chore: bump version to 3.0.9

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

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

@@ -201,11 +201,13 @@ struct RestartAcceptedView {
 #[derive(Debug, Serialize)]
 #[serde(rename_all = "camelCase")]
 struct SystemUpdateEventView {
+    id: String,
     operation_id: Option<String>,
     level: &'static str,
     step: Option<String>,
     message: String,
     terminal: bool,
+    progress_percent: Option<u8>,
     at: String,
 }
 
@@ -403,11 +405,13 @@ where
 impl From<SystemUpdateEvent> for SystemUpdateEventView {
     fn from(event: SystemUpdateEvent) -> Self {
         Self {
+            id: event.id,
             operation_id: event.operation_id,
             level: update_event_level_name(event.level),
             step: event.step,
             message: event.message,
             terminal: event.terminal,
+            progress_percent: event.progress_percent,
             at: event.occurred_at.to_rfc3339(),
         }
     }
@@ -416,11 +420,13 @@ impl From<SystemUpdateEvent> for SystemUpdateEventView {
 impl SystemUpdateEventView {
     fn into_json(self) -> serde_json::Value {
         serde_json::json!({
+            "id": self.id,
             "operationId": self.operation_id,
             "level": self.level,
             "step": self.step,
             "message": self.message,
             "terminal": self.terminal,
+            "progressPercent": self.progress_percent,
             "at": self.at,
         })
     }

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

@@ -39,7 +39,15 @@ pub(crate) async fn models(State(state): State<ApiState>, headers: HeaderMap) ->
             .enumerate()
             .map(|(index, profile)| codex_model_json(profile, index))
             .collect::<Vec<_>>();
-        return (StatusCode::OK, Json(json!({ "models": models }))).into_response();
+        return (
+            StatusCode::OK,
+            Json(json!({
+                "object": "list",
+                "data": data,
+                "models": models,
+            })),
+        )
+            .into_response();
     }
 
     (
@@ -209,6 +217,7 @@ fn codex_model_json(profile: &PublicModelProfile, index: usize) -> Value {
 fn reasoning_effort_description(effort: &str) -> &'static str {
     match effort {
         "none" => "No reasoning",
+        "minimal" => "Minimal reasoning",
         "low" => "Fast responses with lighter reasoning",
         "medium" => "Balances speed and reasoning depth for everyday tasks",
         "high" => "Greater reasoning depth for complex problems",

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

@@ -84,6 +84,10 @@ pub(super) struct AdminTestFixture {
 
 impl AdminTestFixture {
     pub async fn new() -> Self {
+        Self::with_system(Arc::new(UnusedSystem)).await
+    }
+
+    pub async fn with_system(system: Arc<dyn SystemOperations>) -> Self {
         let api_key = Arc::new(Mutex::new(None));
         let auth = Arc::new(MemoryAuthStore::new(api_key.clone()));
         let settings = Arc::new(MemorySettingsStore::new(api_key));
@@ -113,7 +117,7 @@ impl AdminTestFixture {
             providers,
             Arc::new(NoopSnapshot),
             Arc::new(NoopProbe),
-            Arc::new(UnusedSystem),
+            system,
         )
         .await
         .expect("initialize test admin services");

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

@@ -1,4 +1,24 @@
-use gateway_api::admin::system::{UpdateDetailQuery, UpdateRequest};
+use std::sync::Arc;
+
+use async_trait::async_trait;
+use axum::{
+    Router,
+    body::{Body, to_bytes},
+    http::{Request, header},
+};
+use chrono::Utc;
+use futures::stream;
+use gateway_admin::{
+    model::system::{
+        SystemOperationAccepted, SystemUpdateDetail, SystemUpdateEvent, SystemUpdateEventLevel,
+        SystemUpdateStatus, SystemVersion,
+    },
+    ports::system::{SystemOperationError, SystemOperations, SystemUpdateEventStream},
+};
+use gateway_api::admin::system::{self, UpdateDetailQuery, UpdateRequest};
+use tower::ServiceExt as _;
+
+use super::{AdminTestFixture, AdminTestState, unavailable_system};
 
 #[test]
 fn update_detail_query_should_default_to_no_refresh_and_reject_unknown_fields() {
@@ -16,3 +36,84 @@ fn update_request_should_preserve_target_version_for_domain_validation() {
         serde_json::from_str::<UpdateRequest>(r#"{"targetVersion":"v0.2.0","extra":1}"#).is_err()
     );
 }
+
+#[tokio::test]
+async fn update_event_stream_should_preserve_event_id_and_download_progress_percent() {
+    let fixture = AdminTestFixture::with_system(Arc::new(ProgressSystem)).await;
+    fixture.auth.insert_session("valid-session");
+    let response = app(fixture.state())
+        .oneshot(
+            Request::builder()
+                .uri("/api/admin/system/update/events")
+                .header(header::COOKIE, "cpr_admin_session=valid-session")
+                .header("x-request-id", "req_system_update_events")
+                .body(Body::empty())
+                .expect("update event request"),
+        )
+        .await
+        .expect("update event response");
+    let body = to_bytes(response.into_body(), 1024 * 1024)
+        .await
+        .expect("update event body");
+    let body = String::from_utf8(body.to_vec()).expect("UTF-8 event stream");
+
+    assert!(
+        body.contains(r#""id":"update-progress-1""#),
+        "unexpected update event stream: {body}"
+    );
+    assert!(
+        body.contains(r#""progressPercent":40"#),
+        "unexpected update event stream: {body}"
+    );
+}
+
+fn app(state: AdminTestState) -> Router {
+    system::router::<AdminTestState>().with_state(state)
+}
+
+struct ProgressSystem;
+
+#[async_trait]
+impl SystemOperations for ProgressSystem {
+    async fn version(&self) -> Result<SystemVersion, SystemOperationError> {
+        Err(unavailable_system())
+    }
+
+    async fn update_detail(&self, _: bool) -> Result<SystemUpdateDetail, SystemOperationError> {
+        Err(unavailable_system())
+    }
+
+    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(),
+            }
+        }))
+    }
+
+    async fn perform_update(
+        &self,
+        _: Option<String>,
+    ) -> Result<SystemOperationAccepted, SystemOperationError> {
+        Err(unavailable_system())
+    }
+
+    async fn update_status(&self) -> Result<SystemUpdateStatus, SystemOperationError> {
+        Err(unavailable_system())
+    }
+
+    async fn rollback(&self) -> Result<SystemOperationAccepted, SystemOperationError> {
+        Err(unavailable_system())
+    }
+
+    async fn restart(&self) -> Result<SystemOperationAccepted, SystemOperationError> {
+        Err(unavailable_system())
+    }
+}

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

@@ -67,7 +67,9 @@ impl ExecutionService for ModelsExecution {
             )
             .with_reasoning(
                 Some("medium".to_owned()),
-                ["low", "medium", "high"].map(str::to_owned).to_vec(),
+                ["low", "medium", "high", "xhigh"]
+                    .map(str::to_owned)
+                    .to_vec(),
             )
             .with_context_window_tokens(Some(500_000))
             .with_image_input(true)
@@ -138,6 +140,54 @@ async fn models_should_encode_provider_profiles_for_current_codex_clients() {
     assert_eq!(model["context_window"], 500_000);
     assert_eq!(model["apply_patch_tool_type"], "freeform");
     assert_eq!(model["service_tiers"], serde_json::json!([]));
+    assert_eq!(
+        model["supported_reasoning_levels"],
+        serde_json::json!([
+            {
+                "effort": "low",
+                "description": "Fast responses with lighter reasoning"
+            },
+            {
+                "effort": "medium",
+                "description": "Balances speed and reasoning depth for everyday tasks"
+            },
+            {
+                "effort": "high",
+                "description": "Greater reasoning depth for complex problems"
+            },
+            {
+                "effort": "xhigh",
+                "description": "Extra high reasoning depth for complex problems"
+            }
+        ])
+    );
+}
+
+#[tokio::test]
+async fn models_with_provider_profiles_should_keep_the_openai_list_contract() {
+    let response = api_router(ModelsExecution::with_profiles())
+        .await
+        .oneshot(authorized_request("/v1/models"))
+        .await
+        .expect("list compatible models response");
+    let body = to_bytes(response.into_body(), usize::MAX)
+        .await
+        .expect("read compatible models body");
+    let value: serde_json::Value = serde_json::from_slice(&body).expect("models JSON");
+
+    assert_eq!(
+        serde_json::json!({
+            "object": value["object"],
+            "data": value["data"],
+        }),
+        serde_json::json!({
+            "object": "list",
+            "data": [
+                {"id":"model-a","object":"model","created":1700000000_i64,"owned_by":"gateway"},
+                {"id":"model-b","object":"model","created":1700000000_i64,"owned_by":"gateway"}
+            ]
+        })
+    );
 }
 
 #[tokio::test]

backend/crates/gateway-host/src/system_update/download.rs

@@ -49,7 +49,7 @@ pub(crate) async fn download_file(
         .map_err(|error| super::internal(format!("failed to create download file: {error}")))?;
     let mut stream = response.bytes_stream();
     let mut downloaded = 0_u64;
-    let mut last_percent = 0_u8;
+    let mut next_progress = 10_u8;
     while let Some(chunk) = stream.next().await {
         let chunk = chunk.map_err(|error| upstream(format!("download stream failed: {error}")))?;
         downloaded = downloaded.saturating_add(u64::try_from(chunk.len()).unwrap_or(u64::MAX));
@@ -59,9 +59,17 @@ pub(crate) async fn download_file(
         file.write_all(&chunk)
             .map_err(|error| super::internal(format!("failed to write download: {error}")))?;
         let percent = download_percent(downloaded, expected_size);
-        if percent > last_percent {
-            last_percent = percent;
-            events.emit_progress(operation_id, "downloading release archive", percent);
+        if percent >= next_progress || downloaded == expected_size {
+            events.emit_progress(
+                operation_id,
+                &format!(
+                    "已下载 {} / {} ({percent}%)",
+                    format_bytes(downloaded),
+                    format_bytes(expected_size)
+                ),
+                percent,
+            );
+            next_progress = percent.saturating_add(10);
         }
     }
     file.sync_all()
@@ -155,3 +163,15 @@ fn download_percent(downloaded: u64, total: u64) -> u8 {
     )
     .unwrap_or(100)
 }
+
+pub(crate) fn format_bytes(bytes: u64) -> String {
+    const KIB: u64 = 1024;
+    const MIB: u64 = KIB * 1024;
+    if bytes >= MIB {
+        return format!("{:.1} MiB", bytes as f64 / MIB as f64);
+    }
+    if bytes >= KIB {
+        return format!("{:.1} KiB", bytes as f64 / KIB as f64);
+    }
+    format!("{bytes} B")
+}

backend/crates/gateway-host/src/system_update/mod.rs

@@ -232,8 +232,15 @@ impl ProcessSystemOperations {
             .as_deref()
             .ok_or_else(|| conflict("update repository is not configured"))?;
         self.events
-            .info(None, Some("release"), "fetching latest release");
-        let release = fetch_latest(&self.config.github_api_base, repository).await?;
+            .info(None, Some("release"), "正在获取最新 Release 信息");
+        let release = match fetch_latest(&self.config.github_api_base, repository).await {
+            Ok(release) => release,
+            Err(error) => {
+                self.events
+                    .error_terminal(None, Some("release"), error.to_string());
+                return Err(error);
+            }
+        };
         let detail = detail_from_release(&self.config, &release);
         if detail.latest_version != target {
             self.events.warning_terminal(
@@ -258,12 +265,17 @@ impl ProcessSystemOperations {
             Some(&target),
             &self.config.version,
         )?;
+        self.events.info(
+            Some(&operation_id),
+            Some("prepare"),
+            format!("准备更新到 v{target}"),
+        );
         let result = self.install_release(&release, &target, &operation_id).await;
         match &result {
             Ok(()) => self.events.success_terminal(
                 Some(&operation_id),
                 Some("done"),
-                "release files replaced",
+                "更新文件已替换，等待服务重启生效",
             ),
             Err(error) => {
                 self.events
@@ -294,7 +306,23 @@ impl ProcessSystemOperations {
         version: &str,
         operation_id: &str,
     ) -> Result<(), OperationError> {
+        self.events.info(
+            Some(operation_id),
+            Some("asset"),
+            "正在选择匹配当前平台的更新包",
+        );
         let archive = select_archive(release, version)?;
+        self.events.info(
+            Some(operation_id),
+            Some("asset"),
+            format!(
+                "已选择更新包 {} ({})",
+                archive.name,
+                download::format_bytes(archive.size)
+            ),
+        );
+        self.events
+            .info(Some(operation_id), Some("verify"), "正在校验更新资源");
         if archive.size == 0 || archive.size > MAX_DOWNLOAD_SIZE {
             return Err(invalid("release archive size is invalid"));
         }
@@ -306,12 +334,16 @@ impl ProcessSystemOperations {
         if checksum.size == 0 || checksum.size > MAX_CHECKSUM_SIZE {
             return Err(invalid("release checksum size is invalid"));
         }
+        self.events
+            .info(Some(operation_id), Some("prepare"), "正在创建临时更新目录");
         fs::create_dir_all(&self.config.update_temp_dir)
             .map_err(|error| internal(format!("failed to prepare update temp dir: {error}")))?;
         let temp_root = fs::canonicalize(&self.config.update_temp_dir)
             .map_err(|error| internal(format!("failed to resolve update temp dir: {error}")))?;
         let temp = UpdateTempDir::create(&temp_root)?;
         let archive_path = temp.path().join(&archive.name);
+        self.events
+            .info(Some(operation_id), Some("download"), "开始下载更新包");
         download_file(
             &archive.browser_download_url,
             &archive_path,
@@ -321,6 +353,10 @@ impl ProcessSystemOperations {
             &self.events,
         )
         .await?;
+        self.events
+            .success(Some(operation_id), Some("download"), "更新包下载完成");
+        self.events
+            .info(Some(operation_id), Some("checksum"), "正在校验 checksum");
         verify_checksum(
             &archive_path,
             &archive.name,
@@ -329,12 +365,23 @@ impl ProcessSystemOperations {
             &self.config.github_api_base,
         )
         .await?;
+        self.events
+            .success(Some(operation_id), Some("checksum"), "checksum 校验通过");
+        self.events
+            .info(Some(operation_id), Some("extract"), "正在解压更新包");
         let extracted = extract_release(&archive_path, temp.path())?;
+        self.events
+            .success(Some(operation_id), Some("extract"), "更新包解压完成");
+        self.events
+            .info(Some(operation_id), Some("replace"), "正在替换应用文件");
         replace_release_files(
             &self.config.executable_path()?,
             &self.config.web_dist_dir,
             extracted,
-        )
+        )?;
+        self.events
+            .success(Some(operation_id), Some("replace"), "应用文件替换完成");
+        Ok(())
     }
 }
 
@@ -515,6 +562,17 @@ impl UpdateEvents {
         );
     }
 
+    fn success(&self, operation_id: Option<&str>, step: Option<&str>, message: impl Into<String>) {
+        self.emit(
+            SystemUpdateEventLevel::Success,
+            operation_id,
+            step,
+            message,
+            None,
+            false,
+        );
+    }
+
     fn warning_terminal(
         &self,
         operation_id: Option<&str>,

backend/crates/gateway-host/tests/system_update/mod.rs

@@ -204,6 +204,68 @@ async fn update_events_should_open_authenticated_sse_stream() {
     assert!(stream.next().await.is_some());
 }
 
+#[tokio::test]
+async fn update_events_should_preserve_complete_release_stage_sequence() {
+    let server = MockServer::start().await;
+    let fixture = Fixture::new();
+    fixture
+        .mount_release(
+            &server,
+            TARGET_VERSION,
+            ArchiveKind::Safe,
+            ChecksumKind::Valid,
+        )
+        .await;
+    let service = fixture.service(&server);
+    let events = service.update_events();
+    service
+        .perform_update(Some(TARGET_VERSION.to_owned()))
+        .await
+        .expect("update");
+    let steps = events
+        .map(|event| event.step.expect("release update step"))
+        .collect::<Vec<_>>()
+        .await;
+
+    assert_eq!(
+        steps,
+        [
+            "release", "prepare", "asset", "asset", "verify", "prepare", "download", "download",
+            "download", "checksum", "checksum", "extract", "extract", "replace", "replace", "done",
+        ]
+    );
+}
+
+#[tokio::test]
+async fn update_events_should_report_download_bytes_and_percent() {
+    let server = MockServer::start().await;
+    let fixture = Fixture::new();
+    fixture
+        .mount_release(
+            &server,
+            TARGET_VERSION,
+            ArchiveKind::Safe,
+            ChecksumKind::Valid,
+        )
+        .await;
+    let service = fixture.service(&server);
+    let events = service.update_events();
+    service
+        .perform_update(Some(TARGET_VERSION.to_owned()))
+        .await
+        .expect("update");
+    let progress = events
+        .filter_map(
+            |event| async move { event.progress_percent.map(|value| (value, event.message)) },
+        )
+        .collect::<Vec<_>>()
+        .await;
+
+    assert!(progress.iter().any(|(percent, message)| {
+        *percent == 100 && message.starts_with("已下载 ") && message.ends_with(" (100%)")
+    }));
+}
+
 #[tokio::test]
 async fn update_should_fail_when_release_checksum_is_missing() {
     let server = MockServer::start().await;

backend/crates/providers/xai/src/admin.rs

@@ -11,8 +11,9 @@ use gateway_admin::model::accounts::{
     AccountAvailability as AdminAccountAvailability, AccountRecord,
 };
 use gateway_admin::model::observability::{
-    CalculatedBillingBreakdown, CurrencyCost, DashboardWireAttribute, DashboardWireProfile,
-    DashboardWireTarget, DecimalAmount, ProviderBillingInput,
+    CalculatedBillingBreakdown, CurrencyCost, DashboardDesktopRelease, DashboardWireAttribute,
+    DashboardWireProfile, DashboardWireTarget, DecimalAmount, DesktopReleaseStatus,
+    ProviderBillingInput,
 };
 use gateway_admin::model::provider_credentials::{
     AuthorizationMutationTarget, AuthorizationOwner, AuthorizationOwnerBinding,
@@ -57,6 +58,7 @@ use crate::credential::{
     PreparedGrokCredentialRotation, PreparedGrokCredentialRotationGuard, RedirectUriAllowlist,
     RotateManagedGrokCredential, SecretValue, VerifiedGrokAccount, VerifiedTokenSet,
 };
+use crate::transport::profile::{GrokCliReleaseSnapshot, GrokCliReleaseStatus};
 use crate::transport::{GROK_CLI_BASE_URL, XAI_PROVIDER_NAME, grok_billing_breakdown};
 
 const PENDING_SCHEMA_VERSION: u64 = 2;
@@ -66,6 +68,7 @@ const MAX_PENDING_TEXT_BYTES: usize = 512;
 pub(crate) struct XaiAdminProvider {
     provider_kind: ProviderKind,
     wire_profile: XaiWireProfileState,
+    cli_release: GrokCliReleaseStatus,
     accounts: Arc<dyn ProviderAccountStore>,
     repository: GrokCredentialRepository,
     oauth_config: GrokOAuthConfig,
@@ -95,10 +98,12 @@ impl XaiAdminProvider {
         wire_profile: XaiWireProfileState,
         accounts: Arc<dyn ProviderAccountStore>,
         services: XaiAdminServices,
+        cli_release: GrokCliReleaseStatus,
     ) -> Self {
         Self {
             provider_kind,
             wire_profile,
+            cli_release,
             accounts,
             repository: services.repository,
             oauth_config: services.oauth_config,
@@ -216,34 +221,42 @@ impl ProviderAdmin for XaiAdminProvider {
     }
 
     fn dashboard_wire_profile(&self) -> Option<DashboardWireProfile> {
+        let profile = self.wire_profile.snapshot();
+        let release = dashboard_cli_release(&profile.client_version, self.cli_release.snapshot());
         Some(DashboardWireProfile {
             provider: self.provider_kind.as_str().to_owned(),
             product: "Grok Build".to_owned(),
-            version: self.wire_profile.client_version(),
+            version: profile.client_version.clone(),
             build: None,
             target: DashboardWireTarget {
-                os_type: self.wire_profile.target_os(),
+                os_type: profile.target_os.clone(),
                 os_version: "—".to_owned(),
-                arch: self.wire_profile.target_arch(),
-                terminal: self.wire_profile.client_mode(),
+                arch: profile.target_arch.clone(),
+                terminal: profile.client_mode.clone(),
             },
-            user_agent: self.wire_profile.user_agent(),
+            user_agent: format!(
+                "{}/{} ({}; {})",
+                profile.client_identifier,
+                profile.client_version,
+                profile.target_os,
+                profile.target_arch
+            ),
             attributes: vec![
                 DashboardWireAttribute {
                     label: "客户端标识".to_owned(),
-                    value: self.wire_profile.client_identifier(),
+                    value: profile.client_identifier,
                 },
                 DashboardWireAttribute {
                     label: "运行模式".to_owned(),
-                    value: self.wire_profile.client_mode(),
+                    value: profile.client_mode,
                 },
                 DashboardWireAttribute {
                     label: "Token 认证".to_owned(),
                     value: "xai-grok-cli".to_owned(),
                 },
             ],
-            verified_at: Some(self.wire_profile.verified_at()),
-            release: None,
+            verified_at: Some(profile.verified_at),
+            release: Some(release),
         })
     }
 
@@ -771,6 +784,36 @@ fn validate_account_record(
     Ok(())
 }
 
+fn dashboard_cli_release(
+    profile_version: &str,
+    snapshot: GrokCliReleaseSnapshot,
+) -> DashboardDesktopRelease {
+    let status = if snapshot.checked_at.is_none() {
+        DesktopReleaseStatus::Unchecked
+    } else if snapshot.last_error.is_some() {
+        DesktopReleaseStatus::Failed
+    } else if snapshot.latest_version.as_deref() == Some(profile_version) {
+        DesktopReleaseStatus::Current
+    } else if snapshot.latest_version.is_some() {
+        DesktopReleaseStatus::UpdateAvailable
+    } else {
+        DesktopReleaseStatus::Failed
+    };
+    DashboardDesktopRelease {
+        status,
+        checked_at: snapshot.checked_at,
+        latest_version: snapshot.latest_version,
+        latest_build: None,
+        published_at: None,
+        minimum_system_version: None,
+        hardware_requirements: None,
+        download_url: None,
+        download_size: None,
+        signature_present: None,
+        error: snapshot.last_error,
+    }
+}
+
 fn account_from_record(account: &AccountRecord) -> Result<ProviderAccount, ProviderAdminError> {
     let account_id = ProviderAccountId::new(account.id.clone())
         .map_err(|_| provider_error(ProviderAdminErrorKind::Invalid))?;

backend/crates/providers/xai/src/lib.rs

@@ -57,23 +57,25 @@ pub use transport::{
     GrokBillingTransportError, GrokBillingTransportErrorKind, GrokBillingTransportFuture,
     GrokBillingTransportResponse, GrokCanonicalDecoder, GrokCatalogApiBackend,
     GrokCatalogCapabilities, GrokCatalogCapabilityEvidence, GrokCatalogLimits, GrokCatalogMetadata,
-    GrokCatalogModel, GrokClientIdentity, GrokCompactionDecodeError, GrokCompactionRequest,
-    GrokCompactionSummaryDecoder, GrokCredentialFailure, GrokCredentialFeedbackFuture,
-    GrokDnsResolutionError, GrokDnsResolutionPlan, GrokDnsResolutionPolicy, GrokEndpointPolicy,
-    GrokHeader, GrokHeaderValue, GrokInferenceChunkStream, GrokInferenceRequest,
-    GrokInferenceResponse, GrokInferenceTransport, GrokInferenceTransportError,
-    GrokInferenceTransportErrorKind, GrokInferenceTransportFuture, GrokModelCatalogClient,
-    GrokModelCatalogError, GrokModelCatalogRequest, GrokModelCatalogSession,
-    GrokModelCatalogSessionError, GrokModelCatalogSnapshot, GrokModelCatalogTransport,
-    GrokModelCatalogTransportError, GrokModelCatalogTransportErrorKind,
-    GrokModelCatalogTransportFuture, GrokModelCatalogTransportResponse, GrokProviderConfigError,
-    GrokProviderTransport, GrokRequestEncodeError, GrokReqwestTransportBuildError,
-    GrokResponsesRequest, GrokSessionAffinityKey, GrokSessionBinding, GrokSessionDataError,
-    GrokSessionLeaseGuard, GrokSessionSelection, GrokSessionSelector, GrokSessionSelectorError,
-    GrokSessionSelectorFuture, MAX_GROK_BILLING_BYTES, MAX_GROK_MODEL_CATALOG_BYTES,
-    OfficialGrokEndpointPolicy, ReqwestGrokInferenceTransport, ReqwestGrokModelCatalogTransport,
-    ReqwestOAuthTransport, SelectedGrokSession, XAI_PROVIDER_NAME, build_grok_headers,
-    grok_billing_breakdown, parse_grok_billing, parse_grok_model_catalog,
+    GrokCatalogModel, GrokCatalogReasoningEffort, GrokClientIdentity, GrokCompactionDecodeError,
+    GrokCompactionRequest, GrokCompactionSummaryDecoder, GrokCredentialFailure,
+    GrokCredentialFeedbackFuture, GrokDnsResolutionError, GrokDnsResolutionPlan,
+    GrokDnsResolutionPolicy, GrokEndpointPolicy, GrokHeader, GrokHeaderValue,
+    GrokInferenceChunkStream, GrokInferenceClientCacheStatus, GrokInferenceDnsObservation,
+    GrokInferenceDnsSource, GrokInferenceRequest, GrokInferenceResponse, GrokInferenceTransport,
+    GrokInferenceTransportError, GrokInferenceTransportErrorKind, GrokInferenceTransportFuture,
+    GrokInferenceTransportMetrics, GrokModelCatalogClient, GrokModelCatalogError,
+    GrokModelCatalogRequest, GrokModelCatalogSession, GrokModelCatalogSessionError,
+    GrokModelCatalogSnapshot, GrokModelCatalogTransport, GrokModelCatalogTransportError,
+    GrokModelCatalogTransportErrorKind, GrokModelCatalogTransportFuture,
+    GrokModelCatalogTransportResponse, GrokProviderConfigError, GrokProviderTransport,
+    GrokRequestEncodeError, GrokReqwestTransportBuildError, GrokResponsesRequest,
+    GrokSessionAffinityKey, GrokSessionBinding, GrokSessionDataError, GrokSessionLeaseGuard,
+    GrokSessionSelection, GrokSessionSelector, GrokSessionSelectorError, GrokSessionSelectorFuture,
+    MAX_GROK_BILLING_BYTES, MAX_GROK_MODEL_CATALOG_BYTES, OfficialGrokEndpointPolicy,
+    ReqwestGrokInferenceTransport, ReqwestGrokModelCatalogTransport, ReqwestOAuthTransport,
+    SelectedGrokSession, XAI_PROVIDER_NAME, build_grok_headers, grok_billing_breakdown,
+    parse_grok_billing, parse_grok_model_catalog,
 };
 
 /// xAI 初始化后交给组装根的最小能力集。
@@ -99,6 +101,7 @@ pub async fn initialize(
             OfficialGrokCliReleaseTransport::new().map_err(|_| XaiInitializeError::Transport)?,
         ),
     ));
+    let cli_release_status = cli_release.status();
     let provider_kind =
         ProviderKind::new(XAI_PROVIDER_NAME).map_err(|_| XaiInitializeError::ProviderKind)?;
     let accounts: Arc<dyn ProviderAccountStore> = ports.accounts();
@@ -193,6 +196,7 @@ pub async fn initialize(
             catalog: Arc::clone(&catalog),
             runtime_policy,
         },
+        cli_release_status,
     ));
     let worker_contributions = provider::worker_contributions(
         refresh,

backend/crates/providers/xai/src/provider.rs

@@ -21,7 +21,10 @@ use gateway_core::engine::{AttemptContext, ContinuationAttempt, UpstreamSendStat
 use gateway_core::error::{
     ClientVisibleUpstreamError, ContinuationFailure, ProviderError, ProviderErrorKind,
 };
-use gateway_core::event::{GatewayEvent, ProviderEvent, ProviderResponseObservation, ResponseMeta};
+use gateway_core::event::{
+    GatewayEvent, ProviderEvent, ProviderResponseMetadata, ProviderResponseObservation,
+    ProviderResponseTimings, ResponseMeta,
+};
 use gateway_core::operation::{
     Feature, GenerateRequest, Operation, OperationKind, ProviderSessionState,
 };
@@ -52,9 +55,9 @@ use crate::transport::{
     GROK_RESPONSES_URL, GrokCompactionDecodeError, GrokCompactionRequest,
     GrokCompactionSummaryDecoder, GrokCredentialFailure, GrokInferenceChunkStream,
     GrokInferenceRequest, GrokInferenceResponse, GrokInferenceTransport,
-    GrokInferenceTransportError, GrokInferenceTransportErrorKind, GrokProviderConfigError,
-    GrokRequestEncodeError, GrokResponsesRequest, GrokSessionAffinityKey, GrokSessionSelection,
-    GrokSessionSelector, GrokSessionSelectorError, SelectedGrokSession,
+    GrokInferenceTransportError, GrokInferenceTransportErrorKind, GrokInferenceTransportMetrics,
+    GrokProviderConfigError, GrokRequestEncodeError, GrokResponsesRequest, GrokSessionAffinityKey,
+    GrokSessionSelection, GrokSessionSelector, GrokSessionSelectorError, SelectedGrokSession,
 };
 use crate::{GrokCatalogCapabilityEvidence, GrokCatalogModel};
 
@@ -427,7 +430,9 @@ fn default_grok_model_presentation() -> ModelPresentation {
     )
     .with_reasoning(
         Some("medium".to_owned()),
-        ["low", "medium", "high"].map(str::to_owned).to_vec(),
+        ["low", "medium", "high", "xhigh"]
+            .map(str::to_owned)
+            .to_vec(),
     )
     .with_context_window_tokens(Some(500_000))
     .with_image_input(true)
@@ -441,17 +446,35 @@ fn grok_model_presentation(model: &GrokCatalogModel) -> ModelPresentation {
         DEFAULT_GROK_MODEL | "grok-4.5-latest" | "grok-4.5-build-free" | "grok-build-latest"
     );
     let reasoning_evidence = model.capabilities().reasoning_effort();
+    let catalog_reasoning_efforts = model
+        .capabilities()
+        .reasoning_efforts()
+        .iter()
+        .map(|effort| effort.as_str().to_owned())
+        .collect::<Vec<_>>();
+    let catalog_default_reasoning = model
+        .capabilities()
+        .default_reasoning_effort()
+        .map(|effort| effort.as_str().to_owned());
     let (default_reasoning, reasoning_efforts) = match reasoning_evidence {
+        GrokCatalogCapabilityEvidence::DeclaredNative if !catalog_reasoning_efforts.is_empty() => (
+            catalog_default_reasoning.or_else(|| catalog_reasoning_efforts.first().cloned()),
+            catalog_reasoning_efforts,
+        ),
         GrokCatalogCapabilityEvidence::DeclaredNative => (
-            Some("medium".to_owned()),
-            ["low", "medium", "high"].map(str::to_owned).to_vec(),
+            catalog_default_reasoning.or_else(|| Some("medium".to_owned())),
+            ["low", "medium", "high", "xhigh"]
+                .map(str::to_owned)
+                .to_vec(),
         ),
         GrokCatalogCapabilityEvidence::DeclaredUnsupported => {
             (Some("none".to_owned()), vec!["none".to_owned()])
         }
         GrokCatalogCapabilityEvidence::Unknown if known_grok_4_5 => (
-            Some("medium".to_owned()),
-            ["low", "medium", "high"].map(str::to_owned).to_vec(),
+            catalog_default_reasoning.or_else(|| Some("medium".to_owned())),
+            ["low", "medium", "high", "xhigh"]
+                .map(str::to_owned)
+                .to_vec(),
         ),
         GrokCatalogCapabilityEvidence::Unknown => (None, Vec::new()),
     };
@@ -950,17 +973,11 @@ async fn start_grok_inference(
             return Err(GrokInferenceStartFailure { observation, error });
         }
     };
-    let mut observation = ProviderResponseObservation::new(
-        UpstreamTransport::new(HTTP_SSE_TRANSPORT).map_err(|_| GrokInferenceStartFailure {
+    let observation =
+        xai_response_observation(&response).map_err(|error| GrokInferenceStartFailure {
             observation: None,
-            error: protocol_sent(),
-        })?,
-    )
-    .with_http_version(response.http_version())
-    .with_status_code(response.status_code());
-    if let Some(request_id) = response.request_id().cloned() {
-        observation = observation.with_request_id(request_id);
-    }
+            error,
+        })?;
     Ok(AcceptedGrokInference {
         response,
         observation,
@@ -1277,17 +1294,7 @@ fn cold_http_sse_stream(
             }
         };
 
-        let mut observation = ProviderResponseObservation::new(
-            UpstreamTransport::new(HTTP_SSE_TRANSPORT).map_err(|_| provider_error(
-                ProviderErrorKind::Protocol,
-                UpstreamSendState::Sent,
-            ))?,
-        )
-        .with_http_version(response.http_version())
-        .with_status_code(response.status_code());
-        if let Some(request_id) = response.request_id().cloned() {
-            observation = observation.with_request_id(request_id);
-        }
+        let observation = xai_response_observation(&response)?;
         yield ProviderEvent::observation(observation);
 
         let mut body = response.into_body();
@@ -1383,7 +1390,68 @@ fn xai_error_observation(
     if let Some(request_id) = error.request_id().cloned() {
         observation = observation.with_request_id(request_id);
     }
-    Ok(observation)
+    Ok(with_xai_transport_metrics(
+        observation,
+        error.transport_metrics(),
+    ))
+}
+
+fn xai_response_observation(
+    response: &GrokInferenceResponse,
+) -> Result<ProviderResponseObservation, ProviderError> {
+    let mut observation = ProviderResponseObservation::new(
+        UpstreamTransport::new(HTTP_SSE_TRANSPORT)
+            .map_err(|_| provider_error(ProviderErrorKind::Protocol, UpstreamSendState::Sent))?,
+    )
+    .with_http_version(response.http_version())
+    .with_status_code(response.status_code());
+    if let Some(request_id) = response.request_id().cloned() {
+        observation = observation.with_request_id(request_id);
+    }
+    Ok(with_xai_transport_metrics(
+        observation,
+        response.transport_metrics(),
+    ))
+}
+
+fn with_xai_transport_metrics(
+    mut observation: ProviderResponseObservation,
+    metrics: GrokInferenceTransportMetrics,
+) -> ProviderResponseObservation {
+    observation = observation.with_timings(ProviderResponseTimings {
+        headers_ms: metrics.headers_ms(),
+        ..ProviderResponseTimings::default()
+    });
+    if let Some(metadata) = xai_transport_metadata(metrics) {
+        observation = observation.with_provider_metadata(metadata);
+    }
+    observation
+}
+
+fn xai_transport_metadata(
+    metrics: GrokInferenceTransportMetrics,
+) -> Option<ProviderResponseMetadata> {
+    let mut metadata = Map::new();
+    if let Some(status) = metrics.client_cache_status() {
+        metadata.insert(
+            "clientCache".to_owned(),
+            Value::String(status.as_str().to_owned()),
+        );
+    }
+    if let Some(dns) = metrics.dns() {
+        metadata.insert(
+            "dnsSource".to_owned(),
+            Value::String(dns.source().as_str().to_owned()),
+        );
+        metadata.insert("dnsMs".to_owned(), Value::from(dns.duration_ms()));
+    }
+    if let Some(headers_ms) = metrics.headers_ms() {
+        metadata.insert("upstreamHeadersMs".to_owned(), Value::from(headers_ms));
+    }
+    if metadata.is_empty() {
+        return None;
+    }
+    ProviderResponseMetadata::new(serde_json::to_string(&Value::Object(metadata)).ok()?)
 }
 
 async fn record_failure(

backend/crates/providers/xai/src/transport/catalog.rs

@@ -589,11 +589,42 @@ pub enum GrokCatalogApiBackend {
     Unknown,
 }
 
+/// Grok 官方目录允许声明的 reasoning effort。
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Deserialize)]
+#[serde(rename_all = "lowercase")]
+pub enum GrokCatalogReasoningEffort {
+    None,
+    Minimal,
+    Low,
+    Medium,
+    High,
+    Xhigh,
+    Max,
+}
+
+impl GrokCatalogReasoningEffort {
+    /// 返回 Responses API 使用的规范值。
+    #[must_use]
+    pub const fn as_str(self) -> &'static str {
+        match self {
+            Self::None => "none",
+            Self::Minimal => "minimal",
+            Self::Low => "low",
+            Self::Medium => "medium",
+            Self::High => "high",
+            Self::Xhigh => "xhigh",
+            Self::Max => "max",
+        }
+    }
+}
+
 /// Grok 目录中允许进入控制面的能力证据。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct GrokCatalogCapabilities {
     responses_api: GrokCatalogCapabilityEvidence,
     reasoning_effort: GrokCatalogCapabilityEvidence,
+    reasoning_efforts: Vec<GrokCatalogReasoningEffort>,
+    default_reasoning_effort: Option<GrokCatalogReasoningEffort>,
     backend_search: GrokCatalogCapabilityEvidence,
     streaming_tool_calls: GrokCatalogCapabilityEvidence,
     api_backend: Option<GrokCatalogApiBackend>,
@@ -612,6 +643,18 @@ impl GrokCatalogCapabilities {
         self.reasoning_effort
     }
 
+    /// 返回上游声明的可选 reasoning effort，顺序与目录一致。
+    #[must_use]
+    pub fn reasoning_efforts(&self) -> &[GrokCatalogReasoningEffort] {
+        &self.reasoning_efforts
+    }
+
+    /// 返回上游声明或菜单推导出的默认 reasoning effort。
+    #[must_use]
+    pub const fn default_reasoning_effort(&self) -> Option<GrokCatalogReasoningEffort> {
+        self.default_reasoning_effort
+    }
+
     /// 返回后端 search 支持证据。
     #[must_use]
     pub const fn backend_search(&self) -> GrokCatalogCapabilityEvidence {
@@ -850,6 +893,10 @@ struct GrokModelWire {
         alias = "supports_reasoning_effort"
     )]
     supports_reasoning_effort: Option<bool>,
+    #[serde(rename = "reasoningEffort", alias = "reasoning_effort")]
+    reasoning_effort: Option<GrokCatalogReasoningEffort>,
+    #[serde(default, rename = "reasoningEfforts", alias = "reasoning_efforts")]
+    reasoning_efforts: Vec<GrokReasoningEffortOptionWire>,
     #[serde(rename = "supportsBackendSearch", alias = "supports_backend_search")]
     supports_backend_search: Option<bool>,
     #[serde(rename = "streamToolCalls", alias = "stream_tool_calls")]
@@ -857,6 +904,26 @@ struct GrokModelWire {
     hidden: Option<bool>,
 }
 
+#[derive(Debug, Deserialize)]
+#[serde(untagged)]
+enum GrokReasoningEffortOptionWire {
+    Bare(GrokCatalogReasoningEffort),
+    Detailed {
+        value: GrokCatalogReasoningEffort,
+        #[serde(default)]
+        default: bool,
+    },
+}
+
+impl GrokReasoningEffortOptionWire {
+    fn into_parts(self) -> (GrokCatalogReasoningEffort, bool) {
+        match self {
+            Self::Bare(value) => (value, false),
+            Self::Detailed { value, default } => (value, default),
+        }
+    }
+}
+
 /// 解析唯一受支持的 Grok 官方完整快照。
 ///
 /// # Errors
@@ -922,15 +989,36 @@ fn normalize_model(wire: GrokModelWire) -> Result<GrokCatalogModel, GrokModelCat
         .api_backend
         .filter(|backend| *backend != GrokCatalogApiBackend::Unknown);
     let responses_api = responses_evidence(wire.supported_in_api, api_backend);
+    let mut menu_default = None;
+    let reasoning_efforts = wire
+        .reasoning_efforts
+        .into_iter()
+        .map(|option| {
+            let (effort, is_default) = option.into_parts();
+            if is_default && menu_default.is_none() {
+                menu_default = Some(effort);
+            }
+            effort
+        })
+        .collect::<Vec<_>>();
+    let default_reasoning_effort = wire
+        .reasoning_effort
+        .or(menu_default)
+        .or_else(|| reasoning_efforts.first().copied());
+    let reasoning_effort = if reasoning_efforts.is_empty() {
+        GrokCatalogCapabilityEvidence::from_wire(wire.supports_reasoning_effort)
+    } else {
+        GrokCatalogCapabilityEvidence::DeclaredNative
+    };
 
     Ok(GrokCatalogModel {
         request_model,
         display_name: wire.name,
         capabilities: GrokCatalogCapabilities {
             responses_api,
-            reasoning_effort: GrokCatalogCapabilityEvidence::from_wire(
-                wire.supports_reasoning_effort,
-            ),
+            reasoning_effort,
+            reasoning_efforts,
+            default_reasoning_effort,
             backend_search: GrokCatalogCapabilityEvidence::from_wire(wire.supports_backend_search),
             streaming_tool_calls: GrokCatalogCapabilityEvidence::from_wire(wire.stream_tool_calls),
             api_backend,

backend/crates/providers/xai/src/transport/mod.rs

@@ -21,10 +21,10 @@ pub use catalog::{
     GrokBillingRequest, GrokBillingSnapshot, GrokBillingTransport, GrokBillingTransportError,
     GrokBillingTransportErrorKind, GrokBillingTransportFuture, GrokBillingTransportResponse,
     GrokCatalogApiBackend, GrokCatalogCapabilities, GrokCatalogCapabilityEvidence,
-    GrokCatalogLimits, GrokCatalogMetadata, GrokCatalogModel, GrokModelCatalogClient,
-    GrokModelCatalogError, GrokModelCatalogRequest, GrokModelCatalogSession,
-    GrokModelCatalogSessionError, GrokModelCatalogSnapshot, GrokModelCatalogTransport,
-    GrokModelCatalogTransportError, GrokModelCatalogTransportErrorKind,
+    GrokCatalogLimits, GrokCatalogMetadata, GrokCatalogModel, GrokCatalogReasoningEffort,
+    GrokModelCatalogClient, GrokModelCatalogError, GrokModelCatalogRequest,
+    GrokModelCatalogSession, GrokModelCatalogSessionError, GrokModelCatalogSnapshot,
+    GrokModelCatalogTransport, GrokModelCatalogTransportError, GrokModelCatalogTransportErrorKind,
     GrokModelCatalogTransportFuture, GrokModelCatalogTransportResponse, MAX_GROK_BILLING_BYTES,
     MAX_GROK_MODEL_CATALOG_BYTES, parse_grok_billing, parse_grok_model_catalog,
 };
@@ -49,6 +49,8 @@ pub use session::{
     GrokSessionSelector, GrokSessionSelectorError, GrokSessionSelectorFuture, SelectedGrokSession,
 };
 pub use transport::{
-    GrokInferenceChunkStream, GrokInferenceRequest, GrokInferenceResponse, GrokInferenceTransport,
+    GrokInferenceChunkStream, GrokInferenceClientCacheStatus, GrokInferenceDnsObservation,
+    GrokInferenceDnsSource, GrokInferenceRequest, GrokInferenceResponse, GrokInferenceTransport,
     GrokInferenceTransportError, GrokInferenceTransportErrorKind, GrokInferenceTransportFuture,
+    GrokInferenceTransportMetrics,
 };

backend/crates/providers/xai/src/transport/network.rs

@@ -4,8 +4,8 @@ use std::collections::{HashMap, VecDeque};
 use std::fmt;
 use std::io;
 use std::net::{IpAddr, Ipv4Addr, Ipv6Addr, SocketAddr};
-use std::sync::{Arc, Mutex};
-use std::time::Duration;
+use std::sync::{Arc, Mutex, OnceLock};
+use std::time::{Duration, Instant};
 
 use futures::StreamExt;
 use reqwest::dns::{Addrs, Name, Resolve, Resolving};
@@ -20,13 +20,14 @@ use crate::credential::discovery::MAX_OAUTH_RESPONSE_BYTES;
 use crate::{
     GrokBillingRequest, GrokBillingTransport, GrokBillingTransportError,
     GrokBillingTransportErrorKind, GrokBillingTransportFuture, GrokBillingTransportResponse,
+    GrokInferenceClientCacheStatus, GrokInferenceDnsObservation, GrokInferenceDnsSource,
     GrokInferenceRequest, GrokInferenceResponse, GrokInferenceTransport,
     GrokInferenceTransportError, GrokInferenceTransportErrorKind, GrokInferenceTransportFuture,
-    GrokModelCatalogRequest, GrokModelCatalogTransport, GrokModelCatalogTransportError,
-    GrokModelCatalogTransportErrorKind, GrokModelCatalogTransportFuture,
-    GrokModelCatalogTransportResponse, GrokSessionBinding, HttpMethod, MAX_GROK_BILLING_BYTES,
-    MAX_GROK_MODEL_CATALOG_BYTES, OAuthHttpRequest, OAuthHttpResponse, OAuthHttpTransport,
-    TransportFailure, TransportFailureKind, TransportFuture,
+    GrokInferenceTransportMetrics, GrokModelCatalogRequest, GrokModelCatalogTransport,
+    GrokModelCatalogTransportError, GrokModelCatalogTransportErrorKind,
+    GrokModelCatalogTransportFuture, GrokModelCatalogTransportResponse, GrokSessionBinding,
+    HttpMethod, MAX_GROK_BILLING_BYTES, MAX_GROK_MODEL_CATALOG_BYTES, OAuthHttpRequest,
+    OAuthHttpResponse, OAuthHttpTransport, TransportFailure, TransportFailureKind, TransportFuture,
 };
 use gateway_core::engine::UpstreamSendState;
 use gateway_core::error::SafeUpstreamValue;
@@ -42,6 +43,9 @@ pub(crate) const OFFICIAL_USERINFO_PATH: &str = "/oauth2/userinfo";
 const CONNECT_TIMEOUT: Duration = Duration::from_secs(10);
 const OAUTH_REQUEST_TIMEOUT: Duration = Duration::from_secs(30);
 const POOL_IDLE_TIMEOUT: Duration = Duration::from_secs(90);
+const POOL_MAX_IDLE_PER_HOST: usize = 2;
+const HTTP2_KEEP_ALIVE_INTERVAL: Duration = Duration::from_secs(15);
+const HTTP2_KEEP_ALIVE_TIMEOUT: Duration = Duration::from_secs(5);
 const MAX_ERROR_BODY_BYTES: usize = 64 * 1024;
 const MAX_INFERENCE_BODY_BYTES: usize = 256 * 1024 * 1024;
 const MAX_RETRY_AFTER_SECONDS: u64 = 120;
@@ -55,6 +59,10 @@ const TRUSTED_DOH_BOOTSTRAP: [SocketAddr; 2] = [
     SocketAddr::new(IpAddr::V4(Ipv4Addr::new(8, 8, 4, 4)), 443),
 ];
 
+tokio::task_local! {
+    static REQUEST_DNS_OBSERVER: Arc<RequestDnsObserver>;
+}
+
 /// 构建严格 reqwest transport 失败。
 #[derive(Debug, thiserror::Error, Clone, Copy, PartialEq, Eq)]
 pub enum GrokReqwestTransportBuildError {
@@ -314,12 +322,31 @@ impl ReqwestGrokInferenceTransport {
     fn client_for(
         &self,
         binding: &GrokSessionBinding,
-    ) -> Result<Client, GrokInferenceTransportError> {
-        self.clients
+    ) -> Result<(Client, GrokInferenceClientCacheStatus), GrokInferenceTransportError> {
+        let unbound_client = {
+            let mut clients = self
+                .clients
+                .lock()
+                .map_err(|_| inference_client_pool_unavailable())?;
+            if let Some(client) = clients.get(binding) {
+                return Ok((client, GrokInferenceClientCacheStatus::Hit));
+            }
+            clients.take_unbound()
+        };
+
+        let client = match unbound_client {
+            Some(client) => client,
+            None => self
+                .endpoint_policy
+                .build_inference_client(None)
+                .map_err(|_| inference_client_pool_unavailable_for_cache_miss())?,
+        };
+        let client = self
+            .clients
             .lock()
-            .map_err(|_| inference_client_pool_unavailable())?
-            .get_or_insert(binding, self.endpoint_policy.as_ref())
-            .map_err(|_| inference_client_pool_unavailable())
+            .map_err(|_| inference_client_pool_unavailable_for_cache_miss())?
+            .insert_if_absent(binding, client);
+        Ok((client, GrokInferenceClientCacheStatus::Miss))
     }
 }
 
@@ -342,47 +369,62 @@ impl GrokInferenceTransport for ReqwestGrokInferenceTransport {
                     UpstreamSendState::NotSent,
                 ));
             }
-            let client = self.client_for(request.binding())?;
+            let (client, client_cache_status) = self.client_for(request.binding())?;
             let mut builder = client
                 .post(request.endpoint().clone())
                 .body(request.body().to_vec());
             for header in request.headers() {
                 builder = builder.header(header.name(), header.value().expose());
             }
-            let response = builder
-                .send()
+            let dns_observer = Arc::new(RequestDnsObserver::default());
+            let headers_started_at = Instant::now();
+            let response = REQUEST_DNS_OBSERVER
+                .scope(Arc::clone(&dns_observer), builder.send())
                 .await
-                .map_err(classify_inference_reqwest_error)?;
+                .map_err(|error| {
+                    classify_inference_reqwest_error(error).with_transport_metrics(
+                        inference_transport_metrics(client_cache_status, None, &dns_observer),
+                    )
+                })?;
+            let transport_metrics = inference_transport_metrics(
+                client_cache_status,
+                Some(elapsed_millis(headers_started_at.elapsed())),
+                &dns_observer,
+            );
             if !response.status().is_success() {
-                return Err(classify_inference_status(response).await);
+                return Err(classify_inference_status(response)
+                    .await
+                    .with_transport_metrics(transport_metrics));
             }
             let http_version = upstream_http_version(response.version());
             let status_code = response.status().as_u16();
             let request_id = upstream_request_id(&response);
-            let body = response.bytes_stream().scan(0_usize, |observed, chunk| {
-                let item = match chunk {
-                    Ok(chunk)
-                        if observed
-                            .checked_add(chunk.len())
-                            .is_some_and(|total| total <= MAX_INFERENCE_BODY_BYTES) =>
-                    {
-                        *observed += chunk.len();
-                        Ok(chunk.to_vec())
-                    }
-                    Ok(_) => Err(GrokInferenceTransportError::new(
-                        GrokInferenceTransportErrorKind::Protocol,
-                        UpstreamSendState::Sent,
-                    )),
-                    Err(error) => Err(classify_inference_stream_error(&error)),
-                };
-                std::future::ready(Some(item))
-            });
-            Ok(GrokInferenceResponse::new(
-                Box::pin(body),
-                http_version,
-                status_code,
-                request_id,
-            ))
+            let body = response
+                .bytes_stream()
+                .scan(0_usize, move |observed, chunk| {
+                    let item = match chunk {
+                        Ok(chunk)
+                            if observed
+                                .checked_add(chunk.len())
+                                .is_some_and(|total| total <= MAX_INFERENCE_BODY_BYTES) =>
+                        {
+                            *observed += chunk.len();
+                            Ok(chunk.to_vec())
+                        }
+                        Ok(_) => Err(GrokInferenceTransportError::new(
+                            GrokInferenceTransportErrorKind::Protocol,
+                            UpstreamSendState::Sent,
+                        )
+                        .with_transport_metrics(transport_metrics)),
+                        Err(error) => Err(classify_inference_stream_error(&error)
+                            .with_transport_metrics(transport_metrics)),
+                    };
+                    std::future::ready(Some(item))
+                });
+            Ok(
+                GrokInferenceResponse::new(Box::pin(body), http_version, status_code, request_id)
+                    .with_transport_metrics(transport_metrics),
+            )
         })
     }
 }
@@ -406,22 +448,24 @@ impl BoundInferenceClients {
         }
     }
 
-    fn get_or_insert(
-        &mut self,
-        binding: &GrokSessionBinding,
-        endpoint_policy: &dyn GrokEndpointPolicy,
-    ) -> Result<Client, GrokReqwestTransportBuildError> {
+    fn get(&mut self, binding: &GrokSessionBinding) -> Option<Client> {
         if let Some(client) = self.by_binding.get(binding).cloned() {
             self.record_use(binding);
-            return Ok(client);
+            return Some(client);
         }
+        None
+    }
 
-        let client = match self.unbound_client.take() {
-            Some(client) => client,
-            None => endpoint_policy.build_inference_client(None)?,
-        };
+    fn take_unbound(&mut self) -> Option<Client> {
+        self.unbound_client.take()
+    }
+
+    fn insert_if_absent(&mut self, binding: &GrokSessionBinding, client: Client) -> Client {
+        if let Some(existing) = self.get(binding) {
+            return existing;
+        }
         self.insert(binding.clone(), client.clone());
-        Ok(client)
+        client
     }
 
     fn insert(&mut self, binding: GrokSessionBinding, client: Client) {
@@ -448,6 +492,29 @@ fn inference_client_pool_unavailable() -> GrokInferenceTransportError {
     )
 }
 
+fn inference_client_pool_unavailable_for_cache_miss() -> GrokInferenceTransportError {
+    inference_client_pool_unavailable().with_transport_metrics(
+        GrokInferenceTransportMetrics::default()
+            .with_client_cache_status(GrokInferenceClientCacheStatus::Miss),
+    )
+}
+
+fn inference_transport_metrics(
+    client_cache_status: GrokInferenceClientCacheStatus,
+    headers_ms: Option<u64>,
+    dns_observer: &RequestDnsObserver,
+) -> GrokInferenceTransportMetrics {
+    let mut metrics =
+        GrokInferenceTransportMetrics::default().with_client_cache_status(client_cache_status);
+    if let Some(headers_ms) = headers_ms {
+        metrics = metrics.with_headers_ms(headers_ms);
+    }
+    if let Some(dns) = dns_observer.observation() {
+        metrics = metrics.with_dns(dns);
+    }
+    metrics
+}
+
 /// 官方 Grok CLI proxy 模型目录 GET transport。
 pub struct ReqwestGrokModelCatalogTransport {
     client: Client,
@@ -581,8 +648,11 @@ fn build_official_client(
         .no_proxy()
         .connect_timeout(CONNECT_TIMEOUT)
         .pool_idle_timeout(POOL_IDLE_TIMEOUT)
-        .pool_max_idle_per_host(128)
+        .pool_max_idle_per_host(POOL_MAX_IDLE_PER_HOST)
         .http2_adaptive_window(true)
+        .http2_keep_alive_interval(HTTP2_KEEP_ALIVE_INTERVAL)
+        .http2_keep_alive_timeout(HTTP2_KEEP_ALIVE_TIMEOUT)
+        .http2_keep_alive_while_idle(true)
         .tcp_nodelay(true)
         .https_only(true)
         .dns_resolver(Arc::new(StrictDnsResolver::new(dns_policy)?));
@@ -626,6 +696,24 @@ struct StrictDnsResolver {
     trusted_doh: TrustedDohResolver,
 }
 
+#[derive(Debug, Default)]
+struct RequestDnsObserver {
+    observation: OnceLock<GrokInferenceDnsObservation>,
+}
+
+impl RequestDnsObserver {
+    fn record(&self, source: GrokInferenceDnsSource, duration: Duration) {
+        let _ = self.observation.set(GrokInferenceDnsObservation::new(
+            source,
+            elapsed_millis(duration),
+        ));
+    }
+
+    fn observation(&self) -> Option<GrokInferenceDnsObservation> {
+        self.observation.get().copied()
+    }
+}
+
 impl StrictDnsResolver {
     fn new(policy: GrokDnsResolutionPolicy) -> Result<Self, GrokReqwestTransportBuildError> {
         Ok(Self {
@@ -647,7 +735,9 @@ impl Resolve for StrictDnsResolver {
         }
         let policy = self.policy;
         let trusted_doh = self.trusted_doh.clone();
+        let observer = REQUEST_DNS_OBSERVER.try_with(Arc::clone).ok();
         Box::pin(async move {
+            let started_at = Instant::now();
             let system_addresses = match tokio::net::lookup_host((requested_host.as_str(), 0)).await
             {
                 Ok(addresses) => addresses.collect::<Vec<_>>(),
@@ -657,29 +747,43 @@ impl Resolve for StrictDnsResolver {
                 .iter()
                 .map(SocketAddr::ip)
                 .collect::<Vec<_>>();
-            match policy
+            let (source, result) = match policy
                 .plan_system_resolution(&requested_host, &system_ips)
                 .map_err(|_| safe_dns_error("DNS resolution rejected"))?
             {
-                GrokDnsResolutionPlan::System => {
-                    Ok(Box::new(system_addresses.into_iter()) as Addrs)
-                }
+                GrokDnsResolutionPlan::System => (
+                    GrokInferenceDnsSource::System,
+                    Ok(Box::new(system_addresses.into_iter()) as Addrs),
+                ),
                 GrokDnsResolutionPlan::TrustedDoh => {
-                    let addresses = trusted_doh.resolve(&requested_host).await?;
-                    policy
-                        .validate_trusted_doh_resolution(&requested_host, &addresses)
-                        .map_err(|_| safe_dns_error("trusted DNS result rejected"))?;
-                    Ok(Box::new(
-                        addresses
-                            .into_iter()
-                            .map(|address| SocketAddr::new(address, 0)),
-                    ) as Addrs)
+                    let result = match trusted_doh.resolve(&requested_host).await {
+                        Ok(addresses) => policy
+                            .validate_trusted_doh_resolution(&requested_host, &addresses)
+                            .map_err(|_| safe_dns_error("trusted DNS result rejected"))
+                            .map(|()| {
+                                Box::new(
+                                    addresses
+                                        .into_iter()
+                                        .map(|address| SocketAddr::new(address, 0)),
+                                ) as Addrs
+                            }),
+                        Err(error) => Err(error),
+                    };
+                    (GrokInferenceDnsSource::TrustedDoh, result)
                 }
+            };
+            if let Some(observer) = observer {
+                observer.record(source, started_at.elapsed());
             }
+            result
         })
     }
 }
 
+fn elapsed_millis(duration: Duration) -> u64 {
+    u64::try_from(duration.as_millis()).unwrap_or(u64::MAX)
+}
+
 #[derive(Clone)]
 struct TrustedDohResolver {
     client: Client,

backend/crates/providers/xai/src/transport/profile.rs

@@ -145,18 +145,82 @@ impl GrokCliReleaseTransport for OfficialGrokCliReleaseTransport {
 pub struct GrokCliReleaseService {
     profile: XaiWireProfileState,
     transport: Arc<dyn GrokCliReleaseTransport>,
+    status: GrokCliReleaseStatus,
 }
 
 impl GrokCliReleaseService {
     #[must_use]
     pub fn new(profile: XaiWireProfileState, transport: Arc<dyn GrokCliReleaseTransport>) -> Self {
-        Self { profile, transport }
+        Self {
+            profile,
+            transport,
+            status: GrokCliReleaseStatus::default(),
+        }
+    }
+
+    #[must_use]
+    pub(crate) fn status(&self) -> GrokCliReleaseStatus {
+        self.status.clone()
     }
 
     pub async fn refresh(&self) -> Result<String, GrokCliReleaseError> {
-        let version = self.transport.fetch().await?;
-        self.profile.update_client_version(&version);
-        Ok(version)
+        let checked_at = Utc::now();
+        let result = self.transport.fetch().await;
+        match result {
+            Ok(version) => {
+                self.profile.update_client_version(&version);
+                self.status.record_success(checked_at, version.clone());
+                Ok(version)
+            }
+            Err(error) => {
+                self.status.record_failure(checked_at, &error);
+                Err(error)
+            }
+        }
+    }
+}
+
+/// 最近一次官方 Grok CLI 发布检查结果。
+#[derive(Debug, Clone, Default, PartialEq, Eq)]
+pub(crate) struct GrokCliReleaseSnapshot {
+    pub(crate) checked_at: Option<DateTime<Utc>>,
+    pub(crate) latest_version: Option<String>,
+    pub(crate) last_error: Option<String>,
+}
+
+/// Provider 内共享的 Grok CLI 发布检查观察状态。
+#[derive(Debug, Clone, Default)]
+pub(crate) struct GrokCliReleaseStatus {
+    snapshot: Arc<RwLock<GrokCliReleaseSnapshot>>,
+}
+
+impl GrokCliReleaseStatus {
+    #[must_use]
+    pub(crate) fn snapshot(&self) -> GrokCliReleaseSnapshot {
+        self.snapshot
+            .read()
+            .unwrap_or_else(std::sync::PoisonError::into_inner)
+            .clone()
+    }
+
+    fn record_success(&self, checked_at: DateTime<Utc>, latest_version: String) {
+        *self
+            .snapshot
+            .write()
+            .unwrap_or_else(std::sync::PoisonError::into_inner) = GrokCliReleaseSnapshot {
+            checked_at: Some(checked_at),
+            latest_version: Some(latest_version),
+            last_error: None,
+        };
+    }
+
+    fn record_failure(&self, checked_at: DateTime<Utc>, error: &GrokCliReleaseError) {
+        let mut snapshot = self
+            .snapshot
+            .write()
+            .unwrap_or_else(std::sync::PoisonError::into_inner);
+        snapshot.checked_at = Some(checked_at);
+        snapshot.last_error = Some(error.to_string());
     }
 }
 
@@ -191,3 +255,91 @@ pub enum GrokCliReleaseError {
     #[error("Grok CLI release version is invalid")]
     InvalidVersion,
 }
+
+#[cfg(test)]
+mod tests {
+    use std::collections::VecDeque;
+    use std::sync::Mutex;
+
+    use super::*;
+
+    struct ReleaseTransport {
+        outcomes: Mutex<VecDeque<Result<String, GrokCliReleaseError>>>,
+    }
+
+    impl ReleaseTransport {
+        fn new(outcomes: impl IntoIterator<Item = Result<String, GrokCliReleaseError>>) -> Self {
+            Self {
+                outcomes: Mutex::new(outcomes.into_iter().collect()),
+            }
+        }
+    }
+
+    impl GrokCliReleaseTransport for ReleaseTransport {
+        fn fetch(&self) -> BoxFuture<'_, Result<String, GrokCliReleaseError>> {
+            let outcome = self
+                .outcomes
+                .lock()
+                .expect("release outcomes lock")
+                .pop_front()
+                .expect("release outcome");
+            Box::pin(async move { outcome })
+        }
+    }
+
+    #[tokio::test]
+    async fn release_refresh_should_update_profile_and_observation() {
+        let profile = wire_profile();
+        let service = GrokCliReleaseService::new(
+            profile.clone(),
+            Arc::new(ReleaseTransport::new([Ok("0.2.112".to_owned())])),
+        );
+        let status = service.status();
+
+        assert_eq!(service.refresh().await.expect("release"), "0.2.112");
+        assert_eq!(profile.client_version(), "0.2.112");
+        let snapshot = status.snapshot();
+        assert!(snapshot.checked_at.is_some());
+        assert_eq!(snapshot.latest_version.as_deref(), Some("0.2.112"));
+        assert!(snapshot.last_error.is_none());
+    }
+
+    #[tokio::test]
+    async fn failed_release_refresh_should_keep_last_successful_version() {
+        let profile = wire_profile();
+        let service = GrokCliReleaseService::new(
+            profile.clone(),
+            Arc::new(ReleaseTransport::new([
+                Ok("0.2.112".to_owned()),
+                Err(GrokCliReleaseError::InvalidDocument),
+            ])),
+        );
+        let status = service.status();
+
+        service.refresh().await.expect("first release");
+        assert!(matches!(
+            service.refresh().await,
+            Err(GrokCliReleaseError::InvalidDocument)
+        ));
+
+        assert_eq!(profile.client_version(), "0.2.112");
+        let snapshot = status.snapshot();
+        assert!(snapshot.checked_at.is_some());
+        assert_eq!(snapshot.latest_version.as_deref(), Some("0.2.112"));
+        assert_eq!(
+            snapshot.last_error.as_deref(),
+            Some("Grok CLI release document is invalid")
+        );
+    }
+
+    fn wire_profile() -> XaiWireProfileState {
+        XaiWireProfileState::new(XaiWireProfileConfig {
+            client_identifier: "grok-shell".to_owned(),
+            client_version: "0.2.106".to_owned(),
+            client_mode: "headless".to_owned(),
+            target_os: "linux".to_owned(),
+            target_arch: "x86_64".to_owned(),
+            verified_at: Utc::now(),
+        })
+    }
+}

backend/crates/providers/xai/src/transport/transport.rs

@@ -79,6 +79,117 @@ impl fmt::Debug for GrokInferenceRequest {
 pub type GrokInferenceChunkStream =
     Pin<Box<dyn Stream<Item = Result<Vec<u8>, GrokInferenceTransportError>> + Send + 'static>>;
 
+/// Whether the account-isolated inference client was already cached.
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum GrokInferenceClientCacheStatus {
+    /// The binding reused its existing account-isolated client.
+    Hit,
+    /// The binding was absent when the request first checked the cache.
+    Miss,
+}
+
+impl GrokInferenceClientCacheStatus {
+    #[must_use]
+    pub const fn as_str(self) -> &'static str {
+        match self {
+            Self::Hit => "hit",
+            Self::Miss => "miss",
+        }
+    }
+}
+
+/// Resolver that supplied the addresses used by the request.
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum GrokInferenceDnsSource {
+    /// The system resolver returned an entirely public address set.
+    System,
+    /// The system result was unusable and the trusted DoH fallback supplied addresses.
+    TrustedDoh,
+}
+
+impl GrokInferenceDnsSource {
+    #[must_use]
+    pub const fn as_str(self) -> &'static str {
+        match self {
+            Self::System => "system",
+            Self::TrustedDoh => "trusted_doh",
+        }
+    }
+}
+
+/// DNS work observed while opening an upstream connection.
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub struct GrokInferenceDnsObservation {
+    source: GrokInferenceDnsSource,
+    duration_ms: u64,
+}
+
+impl GrokInferenceDnsObservation {
+    #[must_use]
+    pub const fn new(source: GrokInferenceDnsSource, duration_ms: u64) -> Self {
+        Self {
+            source,
+            duration_ms,
+        }
+    }
+
+    #[must_use]
+    pub const fn source(self) -> GrokInferenceDnsSource {
+        self.source
+    }
+
+    #[must_use]
+    pub const fn duration_ms(self) -> u64 {
+        self.duration_ms
+    }
+}
+
+/// Low-cardinality transport timings and pool facts for one inference request.
+#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
+pub struct GrokInferenceTransportMetrics {
+    headers_ms: Option<u64>,
+    client_cache_status: Option<GrokInferenceClientCacheStatus>,
+    dns: Option<GrokInferenceDnsObservation>,
+}
+
+impl GrokInferenceTransportMetrics {
+    #[must_use]
+    pub const fn with_headers_ms(mut self, headers_ms: u64) -> Self {
+        self.headers_ms = Some(headers_ms);
+        self
+    }
+
+    #[must_use]
+    pub const fn with_client_cache_status(
+        mut self,
+        status: GrokInferenceClientCacheStatus,
+    ) -> Self {
+        self.client_cache_status = Some(status);
+        self
+    }
+
+    #[must_use]
+    pub const fn with_dns(mut self, dns: GrokInferenceDnsObservation) -> Self {
+        self.dns = Some(dns);
+        self
+    }
+
+    #[must_use]
+    pub const fn headers_ms(self) -> Option<u64> {
+        self.headers_ms
+    }
+
+    #[must_use]
+    pub const fn client_cache_status(self) -> Option<GrokInferenceClientCacheStatus> {
+        self.client_cache_status
+    }
+
+    #[must_use]
+    pub const fn dns(self) -> Option<GrokInferenceDnsObservation> {
+        self.dns
+    }
+}
+
 /// Accepted inference response. Non-success HTTP responses must be returned as
 /// [`GrokInferenceTransportError`] instead.
 pub struct GrokInferenceResponse {
@@ -86,6 +197,7 @@ pub struct GrokInferenceResponse {
     http_version: UpstreamHttpVersion,
     status_code: u16,
     request_id: Option<SafeUpstreamValue>,
+    transport_metrics: GrokInferenceTransportMetrics,
 }
 
 impl GrokInferenceResponse {
@@ -102,9 +214,19 @@ impl GrokInferenceResponse {
             http_version,
             status_code,
             request_id,
+            transport_metrics: GrokInferenceTransportMetrics::default(),
         }
     }
 
+    #[must_use]
+    pub const fn with_transport_metrics(
+        mut self,
+        transport_metrics: GrokInferenceTransportMetrics,
+    ) -> Self {
+        self.transport_metrics = transport_metrics;
+        self
+    }
+
     #[must_use]
     pub const fn http_version(&self) -> UpstreamHttpVersion {
         self.http_version
@@ -120,6 +242,11 @@ impl GrokInferenceResponse {
         self.request_id.as_ref()
     }
 
+    #[must_use]
+    pub const fn transport_metrics(&self) -> GrokInferenceTransportMetrics {
+        self.transport_metrics
+    }
+
     pub fn into_body(self) -> GrokInferenceChunkStream {
         self.body
     }
@@ -132,6 +259,7 @@ impl fmt::Debug for GrokInferenceResponse {
             .field("http_version", &self.http_version)
             .field("status_code", &self.status_code)
             .field("request_id", &self.request_id)
+            .field("transport_metrics", &self.transport_metrics)
             .field("body", &"[SSE STREAM]")
             .finish()
     }
@@ -174,6 +302,7 @@ pub struct GrokInferenceTransportError {
     http_version: Option<UpstreamHttpVersion>,
     request_id: Option<SafeUpstreamValue>,
     upstream_code: Option<SafeUpstreamValue>,
+    transport_metrics: GrokInferenceTransportMetrics,
     credential_recovery_required: bool,
     sensitive_context_redacted: bool,
 }
@@ -190,6 +319,11 @@ impl GrokInferenceTransportError {
             http_version: None,
             request_id: None,
             upstream_code: None,
+            transport_metrics: GrokInferenceTransportMetrics {
+                headers_ms: None,
+                client_cache_status: None,
+                dns: None,
+            },
             credential_recovery_required: false,
             sensitive_context_redacted: false,
         }
@@ -229,6 +363,15 @@ impl GrokInferenceTransportError {
         self
     }
 
+    #[must_use]
+    pub const fn with_transport_metrics(
+        mut self,
+        transport_metrics: GrokInferenceTransportMetrics,
+    ) -> Self {
+        self.transport_metrics = transport_metrics;
+        self
+    }
+
     #[must_use]
     pub const fn with_credential_recovery(mut self) -> Self {
         self.credential_recovery_required = true;
@@ -281,6 +424,11 @@ impl GrokInferenceTransportError {
         self.upstream_code.as_ref()
     }
 
+    #[must_use]
+    pub const fn transport_metrics(&self) -> GrokInferenceTransportMetrics {
+        self.transport_metrics
+    }
+
     #[must_use]
     pub const fn requires_credential_recovery(&self) -> bool {
         self.credential_recovery_required
@@ -304,6 +452,7 @@ impl fmt::Debug for GrokInferenceTransportError {
             .field("http_version", &self.http_version)
             .field("request_id", &self.request_id)
             .field("upstream_code", &self.upstream_code)
+            .field("transport_metrics", &self.transport_metrics)
             .field(
                 "credential_recovery_required",
                 &self.credential_recovery_required,

backend/crates/providers/xai/tests/admin.rs

@@ -9,7 +9,9 @@ use futures::{StreamExt as _, future::BoxFuture};
 use gateway_admin::model::accounts::{
     AccountAvailability as AdminAccountAvailability, AccountRecord,
 };
-use gateway_admin::model::observability::{CurrencyCost, ProviderBillingInput};
+use gateway_admin::model::observability::{
+    CurrencyCost, DesktopReleaseStatus, ProviderBillingInput,
+};
 use gateway_admin::model::provider_credentials::{
     CompleteAuthorization, PrepareCredentialImport, PrepareCredentialRefresh,
     PrepareCredentialRotation, ProviderDocument, ProviderExportCredentialInput,
@@ -281,7 +283,9 @@ async fn xai_admin_provider_validates_known_billing_breakdown() {
     assert_eq!(profile.product, "Grok Build");
     assert_eq!(profile.version, "0.2.106");
     assert_eq!(profile.user_agent, "grok-shell/0.2.106 (linux; x86_64)");
-    assert!(profile.release.is_none());
+    let release = profile.release.expect("release status");
+    assert_eq!(release.status, DesktopReleaseStatus::Unchecked);
+    assert!(release.checked_at.is_none());
 
     let billing = admin
         .calculated_billing(&ProviderBillingInput {

backend/crates/providers/xai/tests/provider/contract.rs

@@ -31,13 +31,14 @@ use gateway_core::routing::{
 use provider_xai::{
     GrokBuildProvider, GrokCredentialCatalogCache, GrokCredentialFailure,
     GrokCredentialFeedbackFuture, GrokCredentialRecovery, GrokCredentialRecoveryOutcome,
-    GrokCredentialRepository, GrokInferenceRequest, GrokInferenceResponse, GrokInferenceTransport,
+    GrokCredentialRepository, GrokInferenceClientCacheStatus, GrokInferenceDnsObservation,
+    GrokInferenceDnsSource, GrokInferenceRequest, GrokInferenceResponse, GrokInferenceTransport,
     GrokInferenceTransportError, GrokInferenceTransportErrorKind, GrokInferenceTransportFuture,
-    GrokModelCatalogRequest, GrokModelCatalogTransport, GrokModelCatalogTransportError,
-    GrokModelCatalogTransportErrorKind, GrokModelCatalogTransportFuture,
-    GrokModelCatalogTransportResponse, GrokSessionBinding, GrokSessionSelection,
-    GrokSessionSelector, GrokSessionSelectorError, GrokSessionSelectorFuture, SecretValue,
-    SelectedGrokSession,
+    GrokInferenceTransportMetrics, GrokModelCatalogRequest, GrokModelCatalogTransport,
+    GrokModelCatalogTransportError, GrokModelCatalogTransportErrorKind,
+    GrokModelCatalogTransportFuture, GrokModelCatalogTransportResponse, GrokSessionBinding,
+    GrokSessionSelection, GrokSessionSelector, GrokSessionSelectorError, GrokSessionSelectorFuture,
+    SecretValue, SelectedGrokSession,
 };
 use serde_json::{Map, json};
 
@@ -48,6 +49,17 @@ use crate::support::{
 const MODEL: &str = "grok-4.5";
 const CATALOG_FIXTURE: &[u8] =
     include_bytes!("../transport/catalog/fixtures/official_grok_models_snapshot.json");
+
+fn observed_transport_metrics() -> GrokInferenceTransportMetrics {
+    GrokInferenceTransportMetrics::default()
+        .with_headers_ms(42)
+        .with_client_cache_status(GrokInferenceClientCacheStatus::Miss)
+        .with_dns(GrokInferenceDnsObservation::new(
+            GrokInferenceDnsSource::System,
+            7,
+        ))
+}
+
 const CATALOG_WITHOUT_TOOL_METADATA: &[u8] = br#"{
   "object": "list",
   "data": [{
@@ -246,6 +258,7 @@ impl GrokSessionSelector for StubSelector {
 
 enum InferenceMode {
     Success,
+    SuccessWithMetrics(GrokInferenceTransportMetrics),
     SuccessBody(Vec<u8>),
     Error(GrokInferenceTransportError),
     StreamError(GrokInferenceTransportError),
@@ -266,6 +279,14 @@ impl StubInferenceTransport {
         })
     }
 
+    fn success_with_metrics(metrics: GrokInferenceTransportMetrics) -> Arc<Self> {
+        Arc::new(Self {
+            calls: AtomicUsize::new(0),
+            requests: Mutex::new(Vec::new()),
+            modes: Mutex::new(VecDeque::from([InferenceMode::SuccessWithMetrics(metrics)])),
+        })
+    }
+
     fn error(error: GrokInferenceTransportError) -> Arc<Self> {
         Arc::new(Self {
             calls: AtomicUsize::new(0),
@@ -309,6 +330,13 @@ impl GrokInferenceTransport for StubInferenceTransport {
                     200,
                     None,
                 )),
+                InferenceMode::SuccessWithMetrics(metrics) => Ok(GrokInferenceResponse::new(
+                    Box::pin(stream::iter([Ok(SUCCESS_SSE.to_vec())])),
+                    UpstreamHttpVersion::Http2,
+                    200,
+                    None,
+                )
+                .with_transport_metrics(metrics)),
                 InferenceMode::SuccessBody(body) => Ok(GrokInferenceResponse::new(
                     Box::pin(stream::iter([Ok(body)])),
                     UpstreamHttpVersion::Http2,
@@ -719,7 +747,7 @@ async fn execute_forwards_required_account_to_selector() {
 #[tokio::test]
 async fn execute_returns_cold_stream_and_records_selected_account() {
     let selector = StubSelector::success();
-    let transport = StubInferenceTransport::success();
+    let transport = StubInferenceTransport::success_with_metrics(observed_transport_metrics());
     let provider = provider(selector, transport.clone()).await;
     let mut stream = provider
         .execute(
@@ -744,6 +772,23 @@ async fn execute_returns_cold_stream_and_records_selected_account() {
     assert_eq!(observation.transport().as_str(), "http_sse");
     assert_eq!(observation.http_version(), Some(UpstreamHttpVersion::Http2));
     assert_eq!(observation.status_code(), Some(200));
+    assert_eq!(observation.timings().headers_ms, Some(42));
+    let metadata: serde_json::Value = serde_json::from_str(
+        observation
+            .provider_metadata()
+            .expect("xAI transport metadata")
+            .as_json(),
+    )
+    .expect("valid metadata JSON");
+    assert_eq!(
+        metadata,
+        json!({
+            "clientCache": "miss",
+            "dnsSource": "system",
+            "dnsMs": 7,
+            "upstreamHeadersMs": 42
+        })
+    );
     assert!(
         events
             .iter()
@@ -753,6 +798,48 @@ async fn execute_returns_cold_stream_and_records_selected_account() {
     );
 }
 
+#[tokio::test]
+async fn transport_error_observation_should_retain_available_metrics() {
+    let transport = StubInferenceTransport::error(
+        GrokInferenceTransportError::new(
+            GrokInferenceTransportErrorKind::Unavailable,
+            UpstreamSendState::Sent,
+        )
+        .with_status(503)
+        .with_transport_metrics(observed_transport_metrics()),
+    );
+    let provider = provider(StubSelector::success(), transport).await;
+    let mut stream = provider
+        .execute(
+            provider_request("xai"),
+            context(CancellationToken::new(), None),
+        )
+        .await
+        .expect("provider stream");
+
+    let event = stream
+        .next()
+        .await
+        .expect("observation event")
+        .expect("observation must succeed");
+    let observation = event.response_observation().expect("transport observation");
+    assert_eq!(observation.status_code(), Some(503));
+    assert_eq!(observation.timings().headers_ms, Some(42));
+    let metadata: serde_json::Value = serde_json::from_str(
+        observation
+            .provider_metadata()
+            .expect("xAI transport metadata")
+            .as_json(),
+    )
+    .expect("valid metadata JSON");
+    assert_eq!(metadata["clientCache"], "miss");
+    assert_eq!(metadata["dnsSource"], "system");
+    assert_eq!(metadata["dnsMs"], 7);
+
+    let error = next_provider_error(&mut stream).await;
+    assert_eq!(error.kind(), ProviderErrorKind::Unavailable);
+}
+
 #[tokio::test]
 async fn compaction_stream_should_emit_openai_wire_and_keep_only_accounting_canonical() {
     let summary = valid_compaction_summary("validated summary");
@@ -1740,7 +1827,7 @@ async fn provider_compiles_realtime_catalog_capabilities() {
     assert_eq!(presentation.display_name(), Some("Grok 4.5"));
     assert_eq!(
         presentation.supported_reasoning_efforts(),
-        ["low", "medium", "high"]
+        ["low", "medium", "high", "xhigh"]
     );
     assert_eq!(presentation.context_window_tokens(), Some(1_000_000));
     assert!(presentation.agent_tools());

backend/crates/providers/xai/tests/transport/catalog.rs

@@ -261,6 +261,16 @@ fn official_fixture_should_use_actual_model_and_whitelisted_metadata() {
             (
                 model.capabilities().responses_api(),
                 model.capabilities().reasoning_effort(),
+                model
+                    .capabilities()
+                    .reasoning_efforts()
+                    .iter()
+                    .map(|effort| effort.as_str())
+                    .collect::<Vec<_>>(),
+                model
+                    .capabilities()
+                    .default_reasoning_effort()
+                    .map(|effort| effort.as_str()),
                 model.capabilities().backend_search(),
                 model.capabilities().streaming_tool_calls(),
             ),
@@ -278,6 +288,8 @@ fn official_fixture_should_use_actual_model_and_whitelisted_metadata() {
             (
                 GrokCatalogCapabilityEvidence::DeclaredNative,
                 GrokCatalogCapabilityEvidence::DeclaredNative,
+                vec!["low", "medium", "high", "xhigh"],
+                Some("medium"),
                 GrokCatalogCapabilityEvidence::DeclaredNative,
                 GrokCatalogCapabilityEvidence::DeclaredNative,
             ),
@@ -335,6 +347,35 @@ fn missing_capability_fields_should_remain_unknown() {
     );
 }
 
+#[test]
+fn reasoning_effort_menu_should_be_capability_evidence_without_legacy_flag() {
+    let snapshot = parse_grok_model_catalog(
+        br#"{"object":"list","data":[{"id":"grok-reasoning","reasoningEfforts":[{"value":"xhigh","default":true},"low"]}]}"#,
+        None,
+    )
+    .expect("reasoning effort menu");
+    let capabilities = snapshot.models()[0].capabilities();
+
+    assert_eq!(
+        (
+            capabilities.reasoning_effort(),
+            capabilities
+                .reasoning_efforts()
+                .iter()
+                .map(|effort| effort.as_str())
+                .collect::<Vec<_>>(),
+            capabilities
+                .default_reasoning_effort()
+                .map(|effort| effort.as_str()),
+        ),
+        (
+            GrokCatalogCapabilityEvidence::DeclaredNative,
+            vec!["xhigh", "low"],
+            Some("xhigh"),
+        )
+    );
+}
+
 #[test]
 fn model_id_should_take_priority_over_catalog_id() {
     let snapshot = parse_grok_model_catalog(

backend/crates/providers/xai/tests/transport/catalog/fixtures/official_grok_models_snapshot.json

@@ -12,6 +12,13 @@
       "apiBackend": "responses",
       "supportedInApi": true,
       "supportsReasoningEffort": true,
+      "reasoningEffort": "medium",
+      "reasoningEfforts": [
+        "low",
+        { "value": "medium", "label": "Balanced", "default": true },
+        "high",
+        { "id": "extended", "value": "xhigh", "label": "Extended" }
+      ],
       "supportsBackendSearch": true,
       "streamToolCalls": true,
       "hidden": false,

backend/crates/providers/xai/tests/transport/network.rs

@@ -16,11 +16,12 @@ use wiremock::{Mock, MockServer, ResponseTemplate};
 
 use provider_xai::{
     FailClosedTokenVerifier, FormField, GrokBillingClient, GrokDnsResolutionPlan,
-    GrokDnsResolutionPolicy, GrokEndpointPolicy, GrokInferenceRequest, GrokInferenceTransport,
-    GrokInferenceTransportErrorKind, GrokModelCatalogSession, GrokOAuthClient, GrokOAuthConfig,
-    GrokReqwestTransportBuildError, GrokSessionBinding, HttpMethod, OAuthHttpRequest,
-    OAuthHttpTransport, OfficialGrokEndpointPolicy, ReqwestGrokInferenceTransport,
-    ReqwestGrokModelCatalogTransport, ReqwestOAuthTransport, SecretValue,
+    GrokDnsResolutionPolicy, GrokEndpointPolicy, GrokInferenceClientCacheStatus,
+    GrokInferenceRequest, GrokInferenceTransport, GrokInferenceTransportErrorKind,
+    GrokModelCatalogSession, GrokOAuthClient, GrokOAuthConfig, GrokReqwestTransportBuildError,
+    GrokSessionBinding, HttpMethod, OAuthHttpRequest, OAuthHttpTransport,
+    OfficialGrokEndpointPolicy, ReqwestGrokInferenceTransport, ReqwestGrokModelCatalogTransport,
+    ReqwestOAuthTransport, SecretValue,
 };
 
 use crate::support::loopback_endpoint_policy;
@@ -89,6 +90,43 @@ async fn inference_transport_should_stream_one_official_shape_response() {
     assert_eq!(chunks.len(), 1);
 }
 
+#[tokio::test]
+async fn inference_transport_should_report_account_client_cache_miss_then_hit() {
+    let server = MockServer::start().await;
+    Mock::given(method("POST"))
+        .and(path("/v1/responses"))
+        .respond_with(
+            ResponseTemplate::new(200).set_body_raw("data: [DONE]\n\n", "text/event-stream"),
+        )
+        .expect(2)
+        .mount(&server)
+        .await;
+    let origin = Url::parse(&server.uri()).expect("wiremock origin");
+    let transport = inference_transport(&origin);
+
+    let first = transport
+        .execute(inference_request(&origin))
+        .await
+        .expect("first response");
+    let first_metrics = first.transport_metrics();
+    assert_eq!(
+        first_metrics.client_cache_status(),
+        Some(GrokInferenceClientCacheStatus::Miss)
+    );
+    assert!(first_metrics.headers_ms().is_some());
+    first.into_body().collect::<Vec<_>>().await;
+
+    let second = transport
+        .execute(inference_request(&origin))
+        .await
+        .expect("second response");
+    assert_eq!(
+        second.transport_metrics().client_cache_status(),
+        Some(GrokInferenceClientCacheStatus::Hit)
+    );
+    second.into_body().collect::<Vec<_>>().await;
+}
+
 #[tokio::test]
 async fn inference_transport_should_reuse_one_client_only_within_the_same_binding() {
     let server = MockServer::start().await;
@@ -105,6 +143,7 @@ async fn inference_transport_should_reuse_one_client_only_within_the_same_bindin
     let endpoint_policy: Arc<dyn GrokEndpointPolicy> = Arc::new(CountingEndpointPolicy {
         inner: loopback_endpoint_policy(&origin),
         inference_client_builds: Arc::clone(&client_builds),
+        concurrency: None,
     });
     let transport = ReqwestGrokInferenceTransport::new(endpoint_policy).expect("transport");
 
@@ -132,6 +171,7 @@ async fn inference_transport_should_evict_the_least_recent_binding_at_the_fixed_
     let endpoint_policy: Arc<dyn GrokEndpointPolicy> = Arc::new(CountingEndpointPolicy {
         inner: loopback_endpoint_policy(&origin),
         inference_client_builds: Arc::clone(&client_builds),
+        concurrency: None,
     });
     let transport = ReqwestGrokInferenceTransport::new(endpoint_policy).expect("transport");
 
@@ -156,6 +196,62 @@ async fn inference_transport_should_evict_the_least_recent_binding_at_the_fixed_
     );
 }
 
+#[tokio::test]
+async fn inference_transport_should_build_distinct_cold_account_clients_concurrently() {
+    let server = MockServer::start().await;
+    Mock::given(method("POST"))
+        .and(path("/v1/responses"))
+        .respond_with(
+            ResponseTemplate::new(200).set_body_raw("data: [DONE]\n\n", "text/event-stream"),
+        )
+        .expect(3)
+        .mount(&server)
+        .await;
+    let origin = Url::parse(&server.uri()).expect("wiremock origin");
+    let concurrency = Arc::new(BuildConcurrency::new(Duration::from_millis(100)));
+    let endpoint_policy: Arc<dyn GrokEndpointPolicy> = Arc::new(CountingEndpointPolicy {
+        inner: loopback_endpoint_policy(&origin),
+        inference_client_builds: Arc::new(AtomicUsize::new(0)),
+        concurrency: Some(Arc::clone(&concurrency)),
+    });
+    let transport = Arc::new(
+        ReqwestGrokInferenceTransport::new(endpoint_policy).expect("concurrent transport"),
+    );
+    execute_inference(&transport, &origin, "account-primer").await;
+
+    let start = Arc::new(std::sync::Barrier::new(2));
+    let first = {
+        let start = Arc::clone(&start);
+        let transport = Arc::clone(&transport);
+        let origin = origin.clone();
+        tokio::task::spawn_blocking(move || {
+            let runtime = tokio::runtime::Builder::new_current_thread()
+                .enable_all()
+                .build()
+                .expect("first request runtime");
+            start.wait();
+            runtime.block_on(execute_inference(&transport, &origin, "account-cold-a"));
+        })
+    };
+    let second = {
+        let start = Arc::clone(&start);
+        let transport = Arc::clone(&transport);
+        let origin = origin.clone();
+        tokio::task::spawn_blocking(move || {
+            let runtime = tokio::runtime::Builder::new_current_thread()
+                .enable_all()
+                .build()
+                .expect("second request runtime");
+            start.wait();
+            runtime.block_on(execute_inference(&transport, &origin, "account-cold-b"));
+        })
+    };
+    first.await.expect("first task");
+    second.await.expect("second task");
+
+    assert!(concurrency.max_active.load(Ordering::SeqCst) >= 2);
+}
+
 #[tokio::test]
 async fn inference_transport_should_classify_http_failures_without_retaining_bodies() {
     let cases = [
@@ -201,6 +297,11 @@ async fn inference_transport_should_classify_http_failures_without_retaining_bod
                 Some(gateway_core::event::UpstreamHttpVersion::Http11),
             )
         );
+        assert_eq!(
+            error.transport_metrics().client_cache_status(),
+            Some(GrokInferenceClientCacheStatus::Miss)
+        );
+        assert!(error.transport_metrics().headers_ms().is_some());
         assert!(!rendered.contains(&secret));
     }
 }
@@ -535,6 +636,24 @@ async fn execute_inference(transport: &ReqwestGrokInferenceTransport, origin: &U
 struct CountingEndpointPolicy {
     inner: Arc<dyn GrokEndpointPolicy>,
     inference_client_builds: Arc<AtomicUsize>,
+    concurrency: Option<Arc<BuildConcurrency>>,
+}
+
+#[derive(Debug)]
+struct BuildConcurrency {
+    delay: Duration,
+    active: AtomicUsize,
+    max_active: AtomicUsize,
+}
+
+impl BuildConcurrency {
+    fn new(delay: Duration) -> Self {
+        Self {
+            delay,
+            active: AtomicUsize::new(0),
+            max_active: AtomicUsize::new(0),
+        }
+    }
 }
 
 impl GrokEndpointPolicy for CountingEndpointPolicy {
@@ -550,7 +669,15 @@ impl GrokEndpointPolicy for CountingEndpointPolicy {
         timeout: Option<Duration>,
     ) -> Result<Client, GrokReqwestTransportBuildError> {
         self.inference_client_builds.fetch_add(1, Ordering::SeqCst);
-        self.inner.build_inference_client(timeout)
+        let Some(concurrency) = &self.concurrency else {
+            return self.inner.build_inference_client(timeout);
+        };
+        let active = concurrency.active.fetch_add(1, Ordering::SeqCst) + 1;
+        concurrency.max_active.fetch_max(active, Ordering::SeqCst);
+        std::thread::sleep(concurrency.delay);
+        let result = self.inner.build_inference_client(timeout);
+        concurrency.active.fetch_sub(1, Ordering::SeqCst);
+        result
     }
 
     fn validate_oauth(&self, url: &Url) -> bool {

frontend/index.html

@@ -6,7 +6,7 @@
       name="viewport"
       content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no, viewport-fit=cover"
     />
-    <link rel="icon" type="image/svg+xml" href="/favicon.svg" />
+    <link rel="icon" type="image/svg+xml" href="/favicon.svg?v=20260726" />
     <title>Codex Proxy RS</title>
   </head>
   <body>

frontend/public/favicon.svg

@@ -1,9 +1,9 @@
-<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 64 64">
-  <rect width="64" height="64" rx="16" fill="#111827"/>
-  <g transform="translate(10 8) scale(1.85)" fill="none" stroke="#fff" stroke-width="2.2" stroke-linecap="round" stroke-linejoin="round">
-    <path d="M12 5c.67 0 1.35.09 2 .26 1.78-2 5.03-2.84 6.42-2.26 1.4.58-.42 7-.42 7 .57 1.07 1 2.24 1 3.44C21 17.9 16.97 21 12 21s-9-3.1-9-7.56c0-1.25.5-2.4 1-3.44 0 0-1.89-6.42-.5-7S8.22 3.26 10 5.26A8.3 8.3 0 0 1 12 5Z"/>
-    <path d="M8 14v.5"/>
-    <path d="M16 14v.5"/>
-    <path d="M11.25 16.25h1.5L12 17l-.75-.75Z"/>
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="48 48 416 416" role="img" aria-labelledby="title">
+  <title id="title">Codex Proxy</title>
+  <rect x="48" y="48" width="416" height="416" rx="88" fill="#1c2a3d" />
+  <g fill="none" stroke="#fff" stroke-linecap="round" stroke-width="36">
+    <path d="M156 307A112 112 0 0 1 307 156" />
+    <path d="M356 205A112 112 0 0 1 205 356" />
   </g>
+  <path d="m407 105-119 153-183 149 124-157Z" fill="#fff" />
 </svg>

frontend/src/components/base/BaseButton.vue

@@ -108,7 +108,11 @@ const labelClasses = computed(() => [
     :title="title || (iconOnly ? label : undefined)"
     :aria-busy="loading"
   >
-    <LoaderCircle v-if="loading" class="animate-spin" :size="loadingIconSize[size]" />
+    <LoaderCircle
+      v-if="loading"
+      class="shrink-0 animate-spin origin-center transform-view will-change-transform"
+      :size="loadingIconSize[size]"
+    />
     <span v-if="$slots.icon && !loading" class="inline-flex shrink-0">
       <slot name="icon" />
     </span>

frontend/src/components/base/BaseInput.vue

@@ -24,6 +24,11 @@ const props = withDefaults(
 
 const model = defineModel<string>({ default: '' })
 
+// number 输入也保持字符串契约，避免原生 v-model 隐式转换为 number。
+function updateModel(event: Event) {
+  model.value = (event.target as HTMLInputElement).value
+}
+
 const containerClasses = computed(() => [
   'relative inline-flex h-(--cp-input-height-default) w-full min-w-0 items-center gap-2.5 overflow-visible rounded-(--cp-input-radius-base) border-0 px-3.5 text-[13px] text-(--cp-text-primary) shadow-(--cp-shadow-input) transition-[background-color,box-shadow,color] duration-[160ms]',
   props.disabled
@@ -64,7 +69,7 @@ const inputClasses = computed(() => [
         <slot name="prefix" />
       </span>
       <input
-        v-model="model"
+        :value="model"
         class="base-input__field"
         :class="inputClasses"
         :name="name"
@@ -74,6 +79,7 @@ const inputClasses = computed(() => [
         :autocomplete="autocomplete"
         :aria-label="ariaLabel"
         :aria-invalid="error ? 'true' : undefined"
+        @input="updateModel"
       >
       <span v-if="$slots.suffix" :class="iconClasses">
         <slot name="suffix" />

frontend/src/components/base/BaseScrollbar.vue

@@ -1,7 +1,7 @@
 <script setup lang="ts">
-import { useEventListener, useResizeObserver, useScroll, useTimeoutFn } from '@vueuse/core'
+import { useEventListener, useResizeObserver, useTimeoutFn } from '@vueuse/core'
 import { clamp } from 'es-toolkit'
-import { computed, nextTick, onMounted, shallowRef, useTemplateRef } from 'vue'
+import { computed, nextTick, onBeforeUnmount, onMounted, shallowRef, useTemplateRef } from 'vue'
 
 const props = withDefaults(
   defineProps<{
@@ -42,11 +42,26 @@ const verticalTrackHovering = shallowRef(false)
 const horizontalTrackHovering = shallowRef(false)
 const dragging = shallowRef(false)
 const horizontalDragging = shallowRef(false)
+const dragDocument = computed(() =>
+  dragging.value || horizontalDragging.value ? document : null,
+)
+
+interface AxisMetrics {
+  scrollRange: number
+  thumbRange: number
+}
+
+const verticalMetrics: AxisMetrics = { scrollRange: 0, thumbRange: 0 }
+const horizontalMetrics: AxisMetrics = { scrollRange: 0, thumbRange: 0 }
 
 let dragStartY = 0
 let dragStartScrollTop = 0
 let horizontalDragStartX = 0
 let horizontalDragStartScrollLeft = 0
+let scrollTopPosition = 0
+let scrollLeftPosition = 0
+let scrollFrameId: number | undefined
+let rootHovering = false
 const { start: startHideTimer, stop: stopHideTimer } = useTimeoutFn(hideScrollbar, 1600, {
   immediate: false,
 })
@@ -88,30 +103,6 @@ const horizontalTrackInsetClass = computed(() =>
   props.trackInset === 'none' ? 'bottom-0 left-0' : 'bottom-1 left-1',
 )
 
-function trackHeight(wrap: HTMLElement) {
-  return clamp(wrap.clientHeight - 8, 0, Number.POSITIVE_INFINITY)
-}
-
-function maxScrollTop(wrap: HTMLElement) {
-  return clamp(wrap.scrollHeight - wrap.clientHeight, 0, Number.POSITIVE_INFINITY)
-}
-
-function trackWidth(wrap: HTMLElement) {
-  return clamp(wrap.clientWidth - 8, 0, Number.POSITIVE_INFINITY)
-}
-
-function maxScrollLeft(wrap: HTMLElement) {
-  return clamp(wrap.scrollWidth - wrap.clientWidth, 0, Number.POSITIVE_INFINITY)
-}
-
-function maxThumbTop(wrap: HTMLElement) {
-  return clamp(trackHeight(wrap) - thumbHeight.value, 0, Number.POSITIVE_INFINITY)
-}
-
-function maxHorizontalThumbLeft(wrap: HTMLElement) {
-  return clamp(trackWidth(wrap) - horizontalThumbWidth.value, 0, Number.POSITIVE_INFINITY)
-}
-
 function showScrollbar() {
   visible.value = true
 }
@@ -122,7 +113,9 @@ function clearHideTimer() {
 
 function scheduleHideScrollbar() {
   clearHideTimer()
-  startHideTimer()
+  if (!rootHovering) {
+    startHideTimer()
+  }
 }
 
 function hideScrollbar() {
@@ -135,6 +128,16 @@ function activateScrollbar() {
   scheduleHideScrollbar()
 }
 
+function handleRootMouseEnter() {
+  rootHovering = true
+  activateScrollbar()
+}
+
+function handleRootMouseLeave() {
+  rootHovering = false
+  hideScrollbar()
+}
+
 type ScrollbarAxis = 'vertical' | 'horizontal'
 
 function setTrackHovering(axis: ScrollbarAxis, hovering: boolean) {
@@ -163,48 +166,90 @@ function update() {
     return
   }
 
-  updateVerticalScrollbar(wrap)
-  updateHorizontalScrollbar(wrap)
+  measureVerticalScrollbar(wrap)
+  measureHorizontalScrollbar(wrap)
+  syncScrollbarPosition(wrap, true)
 }
 
-function updateVerticalScrollbar(wrap: HTMLElement) {
+function measureVerticalScrollbar(wrap: HTMLElement) {
   if (!props.vertical) {
+    verticalMetrics.scrollRange = 0
+    verticalMetrics.thumbRange = 0
     thumbHeight.value = 0
-    thumbTop.value = 0
     return
   }
 
-  const scrollRange = maxScrollTop(wrap)
-  const availableTrackHeight = trackHeight(wrap)
+  const clientHeight = wrap.clientHeight
+  const scrollHeight = wrap.scrollHeight
+  const scrollRange = clamp(scrollHeight - clientHeight, 0, Number.POSITIVE_INFINITY)
+  const availableTrackHeight = clamp(clientHeight - 8, 0, Number.POSITIVE_INFINITY)
   if (scrollRange <= overflowTolerance || availableTrackHeight <= 0) {
     wrap.scrollTop = 0
+    verticalMetrics.scrollRange = 0
+    verticalMetrics.thumbRange = 0
     thumbHeight.value = 0
-    thumbTop.value = 0
     return
   }
-  const ratio = wrap.clientHeight / wrap.scrollHeight
-  thumbHeight.value = clamp(availableTrackHeight * ratio, 32, availableTrackHeight)
-  thumbTop.value = (wrap.scrollTop / scrollRange) * maxThumbTop(wrap)
+
+  const ratio = clientHeight / scrollHeight
+  const nextThumbHeight = clamp(availableTrackHeight * ratio, 32, availableTrackHeight)
+  verticalMetrics.scrollRange = scrollRange
+  verticalMetrics.thumbRange = availableTrackHeight - nextThumbHeight
+  thumbHeight.value = nextThumbHeight
 }
 
-function updateHorizontalScrollbar(wrap: HTMLElement) {
+function measureHorizontalScrollbar(wrap: HTMLElement) {
   if (!props.horizontal) {
+    horizontalMetrics.scrollRange = 0
+    horizontalMetrics.thumbRange = 0
     horizontalThumbWidth.value = 0
-    horizontalThumbLeft.value = 0
     return
   }
 
-  const scrollRange = maxScrollLeft(wrap)
-  const availableTrackWidth = trackWidth(wrap)
+  const clientWidth = wrap.clientWidth
+  const scrollWidth = wrap.scrollWidth
+  const scrollRange = clamp(scrollWidth - clientWidth, 0, Number.POSITIVE_INFINITY)
+  const availableTrackWidth = clamp(clientWidth - 8, 0, Number.POSITIVE_INFINITY)
   if (scrollRange <= overflowTolerance || availableTrackWidth <= 0) {
     wrap.scrollLeft = 0
+    horizontalMetrics.scrollRange = 0
+    horizontalMetrics.thumbRange = 0
     horizontalThumbWidth.value = 0
-    horizontalThumbLeft.value = 0
     return
   }
-  const ratio = wrap.clientWidth / wrap.scrollWidth
-  horizontalThumbWidth.value = clamp(availableTrackWidth * ratio, 32, availableTrackWidth)
-  horizontalThumbLeft.value = (wrap.scrollLeft / scrollRange) * maxHorizontalThumbLeft(wrap)
+
+  const ratio = clientWidth / scrollWidth
+  const nextThumbWidth = clamp(availableTrackWidth * ratio, 32, availableTrackWidth)
+  horizontalMetrics.scrollRange = scrollRange
+  horizontalMetrics.thumbRange = availableTrackWidth - nextThumbWidth
+  horizontalThumbWidth.value = nextThumbWidth
+}
+
+function updateVerticalThumbPosition(scrollTop: number) {
+  const { scrollRange, thumbRange } = verticalMetrics
+  thumbTop.value
+    = scrollRange > 0 ? (clamp(scrollTop, 0, scrollRange) / scrollRange) * thumbRange : 0
+}
+
+function updateHorizontalThumbPosition(scrollLeft: number) {
+  const { scrollRange, thumbRange } = horizontalMetrics
+  horizontalThumbLeft.value
+    = scrollRange > 0 ? (clamp(scrollLeft, 0, scrollRange) / scrollRange) * thumbRange : 0
+}
+
+function syncScrollbarPosition(wrap: HTMLElement, force = false) {
+  const scrollTop = wrap.scrollTop
+  const scrollLeft = wrap.scrollLeft
+
+  if (force || scrollTop !== scrollTopPosition) {
+    updateVerticalThumbPosition(scrollTop)
+  }
+  if (force || scrollLeft !== scrollLeftPosition) {
+    updateHorizontalThumbPosition(scrollLeft)
+  }
+
+  scrollTopPosition = scrollTop
+  scrollLeftPosition = scrollLeft
 }
 
 async function scrollToTop() {
@@ -230,13 +275,14 @@ async function scrollToBottom() {
   update()
 }
 
-function handleScroll() {
+function flushScrollFrame() {
+  scrollFrameId = undefined
   const wrap = wrapRef.value
   if (!wrap) {
     return
   }
 
-  update()
+  syncScrollbarPosition(wrap)
   activateScrollbar()
   emit('scroll', {
     scrollTop: wrap.scrollTop,
@@ -244,6 +290,14 @@ function handleScroll() {
   })
 }
 
+function handleScroll() {
+  if (scrollFrameId !== undefined) {
+    return
+  }
+
+  scrollFrameId = requestAnimationFrame(flushScrollFrame)
+}
+
 function handleTrackPointerDown(event: PointerEvent) {
   if (event.target !== event.currentTarget) {
     return
@@ -254,11 +308,11 @@ function handleTrackPointerDown(event: PointerEvent) {
     return
   }
 
+  update()
   const rect = (event.currentTarget as HTMLElement).getBoundingClientRect()
   activateScrollbar()
   const nextThumbTop = event.clientY - rect.top - thumbHeight.value / 2
-  const scrollRange = maxScrollTop(wrap)
-  const thumbRange = maxThumbTop(wrap)
+  const { scrollRange, thumbRange } = verticalMetrics
   wrap.scrollTop
     = thumbRange > 0 ? (clamp(nextThumbTop, 0, thumbRange) / thumbRange) * scrollRange : 0
 }
@@ -273,11 +327,11 @@ function handleHorizontalTrackPointerDown(event: PointerEvent) {
     return
   }
 
+  update()
   const rect = (event.currentTarget as HTMLElement).getBoundingClientRect()
   activateScrollbar()
   const nextThumbLeft = event.clientX - rect.left - horizontalThumbWidth.value / 2
-  const scrollRange = maxScrollLeft(wrap)
-  const thumbRange = maxHorizontalThumbLeft(wrap)
+  const { scrollRange, thumbRange } = horizontalMetrics
   wrap.scrollLeft
     = thumbRange > 0 ? (clamp(nextThumbLeft, 0, thumbRange) / thumbRange) * scrollRange : 0
 }
@@ -289,6 +343,7 @@ function handleThumbPointerDown(event: PointerEvent) {
   }
 
   event.preventDefault()
+  update()
   dragging.value = true
   visible.value = true
   clearHideTimer()
@@ -303,6 +358,7 @@ function handleHorizontalThumbPointerDown(event: PointerEvent) {
   }
 
   event.preventDefault()
+  update()
   horizontalDragging.value = true
   visible.value = true
   clearHideTimer()
@@ -320,12 +376,11 @@ function handleThumbPointerMove(event: PointerEvent) {
     return
   }
 
-  const thumbRange = maxThumbTop(wrap)
+  const { scrollRange, thumbRange } = verticalMetrics
   if (thumbRange <= 0) {
     return
   }
 
-  const scrollRange = maxScrollTop(wrap)
   wrap.scrollTop = dragStartScrollTop + ((event.clientY - dragStartY) / thumbRange) * scrollRange
 }
 
@@ -339,12 +394,11 @@ function handleHorizontalThumbPointerMove(event: PointerEvent) {
     return
   }
 
-  const thumbRange = maxHorizontalThumbLeft(wrap)
+  const { scrollRange, thumbRange } = horizontalMetrics
   if (thumbRange <= 0) {
     return
   }
 
-  const scrollRange = maxScrollLeft(wrap)
   wrap.scrollLeft
     = horizontalDragStartScrollLeft
       + ((event.clientX - horizontalDragStartX) / thumbRange) * scrollRange
@@ -368,19 +422,33 @@ function handleHorizontalThumbPointerUp() {
   activateScrollbar()
 }
 
+function handleDocumentPointerMove(event: PointerEvent) {
+  handleThumbPointerMove(event)
+  handleHorizontalThumbPointerMove(event)
+}
+
+function handleDocumentPointerUp() {
+  handleThumbPointerUp()
+  handleHorizontalThumbPointerUp()
+}
+
 onMounted(async () => {
   await nextTick()
   update()
 })
 
+onBeforeUnmount(() => {
+  if (scrollFrameId !== undefined) {
+    cancelAnimationFrame(scrollFrameId)
+  }
+})
+
 useResizeObserver([wrapRef, viewRef], update)
-useScroll(wrapRef, { onScroll: handleScroll })
-useEventListener(document, 'pointermove', handleThumbPointerMove)
-useEventListener(document, 'pointerup', handleThumbPointerUp)
-useEventListener(document, 'pointermove', handleHorizontalThumbPointerMove)
-useEventListener(document, 'pointerup', handleHorizontalThumbPointerUp)
-useEventListener(rootRef, ['mouseenter', 'mousemove'], activateScrollbar)
-useEventListener(rootRef, 'mouseleave', hideScrollbar)
+useEventListener(wrapRef, 'scroll', handleScroll, { passive: true })
+useEventListener(dragDocument, 'pointermove', handleDocumentPointerMove)
+useEventListener(dragDocument, ['pointerup', 'pointercancel'], handleDocumentPointerUp)
+useEventListener(rootRef, 'mouseenter', handleRootMouseEnter)
+useEventListener(rootRef, 'mouseleave', handleRootMouseLeave)
 useEventListener(verticalTrackRef, 'mouseenter', () => handleTrackMouseEnter('vertical'))
 useEventListener(verticalTrackRef, 'mouseleave', () => handleTrackMouseLeave('vertical'))
 useEventListener(verticalTrackRef, 'pointerdown', handleTrackPointerDown)

frontend/src/components/base/BaseTable/useHorizontalStickyShadow.ts

@@ -15,6 +15,8 @@ interface UseHorizontalStickyShadowOptions {
 export function useHorizontalStickyShadow(options: UseHorizontalStickyShadowOptions) {
   const horizontalScrolled = shallowRef(false)
   const horizontalCanScrollRight = shallowRef(false)
+  let horizontalScrollRange = 0
+  let scrollLeftPosition = 0
 
   function maxScrollLeft(wrap: HTMLElement) {
     return Math.max(wrap.scrollWidth - wrap.clientWidth, 0)
@@ -25,11 +27,26 @@ export function useHorizontalStickyShadow(options: UseHorizontalStickyShadowOpti
   }
 
   function resetHorizontalScrollbar() {
+    horizontalScrollRange = 0
+    scrollLeftPosition = 0
     horizontalScrolled.value = false
     horizontalCanScrollRight.value = false
+    syncHeaderScroll(0)
   }
 
-  function updateHorizontalScrollbar() {
+  function syncHeaderScroll(scrollLeft: number) {
+    const headerWrap = options.headerWrapRef.value
+    if (headerWrap && headerWrap.scrollLeft !== scrollLeft) {
+      headerWrap.scrollLeft = scrollLeft
+    }
+  }
+
+  function updateHorizontalScrollPosition(scrollLeft: number) {
+    horizontalScrolled.value = scrollLeft > 0
+    horizontalCanScrollRight.value = scrollLeft < horizontalScrollRange - 1
+  }
+
+  function measureHorizontalScrollbar() {
     const wrap = scrollWrap()
     if (!wrap || !options.hasRows.value) {
       resetHorizontalScrollbar()
@@ -42,21 +59,25 @@ export function useHorizontalStickyShadow(options: UseHorizontalStickyShadowOpti
       return
     }
 
-    horizontalScrolled.value = wrap.scrollLeft > 0
-    horizontalCanScrollRight.value = wrap.scrollLeft < scrollRange - 1
+    horizontalScrollRange = scrollRange
+    scrollLeftPosition = wrap.scrollLeft
+    syncHeaderScroll(scrollLeftPosition)
+    updateHorizontalScrollPosition(scrollLeftPosition)
   }
 
-  function handleTableScroll() {
-    const wrap = scrollWrap()
-    if (wrap && options.headerWrapRef.value) {
-      options.headerWrapRef.value.scrollLeft = wrap.scrollLeft
+  function handleTableScroll(payload: { scrollTop: number, scrollLeft: number }) {
+    if (payload.scrollLeft === scrollLeftPosition) {
+      return
     }
-    updateHorizontalScrollbar()
+
+    scrollLeftPosition = payload.scrollLeft
+    syncHeaderScroll(scrollLeftPosition)
+    updateHorizontalScrollPosition(scrollLeftPosition)
   }
 
   onMounted(async () => {
     await nextTick()
-    updateHorizontalScrollbar()
+    measureHorizontalScrollbar()
   })
 
   useResizeObserver(
@@ -64,12 +85,12 @@ export function useHorizontalStickyShadow(options: UseHorizontalStickyShadowOpti
       [scrollWrap(), options.tableViewRef.value].filter(
         (element): element is HTMLDivElement | HTMLTableElement => Boolean(element),
       ),
-    updateHorizontalScrollbar,
+    measureHorizontalScrollbar,
   )
 
   watch(options.watchSources, async () => {
     await nextTick()
-    updateHorizontalScrollbar()
+    measureHorizontalScrollbar()
   })
 
   return {

frontend/src/layout/components/AppSidebar.vue

@@ -1,7 +1,6 @@
 <script setup lang="ts">
 import {
   ArrowUpCircle,
-  Cat,
   ChartNoAxesColumn,
   Info,
   KeyRound,
@@ -118,7 +117,11 @@ const sidebarEl = ref<HTMLElement | null>(null)
 const brandLabelEl = ref<HTMLElement | null>(null)
 const navSignalEl = useTemplateRef<HTMLElement>('navSignal')
 const isCollapsed = computed(() => !props.mobile && Boolean(props.collapsed))
-const sidebarWidth = computed(() => (isCollapsed.value ? 88 : 256))
+const collapsedSidebarWidth = 88
+const expandedSidebarWidth = 251
+const sidebarWidth = computed(() =>
+  isCollapsed.value ? collapsedSidebarWidth : expandedSidebarWidth,
+)
 const brandLabelVisible = shallowRef(!isCollapsed.value)
 const themeToggleLabel = computed(() =>
   effectiveTheme.value === 'dark' ? '切换浅色模式' : '切换暗黑模式',
@@ -209,7 +212,7 @@ function animateSidebarWidth(collapsed: boolean) {
     return
   }
 
-  const targetWidth = collapsed ? 88 : 256
+  const targetWidth = collapsed ? collapsedSidebarWidth : expandedSidebarWidth
   const currentWidth = sidebarEl.value.getBoundingClientRect().width
 
   if (prefersReducedMotion()) {
@@ -326,7 +329,7 @@ onBeforeUnmount(() => {
     class="z-20 h-dvh shrink-0 flex-col overflow-hidden bg-(--cp-bg-surface) px-4 shadow-(--cp-shadow-sidebar)"
     :class="[
       mobile ? 'flex' : 'hidden min-[961px]:flex',
-      isCollapsed ? 'w-22 basis-22 items-center' : 'w-64 basis-64',
+      isCollapsed ? 'w-22 basis-22 items-center' : 'w-[251px] basis-[251px]',
     ]"
   >
     <div
@@ -336,9 +339,14 @@ onBeforeUnmount(() => {
       <BaseMotionIcon
         aria-hidden="true"
         variant="brand"
-        class="inline-flex size-11 items-center justify-center relative -top-0.5 rounded-(--cp-icon-button-radius) bg-(--cp-bg-muted) text-(--cp-text-primary)"
+        class="inline-flex size-11 items-center justify-center relative -top-0.5 rounded-(--cp-icon-button-radius) bg-(--cp-brand-mark-bg)"
       >
-        <Cat :size="27" stroke-width="2" />
+        <img
+          src="/favicon.svg"
+          alt=""
+          class="block size-9 select-none"
+          draggable="false"
+        >
       </BaseMotionIcon>
       <span
         v-show="brandLabelVisible"

frontend/src/stores/modules/system-update.ts

@@ -1,4 +1,4 @@
-import { useEventSource } from '@vueuse/core'
+import { until, useEventSource } from '@vueuse/core'
 import { delay } from 'es-toolkit'
 import { defineStore } from 'pinia'
 
@@ -14,6 +14,7 @@ import { ApiError } from '@/api/request'
 import { errorMessage } from '@/utils/async'
 
 const maxUpdateLogs = 200
+const updateEventReadyTimeoutMs = 3_000
 const restartReadyTimeoutMs = 60_000
 const restartProbeTimeoutMs = 2_000
 const restartReadyPollIntervalMs = 500
@@ -106,19 +107,30 @@ export const useSystemUpdateStore = defineStore('system-update', () => {
     }
   })
 
-  function connectUpdateEvents(force = false) {
+  async function connectUpdateEvents(force = false) {
     if (force) {
       disconnectUpdateEvents()
     }
     else if (updateEventSource.value) {
-      return
+      return updateEventStatus.value === 'OPEN'
     }
 
     updateStreamError.value = ''
     openUpdateEventSource()
     if (!updateEventSource.value) {
       updateStreamError.value = '当前浏览器不支持实时更新日志'
+      return false
     }
+
+    if (updateEventStatus.value !== 'OPEN') {
+      await until(updateEventStatus).toBe('OPEN', {
+        timeout: updateEventReadyTimeoutMs,
+      })
+    }
+    const connected = updateEventStatus.value === 'OPEN'
+    if (!connected)
+      updateStreamError.value = '更新日志连接超时'
+    return connected
   }
 
   function disconnectUpdateEvents() {
@@ -186,7 +198,7 @@ export const useSystemUpdateStore = defineStore('system-update', () => {
       return null
 
     clearUpdateLogs()
-    connectUpdateEvents(true)
+    await connectUpdateEvents(true)
     updating.value = true
     updateError.value = ''
     updateSuccess.value = false

frontend/src/styles/tokens.css

@@ -8,6 +8,7 @@
   --cp-bg-tertiary: #eef6ff;
   --cp-bg-nav-active: #e9eef5;
   --cp-bg-dark: #111827;
+  --cp-brand-mark-bg: #1c2a3d;
   --cp-white: #ffffff;
   --cp-transparent: #ffffff00;
   --cp-overlay-scrim: #0e17264d;

frontend/src/views/accounts/constants.ts

@@ -98,7 +98,8 @@ export const accountColumns = [
     sortable: true,
     flex: 1.2,
     minWidth: '160px',
-    format: (_value: unknown, row: AccountRow) => row.usage.lastUsedAtDisplay,
+    format: (_value: unknown, row: AccountRow) => optionalAccountCell(row.usage.lastUsedAtDisplay),
+    emptyText: '',
     cellClass: `${relaxedCellClass} text-(--cp-text-secondary)`,
   },
   {
@@ -108,6 +109,8 @@ export const accountColumns = [
     sortKey: 'expiresAt',
     flex: 1.2,
     minWidth: '160px',
+    format: value => optionalAccountCell(value),
+    emptyText: '',
     cellClass: `${relaxedCellClass} text-(--cp-text-secondary)`,
   },
   {
@@ -201,3 +204,7 @@ function accountProviderLabel(value?: string | null) {
     return 'xAI'
   return value || '—'
 }
+
+function optionalAccountCell(value: unknown) {
+  return value === '—' || value === '-' ? '' : value
+}

frontend/src/views/api-keys/components/ApiKeyUseModal.vue

@@ -35,19 +35,30 @@ const configPath = computed(() =>
     ? '%userprofile%\\.codex\\config.toml'
     : '~/.codex/config.toml',
 )
-const authPath = computed(() =>
-  activePlatform.value === 'windows' ? '%userprofile%\\.codex\\auth.json' : '~/.codex/auth.json',
+const tokenPath = computed(() =>
+  activePlatform.value === 'windows'
+    ? '%userprofile%\\.codex\\codex-proxy.token'
+    : '~/.codex/codex-proxy.token',
 )
-const codexAuthJson = computed(() => JSON.stringify({ OPENAI_API_KEY: keyValue.value }, null, 2))
 const defaultModel = computed(() =>
   props.apiKey?.providerKind?.trim().toLowerCase() === 'xai' ? 'grok-4.5' : 'gpt-5.5',
 )
+const providerAuthToml = computed(() =>
+  activePlatform.value === 'windows'
+    ? `[model_providers.OpenAI.auth]
+command = "powershell.exe"
+args = ["-NoLogo", "-NoProfile", "-NonInteractive", "-Command", "Get-Content -Raw (Join-Path (Join-Path $env:USERPROFILE '.codex') 'codex-proxy.token')"]`
+    : `[model_providers.OpenAI.auth]
+command = "sh"
+args = ["-c", 'cat "$HOME/.codex/codex-proxy.token"']`,
+)
 
 const codexConfigToml = computed(
   () => `model_provider = "OpenAI"
 model = "${defaultModel.value}"
 review_model = "${defaultModel.value}"
 model_reasoning_effort = "xhigh"
+service_tier = "default"
 disable_response_storage = true
 network_access = "enabled"
 windows_wsl_setup_acknowledged = true
@@ -56,7 +67,8 @@ windows_wsl_setup_acknowledged = true
 name = "OpenAI"
 base_url = "${props.apiBaseUrl}"
 wire_api = "responses"
-requires_openai_auth = true
+
+${providerAuthToml.value}
 
 [features]
 goals = true`,
@@ -64,7 +76,7 @@ goals = true`,
 
 const visibleFiles = computed(() => [
   { path: configPath.value, content: codexConfigToml.value },
-  { path: authPath.value, content: codexAuthJson.value },
+  { path: tokenPath.value, content: keyValue.value },
 ])
 </script>
 

frontend/src/views/login/components/LoginPanel.vue

@@ -1,5 +1,5 @@
 <script setup lang="ts">
-import { ArrowRight, Cat, CircleAlert, Eye, EyeOff, KeyRound, Mail, Moon, Sun } from '@lucide/vue'
+import { ArrowRight, CircleAlert, Eye, EyeOff, KeyRound, Mail, Moon, Sun } from '@lucide/vue'
 import { computed, shallowRef } from 'vue'
 
 import BaseButton from '@/components/base/BaseButton.vue'
@@ -58,7 +58,12 @@ function togglePasswordVisible(): void {
     <header class="flex min-w-0 items-center justify-between gap-4.5 max-[560px]:gap-3.5">
       <div class="flex min-w-0 items-center gap-3">
         <BaseMotionIcon aria-hidden="true" variant="brand" class="login-logo">
-          <Cat :size="20" :stroke-width="2.1" />
+          <img
+            src="/favicon.svg"
+            alt=""
+            class="block size-8 select-none"
+            draggable="false"
+          >
         </BaseMotionIcon>
         <span class="grid min-w-0 gap-1">
           <strong

frontend/src/views/login/index.vue

@@ -93,7 +93,7 @@ async function handleSubmit(): Promise<void> {
   --login-form-bg-c: color-mix(in srgb, var(--cp-bg-muted) 78%, var(--cp-info-bg));
   --login-form-shadow: color-mix(in srgb, var(--cp-text-primary) 20%, transparent);
   --login-form-line: color-mix(in srgb, var(--cp-info-border) 54%, transparent);
-  --login-logo-bg: color-mix(in srgb, var(--cp-info-bg) 74%, var(--cp-bg-surface));
+  --login-logo-bg: var(--cp-brand-mark-bg);
   --login-logo-text: var(--cp-accent-primary);
   --login-title: var(--cp-text-primary);
   --login-brand-title: var(--cp-text-strong);
@@ -159,7 +159,7 @@ async function handleSubmit(): Promise<void> {
   --login-form-bg-c: color-mix(in srgb, var(--cp-bg-page) 90%, transparent);
   --login-form-shadow: color-mix(in srgb, var(--cp-bg-dark) 70%, transparent);
   --login-form-line: color-mix(in srgb, var(--cp-info-text) 66%, transparent);
-  --login-logo-bg: color-mix(in srgb, var(--cp-bg-surface) 84%, transparent);
+  --login-logo-bg: var(--cp-brand-mark-bg);
   --login-logo-text: var(--cp-info-text);
   --login-title: var(--cp-text-strong);
   --login-brand-title: var(--cp-white);

frontend/src/views/usage/components/UsageSummaryCards.vue

@@ -9,6 +9,10 @@ const props = defineProps<{
   summary: Awaited<ReturnType<typeof getUsageRecordSummary>>
 }>()
 
+function averageLatencyDisplay(value: string) {
+  return !value || value === '—' || value === '-' ? '0 ms' : value
+}
+
 const items = computed(() => [
   {
     key: 'requests',
@@ -38,7 +42,7 @@ const items = computed(() => [
     key: 'latency',
     label: '平均耗时',
     icon: Timer,
-    value: props.summary.averageLatencyMs,
+    value: averageLatencyDisplay(props.summary.averageLatencyMs),
     detail: '成功请求平均值',
     tone: 'text-(--cp-normal-text) bg-(--cp-normal-bg)',
   },

frontend/src/views/usage/composables/useUsageRecordsTable.ts

@@ -247,7 +247,7 @@ function emptySummary() {
     cachedTokens: '0',
     cacheWriteTokens: '0',
     totalTokens: '0',
-    averageLatencyMs: '—',
+    averageLatencyMs: '0 ms',
   }
   return summary
 }

release/version.yaml

@@ -1 +1 @@
-version: "3.0.4"
+version: "3.0.9"