chore(release): v3.27.0

Co-authored-by: Codex <noreply@openai.com>

.agents/skills/cpr-plugin-dev/references/implementation.md

@@ -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

.github/actions/cargo-cache/cargo-cache.sh

@@ -42,8 +42,11 @@ else
   mkdir -p "$(dirname "$directory")"
   temporary="$(mktemp -d "${directory}.XXXXXX")"
   trap 'rm -rf "$temporary"' EXIT
-  mkdir "$temporary/context"
-  "${command[@]}" --output "type=local,dest=$temporary/snapshot" "$temporary/context"
+  mkdir "$temporary"/{context,snapshot}
+  # tar 流避开 local exporter 的逐文件同步阻塞，直接解包以免额外落盘整份归档。
+  # https://github.com/moby/buildkit/issues/2950
+  "${command[@]}" --output type=tar,dest=- "$temporary/context" \
+    | tar -xf - -C "$temporary/snapshot"
   if usable "$temporary/snapshot"; then
     rm -rf "$directory"
     mv "$temporary/snapshot" "$directory"

.github/workflows/release.yml

@@ -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,

backend/Cargo.lock

@@ -145,6 +145,18 @@ dependencies = [
  "serde_json",
 ]
 
+[[package]]
+name = "async-compression"
+version = "0.4.50"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ee19bd99b43e3691acbad4e840420a4881cea6c0b66a208125a824f8fd53f5a1"
+dependencies = [
+ "compression-codecs",
+ "compression-core",
+ "pin-project-lite",
+ "tokio",
+]
+
 [[package]]
 name = "async-lock"
 version = "3.4.2"
@@ -931,6 +943,23 @@ dependencies = [
  "tokio-util",
 ]
 
+[[package]]
+name = "compression-codecs"
+version = "0.4.45"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "98fc98460ba0ad5317075d3632b8dfc45d0be8c4a49347c2a38272019717614a"
+dependencies = [
+ "compression-core",
+ "flate2",
+ "memchr",
+]
+
+[[package]]
+name = "compression-core"
+version = "0.4.33"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6e8ccc4ea9f6acc32d102c0f6d471d11d913ad15f20c04de743374861fa1d414"
+
 [[package]]
 name = "config"
 version = "0.15.27"
@@ -1681,6 +1710,7 @@ dependencies = [
  "gateway-core",
  "heck",
  "hex",
+ "hkdf",
  "prettyplease",
  "quote",
  "rand_core 0.6.4",
@@ -1980,9 +2010,9 @@ 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 +2476,9 @@ 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 +2504,18 @@ 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",
@@ -3289,6 +3319,7 @@ dependencies = [
  "native-tls",
  "openssl",
  "openssl-sys",
+ "regex",
  "reqwest",
  "roxmltree",
  "rustls",
@@ -3400,9 +3431,9 @@ 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",
@@ -3586,9 +3617,9 @@ 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",
@@ -3603,9 +3634,9 @@ 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",
@@ -3748,9 +3779,9 @@ dependencies = [
 
 [[package]]
 name = "rustls"
-version = "0.23.45"
+version = "0.23.46"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0d41d731c7d2f962d1ccc364cec258de3c0e93b38c2fb3ba97ac74513048d634"
+checksum = "48e13bd8c0e9365c43cfa5c9e8f9ad49d3c8444926c9aac819e0e4dc503c8fdf"
 dependencies = [
  "aws-lc-rs",
  "log",
@@ -4503,7 +4534,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "32497e9a4c7b38532efcdebeef879707aa9f794296a4f0244f6f69e9bc8574bd"
 dependencies = [
  "fastrand",
- "getrandom 0.3.4",
+ "getrandom 0.4.3",
  "once_cell",
  "rustix",
  "windows-sys 0.61.2",
@@ -4741,6 +4772,7 @@ version = "0.7.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "08a05a66a4fdd61cbbe0a1d755ffe0ca6aba159dd4820936a0ff8a8278245b9c"
 dependencies = [
+ "async-compression",
  "bitflags",
  "bytes",
  "futures-core",
@@ -5005,9 +5037,9 @@ 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",
@@ -5545,9 +5577,9 @@ 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",
 ]

backend/apps/gateway/src/bootstrap/server.rs

@@ -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(
@@ -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())

backend/apps/gateway/tests/architecture.rs

@@ -4,6 +4,7 @@ use std::{
     collections::{BTreeMap, BTreeSet},
     fs,
     path::{Path, PathBuf},
+    sync::OnceLock,
 };
 
 use syn::{Item, visit::Visit};
@@ -26,22 +27,24 @@ pub(super) const WORKSPACE_MEMBERS: &[&str] = &[
 
 #[test]
 fn workspace_member_list_matches_the_frozen_dag_scope() {
-    let manifest =
-        fs::read_to_string(backend_root().join("Cargo.toml")).expect("read workspace manifest");
-    for member in WORKSPACE_MEMBERS {
-        assert!(
-            manifest.contains(&format!("\"{member}\"")),
-            "workspace must include {member}"
-        );
-    }
-    let member_count = manifest
-        .lines()
-        .map(str::trim)
-        .filter(|line| line.starts_with("\"apps/") || line.starts_with("\"crates/"))
-        .count();
+    let metadata = cargo_metadata_json();
+    let root = backend_root();
+    let actual: BTreeSet<_> = metadata["packages"]
+        .as_array()
+        .expect("Cargo packages")
+        .iter()
+        .map(|package| {
+            Path::new(package["manifest_path"].as_str().expect("package manifest"))
+                .parent()
+                .expect("package directory")
+                .strip_prefix(&root)
+                .expect("workspace member path")
+                .to_path_buf()
+        })
+        .collect();
     assert_eq!(
-        member_count,
-        WORKSPACE_MEMBERS.len(),
+        actual,
+        WORKSPACE_MEMBERS.iter().map(PathBuf::from).collect(),
         "new workspace members must extend the dependency DAG rules"
     );
 }
@@ -378,7 +381,7 @@ const ALLOWED_INTERNAL_EDGES: &[(&str, &str)] = &[
 #[test]
 fn workspace_internal_dependency_edges_match_frozen_dag() {
     let metadata = cargo_metadata_json();
-    let actual = workspace_runtime_dependency_edges(&metadata);
+    let actual = workspace_runtime_dependency_edges(metadata);
     let mut expected: Vec<(String, String)> = ALLOWED_INTERNAL_EDGES
         .iter()
         .map(|(from, to)| ((*from).to_owned(), (*to).to_owned()))
@@ -474,24 +477,6 @@ fn adapter_public_module_surfaces_match_allowlist() {
     }
 }
 
-#[test]
-fn production_sources_do_not_host_tests() {
-    for member in WORKSPACE_MEMBERS {
-        let src = backend_root().join(member).join("src");
-        let sources = super::rust_files(&src);
-        assert!(!sources.is_empty(), "{member} has no production sources");
-        for relative in sources {
-            let path = src.join(relative);
-            let source = fs::read_to_string(&path).expect("read production source");
-            assert!(
-                !source.contains("#[cfg(test)]"),
-                "{} hosts tests in production src",
-                path.display()
-            );
-        }
-    }
-}
-
 #[test]
 fn workspace_modules_follow_conventional_file_layout() {
     let targets = test_source_roots();
@@ -748,40 +733,46 @@ pub(super) fn backend_root() -> PathBuf {
         .expect("backend workspace root")
 }
 
-fn cargo_metadata_json() -> serde_json::Value {
-    let output = std::process::Command::new("cargo")
-        .args(["metadata", "--format-version", "1", "--no-deps"])
-        .current_dir(backend_root())
-        .output()
-        .expect("run cargo metadata");
-    assert!(
-        output.status.success(),
-        "cargo metadata failed: {}",
-        String::from_utf8_lossy(&output.stderr)
-    );
-    serde_json::from_slice(&output.stdout).expect("parse cargo metadata")
+fn cargo_metadata_json() -> &'static serde_json::Value {
+    static METADATA: OnceLock<serde_json::Value> = OnceLock::new();
+    METADATA.get_or_init(|| {
+        let output = std::process::Command::new("cargo")
+            .args(["metadata", "--format-version", "1", "--no-deps", "--locked"])
+            .current_dir(backend_root())
+            .output()
+            .expect("run cargo metadata");
+        assert!(
+            output.status.success(),
+            "cargo metadata failed: {}",
+            String::from_utf8_lossy(&output.stderr)
+        );
+        serde_json::from_slice(&output.stdout).expect("parse cargo metadata")
+    })
 }
 
-/// 提取成员 `[dependencies]` 段内声明的依赖名;段落以下一个 `[` 表头结束
+/// 复用 Cargo 解析后的实际包名，覆盖重命名依赖与平台条件，排除测试和构建依赖
 fn dependency_names(member: &str) -> Vec<String> {
-    let manifest = fs::read_to_string(backend_root().join(member).join("Cargo.toml"))
-        .expect("read member manifest");
-    let mut in_dependencies = false;
-    let mut names = Vec::new();
-    for line in manifest.lines() {
-        let line = line.trim();
-        if line.starts_with('[') {
-            in_dependencies = line == "[dependencies]";
-            continue;
-        }
-        if !in_dependencies || line.is_empty() || line.starts_with('#') {
-            continue;
-        }
-        if let Some((name, _)) = line.split_once('=') {
-            names.push(name.trim().to_owned());
-        }
-    }
-    names
+    let manifest = backend_root().join(member).join("Cargo.toml");
+    let package = cargo_metadata_json()["packages"]
+        .as_array()
+        .expect("Cargo packages")
+        .iter()
+        .find(|package| {
+            Path::new(package["manifest_path"].as_str().expect("package manifest")) == manifest
+        })
+        .expect("workspace member");
+    package["dependencies"]
+        .as_array()
+        .expect("package dependencies")
+        .iter()
+        .filter(|dependency| dependency["kind"].is_null())
+        .map(|dependency| {
+            dependency["name"]
+                .as_str()
+                .expect("dependency name")
+                .to_owned()
+        })
+        .collect()
 }
 
 fn assert_no_dependency(member: &str, forbidden: &[&str]) {

backend/apps/gateway/tests/main.rs

@@ -59,9 +59,16 @@ fn cargo_library_root_is_conventional_lib() {
 fn workspace_production_files_have_no_hidden_modules_or_test_hooks() {
     for member in architecture::WORKSPACE_MEMBERS {
         let root = architecture::backend_root().join(member).join("src");
-        for relative in rust_files(&root) {
+        let sources = rust_files(&root);
+        assert!(!sources.is_empty(), "{member} has no production sources");
+        for relative in sources {
             let path = root.join(relative);
             let source = fs::read_to_string(&path).expect("read production source");
+            assert!(
+                !source.contains("#[cfg(test)]"),
+                "{} hosts tests in production src",
+                path.display()
+            );
             assert!(
                 !source.contains("include!("),
                 "{} uses include!",

backend/crates/gateway-admin/Cargo.toml

@@ -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"] }

backend/crates/gateway-admin/src/backup/task.rs

@@ -491,11 +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(());
@@ -533,16 +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?;
             }
@@ -556,11 +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?;
             }
@@ -568,6 +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,

backend/crates/gateway-admin/src/lib.rs

@@ -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,
@@ -405,9 +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(),
@@ -441,11 +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,
     ));
@@ -506,7 +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(),

backend/crates/gateway-admin/src/model/account_groups.rs

@@ -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,
 }
 

backend/crates/gateway-admin/src/model/accounts.rs

@@ -124,6 +124,7 @@ pub struct AccountRecord {
     pub weight: AccountWeight,
     pub model_access: gateway_core::account::AccountModelAccess,
     pub outbound_proxy: Option<gateway_core::account::OutboundProxy>,
+    pub outbound_proxy_enabled: bool,
     pub credential_state: CredentialState,
     pub credential_observed_at: DateTime<Utc>,
     pub quota: QuotaState,
@@ -133,6 +134,16 @@ pub struct AccountRecord {
     pub updated_at: DateTime<Utc>,
 }
 
+impl AccountRecord {
+    /// 配置保留绑定，执行请求时禁用代理按直连处理
+    #[must_use]
+    pub fn effective_outbound_proxy(&self) -> Option<&gateway_core::account::OutboundProxy> {
+        self.outbound_proxy
+            .as_ref()
+            .filter(|_| self.outbound_proxy_enabled)
+    }
+}
+
 pub use super::observability::{
     AccountModelUsage, AccountPoolMetrics as AccountSummary, AccountRequestBucket,
     CurrencyCost as AccountCost,
@@ -146,9 +157,9 @@ 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,

backend/crates/gateway-admin/src/model/analytics.rs

@@ -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>,
+}

backend/crates/gateway-admin/src/model/auth.rs

@@ -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

backend/crates/gateway-admin/src/model/backup/mod.rs

@@ -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

backend/crates/gateway-admin/src/model/mod.rs

@@ -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;

backend/crates/gateway-admin/src/model/observability.rs

@@ -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>,
@@ -178,7 +182,7 @@ pub struct UsageQuery {
 }
 
 /// 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)]
+#[derive(Debug, Clone, PartialEq, Eq, Hash)]
 pub struct DashboardQuery {
     pub range: TimeRange,
     pub granularity: Granularity,
@@ -230,7 +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,
@@ -363,8 +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,
 }
 
@@ -380,8 +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,
 }
 
@@ -408,7 +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,
@@ -454,9 +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,
@@ -496,7 +500,7 @@ 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,
@@ -556,9 +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,
@@ -591,9 +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,
@@ -628,7 +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>,
 }
@@ -636,6 +640,7 @@ 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,
@@ -657,9 +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>,
@@ -669,9 +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>,
@@ -750,9 +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>,
@@ -830,9 +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>,
@@ -862,6 +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,
@@ -878,6 +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>,
 }
@@ -1001,7 +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>,
@@ -1019,6 +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,
@@ -1134,7 +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>,
@@ -1224,7 +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>,
@@ -1249,7 +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>,
@@ -1259,6 +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,
@@ -1294,6 +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>,
 }

backend/crates/gateway-admin/src/model/proxies.rs

@@ -69,6 +69,7 @@ pub struct ProxyTestResult {
 
 #[derive(Debug, Clone)]
 pub struct ProxyRecord {
+    pub enabled: bool,
     pub auto_location: bool,
     pub detected_location: Option<DetectedProxyLocation>,
     pub location: Option<gateway_core::account::RequestLocation>,
@@ -103,6 +104,7 @@ pub struct NewProxy {
 
 #[derive(Debug, Clone)]
 pub struct UpdateProxy {
+    pub enabled: Option<bool>,
     pub auto_location: Option<bool>,
     pub test: Option<ProxyTestResult>,
     /// 外层为空保留配置，内层为空恢复全局继承

backend/crates/gateway-admin/src/model/quota_forecast_sampling.rs

@@ -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);

backend/crates/gateway-admin/src/model/settings.rs

@@ -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);

backend/crates/gateway-admin/src/ports/provider.rs

@@ -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()

backend/crates/gateway-admin/src/ports/store.rs

@@ -6,7 +6,6 @@ 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::{
@@ -30,7 +29,8 @@ use crate::model::{
     observability::{
         DashboardObservation, DashboardQuery, DiagnosticDimension, DiagnosticsObservation,
         Granularity, OpsErrorPage, OpsErrorQuery, RequestMetricPoint, TimeRange,
-        UsageCalculatedBillingFact, UsageDetail, UsageFilter, UsageOverview, UsagePage, UsageQuery,
+        UsageBillingProjection, UsageCalculatedBillingFact, UsageDetail, UsageFilter,
+        UsageInsightsObservation, UsageOverview, UsagePage, UsageQuery,
     },
     provider_credentials::{
         AuthorizationCommit, CredentialDetails, CredentialImportCommit, CredentialImportResult,
@@ -294,12 +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>>;
@@ -421,13 +421,23 @@ 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,
@@ -448,14 +458,13 @@ pub trait ObservabilityStore: Send + Sync {
         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,
         granularity: Granularity,
-    ) -> UsageCalculatedBillingStream<'_>;
+    ) -> AdminStoreResult<UsageInsightsObservation>;
 
     async fn list_usage_records(&self, query: UsageQuery) -> AdminStoreResult<UsagePage>;
 

backend/crates/gateway-admin/src/public_service/settings.rs

@@ -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,

backend/crates/gateway-admin/src/use_case/auth/mod.rs

@@ -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()))
+}

backend/crates/gateway-admin/src/use_case/auth/service.rs

@@ -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()))
-}

backend/crates/gateway-admin/src/use_case/auth/session.rs

@@ -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",
+        ))
+    }
+}

backend/crates/gateway-admin/src/use_case/credential_mutation.rs

@@ -106,7 +106,8 @@ pub(super) async fn pending_authorization(
             proxy = required_credential(accounts, provider_kind, account_id, resource)
                 .await?
                 .credential
-                .outbound_proxy;
+                .effective_outbound_proxy()
+                .cloned();
             AuthorizationMutationTarget::Reauthorize {
                 account_id: account_id.clone(),
             }
@@ -121,6 +122,9 @@ pub(super) async fn pending_authorization(
                         .await
                         .map_err(|error| map_store_error(error, "proxy"))?;
                     proxy_id = Some(record.id);
+                    if !record.enabled {
+                        return Err(AdminError::invalid("代理已禁用，请启用后再选择"));
+                    }
                     Some(record.proxy)
                 }
                 Some(AccountProxySelection::Direct) | None => None,

backend/crates/gateway-admin/src/use_case/key_usage.rs

@@ -192,10 +192,12 @@ 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, Granularity::for_range(query.range)),
+        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),
@@ -205,8 +207,8 @@ impl KeyUsageService for DefaultKeyUsageService {
         .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)?,
         }))
     }

backend/crates/gateway-admin/src/use_case/observability/mod.rs

@@ -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::{
@@ -21,16 +19,16 @@ use crate::{
             DiagnosticDimension, DiagnosticsItem, DiagnosticsResult, Granularity, 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,
+            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(),
         }
     }
 
@@ -185,7 +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
@@ -199,7 +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
@@ -247,15 +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)
     }
 
@@ -264,12 +211,16 @@ impl ObservabilityService for DefaultObservabilityService {
         range: TimeRange,
         kind: TrendKind,
     ) -> Result<Trend, AdminError> {
-        let points = self
+        let observation = self
             .store
-            .dashboard_trend(range, Granularity::for_range(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> {
@@ -321,21 +272,22 @@ impl ObservabilityService for DefaultObservabilityService {
         filter: UsageFilter,
     ) -> Result<UsageInsights, AdminError> {
         let granularity = Granularity::for_range(range);
-        let aggregates = async {
-            futures::try_join!(
-                self.store.usage_summary(range, filter.clone()),
-                self.store.usage_trend(range, filter.clone(), granularity),
-            )
-            .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(), granularity),
-            ),
-        )?;
+        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)
     }
 
@@ -389,7 +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> {
@@ -423,8 +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,
@@ -442,17 +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(),
@@ -533,14 +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()
@@ -548,7 +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(),
@@ -558,7 +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(
@@ -571,6 +530,7 @@ fn build_usage_insights(
         coverage: overview.attempts.cost_coverage.clone(),
     };
     Ok(UsageInsights {
+        analytics: overview.analytics,
         granularity,
         health,
         performance,
@@ -620,58 +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(
@@ -682,19 +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()
@@ -704,7 +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())?
@@ -829,8 +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) {
@@ -861,8 +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) {
@@ -951,7 +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();
@@ -986,7 +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,
@@ -1007,13 +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,
@@ -1044,12 +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,
@@ -1070,11 +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
 }
 
@@ -1091,13 +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
@@ -1145,20 +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) {
@@ -1177,15 +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 {
@@ -1200,9 +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)
 }

backend/crates/gateway-admin/src/use_case/observability/store_cache.rs

@@ -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
+    }
+}

backend/crates/gateway-admin/src/use_case/plugins/distribution.rs

@@ -305,6 +305,9 @@ impl PluginsService {
             .get(id)
             .await
             .map_err(|error| map_store_error(error, "proxy"))?;
+        if !record.enabled {
+            return Err(AdminError::invalid("下载代理已禁用，请启用或改为直连"));
+        }
         Ok(Some(PluginDistributionEgress::new(
             record.id,
             record.revision,

backend/crates/gateway-admin/src/use_case/settings.rs

@@ -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()

backend/crates/gateway-admin/tests/backup/support.rs

@@ -536,6 +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 {
@@ -543,6 +546,9 @@ impl FakeObjectStore {
         Self {
             objects: Mutex::new(std::collections::HashMap::new()),
             upload_error: None,
+            head_error: None,
+            delete_error: None,
+            connection_error: None,
         }
     }
 
@@ -552,6 +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()
     }
@@ -563,6 +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",
@@ -597,6 +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);
         };
@@ -613,6 +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(())
     }
@@ -690,11 +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)
     }

backend/crates/gateway-admin/tests/backup/task.rs

@@ -324,3 +324,58 @@ async fn completed_recovery_removes_staging_for_dumping_and_uploading_tasks() {
         );
     }
 }
+
+#[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
+        );
+    }
+}

backend/crates/gateway-admin/tests/main.rs

@@ -170,9 +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,

backend/crates/gateway-admin/tests/model/provider_credentials.rs

@@ -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,

backend/crates/gateway-admin/tests/model/quota_forecast.rs

@@ -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()

backend/crates/gateway-admin/tests/model/quota_forecast_sampling.rs

@@ -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(

backend/crates/gateway-admin/tests/use_case/accounts.rs

@@ -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,
@@ -2398,6 +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;
@@ -3031,9 +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,
@@ -3050,6 +3137,7 @@ fn quota_local_usage(account_id: &str, total_tokens: u64) -> AccountUsage {
 pub(super) fn account_record(kind: &str) -> AccountRecord {
     let now = Utc::now();
     AccountRecord {
+        outbound_proxy_enabled: true,
         notes: None,
         model_access: Default::default(),
         outbound_proxy: None,

backend/crates/gateway-admin/tests/use_case/auth/mod.rs

@@ -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;

backend/crates/gateway-admin/tests/use_case/auth/session.rs

@@ -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()
+    );
+}

backend/crates/gateway-admin/tests/use_case/auth_key.rs

@@ -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()));
         }

backend/crates/gateway-admin/tests/use_case/backup.rs

@@ -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
+        );
+    }
+}

backend/crates/gateway-admin/tests/use_case/freeze_recovery.rs

@@ -32,12 +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,

backend/crates/gateway-admin/tests/use_case/mod.rs

@@ -369,11 +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)
     }
@@ -747,6 +747,10 @@ 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,
         _: DashboardQuery,
@@ -772,15 +776,17 @@ impl ObservabilityStore for UnavailableStore {
         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,
         _: Granularity,
-    ) -> gateway_admin::ports::store::UsageCalculatedBillingStream<'_> {
-        Box::pin(futures::stream::once(async {
-            Err(unavailable("usage billing facts"))
-        }))
+    ) -> AdminStoreResult<gateway_admin::model::observability::UsageInsightsObservation> {
+        Err(unavailable("usage insights"))
     }
 
     async fn list_usage_records(&self, _: UsageQuery) -> AdminStoreResult<UsagePage> {

backend/crates/gateway-admin/tests/use_case/observability/mod.rs

@@ -17,13 +17,13 @@ use gateway_admin::{
     model::{
         MutationContext, Revision,
         observability::{
-            AccountPoolMetrics, AttemptMetrics, CostCoverage, CurrencyCost, DashboardAccountUsage,
-            DashboardObservation, DashboardQuery, 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();
@@ -300,7 +401,7 @@ async fn dashboard_summary_should_observe_current_accounts_for_a_historical_rang
 }
 
 #[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");
@@ -330,7 +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]
@@ -403,6 +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 {
@@ -431,23 +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)],
     });
@@ -543,6 +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],
     });
@@ -566,6 +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))
@@ -591,6 +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],
     });
@@ -691,26 +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
@@ -741,9 +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,
@@ -783,8 +868,9 @@ 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>>>,
@@ -794,6 +880,7 @@ struct FixtureObservabilityStore {
     account_usage: Mutex<Vec<DashboardAccountUsage>>,
     dashboard_delay: Mutex<StdDuration>,
     dashboard_summary_calls: AtomicUsize,
+    usage_summary_filters: Mutex<Vec<UsageFilter>>,
 }
 
 impl FixtureObservabilityStore {
@@ -801,13 +888,15 @@ 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),
@@ -817,6 +906,7 @@ impl FixtureObservabilityStore {
             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()),
         }
     }
 
@@ -836,11 +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) {
@@ -858,6 +945,10 @@ 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,
         query: DashboardQuery,
@@ -874,6 +965,7 @@ impl ObservabilityStore for FixtureObservabilityStore {
             tokio::time::sleep(dashboard_delay).await;
         }
         Ok(DashboardObservation {
+            analytics: self.overview.lock().expect("overview").analytics.clone(),
             range: query.range,
             totals: Default::default(),
             provider_accounts: AccountPoolMetrics::default(),
@@ -902,25 +994,29 @@ impl ObservabilityStore for FixtureObservabilityStore {
         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,
         granularity: Granularity,
-    ) -> gateway_admin::ports::store::UsageCalculatedBillingStream<'_> {
+    ) -> AdminStoreResult<UsageInsightsObservation> {
         self.usage_granularities.lock().unwrap().push(granularity);
-        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),
-        ))
+        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> {
@@ -938,8 +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(
@@ -988,12 +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,
@@ -1113,9 +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),
@@ -1228,9 +1342,204 @@ async fn admin_selects_dashboard_defaults_and_matching_usage_buckets_at_range_bo
             .usage_insights(range, UsageFilter::default())
             .await
             .unwrap();
-        assert_eq!(
-            *store.usage_granularities.lock().unwrap(),
-            vec![expected, expected]
+        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}"
         );
     }
 }

backend/crates/gateway-admin/tests/use_case/plugins/distribution.rs

@@ -534,6 +534,7 @@ fn preview_fixture() -> Fixture {
 fn source_proxy() -> ProxyRecord {
     let now = chrono::Utc::now();
     ProxyRecord {
+        enabled: true,
         auto_location: false,
         detected_location: None,
         location: None,
@@ -608,6 +609,38 @@ async fn saved_source_proxy_is_resolved_for_queries_and_frozen_into_verified_sou
     );
 }
 
+#[tokio::test]
+async fn disabled_source_proxy_rejects_queries_and_downloads_before_network_access() {
+    let mut fixture = preview_fixture();
+    fixture.binding.get_mut().unwrap().outbound_proxy_id = Some("source-proxy".into());
+    let mut proxy = source_proxy();
+    proxy.enabled = false;
+    *fixture.proxy.get_mut().unwrap() = Some(proxy);
+    let fixture = Arc::new(fixture);
+    assert_eq!(
+        fixture
+            .service()
+            .check_update("test.example", &[])
+            .await
+            .unwrap_err()
+            .kind(),
+        AdminErrorKind::Invalid
+    );
+    let mut request = preview_request();
+    request.outbound_proxy_id = Some("source-proxy".into());
+    assert_eq!(
+        fixture
+            .service()
+            .verify_remote(request)
+            .await
+            .unwrap_err()
+            .kind(),
+        AdminErrorKind::Invalid
+    );
+    assert!(fixture.egresses.lock().unwrap().is_empty());
+    assert_eq!(*fixture.downloads.lock().unwrap(), 0);
+}
+
 #[tokio::test]
 async fn proxy_revision_change_during_download_rejects_the_verified_candidate() {
     let mut fixture = preview_fixture();

backend/crates/gateway-admin/tests/use_case/proxies.rs

@@ -126,6 +126,7 @@ async fn authorization_uses_selected_proxy_regardless_of_probe_status() {
                 .accounts(FakeAccountStore::new(kind, events.clone()))
                 .proxies(Arc::new(TestProxies {
                     record: Some(ProxyRecord {
+                        enabled: true,
                         auto_location: false,
                         detected_location: None,
                         location: None,

backend/crates/gateway-admin/tests/use_case/service_contract.rs

@@ -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 +80,11 @@ fn contract_type(mut item: Item, name: &str) -> Item {
                     | "ReplaceRuntimeSettings"
                     | "AdminApiKeyMutation"
                     | "RegeneratedAdminApiKey"
+                    | "CodexPrivacyPolicy"
+                    | "PrivacyRule"
+                    | "PrivacyStep"
+                    | "PrivacyPreviewRequest"
+                    | "PrivacyPreviewResult"
             );
             (
                 &mut item.attrs,
@@ -107,6 +113,13 @@ 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 +130,20 @@ 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",
+                "PrivacyStep",
+                "PrivacyRuleOutcome",
+                "PrivacyPreviewRequest",
+                "PrivacyPreviewResult",
+            ][..],
+        ),
         (
             "src/model/settings.rs",
             &[

backend/crates/gateway-admin/tests/use_case/settings.rs

@@ -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,

backend/crates/gateway-api/Cargo.toml

@@ -32,7 +32,7 @@ sha2 = "0.11.0"
 thiserror = "2.0.18"
 tokio = { version = "1.52.3", default-features = false, features = ["macros", "rt", "sync", "time"] }
 tower = { version = "0.5.3", features = ["util"] }
-tower-http = { version = "0.7.0", features = ["cors", "fs", "request-id", "timeout", "trace"] }
+tower-http = { version = "0.7.0", features = ["compression-gzip", "cors", "fs", "request-id", "timeout", "trace"] }
 tracing = "0.1.44"
 url = "2.5.8"
 uuid = { version = "1.23.3", features = ["v7"] }

backend/crates/gateway-api/src/admin/accounts/presenter.rs

@@ -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(),

backend/crates/gateway-api/src/admin/accounts/wire.rs

@@ -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>,

backend/crates/gateway-api/src/admin/compression.rs

@@ -0,0 +1,25 @@
+//! 管理端普通 JSON 响应的压缩范围与大小门槛
+
+use http::{Response, header};
+use http_body::Body;
+use tower_http::compression::predicate::Predicate;
+
+#[derive(Clone, Copy)]
+pub(super) struct AdminJson;
+
+impl Predicate for AdminJson {
+    fn should_compress<B: Body>(&self, response: &Response<B>) -> bool {
+        // 只处理长度已知的 JSON，不为判断门槛收集流式正文
+        response
+            .body()
+            .size_hint()
+            .exact()
+            .is_some_and(|size| size >= 1024)
+            && 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("application/json"))
+    }
+}

backend/crates/gateway-api/src/admin/mod.rs

@@ -9,12 +9,14 @@ use axum::{
     response::Response,
     routing::any,
 };
+use tower_http::compression::{CompressionLayer, CompressionLevel};
 
 pub mod account_groups;
 pub mod accounts;
 pub mod auth;
 pub mod backups;
 pub mod client_keys;
+mod compression;
 pub(crate) mod diagnostics;
 mod extract;
 pub mod observability;
@@ -54,6 +56,12 @@ where
         .method_not_allowed_fallback(method_not_allowed)
         .route("/api/admin", any(admin_not_found))
         .route("/api/admin/{*path}", any(admin_not_found))
+        .layer(
+            CompressionLayer::new()
+                .quality(CompressionLevel::Fastest)
+                .compress_when(compression::AdminJson),
+        )
+        .merge(plugins::public_router().method_not_allowed_fallback(method_not_allowed))
         .layer(middleware::map_response(no_store))
 }
 

backend/crates/gateway-api/src/admin/observability/presenter.rs

@@ -1,6 +1,7 @@
 //! 观测领域事实到管理页面的展示投影
 
 use super::*;
+use gateway_core::metering::Usage;
 
 pub(crate) fn display_duration(value: Option<u64>) -> String {
     let Some(value) = value.and_then(|value| i64::try_from(value).ok()) else {
@@ -58,9 +59,9 @@ 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,
     }
 }
@@ -100,74 +101,63 @@ pub(crate) fn attempt_metrics_view(metrics: &domain::AttemptMetrics) -> AttemptM
 }
 
 pub(crate) fn token_details(record: &domain::UsageRecord) -> TokenDetailsView {
-    TokenDetailsView {
+    token_details_view(&Usage {
         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,
-        input_tokens_display: record
-            .input_tokens
-            .map_or_else(|| "-".to_owned(), format_number),
-        output_tokens_display: record
-            .output_tokens
-            .map_or_else(|| "-".to_owned(), format_number),
-        cached_tokens_display: record
-            .cached_tokens
-            .map_or_else(|| "-".to_owned(), format_compact_number),
-        cache_write_tokens_display: record
-            .cache_write_tokens
-            .map_or_else(|| "-".to_owned(), format_compact_number),
-        reasoning_tokens_display: record
-            .reasoning_tokens
-            .map_or_else(|| "-".to_owned(), format_number),
-        image_input_tokens_display: record
-            .image_input_tokens
-            .map_or_else(|| "-".to_owned(), format_number),
-        image_output_tokens_display: record
-            .image_output_tokens
-            .map_or_else(|| "-".to_owned(), format_number),
-        total_tokens_display: record
-            .total_tokens
-            .map_or_else(|| "-".to_owned(), format_number),
-    }
+    })
 }
 
 pub(crate) fn usage_list_token_details(record: &domain::UsageListRecord) -> TokenDetailsView {
-    TokenDetailsView {
+    token_details_view(&Usage {
         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,
-        input_tokens_display: record
+    })
+}
+
+fn token_details_view(usage: &Usage) -> TokenDetailsView {
+    TokenDetailsView {
+        input_tokens: usage.input_tokens,
+        output_tokens: usage.output_tokens,
+        cached_input_tokens: usage.cached_input_tokens,
+        cache_write_input_tokens: usage.cache_write_input_tokens,
+        reasoning_output_tokens: usage.reasoning_output_tokens,
+        image_input_tokens: usage.image_input_tokens,
+        image_output_tokens: usage.image_output_tokens,
+        total_tokens: usage.total_tokens,
+        input_tokens_display: usage
             .input_tokens
             .map_or_else(|| "-".to_owned(), format_number),
-        output_tokens_display: record
+        output_tokens_display: usage
             .output_tokens
             .map_or_else(|| "-".to_owned(), format_number),
-        cached_tokens_display: record
-            .cached_tokens
+        cached_input_tokens_display: usage
+            .cached_input_tokens
             .map_or_else(|| "-".to_owned(), format_compact_number),
-        cache_write_tokens_display: record
-            .cache_write_tokens
+        cache_write_input_tokens_display: usage
+            .cache_write_input_tokens
             .map_or_else(|| "-".to_owned(), format_compact_number),
-        reasoning_tokens_display: record
-            .reasoning_tokens
+        reasoning_output_tokens_display: usage
+            .reasoning_output_tokens
             .map_or_else(|| "-".to_owned(), format_number),
-        image_input_tokens_display: record
+        image_input_tokens_display: usage
             .image_input_tokens
             .map_or_else(|| "-".to_owned(), format_number),
-        image_output_tokens_display: record
+        image_output_tokens_display: usage
             .image_output_tokens
             .map_or_else(|| "-".to_owned(), format_number),
-        total_tokens_display: record
+        total_tokens_display: usage
             .total_tokens
             .map_or_else(|| "-".to_owned(), format_number),
     }
@@ -430,9 +420,9 @@ pub(crate) fn usage_record_view(
         latency_ms: record.latency_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,
@@ -526,7 +516,7 @@ 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,
@@ -683,8 +673,8 @@ 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),
@@ -749,7 +739,7 @@ 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,
             },
         ],
@@ -800,6 +790,7 @@ 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
@@ -913,6 +904,7 @@ pub(crate) fn dashboard_view(
         rotation_strategy,
     } = result;
     let domain::DashboardObservation {
+        analytics,
         runtime_slots: _,
         range,
         totals,
@@ -982,6 +974,7 @@ 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 {
@@ -1013,7 +1006,7 @@ 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),
             },
         },
@@ -1046,14 +1039,18 @@ 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),
@@ -1139,7 +1136,7 @@ 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),
@@ -1150,6 +1147,7 @@ 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,
@@ -1270,7 +1268,7 @@ 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),
@@ -1302,8 +1300,10 @@ 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
@@ -1356,3 +1356,22 @@ 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,
+    }
+}

backend/crates/gateway-api/src/admin/observability/query.rs

@@ -84,7 +84,6 @@ pub struct DiagnosticsQuery {
     pub provider: Option<String>,
     pub model: Option<String>,
     pub status_code: Option<i64>,
-    pub search: Option<String>,
 }
 
 impl DiagnosticsQuery {
@@ -314,6 +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,

backend/crates/gateway-api/src/admin/observability/routes.rs

@@ -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()),
+        )),
     ))
 }
 

backend/crates/gateway-api/src/admin/observability/wire.rs

@@ -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,
@@ -162,9 +162,9 @@ pub struct UsageRecordView {
     pub latency_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,
@@ -258,7 +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>,
@@ -288,6 +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>,
@@ -306,8 +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,
@@ -388,7 +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,
 }
 
@@ -446,9 +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,
 }
 
@@ -575,6 +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,
@@ -592,11 +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,
@@ -693,7 +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>,
@@ -719,7 +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>,
@@ -741,6 +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,
@@ -778,6 +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>,
 }
@@ -852,3 +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,
+}

backend/crates/gateway-api/src/admin/plugins/management.rs

@@ -53,8 +53,19 @@ pub(super) fn router<S: SessionState + Clone + Send + Sync + 'static>() -> Route
         .route("/api/admin/plugins/extensions/{instance_id}/{artifact_sha256}/{revision}/callback-tickets", post(start_callback::<S>))
         .route("/api/admin/plugins/extensions/{instance_id}/{artifact_sha256}/{revision}/api/{*path}", any(handle::<S>))
         .route("/api/admin/plugins/extensions/{instance_id}/{artifact_sha256}/{revision}/resources/{*path}", get(resource::<S>))
-        .route("/plugins/resources/{instance_id}/{artifact_sha256}/{revision}/{*path}", get(public_resource::<S>))
-        .route("/plugins/callbacks/{instance_id}/{artifact_sha256}/{revision}/{*path}", get(callback::<S>))
+}
+
+pub(in crate::admin) fn public_router<S: SessionState + Clone + Send + Sync + 'static>() -> Router<S>
+{
+    Router::new()
+        .route(
+            "/plugins/resources/{instance_id}/{artifact_sha256}/{revision}/{*path}",
+            get(public_resource::<S>),
+        )
+        .route(
+            "/plugins/callbacks/{instance_id}/{artifact_sha256}/{revision}/{*path}",
+            get(callback::<S>),
+        )
 }
 
 pub(in crate::admin) fn model_router() -> Router<crate::ApiState> {

backend/crates/gateway-api/src/admin/plugins/mod.rs

@@ -5,7 +5,7 @@ mod distribution;
 mod instances;
 mod management;
 
-pub(super) use management::model_router;
+pub(super) use management::{model_router, public_router};
 
 #[derive(serde::Deserialize)]
 #[serde(deny_unknown_fields)]

backend/crates/gateway-api/src/admin/proxies.rs

@@ -60,6 +60,7 @@ struct CreateRequest {
 #[derive(Debug, Deserialize)]
 #[serde(rename_all = "camelCase", deny_unknown_fields)]
 struct UpdateRequest {
+    enabled: Option<bool>,
     auto_location: Option<bool>,
     #[serde(default, deserialize_with = "deserialize_location_update")]
     location: Option<Option<gateway_core::account::RequestLocation>>,
@@ -145,6 +146,7 @@ struct ProxyAccountView {
 #[derive(Serialize)]
 #[serde(rename_all = "camelCase")]
 struct ProxyView {
+    enabled: bool,
     auto_location: bool,
     detected_location: Option<gateway_admin::model::proxies::DetectedProxyLocation>,
     location: Option<gateway_core::account::RequestLocation>,
@@ -168,6 +170,7 @@ impl From<(ProxyRecord, crate::time::TimePresenter)> for ProxyView {
         let endpoint = record.proxy.endpoint();
         Self {
             auto_location: record.auto_location,
+            enabled: record.enabled,
             detected_location: record.detected_location,
             location: record.location,
             id: record.id,
@@ -419,6 +422,7 @@ where
         .proxies()
         .update(
             UpdateProxy {
+                enabled: request.enabled,
                 auto_location: request.auto_location,
                 test: None,
                 location: request.location,

backend/crates/gateway-api/src/admin/settings.rs

@@ -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),
+    ))
+}

backend/crates/gateway-api/src/admin/system.rs

@@ -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,
         }

backend/crates/gateway-api/src/auth.rs

@@ -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)
 }
 

backend/crates/gateway-api/src/key_usage/presenter.rs

@@ -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,

backend/crates/gateway-api/src/middleware/mod.rs

@@ -17,9 +17,10 @@ use axum::{
     http::{HeaderName, HeaderValue, Request, StatusCode},
     response::{IntoResponse as _, Response},
 };
-use gateway_core::engine::middleware::FrozenMiddlewarePlan;
 use gateway_core::engine::middleware::http as contract;
 use gateway_core::engine::middleware::http::Settings;
+use gateway_core::engine::middleware::{FrozenMiddlewarePlan, MiddlewareError};
+use gateway_core::error::GatewayErrorKind;
 use gateway_core::lifecycle::CancellationToken;
 use gateway_core::middleware::compose;
 use http_body::{Body as HttpBody, Frame, SizeHint};
@@ -228,6 +229,8 @@ 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,
@@ -251,12 +254,28 @@ 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"
+                                );
+                            }
+                        },
                     }
                 });
             }
             response.map(|body| Body::new(ResponseBody::new(body, guard)))
         }
+        Err(MiddlewareError::Gateway(error))
+            if error.kind() == GatewayErrorKind::MiddlewareCapacityUnavailable =>
+        {
+            crate::openai::error::gateway_error_response(&error)
+        }
         Err(error) => {
             let status = if error.is_rejected() {
                 StatusCode::FORBIDDEN

backend/crates/gateway-api/src/openai/endpoint.rs

@@ -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

backend/crates/gateway-api/src/openai/error.rs

@@ -13,6 +13,8 @@ use gateway_core::{
 };
 use serde_json::{Value, json};
 
+pub use gateway_core::engine::execution::gateway_error_from_engine;
+
 use super::responses::ProtocolErrorBody;
 
 /// OpenAI 风格错误响应
@@ -148,39 +150,6 @@ pub fn model_not_found_response() -> (StatusCode, Json<Value>) {
     )
 }
 
-/// 将 core Engine 错误收敛为稳定 Gateway 分类
-#[must_use]
-pub fn gateway_error_from_engine(error: &EngineError) -> GatewayError {
-    match error {
-        EngineError::Provider(error) => GatewayError::from_provider(error),
-        EngineError::Cancelled => {
-            GatewayError::new(GatewayErrorKind::Cancelled, "request was cancelled")
-        }
-        EngineError::Deadline => {
-            GatewayError::new(GatewayErrorKind::Timeout, "gateway request timed out")
-        }
-        EngineError::ProviderNotRegistered { .. } | EngineError::EmptyRoutingPlan => {
-            GatewayError::new(
-                GatewayErrorKind::NoAvailableProvider,
-                "no upstream provider is currently available for this request",
-            )
-        }
-        EngineError::Store(source) => {
-            GatewayError::new(GatewayErrorKind::Internal, "gateway execution failed")
-                .with_source(source.clone())
-        }
-        EngineError::ProviderMetadataMismatch
-        | EngineError::ContinuationPinMismatch
-        | EngineError::RequiredAccountMismatch
-        | EngineError::AccountOutsideClientScope
-        | EngineError::DownstreamCommitRequired
-        | EngineError::NoActiveAttempt
-        | EngineError::InvalidDeliveryState => {
-            GatewayError::new(GatewayErrorKind::Internal, "gateway execution failed")
-        }
-    }
-}
-
 /// Gateway 错误的 OpenAI HTTP 表达
 pub fn gateway_error_response(error: &GatewayError) -> Response {
     let (status, default_type, default_code) = gateway_error_contract(error.kind());
@@ -310,6 +279,11 @@ pub const fn gateway_error_contract(
             "server_error",
             "provider_infrastructure_unavailable",
         ),
+        GatewayErrorKind::MiddlewareCapacityUnavailable => (
+            StatusCode::SERVICE_UNAVAILABLE,
+            "server_error",
+            "middleware_capacity_unavailable",
+        ),
         GatewayErrorKind::ConcurrencyQueueFull => (
             StatusCode::TOO_MANY_REQUESTS,
             "rate_limit_error",

backend/crates/gateway-api/src/openai/middleware/http.rs

@@ -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))

backend/crates/gateway-api/src/openai/middleware/mod.rs

@@ -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};

backend/crates/gateway-api/src/openai/models.rs

@@ -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,
     })
 }

backend/crates/gateway-api/src/openai/responses/http.rs

@@ -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(

backend/crates/gateway-api/src/openai/responses/keepalive.rs

@@ -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)
+}

backend/crates/gateway-api/src/openai/responses/mod.rs

@@ -2,6 +2,7 @@
 
 mod error;
 mod http;
+mod keepalive;
 mod request;
 mod response;
 mod validation;

backend/crates/gateway-api/src/openai/responses/request.rs

@@ -5,7 +5,9 @@ use std::{borrow::Cow, fmt, net::IpAddr};
 use axum::http::HeaderMap;
 use base64::{Engine as _, engine::general_purpose::STANDARD};
 use bytes::Bytes;
-use gateway_core::operation::{GenerateRequest, Operation, ProtocolPayload, ProviderSessionState};
+use gateway_core::operation::{
+    ClientTurn, GenerateRequest, Operation, ProtocolPayload, ProviderSessionState,
+};
 use gateway_protocol::openai::{
     X_OPENAI_INTERNAL_CODEX_RESPONSES_LITE_HEADER, X_OPENAI_MEMGEN_REQUEST_HEADER,
     is_transport_managed_request_header,
@@ -497,12 +499,30 @@ pub(super) fn decode_request_object(
     };
     let protocol_context = request_headers.protocol_context(use_websocket, frame_turn_metadata);
 
+    let semantics =
+        gateway_protocol::openai::codex_responses_request_semantics(&object, &protocol_context);
+    let client_turn = if object.get("generate").and_then(Value::as_bool) != Some(false)
+        && semantics.request_kind.as_deref() == Some("turn")
+        && !semantics.compact
+    {
+        gateway_protocol::openai::codex_account_thread_id(&object, &protocol_context)
+            .zip(gateway_protocol::openai::codex_turn_id(
+                &object,
+                &protocol_context,
+            ))
+            .and_then(|(thread, turn)| ClientTurn::new(thread, turn))
+    } else {
+        None
+    };
+
     let payload = ProtocolPayload::json_object(OPENAI_PROTOCOL, object)
         .map_err(|_| RequestDecodeError::CanonicalContract {
             field: "request".to_owned(),
         })?
         .with_context(protocol_context);
-    let operation = Operation::Generate(GenerateRequest::from_protocol_payload(payload));
+    let operation = Operation::Generate(
+        GenerateRequest::from_protocol_payload(payload).with_client_turn(client_turn),
+    );
     Ok(DecodedResponsesRequest {
         operation,
         metadata: ResponsesRequestMetadata {

backend/crates/gateway-api/src/openai/responses/websocket/forward.rs

@@ -150,10 +150,12 @@ pub(super) async fn forward_response(
             ProviderResponseHeader::new(name, value)
         })
         .collect::<Vec<_>>();
+    let mut interrupt = super::interrupt::ResponseInterrupt::default();
     let first = match next_body_input(
         connection,
         body.as_mut(),
         response_control,
+        &mut interrupt,
         &request_id,
         false,
     )
@@ -207,6 +209,7 @@ pub(super) async fn forward_response(
                     connection,
                     body.as_mut(),
                     response_control,
+                    &mut interrupt,
                     &request_id,
                     terminal_seen,
                 )
@@ -274,11 +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);
@@ -315,6 +331,7 @@ 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 {
@@ -331,6 +348,13 @@ async fn next_body_input(
                             connection.defer(event);
                             continue;
                         }
+                        if !terminal_seen && interrupt.retain(payload) {
+                            tokio::select! {
+                                _ = connection.wait_for_exit() => return BodyInput::Disconnect,
+                                () = interrupt.forward_pending(response_control) => {}
+                            }
+                            continue;
+                        }
                         if send_control(connection, response_control, payload, request_id).await == ForwardOutcome::Disconnect {
                             return BodyInput::Disconnect;
                         }

backend/crates/gateway-api/src/openai/responses/websocket/interrupt.rs

@@ -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;
+        }
+    }
+}

backend/crates/gateway-api/src/openai/responses/websocket/mod.rs

@@ -2,6 +2,7 @@
 
 pub mod connection;
 mod forward;
+mod interrupt;
 mod protocol;
 
 use std::{

backend/crates/gateway-api/src/session_cookie.rs

@@ -4,6 +4,7 @@ use axum::http::{HeaderMap, header::ORIGIN};
 use url::Url;
 
 pub(crate) const NAME: &str = "cpr_session";
+pub(crate) const REFRESH_NAME: &str = "cpr_refresh";
 
 pub(crate) fn attributes(headers: &HeaderMap) -> &'static str {
     // HTTPS 反代回源 HTTP 不改变浏览器 Origin
@@ -19,16 +20,24 @@ pub(crate) fn attributes(headers: &HeaderMap) -> &'static str {
                 })
             });
     if http_origin {
-        "Path=/; HttpOnly; SameSite=Lax"
+        "HttpOnly; SameSite=Lax"
     } else {
-        "Path=/; Secure; HttpOnly; SameSite=Lax"
+        "Secure; HttpOnly; SameSite=Lax"
     }
 }
 
 pub(crate) fn value(headers: &HeaderMap) -> Option<String> {
+    named_value(headers, NAME)
+}
+
+pub(crate) fn refresh_value(headers: &HeaderMap) -> Option<String> {
+    named_value(headers, REFRESH_NAME)
+}
+
+fn named_value(headers: &HeaderMap, name: &str) -> Option<String> {
     let cookie = headers.get("cookie")?.to_str().ok()?;
     cookie.split(';').find_map(|part| {
         let (candidate, value) = part.trim().split_once('=')?;
-        (candidate == NAME).then(|| value.to_owned())
+        (candidate == name && !value.is_empty()).then(|| value.to_owned())
     })
 }

backend/crates/gateway-api/tests/admin/accounts/handlers.rs

@@ -12,13 +12,8 @@ use super::super::{AdminTestFixture, AdminTestState};
 #[tokio::test]
 async fn account_cooldown_returns_an_instant_and_server_formatted_recovery() {
     use chrono::{DateTime, Duration, Utc};
-    use gateway_admin::model::{
-        Revision,
-        accounts::{AccountCapacity, AccountPageItem, AccountRecord},
-    };
     use gateway_core::account::{
         AccountCooldown, AccountCooldownKind, AccountStatusFacts, CredentialState, QuotaState,
-        resolve_account_status,
     };
 
     for zone in ["Asia/Shanghai", "UTC", "Asia/Kathmandu", "America/New_York"] {
@@ -65,41 +60,7 @@ async fn account_cooldown_returns_an_instant_and_server_formatted_recovery() {
                 last_error_reason: None,
                 last_error_message: None,
             };
-            *fixture.account.lock().unwrap() = Some(AccountPageItem {
-                account: AccountRecord {
-                    id: "acct_cooldown".to_owned(),
-                    provider_kind: gateway_core::routing::ProviderKind::new("openai").unwrap(),
-                    groups: Vec::new(),
-                    name: "synthetic cooldown account".to_owned(),
-                    notes: None,
-                    email: None,
-                    upstream_user_id: None,
-                    upstream_account_id: None,
-                    plan_type: None,
-                    authentication_kind: "oauth".to_owned(),
-                    credential_revision: Revision::new(1).unwrap(),
-                    has_refresh_token: true,
-                    access_token_expires_at: None,
-                    next_refresh_at: None,
-                    enabled: true,
-                    concurrency_limit: None,
-                    weight: Default::default(),
-                    model_access: Default::default(),
-                    outbound_proxy: None,
-                    credential_state: facts.credential_state,
-                    credential_observed_at: now,
-                    quota: facts.quota,
-                    last_error_reason: None,
-                    last_error_message: None,
-                    created_at: now,
-                    updated_at: now,
-                },
-                capacity: AccountCapacity {
-                    used_slots: None,
-                    total_slots: None,
-                },
-                projection: resolve_account_status(&facts, now.into()),
-            });
+            *fixture.account.lock().unwrap() = Some(account_page_item(facts, now, "oauth"));
             let response = admin::accounts::router::<AdminTestState>()
                 .with_state(fixture.state())
                 .oneshot(
@@ -138,6 +99,133 @@ async fn account_cooldown_returns_an_instant_and_server_formatted_recovery() {
     }
 }
 
+fn account_page_item(
+    facts: gateway_core::account::AccountStatusFacts,
+    now: chrono::DateTime<chrono::Utc>,
+    authentication_kind: &str,
+) -> gateway_admin::model::accounts::AccountPageItem {
+    use gateway_admin::model::{
+        Revision,
+        accounts::{AccountCapacity, AccountPageItem, AccountRecord},
+    };
+    use gateway_core::account::resolve_account_status;
+
+    AccountPageItem {
+        account: AccountRecord {
+            outbound_proxy_enabled: true,
+            id: "acct_cooldown".to_owned(),
+            provider_kind: gateway_core::routing::ProviderKind::new("openai").unwrap(),
+            groups: Vec::new(),
+            name: "synthetic cooldown account".to_owned(),
+            notes: None,
+            email: None,
+            upstream_user_id: None,
+            upstream_account_id: None,
+            plan_type: None,
+            authentication_kind: authentication_kind.to_owned(),
+            credential_revision: Revision::new(1).unwrap(),
+            has_refresh_token: authentication_kind == "oauth",
+            access_token_expires_at: None,
+            next_refresh_at: None,
+            enabled: true,
+            concurrency_limit: None,
+            weight: Default::default(),
+            model_access: Default::default(),
+            outbound_proxy: None,
+            credential_state: facts.credential_state,
+            credential_observed_at: now,
+            quota: facts.quota,
+            last_error_reason: None,
+            last_error_message: None,
+            created_at: now,
+            updated_at: now,
+        },
+        capacity: AccountCapacity {
+            used_slots: None,
+            total_slots: None,
+        },
+        projection: resolve_account_status(&facts, now.into()),
+    }
+}
+
+#[tokio::test]
+async fn account_usage_returns_distinct_cache_read_and_write_tokens_without_aliases() {
+    use chrono::Utc;
+    use gateway_admin::model::accounts::AccountUsage;
+    use gateway_core::account::{AccountStatusFacts, CredentialState, QuotaState};
+
+    let fixture = AdminTestFixture::new().await;
+    fixture.auth.insert_session("valid-session");
+    let now = Utc::now();
+    let facts = AccountStatusFacts {
+        enabled: true,
+        credential_state: CredentialState::Ready,
+        access_token_expires_at: None,
+        quota: QuotaState::unknown(),
+        cooldown: None,
+        last_error_reason: None,
+        last_error_message: None,
+    };
+    *fixture.account.lock().unwrap() = Some(account_page_item(facts, now, "api_key"));
+    for (read, write) in [(Some(13), Some(7)), (None, None)] {
+        *fixture.account_usage.lock().unwrap() = vec![AccountUsage {
+            account_id: "acct_cooldown".to_owned(),
+            request_count: 1,
+            success_count: 1,
+            input_tokens: Some(100),
+            output_tokens: Some(20),
+            cached_input_tokens: read,
+            cache_write_input_tokens: write,
+            reasoning_output_tokens: Some(3),
+            image_input_tokens: None,
+            image_output_tokens: None,
+            image_request_count: 0,
+            image_request_failed_count: 0,
+            total_tokens: Some(120),
+            cost_coverage: Default::default(),
+            costs: Vec::new(),
+            last_used_at: Some(now),
+            request_buckets: Vec::new(),
+            models: Vec::new(),
+        }];
+        let response = admin::accounts::router::<AdminTestState>()
+            .with_state(fixture.state())
+            .oneshot(
+                Request::builder()
+                    .uri("/api/admin/accounts")
+                    .header("x-request-id", "req_account_usage_contract")
+                    .header(header::COOKIE, "cpr_session=valid-session")
+                    .body(Body::empty())
+                    .unwrap(),
+            )
+            .await
+            .unwrap();
+        let status = response.status();
+        let body = to_bytes(response.into_body(), 32768).await.unwrap();
+        let value: serde_json::Value = serde_json::from_slice(&body).unwrap();
+        assert_eq!(status, StatusCode::OK, "{value}");
+        let usage = &value["data"]["items"][0]["usage"];
+        assert_eq!(usage["cachedInputTokens"], serde_json::json!(read));
+        assert_eq!(usage["cacheWriteInputTokens"], serde_json::json!(write));
+        assert_eq!(
+            usage["cachedInputTokensDisplay"],
+            if read.is_some() { "13" } else { "—" }
+        );
+        assert_eq!(
+            usage["cacheWriteInputTokensDisplay"],
+            if write.is_some() { "7" } else { "—" }
+        );
+        for alias in [
+            "createdTokens",
+            "createdTokensDisplay",
+            "readTokens",
+            "readTokensDisplay",
+        ] {
+            assert!(usage.get(alias).is_none(), "obsolete token alias: {alias}");
+        }
+    }
+}
+
 #[tokio::test]
 async fn standalone_credential_rotation_route_is_not_exposed() {
     let fixture = AdminTestFixture::new().await;

backend/crates/gateway-api/tests/admin/accounts/mod.rs

@@ -484,10 +484,10 @@ mod response {
             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,
@@ -498,10 +498,8 @@ mod response {
             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(),
@@ -516,9 +514,9 @@ mod response {
         assert_eq!(value["windowLabelDisplay"], "周/月额度窗口");
         assert!(value["inputTokens"].is_null());
         assert!(value["totalTokens"].is_null());
-        assert!(value["reasoningTokens"].is_null());
-        assert_eq!(value["reasoningTokensDisplay"], "-");
-        assert_eq!(value["createdTokensDisplay"], "-");
+        assert!(value["reasoningOutputTokens"].is_null());
+        assert_eq!(value["reasoningOutputTokensDisplay"], "-");
+        assert_eq!(value["cacheWriteInputTokensDisplay"], "-");
     }
 
     #[test]

backend/crates/gateway-api/tests/admin/compression.rs

@@ -0,0 +1,111 @@
+//! 管理端 JSON 压缩的协商、响应合同与重复编码回归测试
+
+use std::io::Read as _;
+
+use axum::{
+    Router,
+    body::{Body, to_bytes},
+    http::{Request, StatusCode, header},
+    response::Response,
+};
+use flate2::read::GzDecoder;
+use tower::ServiceExt as _;
+use tower_http::compression::CompressionLayer;
+
+use super::AdminTestFixture;
+
+async fn app() -> Router {
+    let fixture = AdminTestFixture::new().await;
+    fixture.auth.insert_session("valid-session");
+    crate::openai::api_router_with_admin(fixture.services)
+}
+
+async fn get(router: Router, uri: &str, encoding: Option<&str>) -> Response {
+    let mut request = Request::builder()
+        .uri(uri)
+        .header(header::COOKIE, "cpr_session=valid-session")
+        .header("x-request-id", "req_admin_compression");
+    if let Some(encoding) = encoding {
+        request = request.header(header::ACCEPT_ENCODING, encoding);
+    }
+    router
+        .oneshot(request.body(Body::empty()).expect("request"))
+        .await
+        .expect("response")
+}
+
+async fn bytes(response: Response) -> Vec<u8> {
+    to_bytes(response.into_body(), 1024 * 1024)
+        .await
+        .expect("response body")
+        .to_vec()
+}
+
+fn decode_gzip(body: &[u8]) -> Vec<u8> {
+    let mut decoded = Vec::new();
+    GzDecoder::new(body)
+        .read_to_end(&mut decoded)
+        .expect("valid gzip body");
+    decoded
+}
+
+#[tokio::test]
+async fn gzip_should_preserve_admin_json_and_response_headers() {
+    let router = app().await;
+    let expected = bytes(get(router.clone(), "/api/admin/settings", None).await).await;
+    assert!(expected.len() >= 1024);
+
+    for encoding in ["gzip", "br, gzip;q=0.8, deflate;q=0.5", "*;q=0.5"] {
+        let response = get(router.clone(), "/api/admin/settings", Some(encoding)).await;
+        assert_eq!(response.status(), StatusCode::OK);
+        assert_eq!(response.headers()[header::CONTENT_ENCODING], "gzip");
+        assert_eq!(response.headers()[header::CONTENT_TYPE], "application/json");
+        assert_eq!(response.headers()[header::CACHE_CONTROL], "no-store");
+        assert_eq!(response.headers()["x-request-id"], "req_admin_compression");
+        assert_eq!(response.headers()[header::VARY], "accept-encoding");
+        assert!(!response.headers().contains_key(header::CONTENT_LENGTH));
+        let compressed = bytes(response).await;
+        assert!(compressed.len() < expected.len());
+        assert_eq!(decode_gzip(&compressed), expected, "{encoding}");
+    }
+}
+
+#[tokio::test]
+async fn clients_without_gzip_support_should_receive_original_json() {
+    let router = app().await;
+    let expected = bytes(get(router.clone(), "/api/admin/settings", None).await).await;
+    for encoding in [None, Some("identity"), Some("br"), Some("gzip;q=0")] {
+        let response = get(router.clone(), "/api/admin/settings", encoding).await;
+        assert_eq!(response.status(), StatusCode::OK);
+        assert!(!response.headers().contains_key(header::CONTENT_ENCODING));
+        assert_eq!(response.headers()[header::VARY], "accept-encoding");
+        assert_eq!(bytes(response).await, expected, "{encoding:?}");
+    }
+}
+
+#[tokio::test]
+async fn small_admin_json_should_remain_uncompressed() {
+    let router = app().await;
+    let uri = "/api/admin/settings/admin-api-key";
+    let expected = bytes(get(router.clone(), uri, None).await).await;
+    assert!(expected.len() < 1024);
+    let response = get(router, uri, Some("gzip")).await;
+    assert_eq!(response.status(), StatusCode::OK);
+    assert!(!response.headers().contains_key(header::CONTENT_ENCODING));
+    assert_eq!(bytes(response).await, expected);
+}
+
+#[tokio::test]
+async fn a_second_compression_layer_should_not_encode_gzip_again() {
+    let router = app().await;
+    let expected = bytes(get(router.clone(), "/api/admin/settings", None).await).await;
+    let response = get(
+        router.layer(CompressionLayer::new()),
+        "/api/admin/settings",
+        Some("gzip"),
+    )
+    .await;
+    assert_eq!(response.headers()[header::CONTENT_ENCODING], "gzip");
+    assert_eq!(response.headers()[header::VARY], "accept-encoding");
+    assert_eq!(decode_gzip(&bytes(response).await), expected);
+}

backend/crates/gateway-api/tests/admin/errors.rs

@@ -511,6 +511,7 @@ mod provider {
                 total_slots: None,
             },
             account: AccountRecord {
+                outbound_proxy_enabled: true,
                 notes: None,
                 model_access: Default::default(),
                 id: "acct_error_test".to_owned(),

backend/crates/gateway-api/tests/admin/mod.rs

@@ -88,6 +88,7 @@ mod account_groups;
 mod accounts;
 mod auth;
 mod client_keys;
+mod compression;
 mod error_diagnostics;
 mod errors;
 mod observability;
@@ -112,6 +113,7 @@ pub(super) struct AdminTestFixture {
     pub dashboard_summary_range: Arc<Mutex<Option<TimeRange>>>,
     pub provider_error: Arc<Mutex<Option<ProviderAdminError>>>,
     pub account: Arc<Mutex<Option<AccountPageItem>>>,
+    pub account_usage: Arc<Mutex<Vec<AccountUsage>>>,
 }
 
 impl AdminTestFixture {
@@ -154,6 +156,7 @@ impl AdminTestFixture {
         let dashboard_summary_range = Arc::new(Mutex::new(None));
         let provider_error = Arc::new(Mutex::new(None));
         let account = Arc::new(Mutex::new(None));
+        let account_usage = Arc::new(Mutex::new(Vec::new()));
         let unused = Arc::new(UnusedStore {
             observations: observations.clone(),
             usage_records: Arc::clone(&usage_records),
@@ -163,6 +166,7 @@ impl AdminTestFixture {
             dashboard_observation: Arc::clone(&dashboard_observation),
             dashboard_summary_range: Arc::clone(&dashboard_summary_range),
             account: Arc::clone(&account),
+            account_usage: Arc::clone(&account_usage),
         });
         let plugin_ports = Arc::new(plugins::TestPluginPorts::default());
         let published_snapshot = gateway_core::runtime::RuntimeSnapshotHandle::default();
@@ -232,6 +236,7 @@ impl AdminTestFixture {
             dashboard_summary_range,
             provider_error,
             account,
+            account_usage,
         }
     }
 
@@ -317,6 +322,7 @@ impl MemoryAuthStore {
                     },
                     admin_user_id: "admin_1".to_owned(),
                 },
+                renewal: None,
                 absolute_expires_at: None,
                 expires_at: Utc::now() + Duration::hours(1),
             },
@@ -335,7 +341,7 @@ impl MemoryAuthStore {
         self.sessions
             .lock()
             .unwrap()
-            .get_mut(session_id)
+            .get_mut(session_id.split('.').nth(1).unwrap_or(session_id))
             .unwrap()
             .expires_at = expires_at;
     }
@@ -411,19 +417,24 @@ 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()));
         }
@@ -600,12 +611,12 @@ impl SettingsStore for MemorySettingsStore {
             rotation_strategy: command.rotation_strategy,
             updated_at: Utc::now(),
             values: gateway_admin::model::settings::RuntimeSettingsValues {
+                codex_privacy_policy: command.values.codex_privacy_policy,
                 request_location_enabled: command.values.request_location_enabled,
                 request_location: command.values.request_location,
                 refresh_margin_seconds: command.values.refresh_margin_seconds,
                 refresh_concurrency: command.values.refresh_concurrency,
                 max_concurrent_per_account: command.values.max_concurrent_per_account,
-                request_interval_ms: command.values.request_interval_ms,
                 max_waiting_per_key: command.values.max_waiting_per_key,
                 max_waiting_per_account: command.values.max_waiting_per_account,
                 concurrency_wait_timeout_seconds: command.values.concurrency_wait_timeout_seconds,
@@ -1099,6 +1110,7 @@ struct UnusedStore {
     dashboard_observation: Arc<Mutex<Option<DashboardObservation>>>,
     dashboard_summary_range: Arc<Mutex<Option<TimeRange>>>,
     account: Arc<Mutex<Option<AccountPageItem>>>,
+    account_usage: Arc<Mutex<Vec<AccountUsage>>>,
 }
 
 struct UnusedClientKeyVerifier;
@@ -1160,18 +1172,41 @@ impl AccountStore for UnusedStore {
     async fn load_account_usage(
         &self,
         _: TimeRange,
-        _: &[String],
+        account_ids: &[String],
     ) -> AdminStoreResult<Vec<AccountUsage>> {
         if self.account.lock().expect("account").is_some() {
-            return Ok(Vec::new());
+            return Ok(self
+                .account_usage
+                .lock()
+                .expect("account usage")
+                .iter()
+                .filter(|usage| account_ids.contains(&usage.account_id))
+                .cloned()
+                .collect());
         }
         Err(unavailable("account usage"))
     }
 
     async fn load_account_usage_by_windows(
         &self,
-        _: &[AccountUsageWindowQuery],
+        windows: &[AccountUsageWindowQuery],
     ) -> AdminStoreResult<Vec<AccountUsageWindowResult>> {
+        if self.account.lock().expect("account").is_some() {
+            let usage = self.account_usage.lock().expect("account usage");
+            return Ok(windows
+                .iter()
+                .filter_map(|window| {
+                    usage
+                        .iter()
+                        .find(|usage| usage.account_id == window.account_id)
+                        .map(|usage| AccountUsageWindowResult {
+                            account_id: window.account_id.clone(),
+                            key: window.key.clone(),
+                            usage: usage.clone(),
+                        })
+                })
+                .collect());
+        }
         Err(unavailable("account quota window usage"))
     }
 
@@ -1345,6 +1380,10 @@ impl AccountRuntimeStore for UnusedStore {
 
 #[async_trait]
 impl ObservabilityStore for UnusedStore {
+    fn query_timeout(&self) -> std::time::Duration {
+        std::time::Duration::from_secs(10)
+    }
+
     async fn dashboard_summary(
         &self,
         query: DashboardQuery,
@@ -1380,15 +1419,39 @@ impl ObservabilityStore for UnusedStore {
         data.trend.clone().ok_or_else(|| unavailable("usage trend"))
     }
 
-    fn usage_calculated_billing_facts(
+    async fn analytics_cache_generation(&self) -> AdminStoreResult<u64> {
+        Ok(self
+            .observations
+            .lock()
+            .expect("observations")
+            .summary
+            .as_ref()
+            .map_or(0, |summary| summary.analytics.generation))
+    }
+
+    async fn usage_insights_observation(
         &self,
-        _: TimeRange,
-        _: UsageFilter,
+        range: TimeRange,
+        filter: UsageFilter,
         _: Granularity,
-    ) -> gateway_admin::ports::store::UsageCalculatedBillingStream<'_> {
-        Box::pin(futures::stream::once(async {
-            Err(unavailable("usage billing facts"))
-        }))
+    ) -> AdminStoreResult<gateway_admin::model::observability::UsageInsightsObservation> {
+        let mut data = self.observations.lock().expect("observations");
+        data.summaries.push((range, filter.clone()));
+        data.trends.push((range, filter));
+        Ok(
+            gateway_admin::model::observability::UsageInsightsObservation {
+                overview: data
+                    .summary
+                    .clone()
+                    .map(|summary| UsageOverview { range, ..summary })
+                    .ok_or_else(|| unavailable("usage summary"))?,
+                trend: data
+                    .trend
+                    .clone()
+                    .ok_or_else(|| unavailable("usage trend"))?,
+                costs: Vec::new(),
+            },
+        )
     }
 
     async fn list_usage_records(&self, query: UsageQuery) -> AdminStoreResult<UsagePage> {
@@ -1667,12 +1730,12 @@ fn test_runtime_settings() -> RuntimeSettings {
         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: 3_600,
             refresh_concurrency: 2,
             max_concurrent_per_account: 3,
-            request_interval_ms: 50,
             max_waiting_per_key: 0,
             max_waiting_per_account: 0,
             concurrency_wait_timeout_seconds: 30,

backend/crates/gateway-api/tests/admin/observability/response.rs

@@ -25,6 +25,17 @@ async fn dashboard_summary_should_include_quota_exhaustion_in_unavailable_headli
         .dashboard_observation
         .lock()
         .expect("dashboard observation") = Some(DashboardObservation {
+        analytics: gateway_admin::model::observability::AnalyticsMetadata {
+            coverage_start: Some(now - Duration::hours(1)),
+            coverage_end: Some(now),
+            generated_at: now,
+            lag_seconds: 12,
+            state: gateway_admin::model::observability::AnalyticsState::Lagging,
+            percentiles_approximate: true,
+            schema_version: 1,
+            histogram_version: 1,
+            generation: 42,
+        },
         runtime_slots: None,
         range: TimeRange::new(now - Duration::hours(1), now).expect("dashboard range"),
         totals: Default::default(),
@@ -59,6 +70,14 @@ async fn dashboard_summary_should_include_quota_exhaustion_in_unavailable_headli
         .expect("dashboard response body");
     let value: serde_json::Value = serde_json::from_slice(&body).expect("dashboard response JSON");
     assert_eq!(status, StatusCode::OK, "{value}");
+    assert_eq!(value["data"]["analytics"]["state"], "lagging");
+    assert_eq!(value["data"]["analytics"]["lagSeconds"], 12);
+    assert_eq!(value["data"]["analytics"]["percentilesApproximate"], true);
+    assert_eq!(value["data"]["analytics"]["schemaVersion"], 1);
+    assert_eq!(value["data"]["analytics"]["histogramVersion"], 1);
+    assert!(value["data"]["analytics"]["coverageStart"].is_string());
+    assert!(value["data"]["analytics"]["generatedAtDisplay"].is_string());
+    assert!(value["data"]["analytics"].get("generation").is_none());
 
     assert_eq!(
         (
@@ -108,12 +127,13 @@ async fn dashboard_summary_should_use_lifetime_totals_for_card_footers() {
         .dashboard_observation
         .lock()
         .expect("dashboard observation") = Some(DashboardObservation {
+        analytics: Default::default(),
         runtime_slots: None,
         range: TimeRange::new(now - Duration::hours(1), now).expect("dashboard range"),
         totals: DashboardTotals {
             request_count: 42,
             input_tokens: 800,
-            cached_tokens: 200,
+            cached_input_tokens: 200,
             total_tokens: 840,
             billing_usd: None,
         },
@@ -141,13 +161,21 @@ async fn dashboard_summary_should_use_lifetime_totals_for_card_footers() {
         .expect("dashboard response body");
     let value: serde_json::Value = serde_json::from_slice(&body).expect("dashboard response JSON");
     assert_eq!(status, StatusCode::OK, "{value}");
+    assert_eq!(
+        value["data"]["analytics"]["coverageStartDisplay"],
+        serde_json::Value::Null
+    );
+    assert_eq!(
+        value["data"]["analytics"]["coverageEndDisplay"],
+        serde_json::Value::Null
+    );
 
     assert_eq!(
         (
             &value["data"]["cards"]["traffic"]["totalRequests"],
             &value["data"]["cards"]["tokens"]["totalTokens"],
             &value["data"]["cards"]["cache"]["totalHitRate"],
-            &value["data"]["cards"]["cache"]["totalCachedTokens"],
+            &value["data"]["cards"]["cache"]["totalCachedInputTokens"],
         ),
         (
             &serde_json::json!("42"),
@@ -180,6 +208,7 @@ async fn dashboard_summary_should_default_to_current_deployment_day() {
         .dashboard_observation
         .lock()
         .expect("dashboard observation") = Some(DashboardObservation {
+        analytics: Default::default(),
         runtime_slots: None,
         range: TimeRange::new(now - Duration::hours(1), now).expect("dashboard range"),
         totals: Default::default(),
@@ -282,9 +311,9 @@ async fn usage_detail_should_keep_attempt_snapshot_contract() {
                 message: Some("limited".to_owned()),
                 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,
                 total_tokens: None,
                 cost_source: Some("unavailable".to_owned()),
                 cost_amount: None,
@@ -401,9 +430,9 @@ async fn zero_attempt_failure_detail_keeps_missing_upstream_facts_and_preparatio
     record.error_message = Some("no upstream account is available".to_owned());
     record.input_tokens = None;
     record.output_tokens = None;
-    record.cached_tokens = None;
-    record.cache_write_tokens = None;
-    record.reasoning_tokens = None;
+    record.cached_input_tokens = None;
+    record.cache_write_input_tokens = None;
+    record.reasoning_output_tokens = None;
     record.image_input_tokens = None;
     record.image_output_tokens = None;
     record.total_tokens = None;
@@ -617,6 +646,7 @@ async fn diagnostics_should_keep_stable_key_and_display_name_contract() {
     let fixture = AdminTestFixture::new().await;
     fixture.auth.insert_session("valid-session");
     *fixture.diagnostics.lock().expect("diagnostics") = DiagnosticsObservation {
+        analytics: Default::default(),
         total_request_count: 4,
         items: vec![DiagnosticObservation {
             key: "acct_diag".to_owned(),
@@ -726,9 +756,9 @@ fn usage_record_with_account(
         retry_after_ms: None,
         input_tokens: Some(1),
         output_tokens: Some(1),
-        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),
         total_tokens: Some(2),
@@ -847,9 +877,9 @@ async fn usage_route_should_expose_table_facts_without_detail_payload() {
             service_tier: Some("default".to_owned()),
             input_tokens: Some(1),
             output_tokens: Some(1),
-            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(31),
             image_output_tokens: Some(9),
             total_tokens: Some(2),
@@ -1101,6 +1131,12 @@ async fn calendar_queries_and_display_follow_deployment_timezone_with_one_anchor
         let fixture = AdminTestFixture::with_timezone(timezone).await;
         fixture.auth.insert_session("valid-session");
         *fixture.dashboard_observation.lock().unwrap() = Some(DashboardObservation {
+            analytics: gateway_admin::model::observability::AnalyticsMetadata {
+                coverage_start: Some(range.start),
+                coverage_end: Some(end),
+                generated_at: end,
+                ..Default::default()
+            },
             runtime_slots: None,
             range,
             totals: Default::default(),
@@ -1142,6 +1178,15 @@ async fn calendar_queries_and_display_follow_deployment_timezone_with_one_anchor
         assert_eq!(queried.end, end);
         assert_eq!(value["data"]["asOf"], anchor);
         assert_eq!(value["data"]["asOfDisplay"], display);
+        let analytics = &value["data"]["analytics"];
+        assert_eq!(analytics["coverageStart"], start);
+        assert_eq!(analytics["coverageEnd"], anchor);
+        assert_eq!(
+            analytics["coverageStartDisplay"],
+            format!("{} 00:00:00", &display[..10])
+        );
+        assert_eq!(analytics["coverageEndDisplay"], display);
+        assert_eq!(analytics["generatedAtDisplay"], display);
         let points = value["data"]["healthTimeline"]["points"]
             .as_array()
             .unwrap();
@@ -1198,3 +1243,63 @@ async fn calendar_query_rejects_an_anchor_outside_the_local_calendar() {
     assert_eq!(response.status(), StatusCode::BAD_REQUEST);
     assert!(fixture.dashboard_summary_range.lock().unwrap().is_none());
 }
+
+#[tokio::test]
+async fn observability_queries_reject_group_filters_and_analytics_search() {
+    use crate::admin::{AdminTestFixture, AdminTestState};
+    use axum::{
+        body::Body,
+        http::{Request, StatusCode, header},
+    };
+    use gateway_api::admin::observability;
+    use tower::ServiceExt as _;
+    let fixture = AdminTestFixture::new().await;
+    fixture.auth.insert_session("valid-session");
+    let router = observability::router::<AdminTestState>().with_state(fixture.state());
+    for (path, parameter) in [
+        ("/api/admin/usage/records", "routingGroupRefs=group-a"),
+        ("/api/admin/operations/errors", "routingGroupRefs=group-a"),
+        (
+            "/api/admin/usage/records/summary",
+            "routingGroupRefs=group-a",
+        ),
+        (
+            "/api/admin/usage/insights/overview",
+            "routingGroupRefs=group-a",
+        ),
+        (
+            "/api/admin/usage/insights/diagnostics",
+            "routingGroupRefs=group-a",
+        ),
+        ("/api/admin/usage/records/summary", "search=request-prefix"),
+        (
+            "/api/admin/usage/insights/overview",
+            "search=request-prefix",
+        ),
+        (
+            "/api/admin/usage/insights/diagnostics",
+            "search=request-prefix",
+        ),
+    ] {
+        let response = router
+            .clone()
+            .oneshot(
+                Request::builder()
+                    .uri(format!("{path}?{parameter}"))
+                    .header(header::COOKIE, "cpr_session=valid-session")
+                    .header("x-request-id", "req_rejected_observability_filter")
+                    .body(Body::empty())
+                    .unwrap(),
+            )
+            .await
+            .unwrap();
+        assert_eq!(
+            response.status(),
+            StatusCode::BAD_REQUEST,
+            "{path}?{parameter}"
+        );
+    }
+    let observations = fixture.observations.lock().unwrap();
+    assert!(observations.records.is_empty());
+    assert!(observations.errors.is_empty());
+}

backend/crates/gateway-api/tests/admin/plugins/management.rs

@@ -395,14 +395,7 @@ async fn published_fixture() -> AdminTestFixture {
     fixture.published_snapshot.publish(
         RuntimeSnapshot::new(
             ConfigRevision::new(7).unwrap(),
-            gateway_core::settings::SettingsValues::new(
-                1,
-                0,
-                "smart",
-                Default::default(),
-                None,
-                None,
-            ),
+            gateway_core::settings::SettingsValues::new(1, "smart", Default::default(), None, None),
             vec![],
             vec![],
             vec![],
@@ -442,6 +435,35 @@ async fn resource_request(
     .unwrap()
 }
 
+#[tokio::test]
+async fn large_html_resource_should_remain_uncompressed() {
+    let fixture = published_fixture().await;
+    let path = format!("ui/{}.html", "a".repeat(2048));
+    let response = crate::openai::api_router_with_admin(fixture.services)
+        .oneshot(
+            Request::builder()
+                .uri(format!(
+                    "/api/admin/plugins/extensions/plugin-instance-diagnostic/{}/7/resources/{path}",
+                    "a".repeat(64)
+                ))
+                .header("cookie", "cpr_session=management-session")
+                .header("accept-encoding", "gzip")
+                .body(Body::empty())
+                .unwrap(),
+        )
+        .await
+        .unwrap();
+    assert_eq!(response.status(), StatusCode::OK);
+    assert_eq!(response.headers()["content-type"], "text/html");
+    assert!(!response.headers().contains_key("content-encoding"));
+    assert_eq!(
+        axum::body::to_bytes(response.into_body(), 4096)
+            .await
+            .unwrap(),
+        path
+    );
+}
+
 #[tokio::test]
 async fn static_resources_revalidate_privately_after_authorization() {
     use axum::body::to_bytes;

backend/crates/gateway-api/tests/admin/proxies.rs

@@ -89,6 +89,43 @@ async fn proxy_location_rejects_invalid_and_incomplete_input() {
 #[derive(Default)]
 pub(super) struct MemoryProxies(Mutex<Option<ProxyRecord>>);
 
+#[tokio::test]
+async fn proxy_enabled_updates_preserve_connection_and_omitted_state() {
+    let fixture = AdminTestFixture::new().await;
+    fixture.auth.insert_session("valid-session");
+    let (status, created) = request(
+        &fixture,
+        "/api/admin/proxies/create",
+        Some(json!({
+            "name":"Office", "proxyUrl":"http://proxy.example:8080"
+        })),
+        true,
+    )
+    .await;
+    assert_eq!(status, StatusCode::CREATED);
+    assert_eq!(created["data"]["record"]["enabled"], true);
+    for (revision, enabled, expected) in [
+        (1, Some(false), false),
+        (2, None, false),
+        (3, Some(true), true),
+    ] {
+        let mut body = json!({"id":"proxy_test", "revision":revision, "name":"Office"});
+        if let Some(enabled) = enabled {
+            body["enabled"] = json!(enabled);
+        }
+        let (status, changed) =
+            request(&fixture, "/api/admin/proxies/update", Some(body), true).await;
+        assert_eq!(status, StatusCode::OK);
+        assert_eq!(changed["data"]["record"]["enabled"], expected);
+        assert_eq!(
+            changed["data"]["record"]["endpoint"],
+            created["data"]["record"]["endpoint"]
+        );
+        let (_, listed) = request(&fixture, "/api/admin/proxies", None, true).await;
+        assert_eq!(listed["data"]["items"][0]["enabled"], expected);
+    }
+}
+
 fn missing() -> AdminStoreError {
     AdminStoreError::new(AdminStoreErrorKind::NotFound, "proxy", "missing proxy")
 }
@@ -165,6 +202,7 @@ impl ProxyStore for MemoryProxies {
         _: &MutationContext,
     ) -> AdminStoreResult<ProxyMutation> {
         let mut record = ProxyRecord {
+            enabled: true,
             auto_location: command.auto_location,
             detected_location: None,
             location: command.location,
@@ -197,6 +235,9 @@ impl ProxyStore for MemoryProxies {
         let mut stored = self.0.lock().unwrap();
         let record = stored.as_mut().ok_or_else(missing)?;
         record.name = command.name;
+        if let Some(enabled) = command.enabled {
+            record.enabled = enabled;
+        }
         if let Some(auto_location) = command.auto_location {
             if auto_location != record.auto_location {
                 record.detected_location = None;

backend/crates/gateway-api/tests/admin/settings.rs

@@ -40,6 +40,7 @@ async fn response_json(response: axum::response::Response) -> Value {
 fn update_body() -> Value {
     json!({
         "configRevision": 7,
+        "codexPrivacyPolicy": {"enabled":false,"onError":"skip_rule","rules":[]},
         "requestLocationEnabled": false,
         "requestLocation": {"country":"US", "region":"Ohio", "city":"Piketon", "timezone":"America/New_York"},
         "modelMappings": {
@@ -49,7 +50,6 @@ fn update_body() -> Value {
         "refreshMarginSeconds": 1800,
         "refreshConcurrency": 4,
         "maxConcurrentPerAccount": 5,
-        "requestIntervalMs": 25,
         "maxWaitingPerKey": 0,
         "maxWaitingPerAccount": 0,
         "openaiGuardianReservedConcurrency": 0,
@@ -78,6 +78,64 @@ fn update_body() -> Value {
     })
 }
 
+#[tokio::test]
+async fn privacy_save_requires_provider_validation_and_preview_requires_admin_auth() {
+    let fixture = AdminTestFixture::new().await;
+    fixture.auth.insert_session("valid-session");
+    let mut body = update_body();
+    let policy = json!({"enabled":true,"onError":"reject_request","rules":[{
+        "id":"auth","name":"自定义认证头","enabled":true,"steps":[{
+            "scope":"request_header","selector":"authorization","action":"remove_field","pattern":null,
+            "replacement":"","value":null,"replaceAll":true,"caseInsensitive":false,"multiLine":false
+        }]
+    }]});
+    body["codexPrivacyPolicy"] = policy.clone();
+    let response = app(fixture.state())
+        .oneshot(request(
+            Method::POST,
+            "/api/admin/settings/update",
+            Some(body),
+        ))
+        .await
+        .unwrap();
+    assert_eq!(response.status(), StatusCode::BAD_REQUEST);
+    let response = app(fixture.state())
+        .oneshot(request(Method::GET, "/api/admin/settings", None))
+        .await
+        .unwrap();
+    assert_eq!(
+        response_json(response).await["data"]["codexPrivacyPolicy"],
+        json!({"enabled":false,"onError":"skip_rule","rules":[]})
+    );
+    let response = app(fixture.state())
+        .oneshot(
+            Request::builder()
+                .method(Method::POST)
+                .uri("/api/admin/settings/privacy/preview")
+                .header(header::CONTENT_TYPE, "application/json")
+                .body(Body::from(
+                    json!({"policy":policy,"body":{},"headers":{},"turnMetadata":null}).to_string(),
+                ))
+                .unwrap(),
+        )
+        .await
+        .unwrap();
+    assert_eq!(response.status(), StatusCode::UNAUTHORIZED);
+}
+
+#[test]
+fn privacy_policy_is_required_and_rejects_unknown_contract_fields() {
+    let mut missing = update_body();
+    missing
+        .as_object_mut()
+        .unwrap()
+        .remove("codexPrivacyPolicy");
+    assert!(serde_json::from_value::<UpdateRuntimeSettingsRequest>(missing).is_err());
+    let mut unknown = update_body();
+    unknown["codexPrivacyPolicy"]["protectedFields"] = json!([]);
+    assert!(serde_json::from_value::<UpdateRuntimeSettingsRequest>(unknown).is_err());
+}
+
 #[tokio::test]
 async fn smart_settings_round_trip_and_invalid_updates_leave_the_saved_value_intact() {
     let fixture = AdminTestFixture::new().await;
@@ -223,12 +281,12 @@ fn settings_response_should_cover_the_full_runtime_settings_contract() {
             .single()
             .expect("timestamp"),
         values: gateway_admin::model::settings::RuntimeSettingsValues {
+            codex_privacy_policy: Default::default(),
             request_location_enabled: false,
             request_location: Default::default(),
             refresh_margin_seconds: 1800,
             refresh_concurrency: 4,
             max_concurrent_per_account: 5,
-            request_interval_ms: 25,
             max_waiting_per_key: 0,
             max_waiting_per_account: 0,
             concurrency_wait_timeout_seconds: 30,
@@ -268,6 +326,7 @@ fn settings_response_should_cover_the_full_runtime_settings_contract() {
             "providerRequestProfiles": {},
             "openaiClientProfile": null,
             "xaiClientProfile": null,
+        "codexPrivacyPolicy": {"enabled":false,"onError":"skip_rule","rules":[]},
         "requestLocationEnabled": false,
         "requestLocation": {"country":"US", "region":"Ohio", "city":"Piketon", "timezone":"America/New_York"},
             "modelMappings": {
@@ -277,7 +336,6 @@ fn settings_response_should_cover_the_full_runtime_settings_contract() {
             "refreshMarginSeconds": 1800,
             "refreshConcurrency": 4,
             "maxConcurrentPerAccount": 5,
-            "requestIntervalMs": 25,
             "maxWaitingPerKey": 0,
             "maxWaitingPerAccount": 0,
             "openaiGuardianReservedConcurrency": 0,
@@ -348,13 +406,13 @@ fn settings_request_and_response_fields_should_stay_in_lockstep() {
             .expect("fixture rotation strategy"),
         updated_at: chrono::Utc::now(),
         values: gateway_admin::model::settings::RuntimeSettingsValues {
+            codex_privacy_policy: Default::default(),
             request_location_enabled: false,
             request_location: Default::default(),
             refresh_margin_seconds: request.values.refresh_margin_seconds,
             refresh_concurrency: u32::try_from(request.values.refresh_concurrency).expect("u32"),
             max_concurrent_per_account: u32::try_from(request.values.max_concurrent_per_account)
                 .expect("u32"),
-            request_interval_ms: request.values.request_interval_ms,
             max_waiting_per_key: 0,
             max_waiting_per_account: 0,
             concurrency_wait_timeout_seconds: 30,

backend/crates/gateway-api/tests/admin/system.rs

@@ -9,7 +9,7 @@ use axum::{
     http::{Request, StatusCode, header},
 };
 use chrono::Utc;
-use futures::stream;
+use futures::{StreamExt as _, stream};
 use gateway_admin::{
     model::system::{
         SystemOperationAccepted, SystemOperationKind, SystemOperationState, SystemOperationStatus,
@@ -19,6 +19,7 @@ use gateway_admin::{
     ports::system::{SystemOperationError, SystemOperations, SystemUpdateEventStream},
 };
 use gateway_api::admin::system::{self, UpdateDetailQuery, UpdateRequest};
+use http_body_util::BodyExt as _;
 use tower::ServiceExt as _;
 
 use super::{AdminTestFixture, AdminTestState, unavailable_system};
@@ -40,25 +41,39 @@ fn update_request_should_preserve_target_version_for_domain_validation() {
     );
 }
 
-#[tokio::test]
+#[tokio::test(start_paused = true)]
 async fn update_event_stream_should_preserve_event_id_and_download_progress_percent() {
-    let fixture = AdminTestFixture::with_system(Arc::new(ProgressSystem)).await;
+    let fixture = AdminTestFixture::with_system(Arc::new(ProgressSystem::default())).await;
     fixture.auth.insert_session("valid-session");
-    let response = app(fixture.state())
+    let response = gateway_api::admin::router::<AdminTestState>()
+        .with_state(fixture.state())
         .oneshot(
             Request::builder()
                 .uri("/api/admin/system/update/events")
                 .header(header::COOKIE, "cpr_session=valid-session")
+                .header(header::ACCEPT_ENCODING, "gzip")
                 .header("x-request-id", "req_system_update_events")
                 .body(Body::empty())
                 .expect("update event request"),
-        )
+        );
+    let response = tokio::time::timeout(std::time::Duration::from_secs(1), response)
         .await
+        .expect("SSE response must not wait for stream completion")
         .expect("update event response");
-    let body = to_bytes(response.into_body(), 1024 * 1024)
+    assert_eq!(response.status(), StatusCode::OK);
+    assert_eq!(
+        response.headers()[header::CONTENT_TYPE],
+        "text/event-stream"
+    );
+    assert!(!response.headers().contains_key(header::CONTENT_ENCODING));
+    let mut stream = response.into_body();
+    let frame = tokio::time::timeout(std::time::Duration::from_secs(1), stream.frame())
         .await
-        .expect("update event body");
-    let body = String::from_utf8(body.to_vec()).expect("UTF-8 event stream");
+        .expect("first SSE event must arrive before stream completion")
+        .expect("first event")
+        .expect("event body");
+    let body = String::from_utf8(frame.into_data().expect("event data").to_vec())
+        .expect("UTF-8 event stream");
 
     assert!(
         body.contains(r#""id":"update-progress-1""#),
@@ -72,7 +87,7 @@ async fn update_event_stream_should_preserve_event_id_and_download_progress_perc
 
 #[tokio::test]
 async fn update_should_return_accepted_and_report_restart_only_through_status() {
-    let fixture = AdminTestFixture::with_system(Arc::new(ProgressSystem)).await;
+    let fixture = AdminTestFixture::with_system(Arc::new(ProgressSystem::default())).await;
     fixture.auth.insert_session("valid-session");
     let router = app(fixture.state());
     let response = router
@@ -119,7 +134,55 @@ fn app(state: AdminTestState) -> Router {
     system::router::<AdminTestState>().with_state(state)
 }
 
-struct ProgressSystem;
+#[tokio::test]
+async fn update_detail_should_compress_json_starting_at_one_kib() {
+    async fn detail(notes: String, encoding: &str) -> axum::response::Response {
+        let fixture =
+            AdminTestFixture::with_system(Arc::new(ProgressSystem { notes: Some(notes) })).await;
+        fixture.auth.insert_session("valid-session");
+        crate::openai::api_router_with_admin(fixture.services)
+            .oneshot(
+                Request::builder()
+                    .uri("/api/admin/system/update/detail")
+                    .header(header::COOKIE, "cpr_session=valid-session")
+                    .header(header::ACCEPT_ENCODING, encoding)
+                    .body(Body::empty())
+                    .unwrap(),
+            )
+            .await
+            .unwrap()
+    }
+
+    let response = detail(String::new(), "identity").await;
+    assert_eq!(response.status(), StatusCode::OK);
+    let base = to_bytes(response.into_body(), 4096).await.unwrap();
+    assert!(base.len() < 1023);
+    for size in [1023, 1024] {
+        let response = detail("x".repeat(size - base.len()), "gzip").await;
+        assert_eq!(response.status(), StatusCode::OK);
+        let compressed = response.headers().get(header::CONTENT_ENCODING).cloned();
+        let bytes = to_bytes(response.into_body(), 4096).await.unwrap();
+        if size == 1023 {
+            assert!(compressed.is_none());
+            assert_eq!(bytes.len(), size);
+        } else {
+            use std::io::Read as _;
+            assert_eq!(compressed.unwrap(), "gzip");
+            let mut decoded = Vec::new();
+            flate2::read::GzDecoder::new(bytes.as_ref())
+                .read_to_end(&mut decoded)
+                .unwrap();
+            assert_eq!(decoded.len(), size);
+            let body: serde_json::Value = serde_json::from_slice(&decoded).unwrap();
+            assert_eq!(body["data"]["notes"], "x".repeat(size - base.len()));
+        }
+    }
+}
+
+#[derive(Default)]
+struct ProgressSystem {
+    notes: Option<String>,
+}
 
 #[async_trait]
 impl SystemOperations for ProgressSystem {
@@ -144,7 +207,7 @@ impl SystemOperations for ProgressSystem {
             deployment_mode: "docker".into(),
             build_type: "release".into(),
             release_url: None,
-            notes: None,
+            notes: self.notes.clone(),
             cached: false,
             update_supported: true,
             unsupported_reason: None,
@@ -153,18 +216,21 @@ impl SystemOperations for ProgressSystem {
     }
 
     fn update_events(&self) -> SystemUpdateEventStream {
-        Box::pin(stream::once(async {
-            SystemUpdateEvent {
-                id: "update-progress-1".to_owned(),
-                operation_id: Some("update-1".to_owned()),
-                level: SystemUpdateEventLevel::Info,
-                step: Some("download".to_owned()),
-                message: "已下载 4.0 MiB / 10.0 MiB (40%)".to_owned(),
-                terminal: true,
-                progress_percent: Some(40),
-                occurred_at: Utc::now(),
-            }
-        }))
+        Box::pin(
+            stream::once(async {
+                SystemUpdateEvent {
+                    id: "update-progress-1".to_owned(),
+                    operation_id: Some("update-1".to_owned()),
+                    level: SystemUpdateEventLevel::Info,
+                    step: Some("download".to_owned()),
+                    message: "已下载 4.0 MiB / 10.0 MiB (40%)".to_owned(),
+                    terminal: false,
+                    progress_percent: Some(40),
+                    occurred_at: Utc::now(),
+                }
+            })
+            .chain(stream::pending()),
+        )
     }
 
     async fn perform_update(
@@ -216,7 +282,7 @@ impl SystemOperations for ProgressSystem {
 
 #[tokio::test]
 async fn update_detail_should_validate_and_forward_the_temporary_channel() {
-    let fixture = AdminTestFixture::with_system(Arc::new(ProgressSystem)).await;
+    let fixture = AdminTestFixture::with_system(Arc::new(ProgressSystem::default())).await;
     fixture.auth.insert_session("valid-session");
     let router = app(fixture.state());
     for (authenticated, query, expected) in [

backend/crates/gateway-api/tests/architecture.rs

@@ -22,13 +22,6 @@ fn manifest_should_depend_only_on_core_protocol_and_http_adapter_layers() {
     );
 }
 
-#[test]
-fn workspace_should_include_gateway_api() {
-    let workspace = include_str!("../../../Cargo.toml");
-
-    assert!(workspace.contains("\"crates/gateway-api\""));
-}
-
 #[test]
 fn admin_routes_should_use_only_get_post_and_static_paths() {
     let root = Path::new(env!("CARGO_MANIFEST_DIR")).join("src/admin");

backend/crates/gateway-api/tests/auth.rs

@@ -23,6 +23,27 @@ fn session_cookie(response: &axum::response::Response) -> String {
         .to_owned()
 }
 
+fn refresh_cookie(response: &axum::response::Response) -> String {
+    response
+        .headers()
+        .get_all(header::SET_COOKIE)
+        .iter()
+        .filter_map(|value| value.to_str().ok())
+        .find(|value| value.starts_with("cpr_refresh="))
+        .expect("refresh cookie")
+        .split(';')
+        .next()
+        .unwrap()
+        .to_owned()
+}
+
+async fn refresh(app: &axum::Router, cookie: &str) -> axum::response::Response {
+    app.clone()
+        .oneshot(cookie_request(Method::POST, "/api/auth/refresh", cookie))
+        .await
+        .unwrap()
+}
+
 async fn login(
     app: &axum::Router,
     body: Value,
@@ -537,64 +558,129 @@ async fn key_auth_should_issue_restore_and_clear_a_unified_cookie() {
 }
 
 #[tokio::test]
-async fn refresh_renews_admin_cookie_and_preserves_fixed_key_expiry() {
+async fn refresh_restores_expired_access_with_only_the_refresh_cookie() {
     let (app, fixture) = auth_app().await;
-    for body in [
+    let response = login(
+        &app,
         json!({"mode": "admin", "password": "strong-admin-password"}),
-        json!({"mode": "key", "apiKey": RAW_KEY}),
-    ] {
-        let response = login(&app, body.clone(), None).await;
-        let cookie = session_cookie(&response);
-        let original = response_json(response).await["data"]["expiresAt"]
-            .as_str()
-            .unwrap()
-            .to_owned();
-        if body["mode"] == "admin" {
-            fixture.set_session_expiry(
-                cookie.split_once('=').unwrap().1,
-                chrono::Utc::now() + chrono::Duration::minutes(1),
-            );
-        }
-        let response = app
-            .clone()
-            .oneshot(cookie_request(Method::POST, "/api/auth/refresh", &cookie))
+        None,
+    )
+    .await;
+    let access = session_cookie(&response);
+    let renewal = refresh_cookie(&response);
+    let cookies: Vec<_> = response
+        .headers()
+        .get_all(header::SET_COOKIE)
+        .iter()
+        .map(|value| value.to_str().unwrap())
+        .collect();
+    assert_eq!(cookies.len(), 2);
+    assert!(cookies[0].contains("Path=/;"));
+    assert!(cookies[1].contains("Path=/api/auth;"));
+    assert!(
+        cookies
+            .iter()
+            .all(|value| value.contains("HttpOnly") && value.contains("SameSite=Lax"))
+    );
+    assert_eq!(
+        response_json(refresh(&app, &access).await).await["data"]["authenticated"],
+        false
+    );
+    fixture.set_session_expiry(
+        access.split_once('=').unwrap().1,
+        chrono::Utc::now() - chrono::Duration::seconds(1),
+    );
+    assert_eq!(
+        get(&app, "/api/admin/system/version", &access)
             .await
-            .unwrap();
-        assert_eq!(response.status(), StatusCode::OK);
-        assert_eq!(response.headers()[header::CACHE_CONTROL], "no-store");
-        assert_eq!(session_cookie(&response), cookie);
-        assert!(
-            response.headers()[header::SET_COOKIE]
-                .to_str()
-                .unwrap()
-                .contains("HttpOnly")
-        );
-        let data = response_json(response).await;
-        assert_eq!(data["data"]["authenticated"], true);
-        let expiry = data["data"]["session"]["expiresAt"].as_str().unwrap();
-        if body["mode"] == "key" {
-            assert_eq!(expiry, original);
-        } else {
-            assert!(
-                chrono::DateTime::parse_from_rfc3339(expiry).unwrap()
-                    > chrono::Utc::now() + chrono::Duration::minutes(1)
-            );
-        }
-    }
+            .status(),
+        StatusCode::UNAUTHORIZED
+    );
+    assert_eq!(
+        response_json(get(&app, "/api/auth/status", &renewal).await).await["data"]["authenticated"],
+        false
+    );
+
+    let response = refresh(&app, &renewal).await;
+    assert_eq!(response.status(), StatusCode::OK);
+    assert_eq!(response.headers()[header::CACHE_CONTROL], "no-store");
+    let next_access = session_cookie(&response);
+    let next_renewal = refresh_cookie(&response);
+    assert_ne!(next_access, access);
+    assert_ne!(next_renewal, renewal);
+    assert_eq!(response_json(response).await["data"]["authenticated"], true);
+    assert_eq!(
+        get(&app, "/api/admin/system/version", &next_access)
+            .await
+            .status(),
+        StatusCode::OK
+    );
+    assert_eq!(
+        get(&app, "/api/admin/system/version", &access)
+            .await
+            .status(),
+        StatusCode::UNAUTHORIZED
+    );
+    // 模拟响应丢失后的重试，返回同一代 Cookie
+    let retry = refresh(&app, &renewal).await;
+    assert_eq!(session_cookie(&retry), next_access);
+    assert_eq!(refresh_cookie(&retry), next_renewal);
+}
+
+#[tokio::test]
+async fn key_refresh_preserves_fixed_expiry_and_clears_admin_refresh_cookie() {
+    let (app, _) = auth_app().await;
+    let admin = login(
+        &app,
+        json!({"mode": "admin", "password": "strong-admin-password"}),
+        None,
+    )
+    .await;
+    let renewal = refresh_cookie(&admin);
+    let response = login(
+        &app,
+        json!({"mode": "key", "apiKey": RAW_KEY}),
+        Some(&renewal),
+    )
+    .await;
+    assert_eq!(refresh_cookie(&response), "cpr_refresh=");
+    assert!(
+        response
+            .headers()
+            .get_all(header::SET_COOKIE)
+            .iter()
+            .any(|value| {
+                let value = value.to_str().unwrap();
+                value.starts_with("cpr_refresh=")
+                    && value.contains("Max-Age=0")
+                    && value.contains("Path=/api/auth;")
+            })
+    );
+    let cookie = session_cookie(&response);
+    let original = response_json(response).await["data"]["expiresAt"].clone();
+    let response = refresh(&app, &cookie).await;
+    assert_eq!(session_cookie(&response), cookie);
+    let data = response_json(response).await;
+    assert_eq!(data["data"]["authenticated"], true);
+    assert_eq!(data["data"]["session"]["expiresAt"], original);
+    assert_eq!(
+        response_json(refresh(&app, &renewal).await).await["data"]["authenticated"],
+        false
+    );
 }
 
 #[tokio::test]
 async fn refresh_after_logout_or_password_change_cannot_recreate_a_session() {
-    let (app, _) = auth_app().await;
+    let (app, fixture) = auth_app().await;
     for password_change in [false, true] {
-        let cookie = session_cookie(
-            &login(
-                &app,
-                json!({"mode": "admin", "password": "strong-admin-password"}),
-                None,
-            )
-            .await,
-        );
+        let login_response = login(
+            &app,
+            json!({"mode": "admin", "password": "strong-admin-password"}),
+            None,
+        )
+        .await;
+        let cookie = session_cookie(&login_response);
+        let renewal = refresh_cookie(&login_response);
         let response = if password_change {
             change_password(
                 &app,
@@ -604,15 +690,34 @@ async fn refresh_after_logout_or_password_change_cannot_recreate_a_session() {
             )
             .await
         } else {
+            fixture.set_session_expiry(
+                cookie.split_once('=').unwrap().1,
+                chrono::Utc::now() - chrono::Duration::seconds(1),
+            );
             app.clone()
-                .oneshot(cookie_request(Method::POST, "/api/auth/logout", &cookie))
+                .oneshot(cookie_request(Method::POST, "/api/auth/logout", &renewal))
                 .await
                 .unwrap()
         };
         assert_eq!(response.status(), StatusCode::OK);
+        assert_eq!(
+            response
+                .headers()
+                .get_all(header::SET_COOKIE)
+                .iter()
+                .count(),
+            2
+        );
+        assert!(
+            response
+                .headers()
+                .get_all(header::SET_COOKIE)
+                .iter()
+                .all(|value| value.to_str().unwrap().contains("Max-Age=0"))
+        );
         let response = app
             .clone()
-            .oneshot(cookie_request(Method::POST, "/api/auth/refresh", &cookie))
+            .oneshot(cookie_request(Method::POST, "/api/auth/refresh", &renewal))
             .await
             .unwrap();
         assert_eq!(response.status(), StatusCode::OK);

backend/crates/gateway-api/tests/key_usage/fixtures.rs

@@ -48,8 +48,8 @@ pub(super) async fn fixture() -> AdminTestFixture {
         failure_count: 1,
         input_tokens: 1000,
         output_tokens: 100,
-        cached_tokens: 900,
-        reasoning_tokens: 40,
+        cached_input_tokens: 900,
+        reasoning_output_tokens: 40,
         total_tokens: 1100,
         ..Default::default()
     };
@@ -65,6 +65,7 @@ pub(super) async fn fixture() -> AdminTestFixture {
     {
         let mut observations = fixture.observations.lock().unwrap();
         observations.summary = Some(UsageOverview {
+            analytics: Default::default(),
             range: TimeRange {
                 start: now - Duration::hours(1),
                 end: now,
@@ -111,9 +112,9 @@ fn usage_record() -> UsageListRecord {
         service_tier: Some("private-sentinel".to_owned()),
         input_tokens: Some(1000),
         output_tokens: Some(100),
-        cached_tokens: Some(900),
-        cache_write_tokens: Some(0),
-        reasoning_tokens: Some(40),
+        cached_input_tokens: Some(900),
+        cache_write_input_tokens: Some(0),
+        reasoning_output_tokens: Some(40),
         image_input_tokens: None,
         image_output_tokens: None,
         total_tokens: Some(1100),

backend/crates/gateway-api/tests/key_usage/mod.rs

@@ -181,6 +181,7 @@ async fn overview_scopes_every_query_and_projects_only_key_visible_fields() {
             "summary",
             "trend",
             "healthTimeline",
+            "analytics",
         ],
     );
     assert_fields(
@@ -203,8 +204,8 @@ async fn overview_scopes_every_query_and_projects_only_key_visible_fields() {
     assert_eq!(data["key"]["dailyUsedUsd"], "0.640001");
     assert_eq!(data["key"]["maxConcurrency"], 0);
     assert_eq!(data["summary"]["totalTokens"], 1100);
-    assert_eq!(data["summary"]["reasoningTokens"], 40);
-    assert_eq!(data["trend"][0]["reasoningTokens"], 40);
+    assert_eq!(data["summary"]["reasoningOutputTokens"], 40);
+    assert_eq!(data["trend"][0]["reasoningOutputTokens"], 40);
     assert_eq!(data["summary"]["costUsd"], "0.123456");
     assert_eq!(data["summary"]["costIncomplete"], true);
     assert_eq!(data["trend"][0]["bucketSeconds"], 900);
@@ -300,7 +301,7 @@ async fn records_keep_pagination_and_hide_admin_and_upstream_data() {
         assert!(!data.to_string().contains("private-sentinel"));
         if kind == "success" {
             assert_eq!(record["billing"]["totalAmountDisplay"], "$0.1235");
-            assert_eq!(record["tokenDetails"]["reasoningTokens"], 40);
+            assert_eq!(record["tokenDetails"]["reasoningOutputTokens"], 40);
             assert_eq!(record["tokenDetails"]["totalTokens"], 1100);
             assert_eq!(record["firstTokenLatencyMs"], 210);
             assert_fields(
@@ -430,6 +431,7 @@ async fn empty_usage_has_zero_cost_but_unknown_pricing_stays_unknown() {
         {
             let mut data = fixture.observations.lock().unwrap();
             let summary = data.summary.as_mut().unwrap();
+            summary.analytics.generation += 1;
             summary.requests = RequestMetrics {
                 request_count: requests,
                 ..Default::default()

backend/crates/gateway-api/tests/middleware/mod.rs

@@ -1,5 +1,6 @@
 //! HTTP 与 WebSocket 中间件测试入口及请求生命周期替身
 
+mod session;
 mod websocket;
 
 use std::{
@@ -34,12 +35,16 @@ use tower::ServiceExt as _;
 
 #[derive(Clone, Copy, Debug)]
 enum Mode {
+    Overloaded,
     Rewrite,
     Upgrade {
         reject: bool,
         idle: bool,
         block_messages: bool,
     },
+    SessionEnd {
+        kind: Option<&'static str>,
+    },
     Service,
     Echo,
     Slow {
@@ -120,7 +125,7 @@ impl MiddlewarePlan for Plan {
         assert!(input.is_null());
         Box::pin(async move {
             let mut result = next.run(input).await?;
-            result["request_interval_ms"] = serde_json::json!(4321);
+            result["refresh_margin_seconds"] = serde_json::json!(4321);
             Ok(result)
         })
     }
@@ -138,6 +143,12 @@ impl MiddlewarePlan for Plan {
         let mode = self.mode;
         Box::pin(async move {
             match mode {
+                Mode::Overloaded => Err(MiddlewareError::Gateway(
+                    gateway_core::error::GatewayError::new(
+                        gateway_core::error::GatewayErrorKind::MiddlewareCapacityUnavailable,
+                        "Request middleware is temporarily busy",
+                    ),
+                )),
                 Mode::Service => unreachable!("service-only plan bypasses HTTP layers"),
                 Mode::Upgrade { reject, idle, .. } => {
                     let upgrade = request
@@ -161,13 +172,43 @@ impl MiddlewarePlan for Plan {
                         session.send(Message { kind: Kind::Text, payload: Bytes::from_static(b"ready") }).await?;
                         let message = receive.await?.unwrap();
                         session.send(message).await?;
-                        session.send(Message { kind: Kind::Close { code: Some(1000) }, payload: Bytes::from_static(b"done") }).await
+                        session.send(Message { kind: Kind::Close { code: Some(1000) }, payload: Bytes::from_static(b"done") }).await.map_err(Into::into)
                     })));
                     if reject {
                         *response.status_mut() = StatusCode::FORBIDDEN;
                     }
                     Ok(response)
                 }
+                Mode::SessionEnd { kind } => {
+                    let upgrade = request
+                        .extensions_mut()
+                        .remove::<Arc<dyn contract::upgrade::WebSocketUpgrade>>()
+                        .unwrap();
+                    let (parts, _) = request.into_parts();
+                    let (mut response, session) = upgrade.accept(parts, Vec::new()).await?;
+                    response
+                        .extensions_mut()
+                        .insert(contract::upgrade::Upgraded::new(
+                            StatusCode::SWITCHING_PROTOCOLS,
+                            Box::pin(async move {
+                                let _session = session.await.map_err(|_| MiddlewareError::Fault)?;
+                                match kind {
+                                    None => Ok(()),
+                                    Some("cancelled") => {
+                                        Err(contract::upgrade::SessionError::Cancelled)
+                                    }
+                                    Some("reported") => {
+                                        Err(contract::upgrade::SessionError::Reported)
+                                    }
+                                    Some(kind) => Err(contract::upgrade::SessionError::Failed {
+                                        kind,
+                                        plugin_instance_id: Some("plugin-fixture".into()),
+                                    }),
+                                }
+                            }),
+                        ));
+                    Ok(response)
+                }
                 Mode::Rewrite => {
                     assert_eq!(request.uri(), "/unrecognized/client/path?raw=%2f%FF");
                     assert_eq!(request.headers()["authorization"], "Bearer fixture-secret");
@@ -389,7 +430,7 @@ async fn admin_http_does_not_invoke_service_middleware_for_native_business_metho
         .await
         .unwrap();
     let result: serde_json::Value = serde_json::from_slice(&bytes).unwrap();
-    assert_ne!(result["data"]["requestIntervalMs"], 4321);
+    assert_ne!(result["data"]["refreshMarginSeconds"], 4321);
     assert_eq!(plan.calls.load(Ordering::SeqCst), 0);
 }
 
@@ -625,3 +666,25 @@ async fn plugin_http_dispatch_uses_host_identity_without_client_credentials() {
         .unwrap();
     assert_eq!(response.status(), StatusCode::UNAUTHORIZED);
 }
+
+#[tokio::test]
+async fn http_middleware_overload_is_an_explicit_503_before_native_routing() {
+    let (router, plan) = router(Mode::Overloaded, None).await;
+    for path in [
+        "/healthz",
+        "/assets/index.js",
+        "/api/settings",
+        "/v1/responses",
+    ] {
+        let response = router
+            .clone()
+            .oneshot(Request::builder().uri(path).body(Body::empty()).unwrap())
+            .await
+            .unwrap();
+        assert_eq!(response.status(), StatusCode::SERVICE_UNAVAILABLE);
+        let body = response.into_body().collect().await.unwrap().to_bytes();
+        let body: serde_json::Value = serde_json::from_slice(&body).unwrap();
+        assert_eq!(body["error"]["code"], "middleware_capacity_unavailable");
+    }
+    assert_eq!(plan.calls.load(Ordering::Acquire), 4);
+}

backend/crates/gateway-api/tests/middleware/session.rs

@@ -0,0 +1,79 @@
+//! 验证升级后终态只记录一次安全分类，正常结束及已报告失败不重复输出
+
+use super::*;
+use tracing::{
+    Event, Metadata, Subscriber,
+    span::{Attributes, Id, Record},
+};
+
+#[derive(Clone, Default)]
+struct Recorder(Arc<Mutex<Vec<String>>>);
+
+impl Subscriber for Recorder {
+    fn enabled(&self, _: &Metadata<'_>) -> bool {
+        true
+    }
+    fn new_span(&self, _: &Attributes<'_>) -> Id {
+        Id::from_u64(1)
+    }
+    fn record(&self, _: &Id, _: &Record<'_>) {}
+    fn record_follows_from(&self, _: &Id, _: &Id) {}
+    fn enter(&self, _: &Id) {}
+    fn exit(&self, _: &Id) {}
+    fn event(&self, event: &Event<'_>) {
+        struct Fields(String);
+        impl tracing::field::Visit for Fields {
+            fn record_debug(&mut self, field: &tracing::field::Field, value: &dyn std::fmt::Debug) {
+                use std::fmt::Write as _;
+                write!(&mut self.0, "{}={value:?} ", field.name()).unwrap();
+            }
+        }
+        let mut fields = Fields(String::new());
+        event.record(&mut fields);
+        if fields.0.contains("middleware.session.failed") {
+            self.0.lock().unwrap().push(fields.0);
+        }
+    }
+}
+
+#[tokio::test]
+async fn upgraded_session_records_one_correlated_failure_and_ignores_expected_endings() {
+    use tokio_tungstenite::{connect_async, tungstenite::client::IntoClientRequest as _};
+    for kind in [
+        None,
+        Some("cancelled"),
+        Some("reported"),
+        Some("permission_denied"),
+    ] {
+        let recorder = Recorder::default();
+        let _subscriber = tracing::subscriber::set_default(recorder.clone());
+        let (router, plan) = router(Mode::SessionEnd { kind }, None).await;
+        let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
+        let address = listener.local_addr().unwrap();
+        let server = tokio::spawn(async move {
+            axum::serve(listener, router).await.unwrap();
+        });
+        let mut request = format!("ws://{address}/plugin-owned/session")
+            .into_client_request()
+            .unwrap();
+        request
+            .headers_mut()
+            .insert("x-request-id", "session-regression".parse().unwrap());
+        let (_socket, response) = connect_async(request).await.unwrap();
+        assert_eq!(response.status(), StatusCode::SWITCHING_PROTOCOLS);
+        let cancellation = plan.cancellation.lock().unwrap().clone().unwrap();
+        tokio::time::timeout(Duration::from_secs(3), cancellation.cancelled())
+            .await
+            .unwrap();
+        let events = recorder.0.lock().unwrap();
+        if kind == Some("permission_denied") {
+            assert_eq!(events.len(), 1, "{events:?}");
+            assert!(events[0].contains("session-regression"));
+            assert!(events[0].contains("plugin-fixture"));
+            assert!(events[0].contains("permission_denied"));
+        } else {
+            assert!(events.is_empty(), "{events:?}");
+        }
+        server.abort();
+    }
+}

backend/crates/gateway-api/tests/openai/error.rs

@@ -13,6 +13,40 @@ use gateway_api::openai::error::{
     gateway_error_response, openai_error_response,
 };
 
+#[tokio::test]
+async fn ordinary_upstream_rejections_preserve_status_body_and_client_retry_advice() {
+    use bytes::Bytes;
+    use gateway_core::error::ClientVisibleUpstreamResponse;
+    use gateway_core::event::ProviderResponseHeader;
+
+    let body = Bytes::from_static(br#"{ "error":{"code":"Vendor.Future.v2","type":"server_error","message":"original failure","future":9007199254740993} }"#);
+    for status in [400, 409, 500, 503, 504] {
+        let error = EngineError::Provider(
+            ProviderError::new(ProviderErrorKind::Unavailable, UpstreamSendState::NotSent)
+                .with_retry_prohibited()
+                .with_client_visible_upstream_response(
+                    ClientVisibleUpstreamResponse::new(
+                        status,
+                        Some(b"application/problem+json".to_vec()),
+                        body.clone(),
+                    )
+                    .with_headers(vec![ProviderResponseHeader::new(
+                        "retry-after",
+                        Bytes::from_static(b"17"),
+                    )]),
+                ),
+        );
+        let response = engine_error_response(&error);
+        assert_eq!(response.status().as_u16(), status);
+        assert_eq!(
+            response.headers()["content-type"],
+            "application/problem+json"
+        );
+        assert_eq!(response.headers()["retry-after"], "17");
+        assert_eq!(to_bytes(response.into_body(), 4096).await.unwrap(), body);
+    }
+}
+
 #[tokio::test]
 async fn capacity_errors_offer_client_retry_without_changing_upstream_facts() {
     use bytes::Bytes;
@@ -229,6 +263,18 @@ fn rate_limited_error_should_map_to_openai_retryable_status() {
     );
 }
 
+#[test]
+fn middleware_capacity_is_service_unavailable() {
+    assert_eq!(
+        gateway_error_contract(GatewayErrorKind::MiddlewareCapacityUnavailable),
+        (
+            StatusCode::SERVICE_UNAVAILABLE,
+            "server_error",
+            "middleware_capacity_unavailable"
+        ),
+    );
+}
+
 #[test]
 fn queue_rejections_keep_distinct_retryable_http_codes() {
     for (kind, code) in [
@@ -514,7 +560,7 @@ fn engine_store_error_should_collapse_to_safe_internal_error() {
 
     let projected = gateway_error_from_engine(&error);
     assert_eq!(projected.kind(), GatewayErrorKind::Internal);
-    assert_eq!(projected.safe_message(), "gateway execution failed");
+    assert_eq!(projected.safe_message(), "request execution failed");
 }
 #[test]
 fn openai_error_response_should_preserve_only_safe_contract_fields() {

backend/crates/gateway-api/tests/openai/mod.rs

@@ -283,19 +283,32 @@ fn snapshot_with_client_key(
     plaintext: &str,
     provider_name: &str,
     client_key_id: &str,
+) -> RuntimeSnapshot {
+    snapshot_with_accounts(plaintext, provider_name, client_key_id, &["acct_api_test"])
+}
+
+fn snapshot_with_accounts(
+    plaintext: &str,
+    provider_name: &str,
+    client_key_id: &str,
+    accounts: &[&str],
 ) -> RuntimeSnapshot {
     let provider = ProviderKind::new(provider_name).expect("provider");
-    let account_directory = Arc::new(RuntimeAccountDirectory::new(BTreeMap::from([(
-        ProviderAccountId::new("acct_api_test").expect("account ID"),
-        RuntimeAccount::new(provider.clone(), BTreeSet::new()),
-    )])));
+    let account_directory = Arc::new(RuntimeAccountDirectory::new(BTreeMap::from_iter(
+        accounts.iter().map(|id| {
+            (
+                ProviderAccountId::new(*id).expect("account ID"),
+                RuntimeAccount::new(provider.clone(), BTreeSet::new()),
+            )
+        }),
+    )));
     let capabilities = ModelCapabilities::new(
         BTreeSet::from([gateway_core::operation::OperationKind::Generate]),
         Some(16_000),
     );
     RuntimeSnapshot::new(
         ConfigRevision::new(1).expect("revision"),
-        gateway_core::settings::SettingsValues::new(2, 1, "smart", Default::default(), None, None),
+        gateway_core::settings::SettingsValues::new(2, "smart", Default::default(), None, None),
         vec![provider.clone()],
         ["model-a", "model-b"]
             .into_iter()

backend/crates/gateway-api/tests/openai/responses/http.rs

@@ -23,7 +23,7 @@ use futures::StreamExt;
 use futures::future::{BoxFuture, pending};
 use gateway_core::engine::execution::{
     AuthenticatedClient, ClientAuthenticationError, ExecutionService, ExecutionSession,
-    StartExecution, StartProviderExecution, StartedExecution,
+    ResponseCommit, StartExecution, StartProviderExecution, StartedExecution,
 };
 use gateway_core::engine::middleware::{FrozenMiddlewarePlan, MiddlewareHeader};
 use gateway_core::engine::{CommitRequirement, CoordinatedEvent, EngineError, ModelRequestId};
@@ -58,6 +58,7 @@ fn responses_middleware() -> RequestMiddleware {
 
 #[derive(Default)]
 struct Trace {
+    response_commit: ResponseCommit,
     events: Mutex<Vec<&'static str>>,
     client_statuses: Mutex<Vec<u16>>,
     cancelled: AtomicBool,
@@ -77,7 +78,7 @@ impl Trace {
         self.client_statuses
             .lock()
             .expect("client status lock")
-            .push(status);
+            .push(self.response_commit.status_code().unwrap_or(status));
     }
 
     fn client_statuses(&self) -> Vec<u16> {
@@ -104,6 +105,7 @@ enum NextStep {
     Event(CoordinatedEvent),
     DelayedEvent(Duration, CoordinatedEvent),
     Error(EngineError),
+    DelayedError(Duration, EngineError),
     FinalizeCancelled,
     FinalizeSuccess,
     End,
@@ -297,6 +299,10 @@ impl FakeSession {
 }
 
 impl ExecutionSession for FakeSession {
+    fn response_commit(&self) -> ResponseCommit {
+        self.trace.response_commit.clone()
+    }
+
     fn next_event(&mut self) -> BoxFuture<'_, Result<Option<CoordinatedEvent>, EngineError>> {
         Box::pin(async move {
             match self.next.pop_front().unwrap_or(NextStep::End) {
@@ -310,6 +316,13 @@ impl ExecutionSession for FakeSession {
                     self.trace.push("next_event");
                     Ok(Some(event))
                 }
+                NextStep::DelayedError(delay, error) => {
+                    self.trace.push("wait_error");
+                    tokio::time::sleep(delay).await;
+                    self.trace.push("next_error");
+                    self.finalized = true;
+                    Err(error)
+                }
                 NextStep::Error(error) => {
                     self.trace.push("next_error");
                     self.finalized = true;
@@ -1288,27 +1301,203 @@ async fn dropping_stream_during_keepalive_should_cancel_and_finalize_execution()
 }
 
 #[tokio::test(start_paused = true)]
-async fn streaming_keepalive_should_wait_for_first_event_before_committing_http_status() {
+async fn streaming_keepalive_should_cover_four_minutes_before_first_event() {
     let trace = Arc::new(Trace::default());
     let session = FakeSession::streaming(
         Arc::clone(&trace),
         vec![
             NextStep::DelayedEvent(
-                Duration::from_secs(45),
-                delivery(started(), CommitRequirement::CommitBeforeDelivery),
+                Duration::from_secs(240),
+                delivery(completed(), CommitRequirement::CommitBeforeDelivery),
+            ),
+            NextStep::FinalizeSuccess,
+        ],
+    );
+    let start = tokio::time::Instant::now();
+    let response = tokio::time::timeout(
+        Duration::from_secs(20),
+        stream_execution_response(Box::new(session), None),
+    )
+    .await
+    .expect("headers and heartbeat must precede the first upstream event");
+    assert_eq!(response.status(), StatusCode::OK);
+    assert_eq!(response.headers()[CONTENT_TYPE], "text/event-stream");
+    assert_eq!(trace.response_commit.status_code(), Some(200));
+    let mut body = response.into_body().into_data_stream();
+    for heartbeat in 1..16 {
+        let chunk = tokio::time::timeout(Duration::from_secs(20), body.next())
+            .await
+            .expect("first-event wait must stay alive")
+            .expect("heartbeat")
+            .expect("bytes");
+        assert_eq!(chunk, Bytes::from_static(b": keep-alive\n\n"));
+        assert_eq!(start.elapsed(), Duration::from_secs(15 * heartbeat));
+        assert_eq!(trace.snapshot(), vec!["wait_event"]);
+    }
+    let terminal = body.next().await.expect("terminal").expect("bytes");
+    assert!(String::from_utf8_lossy(&terminal).contains("response.completed"));
+    assert_eq!(start.elapsed(), Duration::from_secs(240));
+    assert_eq!(
+        body.next().await.unwrap().unwrap(),
+        Bytes::from_static(b"data: [DONE]\n\n")
+    );
+    assert!(body.next().await.is_none());
+    assert_eq!(
+        trace.snapshot(),
+        vec!["wait_event", "next_event", "commit", "next_end"]
+    );
+    assert!(!trace.is_cancelled());
+}
+
+#[tokio::test(start_paused = true)]
+async fn streaming_error_after_initial_keepalive_should_be_a_terminal_sse_failure() {
+    let trace = Arc::new(Trace::default());
+    let session = FakeSession::streaming(
+        Arc::clone(&trace),
+        vec![NextStep::DelayedError(
+            Duration::from_secs(45),
+            EngineError::Deadline,
+        )],
+    )
+    .with_response_headers(headers(&[("x-codex-turn-state", "private-attempt-state")]));
+    let response = stream_execution_response(Box::new(session), None).await;
+    assert_eq!(response.status(), StatusCode::OK);
+    assert!(!response.headers().contains_key("x-codex-turn-state"));
+    let bytes = to_bytes(response.into_body(), usize::MAX).await.unwrap();
+    let events = parse_sse_events(std::str::from_utf8(&bytes).unwrap()).unwrap();
+    assert!(String::from_utf8_lossy(&bytes).starts_with(": keep-alive\n\n"));
+    let failed = events
+        .iter()
+        .find(|event| event.event.as_deref() == Some("response.failed"))
+        .expect("failure event");
+    let payload: Value = serde_json::from_str(&failed.data).unwrap();
+    assert_eq!(payload["response"]["error"]["code"], "request_timeout");
+    assert!(bytes.ends_with(b"data: [DONE]\n\n"));
+    assert_eq!(trace.client_statuses(), vec![200]);
+    assert_eq!(trace.snapshot(), vec!["wait_error", "next_error"]);
+}
+
+#[tokio::test(start_paused = true)]
+async fn streaming_late_upstream_error_should_preserve_extended_error_fields() {
+    let mut error = json!({
+        "type": "invalid_request_error", "code": "misalignment_policy_violation",
+        "message": "synthetic policy error", "misalignment": {"category": "synthetic"},
+        "extension": {"opaque": true}
+    });
+    let failure = ProviderError::new(ProviderErrorKind::InvalidRequest, UpstreamSendState::Sent)
+        .with_client_visible_upstream_response(
+            ClientVisibleUpstreamResponse::new(
+                400,
+                Some(b"application/json".to_vec()),
+                Bytes::from(json!({"error": error}).to_string()),
+            )
+            .with_headers(headers(&[("retry-after", "7")])),
+        );
+    error["headers"] = json!({"retry-after": "7"});
+    let session = FakeSession::streaming(
+        Arc::new(Trace::default()),
+        vec![NextStep::DelayedError(
+            Duration::from_secs(30),
+            EngineError::Provider(failure),
+        )],
+    );
+    let response = stream_execution_response(Box::new(session), None).await;
+    assert_eq!(response.status(), StatusCode::OK);
+    let bytes = to_bytes(response.into_body(), usize::MAX).await.unwrap();
+    let events = parse_sse_events(std::str::from_utf8(&bytes).unwrap()).unwrap();
+    let failed = events
+        .iter()
+        .find(|event| event.event.as_deref() == Some("response.failed"))
+        .unwrap();
+    let payload: Value = serde_json::from_str(&failed.data).unwrap();
+    assert_eq!(payload["response"]["error"], error);
+    assert!(bytes.ends_with(b"data: [DONE]\n\n"));
+}
+
+#[tokio::test]
+async fn responses_http_connection_should_survive_a_shorter_read_idle_timeout() {
+    use tokio::io::{AsyncReadExt as _, AsyncWriteExt as _};
+
+    let trace = Arc::new(Trace::default());
+    let session = FakeSession::streaming(
+        Arc::clone(&trace),
+        vec![
+            NextStep::DelayedEvent(
+                Duration::from_secs(35),
+                delivery(completed(), CommitRequirement::CommitBeforeDelivery),
+            ),
+            NextStep::FinalizeSuccess,
+        ],
+    );
+    let execution = Arc::new(SessionExecution {
+        client: authenticated_client_for_provider("sk_correlation_test", "openai"),
+        session: Mutex::new(Some(Box::new(session))),
+        middleware: Some(Arc::new(responses_middleware()).frozen()),
+    });
+    let app = api_router(execution).await;
+    let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
+    let address = listener.local_addr().unwrap();
+    let server = tokio::spawn(async move { axum::serve(listener, app).await.unwrap() });
+    let mut client = tokio::net::TcpStream::connect(address).await.unwrap();
+    let body = json!({"model": "model-a", "input": "synthetic", "stream": true}).to_string();
+    client.write_all(format!(
+        "POST /v1/responses HTTP/1.1\r\nHost: {address}\r\nAuthorization: Bearer sk_correlation_test\r\nUser-Agent: AnotherTerminal/1.0\r\nContent-Type: application/json\r\nContent-Length: {}\r\nConnection: close\r\n\r\n{body}", body.len()
+    ).as_bytes()).await.unwrap();
+    let mut received = Vec::new();
+    let result = async {
+        loop {
+            let mut buffer = [0; 4096];
+            // 真实 TCP 每次读取都受空闲期限约束，首个业务事件晚于该期限
+            let read =
+                tokio::time::timeout(Duration::from_secs(20), client.read(&mut buffer)).await?;
+            let count = read.unwrap();
+            if count == 0 {
+                break;
+            }
+            received.extend_from_slice(&buffer[..count]);
+        }
+        Ok::<(), tokio::time::error::Elapsed>(())
+    }
+    .await;
+    server.abort();
+    result.expect("HTTP connection must receive keepalive before its read idle deadline");
+    let wire = String::from_utf8(received).unwrap();
+    assert!(wire.starts_with("HTTP/1.1 200 OK\r\n"));
+    assert!(wire.contains("x-accel-buffering: no\r\n"));
+    assert_eq!(wire.matches(": keep-alive\n\n").count(), 2);
+    assert!(wire.contains("response.completed"));
+    assert!(wire.contains("data: [DONE]\n\n"));
+    assert!(!trace.is_cancelled());
+    assert_eq!(
+        trace.snapshot(),
+        vec!["wait_event", "next_event", "commit", "next_end"]
+    );
+}
+
+#[tokio::test(start_paused = true)]
+async fn dropping_stream_before_first_event_should_cancel_the_original_wait() {
+    let trace = Arc::new(Trace::default());
+    let session = FakeSession::streaming(
+        Arc::clone(&trace),
+        vec![
+            NextStep::DelayedEvent(
+                Duration::from_secs(240),
+                delivery(completed(), CommitRequirement::CommitBeforeDelivery),
             ),
             NextStep::FinalizeCancelled,
         ],
     );
-    let response = tokio::spawn(stream_execution_response(Box::new(session), None));
+    let response = stream_execution_response(Box::new(session), None).await;
+    let mut body = response.into_body().into_data_stream();
+    assert_eq!(
+        body.next().await.unwrap().unwrap(),
+        Bytes::from_static(b": keep-alive\n\n")
+    );
+    drop(body);
     tokio::task::yield_now().await;
-    tokio::time::advance(Duration::from_secs(30)).await;
-
-    assert!(!response.is_finished());
-    assert!(trace.client_statuses().is_empty());
-    let response = response.await.expect("response task");
-    assert_eq!(response.status(), StatusCode::OK);
-    assert_eq!(trace.snapshot(), vec!["wait_event", "next_event", "commit"]);
+    assert!(trace.is_cancelled());
+    assert_eq!(trace.detached_finalizations(), 1);
+    assert_eq!(trace.snapshot(), vec!["wait_event", "cancel_finalize"]);
 }
 
 #[tokio::test]
@@ -3086,3 +3275,53 @@ async fn streaming_middleware_preserves_heartbeats_before_and_after_rewriting()
         assert!(!trace.is_cancelled());
     }
 }
+
+#[tokio::test(start_paused = true)]
+async fn responses_route_should_keep_alive_while_request_middleware_waits_for_first_event() {
+    let admin = crate::admin::AdminTestFixture::new().await.services;
+    for invalid_output in [false, true] {
+        let trace = Arc::new(Trace::default());
+        let session = FakeSession::streaming(
+            Arc::clone(&trace),
+            vec![
+                NextStep::DelayedEvent(
+                    Duration::from_secs(150),
+                    delivery(started(), CommitRequirement::CommitBeforeDelivery),
+                ),
+                NextStep::Event(delivery(completed(), CommitRequirement::AlreadyCommitted)),
+                NextStep::FinalizeSuccess,
+            ],
+        );
+        let actions = if invalid_output {
+            vec![ResponseFrameAction::Replace(Bytes::from_static(
+                b"data: {invalid-json}\n\n",
+            ))]
+        } else {
+            Vec::new()
+        };
+        let middleware = Arc::new(responses_middleware().with_response_actions(actions));
+        let response = tokio::time::timeout(
+            Duration::from_secs(20),
+            response_with_middleware(&admin, "openai", session, true, Some(middleware)),
+        )
+        .await
+        .expect("request middleware must not block transport keepalive");
+        assert_eq!(response.status(), StatusCode::OK);
+        assert!(response.headers().contains_key("x-gateway-request-id"));
+        let bytes = to_bytes(response.into_body(), usize::MAX).await.unwrap();
+        let text = std::str::from_utf8(&bytes).unwrap();
+        assert!(text.starts_with(": keep-alive\n\n"));
+        assert!(text.ends_with("data: [DONE]\n\n"));
+        if invalid_output {
+            assert!(text.contains("response.failed"));
+            assert!(text.contains("middleware_failed"));
+            assert!(!text.contains("{invalid-json}"));
+            assert!(trace.is_cancelled());
+        } else {
+            assert!(text.contains("response.completed"));
+            assert!(!text.contains("response.failed"));
+            assert!(!trace.is_cancelled());
+        }
+        assert_eq!(trace.client_statuses(), vec![200]);
+    }
+}

backend/crates/gateway-api/tests/openai/responses/mod.rs

@@ -34,6 +34,49 @@ fn generate_request(body: Value) -> DecodedResponsesRequest {
     decode_request(body.to_string().as_bytes()).expect("test request should decode")
 }
 
+#[test]
+fn decoder_should_attach_only_identified_codex_inference_turns() {
+    let body = json!({"model":"smart-code", "input":"hello", "client_metadata": {
+        "thread_id":"thread", "turn_id":"turn", "x-codex-turn-metadata": r#"{"request_kind":"turn"}"#
+    }});
+    let decoded = generate_request(body.clone());
+    let identity = generate_operation(&decoded).client_turn().unwrap();
+    assert_eq!(identity.thread_id(), "thread");
+    assert_eq!(identity.turn_id(), "turn");
+    assert_eq!(Value::Object(openai_wire_body(&decoded).clone()), body);
+    for variant in [
+        "warmup",
+        "compaction",
+        "missing_thread",
+        "missing_turn",
+        "unknown_kind",
+        "oversized_id",
+    ] {
+        let mut request = body.clone();
+        match variant {
+            "warmup" => request["generate"] = json!(false),
+            "compaction" => {
+                request["client_metadata"]["x-codex-turn-metadata"] =
+                    json!(r#"{"request_kind":"compaction"}"#)
+            }
+            "missing_thread" => request["client_metadata"]["thread_id"] = json!(""),
+            "missing_turn" => request["client_metadata"]["turn_id"] = json!(""),
+            "unknown_kind" => {
+                request["client_metadata"]["x-codex-turn-metadata"] =
+                    json!(r#"{"request_kind":"other"}"#)
+            }
+            "oversized_id" => request["client_metadata"]["turn_id"] = json!("x".repeat(257)),
+            _ => unreachable!(),
+        }
+        assert!(
+            generate_operation(&generate_request(request))
+                .client_turn()
+                .is_none(),
+            "{variant}"
+        );
+    }
+}
+
 fn generate_operation(
     decoded: &DecodedResponsesRequest,
 ) -> &gateway_core::operation::GenerateRequest {