renew_session(None, Some("fixed"))
+            .await
+            .unwrap()
+            .is_none()
+    );
+}
@@ -285,19 +285,24 @@ impl AuthStore for MemoryKeyAuthStore {
        Ok(())
    }

-    async fn renew_session(
+    async fn compare_exchange_session(
        &self,
        session_id: &str,
        expected: &AuthSession,
-        expires_at: chrono::DateTime<chrono::Utc>,
+        replacement: Option<&AuthSession>,
    ) -> AdminStoreResult<Option<AuthSession>> {
        let mut sessions = self.sessions.lock().unwrap();
        if let Some(session) = sessions.get_mut(session_id) {
-            if session.expires_at <= chrono::Utc::now() {
+            if session.retained_until() <= chrono::Utc::now() {
                return Ok(None);
            }
            if session == expected {
-                session.expires_at = expires_at;
+                if let Some(replacement) = replacement {
+                    *session = replacement.clone();
+                } else {
+                    sessions.remove(session_id);
+                    return Ok(None);
+                }
            }
            return Ok(Some(session.clone()));
        }
@@ -102,3 +102,51 @@ async fn backup_service_rejects_download_of_non_completed_record() {
        .expect_err("non-completed record must be rejected");
    assert_eq!(error.kind(), gateway_admin::model::AdminErrorKind::Conflict);
 }
+
+#[tokio::test]
+async fn failed_delete_probe_does_not_refresh_verification() {
+    use gateway_admin::{model::backup::code, ports::backup::BackupRepository as _};
+    for succeeds in [false, true] {
+        let mut settings = configured_settings();
+        settings.last_verified_at = None;
+        let repository = Arc::new(FakeBackupRepository::new(settings));
+        let auth = Arc::new(FakeAuthStore::new());
+        let store = FakeObjectStore::new();
+        let store = if succeeds {
+            store
+        } else {
+            store.fail_connection(code::S3_PERMISSION_DENIED)
+        };
+        let services = AdminHarness::new()
+            .auth(auth.clone())
+            .backup(BackupStorePorts::new(
+                repository.clone(),
+                Arc::new(FakeDumpPort::new()),
+                Arc::new(store),
+            ))
+            .build()
+            .await;
+        let result = services
+            .backups()
+            .test_connection(&system_context())
+            .await
+            .unwrap();
+        assert_eq!(result.ok, succeeds);
+        assert_eq!(
+            repository
+                .load_settings()
+                .await
+                .unwrap()
+                .last_verified_at
+                .is_some(),
+            succeeds
+        );
+        assert_eq!(
+            auth.audit_actions()
+                .iter()
+                .filter(|action| action.as_str() == "backup.s3_connection_tested")
+                .count(),
+            1
+        );
+    }
+}
@@ -5,7 +5,6 @@ use std::sync::{Arc, Mutex};

 use async_trait::async_trait;
 use chrono::{DateTime, Duration as TimeDelta, Utc};
-use gateway_admin::freeze_recovery::{FreezeRecoveryDeps, FreezeRecoveryTask};
 use gateway_admin::model::MutationContext;
 use gateway_admin::model::accounts::{AccountFreeze, AccountRuntimeSnapshot};
 use gateway_admin::model::settings::{
@@ -18,7 +17,9 @@ use gateway_core::engine::probe::{
    AccountProbe, AccountProbeError, AccountProbeRequest, AccountProbeResult,
 };
 use gateway_core::lifecycle::CancellationToken;
-use gateway_core::task::{ScheduledTask as _, WorkerCycleContext, WorkerId, WorkerKind};
+use gateway_core::task::{
+    ScheduledTask, WorkerContribution, WorkerCycleContext, WorkerId, WorkerKind, WorkerRunnable,
+};

 use super::AdminHarness;
 use super::accounts::{FakeAccountStore, FakeProviderAdmin, account_record, events, revision};
@@ -31,12 +32,12 @@ fn runtime_settings(enabled: bool, probe_enabled: bool, adaptive: bool) -> Runti
        rotation_strategy: gateway_admin::model::settings::RotationStrategy::Smart,
        updated_at: Utc::now(),
        values: gateway_admin::model::settings::RuntimeSettingsValues {
+            codex_privacy_policy: Default::default(),
            request_location_enabled: false,
            request_location: Default::default(),
            refresh_margin_seconds: 300,
            refresh_concurrency: 2,
            max_concurrent_per_account: 5,
-            request_interval_ms: 0,
            max_waiting_per_key: 0,
            max_waiting_per_account: 0,
            concurrency_wait_timeout_seconds: 30,
@@ -246,7 +247,7 @@ async fn recovery_task(
    settings: RuntimeSettings,
    runtime: Arc<FreezeRuntimeStore>,
    probe: Arc<dyn AccountProbe>,
-) -> (FreezeRecoveryTask, Arc<FakeAccountStore>) {
+) -> (Box<dyn ScheduledTask>, Arc<FakeAccountStore>) {
    recovery_task_with_store(settings, runtime, probe).await
 }

@@ -254,9 +255,9 @@ async fn recovery_task_with_store(
    settings: RuntimeSettings,
    runtime: Arc<FreezeRuntimeStore>,
    probe: Arc<dyn AccountProbe>,
-) -> (FreezeRecoveryTask, Arc<FakeAccountStore>) {
+) -> (Box<dyn ScheduledTask>, Arc<FakeAccountStore>) {
    let store = FakeAccountStore::new("openai", events());
-    let services = AdminHarness::new()
+    let bundle = AdminHarness::new()
        .accounts(Arc::clone(&store) as Arc<dyn AccountStore>)
        .account_runtime(Arc::clone(&runtime) as Arc<dyn AccountRuntimeStore>)
        .settings(Arc::new(FreezeSettingsStore {
@@ -264,20 +265,32 @@ async fn recovery_task_with_store(
        }))
        .provider(FakeProviderAdmin::new("openai", events()))
        .probe(probe)
-        .build()
+        .build_bundle()
        .await;
-    let task = FreezeRecoveryTask::new(FreezeRecoveryDeps {
-        accounts: services.accounts_handle(),
-        store: store.clone(),
-        runtime,
-        settings: Arc::new(FreezeSettingsStore {
-            settings: settings.clone(),
-        }),
-    });
+    let task = freeze_worker(bundle);
    (task, store)
 }

-async fn run_cycle(task: &FreezeRecoveryTask) {
+fn freeze_worker(mut bundle: gateway_admin::AdminBundle) -> Box<dyn ScheduledTask> {
+    bundle
+        .take_worker_contributions()
+        .into_iter()
+        .find_map(|contribution| {
+            let WorkerContribution::Registration(registration) = contribution else {
+                return None;
+            };
+            if registration.id.kind() != WorkerKind::AccountFreezeRecovery {
+                return None;
+            }
+            match registration.runnable {
+                WorkerRunnable::Scheduled { task, .. } => Some(task),
+                WorkerRunnable::Daemon { .. } => None,
+            }
+        })
+        .expect("registered freeze recovery worker")
+}
+
+async fn run_cycle(task: &dyn ScheduledTask) {
    let worker = WorkerId::try_new(WorkerKind::AccountFreezeRecovery, "test").expect("worker id");
    let context = WorkerCycleContext::new(worker, None, CancellationToken::new());
    task.run_cycle(context)
@@ -311,7 +324,7 @@ async fn probe_success_clears_freeze() {
    )
    .await;

-    run_cycle(&task).await;
+    run_cycle(task.as_ref()).await;

    assert_eq!(runtime.cleared(), vec!["acct_test".to_owned()]);
    assert!(runtime.extended().is_empty());
@@ -327,7 +340,7 @@ async fn probe_failure_postpones_freeze() {
    )
    .await;

-    run_cycle(&task).await;
+    run_cycle(task.as_ref()).await;

    assert!(runtime.cleared().is_empty());
    let extended = runtime.extended();
@@ -351,7 +364,7 @@ async fn disabled_policy_releases_due_freeze_without_probing() {
    )
    .await;

-    run_cycle(&task).await;
+    run_cycle(task.as_ref()).await;

    assert_eq!(runtime.cleared(), vec!["acct_test".to_owned()]);
    assert!(runtime.extended().is_empty());
@@ -370,7 +383,7 @@ async fn adaptive_concurrency_lowers_limit_to_observed_peak() {
    )
    .await;

-    run_cycle(&task).await;
+    run_cycle(task.as_ref()).await;

    // 峰值 4 × 0.8 = 3（不低于下限 2），低于全局默认 5，应下调到 3
    assert_eq!(
@@ -395,7 +408,7 @@ async fn adaptive_concurrency_never_raises_limit() {
    )
    .await;

-    run_cycle(&task).await;
+    run_cycle(task.as_ref()).await;

    // 峰值 40 的目标 32 高于全局默认 5；只降不升，不下发任何更新
    assert!(store.update_commands().is_empty());
@@ -415,7 +428,7 @@ async fn probe_skips_freezes_far_from_expiry() {
    )
    .await;

-    run_cycle(&task).await;
+    run_cycle(task.as_ref()).await;

    assert!(runtime.cleared().is_empty());
    assert!(runtime.extended().is_empty());
@@ -431,7 +444,7 @@ async fn disabled_accounts_are_skipped() {
    let mut record = account_record("openai");
    record.enabled = false;
    let store = FakeAccountStore::with_account(record, events());
-    let services = AdminHarness::new()
+    let bundle = AdminHarness::new()
        .accounts(Arc::clone(&store) as Arc<dyn AccountStore>)
        .account_runtime(Arc::clone(&runtime) as Arc<dyn AccountRuntimeStore>)
        .settings(Arc::new(FreezeSettingsStore {
@@ -439,18 +452,11 @@ async fn disabled_accounts_are_skipped() {
        }))
        .provider(FakeProviderAdmin::new("openai", events()))
        .probe(Arc::new(SuccessfulProbe))
-        .build()
+        .build_bundle()
        .await;
-    let task = FreezeRecoveryTask::new(FreezeRecoveryDeps {
-        accounts: services.accounts_handle(),
-        store: store.clone(),
-        runtime: Arc::clone(&runtime) as Arc<dyn AccountRuntimeStore>,
-        settings: Arc::new(FreezeSettingsStore {
-            settings: runtime_settings(true, true, true),
-        }),
-    });
+    let task = freeze_worker(bundle);

-    run_cycle(&task).await;
+    run_cycle(task.as_ref()).await;

    assert!(runtime.cleared().is_empty());
    assert!(runtime.extended().is_empty());
@@ -29,8 +29,9 @@ use gateway_admin::{
    model::{
        MutationContext, Revision,
        account_groups::{
-            AccountGroupListQuery, AccountGroupMemberFact, AccountGroupMutation, AccountGroupPage,
-            DeleteAccountGroup, NewAccountGroup, SetAccountGroupEnabled, UpdateAccountGroup,
+            AccountGroupListQuery, AccountGroupMemberFact, AccountGroupMutation,
+            AccountGroupOptionsPage, AccountGroupPage, DeleteAccountGroup, NewAccountGroup,
+            SetAccountGroupEnabled, UpdateAccountGroup,
        },
        accounts::{
            AccountListQuery, AccountPage, AccountRuntimeSnapshot, AccountUpdateResult,
@@ -44,10 +45,10 @@ use gateway_admin::{
            NewClientKey, SetClientKeyEnabled, UpdateClientKey,
        },
        observability::{
-            DashboardDesktopRelease, DashboardObservation, DashboardWireAttribute,
+            DashboardDesktopRelease, DashboardObservation, DashboardQuery, DashboardWireAttribute,
            DashboardWireProfile, DashboardWireTarget, DesktopReleaseStatus, DiagnosticDimension,
-            DiagnosticsObservation, OpsErrorPage, OpsErrorQuery, RequestMetricPoint, TimeRange,
-            UsageDetail, UsageFilter, UsageOverview, UsagePage, UsageQuery,
+            DiagnosticsObservation, Granularity, OpsErrorPage, OpsErrorQuery, RequestMetricPoint,
+            TimeRange, UsageDetail, UsageFilter, UsageOverview, UsagePage, UsageQuery,
        },
        provider_credentials::{
            AuthorizationCommit, AuthorizationStarted, CompleteAuthorization, CredentialDetails,
@@ -107,7 +108,7 @@ pub(super) struct AdminHarness {
    plugin_store: Arc<dyn gateway_admin::ports::plugins::PluginStore>,
    plugin_inspector: Arc<dyn gateway_admin::ports::plugins::PluginPackageInspector>,
    client_key_verifier: Arc<dyn ClientKeyVerifier>,
-    service_middleware: gateway_admin::service::PlanSource,
+    service_middleware: gateway_admin::public_service::PlanSource,
 }

 impl AdminHarness {
@@ -194,7 +195,10 @@ impl AdminHarness {
        self
    }

-    pub(super) fn service_middleware(mut self, source: gateway_admin::service::PlanSource) -> Self {
+    pub(super) fn service_middleware(
+        mut self,
+        source: gateway_admin::public_service::PlanSource,
+    ) -> Self {
        self.service_middleware = source;
        self
    }
@@ -365,11 +369,11 @@ impl AuthStore for BootstrapAuthStore {
        Err(unavailable("admin session"))
    }

-    async fn renew_session(
+    async fn compare_exchange_session(
        &self,
        _: &str,
        _: &gateway_admin::model::auth::AuthSession,
-        _: chrono::DateTime<chrono::Utc>,
+        _: Option<&gateway_admin::model::auth::AuthSession>,
    ) -> AdminStoreResult<Option<gateway_admin::model::auth::AuthSession>> {
        Ok(None)
    }
@@ -421,6 +425,13 @@ impl AccountGroupStore for UnavailableAccountGroupStore {
        Err(unavailable("account groups"))
    }

+    async fn list_account_group_options(
+        &self,
+        _: AccountGroupListQuery,
+    ) -> AdminStoreResult<AccountGroupOptionsPage> {
+        Err(unavailable("account group options"))
+    }
+
    async fn load_account_group_members(
        &self,
        _: &[gateway_core::routing::AccountGroupId],
@@ -736,15 +747,23 @@ impl ClientKeyStore for UnavailableStore {

 #[async_trait]
 impl ObservabilityStore for UnavailableStore {
+    fn query_timeout(&self) -> std::time::Duration {
+        std::time::Duration::from_secs(10)
+    }
+
    async fn dashboard_summary(
        &self,
-        _: TimeRange,
+        _: DashboardQuery,
        _: DateTime<Utc>,
    ) -> AdminStoreResult<DashboardObservation> {
        Err(unavailable("dashboard"))
    }

-    async fn dashboard_trend(&self, _: TimeRange) -> AdminStoreResult<Vec<RequestMetricPoint>> {
+    async fn dashboard_trend(
+        &self,
+        _: TimeRange,
+        _: Granularity,
+    ) -> AdminStoreResult<Vec<RequestMetricPoint>> {
        Err(unavailable("dashboard trend"))
    }

@@ -752,18 +771,22 @@ impl ObservabilityStore for UnavailableStore {
        &self,
        _: TimeRange,
        _: UsageFilter,
+        _: Granularity,
    ) -> AdminStoreResult<Vec<RequestMetricPoint>> {
        Err(unavailable("usage trend"))
    }

-    fn usage_calculated_billing_facts(
+    async fn analytics_cache_generation(&self) -> AdminStoreResult<u64> {
+        Err(unavailable("analytics generation"))
+    }
+
+    async fn usage_insights_observation(
        &self,
        _: TimeRange,
        _: UsageFilter,
-    ) -> gateway_admin::ports::store::UsageCalculatedBillingStream<'_> {
-        Box::pin(futures::stream::once(async {
-            Err(unavailable("usage billing facts"))
-        }))
+        _: Granularity,
+    ) -> AdminStoreResult<gateway_admin::model::observability::UsageInsightsObservation> {
+        Err(unavailable("usage insights"))
    }

    async fn list_usage_records(&self, _: UsageQuery) -> AdminStoreResult<UsagePage> {
@@ -783,6 +806,7 @@ impl ObservabilityStore for UnavailableStore {
        _: TimeRange,
        _: UsageFilter,
        _: DiagnosticDimension,
+        _: u16,
    ) -> AdminStoreResult<DiagnosticsObservation> {
        Err(unavailable("usage diagnostics"))
    }
@@ -17,13 +17,13 @@ use gateway_admin::{
    model::{
        MutationContext, Revision,
        observability::{
-            AccountPoolMetrics, AttemptMetrics, CostCoverage, CurrencyCost, DashboardAccountUsage,
-            DashboardObservation, DashboardRuntimeSlots, DiagnosticDimension,
-            DiagnosticObservation, DiagnosticsObservation, Granularity, HealthStatus,
-            LatencyPercentiles, ObservabilityPageSize, OpsErrorPage, OpsErrorQuery,
+            AccountPoolMetrics, AnalyticsState, AttemptMetrics, CostCoverage, CurrencyCost,
+            DashboardAccountUsage, DashboardObservation, DashboardQuery, DashboardRuntimeSlots,
+            DiagnosticDimension, DiagnosticObservation, DiagnosticsObservation, Granularity,
+            HealthStatus, LatencyPercentiles, ObservabilityPageSize, OpsErrorPage, OpsErrorQuery,
            PercentileMilliseconds, RequestMetricPoint, RequestMetrics, TimeRange, TrendKind,
-            UsageBilling, UsageCalculatedBillingFact, UsageDetail, UsageFilter, UsageListRecord,
-            UsageOverview, UsagePage, UsageQuery,
+            UsageBilling, UsageDetail, UsageFilter, UsageInsightsObservation, UsageListRecord,
+            UsageOverview, UsagePage, UsageProjectedCostPoint, UsageQuery,
        },
        settings::{
            AdminApiKey, AdminApiKeyMutation, ReplaceRuntimeSettings, RotationStrategy,
@@ -148,7 +148,7 @@ async fn dashboard_summary_should_derive_first_token_average_from_trend() {
 }

 #[tokio::test]
-async fn health_timeline_should_match_legacy_status_precedence_and_thresholds() {
+async fn health_timeline_should_apply_status_precedence_and_thresholds() {
    let now = Utc::now();
    let current_slot = quarter_hour_start(now);
    let store = Arc::new(FixtureObservabilityStore::new(observation_range(now)));
@@ -158,13 +158,28 @@ async fn health_timeline_should_match_legacy_status_precedence_and_thresholds()
            RequestMetrics {
                failure_count: 1,
                cancelled_count: 1,
-                incomplete_count: 1,
                caller_error_count: 1,
                ..RequestMetrics::default()
            },
            HealthStatus::NoData,
            None,
        ),
+        (
+            RequestMetrics {
+                incomplete_count: 1,
+                ..RequestMetrics::default()
+            },
+            HealthStatus::LowSample,
+            Some(0.0),
+        ),
+        (
+            RequestMetrics {
+                incomplete_count: 3,
+                ..RequestMetrics::default()
+            },
+            HealthStatus::Unavailable,
+            Some(0.0),
+        ),
        (
            RequestMetrics {
                failure_count: 3,
@@ -184,21 +199,21 @@ async fn health_timeline_should_match_legacy_status_precedence_and_thresholds()
        ),
        (
            RequestMetrics {
-                success_count: 98,
-                failure_count: 2,
+                success_count: 94,
+                failure_count: 6,
                ..RequestMetrics::default()
            },
            HealthStatus::Unstable,
-            Some(98.0),
+            Some(94.0),
        ),
        (
            RequestMetrics {
-                success_count: 99,
-                failure_count: 1,
+                success_count: 95,
+                incomplete_count: 5,
                ..RequestMetrics::default()
            },
            HealthStatus::Stable,
-            Some(99.0),
+            Some(95.0),
        ),
    ];

@@ -224,6 +239,92 @@ async fn health_timeline_should_match_legacy_status_precedence_and_thresholds()
    }
 }

+#[tokio::test]
+async fn health_views_should_include_incomplete_and_keep_final_outcomes_separate() {
+    let now = Utc::now();
+    let current_slot = quarter_hour_start(now);
+    let store = Arc::new(FixtureObservabilityStore::new(observation_range(now)));
+    let services = observability_services(store.clone()).await;
+    let fixtures = [
+        (162, 0, 2, 0, 0, 98.780_487_804_878_05),
+        (297, 0, 2, 5, 0, 99.331_103_678_929_76),
+        (467, 1, 5, 0, 0, 98.731_501_057_082_45),
+        (95, 2, 3, 4, 1, 95.0),
+        (100, 0, 0, 0, 0, 100.0),
+    ];
+
+    for (index, (success, failed, incomplete, cancelled, caller_error, expected_percent)) in
+        fixtures.into_iter().enumerate()
+    {
+        let range = observation_range(
+            now + Duration::seconds(i64::try_from(index).expect("fixture index fits i64") * 2),
+        );
+        let metrics = RequestMetrics {
+            request_count: success + failed + incomplete + cancelled + caller_error,
+            success_count: success,
+            failure_count: failed + caller_error,
+            incomplete_count: incomplete,
+            cancelled_count: cancelled,
+            caller_error_count: caller_error,
+            ..RequestMetrics::default()
+        };
+        store.replace_trend(vec![health_metric_point(current_slot, metrics.clone())]);
+        store.replace_overview(UsageOverview {
+            analytics: Default::default(),
+            range,
+            requests: metrics,
+            // 中间尝试失败不会增加最终失败请求数
+            attempts: AttemptMetrics {
+                failure_count: 2,
+                ..AttemptMetrics::default()
+            },
+            providers: Vec::new(),
+        });
+
+        let dashboard = services
+            .observability()
+            .dashboard_summary(range, TrendKind::Usage)
+            .await
+            .expect("dashboard summary");
+        let timeline = dashboard.health_timeline;
+        let point = timeline
+            .points
+            .iter()
+            .find(|point| point.bucket_start == current_slot)
+            .expect("current health slot");
+        assert_eq!(point.status, HealthStatus::Stable);
+        assert_eq!(point.failed_requests, failed);
+        assert_eq!(point.incomplete_requests, incomplete);
+        assert_eq!(point.cancelled_requests, cancelled);
+        assert_eq!(point.caller_error_requests, caller_error);
+        for reliability in [timeline.reliability_percent, point.reliability_percent] {
+            assert!((reliability.expect("health reliability") - expected_percent).abs() < 1e-10);
+        }
+        for success_rate in [
+            dashboard.trend.summary.success_rate,
+            dashboard.trend.points[0].success_rate,
+        ] {
+            assert!(
+                (success_rate.expect("trend success rate") * 100.0 - expected_percent).abs()
+                    < 1e-10
+            );
+        }
+
+        let insights = services
+            .observability()
+            .usage_insights(range, UsageFilter::default())
+            .await
+            .expect("usage insights");
+        assert_eq!(insights.health.failed_requests, failed);
+        assert_eq!(insights.health.incomplete_requests, incomplete);
+        assert!((insights.health.success_rate * 100.0 - expected_percent).abs() < 1e-10);
+        assert!(
+            (insights.health.points[0].error_rate * 100.0 - (100.0 - expected_percent)).abs()
+                < 1e-10
+        );
+    }
+}
+
 #[tokio::test]
 async fn dashboard_summary_should_project_rebuildable_runtime_slots() {
    let now = Utc::now();
@@ -282,7 +383,7 @@ async fn dashboard_capacity_distinguishes_unlimited_inheritance_finite_overrides
 }

 #[tokio::test]
-async fn dashboard_summary_should_share_one_current_observation_time_across_runtime_facts() {
+async fn dashboard_summary_should_observe_current_accounts_for_a_historical_range() {
    let historical_end = Utc::now() - Duration::hours(1);
    let store = Arc::new(FixtureObservabilityStore::new(observation_range(
        historical_end,
@@ -295,13 +396,12 @@ async fn dashboard_summary_should_share_one_current_observation_time_across_runt
        .await
        .expect("dashboard summary");

-    let (summary_observed_at, slots_observed_at) = store.observed_times();
-    assert_eq!(summary_observed_at, slots_observed_at);
+    let summary_observed_at = *store.summary_observed_at.lock().unwrap();
    assert!(summary_observed_at.is_some_and(|value| value > historical_end));
 }

 #[tokio::test]
-async fn dashboard_summary_should_coalesce_concurrent_requests_in_one_short_window() {
+async fn dashboard_summary_should_keep_distinct_exact_ranges_in_one_short_window() {
    let end_bucket = Utc::now().timestamp().div_euclid(2) * 2;
    let first_end = DateTime::from_timestamp(end_bucket, 100_000_000).expect("first end");
    let second_end = DateTime::from_timestamp(end_bucket, 900_000_000).expect("second end");
@@ -331,7 +431,7 @@ async fn dashboard_summary_should_coalesce_concurrent_requests_in_one_short_wind

    first.expect("first dashboard summary");
    second.expect("second dashboard summary");
-    assert_eq!(store.dashboard_summary_calls(), 1);
+    assert_eq!(store.dashboard_summary_calls(), 2);
 }

 #[tokio::test]
@@ -404,6 +504,7 @@ async fn observability_services_should_calculate_usage_insights_and_diagnostic_s
        ..RequestMetrics::default()
    };
    store.replace_overview(UsageOverview {
+        analytics: Default::default(),
        range,
        requests: metrics.clone(),
        attempts: AttemptMetrics {
@@ -432,23 +533,13 @@ async fn observability_services_should_calculate_usage_insights_and_diagnostic_s
                .expect("bucket USD cost"),
        }],
    }]);
-    store.replace_calculated_billing_facts(vec![UsageCalculatedBillingFact {
-        breakdown: None,
+    store.replace_projected_costs(vec![UsageProjectedCostPoint {
        bucket_start: quarter_hour_start(now),
-        provider_kind: "openai".to_owned(),
-        upstream_model_id: "gpt-5.5".to_owned(),
-        service_tier: None,
-        input_tokens: Some(800),
-        output_tokens: Some(200),
-        cached_tokens: Some(0),
-        cache_write_tokens: Some(0),
-        total: CurrencyCost {
-            currency: "USD".to_owned(),
-            amount: gateway_admin::model::observability::DecimalAmount::from_str("1.25")
-                .expect("calculated total"),
-        },
+        standard_amount: Some("1".parse().expect("standard cost")),
+        no_cache_amount: Some("1.25".parse().expect("no-cache cost")),
    }]);
    store.replace_diagnostics(DiagnosticsObservation {
+        analytics: Default::default(),
        total_request_count: 4,
        items: vec![diagnostic("openai", 3), diagnostic("xai", 1)],
    });
@@ -544,6 +635,7 @@ async fn diagnostics_should_preserve_request_order_when_a_small_sample_fails() {
    failure.success_count = 0;
    failure.failure_count = 1;
    store.replace_diagnostics(DiagnosticsObservation {
+        analytics: Default::default(),
        total_request_count: 101,
        items: vec![success, failure],
    });
@@ -567,6 +659,7 @@ async fn diagnostics_should_use_the_total_before_truncating_groups() {
    let range = observation_range(Utc::now());
    let store = Arc::new(FixtureObservabilityStore::new(range));
    store.replace_diagnostics(DiagnosticsObservation {
+        analytics: Default::default(),
        total_request_count: 200,
        items: (0..100)
            .map(|index| diagnostic(&format!("model-{index}"), 1))
@@ -592,6 +685,7 @@ async fn diagnostics_should_count_each_retried_request_once() {
    item.retry_count = 6;
    item.retried_request_count = 2;
    store.replace_diagnostics(DiagnosticsObservation {
+        analytics: Default::default(),
        total_request_count: 8,
        items: vec![item],
    });
@@ -692,26 +786,16 @@ async fn usage_records_should_enrich_provider_reported_totals_when_pricing_match
 }

 #[tokio::test]
-async fn usage_insights_should_reject_partial_costs_when_billing_stream_fails() {
+async fn usage_insights_should_reject_partial_costs_when_insights_fail() {
    let now = Utc::now();
    let range = observation_range(now);
    let store = Arc::new(FixtureObservabilityStore::new(range));
-    store.replace_calculated_billing_facts(vec![UsageCalculatedBillingFact {
-        breakdown: None,
+    store.replace_projected_costs(vec![UsageProjectedCostPoint {
        bucket_start: quarter_hour_start(now),
-        provider_kind: "openai".to_owned(),
-        upstream_model_id: "gpt-5.5".to_owned(),
-        service_tier: None,
-        input_tokens: Some(800),
-        output_tokens: Some(200),
-        cached_tokens: Some(0),
-        cache_write_tokens: Some(0),
-        total: CurrencyCost {
-            currency: "USD".to_owned(),
-            amount: "1.25".parse().expect("cost"),
-        },
+        standard_amount: Some("1".parse().expect("standard cost")),
+        no_cache_amount: Some("1.25".parse().expect("no-cache cost")),
    }]);
-    store.billing_stream_fails.store(true, Ordering::SeqCst);
+    store.insights_fail.store(true, Ordering::SeqCst);
    let services = observability_services_with_calculated_billing(store).await;
    assert!(
        services
@@ -742,9 +826,9 @@ async fn dashboard_should_preserve_provider_plan_names() {
            success_count: 0,
            input_tokens: None,
            output_tokens: None,
-            cached_tokens: None,
-            cache_write_tokens: None,
-            reasoning_tokens: None,
+            cached_input_tokens: None,
+            cache_write_input_tokens: None,
+            reasoning_output_tokens: None,
            image_input_tokens: None,
            image_output_tokens: None,
            image_request_count: 0,
@@ -784,16 +868,19 @@ async fn dashboard_should_preserve_provider_plan_names() {
 struct FixtureObservabilityStore {
    trend: Mutex<Vec<RequestMetricPoint>>,
    overview: Mutex<UsageOverview>,
-    calculated_billing_facts: Mutex<Vec<UsageCalculatedBillingFact>>,
-    billing_stream_fails: AtomicBool,
+    projected_costs: Mutex<Vec<UsageProjectedCostPoint>>,
+    insights_fail: AtomicBool,
+    summary_fail: AtomicBool,
    diagnostics: Mutex<DiagnosticsObservation>,
    runtime_slots: Mutex<Option<DashboardRuntimeSlots>>,
    summary_observed_at: Mutex<Option<DateTime<Utc>>>,
-    slots_observed_at: Mutex<Option<DateTime<Utc>>>,
+    summary_query: Mutex<Option<DashboardQuery>>,
+    usage_granularities: Mutex<Vec<Granularity>>,
    usage_records: Mutex<Vec<UsageListRecord>>,
    account_usage: Mutex<Vec<DashboardAccountUsage>>,
    dashboard_delay: Mutex<StdDuration>,
    dashboard_summary_calls: AtomicUsize,
+    usage_summary_filters: Mutex<Vec<UsageFilter>>,
 }

 impl FixtureObservabilityStore {
@@ -801,21 +888,25 @@ impl FixtureObservabilityStore {
        Self {
            trend: Mutex::new(Vec::new()),
            overview: Mutex::new(UsageOverview {
+                analytics: Default::default(),
                range,
                requests: RequestMetrics::default(),
                attempts: AttemptMetrics::default(),
                providers: Vec::new(),
            }),
-            calculated_billing_facts: Mutex::new(Vec::new()),
-            billing_stream_fails: AtomicBool::new(false),
+            projected_costs: Mutex::new(Vec::new()),
+            insights_fail: AtomicBool::new(false),
+            summary_fail: AtomicBool::new(false),
            diagnostics: Mutex::new(DiagnosticsObservation::default()),
            runtime_slots: Mutex::new(None),
            summary_observed_at: Mutex::new(None),
-            slots_observed_at: Mutex::new(None),
+            summary_query: Mutex::new(None),
+            usage_granularities: Mutex::new(Vec::new()),
            usage_records: Mutex::new(Vec::new()),
            account_usage: Mutex::new(Vec::new()),
            dashboard_delay: Mutex::new(StdDuration::ZERO),
            dashboard_summary_calls: AtomicUsize::new(0),
+            usage_summary_filters: Mutex::new(Vec::new()),
        }
    }

@@ -835,11 +926,8 @@ impl FixtureObservabilityStore {
        *self.overview.lock().expect("overview") = overview;
    }

-    fn replace_calculated_billing_facts(&self, facts: Vec<UsageCalculatedBillingFact>) {
-        *self
-            .calculated_billing_facts
-            .lock()
-            .expect("calculated billing facts") = facts;
+    fn replace_projected_costs(&self, facts: Vec<UsageProjectedCostPoint>) {
+        *self.projected_costs.lock().expect("projected costs") = facts;
    }

    fn replace_diagnostics(&self, diagnostics: DiagnosticsObservation) {
@@ -850,16 +938,6 @@ impl FixtureObservabilityStore {
        *self.runtime_slots.lock().expect("runtime slots") = runtime_slots;
    }

-    fn observed_times(&self) -> (Option<DateTime<Utc>>, Option<DateTime<Utc>>) {
-        (
-            *self
-                .summary_observed_at
-                .lock()
-                .expect("summary observed at"),
-            *self.slots_observed_at.lock().expect("slots observed at"),
-        )
-    }
-
    fn replace_usage_records(&self, records: Vec<UsageListRecord>) {
        *self.usage_records.lock().expect("usage records") = records;
    }
@@ -867,12 +945,17 @@ impl FixtureObservabilityStore {

 #[async_trait]
 impl ObservabilityStore for FixtureObservabilityStore {
+    fn query_timeout(&self) -> std::time::Duration {
+        std::time::Duration::from_secs(10)
+    }
+
    async fn dashboard_summary(
        &self,
-        range: TimeRange,
+        query: DashboardQuery,
        observed_at: DateTime<Utc>,
    ) -> AdminStoreResult<DashboardObservation> {
        self.dashboard_summary_calls.fetch_add(1, Ordering::Relaxed);
+        *self.summary_query.lock().unwrap() = Some(query.clone());
        *self
            .summary_observed_at
            .lock()
@@ -882,24 +965,22 @@ impl ObservabilityStore for FixtureObservabilityStore {
            tokio::time::sleep(dashboard_delay).await;
        }
        Ok(DashboardObservation {
-            range,
+            analytics: self.overview.lock().expect("overview").analytics.clone(),
+            range: query.range,
            totals: Default::default(),
            provider_accounts: AccountPoolMetrics::default(),
+            runtime_slots: *self.runtime_slots.lock().expect("runtime slots"),
            trend: self.trend.lock().expect("trend").clone(),
            account_usage: self.account_usage.lock().expect("account usage").clone(),
            recent_requests: Vec::new(),
        })
    }

-    async fn dashboard_runtime_slots(
+    async fn dashboard_trend(
        &self,
-        observed_at: DateTime<Utc>,
-    ) -> AdminStoreResult<Option<DashboardRuntimeSlots>> {
-        *self.slots_observed_at.lock().expect("slots observed at") = Some(observed_at);
-        Ok(*self.runtime_slots.lock().expect("runtime slots"))
-    }
-
-    async fn dashboard_trend(&self, _: TimeRange) -> AdminStoreResult<Vec<RequestMetricPoint>> {
+        _: TimeRange,
+        _: Granularity,
+    ) -> AdminStoreResult<Vec<RequestMetricPoint>> {
        Ok(self.trend.lock().expect("trend").clone())
    }

@@ -907,27 +988,35 @@ impl ObservabilityStore for FixtureObservabilityStore {
        &self,
        _: TimeRange,
        _: UsageFilter,
+        granularity: Granularity,
    ) -> AdminStoreResult<Vec<RequestMetricPoint>> {
+        self.usage_granularities.lock().unwrap().push(granularity);
        Ok(self.trend.lock().expect("trend").clone())
    }

-    fn usage_calculated_billing_facts(
+    async fn analytics_cache_generation(&self) -> AdminStoreResult<u64> {
+        Ok(self.overview.lock().expect("overview").analytics.generation)
+    }
+
+    async fn usage_insights_observation(
        &self,
        _: TimeRange,
        _: UsageFilter,
-    ) -> gateway_admin::ports::store::UsageCalculatedBillingStream<'_> {
-        let facts = self
-            .calculated_billing_facts
-            .lock()
-            .expect("calculated billing facts")
-            .clone();
-        let error = self
-            .billing_stream_fails
-            .load(Ordering::SeqCst)
-            .then(|| Err(super::unavailable("billing stream failed")));
-        Box::pin(futures::stream::iter(
-            facts.into_iter().map(Ok).chain(error),
-        ))
+        granularity: Granularity,
+    ) -> AdminStoreResult<UsageInsightsObservation> {
+        self.usage_granularities.lock().unwrap().push(granularity);
+        if self.insights_fail.load(Ordering::SeqCst) {
+            return Err(super::unavailable("projection read failed"));
+        }
+        Ok(UsageInsightsObservation {
+            overview: self.overview.lock().expect("overview").clone(),
+            trend: self.trend.lock().expect("trend").clone(),
+            costs: self
+                .projected_costs
+                .lock()
+                .expect("projected costs")
+                .clone(),
+        })
    }

    async fn list_usage_records(&self, query: UsageQuery) -> AdminStoreResult<UsagePage> {
@@ -945,8 +1034,26 @@ impl ObservabilityStore for FixtureObservabilityStore {
        Err(super::unavailable("usage detail"))
    }

-    async fn usage_summary(&self, _: TimeRange, _: UsageFilter) -> AdminStoreResult<UsageOverview> {
-        Ok(self.overview.lock().expect("overview").clone())
+    async fn usage_summary(
+        &self,
+        range: TimeRange,
+        filter: UsageFilter,
+    ) -> AdminStoreResult<UsageOverview> {
+        self.usage_summary_filters
+            .lock()
+            .expect("summary filters")
+            .push(filter);
+        let delay = *self.dashboard_delay.lock().expect("query delay");
+        if !delay.is_zero() {
+            tokio::time::sleep(delay).await;
+        }
+        if self.summary_fail.load(Ordering::SeqCst) {
+            return Err(super::unavailable("projection summary failed"));
+        }
+        Ok(UsageOverview {
+            range,
+            ..self.overview.lock().expect("overview").clone()
+        })
    }

    async fn usage_diagnostics(
@@ -954,6 +1061,7 @@ impl ObservabilityStore for FixtureObservabilityStore {
        _: TimeRange,
        _: UsageFilter,
        _: DiagnosticDimension,
+        _: u16,
    ) -> AdminStoreResult<DiagnosticsObservation> {
        Ok(self.diagnostics.lock().expect("diagnostics").clone())
    }
@@ -994,12 +1102,12 @@ impl SettingsStore for FixtureSettingsStore {
            rotation_strategy: RotationStrategy::Smart,
            updated_at: Utc::now(),
            values: gateway_admin::model::settings::RuntimeSettingsValues {
+                codex_privacy_policy: Default::default(),
                request_location_enabled: false,
                request_location: Default::default(),
                refresh_margin_seconds: 300,
                refresh_concurrency: 2,
                max_concurrent_per_account: self.max_concurrent_per_account,
-                request_interval_ms: 0,
                max_waiting_per_key: 0,
                max_waiting_per_account: 0,
                concurrency_wait_timeout_seconds: 30,
@@ -1119,9 +1227,9 @@ fn total_record(
        service_tier: None,
        input_tokens: Some(800),
        output_tokens: Some(200),
-        cached_tokens: Some(0),
-        cache_write_tokens: Some(0),
-        reasoning_tokens: Some(0),
+        cached_input_tokens: Some(0),
+        cache_write_input_tokens: Some(0),
+        reasoning_output_tokens: Some(0),
        image_input_tokens: None,
        image_output_tokens: None,
        total_tokens: Some(1_000),
@@ -1144,6 +1252,13 @@ fn total_record(
        first_text_ms: None,
        first_token_ms: None,
        provider_processing_ms: None,
+        upstream_response_ms: None,
+        upstream_api_overhead_ms: None,
+        upstream_engine_ms: None,
+        upstream_engine_iapi_ttft_ms: None,
+        upstream_engine_service_ttft_ms: None,
+        upstream_engine_iapi_tbt_ms: None,
+        upstream_engine_service_tbt_ms: None,
        latency_ms: Some(100),
        admission_decision_ms: None,
        account_selection_wait_ms: None,
@@ -1195,3 +1310,236 @@ fn quarter_hour_start(value: DateTime<Utc>) -> DateTime<Utc> {
    let elapsed = value.timestamp().rem_euclid(15 * 60);
    value - Duration::seconds(elapsed) - Duration::nanoseconds(i64::from(value.nanosecond()))
 }
+
+#[tokio::test]
+async fn admin_selects_dashboard_defaults_and_matching_usage_buckets_at_range_boundaries() {
+    let now = Utc::now();
+    for (duration, expected) in [
+        (Duration::days(2), Granularity::FifteenMinutes),
+        (Duration::days(2) + Duration::seconds(1), Granularity::Hour),
+        (Duration::days(31), Granularity::Hour),
+        (Duration::days(31) + Duration::seconds(1), Granularity::Day),
+    ] {
+        let range = TimeRange::new(now - duration, now).unwrap();
+        let store = Arc::new(FixtureObservabilityStore::new(range));
+        let services = observability_services(store.clone()).await;
+        services
+            .observability()
+            .dashboard_summary(range, TrendKind::Usage)
+            .await
+            .unwrap();
+        let query = store.summary_query.lock().unwrap().clone().unwrap();
+        assert_eq!(query.range, range);
+        assert_eq!(query.granularity, expected);
+        assert_eq!(query.account_limit, 4);
+        assert_eq!(query.recent_request_limit, 10);
+        assert_eq!(
+            query.recent_request_filter.outcome,
+            Some(gateway_admin::model::observability::RequestOutcome::Succeeded)
+        );
+        services
+            .observability()
+            .usage_insights(range, UsageFilter::default())
+            .await
+            .unwrap();
+        assert_eq!(*store.usage_granularities.lock().unwrap(), vec![expected]);
+    }
+}
+
+#[tokio::test]
+async fn usage_summary_cache_should_coalesce_identical_queries_and_invalidate_deleted_generation() {
+    let range = observation_range(Utc::now());
+    let store = Arc::new(FixtureObservabilityStore::new(range));
+    store.set_dashboard_delay(StdDuration::from_millis(20));
+    let services = observability_services(store.clone()).await;
+    let service = services.observability();
+    let filter = UsageFilter {
+        client_api_key_ref: Some("deleted-key".to_owned()),
+        ..Default::default()
+    };
+    let (first, second) = tokio::join!(
+        service.usage_summary(range, filter.clone()),
+        service.usage_summary(range, filter.clone()),
+    );
+    first.expect("first summary");
+    second.expect("coalesced summary");
+    assert_eq!(store.usage_summary_filters.lock().unwrap().len(), 1);
+    {
+        let mut overview = store.overview.lock().unwrap();
+        overview.analytics.generation = 1;
+        overview.requests.request_count = 7;
+    }
+    let refreshed = service
+        .usage_summary(range, filter)
+        .await
+        .expect("generation refresh");
+    assert_eq!(refreshed.overview.analytics.generation, 1);
+    assert_eq!(refreshed.overview.requests.request_count, 7);
+    assert_eq!(store.usage_summary_filters.lock().unwrap().len(), 2);
+}
+
+#[tokio::test(start_paused = true)]
+async fn usage_summary_cache_should_coalesce_when_generation_advances_during_the_first_load() {
+    let range = observation_range(Utc::now());
+    let store = Arc::new(FixtureObservabilityStore::new(range));
+    store.set_dashboard_delay(StdDuration::from_millis(20));
+    let services = observability_services(store.clone()).await;
+    let service = services.observability();
+    let (first, second, ()) = tokio::join!(
+        service.usage_summary(range, UsageFilter::default()),
+        service.usage_summary(range, UsageFilter::default()),
+        async {
+            tokio::time::sleep(StdDuration::from_millis(5)).await;
+            store.overview.lock().unwrap().analytics.generation = 1;
+        },
+    );
+    assert_eq!(
+        first.expect("first summary").overview.analytics.generation,
+        1
+    );
+    assert_eq!(
+        second
+            .expect("coalesced summary")
+            .overview
+            .analytics
+            .generation,
+        1
+    );
+    assert_eq!(store.usage_summary_filters.lock().unwrap().len(), 1);
+}
+
+#[tokio::test]
+async fn usage_summary_cache_should_isolate_key_identity_and_filters() {
+    let range = observation_range(Utc::now());
+    let store = Arc::new(FixtureObservabilityStore::new(range));
+    let services = observability_services(store.clone()).await;
+    let service = services.observability();
+    for (key, model) in [
+        ("key-a", None),
+        ("key-a", None),
+        ("key-b", None),
+        ("key-a", Some("model-a")),
+    ] {
+        service
+            .usage_summary(
+                range,
+                UsageFilter {
+                    client_api_key_ref: Some(key.to_owned()),
+                    model: model.map(str::to_owned),
+                    ..Default::default()
+                },
+            )
+            .await
+            .expect("isolated summary");
+    }
+    let calls = store.usage_summary_filters.lock().unwrap();
+    assert_eq!(calls.len(), 3);
+    assert_eq!(calls[0].client_api_key_ref.as_deref(), Some("key-a"));
+    assert_eq!(calls[1].client_api_key_ref.as_deref(), Some("key-b"));
+    assert_eq!(calls[2].model.as_deref(), Some("model-a"));
+}
+
+#[tokio::test(start_paused = true)]
+async fn usage_summary_cache_should_bound_waiting_after_failed_refresh_and_allow_recovery() {
+    let range = observation_range(Utc::now());
+    let store = Arc::new(FixtureObservabilityStore::new(range));
+    store.set_dashboard_delay(store.query_timeout().mul_f64(0.7));
+    store.summary_fail.store(true, Ordering::SeqCst);
+    let services = observability_services(store.clone()).await;
+    let service = services.observability();
+    let started = tokio::time::Instant::now();
+    let (first, second, third, fourth) = tokio::join!(
+        service.usage_summary(range, UsageFilter::default()),
+        service.usage_summary(range, UsageFilter::default()),
+        service.usage_summary(range, UsageFilter::default()),
+        service.usage_summary(range, UsageFilter::default()),
+    );
+    assert!(first.is_err() && second.is_err() && third.is_err() && fourth.is_err());
+    assert!(
+        started.elapsed() <= store.query_timeout(),
+        "同键失败不能使后续请求逐个等待完整数据库超时: {:?}",
+        started.elapsed()
+    );
+
+    store.summary_fail.store(false, Ordering::SeqCst);
+    store.set_dashboard_delay(StdDuration::ZERO);
+    service
+        .usage_summary(range, UsageFilter::default())
+        .await
+        .expect("cancelled cache refresh releases its slot for recovery");
+}
+
+#[tokio::test(start_paused = true)]
+async fn insights_cache_should_bound_stale_lifetime_without_renewing_failed_refreshes() {
+    let range = observation_range(Utc::now());
+    let store = Arc::new(FixtureObservabilityStore::new(range));
+    {
+        let mut overview = store.overview.lock().unwrap();
+        overview.analytics.state = AnalyticsState::Ready;
+        overview.analytics.generated_at = Utc::now();
+        overview.analytics.lag_seconds = 7;
+        overview.requests.request_count = 19;
+    }
+    let services = observability_services(store.clone()).await;
+    let service = services.observability();
+    service
+        .usage_insights(range, UsageFilter::default())
+        .await
+        .unwrap();
+    store.insights_fail.store(true, Ordering::SeqCst);
+    tokio::time::advance(StdDuration::from_secs(16)).await;
+    let stale = service
+        .usage_insights(range, UsageFilter::default())
+        .await
+        .unwrap();
+    assert_eq!(stale.analytics.state, AnalyticsState::Stale);
+    assert!(stale.analytics.lag_seconds >= 7);
+    assert_eq!(stale.health.total_requests, 19);
+    tokio::time::advance(StdDuration::from_secs(45)).await;
+    assert!(
+        service
+            .usage_insights(range, UsageFilter::default())
+            .await
+            .is_err()
+    );
+}
+
+#[tokio::test(start_paused = true)]
+async fn insights_cache_should_reject_deleted_building_and_old_generation_times() {
+    for reason in ["deleted", "building", "generated-too-long-ago"] {
+        let range = observation_range(Utc::now());
+        let store = Arc::new(FixtureObservabilityStore::new(range));
+        {
+            let mut overview = store.overview.lock().unwrap();
+            overview.analytics.state = if reason == "building" {
+                AnalyticsState::Building
+            } else {
+                AnalyticsState::Ready
+            };
+            overview.analytics.generated_at = Utc::now()
+                - Duration::seconds(if reason == "generated-too-long-ago" {
+                    61
+                } else {
+                    0
+                });
+        }
+        let services = observability_services(store.clone()).await;
+        let service = services.observability();
+        service
+            .usage_insights(range, UsageFilter::default())
+            .await
+            .unwrap();
+        store.insights_fail.store(true, Ordering::SeqCst);
+        if reason == "deleted" {
+            store.overview.lock().unwrap().analytics.generation += 1;
+        }
+        tokio::time::advance(StdDuration::from_secs(16)).await;
+        assert!(
+            service
+                .usage_insights(range, UsageFilter::default())
+                .await
+                .is_err(),
+            "{reason}"
+        );
+    }
+}
@@ -24,12 +24,10 @@ use gateway_admin::{
        store::{AdminStoreError, AdminStoreErrorKind, AdminStoreResult},
    },
 };
+use gateway_core::routing::extensions::{ExtensionSetId, ExtensionSetLease, ExtensionSetReference};
 use gateway_core::{
    routing::ConfigRevision,
-    runtime::{
-        RuntimeSnapshotHandle, SnapshotControl,
-        extensions::{ExtensionSetId, ExtensionSetLease, ExtensionSetReference},
-    },
+    runtime::{RuntimeSnapshotHandle, SnapshotControl},
 };
 use serde_json::json;

@@ -117,7 +115,7 @@ impl gateway_admin::ports::plugins::PluginRuntimeDiagnostics for Fixture {
        &self,
        _: &gateway_admin::model::plugins::instances::PluginInstanceSnapshot,
        _: Option<u64>,
-        _: Option<&gateway_core::runtime::extensions::ExtensionSetReference>,
+        _: Option<&gateway_core::routing::extensions::ExtensionSetReference>,
    ) -> Option<
        std::collections::BTreeMap<
            String,
@@ -132,7 +130,7 @@ impl gateway_admin::ports::plugins::PluginRuntimeDiagnostics for Fixture {
 impl gateway_admin::ports::plugins::PluginStateLifecycle for Fixture {
    async fn activate_state(
        &self,
-        _: &gateway_core::runtime::extensions::ExtensionSetReference,
+        _: &gateway_core::routing::extensions::ExtensionSetReference,
        _: &gateway_admin::model::plugins::instances::PluginInstance,
    ) -> Result<(), AdminError> {
        Ok(())
@@ -142,7 +140,7 @@ impl gateway_admin::ports::plugins::PluginStateLifecycle for Fixture {
    }
    async fn migrate_state(
        &self,
-        _: &gateway_core::runtime::extensions::ExtensionSetReference,
+        _: &gateway_core::routing::extensions::ExtensionSetReference,
        _: gateway_admin::model::plugins::state::PluginStateTransition,
    ) -> Result<(), AdminError> {
        panic!("unexpected state migration")
@@ -40,12 +40,10 @@ use gateway_admin::{
        store::{AdminStoreError, AdminStoreErrorKind, AdminStoreResult},
    },
 };
+use gateway_core::routing::extensions::{ExtensionSetId, ExtensionSetLease, ExtensionSetReference};
 use gateway_core::{
    routing::ConfigRevision,
-    runtime::{
-        RuntimeSnapshotHandle, SnapshotControl,
-        extensions::{ExtensionSetId, ExtensionSetLease, ExtensionSetReference},
-    },
+    runtime::{RuntimeSnapshotHandle, SnapshotControl},
 };
 use serde_json::json;

@@ -87,9 +85,10 @@ impl gateway_admin::ports::plugins::PluginPackageInspector for LifecycleFixture
    }
    async fn compatibility_warning(
        &self,
-        _: Arc<[u8]>,
-        _: String,
+        archive: Arc<[u8]>,
+        digest: String,
    ) -> Result<Option<String>, AdminError> {
+        self.inspect(archive, Some(digest)).await?;
        Ok(self.data.lock().unwrap().compatibility_warning.clone())
    }
    async fn inspect(
@@ -132,6 +131,9 @@ struct FixtureData {
    saves: Vec<SavedInstance>,
    history: BTreeMap<String, PluginVersionConfiguration>,
    aborted: usize,
+    transition_active: bool,
+    fail_reload_after_migration: bool,
+    fail_next_load: bool,
    activated: usize,
    quiesced: usize,
    diagnostics: Option<BTreeMap<String, PluginInstanceRuntime>>,
@@ -185,6 +187,9 @@ impl LifecycleFixture {
                    },
                )]),
                aborted: 0,
+                transition_active: false,
+                fail_reload_after_migration: false,
+                fail_next_load: false,
                activated: 0,
                quiesced: 0,
                diagnostics: None,
@@ -237,6 +242,9 @@ impl LifecycleFixture {
            .instances
            .retain(|current| current.id != instance.id);
        data.snapshot.instances.push(instance.clone());
+        if transition_id.is_some() {
+            data.transition_active = false;
+        }
        data.saves.push(SavedInstance {
            artifact_sha256: instance.artifact_sha256.clone(),
            enabled: instance.enabled,
@@ -336,7 +344,11 @@ impl gateway_admin::ports::plugins::PluginStateLifecycle for LifecycleFixture {
        _: PluginStateTransition,
    ) -> Result<(), AdminError> {
        match self.behavior {
-            MigrationBehavior::Succeed => Ok(()),
+            MigrationBehavior::Succeed => {
+                let mut data = self.data.lock().unwrap();
+                data.fail_next_load = std::mem::take(&mut data.fail_reload_after_migration);
+                Ok(())
+            }
            MigrationBehavior::Fail => Err(AdminError::invalid("migration fixture failed")),
            MigrationBehavior::ConcurrentChangeThenFail => {
                let mut data = self.data.lock().unwrap();
@@ -400,9 +412,10 @@ impl PluginStateStore for LifecycleFixture {
        artifact_sha256: &str,
        _: PluginStateConfiguration,
    ) -> PluginStateStoreResult<PluginStateTransition> {
-        let data = self.data.lock().unwrap();
+        let mut data = self.data.lock().unwrap();
        let current = &data.snapshot.instances[0];
-        if current.enabled
+        if data.transition_active
+            || current.enabled
            || current.id != instance_id
            || current.revision != expected_instance_revision
            || artifact_sha256 != NEW_ARTIFACT
@@ -411,6 +424,7 @@ impl PluginStateStore for LifecycleFixture {
                PluginStateStoreErrorKind::Conflict,
            ));
        }
+        data.transition_active = true;
        Ok(PluginStateTransition {
            id: "00000000-0000-7000-8000-000000000002".into(),
            instance_id: instance_id.into(),
@@ -440,7 +454,9 @@ impl PluginStateStore for LifecycleFixture {
    }

    async fn abort_transition(&self, _: &str) -> PluginStateStoreResult<()> {
-        self.data.lock().unwrap().aborted += 1;
+        let mut data = self.data.lock().unwrap();
+        data.aborted += 1;
+        data.transition_active = false;
        Ok(())
    }
 }
@@ -465,7 +481,11 @@ impl PluginStore for LifecycleFixture {
            }))
    }
    async fn load_instances(&self) -> AdminStoreResult<PluginInstanceSnapshot> {
-        Ok(self.snapshot())
+        let mut data = self.data.lock().unwrap();
+        if std::mem::take(&mut data.fail_next_load) {
+            return Err(admin_error(AdminStoreErrorKind::Unavailable));
+        }
+        Ok(data.snapshot.clone())
    }

    async fn load_version_configuration(
@@ -1048,6 +1068,36 @@ async fn failed_state_migration_restores_the_previous_enabled_version_with_cas()
    assert_eq!(published.revisions.lock().unwrap().as_slice(), [11, 12]);
 }

+#[tokio::test]
+async fn reload_failure_after_migration_aborts_restores_and_allows_retry() {
+    let fixture = LifecycleFixture::new(MigrationBehavior::Succeed);
+    fixture.data.lock().unwrap().fail_reload_after_migration = true;
+    let published = Arc::new(Published::default());
+    let service = service(fixture.clone(), published.clone());
+    let id = "00000000-0000-7000-8000-000000000001";
+    let error = service
+        .configure_instance(Some(id), input(), &context())
+        .await
+        .err()
+        .unwrap();
+    assert_eq!(error.kind(), AdminErrorKind::Unavailable);
+    {
+        let data = fixture.data.lock().unwrap();
+        assert_eq!(data.aborted, 1);
+        assert!(!data.transition_active);
+        assert!(data.snapshot.instances[0].enabled);
+        assert_eq!(data.snapshot.instances[0].artifact_sha256, OLD_ARTIFACT);
+        assert_eq!(*published.revisions.lock().unwrap(), [11, 12]);
+    }
+    let result = service
+        .configure_instance(Some(id), input(), &context())
+        .await
+        .unwrap();
+    assert_eq!(result.instance.artifact_sha256, NEW_ARTIFACT);
+    assert!(result.instance.enabled);
+    assert!(!fixture.data.lock().unwrap().transition_active);
+}
+
 #[tokio::test]
 async fn failed_state_migration_never_overwrites_a_concurrent_configuration_change() {
    let fixture = LifecycleFixture::new(MigrationBehavior::ConcurrentChangeThenFail);
@@ -111,7 +111,7 @@ impl gateway_admin::ports::proxy::ProxyStore for TestPluginPorts {
 impl gateway_admin::ports::plugin_management::PluginManagement for TestPluginPorts {
    async fn validate_target(
        &self,
-        _: &gateway_core::runtime::extensions::ExtensionSetReference,
+        _: &gateway_core::routing::extensions::ExtensionSetReference,
        _: &gateway_admin::model::plugins::management::PluginManagementTarget,
    ) -> Result<(), AdminError> {
        Err(AdminError::not_found("unused plugin fixture"))
@@ -119,7 +119,7 @@ impl gateway_admin::ports::plugin_management::PluginManagement for TestPluginPor

    async fn start_callback(
        &self,
-        _: &gateway_core::runtime::extensions::ExtensionSetReference,
+        _: &gateway_core::routing::extensions::ExtensionSetReference,
        _: &gateway_admin::model::plugins::management::PluginManagementTarget,
        _: gateway_admin::model::plugins::management::StartPluginManagementCallback,
        _: &gateway_admin::model::auth::AdminRequestContext,
@@ -129,7 +129,7 @@ impl gateway_admin::ports::plugin_management::PluginManagement for TestPluginPor
    }
    async fn callback(
        &self,
-        _: &gateway_core::runtime::extensions::ExtensionSetReference,
+        _: &gateway_core::routing::extensions::ExtensionSetReference,
        _: &gateway_admin::model::plugins::management::PluginManagementTarget,
        _: &str,
        _: gateway_admin::model::plugins::management::PluginManagementRequest,
@@ -139,14 +139,14 @@ impl gateway_admin::ports::plugin_management::PluginManagement for TestPluginPor
    }
    async fn views(
        &self,
-        _: &gateway_core::runtime::extensions::ExtensionSetReference,
+        _: &gateway_core::routing::extensions::ExtensionSetReference,
    ) -> Result<Vec<gateway_admin::model::plugins::management::PluginManagementView>, AdminError>
    {
        Ok(Vec::new())
    }
    async fn resource(
        &self,
-        _: &gateway_core::runtime::extensions::ExtensionSetReference,
+        _: &gateway_core::routing::extensions::ExtensionSetReference,
        _: &gateway_admin::model::plugins::management::PluginManagementTarget,
        _: &str,
        _: bool,
@@ -156,7 +156,7 @@ impl gateway_admin::ports::plugin_management::PluginManagement for TestPluginPor
    }
    async fn handle(
        &self,
-        _: &gateway_core::runtime::extensions::ExtensionSetReference,
+        _: &gateway_core::routing::extensions::ExtensionSetReference,
        _: &gateway_admin::model::plugins::management::PluginManagementTarget,
        _: gateway_admin::model::plugins::management::PluginManagementRequest,
    ) -> Result<gateway_admin::model::plugins::management::PluginManagementResponse, AdminError>
@@ -171,7 +171,7 @@ impl gateway_admin::ports::plugins::PluginRuntimeDiagnostics for TestPluginPorts
        &self,
        _: &gateway_admin::model::plugins::instances::PluginInstanceSnapshot,
        _: Option<u64>,
-        _: Option<&gateway_core::runtime::extensions::ExtensionSetReference>,
+        _: Option<&gateway_core::routing::extensions::ExtensionSetReference>,
    ) -> Option<
        std::collections::BTreeMap<
            String,
@@ -186,7 +186,7 @@ impl gateway_admin::ports::plugins::PluginRuntimeDiagnostics for TestPluginPorts
 impl gateway_admin::ports::plugins::PluginStateLifecycle for TestPluginPorts {
    async fn activate_state(
        &self,
-        _: &gateway_core::runtime::extensions::ExtensionSetReference,
+        _: &gateway_core::routing::extensions::ExtensionSetReference,
        _: &gateway_admin::model::plugins::instances::PluginInstance,
    ) -> Result<(), AdminError> {
        panic!("unexpected state activation")
@@ -196,7 +196,7 @@ impl gateway_admin::ports::plugins::PluginStateLifecycle for TestPluginPorts {
    }
    async fn migrate_state(
        &self,
-        _: &gateway_core::runtime::extensions::ExtensionSetReference,
+        _: &gateway_core::routing::extensions::ExtensionSetReference,
        _: gateway_admin::model::plugins::state::PluginStateTransition,
    ) -> Result<(), AdminError> {
        panic!("unexpected state migration")
@@ -222,7 +222,7 @@ impl gateway_admin::ports::plugins::PluginPreparation for TestPluginPorts {
    async fn prepare(
        &self,
        _: gateway_admin::model::plugins::instances::PluginInstanceSnapshot,
-    ) -> Result<gateway_core::runtime::extensions::ExtensionSetReference, AdminError> {
+    ) -> Result<gateway_core::routing::extensions::ExtensionSetReference, AdminError> {
        Err(AdminError::invalid("unused plugin fixture"))
    }
 }
@@ -57,6 +57,7 @@ impl VisitMut for WireTypes {
            let last = path.path.segments.last().unwrap().clone();
            *ty = match last.ident.to_string().as_str() {
                "DateTime" | "Tz" | "TokenPrice" | "AdminApiKey" => parse_quote!(String),
+                "Value" => parse_quote!(serde_json::Value),
                "OpaqueProviderData" => parse_quote!(serde_json::Map<String, serde_json::Value>),
                _ => Type::Path(syn::TypePath {
                    attrs: std::mem::take(&mut path.attrs),
@@ -79,6 +80,10 @@ fn contract_type(mut item: Item, name: &str) -> Item {
                    | "ReplaceRuntimeSettings"
                    | "AdminApiKeyMutation"
                    | "RegeneratedAdminApiKey"
+                    | "CodexPrivacyPolicy"
+                    | "PrivacyRule"
+                    | "PrivacyPreviewRequest"
+                    | "PrivacyPreviewResult"
            );
            (
                &mut item.attrs,
@@ -107,6 +112,13 @@ fn contract_type(mut item: Item, name: &str) -> Item {
            field.vis = parse_quote!(pub);
        }
    }
+    if let Item::Enum(item) = &mut item {
+        for variant in &mut item.variants {
+            variant
+                .attrs
+                .retain(|attr| !attr.path().is_ident("default"));
+        }
+    }
    WireTypes.visit_item_mut(&mut item);
    item
 }
@@ -117,6 +129,19 @@ fn sdk_settings_contract_matches_host_declarations() {
    let mut types = Vec::new();
    let mut replacement_fields = Vec::new();
    for (path, names) in [
+        (
+            "../gateway-core/src/settings/privacy.rs",
+            &[
+                "CodexPrivacyPolicy",
+                "PrivacyFailureMode",
+                "PrivacyScope",
+                "PrivacyAction",
+                "PrivacyRule",
+                "PrivacyRuleOutcome",
+                "PrivacyPreviewRequest",
+                "PrivacyPreviewResult",
+            ][..],
+        ),
        (
            "src/model/settings.rs",
            &[
@@ -247,7 +272,7 @@ fn sdk_settings_contract_matches_host_declarations() {
            _ => None,
        })
        .collect();
-    let register = source(root, "src/service/settings.rs")
+    let register = source(root, "src/public_service/settings.rs")
        .items
        .into_iter()
        .find_map(|item| match item {
@@ -293,7 +318,7 @@ fn sdk_settings_contract_matches_host_declarations() {
    let generated = quote! {
        //! 宿主设置服务的操作标识与请求、响应数据合同
        //!
-        //! 从宿主设置类型与 service/settings.rs 生成；更新命令见 SDK 维护说明
+        //! 从宿主设置类型与 public_service/settings.rs 生成；更新命令见 SDK 维护说明

        use super::Operation;
        use serde::{Deserialize, Serialize};
@@ -28,7 +28,7 @@ struct PricingSettingsStore {

 #[tokio::test]
 async fn explicit_service_calls_freeze_empty_plan_and_cancel_before_entering_terminal() {
-    use gateway_admin::service::{Origin, Plan, scope};
+    use gateway_admin::public_service::{Origin, Plan, scope};
    use std::sync::atomic::{AtomicUsize, Ordering};

    let resolutions = Arc::new(AtomicUsize::new(0));
@@ -100,6 +100,51 @@ async fn client_profile_preview_rejects_unknown_provider_before_loading_settings
    assert_eq!(error.kind(), AdminErrorKind::Invalid);
 }

+#[tokio::test]
+async fn pricing_accepts_ultrafast_for_openai_but_rejects_it_for_xai() {
+    for provider in ["openai", "xai"] {
+        let store = Arc::new(PricingSettingsStore::default());
+        let services = super::AdminHarness::new()
+            .settings(store.clone())
+            .provider(super::test_provider(provider))
+            .build()
+            .await;
+        let context = MutationContext {
+            actor: gateway_admin::model::MutationActor::System,
+            request_id: "request-ultrafast-pricing".to_owned(),
+        };
+        for band in ["ultrafast", "long_ultrafast"] {
+            let pricing = serde_json::from_value(serde_json::json!({
+                "multiplierBps": 10000,
+                "bands": {
+                    "standard": {"input":"2", "output":"10", "cacheRead":"0.1", "cacheWrite":"2.5"},
+                    (band): {"input":"12", "output":"60", "cacheRead":"0.6", "cacheWrite":"15"}
+                }
+            }))
+            .expect("Ultrafast override");
+            let update = UpdatePricing {
+                provider: provider.to_owned(),
+                models: vec!["example-model".to_owned()],
+                change: PricingChange::Replace(pricing),
+            };
+            let result = services
+                .settings()
+                .update_pricing(&context, update.clone())
+                .await;
+            if provider == "openai" {
+                result.expect("OpenAI accepts Ultrafast overrides");
+                assert_eq!(store.updated.lock().unwrap().as_ref(), Some(&update));
+            } else {
+                assert_eq!(
+                    result.expect_err("xAI rejects Ultrafast").kind(),
+                    AdminErrorKind::Invalid
+                );
+                assert!(store.updated.lock().unwrap().is_none());
+            }
+        }
+    }
+}
+
 #[tokio::test]
 async fn pricing_accepts_native_provider_and_rejects_unknown_sync_provider() {
    let store = Arc::new(PricingSettingsStore::default());
@@ -280,12 +325,12 @@ async fn settings_should_reject_zero_refresh_margin_before_store_call() {
                model_mappings: Default::default(),
                rotation_strategy: RotationStrategy::Smart,
                values: gateway_admin::model::settings::RuntimeSettingsValues {
+                    codex_privacy_policy: Default::default(),
                    request_location_enabled: false,
                    request_location: Default::default(),
                    refresh_margin_seconds: 0,
                    refresh_concurrency: 1,
                    max_concurrent_per_account: 1,
-                    request_interval_ms: 0,
                    max_waiting_per_key: 0,
                    max_waiting_per_account: 0,
                    concurrency_wait_timeout_seconds: 30,
@@ -16,8 +16,9 @@ use gateway_admin::model::{
    PageSize,
    account_groups::{
        AccountGroupAccountSummary, AccountGroupCapacity, AccountGroupColor, AccountGroupListQuery,
-        AccountGroupMutation, AccountGroupPage, AccountGroupRecord, AccountGroupUsage,
-        CreateAccountGroup, DeleteAccountGroup, SetAccountGroupEnabled, UpdateAccountGroup,
+        AccountGroupMutation, AccountGroupOptionsPage, AccountGroupPage, AccountGroupRecord,
+        AccountGroupUsage, CreateAccountGroup, DeleteAccountGroup, SetAccountGroupEnabled,
+        UpdateAccountGroup,
    },
 };
 use gateway_core::{account::FastMode, routing::AccountGroupId};
@@ -212,6 +213,38 @@ struct AccountGroupPageData {
    config_revision: u64,
 }

+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+struct AccountGroupOptionsPageData {
+    items: Vec<AccountGroupRefView>,
+    page: PageMeta,
+    config_revision: u64,
+}
+
+impl From<AccountGroupOptionsPage> for AccountGroupOptionsPageData {
+    fn from(page: AccountGroupOptionsPage) -> Self {
+        let total_pages = if page.total == 0 {
+            0
+        } else {
+            page.total.div_ceil(u64::from(page.page_size))
+        };
+        Self {
+            items: page
+                .items
+                .into_iter()
+                .map(AccountGroupRefView::from)
+                .collect(),
+            page: PageMeta::new(
+                page.page,
+                u32::from(page.page_size),
+                page.total,
+                u32::try_from(total_pages).unwrap_or(u32::MAX),
+            ),
+            config_revision: page.config_revision.get(),
+        }
+    }
+}
+
 impl From<(AccountGroupPage, crate::time::TimePresenter)> for AccountGroupPageData {
    fn from((page, time): (AccountGroupPage, crate::time::TimePresenter)) -> Self {
        let total_pages = if page.total == 0 {
@@ -263,6 +296,7 @@ where
 {
    Router::new()
        .route("/api/admin/account-groups", get(list::<S>))
+        .route("/api/admin/account-groups/options", get(list_options::<S>))
        .route("/api/admin/account-groups/create", post(create::<S>))
        .route("/api/admin/account-groups/update", post(update::<S>))
        .route("/api/admin/account-groups/enable", post(enable::<S>))
@@ -270,6 +304,26 @@ where
        .route("/api/admin/account-groups/delete", post(delete::<S>))
 }

+async fn list_options<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<ListAccountGroupsQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: SessionState + Send + Sync,
+{
+    let result = state
+        .admin_services()
+        .account_groups()
+        .list_options(query.into_command().map_err(map_wire_error)?)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(AccountGroupOptionsPageData::from(result)),
+    ))
+}
+
 async fn list<S>(
    _auth: AdminAuth,
    State(state): State<S>,
@@ -308,8 +308,8 @@ pub(super) fn quota_local_usage(usage: &AccountUsage, time: crate::time::TimePre
        "inputTokensDisplay": display_optional_tokens(usage.input_tokens),
        "outputTokens": usage.output_tokens.unwrap_or_default(),
        "outputTokensDisplay": display_optional_tokens(usage.output_tokens),
-        "cachedTokens": usage.cached_tokens.unwrap_or_default(),
-        "cachedTokensDisplay": display_optional_tokens(usage.cached_tokens),
+        "cachedInputTokens": usage.cached_input_tokens.unwrap_or_default(),
+        "cachedInputTokensDisplay": display_optional_tokens(usage.cached_input_tokens),
        "imageInputTokens": usage.image_input_tokens.unwrap_or_default(),
        "imageInputTokensDisplay": display_optional_tokens(usage.image_input_tokens),
        "imageOutputTokens": usage.image_output_tokens.unwrap_or_default(),
@@ -355,10 +355,10 @@ pub(super) fn account_usage_view(
        input_tokens_display: display_optional_tokens(usage.input_tokens),
        output_tokens: usage.output_tokens,
        output_tokens_display: display_optional_tokens(usage.output_tokens),
-        cached_tokens: usage.cached_tokens,
-        cached_tokens_display: display_optional_tokens(usage.cached_tokens),
-        reasoning_tokens: usage.reasoning_tokens,
-        reasoning_tokens_display: display_optional_tokens(usage.reasoning_tokens),
+        cached_input_tokens: usage.cached_input_tokens,
+        cached_input_tokens_display: display_optional_tokens(usage.cached_input_tokens),
+        reasoning_output_tokens: usage.reasoning_output_tokens,
+        reasoning_output_tokens_display: display_optional_tokens(usage.reasoning_output_tokens),
        image_input_tokens: usage.image_input_tokens,
        image_input_tokens_display: display_optional_tokens(usage.image_input_tokens),
        image_output_tokens: usage.image_output_tokens,
@@ -369,10 +369,8 @@ pub(super) fn account_usage_view(
        image_request_failed_count_display: format_number(usage.image_request_failed_count),
        total_tokens: usage.total_tokens,
        total_tokens_display: display_optional_tokens(usage.total_tokens),
-        created_tokens: usage.cache_write_tokens,
-        created_tokens_display: display_optional_tokens(usage.cache_write_tokens),
-        read_tokens: usage.cached_tokens,
-        read_tokens_display: display_optional_tokens(usage.cached_tokens),
+        cache_write_input_tokens: usage.cache_write_input_tokens,
+        cache_write_input_tokens_display: display_optional_tokens(usage.cache_write_input_tokens),
        last_used_at: usage.last_used_at.map(|value| time.rfc3339(&value)),
        last_used_at_full_display: usage.last_used_at.map(|value| time.datetime(&value)),
        last_used_at_display: usage
@@ -429,8 +427,8 @@ pub(super) fn account_model_usage_view(
        input_tokens_display: display_optional_tokens(usage.input_tokens),
        output_tokens: usage.output_tokens,
        output_tokens_display: display_optional_tokens(usage.output_tokens),
-        cached_tokens: usage.cached_tokens,
-        cached_tokens_display: display_optional_tokens(usage.cached_tokens),
+        cached_input_tokens: usage.cached_input_tokens,
+        cached_input_tokens_display: display_optional_tokens(usage.cached_input_tokens),
        image_input_tokens: usage.image_input_tokens,
        image_input_tokens_display: display_optional_tokens(usage.image_input_tokens),
        image_output_tokens: usage.image_output_tokens,
@@ -478,10 +476,10 @@ pub(super) fn empty_account_usage() -> AccountUsageView {
        input_tokens_display: "—".to_owned(),
        output_tokens: None,
        output_tokens_display: "—".to_owned(),
-        cached_tokens: None,
-        cached_tokens_display: "—".to_owned(),
-        reasoning_tokens: None,
-        reasoning_tokens_display: "—".to_owned(),
+        cached_input_tokens: None,
+        cached_input_tokens_display: "—".to_owned(),
+        reasoning_output_tokens: None,
+        reasoning_output_tokens_display: "—".to_owned(),
        image_input_tokens: None,
        image_input_tokens_display: "—".to_owned(),
        image_output_tokens: None,
@@ -492,10 +490,8 @@ pub(super) fn empty_account_usage() -> AccountUsageView {
        image_request_failed_count_display: "—".to_owned(),
        total_tokens: None,
        total_tokens_display: "—".to_owned(),
-        created_tokens: None,
-        created_tokens_display: "—".to_owned(),
-        read_tokens: None,
-        read_tokens_display: "—".to_owned(),
+        cache_write_input_tokens: None,
+        cache_write_input_tokens_display: "—".to_owned(),
        last_used_at: None,
        last_used_at_full_display: None,
        last_used_at_display: "—".to_owned(),
@@ -435,10 +435,10 @@ pub struct AccountUsageView {
    pub input_tokens_display: String,
    pub output_tokens: Option<u64>,
    pub output_tokens_display: String,
-    pub cached_tokens: Option<u64>,
-    pub cached_tokens_display: String,
-    pub reasoning_tokens: Option<u64>,
-    pub reasoning_tokens_display: String,
+    pub cached_input_tokens: Option<u64>,
+    pub cached_input_tokens_display: String,
+    pub reasoning_output_tokens: Option<u64>,
+    pub reasoning_output_tokens_display: String,
    pub image_input_tokens: Option<u64>,
    pub image_input_tokens_display: String,
    pub image_output_tokens: Option<u64>,
@@ -449,10 +449,8 @@ pub struct AccountUsageView {
    pub image_request_failed_count_display: String,
    pub total_tokens: Option<u64>,
    pub total_tokens_display: String,
-    pub created_tokens: Option<u64>,
-    pub created_tokens_display: String,
-    pub read_tokens: Option<u64>,
-    pub read_tokens_display: String,
+    pub cache_write_input_tokens: Option<u64>,
+    pub cache_write_input_tokens_display: String,
    pub last_used_at: Option<String>,
    pub last_used_at_display: String,
    pub last_used_at_full_display: Option<String>,
@@ -477,8 +475,8 @@ pub struct ModelUsageView {
    pub input_tokens_display: String,
    pub output_tokens: Option<u64>,
    pub output_tokens_display: String,
-    pub cached_tokens: Option<u64>,
-    pub cached_tokens_display: String,
+    pub cached_input_tokens: Option<u64>,
+    pub cached_input_tokens_display: String,
    pub image_input_tokens: Option<u64>,
    pub image_input_tokens_display: String,
    pub image_output_tokens: Option<u64>,
@@ -58,9 +58,9 @@ pub(crate) fn request_metrics_view(metrics: &domain::RequestMetrics) -> RequestM
        caller_error_count: metrics.caller_error_count,
        input_tokens: metrics.input_tokens,
        output_tokens: metrics.output_tokens,
-        cached_tokens: metrics.cached_tokens,
-        cache_write_tokens: metrics.cache_write_tokens,
-        reasoning_tokens: metrics.reasoning_tokens,
+        cached_input_tokens: metrics.cached_input_tokens,
+        cache_write_input_tokens: metrics.cache_write_input_tokens,
+        reasoning_output_tokens: metrics.reasoning_output_tokens,
        total_tokens: metrics.total_tokens,
    }
 }
@@ -103,9 +103,9 @@ pub(crate) fn token_details(record: &domain::UsageRecord) -> TokenDetailsView {
    TokenDetailsView {
        input_tokens: record.input_tokens,
        output_tokens: record.output_tokens,
-        cached_tokens: record.cached_tokens,
-        cache_write_tokens: record.cache_write_tokens,
-        reasoning_tokens: record.reasoning_tokens,
+        cached_input_tokens: record.cached_input_tokens,
+        cache_write_input_tokens: record.cache_write_input_tokens,
+        reasoning_output_tokens: record.reasoning_output_tokens,
        image_input_tokens: record.image_input_tokens,
        image_output_tokens: record.image_output_tokens,
        total_tokens: record.total_tokens,
@@ -115,14 +115,14 @@ pub(crate) fn token_details(record: &domain::UsageRecord) -> TokenDetailsView {
        output_tokens_display: record
            .output_tokens
            .map_or_else(|| "-".to_owned(), format_number),
-        cached_tokens_display: record
-            .cached_tokens
+        cached_input_tokens_display: record
+            .cached_input_tokens
            .map_or_else(|| "-".to_owned(), format_compact_number),
-        cache_write_tokens_display: record
-            .cache_write_tokens
+        cache_write_input_tokens_display: record
+            .cache_write_input_tokens
            .map_or_else(|| "-".to_owned(), format_compact_number),
-        reasoning_tokens_display: record
-            .reasoning_tokens
+        reasoning_output_tokens_display: record
+            .reasoning_output_tokens
            .map_or_else(|| "-".to_owned(), format_number),
        image_input_tokens_display: record
            .image_input_tokens
@@ -140,9 +140,9 @@ pub(crate) fn usage_list_token_details(record: &domain::UsageListRecord) -> Toke
    TokenDetailsView {
        input_tokens: record.input_tokens,
        output_tokens: record.output_tokens,
-        cached_tokens: record.cached_tokens,
-        cache_write_tokens: record.cache_write_tokens,
-        reasoning_tokens: record.reasoning_tokens,
+        cached_input_tokens: record.cached_input_tokens,
+        cache_write_input_tokens: record.cache_write_input_tokens,
+        reasoning_output_tokens: record.reasoning_output_tokens,
        image_input_tokens: record.image_input_tokens,
        image_output_tokens: record.image_output_tokens,
        total_tokens: record.total_tokens,
@@ -152,14 +152,14 @@ pub(crate) fn usage_list_token_details(record: &domain::UsageListRecord) -> Toke
        output_tokens_display: record
            .output_tokens
            .map_or_else(|| "-".to_owned(), format_number),
-        cached_tokens_display: record
-            .cached_tokens
+        cached_input_tokens_display: record
+            .cached_input_tokens
            .map_or_else(|| "-".to_owned(), format_compact_number),
-        cache_write_tokens_display: record
-            .cache_write_tokens
+        cache_write_input_tokens_display: record
+            .cache_write_input_tokens
            .map_or_else(|| "-".to_owned(), format_compact_number),
-        reasoning_tokens_display: record
-            .reasoning_tokens
+        reasoning_output_tokens_display: record
+            .reasoning_output_tokens
            .map_or_else(|| "-".to_owned(), format_number),
        image_input_tokens_display: record
            .image_input_tokens
@@ -307,8 +307,14 @@ pub(crate) fn usage_list_record_view(
            first_event_ms: record.first_event_ms,
            first_reasoning_ms: record.first_reasoning_ms,
            first_text_ms: record.first_text_ms,
-            first_token_ms: record.first_token_ms,
            openai_processing_ms: record.provider_processing_ms,
+            upstream_response_ms: record.upstream_response_ms,
+            upstream_api_overhead_ms: record.upstream_api_overhead_ms,
+            upstream_engine_ms: record.upstream_engine_ms,
+            upstream_engine_iapi_ttft_ms: record.upstream_engine_iapi_ttft_ms,
+            upstream_engine_service_ttft_ms: record.upstream_engine_service_ttft_ms,
+            upstream_engine_iapi_tbt_ms: record.upstream_engine_iapi_tbt_ms,
+            upstream_engine_service_tbt_ms: record.upstream_engine_service_tbt_ms,
        },
        first_token_latency_ms: record.first_token_ms,
        latency_ms: record.latency_ms,
@@ -345,7 +351,6 @@ pub(crate) fn usage_record_view(
        .error_message
        .clone()
        .unwrap_or_else(|| outcome.clone());
-    let first_token_display = display_duration(record.first_token_ms);
    let latency_display = display_duration(record.latency_ms);
    let cost_coverage = match record.cost_source.as_str() {
        "provider_reported" | "calculated" => CostCoverageView {
@@ -409,20 +414,25 @@ pub(crate) fn usage_record_view(
            first_event_ms: record.first_event_ms,
            first_reasoning_ms: record.first_reasoning_ms,
            first_text_ms: record.first_text_ms,
-            first_token_ms: record.first_token_ms,
            openai_processing_ms: record.provider_processing_ms,
+            upstream_response_ms: record.upstream_response_ms,
+            upstream_api_overhead_ms: record.upstream_api_overhead_ms,
+            upstream_engine_ms: record.upstream_engine_ms,
+            upstream_engine_iapi_ttft_ms: record.upstream_engine_iapi_ttft_ms,
+            upstream_engine_service_ttft_ms: record.upstream_engine_service_ttft_ms,
+            upstream_engine_iapi_tbt_ms: record.upstream_engine_iapi_tbt_ms,
+            upstream_engine_service_tbt_ms: record.upstream_engine_service_tbt_ms,
        },
        attempt_index: None,
        attempt_count: u64::from(record.attempt_count),
        response_id: record.client_response_id,
        upstream_request_id: record.upstream_request_id,
        latency_ms: record.latency_ms,
-        first_token_ms: record.first_token_ms,
        input_tokens: record.input_tokens,
        output_tokens: record.output_tokens,
-        cached_tokens: record.cached_tokens,
-        cache_write_tokens: record.cache_write_tokens,
-        reasoning_tokens: record.reasoning_tokens,
+        cached_input_tokens: record.cached_input_tokens,
+        cache_write_input_tokens: record.cache_write_input_tokens,
+        reasoning_output_tokens: record.reasoning_output_tokens,
        image_input_tokens: record.image_input_tokens,
        image_output_tokens: record.image_output_tokens,
        message,
@@ -441,7 +451,6 @@ pub(crate) fn usage_record_view(
        costs,
        cost_coverage,
        first_token_latency_ms: record.first_token_ms,
-        first_token_latency_ms_display: first_token_display,
        latency_ms_display: latency_display,
        logical_outcome: outcome,
    }
@@ -517,7 +526,7 @@ pub(crate) fn usage_attempt_view(attempt: domain::UsageAttempt) -> UsageAttemptV
        estimated_cost_currency: attempt.cost_currency,
        input_tokens: attempt.input_tokens,
        output_tokens: attempt.output_tokens,
-        cached_tokens: attempt.cached_tokens,
+        cached_input_tokens: attempt.cached_input_tokens,
        total_tokens: attempt.total_tokens,
        first_token_ms: None,
        latency_ms: attempt.latency_ms,
@@ -674,8 +683,8 @@ pub(crate) fn trend_point_view(
        input_tokens_value: point.metrics.input_tokens,
        output_tokens: format_compact_number(point.metrics.output_tokens),
        output_tokens_value: point.metrics.output_tokens,
-        cached_tokens: format_compact_number(point.metrics.cached_tokens),
-        cached_tokens_value: point.metrics.cached_tokens,
+        cached_input_tokens: format_compact_number(point.metrics.cached_input_tokens),
+        cached_input_tokens_value: point.metrics.cached_input_tokens,
        cache_hit_rate_value: point.cached_token_rate,
        tokens_value: point.metrics.total_tokens,
        errors: format_compact_number(point.service_failure_count),
@@ -740,7 +749,7 @@ pub(crate) fn trend_summary_view(
            },
            TrendSummaryView {
                label: "缓存".to_owned(),
-                value: format_compact_number(summary.cached_tokens),
+                value: format_compact_number(summary.cached_input_tokens),
                ratio: None,
            },
        ],
@@ -756,7 +765,7 @@ pub(crate) fn trend_summary_view(
                ratio: None,
            },
            TrendSummaryView {
-                label: "吞吐 P50".to_owned(),
+                label: "速率 P50".to_owned(),
                value: summary
                    .minimum_output_throughput_p50
                    .map_or_else(|| "—".to_owned(), |value| format!("{value} tok/s")),
@@ -791,6 +800,7 @@ pub(crate) fn trend_view(
    time: crate::time::TimePresenter,
 ) -> TrendData {
    TrendData {
+        analytics: analytics_view(trend.analytics, time),
        kind,
        summary: trend_summary_view(kind, &trend.summary),
        points: trend
@@ -904,6 +914,8 @@ pub(crate) fn dashboard_view(
        rotation_strategy,
    } = result;
    let domain::DashboardObservation {
+        analytics,
+        runtime_slots: _,
        range,
        totals,
        provider_accounts,
@@ -972,6 +984,7 @@ pub(crate) fn dashboard_view(
        .saturating_sub(provider_accounts.normal);

    DashboardDataView {
+        analytics: analytics_view(analytics, time),
        as_of: range.end,
        as_of_display: time.datetime(&range.end),
        cards: DashboardCardsView {
@@ -1003,7 +1016,7 @@ pub(crate) fn dashboard_view(
                today_hit_rate_value: today.observed_cached_token_rate,
                yesterday_hit_rate_value: yesterday.observed_cached_token_rate,
                total_hit_rate: display_rate(total_cached_token_rate),
-                total_cached_tokens: format_compact_number(totals.cached_tokens),
+                total_cached_input_tokens: format_compact_number(totals.cached_input_tokens),
                average_first_token_latency_ms: display_duration(average_first_token_latency_ms),
            },
        },
@@ -1036,14 +1049,18 @@ pub(crate) fn dashboard_view(
    }
 }

-pub(crate) fn usage_summary_view(summary: domain::UsageSummary) -> UsageSummaryView {
+pub(crate) fn usage_summary_view(
+    summary: domain::UsageSummary,
+    time: crate::time::TimePresenter,
+) -> UsageSummaryView {
    let overview = summary.overview;
    UsageSummaryView {
+        analytics: analytics_view(overview.analytics, time),
        total_requests: format_compact_number(overview.requests.request_count),
        input_tokens: format_compact_number(overview.requests.input_tokens),
        output_tokens: format_compact_number(overview.requests.output_tokens),
-        cached_tokens: format_compact_number(overview.requests.cached_tokens),
-        cache_write_tokens: format_compact_number(overview.requests.cache_write_tokens),
+        cached_input_tokens: format_compact_number(overview.requests.cached_input_tokens),
+        cache_write_input_tokens: format_compact_number(overview.requests.cache_write_input_tokens),
        total_tokens: format_compact_number(overview.requests.total_tokens),
        average_latency_ms: display_duration(summary.average_latency_ms),
        logical_requests: request_metrics_view(&overview.requests),
@@ -1129,7 +1146,7 @@ pub(crate) fn usage_insights_view(
            label: time.label(point.bucket_start, "%m-%d %H:%M"),
            input_tokens: point.input_tokens,
            output_tokens: point.output_tokens,
-            cached_tokens: point.cached_tokens,
+            cached_input_tokens: point.cached_input_tokens,
            total_tokens: point.total_tokens,
            estimated_cost: point.estimated_cost.as_ref().map(ToString::to_string),
            standard_cost: point.standard_cost.as_ref().map(ToString::to_string),
@@ -1140,6 +1157,7 @@ pub(crate) fn usage_insights_view(
        })
        .collect();
    UsageInsightsOverviewView {
+        analytics: analytics_view(insights.analytics, time),
        granularity: granularity_name(insights.granularity).to_owned(),
        health: OverviewHealthView {
            total_requests: insights.health.total_requests,
@@ -1260,7 +1278,7 @@ pub(crate) fn usage_insights_view(
            cache_hit_request_rate: insights.cost.cache_hit_request_rate,
            input_tokens: insights.cost.input_tokens,
            output_tokens: insights.cost.output_tokens,
-            cached_tokens: insights.cost.cached_tokens,
+            cached_input_tokens: insights.cost.cached_input_tokens,
            total_tokens: insights.cost.total_tokens,
            points: cost_points,
            costs: cost_views(&insights.cost.costs),
@@ -1292,8 +1310,10 @@ pub(crate) fn granularity_name(granularity: domain::Granularity) -> &'static str
 pub(crate) fn diagnostics_view(
    result: domain::DiagnosticsResult,
    dimension: DiagnosticDimension,
+    time: crate::time::TimePresenter,
 ) -> DiagnosticsView {
    DiagnosticsView {
+        analytics: analytics_view(result.analytics, time),
        dimension: dimension.display_name().to_owned(),
        items: result
            .items
@@ -1346,3 +1366,22 @@ pub(crate) fn map_wire_error(error: WireValidationError) -> AdminError {
 pub(crate) fn map_service_error(error: gateway_admin::model::AdminError) -> AdminError {
    map_admin_service_error(error)
 }
+
+pub(crate) fn analytics_view(
+    metadata: domain::AnalyticsMetadata,
+    time: crate::time::TimePresenter,
+) -> AnalyticsView {
+    AnalyticsView {
+        coverage_start: metadata.coverage_start,
+        coverage_start_display: metadata.coverage_start.map(|value| time.datetime(&value)),
+        coverage_end: metadata.coverage_end,
+        coverage_end_display: metadata.coverage_end.map(|value| time.datetime(&value)),
+        generated_at: metadata.generated_at,
+        generated_at_display: time.datetime(&metadata.generated_at),
+        lag_seconds: metadata.lag_seconds,
+        state: metadata.state.as_str().to_owned(),
+        percentiles_approximate: metadata.percentiles_approximate,
+        schema_version: metadata.schema_version,
+        histogram_version: metadata.histogram_version,
+    }
+}
@@ -54,15 +54,7 @@ pub struct UsageQuery {
 impl UsageQuery {
    /// 校验 Element Plus 风格的页码分页字段
    pub fn validate_pagination(&self) -> Result<(u32, u16), WireValidationError> {
-        let current_page = self.current_page.unwrap_or(1);
-        if current_page == 0 {
-            return Err(WireValidationError::new("currentPage"));
-        }
-        let page_size = self.page_size.unwrap_or(DEFAULT_PAGE_SIZE);
-        if DomainPageSize::new(page_size).is_err() {
-            return Err(WireValidationError::new("pageSize"));
-        }
-        Ok((current_page, page_size))
+        validate_pagination(self.current_page, self.page_size)
    }
 }

@@ -92,7 +84,6 @@ pub struct DiagnosticsQuery {
    pub provider: Option<String>,
    pub model: Option<String>,
    pub status_code: Option<i64>,
-    pub search: Option<String>,
 }

 impl DiagnosticsQuery {
@@ -131,15 +122,7 @@ pub struct OpsQuery {
 impl OpsQuery {
    /// 校验 Element Plus 风格的页码分页字段
    pub fn validate_pagination(&self) -> Result<(u32, u16), WireValidationError> {
-        let current_page = self.current_page.unwrap_or(1);
-        if current_page == 0 {
-            return Err(WireValidationError::new("currentPage"));
-        }
-        let page_size = self.page_size.unwrap_or(DEFAULT_PAGE_SIZE);
-        if DomainPageSize::new(page_size).is_err() {
-            return Err(WireValidationError::new("pageSize"));
-        }
-        Ok((current_page, page_size))
+        validate_pagination(self.current_page, self.page_size)
    }
 }

@@ -330,6 +313,15 @@ pub(crate) fn usage_filter(query: &UsageQuery) -> Result<domain::UsageFilter, Wi
    })
 }

+pub(crate) fn analytics_filter(
+    query: &UsageQuery,
+) -> Result<domain::UsageFilter, WireValidationError> {
+    if query.search.is_some() {
+        return Err(WireValidationError::new("search"));
+    }
+    usage_filter(query)
+}
+
 pub(crate) fn usage_command(
    query: &UsageQuery,
    timezone: gateway_core::time::DeploymentTimeZone,
@@ -396,3 +388,18 @@ pub(crate) fn non_empty(value: Option<String>) -> Option<String> {
        .map(|value| value.trim().to_owned())
        .filter(|value| !value.is_empty())
 }
+
+fn validate_pagination(
+    current_page: Option<u32>,
+    page_size: Option<u16>,
+) -> Result<(u32, u16), WireValidationError> {
+    let current_page = current_page.unwrap_or(1);
+    if current_page == 0 {
+        return Err(WireValidationError::new("currentPage"));
+    }
+    let page_size = page_size.unwrap_or(DEFAULT_PAGE_SIZE);
+    if DomainPageSize::new(page_size).is_err() {
+        return Err(WireValidationError::new("pageSize"));
+    }
+    Ok((current_page, page_size))
+}
@@ -151,7 +151,7 @@ where
        state.admin_services().timezone(),
    )
    .map_err(map_wire_error)?;
-    let filter = usage_filter(&query).map_err(map_wire_error)?;
+    let filter = analytics_filter(&query).map_err(map_wire_error)?;
    let result = state
        .admin_services()
        .observability()
@@ -160,7 +160,10 @@ where
        .map_err(map_service_error)?;
    Ok(AdminResponse::new(
        StatusCode::OK,
-        AdminEnvelope::ok(usage_summary_view(result)),
+        AdminEnvelope::ok(usage_summary_view(
+            result,
+            crate::time::TimePresenter::new(state.admin_services().timezone()),
+        )),
    ))
 }

@@ -181,7 +184,7 @@ where
        state.admin_services().timezone(),
    )
    .map_err(map_wire_error)?;
-    let filter = usage_filter(&query).map_err(map_wire_error)?;
+    let filter = analytics_filter(&query).map_err(map_wire_error)?;
    let result = state
        .admin_services()
        .observability()
@@ -215,7 +218,6 @@ where
        provider_kind: non_empty(query.provider),
        model: non_empty(query.model),
        status_code: parse_status(query.status_code).map_err(map_wire_error)?,
-        search: non_empty(query.search),
        ..domain::UsageFilter::default()
    };
    let result = state
@@ -226,7 +228,11 @@ where
        .map_err(map_service_error)?;
    Ok(AdminResponse::new(
        StatusCode::OK,
-        AdminEnvelope::ok(diagnostics_view(result, dimension)),
+        AdminEnvelope::ok(diagnostics_view(
+            result,
+            dimension,
+            crate::time::TimePresenter::new(state.admin_services().timezone()),
+        )),
    ))
 }

@@ -18,17 +18,17 @@ pub struct PageData<T> {
 pub struct TokenDetailsView {
    pub input_tokens: Option<u64>,
    pub output_tokens: Option<u64>,
-    pub cached_tokens: Option<u64>,
-    pub cache_write_tokens: Option<u64>,
-    pub reasoning_tokens: Option<u64>,
+    pub cached_input_tokens: Option<u64>,
+    pub cache_write_input_tokens: Option<u64>,
+    pub reasoning_output_tokens: Option<u64>,
    pub image_input_tokens: Option<u64>,
    pub image_output_tokens: Option<u64>,
    pub total_tokens: Option<u64>,
    pub input_tokens_display: String,
    pub output_tokens_display: String,
-    pub cached_tokens_display: String,
-    pub cache_write_tokens_display: String,
-    pub reasoning_tokens_display: String,
+    pub cached_input_tokens_display: String,
+    pub cache_write_input_tokens_display: String,
+    pub reasoning_output_tokens_display: String,
    pub image_input_tokens_display: String,
    pub image_output_tokens_display: String,
    pub total_tokens_display: String,
@@ -160,12 +160,11 @@ pub struct UsageRecordView {
    pub response_id: Option<String>,
    pub upstream_request_id: Option<String>,
    pub latency_ms: Option<u64>,
-    pub first_token_ms: Option<u64>,
    pub input_tokens: Option<u64>,
    pub output_tokens: Option<u64>,
-    pub cached_tokens: Option<u64>,
-    pub cache_write_tokens: Option<u64>,
-    pub reasoning_tokens: Option<u64>,
+    pub cached_input_tokens: Option<u64>,
+    pub cache_write_input_tokens: Option<u64>,
+    pub reasoning_output_tokens: Option<u64>,
    pub image_input_tokens: Option<u64>,
    pub image_output_tokens: Option<u64>,
    pub message: String,
@@ -185,7 +184,6 @@ pub struct UsageRecordView {
    pub costs: Vec<CostView>,
    pub cost_coverage: CostCoverageView,
    pub first_token_latency_ms: Option<u64>,
-    pub first_token_latency_ms_display: String,
    pub latency_ms_display: String,
    pub logical_outcome: String,
 }
@@ -222,9 +220,21 @@ pub struct UsageLatencyDetailsView {
    #[serde(skip_serializing_if = "Option::is_none")]
    pub first_text_ms: Option<u64>,
    #[serde(skip_serializing_if = "Option::is_none")]
-    pub first_token_ms: Option<u64>,
-    #[serde(skip_serializing_if = "Option::is_none")]
    pub openai_processing_ms: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub upstream_response_ms: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub upstream_api_overhead_ms: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub upstream_engine_ms: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub upstream_engine_iapi_ttft_ms: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub upstream_engine_service_ttft_ms: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub upstream_engine_iapi_tbt_ms: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub upstream_engine_service_tbt_ms: Option<f64>,
 }

 /// 单次上游尝试展示
@@ -248,7 +258,7 @@ pub struct UsageAttemptView {
    pub estimated_cost_currency: Option<String>,
    pub input_tokens: Option<u64>,
    pub output_tokens: Option<u64>,
-    pub cached_tokens: Option<u64>,
+    pub cached_input_tokens: Option<u64>,
    pub total_tokens: Option<u64>,
    pub first_token_ms: Option<u64>,
    pub latency_ms: Option<u64>,
@@ -278,6 +288,7 @@ pub struct UsageRecordDetailView {
 #[derive(Debug, Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct TrendData {
+    pub analytics: AnalyticsView,
    pub kind: TrendKind,
    pub points: Vec<TrendPointView>,
    pub summary: Vec<TrendSummaryView>,
@@ -296,8 +307,8 @@ pub struct TrendPointView {
    pub input_tokens_value: u64,
    pub output_tokens: String,
    pub output_tokens_value: u64,
-    pub cached_tokens: String,
-    pub cached_tokens_value: u64,
+    pub cached_input_tokens: String,
+    pub cached_input_tokens_value: u64,
    pub cache_hit_rate_value: f64,
    pub tokens_value: u64,
    pub errors: String,
@@ -378,7 +389,7 @@ pub struct DashboardCacheCardView {
    pub today_hit_rate_value: Option<f64>,
    pub yesterday_hit_rate_value: Option<f64>,
    pub total_hit_rate: String,
-    pub total_cached_tokens: String,
+    pub total_cached_input_tokens: String,
    pub average_first_token_latency_ms: String,
 }

@@ -436,9 +447,9 @@ pub struct RequestMetricsView {
    pub caller_error_count: u64,
    pub input_tokens: u64,
    pub output_tokens: u64,
-    pub cached_tokens: u64,
-    pub cache_write_tokens: u64,
-    pub reasoning_tokens: u64,
+    pub cached_input_tokens: u64,
+    pub cache_write_input_tokens: u64,
+    pub reasoning_output_tokens: u64,
    pub total_tokens: u64,
 }

@@ -565,6 +576,7 @@ impl From<domain::DesktopReleaseStatus> for DashboardDesktopReleaseStatusView {
 #[derive(Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct DashboardDataView {
+    pub analytics: AnalyticsView,
    pub as_of: DateTime<Utc>,
    pub as_of_display: String,
    pub cards: DashboardCardsView,
@@ -582,11 +594,12 @@ pub struct DashboardDataView {
 #[derive(Debug, Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct UsageSummaryView {
+    pub analytics: AnalyticsView,
    pub total_requests: String,
    pub input_tokens: String,
    pub output_tokens: String,
-    pub cached_tokens: String,
-    pub cache_write_tokens: String,
+    pub cached_input_tokens: String,
+    pub cache_write_input_tokens: String,
    pub total_tokens: String,
    pub average_latency_ms: String,
    pub logical_requests: RequestMetricsView,
@@ -683,7 +696,7 @@ pub struct OverviewCostPointView {
    pub label: String,
    pub input_tokens: u64,
    pub output_tokens: u64,
-    pub cached_tokens: u64,
+    pub cached_input_tokens: u64,
    pub total_tokens: u64,
    pub estimated_cost: Option<String>,
    pub standard_cost: Option<String>,
@@ -709,7 +722,7 @@ pub struct OverviewCostView {
    pub cache_hit_request_rate: Option<f64>,
    pub input_tokens: u64,
    pub output_tokens: u64,
-    pub cached_tokens: u64,
+    pub cached_input_tokens: u64,
    pub total_tokens: u64,
    pub points: Vec<OverviewCostPointView>,
    pub costs: Vec<CostView>,
@@ -731,6 +744,7 @@ pub struct ProviderOverviewView {
 #[derive(Debug, Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct UsageInsightsOverviewView {
+    pub analytics: AnalyticsView,
    pub granularity: String,
    pub health: OverviewHealthView,
    pub performance: OverviewPerformanceView,
@@ -768,6 +782,7 @@ pub struct DiagnosticItemView {
 #[derive(Debug, Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct DiagnosticsView {
+    pub analytics: AnalyticsView,
    pub dimension: String,
    pub items: Vec<DiagnosticItemView>,
 }
@@ -842,3 +857,20 @@ pub struct OpsErrorMetadataView {
    pub recovery_retry_delay_ms: Option<u64>,
    pub recovery_total_latency_ms: Option<u64>,
 }
+
+/// 统计覆盖、新鲜度与近似口径，时间文案使用部署时区
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AnalyticsView {
+    pub coverage_start: Option<DateTime<Utc>>,
+    pub coverage_start_display: Option<String>,
+    pub coverage_end: Option<DateTime<Utc>>,
+    pub coverage_end_display: Option<String>,
+    pub generated_at: DateTime<Utc>,
+    pub generated_at_display: String,
+    pub lag_seconds: u64,
+    pub state: String,
+    pub percentiles_approximate: bool,
+    pub schema_version: u32,
+    pub histogram_version: u32,
+}
@@ -36,12 +36,12 @@ pub type ProviderRequestProfileUpdates =
 #[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
 #[serde(rename_all = "camelCase")]
 pub struct RuntimeSettingsFields {
+    pub codex_privacy_policy: gateway_core::settings::privacy::CodexPrivacyPolicy,
    pub request_location_enabled: bool,
    pub request_location: gateway_core::account::RequestLocation,
    pub refresh_margin_seconds: u64,
    pub refresh_concurrency: u64,
    pub max_concurrent_per_account: u64,
-    pub request_interval_ms: u64,
    pub max_waiting_per_key: u32,
    pub max_waiting_per_account: u32,
    pub concurrency_wait_timeout_seconds: u32,
@@ -283,6 +283,10 @@ where
            "/api/admin/settings/client-profiles/{provider}/preview",
            post(preview_client_profile::<S>),
        )
+        .route(
+            "/api/admin/settings/privacy/preview",
+            post(preview_privacy::<S>),
+        )
        .route("/api/admin/settings/update", post(update_settings::<S>))
        .route(
            "/api/admin/settings/client-downloads/codex-desktop/windows",
@@ -719,6 +723,7 @@ impl RuntimeSettingsFields {
        self,
    ) -> Result<gateway_admin::model::settings::RuntimeSettingsValues, WireValidationError> {
        let values = gateway_admin::model::settings::RuntimeSettingsValues {
+            codex_privacy_policy: self.codex_privacy_policy,
            request_location_enabled: self.request_location_enabled,
            request_location: self
                .request_location
@@ -729,7 +734,6 @@ impl RuntimeSettingsFields {
                .map_err(|_| WireValidationError::new("settingsRefreshConcurrencyOverflow"))?,
            max_concurrent_per_account: u32::try_from(self.max_concurrent_per_account)
                .map_err(|_| WireValidationError::new("settingsMaxConcurrencyOverflow"))?,
-            request_interval_ms: self.request_interval_ms,
            max_waiting_per_key: self.max_waiting_per_key,
            max_waiting_per_account: self.max_waiting_per_account,
            concurrency_wait_timeout_seconds: self.concurrency_wait_timeout_seconds,
@@ -767,12 +771,12 @@ impl RuntimeSettingsFields {
 impl From<gateway_admin::model::settings::RuntimeSettingsValues> for RuntimeSettingsFields {
    fn from(settings: gateway_admin::model::settings::RuntimeSettingsValues) -> Self {
        crate::admin::settings::RuntimeSettingsFields {
+            codex_privacy_policy: settings.codex_privacy_policy,
            request_location_enabled: settings.request_location_enabled,
            request_location: settings.request_location,
            refresh_margin_seconds: settings.refresh_margin_seconds,
            refresh_concurrency: u64::from(settings.refresh_concurrency),
            max_concurrent_per_account: u64::from(settings.max_concurrent_per_account),
-            request_interval_ms: settings.request_interval_ms,
            max_waiting_per_key: settings.max_waiting_per_key,
            max_waiting_per_account: settings.max_waiting_per_account,
            concurrency_wait_timeout_seconds: settings.concurrency_wait_timeout_seconds,
@@ -828,7 +832,6 @@ fn settings_validation_error(field: &'static str) -> WireValidationError {
        "ops_event_retention_days" => "opsEventRetentionDays",
        "refresh_concurrency" => "refreshConcurrency",
        "refresh_margin_seconds" => "refreshMarginSeconds",
-        "request_interval_ms" => "requestIntervalMs",
        "request_location" => "requestLocation",
        "request_location_enabled" => "requestLocationEnabled",
        "responses_max_decompressed_body_bytes" => "responsesMaxDecompressedBodyBytes",
@@ -837,3 +840,23 @@ fn settings_validation_error(field: &'static str) -> WireValidationError {
        _ => "settings",
    })
 }
+
+async fn preview_privacy<S>(
+    State(state): State<S>,
+    _auth: AdminAuth,
+    AdminJson(request): AdminJson<gateway_core::settings::privacy::PrivacyPreviewRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: SessionState + Send + Sync,
+{
+    let result = state
+        .admin_services()
+        .settings()
+        .preview_privacy_policy(request)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(result),
+    ))
+}
@@ -114,7 +114,6 @@ struct SystemUpdateDetailView {
    notes: Option<String>,
    cached: bool,
    update_supported: bool,
-    restart_confirmation_supported: bool,
    unsupported_reason: Option<String>,
    warning: Option<String>,
 }
@@ -134,7 +133,6 @@ impl From<SystemUpdateDetail> for SystemUpdateDetailView {
            notes: detail.notes,
            cached: detail.cached,
            update_supported: detail.update_supported,
-            restart_confirmation_supported: true,
            unsupported_reason: detail.unsupported_reason,
            warning: detail.warning,
        }
@@ -138,7 +138,9 @@ where
        .login(
            payload.into(),
            peer.ip(),
-            session_cookie::value(&headers).as_deref(),
+            session_cookie::refresh_value(&headers)
+                .or_else(|| session_cookie::value(&headers))
+                .as_deref(),
        )
        .await
        .map_err(map_login_error)?;
@@ -149,8 +151,7 @@ where
        )
        .into_response(),
        &headers,
-        &result.session_id,
-        &result.session,
+        &result,
    )
 }

@@ -177,16 +178,18 @@ async fn refresh_session<S>(
 where
    S: SessionState + Send + Sync,
 {
-    let session_id = session_cookie::value(&headers);
-    let session = state
+    let grant = state
        .admin_services()
        .auth()
-        .renew_session(session_id.as_deref())
+        .renew_session(
+            session_cookie::refresh_value(&headers).as_deref(),
+            session_cookie::value(&headers).as_deref(),
+        )
        .await
        .map_err(map_admin_service_error)?;
-    let response = session_response(session.as_ref());
-    if let (Some(session_id), Some(session)) = (session_id, session) {
-        return set_session_cookie(response, &headers, &session_id, &session);
+    let response = session_response(grant.as_ref().map(|grant| &grant.session));
+    if let Some(grant) = grant {
+        return set_session_cookie(response, &headers, &grant);
    }
    // 失效响应不清 Cookie，避免晚到的请求覆盖另一个标签页刚建立的会话
    Ok(response)
@@ -206,32 +209,72 @@ fn session_response(session: Option<&AuthSession>) -> Response {
 fn set_session_cookie(
    mut response: Response,
    headers: &HeaderMap,
-    session_id: &str,
-    session: &AuthSession,
+    grant: &gateway_admin::model::auth::SessionGrant,
 ) -> Result<Response, AdminError> {
-    let max_age = session
-        .expires_at
-        .signed_duration_since(chrono::Utc::now())
-        .num_seconds()
-        .max(1);
-    let expires = session.expires_at.format("%a, %d %b %Y %H:%M:%S GMT");
-    let cookie = format!(
-        "{}={session_id}; {}; Max-Age={max_age}; Expires={expires}",
+    append_cookie(
+        &mut response,
+        headers,
        session_cookie::NAME,
-        session_cookie::attributes(headers)
-    );
-    response.headers_mut().insert(
-        header::SET_COOKIE,
-        HeaderValue::from_str(&cookie).map_err(|_| AdminError::internal())?,
-    );
+        &grant.session_id,
+        Some(grant.session.expires_at),
+    )?;
+    append_cookie(
+        &mut response,
+        headers,
+        session_cookie::REFRESH_NAME,
+        grant.refresh_token.as_deref().unwrap_or_default(),
+        grant
+            .session
+            .renewal
+            .as_ref()
+            .map(|renewal| renewal.expires_at),
+    )?;
    Ok(response)
 }

+fn append_cookie(
+    response: &mut Response,
+    headers: &HeaderMap,
+    name: &str,
+    value: &str,
+    expires_at: Option<chrono::DateTime<chrono::Utc>>,
+) -> Result<(), AdminError> {
+    let attributes = session_cookie::attributes(headers);
+    let path = if name == session_cookie::REFRESH_NAME {
+        "/api/auth"
+    } else {
+        "/"
+    };
+    let lifetime = expires_at.map_or_else(
+        || "Max-Age=0".to_owned(),
+        |expiry| {
+            format!(
+                "Max-Age={}; Expires={}",
+                expiry
+                    .signed_duration_since(chrono::Utc::now())
+                    .num_seconds()
+                    .max(1),
+                expiry.format("%a, %d %b %Y %H:%M:%S GMT")
+            )
+        },
+    );
+    response.headers_mut().append(
+        header::SET_COOKIE,
+        HeaderValue::from_str(&format!(
+            "{name}={value}; Path={path}; {attributes}; {lifetime}"
+        ))
+        .map_err(|_| AdminError::internal())?,
+    );
+    Ok(())
+}
+
 async fn logout<S>(State(state): State<S>, headers: HeaderMap) -> Result<Response, AdminError>
 where
    S: SessionState + Send + Sync,
 {
-    if let Some(session_id) = session_cookie::value(&headers) {
+    if let Some(session_id) =
+        session_cookie::refresh_value(&headers).or_else(|| session_cookie::value(&headers))
+    {
        state
            .admin_services()
            .auth()
@@ -285,15 +328,9 @@ fn clear_session_cookie(
    mut response: Response,
    headers: &HeaderMap,
 ) -> Result<Response, AdminError> {
-    let cookie = format!(
-        "{}=; {}; Max-Age=0",
-        session_cookie::NAME,
-        session_cookie::attributes(headers)
-    );
-    response.headers_mut().insert(
-        header::SET_COOKIE,
-        HeaderValue::from_str(&cookie).map_err(|_| AdminError::internal())?,
-    );
+    for name in [session_cookie::NAME, session_cookie::REFRESH_NAME] {
+        append_cookie(&mut response, headers, name, "", None)?;
+    }
    Ok(response)
 }

@@ -1,10 +1,12 @@
 //! `/healthz` 对 Core、Store 与 Host 关键 worker 健康事实的聚合

-use std::sync::Arc;
+use std::sync::{Arc, Mutex};
 use std::time::Duration;

 use axum::{extract::State, http::StatusCode};
 use futures::future::join_all;
+use gateway_core::diagnostics::{OperationalDiagnostics, OperationalFailure};
+use gateway_core::error::{ErrorDetails, ErrorSource};
 use gateway_core::health::{
    HealthProbe, HealthState, WorkerHealthKey, WorkerHealthSnapshot, WorkerHealthSource,
    WorkerRuntimeState,
@@ -19,6 +21,16 @@ const HEALTH_CHECK_TIMEOUT: Duration = Duration::from_secs(2);
 pub(crate) struct HealthStatus {
    probes: Arc<[Arc<dyn HealthProbe>]>,
    workers: Arc<dyn WorkerHealthSource>,
+    diagnostics: Arc<dyn OperationalDiagnostics>,
+    failures: Arc<Mutex<Vec<HealthFailure>>>,
+}
+
+#[derive(Clone, PartialEq, Eq, Debug, thiserror::Error)]
+#[error("{component} is {state}: {reason}")]
+struct HealthFailure {
+    component: String,
+    state: &'static str,
+    reason: String,
 }

 impl HealthStatus {
@@ -26,31 +38,93 @@ impl HealthStatus {
    pub(crate) fn new(
        probes: Vec<Arc<dyn HealthProbe>>,
        workers: Arc<dyn WorkerHealthSource>,
+        diagnostics: Arc<dyn OperationalDiagnostics>,
    ) -> Self {
        Self {
            probes: probes.into(),
            workers,
+            diagnostics,
+            failures: Arc::default(),
        }
    }

    pub(crate) async fn healthy(&self) -> bool {
-        if !self
+        let mut failures: Vec<_> = self
            .workers
            .snapshot()
-            .iter()
-            .filter(|worker| worker_affects_healthz(worker))
-            .all(worker_is_healthy)
-        {
-            return false;
-        }
-        let checks = self.probes.iter().map(|probe| probe.check());
-        tokio::time::timeout(HEALTH_CHECK_TIMEOUT, join_all(checks))
-            .await
-            .is_ok_and(|states| {
-                states
-                    .into_iter()
-                    .all(|state| matches!(state, HealthState::Healthy))
+            .into_iter()
+            .filter(|worker| worker_affects_healthz(worker) && !worker_is_healthy(worker))
+            .map(|worker| HealthFailure {
+                component: match worker.key {
+                    WorkerHealthKey::Task(id) => format!("worker:{id}"),
+                    WorkerHealthKey::Disabled(kind) => format!("worker:{kind:?}"),
+                },
+                state: "unhealthy",
+                reason: format!(
+                    "state={:?}; last_error={}",
+                    worker.state,
+                    worker.last_error.as_deref().unwrap_or("none")
+                ),
            })
+            .collect();
+        // 逐个探针共享截止时间，保留已完成结果并指出具体超时组件
+        let deadline = tokio::time::Instant::now() + HEALTH_CHECK_TIMEOUT;
+        let checks = self.probes.iter().map(|probe| async move {
+            let (state, reason) = match tokio::time::timeout_at(deadline, probe.check()).await {
+                Ok(HealthState::Healthy) => return None,
+                Ok(HealthState::Degraded(reason)) => ("degraded", reason),
+                Ok(HealthState::Unhealthy(reason)) => ("unhealthy", reason),
+                Err(_) => ("timed_out", "health probe exceeded 2s deadline".to_owned()),
+            };
+            Some(HealthFailure {
+                component: format!("probe:{}", probe.name()),
+                state,
+                reason,
+            })
+        });
+        failures.extend(join_all(checks).await.into_iter().flatten());
+        let healthy = failures.is_empty();
+        let changed = {
+            let mut previous = self
+                .failures
+                .lock()
+                .unwrap_or_else(std::sync::PoisonError::into_inner);
+            let changed = failures
+                .iter()
+                .filter(|failure| !previous.contains(failure))
+                .cloned()
+                .collect::<Vec<_>>();
+            for recovered in previous
+                .iter()
+                .filter(|old| !failures.iter().any(|new| new.component == old.component))
+            {
+                tracing::info!(component = %recovered.component, "health component recovered");
+            }
+            *previous = failures;
+            changed
+        };
+        // 只记录故障变化；使用既有有界观测队列，文件日志失效时仍有独立的运维证据
+        for failure in changed {
+            tracing::warn!(component = %failure.component, state = failure.state, "health check failed");
+            let mut event = OperationalFailure::new(
+                "health",
+                "check",
+                "health_check_failed",
+                "Health check failed",
+            );
+            event.correlation_id = Some(failure.component.clone());
+            event.details =
+                ErrorDetails::capture(Some(&ErrorSource::new(failure.clone())), None, false);
+            if self.diagnostics.record_failure(event).await.is_err() {
+                tracing::warn!("health diagnostic could not be recorded");
+                // 入队失败不能抑制下次探测的记录机会，也不改变本次健康判定
+                self.failures
+                    .lock()
+                    .unwrap_or_else(std::sync::PoisonError::into_inner)
+                    .retain(|previous| previous != &failure);
+            }
+        }
+        healthy
    }
 }

@@ -49,6 +49,7 @@ pub(super) fn config(secret: ClientKeySecret) -> ConfigView {
 #[derive(Serialize)]
 #[serde(rename_all = "camelCase")]
 pub(super) struct OverviewView {
+    analytics: crate::admin::observability::AnalyticsView,
    as_of: DateTime<Utc>,
    as_of_display: String,
    start_time: DateTime<Utc>,
@@ -82,9 +83,9 @@ struct MetricsView {
    requests: u64,
    input_tokens: u64,
    output_tokens: u64,
-    cached_tokens: u64,
-    cache_write_tokens: u64,
-    reasoning_tokens: u64,
+    cached_input_tokens: u64,
+    cache_write_input_tokens: u64,
+    reasoning_output_tokens: u64,
    total_tokens: u64,
    cost_usd: Option<String>,
    cost_incomplete: bool,
@@ -95,9 +96,9 @@ fn metrics(value: &RequestMetrics, costs: &[CurrencyCost], coverage: &CostCovera
        requests: value.request_count,
        input_tokens: value.input_tokens,
        output_tokens: value.output_tokens,
-        cached_tokens: value.cached_tokens,
-        cache_write_tokens: value.cache_write_tokens,
-        reasoning_tokens: value.reasoning_tokens,
+        cached_input_tokens: value.cached_input_tokens,
+        cache_write_input_tokens: value.cache_write_input_tokens,
+        reasoning_output_tokens: value.reasoning_output_tokens,
        total_tokens: value.total_tokens,
        cost_usd: costs
            .iter()
@@ -121,6 +122,10 @@ struct TrendPointView {
 pub(super) fn overview(value: KeyUsageOverview, time: crate::time::TimePresenter) -> OverviewView {
    let key = value.key;
    OverviewView {
+        analytics: crate::admin::observability::analytics_view(
+            value.overview.analytics.clone(),
+            time,
+        ),
        as_of: value.overview.range.end,
        as_of_display: time.time(&value.overview.range.end),
        start_time: value.overview.range.start,
@@ -201,6 +206,20 @@ pub(super) struct RecordView {
 #[derive(Default, Serialize)]
 #[serde(rename_all = "camelCase")]
 struct OutputTimingView {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    upstream_response_ms: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    upstream_api_overhead_ms: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    upstream_engine_ms: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    upstream_engine_iapi_ttft_ms: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    upstream_engine_service_ttft_ms: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    upstream_engine_iapi_tbt_ms: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    upstream_engine_service_tbt_ms: Option<f64>,
    #[serde(skip_serializing_if = "Option::is_none")]
    first_event_ms: Option<u64>,
    #[serde(skip_serializing_if = "Option::is_none")]
@@ -226,6 +245,13 @@ fn success_record(value: UsageListRecord, time: crate::time::TimePresenter) -> R
        latency_ms: value.latency_ms,
        first_token_latency_ms: value.first_token_ms,
        latency_details: OutputTimingView {
+            upstream_response_ms: value.upstream_response_ms,
+            upstream_api_overhead_ms: value.upstream_api_overhead_ms,
+            upstream_engine_ms: value.upstream_engine_ms,
+            upstream_engine_iapi_ttft_ms: value.upstream_engine_iapi_ttft_ms,
+            upstream_engine_service_ttft_ms: value.upstream_engine_service_ttft_ms,
+            upstream_engine_iapi_tbt_ms: value.upstream_engine_iapi_tbt_ms,
+            upstream_engine_service_tbt_ms: value.upstream_engine_service_tbt_ms,
            first_event_ms: value.first_event_ms,
            first_reasoning_ms: value.first_reasoning_ms,
            first_text_ms: value.first_text_ms,
@@ -138,7 +138,7 @@ impl ApiBundle {
    }

    /// 内部调用使用同一总路由；组合根持有强引用，Runtime 只保存 Weak
-    pub fn dispatcher(&self) -> Arc<dyn gateway_core::middleware::http::Dispatcher> {
+    pub fn dispatcher(&self) -> Arc<dyn gateway_core::engine::middleware::http::Dispatcher> {
        Arc::new(middleware::RouterDispatcher {
            router: middleware::wrap(
                self.router.clone(),
@@ -190,7 +190,7 @@ pub fn initialize(
    let state = ApiState {
        admin,
        openai: OpenAiService::new(execution, lifecycle),
-        health: HealthStatus::new(probes, worker_health),
+        health: HealthStatus::new(probes, worker_health, diagnostics.clone()),
    };
    let index = config.asset_directory.join("index.html");
    let mut router = Router::new()
@@ -17,23 +17,21 @@ use axum::{
    http::{HeaderName, HeaderValue, Request, StatusCode},
    response::{IntoResponse as _, Response},
 };
-use gateway_core::{
-    engine::middleware::FrozenMiddlewarePlan,
-    lifecycle::CancellationToken,
-    middleware::{
-        compose,
-        http::{self as contract, Settings},
-    },
-};
+use gateway_core::engine::middleware::FrozenMiddlewarePlan;
+use gateway_core::engine::middleware::http as contract;
+use gateway_core::engine::middleware::http::Settings;
+use gateway_core::lifecycle::CancellationToken;
+use gateway_core::middleware::compose;
 use http_body::{Body as HttpBody, Frame, SizeHint};
 use http_body_util::BodyExt as _;
 use tokio::time::Instant;
 use tower::ServiceExt as _;

 tokio::task_local! { static CURRENT: contract::Context; }
-tokio::task_local! { static SETTINGS: Option<gateway_core::settings::RequestSettings>; }
+tokio::task_local! { static SETTINGS: Option<gateway_core::routing::request_settings::RequestSettings>; }

-pub(crate) fn current_settings() -> Option<gateway_core::settings::RequestSettings> {
+pub(crate) fn current_settings() -> Option<gateway_core::routing::request_settings::RequestSettings>
+{
    SETTINGS.try_with(Clone::clone).ok().flatten()
 }

@@ -52,7 +50,7 @@ pub(crate) async fn scope<T>(
 }

 pub(crate) type SettingsSource =
-    Arc<dyn Fn() -> Option<gateway_core::settings::RequestSettings> + Send + Sync>;
+    Arc<dyn Fn() -> Option<gateway_core::routing::request_settings::RequestSettings> + Send + Sync>;

 pub(crate) struct RouterDispatcher {
    pub(crate) router: Router,
@@ -60,7 +58,7 @@ pub(crate) struct RouterDispatcher {
 }

 impl contract::Dispatcher for RouterDispatcher {
-    fn request_settings(&self) -> Option<gateway_core::settings::RequestSettings> {
+    fn request_settings(&self) -> Option<gateway_core::routing::request_settings::RequestSettings> {
        (self.settings)()
    }

@@ -195,12 +193,12 @@ async fn handle(
    });
    request.extensions_mut().insert(guard.clone());
    request.extensions_mut().insert(context.clone());
-    let service_context = gateway_admin::service::Origin {
+    let service_context = gateway_admin::public_service::Origin {
        request_id: context.request_id.clone(),
        call_id: context.call_id.clone(),
        cancellation: context.cancellation.clone(),
        extensions: context.extensions.clone(),
-        plan: gateway_admin::service::Plan::Frozen(plan.clone()),
+        plan: gateway_admin::public_service::Plan::Frozen(plan.clone()),
    };
    request
        .extensions_mut()
@@ -220,7 +218,7 @@ async fn handle(
                    terminal_context,
                    SETTINGS.scope(
                        settings,
-                        gateway_admin::service::scope(
+                        gateway_admin::public_service::scope(
                            service_context,
                            dispatch(router, request.map(Body::new), started),
                        ),
@@ -230,6 +228,8 @@ async fn handle(
            Ok(response.map(|body| body.map_err(|error| Box::new(error) as _).boxed_unsync()))
        })
    });
+    let request_id = context.request_id.clone();
+    let call_id = context.call_id.clone();
    let result = match plan {
        Some(plan) => plan.handle_http(context, request, next).await,
        None => next.run(request).await,
@@ -253,7 +253,18 @@ async fn handle(
                    tokio::select! {
                        biased;
                        () = cancellation.cancelled() => {},
-                        _ = task => {},
+                        result = task => {
+                            if let Err(contract::upgrade::SessionError::Failed { kind, plugin_instance_id }) = result {
+                                tracing::warn!(
+                                    event = "middleware.session.failed",
+                                    request_id,
+                                    call_id,
+                                    plugin_instance_id,
+                                    kind,
+                                    "升级后的中间件会话失败"
+                                );
+                            }
+                        },
                    }
                });
            }
@@ -14,15 +14,14 @@ use futures::{
    future::BoxFuture,
    stream::{SplitSink, SplitStream},
 };
-use gateway_core::{
-    engine::middleware::{FrozenMiddlewarePlan, MiddlewareError, MiddlewareHeader},
-    lifecycle::CancellationToken,
-    middleware::{
-        compose,
-        http::{self as http, upgrade},
-        websocket as core,
-    },
-};
+use gateway_core::engine::middleware::FrozenMiddlewarePlan;
+use gateway_core::engine::middleware::MiddlewareError;
+use gateway_core::engine::middleware::MiddlewareHeader;
+use gateway_core::engine::middleware::http;
+use gateway_core::engine::middleware::http::upgrade;
+use gateway_core::engine::middleware::websocket as core;
+use gateway_core::lifecycle::CancellationToken;
+use gateway_core::middleware::compose;
 use http_body_util::BodyExt as _;

 pub(super) struct Upgrade {
@@ -84,30 +84,6 @@ impl ClientApiKeyAuthError {
    }
 }

-/// 从请求头提取 Bearer Client API key
-///
-/// # Errors
-///
-/// Header 缺失、Bearer 语法错误或 Key 不能作为 HTTP Bearer 值时返回稳定错误
-pub fn bearer_client_api_key(headers: &HeaderMap) -> Result<&str, ClientApiKeyAuthError> {
-    let raw = headers
-        .get(AUTHORIZATION)
-        .ok_or(ClientApiKeyAuthError::MissingAuthorization)?
-        .to_str()
-        .map_err(|_| ClientApiKeyAuthError::MalformedAuthorization)?;
-    let token = raw
-        .strip_prefix("Bearer ")
-        .ok_or(ClientApiKeyAuthError::MalformedAuthorization)?
-        .trim();
-    if token.is_empty() {
-        return Err(ClientApiKeyAuthError::MalformedAuthorization);
-    }
-    if gateway_core::policy::PlaintextClientApiKey::validate(token).is_err() {
-        return Err(ClientApiKeyAuthError::InvalidKeyFormat);
-    }
-    Ok(token)
-}
-
 pub(crate) async fn authenticate_client(
    service: &OpenAiService,
    headers: &HeaderMap,
@@ -62,7 +62,7 @@ where
                let started = match service
                    .start_prepared_provider_endpoint(
                        prepared, operation,
-                        // 图像/搜索等原生端点没有对应的上游模型权限。
+                        // 原生端点的模型语义由 Provider 从正文提取并检查账号政策
                        None, client_ip, user_agent, endpoint,
                    )
                    .await
@@ -19,6 +19,9 @@ use gateway_core::{
    error::GatewayError,
 };

+pub(crate) const SSE_KEEPALIVE_INTERVAL: std::time::Duration = std::time::Duration::from_secs(15);
+pub(crate) const SSE_KEEPALIVE_FRAME: Bytes = Bytes::from_static(b": keep-alive\n\n");
+
 /// 只读目录/用量与协议错误共用的单帧响应；没有 Provider attempt 或计量副作用
 pub(crate) async fn buffered_response(
    protocol: &str,
@@ -161,8 +164,8 @@ pub(crate) async fn into_http_response(
        let chunk = tokio::select! {
            biased;
            chunk = stream.next() => chunk?,
-            () = tokio::time::sleep(std::time::Duration::from_secs(15)), if keep_alive => {
-                Ok(Bytes::from_static(b": keep-alive\n\n"))
+            () = tokio::time::sleep(SSE_KEEPALIVE_INTERVAL), if keep_alive => {
+                Ok(SSE_KEEPALIVE_FRAME)
            }
        };
        Some((chunk, stream))
@@ -4,6 +4,9 @@ mod http;
 mod request;
 mod session;

-pub(crate) use http::{ExpectedBody, buffered_response, error_response, into_http_response};
+pub(crate) use http::{
+    ExpectedBody, SSE_KEEPALIVE_FRAME, SSE_KEEPALIVE_INTERVAL, buffered_response, error_response,
+    into_http_response,
+};
 pub(crate) use request::{RequestInput, invoke_request, query_response, request_parts};
 pub(crate) use session::{PendingExecution, finalize_session, pending_execution_response};
@@ -86,7 +86,9 @@ async fn models_response(
            .iter()
            .enumerate()
            .map(|(index, entry)| match entry {
-                PublicModelDescriptor::Adapted(profile) => Ok(codex_model_json(profile, index)),
+                PublicModelDescriptor::Adapted(profile) => {
+                    Ok(adapted_codex_model_json(profile, index))
+                }
                PublicModelDescriptor::Native { model, payload } => {
                    if payload.protocol() != "codex" {
                        return Err(());
@@ -192,7 +194,7 @@ fn openai_model_json(id: &str) -> Value {
    })
 }

-fn codex_model_json(profile: &PublicModelProfile, index: usize) -> Value {
+fn adapted_codex_model_json(profile: &PublicModelProfile, index: usize) -> Value {
    let id = profile.model().as_str();
    let presentation = profile.presentation();
    let reasoning_levels = presentation
@@ -265,6 +267,8 @@ fn codex_model_json(profile: &PublicModelProfile, index: usize) -> Value {
        "experimental_supported_tools": [],
        "input_modalities": input_modalities,
        "supports_search_tool": presentation.search_tool(),
+        // 通用画像没有 Responses Lite 支持依据，避免客户端启用未经声明的协议行为
+        // 原生目录由 Native 分支保留上游字段，不经过此处
        "use_responses_lite": false,
    })
 }
@@ -141,6 +141,7 @@ pub(crate) async fn execute_prepared_responses(
    let cancellation = prepared.cancellation();
    let started_request_id = Arc::new(OnceLock::new());
    let terminal_request_id = Arc::clone(&started_request_id);
+    let (admitted, keepalive) = tokio::sync::oneshot::channel();
    let mut middleware_headers = headers.clone();
    // 中间件正文已经由入口按上限解压；传输编码和旧长度不能与改写后的正文混用
    middleware_headers.remove(CONTENT_ENCODING);
@@ -213,37 +214,45 @@ pub(crate) async fn execute_prepared_responses(
                    .session
                    .trace()
                    .capture("client.request.body", &request_body);
+                let _ = admitted.send(started.session.response_commit());
                execution_middleware_response(started, connection_guard, terminal_validation).await
            })
        }),
    );
-    let middleware = if let Some(authorization) = authorization.as_ref() {
-        match await_with_authorization(middleware, authorization, &cancellation).await {
-            Ok(result) => result,
-            Err(error) => Err(MiddlewareError::Gateway(error)),
+    let response = async move {
+        let middleware = if let Some(authorization) = authorization.as_ref() {
+            match await_with_authorization(middleware, authorization, &cancellation).await {
+                Ok(result) => result,
+                Err(error) => Err(MiddlewareError::Gateway(error)),
+            }
+        } else {
+            middleware.await
+        };
+        let expected = if stream {
+            ExpectedBody::Sse
+        } else {
+            ExpectedBody::SingleJson
+        };
+        match middleware {
+            Ok(response) => {
+                let response = if let Some(authorization) = authorization {
+                    authorized_middleware_response(response, authorization, cancellation)
+                } else {
+                    response
+                };
+                into_http_response(
+                    validated_middleware_response(response, validation, stream),
+                    expected,
+                )
+                .await
+            }
+            Err(error) => error_response(error),
        }
-    } else {
-        middleware.await
    };
-    let expected = if stream {
-        ExpectedBody::Sse
+    let response = if stream {
+        super::keepalive::response(response, keepalive).await
    } else {
-        ExpectedBody::SingleJson
-    };
-    let response = match middleware {
-        Ok(response) => {
-            let response = if let Some(authorization) = authorization {
-                authorized_middleware_response(response, authorization, cancellation)
-            } else {
-                response
-            };
-            into_http_response(
-                validated_middleware_response(response, validation, stream),
-                expected,
-            )
-            .await
-        }
-        Err(error) => error_response(error),
+        response.await
    };
    super::super::with_model_request_id(response, started_request_id.get().unwrap_or(&request_id))
 }
@@ -519,16 +528,24 @@ pub async fn stream_execution_response(
    session: Box<dyn ExecutionSession>,
    connection_guard: Option<Box<dyn ConnectionGuard>>,
 ) -> Response {
-    match streaming_execution_middleware_response(
-        session,
-        connection_guard,
-        ResponseValidationFacts::default(),
+    let (admitted, keepalive) = tokio::sync::oneshot::channel();
+    let _ = admitted.send(session.response_commit());
+    super::keepalive::response(
+        async move {
+            match streaming_execution_middleware_response(
+                session,
+                connection_guard,
+                ResponseValidationFacts::default(),
+            )
+            .await
+            {
+                Ok(response) => into_http_response(response, ExpectedBody::Sse).await,
+                Err(error) => error_response(error),
+            }
+        },
+        keepalive,
    )
    .await
-    {
-        Ok(response) => into_http_response(response, ExpectedBody::Sse).await,
-        Err(error) => error_response(error),
-    }
 }

 fn validated_middleware_response(
@@ -0,0 +1,151 @@
+//! 准入成功后覆盖 Responses 首帧等待；已发心跳的 HTTP 错误转为流内失败
+
+use std::future::Future;
+
+use axum::{
+    body::{Body, BodyDataStream, Bytes, to_bytes},
+    http::{HeaderValue, StatusCode, header},
+    response::Response,
+};
+use futures::{StreamExt as _, future::BoxFuture, stream};
+use gateway_core::engine::execution::ResponseCommit;
+use gateway_protocol::openai::sse::{
+    DONE_SSE_FRAME, encode_sse_event, response_failed_sse_data_from_error_event,
+    response_failed_sse_data_with_id,
+};
+use serde_json::Value;
+use tokio::sync::oneshot;
+
+use crate::openai::middleware::{SSE_KEEPALIVE_FRAME, SSE_KEEPALIVE_INTERVAL};
+
+pub(super) async fn response(
+    response: impl Future<Output = Response> + Send + 'static,
+    admitted: oneshot::Receiver<ResponseCommit>,
+) -> Response {
+    let mut response = Box::pin(response);
+    // 鉴权、模型门禁和准入失败仍保留原 HTTP 状态，不提前建立 SSE
+    let commit = tokio::select! {
+        biased;
+        response = &mut response => return response,
+        admitted = admitted => match admitted {
+            Ok(commit) => commit,
+            Err(_) => return response.await,
+        },
+    };
+    tokio::select! {
+        biased;
+        response = &mut response => return response,
+        () = tokio::time::sleep(SSE_KEEPALIVE_INTERVAL) => {}
+    }
+    if !commit.record(Some(StatusCode::OK.as_u16())) {
+        return response.await;
+    }
+    let pending = PendingResponse::Waiting(response);
+    let stream = stream::once(async { Ok::<_, axum::Error>(SSE_KEEPALIVE_FRAME) })
+        .chain(stream::try_unfold(pending, PendingResponse::next));
+    let mut response = Response::new(Body::from_stream(stream));
+    let headers = response.headers_mut();
+    headers.insert(
+        header::CONTENT_TYPE,
+        HeaderValue::from_static("text/event-stream"),
+    );
+    headers.insert(
+        header::CACHE_CONTROL,
+        HeaderValue::from_static("no-cache, no-transform"),
+    );
+    headers.insert("x-accel-buffering", HeaderValue::from_static("no"));
+    response
+}
+
+enum PendingResponse {
+    Waiting(BoxFuture<'static, Response>),
+    Streaming(BodyDataStream),
+}
+
+impl PendingResponse {
+    async fn next(mut self) -> Result<Option<(Bytes, Self)>, axum::Error> {
+        loop {
+            match &mut self {
+                Self::Waiting(response) => {
+                    // 心跳只轮询同一个 future，不取消重建首帧等待或插件调用
+                    let response = tokio::select! {
+                        biased;
+                        response = response => response,
+                        () = tokio::time::sleep(SSE_KEEPALIVE_INTERVAL) => return Ok(Some((SSE_KEEPALIVE_FRAME, self))),
+                    };
+                    let sse = response.status().is_success()
+                        && response
+                            .headers()
+                            .get(header::CONTENT_TYPE)
+                            .and_then(|value| value.to_str().ok())
+                            .and_then(|value| value.split(';').next())
+                            .is_some_and(|value| {
+                                value.trim().eq_ignore_ascii_case("text/event-stream")
+                            });
+                    let body = if sse {
+                        response.into_body()
+                    } else {
+                        stream_failure(response).await
+                    };
+                    // 正式响应的正文已经带有交付期心跳，后续只转交，不叠加定时器
+                    self = Self::Streaming(body.into_data_stream());
+                }
+                Self::Streaming(body) => {
+                    return body
+                        .next()
+                        .await
+                        .transpose()
+                        .map(|chunk| chunk.map(|chunk| (chunk, self)));
+                }
+            }
+        }
+    }
+}
+
+async fn stream_failure(response: Response) -> Body {
+    let status = response.status();
+    let retry_after = response
+        .headers()
+        .get(header::RETRY_AFTER)
+        .and_then(|value| value.to_str().ok())
+        .map(ToOwned::to_owned);
+    let bytes = to_bytes(response.into_body(), usize::MAX)
+        .await
+        .unwrap_or_default();
+    let json = serde_json::from_slice::<Value>(&bytes).ok();
+    let raw_message = std::str::from_utf8(&bytes)
+        .ok()
+        .map(str::trim)
+        .filter(|text| !text.is_empty());
+    // 已完成客户端错误投影的对象原样保留，包括重试建议和策略错误的扩展字段
+    let mut data = json
+        .as_ref()
+        .and_then(|json| response_failed_sse_data_from_error_event(None, None, json))
+        .unwrap_or_else(|| {
+            response_failed_sse_data_with_id(
+                None,
+                "server_error",
+                "upstream_error",
+                raw_message.unwrap_or_else(|| {
+                    status
+                        .canonical_reason()
+                        .unwrap_or("Response stream failed")
+                }),
+            )
+        });
+    // HTTP 头已提交，按官方 SSE 错误合同保留允许下发的重试建议
+    if let Some(retry_after) = retry_after
+        && let Some(error) = data["response"]["error"].as_object_mut()
+        && let Some(headers) = error
+            .entry("headers")
+            .or_insert_with(|| serde_json::json!({}))
+            .as_object_mut()
+    {
+        headers
+            .entry("retry-after")
+            .or_insert(Value::String(retry_after));
+    }
+    let mut event = encode_sse_event("response.failed", &data.to_string());
+    event.push_str(DONE_SSE_FRAME);
+    Body::from(event)
+}
@@ -2,6 +2,7 @@

 mod error;
 mod http;
+mod keepalive;
 mod request;
 mod response;
 mod validation;
@@ -95,15 +95,25 @@ impl OpenAiRequestHeaders {
        }
    }

-    /// 独立端点只消费会话身份与 turn metadata，不携带 Responses 的连接状态
+    /// 独立端点保留业务扩展头与会话身份，不携带 Responses 的连接状态
    pub(crate) fn session_context(&self) -> Map<String, Value> {
        let mut context = Map::new();
        insert_protocol_context(&mut context, "session_id", self.session_id.as_ref());
        insert_protocol_context(&mut context, "thread_id", self.thread_id.as_ref());
        insert_protocol_context(&mut context, "turn_metadata", self.turn_metadata.as_ref());
+        self.insert_passthrough_headers(&mut context);
        context
    }

+    fn insert_passthrough_headers(&self, context: &mut Map<String, Value>) {
+        if !self.passthrough_headers.is_empty() {
+            context.insert(
+                PASSTHROUGH_HEADERS_CONTEXT_KEY.to_owned(),
+                Value::Array(self.passthrough_headers.clone()),
+            );
+        }
+    }
+
    fn protocol_context(
        &self,
        use_websocket: Option<bool>,
@@ -153,12 +163,7 @@ impl OpenAiRequestHeaders {
        insert_protocol_context(&mut context, "turn_id", self.turn_id.as_ref());
        insert_protocol_context(&mut context, "responses_lite", self.responses_lite.as_ref());
        insert_protocol_context(&mut context, "memgen_request", self.memgen_request.as_ref());
-        if !self.passthrough_headers.is_empty() {
-            context.insert(
-                PASSTHROUGH_HEADERS_CONTEXT_KEY.to_owned(),
-                Value::Array(self.passthrough_headers.clone()),
-            );
-        }
+        self.insert_passthrough_headers(&mut context);
        if let Some(use_websocket) = use_websocket {
            context.insert("use_websocket".to_owned(), Value::Bool(use_websocket));
        }
@@ -47,7 +47,7 @@ impl OpenAiResponsesEncoder {
            return Vec::new();
        };
        self.observe_wire(wire);
-        let projected = client_failure_payload(wire);
+        let projected = client_payload(wire);
        let data = projected.as_ref().unwrap_or_else(|| wire.data());
        // 当前 Codex 不消费 Responses `error` event，会在 EOF 时丢失失败原因
        // 在客户端 SSE 边界统一投影成它能识别的 `response.failed`
@@ -70,22 +70,29 @@ impl OpenAiResponsesEncoder {
        {
            return vec![raw_sse_frame.clone()];
        }
+        let data = if projected.is_none() {
+            wire.raw_websocket_message()
+                .map(str::to_owned)
+                .unwrap_or_else(|| data.to_string())
+        } else {
+            data.to_string()
+        };
        vec![Bytes::from(encode_sse_event_with_metadata(
            effective_event_type(wire).unwrap_or_default(),
-            &data.to_string(),
+            &data,
            wire.sse_id(),
            wire.sse_retry(),
        ))]
    }

-    /// 消费一个 Provider event，并返回 WebSocket JSON messages
+    /// 消费一个 Provider event，并返回完整 WebSocket 文本消息
    pub fn push_websocket(&mut self, event: &ProviderEvent) -> Vec<String> {
        self.observe_canonical_identity(event);
-        let Some(wire) = openai_wire(event).filter(|wire| wire.has_json_data()) else {
+        let Some(wire) = openai_wire(event) else {
            return Vec::new();
        };
        self.observe_wire(wire);
-        let projected = client_failure_payload(wire);
+        let projected = client_payload(wire);
        let data = projected.as_ref().unwrap_or_else(|| wire.data());
        // WS 客户端只对它无法消费的裸 `error` 帧做投影：codex 的 WS 端点
        // 会静默忽略缺少 status 且不含内置可重试错误码的 `error` 帧，客户
@@ -104,6 +111,14 @@ impl OpenAiResponsesEncoder {
        {
            return vec![data.to_string()];
        }
+        if projected.is_none()
+            && let Some(raw) = wire.raw_websocket_message()
+        {
+            return vec![raw.to_owned()];
+        }
+        if !wire.has_json_data() {
+            return Vec::new();
+        }
        vec![data.to_string()]
    }

@@ -248,15 +263,43 @@ fn effective_event_type(wire: &ProtocolWireEvent) -> Option<&str> {
        .or_else(|| wire.data().get("type").and_then(Value::as_str))
 }

-fn client_failure_payload(wire: &ProtocolWireEvent) -> Option<Value> {
+fn client_payload(wire: &ProtocolWireEvent) -> Option<Value> {
    if matches!(
        effective_event_type(wire),
        Some("error" | "response.failed")
    ) {
-        capacity_error_for_client(wire.data())
-    } else {
-        None
+        return capacity_error_for_client(wire.data());
    }
+    if !matches!(
+        effective_event_type(wire),
+        Some("response.metadata" | "codex.response.metadata")
+    ) {
+        return None;
+    }
+    let headers = wire.data().get("headers")?.as_object()?;
+    let connection_options: Vec<String> = headers
+        .iter()
+        .filter(|(name, _)| name.eq_ignore_ascii_case("connection"))
+        .flat_map(|(_, value)| match value {
+            Value::Array(values) => values.iter().filter_map(Value::as_str).collect::<Vec<_>>(),
+            _ => value.as_str().into_iter().collect(),
+        })
+        .flat_map(|value| value.split(','))
+        .map(|name| name.trim().to_ascii_lowercase())
+        .collect();
+    if headers
+        .keys()
+        .all(|name| super::response_header_is_forwardable(name, &connection_options))
+    {
+        return None;
+    }
+    // 只剥离既有响应头隔离策略禁止的字段，metadata 业务扩展保持不透明
+    let mut projected = wire.data().clone();
+    projected
+        .get_mut("headers")?
+        .as_object_mut()?
+        .retain(|name, _| super::response_header_is_forwardable(name, &connection_options));
+    Some(projected)
 }

 /// 判断 WS 上游的 `error` 帧是否已经是客户端可直接消费的形状
@@ -209,6 +209,11 @@ impl ResponsesDeliveryValidator {
        transformed: bool,
        facts: &ResponseValidationFacts,
    ) -> Result<(), ResponseValidationError> {
+        // 未改写的未知载荷不参与本地关联判断，不能因旁路解析失败截断原流
+        // 插件实际改写的载荷仍须满足交付合同
+        if parsed.is_err() && !transformed {
+            return Ok(());
+        }
        if !self.active && !transformed {
            if parsed.and_then(|frame| self.state.apply(frame)).is_err() {
                self.invalid_prefix = true;
@@ -253,7 +258,7 @@ impl ResponsesDeliveryValidator {
                    return Err(ResponseValidationError);
                }
            }
-            ParsedFrame::Event { .. } | ParsedFrame::Done => {}
+            ParsedFrame::Event { .. } | ParsedFrame::Done | ParsedFrame::NonEvent => {}
        }
        self.state.apply(parsed)
    }
@@ -292,6 +297,7 @@ impl ResponsesDeliveryValidator {
 enum ParsedFrame {
    Event { event_type: String, value: Value },
    Done,
+    NonEvent,
 }

 impl ParsedFrame {
@@ -301,6 +307,10 @@ impl ParsedFrame {
            return Ok(Self::Done);
        }
        let mut events = parse_sse_events(frame).map_err(|_| ResponseValidationError)?;
+        // 注释和仅含 SSE 元数据的帧不承载响应业务事实
+        if events.is_empty() {
+            return Ok(Self::NonEvent);
+        }
        if events.len() != 1 {
            return Err(ResponseValidationError);
        }
@@ -363,6 +373,9 @@ struct DeliveryState {

 impl DeliveryState {
    fn apply(&mut self, frame: ParsedFrame) -> Result<(), ResponseValidationError> {
+        if matches!(frame, ParsedFrame::NonEvent) {
+            return Ok(());
+        }
        if self.done {
            return Err(ResponseValidationError);
        }
@@ -0,0 +1,171 @@
+//! 下游连接的帧、写入结果、退出原因与队列预算
+
+use std::{sync::Arc, time::Duration};
+use thiserror::Error;
+use tokio::sync::OwnedSemaphorePermit;
+
+pub(super) const OUTBOUND_COMMAND_BUFFER: usize = 32;
+pub(super) const INBOUND_EVENT_BUFFER: usize = 32;
+pub(super) const DOWNSTREAM_WRITE_TIMEOUT: Duration = Duration::from_secs(5 * 60);
+pub(super) const DOWNSTREAM_CLOSE_TIMEOUT: Duration = Duration::from_secs(1);
+pub(super) const CONNECTION_MAX_AGE: Duration = Duration::from_secs(60 * 60);
+pub(super) const DOWNSTREAM_PING_INTERVAL: Duration = Duration::from_secs(25);
+
+/// WebSocket pump 的写入与生命周期预算
+#[derive(Clone, Copy)]
+pub struct ConnectionConfig {
+    pub(super) write_timeout: Duration,
+    pub(super) max_age: Duration,
+}
+
+impl ConnectionConfig {
+    /// 生产环境固定预算
+    pub const PRODUCTION: Self = Self {
+        write_timeout: DOWNSTREAM_WRITE_TIMEOUT,
+        max_age: CONNECTION_MAX_AGE,
+    };
+}
+
+/// 业务层可观察的客户端输入；Ping/Pong 始终由 pump 消费
+pub enum ConnectionEvent {
+    Text(String),
+    Binary,
+    Expired,
+    Exited(PumpExitReason),
+}
+
+/// 接收队列与活动期间暂存的请求共用容量；移动帧不释放它占用的名额
+pub(in super::super) struct PendingConnectionEvent {
+    pub(in super::super) event: ConnectionEvent,
+    pub(super) _permit: Option<OwnedSemaphorePermit>,
+}
+
+impl PendingConnectionEvent {
+    pub(super) fn exited(reason: PumpExitReason) -> Self {
+        Self {
+            event: ConnectionEvent::Exited(reason),
+            _permit: None,
+        }
+    }
+}
+
+/// 下游写入阶段；名称刻意使用 write，而不是暗示客户端已消费的 delivery
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum FramePhase {
+    Metadata,
+    First,
+    Data,
+    Terminal,
+    FirstAndTerminal,
+    Error,
+    ConnectionLimit,
+    Close,
+}
+
+impl FramePhase {
+    pub(super) const fn as_str(self) -> &'static str {
+        match self {
+            Self::Metadata => "metadata",
+            Self::First => "first",
+            Self::Data => "data",
+            Self::Terminal => "terminal",
+            Self::FirstAndTerminal => "first_and_terminal",
+            Self::Error => "error",
+            Self::ConnectionLimit => "connection_limit",
+            Self::Close => "close",
+        }
+    }
+
+    pub(super) const fn is_milestone(self) -> bool {
+        matches!(
+            self,
+            Self::First
+                | Self::Terminal
+                | Self::FirstAndTerminal
+                | Self::Error
+                | Self::ConnectionLimit
+                | Self::Close
+        )
+    }
+}
+
+/// 一次下游写入的请求归属与协议阶段
+#[derive(Clone)]
+pub struct WriteContext {
+    pub(super) request_id: Option<Arc<str>>,
+    pub(super) phase: FramePhase,
+}
+
+impl WriteContext {
+    /// 创建归属于某个请求的写入上下文
+    #[must_use]
+    pub fn request(request_id: &Arc<str>, phase: FramePhase) -> Self {
+        Self {
+            request_id: Some(Arc::clone(request_id)),
+            phase,
+        }
+    }
+
+    /// 创建连接级写入上下文
+    #[must_use]
+    pub const fn connection(phase: FramePhase) -> Self {
+        Self {
+            request_id: None,
+            phase,
+        }
+    }
+}
+
+/// WebSocket pump 停止的稳定原因
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum PumpExitReason {
+    ClientClose,
+    PeerEof,
+    ReadError,
+    WriteError,
+    WriteTimeout,
+    LifecycleShutdown,
+    ConnectionMaxAge,
+    CoordinatorDropped,
+    InboundOverload,
+    ServerClose,
+    PumpStopped,
+    MiddlewareFailed,
+}
+
+impl PumpExitReason {
+    pub(in super::super) const fn as_str(self) -> &'static str {
+        match self {
+            Self::ClientClose => "client_close",
+            Self::PeerEof => "peer_eof",
+            Self::ReadError => "read_error",
+            Self::WriteError => "write_error",
+            Self::WriteTimeout => "write_timeout",
+            Self::LifecycleShutdown => "lifecycle_shutdown",
+            Self::ConnectionMaxAge => "connection_max_age",
+            Self::CoordinatorDropped => "coordinator_dropped",
+            Self::InboundOverload => "inbound_overload",
+            Self::ServerClose => "server_close",
+            Self::PumpStopped => "pump_stopped",
+            Self::MiddlewareFailed => "middleware_failed",
+        }
+    }
+}
+
+/// 下游 WebSocket 写入失败
+#[derive(Debug, Error)]
+pub enum ConnectionWriteError {
+    #[error("downstream WebSocket pump is closed")]
+    Closed,
+    #[error("downstream WebSocket write timed out after {timeout:?}")]
+    Timeout { timeout: Duration },
+    #[error("downstream WebSocket transport write failed: {message}")]
+    Transport { message: String },
+}
+
+/// 只有实际 transport 写入才记为 Written；插件丢弃消息不伪造写入成功
+#[derive(Clone, Copy, Debug, PartialEq, Eq)]
+pub enum WriteOutcome {
+    Written,
+    Suppressed,
+}
@@ -0,0 +1,362 @@
+//! 协调层持有的连接句柄与唯一 pump 启动入口
+
+use super::{
+    frame::*,
+    pump::run_pump,
+    state::{ConnectionCommand, ConnectionStats},
+};
+use axum::extract::ws::{CloseFrame, Message, WebSocket, close_code};
+use futures::{Sink, Stream};
+use gateway_core::{
+    engine::middleware::{FrozenMiddlewarePlan, MiddlewareHeader},
+    lifecycle::CancellationToken,
+};
+use std::{
+    collections::VecDeque,
+    fmt,
+    sync::{
+        Arc,
+        atomic::{AtomicBool, Ordering},
+    },
+    time::Duration,
+};
+use tokio::{
+    sync::{mpsc, oneshot},
+    task::JoinHandle,
+    time::{Instant, timeout},
+};
+
+/// 协调层持有的单 owner WebSocket 连接句柄
+pub struct ResponsesWebSocketConnection {
+    connection_id: Arc<str>,
+    opened_at: Instant,
+    expired: Arc<AtomicBool>,
+    commands: Option<mpsc::Sender<ConnectionCommand>>,
+    incoming: mpsc::Receiver<PendingConnectionEvent>,
+    deferred: VecDeque<PendingConnectionEvent>,
+    exited: oneshot::Receiver<PumpExitReason>,
+    pump_task: Option<JoinHandle<()>>,
+    stats: Arc<ConnectionStats>,
+    config: ConnectionConfig,
+    exit_reason: Option<PumpExitReason>,
+}
+
+impl ResponsesWebSocketConnection {
+    pub(in super::super) fn new(
+        socket: WebSocket,
+        connection_id: String,
+        cancellation: CancellationToken,
+        middleware: Option<FrozenMiddlewarePlan>,
+        headers: Arc<[MiddlewareHeader]>,
+    ) -> Self {
+        spawn_connection(
+            socket,
+            Arc::<str>::from(connection_id),
+            cancellation,
+            ConnectionConfig::PRODUCTION,
+            middleware,
+            headers,
+        )
+    }
+
+    pub(in super::super) fn id(&self) -> &str {
+        &self.connection_id
+    }
+
+    /// 返回连接是否已经达到生命周期上限
+    #[must_use]
+    pub fn is_expired(&self) -> bool {
+        self.expired.load(Ordering::Acquire)
+    }
+
+    pub(in super::super) fn age(&self) -> Duration {
+        self.opened_at.elapsed()
+    }
+
+    /// 等待下一个需要业务层处理的客户端事件
+    pub async fn next_event(&mut self) -> Option<ConnectionEvent> {
+        if self.exit_reason.is_none() {
+            match self.exited.try_recv() {
+                Ok(reason) => {
+                    self.exit_reason = Some(reason);
+                }
+                Err(tokio::sync::oneshot::error::TryRecvError::Closed) => {
+                    self.exit_reason = Some(PumpExitReason::PumpStopped);
+                }
+                Err(tokio::sync::oneshot::error::TryRecvError::Empty) => {}
+            }
+        }
+        if let Some(reason) = self.exit_reason {
+            return Some(ConnectionEvent::Exited(reason));
+        }
+        if let Some(event) = self.deferred.pop_front() {
+            return Some(event.event);
+        }
+        self.next_active_event().await.map(|event| event.event)
+    }
+
+    /// 活动响应期间只消费新到的帧，已排队的下一轮请求继续保持串行
+    pub(in super::super) async fn next_active_event(&mut self) -> Option<PendingConnectionEvent> {
+        if let Some(reason) = self.exit_reason {
+            return Some(PendingConnectionEvent::exited(reason));
+        }
+        let event = tokio::select! {
+            biased;
+            reason = &mut self.exited => {
+                Some(PendingConnectionEvent::exited(reason.unwrap_or(PumpExitReason::PumpStopped)))
+            }
+            event = self.incoming.recv() => event,
+        };
+        if let Some(PendingConnectionEvent {
+            event: ConnectionEvent::Exited(reason),
+            ..
+        }) = event.as_ref()
+        {
+            self.exit_reason.get_or_insert(*reason);
+        } else if event.is_none() {
+            self.exit_reason.get_or_insert(PumpExitReason::PumpStopped);
+        }
+        event
+    }
+
+    pub(in super::super) fn defer(&mut self, event: PendingConnectionEvent) {
+        self.deferred.push_back(event);
+    }
+
+    /// 等待连接退出，不消费留给后续串行请求的业务帧
+    pub async fn wait_for_exit(&mut self) -> PumpExitReason {
+        if let Some(reason) = self.exit_reason {
+            return reason;
+        }
+        let reason = (&mut self.exited)
+            .await
+            .unwrap_or(PumpExitReason::PumpStopped);
+        self.exit_reason = Some(reason);
+        reason
+    }
+
+    /// 串行写入文本帧，并等待 pump 确认 transport 写入结果
+    ///
+    /// # Errors
+    ///
+    /// pump 已关闭、写入超时或 transport 失败时返回稳定错误
+    pub async fn send_text(
+        &mut self,
+        payload: String,
+        context: WriteContext,
+    ) -> Result<WriteOutcome, ConnectionWriteError> {
+        self.send(Message::Text(payload.into()), context).await
+    }
+
+    pub(in super::super) async fn close_policy(
+        &mut self,
+        reason: &'static str,
+        request_id: Option<&Arc<str>>,
+    ) {
+        let context = request_id.map_or_else(
+            || WriteContext::connection(FramePhase::Close),
+            |request_id| WriteContext::request(request_id, FramePhase::Close),
+        );
+        self.close(
+            CloseFrame {
+                code: close_code::POLICY,
+                reason: reason.into(),
+            },
+            context,
+            PumpExitReason::ServerClose,
+        )
+        .await;
+    }
+
+    pub(in super::super) async fn close_for_connection_limit(&mut self, reason: &'static str) {
+        self.close(
+            CloseFrame {
+                code: close_code::NORMAL,
+                reason: reason.into(),
+            },
+            WriteContext::connection(FramePhase::Close),
+            PumpExitReason::ConnectionMaxAge,
+        )
+        .await;
+    }
+
+    async fn close(
+        &mut self,
+        frame: CloseFrame,
+        context: WriteContext,
+        exit_reason: PumpExitReason,
+    ) {
+        if self
+            .send(Message::Close(Some(frame)), context)
+            .await
+            .is_ok()
+        {
+            self.exit_reason.get_or_insert(exit_reason);
+        }
+    }
+
+    async fn send(
+        &mut self,
+        message: Message,
+        context: WriteContext,
+    ) -> Result<WriteOutcome, ConnectionWriteError> {
+        let Some(commands) = self.commands.as_ref().cloned() else {
+            return Err(ConnectionWriteError::Closed);
+        };
+        self.stats.observe_command_queue(&commands);
+        let (acknowledged, acknowledgement) = oneshot::channel();
+        let started_at = Instant::now();
+        let request_id = context.request_id.clone();
+        let phase = context.phase;
+        let command = ConnectionCommand {
+            message,
+            context,
+            acknowledged,
+        };
+        let write = async move {
+            commands
+                .send(command)
+                .await
+                .map_err(|_| ConnectionWriteError::Closed)?;
+            acknowledgement
+                .await
+                .map_err(|_| ConnectionWriteError::Closed)?
+        };
+        let result = match timeout(self.config.write_timeout, write).await {
+            Ok(result) => result,
+            Err(_) => Err(ConnectionWriteError::Timeout {
+                timeout: self.config.write_timeout,
+            }),
+        };
+        let duration = started_at.elapsed();
+        match &result {
+            Ok(WriteOutcome::Written) if phase.is_milestone() => tracing::info!(
+                websocket_connection_id = %self.connection_id,
+                request_id = request_id.as_deref().unwrap_or(""),
+                frame_phase = phase.as_str(),
+                write_duration_ms = duration.as_millis(),
+                "Responses WebSocket frame write succeeded"
+            ),
+            Ok(outcome) => tracing::debug!(
+                websocket_connection_id = %self.connection_id,
+                request_id = request_id.as_deref().unwrap_or(""),
+                frame_phase = phase.as_str(),
+                write_duration_ms = duration.as_millis(),
+                ?outcome,
+                "Responses WebSocket frame processed"
+            ),
+            Err(error) => tracing::info!(
+                websocket_connection_id = %self.connection_id,
+                request_id = request_id.as_deref().unwrap_or(""),
+                frame_phase = phase.as_str(),
+                write_duration_ms = duration.as_millis(),
+                error = %error,
+                "Responses WebSocket frame write failed"
+            ),
+        }
+        if let Err(error) = &result {
+            let reason = match error {
+                ConnectionWriteError::Timeout { .. } => PumpExitReason::WriteTimeout,
+                ConnectionWriteError::Transport { .. } => PumpExitReason::WriteError,
+                ConnectionWriteError::Closed => PumpExitReason::PumpStopped,
+            };
+            self.terminate(reason);
+        }
+        result
+    }
+
+    fn terminate(&mut self, reason: PumpExitReason) {
+        self.exit_reason.get_or_insert(reason);
+        self.commands.take();
+        if let Some(task) = self.pump_task.take() {
+            task.abort();
+        }
+    }
+
+    pub(in super::super) fn log_summary(&self, request_count: u64) {
+        let connection_age_ms = self.age().as_millis();
+        let read_idle_ms = connection_age_ms
+            .saturating_sub(u128::from(self.stats.last_read_ms.load(Ordering::Relaxed)));
+        let write_idle_ms = connection_age_ms
+            .saturating_sub(u128::from(self.stats.last_write_ms.load(Ordering::Relaxed)));
+        tracing::info!(
+            websocket_connection_id = %self.connection_id,
+            request_count,
+            connection_age_ms,
+            pump_exit_reason = self
+                .exit_reason
+                .map_or("unknown", PumpExitReason::as_str),
+            command_queue_high_water = self
+                .stats
+                .command_queue_high_water
+                .load(Ordering::Relaxed),
+            command_backpressure_count = self
+                .stats
+                .command_backpressure_count
+                .load(Ordering::Relaxed),
+            ping_received_count = self.stats.ping_received_count.load(Ordering::Relaxed),
+            ping_written_count = self.stats.ping_written_count.load(Ordering::Relaxed),
+            pong_received_count = self.stats.pong_received_count.load(Ordering::Relaxed),
+            read_idle_ms,
+            write_idle_ms,
+            "Responses WebSocket disconnected"
+        );
+    }
+}
+
+impl Drop for ResponsesWebSocketConnection {
+    fn drop(&mut self) {
+        self.commands.take();
+        if let Some(task) = self.pump_task.take() {
+            task.abort();
+        }
+    }
+}
+
+/// 为 WebSocket transport 启动包含冻结中间件计划的单 owner pump
+pub fn spawn_connection<S, E>(
+    socket: S,
+    connection_id: Arc<str>,
+    cancellation: CancellationToken,
+    config: ConnectionConfig,
+    middleware: Option<FrozenMiddlewarePlan>,
+    headers: Arc<[MiddlewareHeader]>,
+) -> ResponsesWebSocketConnection
+where
+    S: Stream<Item = Result<Message, E>> + Sink<Message, Error = E> + Unpin + Send + 'static,
+    E: fmt::Display + Send + 'static,
+{
+    let opened_at = Instant::now();
+    let expired = Arc::new(AtomicBool::new(false));
+    let stats = Arc::new(ConnectionStats::default());
+    let (command_tx, command_rx) = mpsc::channel(OUTBOUND_COMMAND_BUFFER);
+    let (incoming_tx, incoming_rx) = mpsc::channel(INBOUND_EVENT_BUFFER);
+    let (exit_tx, exit_rx) = oneshot::channel();
+    let pump_task = tokio::spawn(run_pump(
+        socket,
+        command_rx,
+        incoming_tx,
+        exit_tx,
+        Arc::clone(&connection_id),
+        cancellation,
+        opened_at,
+        Arc::clone(&expired),
+        Arc::clone(&stats),
+        config,
+        middleware,
+        headers,
+    ));
+    ResponsesWebSocketConnection {
+        connection_id,
+        opened_at,
+        expired,
+        commands: Some(command_tx),
+        incoming: incoming_rx,
+        deferred: VecDeque::new(),
+        exited: exit_rx,
+        pump_task: Some(pump_task),
+        stats,
+        config,
+        exit_reason: None,
+    }
+}
@@ -1,11 +1,13 @@
 //! 插件消息组合在 transport 锁之外执行，主动发送复用唯一 writer
-use super::{ConnectionWriteError, PumpContext, write_message};
+use super::{ConnectionWriteError, frame::DOWNSTREAM_CLOSE_TIMEOUT, state::PumpContext};
 pub(super) use crate::middleware::websocket::CancelOnDrop;
 use crate::middleware::websocket::{from_core, into_core};
 use axum::extract::ws::Message;
-use futures::{Sink, future::BoxFuture};
-use gateway_core::{engine::middleware::MiddlewareError, middleware::websocket as core};
-use std::sync::Arc;
+use futures::{Sink, SinkExt, future::BoxFuture};
+use gateway_core::engine::middleware::{MiddlewareError, websocket as core};
+use gateway_core::lifecycle::CancellationToken;
+use std::{fmt, sync::Arc};
+use tokio::time::timeout;

 pub(super) struct Writer<S> {
    socket: tokio::sync::Mutex<S>,
@@ -37,6 +39,36 @@ where
            }) => result.unwrap_or(Err(ConnectionWriteError::Timeout { timeout: self.context.config.write_timeout })),
        }
    }
+
+    pub(super) async fn finish_peer_close(
+        &self,
+        cancellation: &CancellationToken,
+    ) -> Result<(), ConnectionWriteError> {
+        // 主动 Sender 也可能在 pump 之外持锁；先独占 transport 再取消业务，
+        // 有在途写或已取消的半帧时立即跳过，不能等待它释放锁后继续刷新
+        let socket = self
+            .socket
+            .try_lock()
+            .ok()
+            .filter(|_| !self.context.cancellation.is_cancelled());
+        self.context.cancellation.cancel();
+        let Some(mut socket) = socket else {
+            return Err(ConnectionWriteError::Closed);
+        };
+        // 收到 Close 后 transport 已排队应答；只刷新它，不能再发送一份 Close
+        // 业务调用已取消，清理只受宿主取消与独立短预算约束，不沿用业务写入的长超时
+        tokio::select! {
+            biased;
+            () = cancellation.cancelled() => Err(ConnectionWriteError::Closed),
+            result = timeout(DOWNSTREAM_CLOSE_TIMEOUT, async {
+                socket.flush().await.map_err(|error| {
+                    ConnectionWriteError::Transport { message: error.to_string() }
+                })
+            }) => result.unwrap_or(Err(ConnectionWriteError::Timeout {
+                timeout: DOWNSTREAM_CLOSE_TIMEOUT,
+            })),
+        }
+    }
 }
 impl<S, E> core::Sender for Writer<S>
 where
@@ -81,3 +113,25 @@ pub(super) async fn transform(
    .map(from_core)
    .transpose()
 }
+
+async fn write_message<S, E>(
+    socket: &mut S,
+    message: Message,
+    context: &PumpContext,
+) -> Result<(), ConnectionWriteError>
+where
+    S: Sink<Message, Error = E> + Unpin,
+    E: fmt::Display,
+{
+    tokio::select! {
+        biased;
+        () = context.cancellation.cancelled() => Err(ConnectionWriteError::Closed),
+        result = timeout(context.config.write_timeout, socket.send(message)) => {
+            match result {
+                Ok(Ok(())) => { context.stats.record_write(context.opened_at); Ok(()) }
+                Ok(Err(error)) => Err(ConnectionWriteError::Transport { message: error.to_string() }),
+                Err(_) => Err(ConnectionWriteError::Timeout { timeout: context.config.write_timeout }),
+            }
+        }
+    }
+}
@@ -1,826 +1,13 @@
-//! 下游客户端 WebSocket 的单 owner pump 与有界收发边界
+//! 下游客户端 WebSocket 的连接合同、句柄与单 owner pump

+mod frame;
+mod handle;
 mod middleware;
+mod pump;
+mod state;

-use std::{
-    collections::VecDeque,
-    fmt,
-    sync::{
-        Arc,
-        atomic::{AtomicBool, AtomicU64, AtomicUsize, Ordering},
-    },
-    time::Duration,
+pub use frame::{
+    ConnectionConfig, ConnectionEvent, ConnectionWriteError, FramePhase, PumpExitReason,
+    WriteContext, WriteOutcome,
 };
-
-use axum::extract::ws::{CloseFrame, Message, WebSocket, close_code};
-use futures::{Sink, SinkExt, Stream, StreamExt};
-use gateway_core::{
-    engine::middleware::{FrozenMiddlewarePlan, MiddlewareHeader},
-    lifecycle::CancellationToken,
-    middleware::websocket as contract,
-};
-use thiserror::Error;
-use tokio::{
-    sync::{OwnedSemaphorePermit, Semaphore, mpsc, oneshot},
-    task::JoinHandle,
-    time::{Instant, timeout},
-};
-
-const OUTBOUND_COMMAND_BUFFER: usize = 32;
-const INBOUND_EVENT_BUFFER: usize = 32;
-const DOWNSTREAM_WRITE_TIMEOUT: Duration = Duration::from_secs(5 * 60);
-const CONNECTION_MAX_AGE: Duration = Duration::from_secs(60 * 60);
-const DOWNSTREAM_PING_INTERVAL: Duration = Duration::from_secs(25);
-
-/// WebSocket pump 的写入与生命周期预算
-#[derive(Clone, Copy)]
-pub struct ConnectionConfig {
-    write_timeout: Duration,
-    max_age: Duration,
-}
-
-impl ConnectionConfig {
-    /// 生产环境固定预算
-    pub const PRODUCTION: Self = Self {
-        write_timeout: DOWNSTREAM_WRITE_TIMEOUT,
-        max_age: CONNECTION_MAX_AGE,
-    };
-}
-
-/// 业务层可观察的客户端输入；Ping/Pong 始终由 pump 消费
-pub enum ConnectionEvent {
-    Text(String),
-    Binary,
-    Expired,
-    Exited(PumpExitReason),
-}
-
-/// 接收队列与活动期间暂存的请求共用容量；移动帧不释放它占用的名额
-pub(super) struct PendingConnectionEvent {
-    pub(super) event: ConnectionEvent,
-    _permit: Option<OwnedSemaphorePermit>,
-}
-
-impl PendingConnectionEvent {
-    fn exited(reason: PumpExitReason) -> Self {
-        Self {
-            event: ConnectionEvent::Exited(reason),
-            _permit: None,
-        }
-    }
-}
-
-/// 下游写入阶段；名称刻意使用 write，而不是暗示客户端已消费的 delivery
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub enum FramePhase {
-    Metadata,
-    First,
-    Data,
-    Terminal,
-    FirstAndTerminal,
-    Error,
-    ConnectionLimit,
-    Close,
-}
-
-impl FramePhase {
-    const fn as_str(self) -> &'static str {
-        match self {
-            Self::Metadata => "metadata",
-            Self::First => "first",
-            Self::Data => "data",
-            Self::Terminal => "terminal",
-            Self::FirstAndTerminal => "first_and_terminal",
-            Self::Error => "error",
-            Self::ConnectionLimit => "connection_limit",
-            Self::Close => "close",
-        }
-    }
-
-    const fn is_milestone(self) -> bool {
-        matches!(
-            self,
-            Self::First
-                | Self::Terminal
-                | Self::FirstAndTerminal
-                | Self::Error
-                | Self::ConnectionLimit
-                | Self::Close
-        )
-    }
-}
-
-/// 一次下游写入的请求归属与协议阶段
-#[derive(Clone)]
-pub struct WriteContext {
-    request_id: Option<Arc<str>>,
-    phase: FramePhase,
-}
-
-impl WriteContext {
-    /// 创建归属于某个请求的写入上下文
-    #[must_use]
-    pub fn request(request_id: &Arc<str>, phase: FramePhase) -> Self {
-        Self {
-            request_id: Some(Arc::clone(request_id)),
-            phase,
-        }
-    }
-
-    /// 创建连接级写入上下文
-    #[must_use]
-    pub const fn connection(phase: FramePhase) -> Self {
-        Self {
-            request_id: None,
-            phase,
-        }
-    }
-}
-
-/// WebSocket pump 停止的稳定原因
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub enum PumpExitReason {
-    ClientClose,
-    PeerEof,
-    ReadError,
-    WriteError,
-    WriteTimeout,
-    LifecycleShutdown,
-    ConnectionMaxAge,
-    CoordinatorDropped,
-    InboundOverload,
-    ServerClose,
-    PumpStopped,
-    MiddlewareFailed,
-}
-
-impl PumpExitReason {
-    pub(super) const fn as_str(self) -> &'static str {
-        match self {
-            Self::ClientClose => "client_close",
-            Self::PeerEof => "peer_eof",
-            Self::ReadError => "read_error",
-            Self::WriteError => "write_error",
-            Self::WriteTimeout => "write_timeout",
-            Self::LifecycleShutdown => "lifecycle_shutdown",
-            Self::ConnectionMaxAge => "connection_max_age",
-            Self::CoordinatorDropped => "coordinator_dropped",
-            Self::InboundOverload => "inbound_overload",
-            Self::ServerClose => "server_close",
-            Self::PumpStopped => "pump_stopped",
-            Self::MiddlewareFailed => "middleware_failed",
-        }
-    }
-}
-
-/// 下游 WebSocket 写入失败
-#[derive(Debug, Error)]
-pub enum ConnectionWriteError {
-    #[error("downstream WebSocket pump is closed")]
-    Closed,
-    #[error("downstream WebSocket write timed out after {timeout:?}")]
-    Timeout { timeout: Duration },
-    #[error("downstream WebSocket transport write failed: {message}")]
-    Transport { message: String },
-}
-
-/// 只有实际 transport 写入才记为 Written；插件丢弃消息不伪造写入成功
-#[derive(Clone, Copy, Debug, PartialEq, Eq)]
-pub enum WriteOutcome {
-    Written,
-    Suppressed,
-}
-
-struct ConnectionCommand {
-    message: Message,
-    context: WriteContext,
-    acknowledged: oneshot::Sender<Result<WriteOutcome, ConnectionWriteError>>,
-}
-
-#[derive(Default)]
-struct ConnectionStats {
-    command_queue_high_water: AtomicUsize,
-    command_backpressure_count: AtomicU64,
-    ping_received_count: AtomicU64,
-    ping_written_count: AtomicU64,
-    pong_received_count: AtomicU64,
-    last_read_ms: AtomicU64,
-    last_write_ms: AtomicU64,
-}
-
-impl ConnectionStats {
-    fn record_read(&self, opened_at: Instant) {
-        self.last_read_ms.store(
-            u64::try_from(opened_at.elapsed().as_millis()).unwrap_or(u64::MAX),
-            Ordering::Relaxed,
-        );
-    }
-
-    fn record_write(&self, opened_at: Instant) {
-        self.last_write_ms.store(
-            u64::try_from(opened_at.elapsed().as_millis()).unwrap_or(u64::MAX),
-            Ordering::Relaxed,
-        );
-    }
-
-    fn observe_command_queue(&self, sender: &mpsc::Sender<ConnectionCommand>) {
-        let queued = OUTBOUND_COMMAND_BUFFER
-            .saturating_sub(sender.capacity())
-            .saturating_add(1)
-            .min(OUTBOUND_COMMAND_BUFFER);
-        self.command_queue_high_water
-            .fetch_max(queued, Ordering::Relaxed);
-        if sender.capacity() == 0 {
-            self.command_backpressure_count
-                .fetch_add(1, Ordering::Relaxed);
-        }
-    }
-}
-
-/// 协调层持有的单 owner WebSocket 连接句柄
-pub struct ResponsesWebSocketConnection {
-    connection_id: Arc<str>,
-    opened_at: Instant,
-    expired: Arc<AtomicBool>,
-    commands: Option<mpsc::Sender<ConnectionCommand>>,
-    incoming: mpsc::Receiver<PendingConnectionEvent>,
-    deferred: VecDeque<PendingConnectionEvent>,
-    exited: oneshot::Receiver<PumpExitReason>,
-    pump_task: Option<JoinHandle<()>>,
-    stats: Arc<ConnectionStats>,
-    config: ConnectionConfig,
-    exit_reason: Option<PumpExitReason>,
-}
-
-impl ResponsesWebSocketConnection {
-    pub(super) fn new(
-        socket: WebSocket,
-        connection_id: String,
-        cancellation: CancellationToken,
-        middleware: Option<FrozenMiddlewarePlan>,
-        headers: Arc<[MiddlewareHeader]>,
-    ) -> Self {
-        spawn_with_middleware(
-            socket,
-            Arc::<str>::from(connection_id),
-            cancellation,
-            ConnectionConfig::PRODUCTION,
-            middleware,
-            headers,
-        )
-    }
-
-    pub(super) fn id(&self) -> &str {
-        &self.connection_id
-    }
-
-    /// 返回连接是否已经达到生命周期上限
-    #[must_use]
-    pub fn is_expired(&self) -> bool {
-        self.expired.load(Ordering::Acquire)
-    }
-
-    pub(super) fn age(&self) -> Duration {
-        self.opened_at.elapsed()
-    }
-
-    /// 等待下一个需要业务层处理的客户端事件
-    pub async fn next_event(&mut self) -> Option<ConnectionEvent> {
-        if self.exit_reason.is_none() {
-            match self.exited.try_recv() {
-                Ok(reason) => {
-                    self.exit_reason = Some(reason);
-                }
-                Err(tokio::sync::oneshot::error::TryRecvError::Closed) => {
-                    self.exit_reason = Some(PumpExitReason::PumpStopped);
-                }
-                Err(tokio::sync::oneshot::error::TryRecvError::Empty) => {}
-            }
-        }
-        if let Some(reason) = self.exit_reason {
-            return Some(ConnectionEvent::Exited(reason));
-        }
-        if let Some(event) = self.deferred.pop_front() {
-            return Some(event.event);
-        }
-        self.next_active_event().await.map(|event| event.event)
-    }
-
-    /// 活动响应期间只消费新到的帧，已排队的下一轮请求继续保持串行
-    pub(super) async fn next_active_event(&mut self) -> Option<PendingConnectionEvent> {
-        if let Some(reason) = self.exit_reason {
-            return Some(PendingConnectionEvent::exited(reason));
-        }
-        let event = tokio::select! {
-            biased;
-            reason = &mut self.exited => {
-                Some(PendingConnectionEvent::exited(reason.unwrap_or(PumpExitReason::PumpStopped)))
-            }
-            event = self.incoming.recv() => event,
-        };
-        if let Some(PendingConnectionEvent {
-            event: ConnectionEvent::Exited(reason),
-            ..
-        }) = event.as_ref()
-        {
-            self.exit_reason.get_or_insert(*reason);
-        } else if event.is_none() {
-            self.exit_reason.get_or_insert(PumpExitReason::PumpStopped);
-        }
-        event
-    }
-
-    pub(super) fn defer(&mut self, event: PendingConnectionEvent) {
-        self.deferred.push_back(event);
-    }
-
-    /// 等待连接退出，不消费留给后续串行请求的业务帧
-    pub async fn wait_for_exit(&mut self) -> PumpExitReason {
-        if let Some(reason) = self.exit_reason {
-            return reason;
-        }
-        let reason = (&mut self.exited)
-            .await
-            .unwrap_or(PumpExitReason::PumpStopped);
-        self.exit_reason = Some(reason);
-        reason
-    }
-
-    /// 串行写入文本帧，并等待 pump 确认 transport 写入结果
-    ///
-    /// # Errors
-    ///
-    /// pump 已关闭、写入超时或 transport 失败时返回稳定错误
-    pub async fn send_text(
-        &mut self,
-        payload: String,
-        context: WriteContext,
-    ) -> Result<WriteOutcome, ConnectionWriteError> {
-        self.send(Message::Text(payload.into()), context).await
-    }
-
-    pub(super) async fn close_policy(
-        &mut self,
-        reason: &'static str,
-        request_id: Option<&Arc<str>>,
-    ) {
-        let context = request_id.map_or_else(
-            || WriteContext::connection(FramePhase::Close),
-            |request_id| WriteContext::request(request_id, FramePhase::Close),
-        );
-        self.close(
-            CloseFrame {
-                code: close_code::POLICY,
-                reason: reason.into(),
-            },
-            context,
-            PumpExitReason::ServerClose,
-        )
-        .await;
-    }
-
-    pub(super) async fn close_for_connection_limit(&mut self, reason: &'static str) {
-        self.close(
-            CloseFrame {
-                code: close_code::NORMAL,
-                reason: reason.into(),
-            },
-            WriteContext::connection(FramePhase::Close),
-            PumpExitReason::ConnectionMaxAge,
-        )
-        .await;
-    }
-
-    async fn close(
-        &mut self,
-        frame: CloseFrame,
-        context: WriteContext,
-        exit_reason: PumpExitReason,
-    ) {
-        if self
-            .send(Message::Close(Some(frame)), context)
-            .await
-            .is_ok()
-        {
-            self.exit_reason.get_or_insert(exit_reason);
-        }
-    }
-
-    async fn send(
-        &mut self,
-        message: Message,
-        context: WriteContext,
-    ) -> Result<WriteOutcome, ConnectionWriteError> {
-        let Some(commands) = self.commands.as_ref().cloned() else {
-            return Err(ConnectionWriteError::Closed);
-        };
-        self.stats.observe_command_queue(&commands);
-        let (acknowledged, acknowledgement) = oneshot::channel();
-        let started_at = Instant::now();
-        let request_id = context.request_id.clone();
-        let phase = context.phase;
-        let command = ConnectionCommand {
-            message,
-            context,
-            acknowledged,
-        };
-        let write = async move {
-            commands
-                .send(command)
-                .await
-                .map_err(|_| ConnectionWriteError::Closed)?;
-            acknowledgement
-                .await
-                .map_err(|_| ConnectionWriteError::Closed)?
-        };
-        let result = match timeout(self.config.write_timeout, write).await {
-            Ok(result) => result,
-            Err(_) => Err(ConnectionWriteError::Timeout {
-                timeout: self.config.write_timeout,
-            }),
-        };
-        let duration = started_at.elapsed();
-        match &result {
-            Ok(WriteOutcome::Written) if phase.is_milestone() => tracing::info!(
-                websocket_connection_id = %self.connection_id,
-                request_id = request_id.as_deref().unwrap_or(""),
-                frame_phase = phase.as_str(),
-                write_duration_ms = duration.as_millis(),
-                "Responses WebSocket frame write succeeded"
-            ),
-            Ok(outcome) => tracing::debug!(
-                websocket_connection_id = %self.connection_id,
-                request_id = request_id.as_deref().unwrap_or(""),
-                frame_phase = phase.as_str(),
-                write_duration_ms = duration.as_millis(),
-                ?outcome,
-                "Responses WebSocket frame processed"
-            ),
-            Err(error) => tracing::info!(
-                websocket_connection_id = %self.connection_id,
-                request_id = request_id.as_deref().unwrap_or(""),
-                frame_phase = phase.as_str(),
-                write_duration_ms = duration.as_millis(),
-                error = %error,
-                "Responses WebSocket frame write failed"
-            ),
-        }
-        if let Err(error) = &result {
-            let reason = match error {
-                ConnectionWriteError::Timeout { .. } => PumpExitReason::WriteTimeout,
-                ConnectionWriteError::Transport { .. } => PumpExitReason::WriteError,
-                ConnectionWriteError::Closed => PumpExitReason::PumpStopped,
-            };
-            self.terminate(reason);
-        }
-        result
-    }
-
-    fn terminate(&mut self, reason: PumpExitReason) {
-        self.exit_reason.get_or_insert(reason);
-        self.commands.take();
-        if let Some(task) = self.pump_task.take() {
-            task.abort();
-        }
-    }
-
-    pub(super) fn log_summary(&self, request_count: u64) {
-        let connection_age_ms = self.age().as_millis();
-        let read_idle_ms = connection_age_ms
-            .saturating_sub(u128::from(self.stats.last_read_ms.load(Ordering::Relaxed)));
-        let write_idle_ms = connection_age_ms
-            .saturating_sub(u128::from(self.stats.last_write_ms.load(Ordering::Relaxed)));
-        tracing::info!(
-            websocket_connection_id = %self.connection_id,
-            request_count,
-            connection_age_ms,
-            pump_exit_reason = self
-                .exit_reason
-                .map_or("unknown", PumpExitReason::as_str),
-            command_queue_high_water = self
-                .stats
-                .command_queue_high_water
-                .load(Ordering::Relaxed),
-            command_backpressure_count = self
-                .stats
-                .command_backpressure_count
-                .load(Ordering::Relaxed),
-            ping_received_count = self.stats.ping_received_count.load(Ordering::Relaxed),
-            ping_written_count = self.stats.ping_written_count.load(Ordering::Relaxed),
-            pong_received_count = self.stats.pong_received_count.load(Ordering::Relaxed),
-            read_idle_ms,
-            write_idle_ms,
-            "Responses WebSocket disconnected"
-        );
-    }
-}
-
-impl Drop for ResponsesWebSocketConnection {
-    fn drop(&mut self) {
-        self.commands.take();
-        if let Some(task) = self.pump_task.take() {
-            task.abort();
-        }
-    }
-}
-
-/// 为自动处理 Ping/Pong 的 WebSocket transport 启动单 owner pump
-pub fn spawn_connection<S, E>(
-    socket: S,
-    connection_id: Arc<str>,
-    cancellation: CancellationToken,
-    config: ConnectionConfig,
-) -> ResponsesWebSocketConnection
-where
-    S: Stream<Item = Result<Message, E>> + Sink<Message, Error = E> + Unpin + Send + 'static,
-    E: fmt::Display + Send + 'static,
-{
-    spawn_with_middleware(
-        socket,
-        connection_id,
-        cancellation,
-        config,
-        None,
-        Arc::from([]),
-    )
-}
-
-fn spawn_with_middleware<S, E>(
-    socket: S,
-    connection_id: Arc<str>,
-    cancellation: CancellationToken,
-    config: ConnectionConfig,
-    middleware: Option<FrozenMiddlewarePlan>,
-    headers: Arc<[MiddlewareHeader]>,
-) -> ResponsesWebSocketConnection
-where
-    S: Stream<Item = Result<Message, E>> + Sink<Message, Error = E> + Unpin + Send + 'static,
-    E: fmt::Display + Send + 'static,
-{
-    let opened_at = Instant::now();
-    let expired = Arc::new(AtomicBool::new(false));
-    let stats = Arc::new(ConnectionStats::default());
-    let (command_tx, command_rx) = mpsc::channel(OUTBOUND_COMMAND_BUFFER);
-    let (incoming_tx, incoming_rx) = mpsc::channel(INBOUND_EVENT_BUFFER);
-    let (exit_tx, exit_rx) = oneshot::channel();
-    let pump_task = tokio::spawn(run_pump(
-        socket,
-        command_rx,
-        incoming_tx,
-        exit_tx,
-        Arc::clone(&connection_id),
-        cancellation,
-        opened_at,
-        Arc::clone(&expired),
-        Arc::clone(&stats),
-        config,
-        middleware,
-        headers,
-    ));
-    ResponsesWebSocketConnection {
-        connection_id,
-        opened_at,
-        expired,
-        commands: Some(command_tx),
-        incoming: incoming_rx,
-        deferred: VecDeque::new(),
-        exited: exit_rx,
-        pump_task: Some(pump_task),
-        stats,
-        config,
-        exit_reason: None,
-    }
-}
-
-#[expect(clippy::too_many_arguments)]
-async fn run_pump<S, E>(
-    socket: S,
-    commands: mpsc::Receiver<ConnectionCommand>,
-    incoming: mpsc::Sender<PendingConnectionEvent>,
-    exited: oneshot::Sender<PumpExitReason>,
-    connection_id: Arc<str>,
-    cancellation: CancellationToken,
-    opened_at: Instant,
-    expired: Arc<AtomicBool>,
-    stats: Arc<ConnectionStats>,
-    config: ConnectionConfig,
-    middleware: Option<FrozenMiddlewarePlan>,
-    headers: Arc<[MiddlewareHeader]>,
-) where
-    S: Stream<Item = Result<Message, E>> + Sink<Message, Error = E> + Unpin + Send + 'static,
-    E: fmt::Display + Send + 'static,
-{
-    let context = Arc::new(PumpContext {
-        connection_id,
-        cancellation: cancellation.child_token(),
-        opened_at,
-        expired,
-        stats,
-        config,
-        middleware,
-        headers,
-    });
-    let _lifetime = middleware::CancelOnDrop(Some(context.cancellation.clone()));
-    let (writer, mut reader) = socket.split();
-    let writer = Arc::new(middleware::Writer::new(writer, context.clone()));
-    let sender: Arc<dyn contract::Sender> = writer.clone();
-    // 同一个受管任务同时驱动两侧；等待写入不能阻塞入站控制、关闭或取消
-    let reason = tokio::select! {
-        biased;
-        reason = read_connection(&mut reader, &incoming, sender.clone(), &context) => reason,
-        reason = write_connection(writer.clone(), commands, &context) => reason,
-    };
-    context.cancellation.cancel();
-    let _ = exited.send(reason);
-    tracing::debug!(websocket_connection_id = %context.connection_id, pump_exit_reason = reason.as_str(), "Responses WebSocket pump exited");
-}
-
-struct PumpContext {
-    middleware: Option<FrozenMiddlewarePlan>,
-    headers: Arc<[MiddlewareHeader]>,
-    connection_id: Arc<str>,
-    cancellation: CancellationToken,
-    opened_at: Instant,
-    expired: Arc<AtomicBool>,
-    stats: Arc<ConnectionStats>,
-    config: ConnectionConfig,
-}
-
-async fn read_connection<S, E>(
-    socket: &mut S,
-    incoming: &mpsc::Sender<PendingConnectionEvent>,
-    sender: Arc<dyn contract::Sender>,
-    context: &PumpContext,
-) -> PumpExitReason
-where
-    S: Stream<Item = Result<Message, E>> + Unpin,
-    E: fmt::Display,
-{
-    let event_slots = Arc::new(Semaphore::new(INBOUND_EVENT_BUFFER));
-    let deadline = tokio::time::sleep_until(context.opened_at + context.config.max_age);
-    tokio::pin!(deadline);
-    let mut deadline_elapsed = false;
-    loop {
-        tokio::select! {
-            biased;
-            () = context.cancellation.cancelled() => return PumpExitReason::LifecycleShutdown,
-            () = &mut deadline, if !deadline_elapsed => {
-                deadline_elapsed = true;
-                context.expired.store(true, Ordering::Release);
-                // 到期只阻止下一轮，当前响应仍由协调层按原有合同收尾
-                match emit_incoming(incoming, &event_slots, ConnectionEvent::Expired) {
-                    Ok(()) | Err(PumpExitReason::InboundOverload) => {}
-                    Err(reason) => return reason,
-                }
-            }
-            message = socket.next() => {
-                if matches!(&message, Some(Ok(_))) { context.stats.record_read(context.opened_at); }
-                let message = match message {
-                    Some(Ok(message)) => match middleware::transform(message, contract::Direction::Incoming, sender.clone(), context).await {
-                        Ok(Some(message)) => Some(Ok(message)),
-                        Ok(None) => continue,
-                        Err(_) => return PumpExitReason::MiddlewareFailed,
-                    },
-                    other => other,
-                };
-                let event = match message {
-                    Some(Ok(Message::Text(payload))) => Some(ConnectionEvent::Text(payload.to_string())),
-                    Some(Ok(Message::Binary(_))) => Some(ConnectionEvent::Binary),
-                    Some(Ok(Message::Ping(_))) => {
-                        // Axum/tungstenite 在继续读取时自动刷新 Pong，不能再手工发送一份
-                        context.stats.ping_received_count.fetch_add(1, Ordering::Relaxed);
-                        None
-                    }
-                    Some(Ok(Message::Pong(_))) => {
-                        context.stats.pong_received_count.fetch_add(1, Ordering::Relaxed);
-                        None
-                    }
-                    Some(Ok(Message::Close(_))) => return PumpExitReason::ClientClose,
-                    Some(Err(error)) => {
-                        tracing::info!(websocket_connection_id = %context.connection_id, error = %error, "Responses WebSocket receive failed");
-                        return PumpExitReason::ReadError;
-                    }
-                    None => return PumpExitReason::PeerEof,
-                };
-                if let Some(event) = event && let Err(reason) = emit_incoming(incoming, &event_slots, event) { return reason; }
-            }
-        }
-    }
-}
-
-async fn write_connection<S, E>(
-    writer: Arc<middleware::Writer<S>>,
-    mut commands: mpsc::Receiver<ConnectionCommand>,
-    context: &PumpContext,
-) -> PumpExitReason
-where
-    S: Sink<Message, Error = E> + Unpin + Send + 'static,
-    E: fmt::Display + Send + 'static,
-{
-    let mut heartbeat = tokio::time::interval_at(
-        context.opened_at + DOWNSTREAM_PING_INTERVAL,
-        DOWNSTREAM_PING_INTERVAL,
-    );
-    heartbeat.set_missed_tick_behavior(tokio::time::MissedTickBehavior::Skip);
-    let mut ping_sequence = 0_u64;
-    loop {
-        let message = tokio::select! {
-            biased;
-            () = context.cancellation.cancelled() => return PumpExitReason::LifecycleShutdown,
-            command = commands.recv() => {
-                let Some(command) = command else { return PumpExitReason::CoordinatorDropped; };
-                let ConnectionCommand { message, context: write_context, acknowledged } = command;
-                let closing = matches!(message, Message::Close(_));
-                let result = match middleware::transform(message, contract::Direction::Outgoing, writer.clone(), context).await {
-                    Ok(Some(message)) => writer.write(message).await.map(|()| WriteOutcome::Written),
-                    Ok(None) => Ok(WriteOutcome::Suppressed),
-                    Err(error) => Err(ConnectionWriteError::Transport { message: error.to_string() }),
-                };
-                let reason = result.as_ref().err().map(|error| write_exit_reason(error, context));
-                if let Err(error) = &result {
-                    tracing::debug!(websocket_connection_id = %context.connection_id, request_id = write_context.request_id.as_deref().unwrap_or(""), frame_phase = write_context.phase.as_str(), error = %error, "Responses WebSocket pump transport write failed");
-                }
-                let _ = acknowledged.send(result);
-                if let Some(reason) = reason { return reason; }
-                if closing { return PumpExitReason::ServerClose; }
-                continue;
-            }
-            _ = heartbeat.tick() => {
-                ping_sequence = ping_sequence.wrapping_add(1);
-                Message::Ping(ping_sequence.to_be_bytes().to_vec().into())
-            }
-        };
-        let message = match middleware::transform(
-            message,
-            contract::Direction::Outgoing,
-            writer.clone(),
-            context,
-        )
-        .await
-        {
-            Ok(Some(message)) => message,
-            Ok(None) => continue,
-            Err(_) => return PumpExitReason::MiddlewareFailed,
-        };
-        if let Err(error) = writer.write(message).await {
-            tracing::info!(websocket_connection_id = %context.connection_id, error = %error, "Responses WebSocket control write failed");
-            return write_exit_reason(&error, context);
-        }
-        context
-            .stats
-            .ping_written_count
-            .fetch_add(1, Ordering::Relaxed);
-    }
-}
-
-async fn write_message<S, E>(
-    socket: &mut S,
-    message: Message,
-    context: &PumpContext,
-) -> Result<(), ConnectionWriteError>
-where
-    S: Sink<Message, Error = E> + Unpin,
-    E: fmt::Display,
-{
-    tokio::select! {
-        biased;
-        () = context.cancellation.cancelled() => Err(ConnectionWriteError::Closed),
-        result = timeout(context.config.write_timeout, socket.send(message)) => {
-            match result {
-                Ok(Ok(())) => { context.stats.record_write(context.opened_at); Ok(()) }
-                Ok(Err(error)) => Err(ConnectionWriteError::Transport { message: error.to_string() }),
-                Err(_) => Err(ConnectionWriteError::Timeout { timeout: context.config.write_timeout }),
-            }
-        }
-    }
-}
-
-fn write_exit_reason(error: &ConnectionWriteError, context: &PumpContext) -> PumpExitReason {
-    match error {
-        ConnectionWriteError::Timeout { .. } => PumpExitReason::WriteTimeout,
-        ConnectionWriteError::Transport { .. } => PumpExitReason::WriteError,
-        ConnectionWriteError::Closed if context.cancellation.is_cancelled() => {
-            PumpExitReason::LifecycleShutdown
-        }
-        ConnectionWriteError::Closed => PumpExitReason::PumpStopped,
-    }
-}
-
-fn emit_incoming(
-    incoming: &mpsc::Sender<PendingConnectionEvent>,
-    slots: &Arc<Semaphore>,
-    event: ConnectionEvent,
-) -> Result<(), PumpExitReason> {
-    let permit = Arc::clone(slots)
-        .try_acquire_owned()
-        .map_err(|_| PumpExitReason::InboundOverload)?;
-    incoming
-        .try_send(PendingConnectionEvent {
-            event,
-            _permit: Some(permit),
-        })
-        .map_err(|error| match error {
-            mpsc::error::TrySendError::Full(_) => PumpExitReason::InboundOverload,
-            mpsc::error::TrySendError::Closed(_) => PumpExitReason::CoordinatorDropped,
-        })
-}
+pub use handle::{ResponsesWebSocketConnection, spawn_connection};
@@ -0,0 +1,230 @@
+//! 单 owner 驱动连接读写、心跳与有界入站队列
+
+use super::{
+    frame::*,
+    middleware,
+    state::{ConnectionCommand, ConnectionStats, PumpContext},
+};
+use axum::extract::ws::Message;
+use futures::{Sink, Stream, StreamExt};
+use gateway_core::{
+    engine::middleware::{FrozenMiddlewarePlan, MiddlewareHeader, websocket as contract},
+    lifecycle::CancellationToken,
+};
+use std::{
+    fmt,
+    sync::{
+        Arc,
+        atomic::{AtomicBool, Ordering},
+    },
+};
+use tokio::{
+    sync::{Semaphore, mpsc, oneshot},
+    time::Instant,
+};
+
+#[expect(clippy::too_many_arguments)]
+pub(super) async fn run_pump<S, E>(
+    socket: S,
+    commands: mpsc::Receiver<ConnectionCommand>,
+    incoming: mpsc::Sender<PendingConnectionEvent>,
+    exited: oneshot::Sender<PumpExitReason>,
+    connection_id: Arc<str>,
+    cancellation: CancellationToken,
+    opened_at: Instant,
+    expired: Arc<AtomicBool>,
+    stats: Arc<ConnectionStats>,
+    config: ConnectionConfig,
+    middleware: Option<FrozenMiddlewarePlan>,
+    headers: Arc<[MiddlewareHeader]>,
+) where
+    S: Stream<Item = Result<Message, E>> + Sink<Message, Error = E> + Unpin + Send + 'static,
+    E: fmt::Display + Send + 'static,
+{
+    let context = Arc::new(PumpContext {
+        connection_id,
+        cancellation: cancellation.child_token(),
+        opened_at,
+        expired,
+        stats,
+        config,
+        middleware,
+        headers,
+    });
+    let _lifetime = middleware::CancelOnDrop(Some(context.cancellation.clone()));
+    let (writer, mut reader) = socket.split();
+    let writer = Arc::new(middleware::Writer::new(writer, context.clone()));
+    let sender: Arc<dyn contract::Sender> = writer.clone();
+    // 同一个受管任务同时驱动两侧；等待写入不能阻塞入站控制、关闭或取消
+    let reason = tokio::select! {
+        biased;
+        reason = read_connection(&mut reader, &incoming, sender.clone(), &context) => reason,
+        reason = write_connection(writer.clone(), commands, &context) => reason,
+    };
+    if matches!(reason, PumpExitReason::ClientClose) {
+        if let Err(error) = writer.finish_peer_close(&cancellation).await {
+            tracing::debug!(websocket_connection_id = %context.connection_id, %error, "Responses WebSocket close acknowledgement could not be flushed");
+        }
+    } else {
+        context.cancellation.cancel();
+    }
+    let _ = exited.send(reason);
+    tracing::debug!(websocket_connection_id = %context.connection_id, pump_exit_reason = reason.as_str(), "Responses WebSocket pump exited");
+}
+
+async fn read_connection<S, E>(
+    socket: &mut S,
+    incoming: &mpsc::Sender<PendingConnectionEvent>,
+    sender: Arc<dyn contract::Sender>,
+    context: &PumpContext,
+) -> PumpExitReason
+where
+    S: Stream<Item = Result<Message, E>> + Unpin,
+    E: fmt::Display,
+{
+    let event_slots = Arc::new(Semaphore::new(INBOUND_EVENT_BUFFER));
+    let deadline = tokio::time::sleep_until(context.opened_at + context.config.max_age);
+    tokio::pin!(deadline);
+    let mut deadline_elapsed = false;
+    loop {
+        tokio::select! {
+            biased;
+            () = context.cancellation.cancelled() => return PumpExitReason::LifecycleShutdown,
+            () = &mut deadline, if !deadline_elapsed => {
+                deadline_elapsed = true;
+                context.expired.store(true, Ordering::Release);
+                // 到期只阻止下一轮，当前响应仍由协调层按原有合同收尾
+                match emit_incoming(incoming, &event_slots, ConnectionEvent::Expired) {
+                    Ok(()) | Err(PumpExitReason::InboundOverload) => {}
+                    Err(reason) => return reason,
+                }
+            }
+            message = socket.next() => {
+                if matches!(&message, Some(Ok(_))) { context.stats.record_read(context.opened_at); }
+                let message = match message {
+                    Some(Ok(message)) => match middleware::transform(message, contract::Direction::Incoming, sender.clone(), context).await {
+                        Ok(Some(message)) => Some(Ok(message)),
+                        Ok(None) => continue,
+                        Err(_) => return PumpExitReason::MiddlewareFailed,
+                    },
+                    other => other,
+                };
+                let event = match message {
+                    Some(Ok(Message::Text(payload))) => Some(ConnectionEvent::Text(payload.to_string())),
+                    Some(Ok(Message::Binary(_))) => Some(ConnectionEvent::Binary),
+                    Some(Ok(Message::Ping(_))) => {
+                        // Axum/tungstenite 在继续读取时自动刷新 Pong，不能再手工发送一份
+                        context.stats.ping_received_count.fetch_add(1, Ordering::Relaxed);
+                        None
+                    }
+                    Some(Ok(Message::Pong(_))) => {
+                        context.stats.pong_received_count.fetch_add(1, Ordering::Relaxed);
+                        None
+                    }
+                    Some(Ok(Message::Close(_))) => return PumpExitReason::ClientClose,
+                    Some(Err(error)) => {
+                        tracing::info!(websocket_connection_id = %context.connection_id, error = %error, "Responses WebSocket receive failed");
+                        return PumpExitReason::ReadError;
+                    }
+                    None => return PumpExitReason::PeerEof,
+                };
+                if let Some(event) = event && let Err(reason) = emit_incoming(incoming, &event_slots, event) { return reason; }
+            }
+        }
+    }
+}
+
+async fn write_connection<S, E>(
+    writer: Arc<middleware::Writer<S>>,
+    mut commands: mpsc::Receiver<ConnectionCommand>,
+    context: &PumpContext,
+) -> PumpExitReason
+where
+    S: Sink<Message, Error = E> + Unpin + Send + 'static,
+    E: fmt::Display + Send + 'static,
+{
+    let mut heartbeat = tokio::time::interval_at(
+        context.opened_at + DOWNSTREAM_PING_INTERVAL,
+        DOWNSTREAM_PING_INTERVAL,
+    );
+    heartbeat.set_missed_tick_behavior(tokio::time::MissedTickBehavior::Skip);
+    let mut ping_sequence = 0_u64;
+    loop {
+        let message = tokio::select! {
+            biased;
+            () = context.cancellation.cancelled() => return PumpExitReason::LifecycleShutdown,
+            command = commands.recv() => {
+                let Some(command) = command else { return PumpExitReason::CoordinatorDropped; };
+                let ConnectionCommand { message, context: write_context, acknowledged } = command;
+                let closing = matches!(message, Message::Close(_));
+                let result = match middleware::transform(message, contract::Direction::Outgoing, writer.clone(), context).await {
+                    Ok(Some(message)) => writer.write(message).await.map(|()| WriteOutcome::Written),
+                    Ok(None) => Ok(WriteOutcome::Suppressed),
+                    Err(error) => Err(ConnectionWriteError::Transport { message: error.to_string() }),
+                };
+                let reason = result.as_ref().err().map(|error| write_exit_reason(error, context));
+                if let Err(error) = &result {
+                    tracing::debug!(websocket_connection_id = %context.connection_id, request_id = write_context.request_id.as_deref().unwrap_or(""), frame_phase = write_context.phase.as_str(), error = %error, "Responses WebSocket pump transport write failed");
+                }
+                let _ = acknowledged.send(result);
+                if let Some(reason) = reason { return reason; }
+                if closing { return PumpExitReason::ServerClose; }
+                continue;
+            }
+            _ = heartbeat.tick() => {
+                ping_sequence = ping_sequence.wrapping_add(1);
+                Message::Ping(ping_sequence.to_be_bytes().to_vec().into())
+            }
+        };
+        let message = match middleware::transform(
+            message,
+            contract::Direction::Outgoing,
+            writer.clone(),
+            context,
+        )
+        .await
+        {
+            Ok(Some(message)) => message,
+            Ok(None) => continue,
+            Err(_) => return PumpExitReason::MiddlewareFailed,
+        };
+        if let Err(error) = writer.write(message).await {
+            tracing::info!(websocket_connection_id = %context.connection_id, error = %error, "Responses WebSocket control write failed");
+            return write_exit_reason(&error, context);
+        }
+        context
+            .stats
+            .ping_written_count
+            .fetch_add(1, Ordering::Relaxed);
+    }
+}
+
+fn write_exit_reason(error: &ConnectionWriteError, context: &PumpContext) -> PumpExitReason {
+    match error {
+        ConnectionWriteError::Timeout { .. } => PumpExitReason::WriteTimeout,
+        ConnectionWriteError::Transport { .. } => PumpExitReason::WriteError,
+        ConnectionWriteError::Closed if context.cancellation.is_cancelled() => {
+            PumpExitReason::LifecycleShutdown
+        }
+        ConnectionWriteError::Closed => PumpExitReason::PumpStopped,
+    }
+}
+
+fn emit_incoming(
+    incoming: &mpsc::Sender<PendingConnectionEvent>,
+    slots: &Arc<Semaphore>,
+    event: ConnectionEvent,
+) -> Result<(), PumpExitReason> {
+    let permit = Arc::clone(slots)
+        .try_acquire_owned()
+        .map_err(|_| PumpExitReason::InboundOverload)?;
+    incoming
+        .try_send(PendingConnectionEvent {
+            event,
+            _permit: Some(permit),
+        })
+        .map_err(|error| match error {
+            mpsc::error::TrySendError::Full(_) => PumpExitReason::InboundOverload,
+            mpsc::error::TrySendError::Closed(_) => PumpExitReason::CoordinatorDropped,
+        })
+}
@@ -0,0 +1,75 @@
+//! 单连接共享的命令、运行预算与观测状态
+
+use super::frame::{
+    ConnectionConfig, ConnectionWriteError, OUTBOUND_COMMAND_BUFFER, WriteContext, WriteOutcome,
+};
+use axum::extract::ws::Message;
+use gateway_core::{
+    engine::middleware::{FrozenMiddlewarePlan, MiddlewareHeader},
+    lifecycle::CancellationToken,
+};
+use std::sync::{
+    Arc,
+    atomic::{AtomicBool, AtomicU64, AtomicUsize, Ordering},
+};
+use tokio::{
+    sync::{mpsc, oneshot},
+    time::Instant,
+};
+
+pub(super) struct ConnectionCommand {
+    pub(super) message: Message,
+    pub(super) context: WriteContext,
+    pub(super) acknowledged: oneshot::Sender<Result<WriteOutcome, ConnectionWriteError>>,
+}
+
+#[derive(Default)]
+pub(super) struct ConnectionStats {
+    pub(super) command_queue_high_water: AtomicUsize,
+    pub(super) command_backpressure_count: AtomicU64,
+    pub(super) ping_received_count: AtomicU64,
+    pub(super) ping_written_count: AtomicU64,
+    pub(super) pong_received_count: AtomicU64,
+    pub(super) last_read_ms: AtomicU64,
+    pub(super) last_write_ms: AtomicU64,
+}
+
+impl ConnectionStats {
+    pub(super) fn record_read(&self, opened_at: Instant) {
+        self.last_read_ms.store(
+            u64::try_from(opened_at.elapsed().as_millis()).unwrap_or(u64::MAX),
+            Ordering::Relaxed,
+        );
+    }
+
+    pub(super) fn record_write(&self, opened_at: Instant) {
+        self.last_write_ms.store(
+            u64::try_from(opened_at.elapsed().as_millis()).unwrap_or(u64::MAX),
+            Ordering::Relaxed,
+        );
+    }
+
+    pub(super) fn observe_command_queue(&self, sender: &mpsc::Sender<ConnectionCommand>) {
+        let queued = OUTBOUND_COMMAND_BUFFER
+            .saturating_sub(sender.capacity())
+            .saturating_add(1)
+            .min(OUTBOUND_COMMAND_BUFFER);
+        self.command_queue_high_water
+            .fetch_max(queued, Ordering::Relaxed);
+        if sender.capacity() == 0 {
+            self.command_backpressure_count
+                .fetch_add(1, Ordering::Relaxed);
+        }
+    }
+}
+
+pub(super) struct PumpContext {
+    pub(super) middleware: Option<FrozenMiddlewarePlan>,
+    pub(super) headers: Arc<[MiddlewareHeader]>,
+    pub(super) connection_id: Arc<str>,
+    pub(super) cancellation: CancellationToken,
+    pub(super) opened_at: Instant,
+    pub(super) expired: Arc<AtomicBool>,
+    pub(super) stats: Arc<ConnectionStats>,
+    pub(super) config: ConnectionConfig,
+}
@@ -12,7 +12,7 @@ use gateway_core::engine::middleware::{
    MiddlewareBody, MiddlewareError, MiddlewareFrame, MiddlewareFraming, MiddlewareHeader,
    MiddlewareResponse,
 };
-use gateway_core::engine::response_control::ResponseControl;
+use gateway_core::engine::response_control::{ResponseControl, ResponseControlUnavailable};
 use gateway_core::error::{GatewayError, GatewayErrorKind};
 use gateway_core::event::ProviderResponseHeader;
 use gateway_core::operation::ProviderSessionState;
@@ -25,7 +25,7 @@ use super::{
    super::{DecodedResponsesRequest, OpenAiResponsesEncoder, ProtocolErrorBody},
    connection::{ConnectionEvent, FramePhase, ResponsesWebSocketConnection, WriteContext},
    protocol::{
-        decode_response_interrupt, error_event, initial_engine_error_event, response_metadata_event,
+        error_event, initial_engine_error_event, is_response_create, response_metadata_event,
    },
 };

@@ -137,7 +137,7 @@ pub(super) async fn forward_response(
    replay: &mut ConnectionReplaySnapshot,
    capture: ReplayCaptureHandle,
    validation: ResponseValidationFacts,
-    response_control: ResponseControl,
+    response_control: &ResponseControl,
 ) -> ForwardOutcome {
    let (protocol, status, headers, mut body, _) = response.into_parts();
    if protocol != "openai" || StatusCode::from_u16(status).is_err() {
@@ -150,8 +150,16 @@ pub(super) async fn forward_response(
            ProviderResponseHeader::new(name, value)
        })
        .collect::<Vec<_>>();
-    let first = match next_body_input(connection, body.as_mut(), &response_control, &request_id)
-        .await
+    let mut interrupt = super::interrupt::ResponseInterrupt::default();
+    let first = match next_body_input(
+        connection,
+        body.as_mut(),
+        response_control,
+        &mut interrupt,
+        &request_id,
+        false,
+    )
+    .await
    {
        BodyInput::Frame(Ok(Some(frame))) => frame,
        BodyInput::Frame(Ok(None)) => {
@@ -197,8 +205,15 @@ pub(super) async fn forward_response(
        let frame = match current.take() {
            Some(frame) => frame,
            None => {
-                match next_body_input(connection, body.as_mut(), &response_control, &request_id)
-                    .await
+                match next_body_input(
+                    connection,
+                    body.as_mut(),
+                    response_control,
+                    &mut interrupt,
+                    &request_id,
+                    terminal_seen,
+                )
+                .await
                {
                    BodyInput::Frame(Ok(Some(frame))) => frame,
                    BodyInput::Frame(Ok(None)) if terminal_seen && body.is_finalized() => {
@@ -262,11 +277,24 @@ pub(super) async fn forward_response(
            (true, true) => FramePhase::Terminal,
            (true, false) => FramePhase::Data,
        };
+        let created_id = super::interrupt::ResponseInterrupt::created_id(&message);
        match connection
            .send_text(message, WriteContext::request(&request_id, phase))
            .await
        {
-            Ok(super::connection::WriteOutcome::Written) => first_frame_written = true,
+            Ok(super::connection::WriteOutcome::Written) => {
+                first_frame_written = true;
+                if let Some(id) = created_id {
+                    interrupt.observe_created(id, response_control);
+                    tokio::select! {
+                        _ = connection.wait_for_exit() => {
+                            detach_body(body);
+                            return ForwardOutcome::Disconnect;
+                        }
+                        () = interrupt.forward_pending(response_control) => {}
+                    }
+                }
+            }
            Ok(super::connection::WriteOutcome::Suppressed) => {}
            Err(_) => {
                detach_body(body);
@@ -284,8 +312,10 @@ fn detach_body(body: Box<dyn MiddlewareBody>) {
 }

 fn validate_frame(frame: &MiddlewareFrame) -> Result<(), MiddlewareError> {
-    if frame.framing() != MiddlewareFraming::JsonDocument
-        || serde_json::from_slice::<serde::de::IgnoredAny>(frame.bytes()).is_err()
+    if !matches!(
+        frame.framing(),
+        MiddlewareFraming::JsonDocument | MiddlewareFraming::RawBytes
+    ) || std::str::from_utf8(frame.bytes()).is_err()
    {
        return Err(MiddlewareError::InvalidState);
    }
@@ -301,7 +331,9 @@ async fn next_body_input(
    connection: &mut ResponsesWebSocketConnection,
    body: &mut dyn MiddlewareBody,
    response_control: &ResponseControl,
+    interrupt: &mut super::interrupt::ResponseInterrupt,
    request_id: &Arc<str>,
+    terminal_seen: bool,
 ) -> BodyInput {
    // 处理控制帧时继续持有同一个读取 future，不能取消正在加工正文的中间件
    let frame = body.next_frame();
@@ -312,19 +344,18 @@ async fn next_body_input(
                let Some(event) = event else { return BodyInput::Disconnect; };
                match &event.event {
                    ConnectionEvent::Text(payload) => {
-                        let error = match decode_response_interrupt(payload) {
-                            Ok(Some(response_id)) => response_control.interrupt(&response_id).err().map(|_| {
-                                super::super::RequestDecodeError::InvalidValue { field: "response_id".to_owned() }.protocol_body()
-                            }),
-                            Ok(None) => {
-                                connection.defer(event);
-                                continue;
+                        if is_response_create(payload) {
+                            connection.defer(event);
+                            continue;
+                        }
+                        if !terminal_seen && interrupt.retain(payload) {
+                            tokio::select! {
+                                _ = connection.wait_for_exit() => return BodyInput::Disconnect,
+                                () = interrupt.forward_pending(response_control) => {}
                            }
-                            Err(error) => Some(error.protocol_body()),
-                        };
-                        if let Some(error) = error
-                            && send_protocol_error(connection, StatusCode::BAD_REQUEST, error, request_id).await == ForwardOutcome::Disconnect
-                        {
+                            continue;
+                        }
+                        if send_control(connection, response_control, payload, request_id).await == ForwardOutcome::Disconnect {
                            return BodyInput::Disconnect;
                        }
                    }
@@ -337,6 +368,11 @@ async fn next_body_input(
                    ConnectionEvent::Exited(_) => return BodyInput::Disconnect,
                }
            }
+            event = response_control.receive(), if terminal_seen => {
+                if forward_control_event(connection, response_control, event).await == ForwardOutcome::Disconnect {
+                    return BodyInput::Disconnect;
+                }
+            }
            frame = &mut frame => return BodyInput::Frame(frame),
        }
    }
@@ -537,19 +573,26 @@ impl WebSocketExecutionBody {
                    self.transformed_pending = transformed;
                    continue;
                }
-                messages.extend(encoded.into_iter().map(|message| (message, transformed)));
+                let framing = if event.wire_event().is_some_and(|wire| {
+                    wire.raw_websocket_message().is_some() && !wire.has_json_data()
+                }) {
+                    MiddlewareFraming::RawBytes
+                } else {
+                    MiddlewareFraming::JsonDocument
+                };
+                messages.extend(
+                    encoded
+                        .into_iter()
+                        .map(|message| (message, transformed, framing)),
+                );
                self.transformed_pending = false;
            }
            let terminal = self.encoder.is_completed() || self.encoder.has_wire_failure();
            let last = messages.len().saturating_sub(1);
            self.pending.extend(messages.into_iter().enumerate().map(
-                |(index, (message, transformed))| {
-                    MiddlewareFrame::new(
-                        Bytes::from(message),
-                        MiddlewareFraming::JsonDocument,
-                        terminal && index == last,
-                    )
-                    .with_transformed(transformed)
+                |(index, (message, transformed, framing))| {
+                    MiddlewareFrame::new(Bytes::from(message), framing, terminal && index == last)
+                        .with_transformed(transformed)
                },
            ));
            self.awaiting_terminal_eof = terminal;
@@ -720,3 +763,46 @@ async fn send_metadata(
        .await
        .is_ok()
 }
+
+pub(super) async fn send_control(
+    connection: &mut ResponsesWebSocketConnection,
+    control: &ResponseControl,
+    payload: &str,
+    request_id: &Arc<str>,
+) -> ForwardOutcome {
+    let result = tokio::select! {
+        _ = connection.wait_for_exit() => return ForwardOutcome::Disconnect,
+        result = control.send(payload) => result,
+    };
+    if result.is_err() {
+        return send_gateway_error(
+            connection,
+            &GatewayError::new(
+                GatewayErrorKind::InvalidRequest,
+                "No upstream WebSocket connection is available for control messages",
+            ),
+            request_id,
+        )
+        .await;
+    }
+    ForwardOutcome::Continue
+}
+
+pub(super) async fn forward_control_event(
+    connection: &mut ResponsesWebSocketConnection,
+    control: &ResponseControl,
+    event: Result<String, ResponseControlUnavailable>,
+) -> ForwardOutcome {
+    let Ok(payload) = event else {
+        control.clear();
+        return ForwardOutcome::Continue;
+    };
+    if connection
+        .send_text(payload, WriteContext::connection(FramePhase::Data))
+        .await
+        .is_err()
+    {
+        return ForwardOutcome::Disconnect;
+    }
+    ForwardOutcome::Continue
+}
@@ -0,0 +1,91 @@
+//! 当前逻辑响应的中断意图，跨重试连接保留并随新响应 ID 转发
+
+use std::{borrow::Cow, collections::BTreeSet};
+
+use gateway_core::engine::response_control::{ResponseControl, ResponseControlBinding};
+use serde::Deserialize;
+use serde_json::Value;
+
+#[derive(Deserialize)]
+struct EventIdentity<'a> {
+    #[serde(rename = "type", borrow)]
+    event_type: Cow<'a, str>,
+    #[serde(borrow)]
+    response: Option<ResponseIdentity<'a>>,
+}
+
+#[derive(Deserialize)]
+struct ResponseIdentity<'a> {
+    #[serde(borrow)]
+    id: Cow<'a, str>,
+}
+
+#[derive(Default)]
+pub(super) struct ResponseInterrupt {
+    delivered_ids: BTreeSet<String>,
+    current: Option<(String, ResponseControlBinding)>,
+    pending: Option<Value>,
+    sent: bool,
+}
+
+impl ResponseInterrupt {
+    pub(super) fn created_id(payload: &str) -> Option<String> {
+        let event: EventIdentity<'_> = serde_json::from_str(payload).ok()?;
+        (event.event_type == "response.created").then_some(())?;
+        Some(event.response?.id.into_owned())
+    }
+
+    /// 只在 created 实际写入下游后更新，不能把未交付的 ID 当成客户端目标
+    pub(super) fn observe_created(&mut self, id: String, control: &ResponseControl) {
+        let Some(binding) = control.binding() else {
+            return;
+        };
+        if self
+            .current
+            .as_ref()
+            .is_none_or(|(previous, old)| previous != &id || !old.same_binding(&binding))
+        {
+            self.sent = false;
+        }
+        self.delivered_ids.insert(id.clone());
+        self.current = Some((id, binding));
+    }
+
+    /// 未知控制消息、模式和其他逻辑响应的 ID 仍走原始透明通道
+    pub(super) fn retain(&mut self, payload: &str) -> bool {
+        let Ok(event) = serde_json::from_str::<Value>(payload) else {
+            return false;
+        };
+        if event["type"] != "response.interrupt"
+            || event["mode"] != "discard_partial_items"
+            || !event["response_id"]
+                .as_str()
+                .is_some_and(|id| self.delivered_ids.contains(id))
+        {
+            return false;
+        }
+        self.pending = Some(event);
+        self.sent = false;
+        true
+    }
+
+    pub(super) async fn forward_pending(&mut self, control: &ResponseControl) {
+        if self.sent {
+            return;
+        }
+        let (Some(payload), Some((id, binding))) = (&mut self.pending, &self.current) else {
+            return;
+        };
+        // 换号已绑定、created 尚未交付时等待新 ID；连接快照保证 await 期间也不会串号
+        if !control
+            .binding()
+            .is_some_and(|current| binding.same_binding(&current))
+        {
+            return;
+        }
+        payload["response_id"] = Value::String(id.clone());
+        if binding.send(&payload.to_string()).await.is_ok() {
+            self.sent = true;
+        }
+    }
+}
@@ -2,6 +2,7 @@

 pub mod connection;
 mod forward;
+mod interrupt;
 mod protocol;

 use std::{
@@ -24,6 +25,7 @@ use gateway_core::{
    engine::{
        execution::{AuthenticatedClient, ClientTransport},
        middleware::{FrozenMiddlewarePlan, MiddlewareError},
+        response_control::ResponseControl,
    },
    lifecycle::{ConnectionGuard, ConnectionLifecycle},
    operation::OperationKind,
@@ -46,11 +48,12 @@ use super::{
 };
 use connection::{ConnectionEvent, FramePhase, ResponsesWebSocketConnection, WriteContext};
 use forward::{
-    ConnectionReplaySnapshot, ForwardOutcome, execution_response, forward_response,
-    new_replay_capture, send_gateway_error, send_middleware_error, send_protocol_error,
+    ConnectionReplaySnapshot, ForwardOutcome, execution_response, forward_control_event,
+    forward_response, new_replay_capture, send_control, send_gateway_error, send_middleware_error,
+    send_protocol_error,
 };
-use protocol::connection_limit_event;
 pub use protocol::{ResponseCreateFrameError, decode_response_create_with_context};
+use protocol::{connection_limit_event, is_response_create};

 const TEXT_FRAMES_ONLY: &str = "Responses WebSocket accepts text frames only";
 const CONNECTION_LIMIT_CLOSE_REASON: &str = "Responses websocket connection limit reached";
@@ -191,10 +194,20 @@ async fn serve_responses_websocket(socket: WebSocket, session: ResponsesWebSocke
    );
    let mut request_count = 0_u64;
    let mut replay = ConnectionReplaySnapshot::default();
+    let mut response_control = ResponseControl::default();

    loop {
-        let Some(event) = connection.next_event().await else {
-            break;
+        let event = tokio::select! {
+            event = connection.next_event() => {
+                let Some(event) = event else { break };
+                event
+            }
+            event = response_control.receive() => {
+                if forward_control_event(&mut connection, &response_control, event).await == ForwardOutcome::Disconnect {
+                    break;
+                }
+                continue;
+            }
        };
        let payload = match event {
            ConnectionEvent::Text(payload) => payload,
@@ -212,8 +225,22 @@ async fn serve_responses_websocket(socket: WebSocket, session: ResponsesWebSocke
            expire_connection(&mut connection).await;
            break;
        }
-        request_count = request_count.saturating_add(1);
        let correlation_id = Arc::<str>::from(service.next_request_id());
+        if !is_response_create(&payload) {
+            if send_control(
+                &mut connection,
+                &response_control,
+                &payload,
+                &correlation_id,
+            )
+            .await
+                == ForwardOutcome::Disconnect
+            {
+                break;
+            }
+            continue;
+        }
+        request_count = request_count.saturating_add(1);
        // 初步解码只保留路由事实，避免整份正文跨越准入等待和响应交付
        let model_hint = match decode_response_create_with_context(&payload, &request_headers) {
            Ok(decoded) => Some(decoded.metadata().requested_model().to_owned()),
@@ -251,6 +278,7 @@ async fn serve_responses_websocket(socket: WebSocket, session: ResponsesWebSocke
            expire_connection(&mut connection).await;
            break;
        }
+        response_control.clear();
        let execution = service.execution();
        let preparation = async {
            // 握手的显式改写可继承，Key 策略与宿主设置仍在每轮执行前刷新
@@ -291,7 +319,7 @@ async fn serve_responses_websocket(socket: WebSocket, session: ResponsesWebSocke
            }
        };
        let request_id = Arc::<str>::from(prepared.request_id().to_string());
-        let response_control = prepared.response_control();
+        response_control = prepared.response_control();
        let capture = new_replay_capture();
        let validation = ResponseValidationFacts::default();
        let input = RequestInput {
@@ -381,7 +409,7 @@ async fn serve_responses_websocket(socket: WebSocket, session: ResponsesWebSocke
            &mut replay,
            capture,
            validation,
-            response_control,
+            &response_control,
        )
        .await
            == ForwardOutcome::Disconnect
@@ -31,42 +31,22 @@ pub fn decode_response_create_with_context(
    decode_response_create_inner(payload, request_headers)
 }

-/// 中断只引用活动响应；普通创建帧仍交给原有解码与串行准入路径
-pub(super) fn decode_response_interrupt(
-    payload: &str,
-) -> Result<Option<String>, ResponseCreateFrameError> {
+/// 只识别需要本地准入的创建帧，其余文本不在网关解释
+pub(super) fn is_response_create(payload: &str) -> bool {
    #[derive(serde::Deserialize)]
    struct FrameType {
        #[serde(rename = "type")]
-        message_type: Option<String>,
+        message_type: String,
    }
-    // 非控制帧仍在原来的串行请求边界校验，不能抢先拒绝排队的普通请求
    // 只投影类型，避免为排队的大型 response.create 再构造完整 JSON 树
-    let Ok(frame) = serde_json::from_str::<FrameType>(payload) else {
-        return Ok(None);
-    };
-    if frame.message_type.as_deref() != Some("response.interrupt") {
-        return Ok(None);
+    match serde_json::from_str::<FrameType>(payload) {
+        Ok(frame) => frame.message_type == "response.create",
+        // struct 投影拒绝重复 type；沿用创建解码器的 JSON object 语义，
+        // 避免这类创建请求绕过准入进入透传路径
+        Err(_) => serde_json::from_str::<Value>(payload).is_ok_and(|frame| {
+            frame.get("type").and_then(Value::as_str) == Some("response.create")
+        }),
    }
-    let value: Value =
-        serde_json::from_str(payload).map_err(|_| ResponseCreateFrameError::InvalidJson)?;
-    if value.get("mode").and_then(Value::as_str) != Some("discard_partial_items") {
-        return Err(ResponseCreateFrameError::Request(
-            RequestDecodeError::InvalidValue {
-                field: "mode".to_owned(),
-            },
-        ));
-    }
-    let id = value
-        .get("response_id")
-        .and_then(Value::as_str)
-        .filter(|id| !id.is_empty())
-        .ok_or_else(|| {
-            ResponseCreateFrameError::Request(RequestDecodeError::InvalidValue {
-                field: "response_id".to_owned(),
-            })
-        })?;
-    Ok(Some(id.to_owned()))
 }

 fn decode_response_create_inner(
--- a/Show More
+++ b/Show More