Merge main into Claude Code dynamic client profile

apps/aether-gateway/.aether-windsurf-binary-test-03d740bc-64f1-49cb-b13d-4e5234e5de31/language-server

@@ -1 +0,0 @@
-test binary

apps/aether-gateway/src/ai_serving/planner/common.rs

@@ -19,12 +19,12 @@ pub(crate) use crate::ai_serving::{
     GEMINI_FILES_UPLOAD_PLAN_KIND, GEMINI_VIDEO_CANCEL_SYNC_PLAN_KIND,
     GEMINI_VIDEO_CREATE_SYNC_PLAN_KIND, OPENAI_CHAT_STREAM_PLAN_KIND, OPENAI_CHAT_SYNC_PLAN_KIND,
     OPENAI_EMBEDDING_SYNC_PLAN_KIND, OPENAI_IMAGE_STREAM_PLAN_KIND, OPENAI_IMAGE_SYNC_PLAN_KIND,
-    OPENAI_RERANK_SYNC_PLAN_KIND, OPENAI_RESPONSES_COMPACT_STREAM_PLAN_KIND,
-    OPENAI_RESPONSES_COMPACT_SYNC_PLAN_KIND, OPENAI_RESPONSES_STREAM_PLAN_KIND,
-    OPENAI_RESPONSES_SYNC_PLAN_KIND, OPENAI_SEARCH_SYNC_PLAN_KIND,
-    OPENAI_VIDEO_CANCEL_SYNC_PLAN_KIND, OPENAI_VIDEO_CONTENT_PLAN_KIND,
-    OPENAI_VIDEO_CREATE_SYNC_PLAN_KIND, OPENAI_VIDEO_DELETE_SYNC_PLAN_KIND,
-    OPENAI_VIDEO_REMIX_SYNC_PLAN_KIND,
+    OPENAI_MEMORIES_SYNC_PLAN_KIND, OPENAI_RERANK_SYNC_PLAN_KIND,
+    OPENAI_RESPONSES_COMPACT_STREAM_PLAN_KIND, OPENAI_RESPONSES_COMPACT_SYNC_PLAN_KIND,
+    OPENAI_RESPONSES_STREAM_PLAN_KIND, OPENAI_RESPONSES_SYNC_PLAN_KIND,
+    OPENAI_SEARCH_SYNC_PLAN_KIND, OPENAI_VIDEO_CANCEL_SYNC_PLAN_KIND,
+    OPENAI_VIDEO_CONTENT_PLAN_KIND, OPENAI_VIDEO_CREATE_SYNC_PLAN_KIND,
+    OPENAI_VIDEO_DELETE_SYNC_PLAN_KIND, OPENAI_VIDEO_REMIX_SYNC_PLAN_KIND,
 };
 
 pub(crate) use aether_ai_serving::AiRequestedModelFamily as RequestedModelFamily;

apps/aether-gateway/src/ai_serving/planner/decision/control_plan.rs

@@ -6,12 +6,13 @@ use crate::ai_serving::planner::common::{
     GEMINI_FILES_DOWNLOAD_PLAN_KIND, GEMINI_FILES_GET_PLAN_KIND, GEMINI_FILES_LIST_PLAN_KIND,
     GEMINI_VIDEO_CANCEL_SYNC_PLAN_KIND, GEMINI_VIDEO_CREATE_SYNC_PLAN_KIND,
     OPENAI_CHAT_STREAM_PLAN_KIND, OPENAI_CHAT_SYNC_PLAN_KIND, OPENAI_EMBEDDING_SYNC_PLAN_KIND,
-    OPENAI_IMAGE_STREAM_PLAN_KIND, OPENAI_IMAGE_SYNC_PLAN_KIND, OPENAI_RERANK_SYNC_PLAN_KIND,
-    OPENAI_RESPONSES_COMPACT_STREAM_PLAN_KIND, OPENAI_RESPONSES_COMPACT_SYNC_PLAN_KIND,
-    OPENAI_RESPONSES_STREAM_PLAN_KIND, OPENAI_RESPONSES_SYNC_PLAN_KIND,
-    OPENAI_SEARCH_SYNC_PLAN_KIND, OPENAI_VIDEO_CANCEL_SYNC_PLAN_KIND,
-    OPENAI_VIDEO_CONTENT_PLAN_KIND, OPENAI_VIDEO_CREATE_SYNC_PLAN_KIND,
-    OPENAI_VIDEO_DELETE_SYNC_PLAN_KIND, OPENAI_VIDEO_REMIX_SYNC_PLAN_KIND,
+    OPENAI_IMAGE_STREAM_PLAN_KIND, OPENAI_IMAGE_SYNC_PLAN_KIND, OPENAI_MEMORIES_SYNC_PLAN_KIND,
+    OPENAI_RERANK_SYNC_PLAN_KIND, OPENAI_RESPONSES_COMPACT_STREAM_PLAN_KIND,
+    OPENAI_RESPONSES_COMPACT_SYNC_PLAN_KIND, OPENAI_RESPONSES_STREAM_PLAN_KIND,
+    OPENAI_RESPONSES_SYNC_PLAN_KIND, OPENAI_SEARCH_SYNC_PLAN_KIND,
+    OPENAI_VIDEO_CANCEL_SYNC_PLAN_KIND, OPENAI_VIDEO_CONTENT_PLAN_KIND,
+    OPENAI_VIDEO_CREATE_SYNC_PLAN_KIND, OPENAI_VIDEO_DELETE_SYNC_PLAN_KIND,
+    OPENAI_VIDEO_REMIX_SYNC_PLAN_KIND,
 };
 use crate::ai_serving::planner::plan_builders::{
     build_gemini_stream_plan_from_decision, build_gemini_sync_plan_from_decision,
@@ -101,7 +102,9 @@ fn build_sync_plan_payload_from_decision(
         OPENAI_RESPONSES_SYNC_PLAN_KIND => {
             build_openai_responses_sync_plan_from_decision(parts, body_json, payload, false)?
         }
-        OPENAI_IMAGE_SYNC_PLAN_KIND | OPENAI_SEARCH_SYNC_PLAN_KIND => {
+        OPENAI_IMAGE_SYNC_PLAN_KIND
+        | OPENAI_SEARCH_SYNC_PLAN_KIND
+        | OPENAI_MEMORIES_SYNC_PLAN_KIND => {
             build_passthrough_sync_plan_from_decision(parts, payload)?
         }
         OPENAI_RESPONSES_COMPACT_SYNC_PLAN_KIND => {

apps/aether-gateway/src/ai_serving/planner/decision_input.rs

@@ -17,7 +17,7 @@ use crate::ai_serving::transport::ProviderOutboundRequestContext;
 use crate::ai_serving::{
     ClientSurface, ExecutionRuntimeAuthContext, GatewayAuthApiKeySnapshot,
     GatewayCredentialCarrier, GatewayProviderTransportSnapshot, PlannerAppState,
-    CODEX_RESPONSES_LITE_HEADER,
+    CODEX_RESPONSES_LITE_HEADER, OPENAI_MEMORIES_SYNC_PLAN_KIND,
 };
 use crate::cache::CacheLoadObserver;
 use crate::client_session_affinity::client_session_affinity_from_api_request;
@@ -123,6 +123,7 @@ pub(crate) fn apply_provider_request_routing_policy_to_decision_with_websocket_m
     transport: Option<&GatewayProviderTransportSnapshot>,
     websocket_continuation: bool,
 ) -> Result<(), GatewayError> {
+    let native_memories = decision.decision_kind.as_deref() == Some(OPENAI_MEMORIES_SYNC_PLAN_KIND);
     let provider_api_format = decision
         .provider_api_format
         .clone()
@@ -150,7 +151,12 @@ pub(crate) fn apply_provider_request_routing_policy_to_decision_with_websocket_m
             input.requested_model.as_str(),
         )
     });
-    crate::ai_serving::apply_codex_openai_responses_lite_header_for_request_body_with_capabilities(
+    if native_memories {
+        decision
+            .provider_request_headers
+            .retain(|name, _| !name.eq_ignore_ascii_case(CODEX_RESPONSES_LITE_HEADER));
+    } else {
+        crate::ai_serving::apply_codex_openai_responses_lite_header_for_request_body_with_capabilities(
         &mut decision.provider_request_headers,
         decision.provider_request_body.as_ref(),
         provider_type.as_str(),
@@ -159,6 +165,7 @@ pub(crate) fn apply_provider_request_routing_policy_to_decision_with_websocket_m
         input.requested_model.as_str(),
         model_capabilities.as_ref(),
     );
+    }
 
     let Some(context) = input.routing_context.as_ref() else {
         // Cache identity headers are projected only at the terminal boundary. Any non-empty
@@ -260,7 +267,7 @@ pub(crate) fn apply_provider_request_routing_policy_to_decision_with_websocket_m
             provider_headers.insert(HeaderName::from_static(name), value);
         }
     }
-    if original_provider_request_body.is_some() {
+    if original_provider_request_body.is_some() && !native_memories {
         let provider_model = provider_request_body
             .get("model")
             .and_then(Value::as_str)
@@ -318,6 +325,12 @@ pub(crate) fn apply_provider_request_routing_policy_to_decision_with_websocket_m
         }
         .map_err(|_| invalid_routing_provider_contract())?;
     }
+    if native_memories {
+        crate::ai_serving::transport::enforce_same_format_provider_api_operation_body_policy(
+            &mut provider_request_body,
+            Some(crate::ai_serving::ApiOperation::OpenAiMemoriesSummarize),
+        );
+    }
     let provider_model = provider_request_body
         .get("model")
         .and_then(Value::as_str)
@@ -339,7 +352,11 @@ pub(crate) fn apply_provider_request_routing_policy_to_decision_with_websocket_m
         provider_type.as_str(),
         provider_api_format.as_str(),
     );
-    crate::ai_serving::apply_codex_openai_responses_lite_header_for_request_body_with_capabilities(
+    if native_memories {
+        provider_request_headers
+            .retain(|name, _| !name.eq_ignore_ascii_case(CODEX_RESPONSES_LITE_HEADER));
+    } else {
+        crate::ai_serving::apply_codex_openai_responses_lite_header_for_request_body_with_capabilities(
         &mut provider_request_headers,
         Some(&provider_request_body),
         provider_type.as_str(),
@@ -348,6 +365,7 @@ pub(crate) fn apply_provider_request_routing_policy_to_decision_with_websocket_m
         input.requested_model.as_str(),
         model_capabilities.as_ref(),
     );
+    }
     crate::ai_serving::apply_codex_openai_compact_terminal_headers(
         &mut provider_request_headers,
         provider_type.as_str(),
@@ -382,6 +400,15 @@ fn apply_provider_outbound_request_policies_to_decision(
     let Some(context) = input.provider_outbound_context.as_ref() else {
         return;
     };
+    let native_context;
+    let context = if decision.decision_kind.as_deref() == Some(OPENAI_MEMORIES_SYNC_PLAN_KIND) {
+        native_context = context
+            .clone()
+            .with_api_operation(crate::ai_serving::ApiOperation::OpenAiMemoriesSummarize);
+        &native_context
+    } else {
+        context
+    };
     let results = crate::ai_serving::transport::apply_provider_outbound_request_policies(
         transport,
         provider_api_format,

apps/aether-gateway/src/ai_serving/planner/passthrough/provider/family/request.rs

@@ -24,7 +24,9 @@ use crate::ai_serving::transport::{
     SameFormatProviderCompatibilityEditAction, SameFormatProviderHeadersInput,
     GEMINI_CLI_USER_AGENT, GROK_CHAT_PATH,
 };
-use crate::ai_serving::{CandidateFailureDiagnostic, GatewayProviderTransportSnapshot};
+use crate::ai_serving::{
+    CandidateFailureDiagnostic, GatewayProviderTransportSnapshot, CODEX_RESPONSES_LITE_HEADER,
+};
 use crate::{AppState, GatewayError};
 
 mod policy;
@@ -255,7 +257,9 @@ pub(crate) async fn resolve_local_same_format_provider_candidate_payload_parts(
         // re-enforce stream-field policy afterward.
         // Kiro behavior classification already hard-requires upstream streaming,
         // and the Kiro envelope does not use a top-level body stream field.
-        if prepared.kiro_auth.is_none() {
+        if prepared.kiro_auth.is_none()
+            && spec.operation != Some(crate::ai_serving::ApiOperation::OpenAiMemoriesSummarize)
+        {
             enforce_provider_body_stream_policy(
                 &mut base_provider_request_body,
                 prepared.provider_api_format.as_str(),
@@ -275,7 +279,8 @@ pub(crate) async fn resolve_local_same_format_provider_candidate_payload_parts(
         prepared.mapped_model.as_str(),
         source_model,
     );
-    if let Err(violation) =
+    if spec.operation != Some(crate::ai_serving::ApiOperation::OpenAiMemoriesSummarize) {
+        if let Err(violation) =
         crate::ai_serving::finalize_openai_provider_request_with_codex_model_capabilities_and_reasoning_replay_policy(
             &mut base_provider_request_body,
             crate::ai_serving::OpenAiProviderRequestFinalization {
@@ -313,6 +318,7 @@ pub(crate) async fn resolve_local_same_format_provider_candidate_payload_parts(
         .await;
         return Ok(None);
     }
+    }
 
     // Same-format requests skip `apply_transport_request_body_semantics`, so the opt-in
     // Claude Code body mimicry has to be applied here as well.
@@ -597,6 +603,11 @@ pub(crate) async fn resolve_local_same_format_provider_candidate_payload_parts(
         source_model,
         codex_model_capabilities.as_ref(),
     );
+    if spec.operation == Some(crate::ai_serving::ApiOperation::OpenAiMemoriesSummarize) {
+        provider_request_headers
+            .retain(|name, _| !name.eq_ignore_ascii_case(CODEX_RESPONSES_LITE_HEADER));
+        provider_request_headers.insert("accept".to_string(), "application/json".to_string());
+    }
     crate::ai_serving::transport::xai::insert_cli_identity_headers_if_needed(
         transport.as_ref(),
         prepared.provider_api_format.as_str(),

apps/aether-gateway/src/ai_serving/planner/passthrough/provider/request/body.rs

@@ -3,7 +3,7 @@ use serde_json::Value;
 use super::super::LocalSameFormatProviderSpec;
 use crate::ai_serving::transport::{
     build_same_format_provider_request_body as build_same_format_provider_request_body_impl,
-    build_same_format_provider_request_body_with_compatibility_report_and_reasoning_replay_policy as build_same_format_provider_request_body_with_compatibility_report_impl,
+    build_same_format_provider_request_body_for_operation as build_same_format_provider_request_body_with_compatibility_report_impl,
     SameFormatProviderFamily, SameFormatProviderRequestBodyInput,
     SameFormatProviderRequestBodyOutput,
 };
@@ -69,6 +69,7 @@ pub(crate) fn build_same_format_provider_request_body_with_compatibility_report(
             enable_model_directives,
         },
         reasoning_replay_policy,
+        spec.operation,
     )
 }
 

apps/aether-gateway/src/ai_serving/planner/standard/normalize/chat.rs

@@ -112,6 +112,22 @@ pub(crate) fn build_cross_format_openai_chat_request_body(
     Some(provider_request_body)
 }
 
+pub(crate) fn build_cross_format_openai_chat_upstream_url(
+    parts: &http::request::Parts,
+    transport: &GatewayProviderTransportSnapshot,
+    mapped_model: &str,
+    provider_api_format: &str,
+    upstream_is_stream: bool,
+) -> Option<String> {
+    crate::ai_serving::transport::build_cross_format_openai_chat_upstream_url(
+        transport,
+        mapped_model,
+        provider_api_format,
+        upstream_is_stream,
+        parts.uri.query(),
+    )
+}
+
 #[cfg(test)]
 mod antigravity_schema_tests {
     use super::*;
@@ -147,19 +163,3 @@ mod antigravity_schema_tests {
         }
     }
 }
-
-pub(crate) fn build_cross_format_openai_chat_upstream_url(
-    parts: &http::request::Parts,
-    transport: &GatewayProviderTransportSnapshot,
-    mapped_model: &str,
-    provider_api_format: &str,
-    upstream_is_stream: bool,
-) -> Option<String> {
-    crate::ai_serving::transport::build_cross_format_openai_chat_upstream_url(
-        transport,
-        mapped_model,
-        provider_api_format,
-        upstream_is_stream,
-        parts.uri.query(),
-    )
-}

apps/aether-gateway/src/ai_serving/planner/standard/normalize/responses.rs

@@ -275,6 +275,24 @@ pub(crate) fn build_local_openai_responses_upstream_url(
     )
 }
 
+pub(crate) fn build_cross_format_openai_responses_upstream_url(
+    parts: &http::request::Parts,
+    transport: &GatewayProviderTransportSnapshot,
+    mapped_model: &str,
+    client_api_format: &str,
+    provider_api_format: &str,
+    upstream_is_stream: bool,
+) -> Option<String> {
+    crate::ai_serving::transport::build_cross_format_openai_responses_upstream_url(
+        transport,
+        mapped_model,
+        client_api_format,
+        provider_api_format,
+        upstream_is_stream,
+        parts.uri.query(),
+    )
+}
+
 #[cfg(test)]
 mod antigravity_schema_tests {
     use super::*;
@@ -309,21 +327,3 @@ mod antigravity_schema_tests {
         }
     }
 }
-
-pub(crate) fn build_cross_format_openai_responses_upstream_url(
-    parts: &http::request::Parts,
-    transport: &GatewayProviderTransportSnapshot,
-    mapped_model: &str,
-    client_api_format: &str,
-    provider_api_format: &str,
-    upstream_is_stream: bool,
-) -> Option<String> {
-    crate::ai_serving::transport::build_cross_format_openai_responses_upstream_url(
-        transport,
-        mapped_model,
-        client_api_format,
-        provider_api_format,
-        upstream_is_stream,
-        parts.uri.query(),
-    )
-}

apps/aether-gateway/src/ai_serving/pure/mod.rs

@@ -163,7 +163,7 @@ pub(crate) use aether_ai_formats::api::{
     OPENAI_EMBEDDING_SYNC_PLAN_KIND, OPENAI_IMAGE_STREAM_PLAN_KIND,
     OPENAI_IMAGE_STREAM_SUCCESS_REPORT_KIND, OPENAI_IMAGE_SYNC_FINALIZE_REPORT_KIND,
     OPENAI_IMAGE_SYNC_PLAN_KIND, OPENAI_IMAGE_SYNC_SUCCESS_REPORT_KIND,
-    OPENAI_REALTIME_STREAM_PLAN_KIND, OPENAI_RERANK_SYNC_PLAN_KIND,
+    OPENAI_MEMORIES_SYNC_PLAN_KIND, OPENAI_REALTIME_STREAM_PLAN_KIND, OPENAI_RERANK_SYNC_PLAN_KIND,
     OPENAI_RESPONSES_COMPACT_STREAM_PLAN_KIND, OPENAI_RESPONSES_COMPACT_STREAM_SUCCESS_REPORT_KIND,
     OPENAI_RESPONSES_COMPACT_SYNC_ERROR_REPORT_KIND,
     OPENAI_RESPONSES_COMPACT_SYNC_FINALIZE_REPORT_KIND, OPENAI_RESPONSES_COMPACT_SYNC_PLAN_KIND,

apps/aether-gateway/src/ai_serving/transport.rs

@@ -78,7 +78,7 @@ pub(crate) use aether_provider_transport::{
     build_local_openai_chat_upstream_url, build_local_openai_responses_upstream_url,
     build_openai_image_headers, build_openai_image_upstream_url, build_passthrough_headers,
     build_request_trace_proxy_value, build_same_format_provider_headers,
-    build_same_format_provider_request_body,
+    build_same_format_provider_request_body, build_same_format_provider_request_body_for_operation,
     build_same_format_provider_request_body_with_compatibility_report,
     build_same_format_provider_request_body_with_compatibility_report_and_reasoning_replay_policy,
     build_same_format_provider_upstream_url, build_standard_plan_fallback_headers,

apps/aether-gateway/src/cache/mod.rs

@@ -4,6 +4,7 @@ mod auth_runtime;
 mod candidate_page;
 mod dashboard_response;
 mod direct_plan_bypass;
+mod overview_total;
 mod scheduler_affinity;
 mod system_config;
 
@@ -30,6 +31,7 @@ pub(crate) use candidate_page::{
 };
 pub(crate) use dashboard_response::DashboardResponseCache;
 pub(crate) use direct_plan_bypass::DirectPlanBypassCache;
+pub(crate) use overview_total::{OverviewTotalCache, OverviewTotalRead};
 pub(crate) use scheduler_affinity::{
     SchedulerAffinityCache, SchedulerAffinitySnapshotEntry, SchedulerAffinityTarget,
 };

apps/aether-gateway/src/cache/overview_total.rs

@@ -0,0 +1,196 @@
+use std::sync::{Arc, Mutex};
+use std::time::{Duration, Instant};
+
+use aether_data_contracts::repository::usage::StoredUsageDashboardAnalytics;
+
+const FRESH_FOR: Duration = Duration::from_secs(5 * 60);
+const FAILURE_BACKOFF: Duration = Duration::from_secs(10);
+
+#[derive(Debug, Default)]
+pub(crate) struct OverviewTotalCache {
+    state: Mutex<CacheState>,
+}
+
+#[derive(Debug, Default)]
+struct CacheState {
+    value: Option<(Instant, Arc<StoredUsageDashboardAnalytics>)>,
+    refreshing: bool,
+    retry_after: Option<Instant>,
+}
+
+pub(crate) enum OverviewTotalRead {
+    Pending,
+    Failed,
+    Ready {
+        snapshot: Arc<StoredUsageDashboardAnalytics>,
+        stale: bool,
+    },
+}
+
+/// Owns the single refresh slot even if the request that launched it disconnects.
+/// Dropping a cancelled or panicking worker also releases the slot with backoff.
+pub(crate) struct OverviewTotalRefresh {
+    cache: Arc<OverviewTotalCache>,
+    completed: bool,
+}
+
+impl OverviewTotalCache {
+    pub(crate) fn read(
+        self: &Arc<Self>,
+        now: Instant,
+    ) -> (OverviewTotalRead, Option<OverviewTotalRefresh>) {
+        let mut state = self.state.lock().unwrap_or_else(|error| error.into_inner());
+        let fresh = state
+            .value
+            .as_ref()
+            .is_some_and(|(at, _)| now.saturating_duration_since(*at) < FRESH_FOR);
+        let retry_allowed = state.retry_after.is_none_or(|after| now >= after);
+        let refresh = if !fresh && !state.refreshing && retry_allowed {
+            state.refreshing = true;
+            Some(OverviewTotalRefresh {
+                cache: Arc::clone(self),
+                completed: false,
+            })
+        } else {
+            None
+        };
+        let result = match &state.value {
+            Some((_, snapshot)) => OverviewTotalRead::Ready {
+                snapshot: Arc::clone(snapshot),
+                stale: !fresh,
+            },
+            None if state.refreshing => OverviewTotalRead::Pending,
+            None => OverviewTotalRead::Failed,
+        };
+        (result, refresh)
+    }
+}
+
+impl OverviewTotalRefresh {
+    pub(crate) fn finish(mut self, snapshot: Option<StoredUsageDashboardAnalytics>, now: Instant) {
+        let mut state = self
+            .cache
+            .state
+            .lock()
+            .unwrap_or_else(|error| error.into_inner());
+        state.refreshing = false;
+        if let Some(snapshot) = snapshot {
+            state.value = Some((now, Arc::new(snapshot)));
+            state.retry_after = None;
+        } else {
+            state.retry_after = Some(now + FAILURE_BACKOFF);
+        }
+        self.completed = true;
+    }
+}
+
+impl Drop for OverviewTotalRefresh {
+    fn drop(&mut self) {
+        if !self.completed {
+            let mut state = self
+                .cache
+                .state
+                .lock()
+                .unwrap_or_else(|error| error.into_inner());
+            state.refreshing = false;
+            state.retry_after = Some(Instant::now() + FAILURE_BACKOFF);
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn snapshot() -> StoredUsageDashboardAnalytics {
+        let mut snapshot = StoredUsageDashboardAnalytics::default();
+        snapshot.total.generated_at = "2026-09-18T00:00:00Z".into();
+        snapshot.total.read_revision = "revision-1".into();
+        snapshot.total.summary.request_count = 42;
+        snapshot
+    }
+
+    #[test]
+    fn concurrent_cold_reads_claim_one_refresh() {
+        let cache = Arc::new(OverviewTotalCache::default());
+        let barrier = Arc::new(std::sync::Barrier::new(16));
+        let now = Instant::now();
+        let workers = (0..16)
+            .map(|_| {
+                let cache = Arc::clone(&cache);
+                let barrier = Arc::clone(&barrier);
+                std::thread::spawn(move || {
+                    barrier.wait();
+                    let (read, refresh) = cache.read(now);
+                    assert!(matches!(read, OverviewTotalRead::Pending));
+                    refresh
+                })
+            })
+            .collect::<Vec<_>>();
+        let mut refreshes = workers
+            .into_iter()
+            .filter_map(|worker| worker.join().unwrap())
+            .collect::<Vec<_>>();
+        assert_eq!(refreshes.len(), 1);
+        refreshes.pop().unwrap().finish(Some(snapshot()), now);
+        let (read, refresh) = cache.read(now);
+        assert!(matches!(
+            read,
+            OverviewTotalRead::Ready { stale: false, .. }
+        ));
+        assert!(refresh.is_none());
+    }
+
+    #[test]
+    fn expiration_returns_original_snapshot_and_failed_refresh_preserves_it() {
+        let cache = Arc::new(OverviewTotalCache::default());
+        let now = Instant::now();
+        cache.read(now).1.unwrap().finish(Some(snapshot()), now);
+        assert!(cache
+            .read(now + FRESH_FOR - Duration::from_secs(1))
+            .1
+            .is_none());
+        let expired = now + FRESH_FOR;
+        let (read, refresh) = cache.read(expired);
+        let OverviewTotalRead::Ready {
+            snapshot: old,
+            stale: true,
+        } = read
+        else {
+            panic!("expired success must remain visible")
+        };
+        assert_eq!(old.total.generated_at, "2026-09-18T00:00:00Z");
+        assert_eq!(old.total.read_revision, "revision-1");
+        assert!(cache.read(expired).1.is_none());
+        refresh.unwrap().finish(None, expired);
+        let (read, retry) = cache.read(expired + FAILURE_BACKOFF - Duration::from_secs(1));
+        let OverviewTotalRead::Ready {
+            snapshot: retained,
+            stale: true,
+        } = read
+        else {
+            panic!("failed refresh must retain stale success")
+        };
+        assert!(Arc::ptr_eq(&old, &retained));
+        assert!(retry.is_none());
+        assert!(cache.read(expired + FAILURE_BACKOFF).1.is_some());
+    }
+
+    #[test]
+    fn cold_failure_and_worker_cancellation_back_off_before_retrying() {
+        let cache = Arc::new(OverviewTotalCache::default());
+        let now = Instant::now();
+        cache.read(now).1.unwrap().finish(None, now);
+        let (read, refresh) = cache.read(now + Duration::from_secs(9));
+        assert!(matches!(read, OverviewTotalRead::Failed));
+        assert!(refresh.is_none());
+        let (read, refresh) = cache.read(now + FAILURE_BACKOFF);
+        assert!(matches!(read, OverviewTotalRead::Pending));
+        drop(refresh);
+        let after_cancel = Instant::now();
+        let (read, refresh) = cache.read(after_cancel);
+        assert!(matches!(read, OverviewTotalRead::Failed));
+        assert!(refresh.is_none());
+        assert!(cache.read(after_cancel + FAILURE_BACKOFF).1.is_some());
+    }
+}

apps/aether-gateway/src/constants.rs

@@ -126,6 +126,7 @@ pub(crate) const RUST_FRONTDOOR_OWNED_ROUTE_PATTERNS: &[&str] = &[
     "/v1/messages/count_tokens",
     "/v1/responses",
     "/v1/responses/compact",
+    "/v1/memories/trace_summarize",
     "/v1/realtime",
     "/v1/realtime/calls",
     "/v1/live",

apps/aether-gateway/src/control/route/admin/basic_families.rs

@@ -7,6 +7,35 @@ pub(super) fn classify_admin_basic_family_route(
     normalized_path: &str,
     normalized_path_no_trailing: &str,
 ) -> Option<ClassifiedRoute> {
+    let finance_path = normalized_path_no_trailing;
+    if (method == http::Method::GET
+        && matches!(
+            finance_path,
+            "/api/admin/billing/provider-accounts" | "/api/admin/billing/provider-expenses"
+        ))
+        || (method == http::Method::POST && finance_path == "/api/admin/billing/provider-expenses")
+        || (method == http::Method::POST
+            && finance_path
+                .strip_prefix("/api/admin/billing/provider-expenses/")
+                .and_then(|v| v.strip_suffix("/void"))
+                .is_some_and(|id| !id.is_empty() && !id.contains('/')))
+    {
+        return Some(classified(
+            "admin_proxy",
+            "billing_manage",
+            if finance_path.ends_with("/provider-accounts") {
+                "provider_accounts"
+            } else if method == http::Method::GET {
+                "provider_expenses"
+            } else if finance_path.ends_with("/void") {
+                "void_provider_expense"
+            } else {
+                "create_provider_expense"
+            },
+            "admin:billing",
+            false,
+        ));
+    }
     if method == http::Method::GET
         && matches!(
             normalized_path,

apps/aether-gateway/src/control/route/admin/endpoints_families.rs

@@ -6,6 +6,33 @@ pub(super) fn classify_admin_endpoints_family_route(
     method: &http::Method,
     normalized_path: &str,
 ) -> Option<ClassifiedRoute> {
+    if normalized_path == "/api/admin/endpoints/health/v2/publication"
+        && (method == http::Method::GET || method == http::Method::PUT)
+    {
+        return Some(classified(
+            "admin_proxy",
+            "endpoints_health",
+            "health_v2_publication",
+            "admin:endpoints_health",
+            false,
+        ));
+    }
+    if method == http::Method::GET
+        && (matches!(
+            normalized_path,
+            "/api/admin/endpoints/health/v2/summary" | "/api/admin/endpoints/health/v2/objects"
+        ) || normalized_path
+            .strip_prefix("/api/admin/endpoints/health/v2/objects/")
+            .is_some_and(|id| !id.is_empty() && !id.contains('/')))
+    {
+        return Some(classified(
+            "admin_proxy",
+            "endpoints_health",
+            "health_v2",
+            "admin:endpoints_health",
+            false,
+        ));
+    }
     if method == http::Method::GET && normalized_path == "/api/admin/endpoints/health/summary" {
         Some(classified(
             "admin_proxy",

apps/aether-gateway/src/control/route/admin/observability_families.rs

@@ -7,6 +7,15 @@ pub(super) fn classify_admin_observability_family_route(
     normalized_path: &str,
     normalized_path_no_trailing: &str,
 ) -> Option<ClassifiedRoute> {
+    if let Some(kind) = classify_overview_route(method, normalized_path_no_trailing) {
+        return Some(classified(
+            "admin_proxy",
+            "overview_manage",
+            kind,
+            "admin:stats",
+            false,
+        ));
+    }
     if method == http::Method::POST
         && matches!(
             normalized_path,
@@ -727,3 +736,32 @@ pub(super) fn classify_admin_observability_family_route(
         None
     }
 }
+
+fn classify_overview_route(method: &http::Method, path: &str) -> Option<&'static str> {
+    if method != http::Method::GET {
+        return None;
+    }
+    match path.strip_prefix("/api/admin/overview/")? {
+        "dashboard" => Some("dashboard"),
+        "dashboard/summary" => Some("dashboard_summary"),
+        "dashboard/total" => Some("dashboard_total"),
+        "dashboard/charts" => Some("dashboard_charts"),
+        "summary" => Some("summary"),
+        "timeseries" => Some("timeseries"),
+        "breakdown" => Some("breakdown"),
+        "users" => Some("users"),
+        "consumption" => Some("consumption"),
+        "costs" => Some("costs"),
+        "operations/live" => Some("operations_live"),
+        "operations/performance" => Some("operations_performance"),
+        "operations/resources" => Some("operations_resources"),
+        detail
+            if detail
+                .strip_prefix("users/")
+                .is_some_and(|id| !id.is_empty() && !id.contains('/')) =>
+        {
+            Some("user_detail")
+        }
+        _ => None,
+    }
+}

apps/aether-gateway/src/control/route/ai.rs

@@ -88,6 +88,11 @@ pub(super) fn classify_ai_public_route(
                 true,
             ))
         }
+    } else if method == http::Method::POST && normalized_path == "/v1/memories/trace_summarize" {
+        Some(
+            classified("ai_public", "openai", "memories", "openai:responses", true)
+                .with_api_operation(ApiOperation::OpenAiMemoriesSummarize),
+        )
     } else if method == http::Method::POST && normalized_path == "/v1/alpha/search" {
         Some(classified(
             "ai_public",

apps/aether-gateway/src/control/route/public_support.rs

@@ -146,6 +146,36 @@ pub(super) fn classify_public_support_route(
             "public:announcements",
             false,
         ))
+    } else if method == http::Method::GET
+        && (matches!(
+            normalized_path,
+            "/api/users/me/health/v2/summary" | "/api/users/me/health/v2/objects"
+        ) || normalized_path
+            .strip_prefix("/api/users/me/health/v2/objects/")
+            .is_some_and(|id| !id.is_empty() && !id.contains('/')))
+    {
+        Some(classified(
+            "public_support",
+            "health_user",
+            "health_v2",
+            "user:health",
+            false,
+        ))
+    } else if method == http::Method::GET
+        && (matches!(
+            normalized_path,
+            "/api/public/health/v2/summary" | "/api/public/health/v2/objects"
+        ) || normalized_path
+            .strip_prefix("/api/public/health/v2/objects/")
+            .is_some_and(|id| !id.is_empty() && !id.contains('/')))
+    {
+        Some(classified(
+            "public_support",
+            "public_catalog",
+            "health_v2",
+            "public:catalog",
+            false,
+        ))
     } else if method == http::Method::GET
         && matches!(
             normalized_path,
@@ -273,6 +303,19 @@ pub(super) fn classify_public_support_route(
             "user:monitoring",
             false,
         ))
+    } else if method == http::Method::GET
+        && matches!(
+            normalized_path,
+            "/api/announcements/users/me" | "/api/announcements/users/me/"
+        )
+    {
+        Some(classified(
+            "public_support",
+            "announcement_user",
+            "list",
+            "user:announcements",
+            false,
+        ))
     } else if method == http::Method::GET
         && matches!(
             normalized_path,

apps/aether-gateway/src/control/tests/admin_billing.rs

@@ -203,3 +203,50 @@ fn admin_billing_plan_write_routes_buffer_request_body() {
         );
     }
 }
+
+#[test]
+fn provider_finance_routes_require_admin_billing_and_buffer_expense_input() {
+    let headers = headers(&[]);
+    for (method, path, kind) in [
+        (
+            http::Method::GET,
+            "/api/admin/billing/provider-accounts",
+            "provider_accounts",
+        ),
+        (
+            http::Method::GET,
+            "/api/admin/billing/provider-expenses",
+            "provider_expenses",
+        ),
+        (
+            http::Method::POST,
+            "/api/admin/billing/provider-expenses",
+            "create_provider_expense",
+        ),
+        (
+            http::Method::POST,
+            "/api/admin/billing/provider-expenses/entry-1/void",
+            "void_provider_expense",
+        ),
+    ] {
+        let uri: Uri = path.parse().unwrap();
+        let decision = classify_control_route(&method, &uri, &headers).unwrap();
+        assert_eq!(decision.route_family.as_deref(), Some("billing_manage"));
+        assert_eq!(decision.route_kind.as_deref(), Some(kind));
+        assert_eq!(
+            decision.auth_endpoint_signature.as_deref(),
+            Some("admin:billing")
+        );
+        let context = GatewayPublicRequestContext::from_request_parts(
+            "expense-test",
+            &method,
+            &uri,
+            &headers,
+            Some(decision),
+        );
+        assert_eq!(
+            local_proxy_route_requires_buffered_body(&context),
+            kind == "create_provider_expense"
+        );
+    }
+}

apps/aether-gateway/src/control/tests/admin_stats.rs

@@ -2,6 +2,46 @@ use http::Uri;
 
 use super::{classify_control_route, headers};
 
+#[test]
+fn overview_routes_require_the_admin_stats_principal_and_get_method() {
+    for (suffix, kind) in [
+        ("dashboard", "dashboard"),
+        ("dashboard/summary", "dashboard_summary"),
+        ("dashboard/total", "dashboard_total"),
+        ("dashboard/charts", "dashboard_charts"),
+        ("summary", "summary"),
+        ("timeseries", "timeseries"),
+        ("breakdown", "breakdown"),
+        ("users", "users"),
+        ("users/employee-1", "user_detail"),
+        ("consumption", "consumption"),
+        ("costs", "costs"),
+        ("operations/live", "operations_live"),
+        ("operations/performance", "operations_performance"),
+        ("operations/resources", "operations_resources"),
+    ] {
+        for trailing in ["", "/"] {
+            let uri: Uri = format!("/api/admin/overview/{suffix}{trailing}")
+                .parse()
+                .unwrap();
+            let decision = classify_control_route(&http::Method::GET, &uri, &headers(&[])).unwrap();
+            assert_eq!(decision.route_family.as_deref(), Some("overview_manage"));
+            assert_eq!(decision.route_kind.as_deref(), Some(kind));
+            assert_eq!(
+                decision.auth_endpoint_signature.as_deref(),
+                Some("admin:stats")
+            );
+            assert!(!decision.is_execution_runtime_candidate());
+            let decision = classify_control_route(&http::Method::POST, &uri, &headers(&[]));
+            assert!(
+                decision.is_none_or(
+                    |decision| decision.route_family.as_deref() != Some("overview_manage")
+                )
+            );
+        }
+    }
+}
+
 #[test]
 fn classifies_admin_stats_provider_quota_usage_as_admin_proxy_route() {
     let headers = headers(&[]);

apps/aether-gateway/src/control/tests/public_support.rs

@@ -261,6 +261,27 @@ fn classifies_wallet_redeem_as_public_support_route() {
     );
 }
 
+#[test]
+fn classifies_personal_announcements_as_authenticated_user_route() {
+    let headers = headers(&[]);
+    for path in [
+        "/api/announcements/users/me?limit=20&offset=0&unread_only=false",
+        "/api/announcements/users/me/",
+    ] {
+        let uri: Uri = path.parse().expect("uri should parse");
+        let decision = classify_control_route(&http::Method::GET, &uri, &headers)
+            .expect("route should classify");
+        assert_eq!(decision.route_class.as_deref(), Some("public_support"));
+        assert_eq!(decision.route_family.as_deref(), Some("announcement_user"));
+        assert_eq!(decision.route_kind.as_deref(), Some("list"));
+        assert_eq!(
+            decision.auth_endpoint_signature.as_deref(),
+            Some("user:announcements")
+        );
+        assert!(!decision.is_execution_runtime_candidate());
+    }
+}
+
 #[test]
 fn classifies_announcement_unread_count_as_public_support_route() {
     let headers = headers(&[]);

apps/aether-gateway/src/data/state/auth.rs

@@ -1252,6 +1252,7 @@ impl GatewayDataState {
         // exists while avoiding an unbounded read during error compensation.
         let page = repository
             .list_admin_wallets(&aether_data::repository::wallet::AdminWalletListQuery {
+                user_id: None,
                 status: None,
                 owner_type: Some("api_key".to_string()),
                 limit: 1,

apps/aether-gateway/src/data/state/runtime.rs

@@ -43,6 +43,9 @@ use super::{
     VideoTaskStatusCount, WalletDailyUsageAggregationInput, WalletDailyUsageAggregationResult,
     WalletLookupKey, WalletMutationOutcome,
 };
+use aether_data_contracts::repository::billing::{
+    ProviderExpenseInput, ProviderExpensePage, ProviderExpenseQuery, ProviderExpenseRecord,
+};
 use aether_data_contracts::repository::usage::{
     PendingUsageCleanupSummary, ProviderApiKeyWindowUsageRequest,
     StoredProviderApiKeyWindowUsageSummary, StoredUsageDailySummary, UsageAuditListQuery,
@@ -366,6 +369,26 @@ impl GatewayDataState {
         }
     }
 
+    pub(crate) async fn rebuild_overview_buckets(
+        &self,
+        input: &aether_data::StatsHourlyAggregationInput,
+    ) -> Result<usize, DataLayerError> {
+        match &self.backends {
+            Some(backends) => backends.rebuild_overview_buckets(input).await,
+            None => Ok(0),
+        }
+    }
+
+    pub(crate) async fn drain_overview_dirty_events(
+        &self,
+        now: chrono::DateTime<chrono::Utc>,
+    ) -> Result<u64, DataLayerError> {
+        match &self.backends {
+            Some(backends) => backends.drain_overview_dirty_events(now).await,
+            None => Ok(0),
+        }
+    }
+
     pub(crate) async fn aggregate_stats_daily(
         &self,
         input: &aether_data::StatsDailyAggregationInput,
@@ -386,6 +409,18 @@ impl GatewayDataState {
         }
     }
 
+    pub(crate) async fn list_user_announcements(
+        &self,
+        user_id: &str,
+        query: &aether_data::repository::announcements::UserAnnouncementListQuery,
+    ) -> Result<aether_data::repository::announcements::StoredUserAnnouncementPage, DataLayerError>
+    {
+        match &self.announcement_reader {
+            Some(repository) => repository.list_user_announcements(user_id, query).await,
+            None => Ok(Default::default()),
+        }
+    }
+
     pub(crate) async fn find_announcement_by_id(
         &self,
         announcement_id: &str,
@@ -1729,6 +1764,60 @@ impl GatewayDataState {
         }
     }
 
+    pub(crate) async fn query_dashboard_summary(
+        &self,
+        query: &aether_data_contracts::repository::usage::UsageDashboardAnalyticsQuery,
+    ) -> Result<aether_data_contracts::repository::usage::StoredDashboardSummary, DataLayerError>
+    {
+        match &self.usage_reader {
+            Some(repository) => repository.query_dashboard_summary(query).await,
+            None => Err(DataLayerError::InvalidInput(
+                "dashboard summary repository is unavailable".into(),
+            )),
+        }
+    }
+
+    pub(crate) async fn query_dashboard_analytics(
+        &self,
+        query: &aether_data_contracts::repository::usage::UsageDashboardAnalyticsQuery,
+    ) -> Result<
+        aether_data_contracts::repository::usage::StoredUsageDashboardAnalytics,
+        DataLayerError,
+    > {
+        match &self.usage_reader {
+            Some(repository) => repository.query_dashboard_analytics(query).await,
+            None => Err(DataLayerError::InvalidInput(
+                "usage analytics repository is unavailable".into(),
+            )),
+        }
+    }
+
+    pub(crate) async fn query_usage_analytics(
+        &self,
+        query: &aether_data_contracts::repository::usage::UsageAnalyticsQuery,
+    ) -> Result<aether_data_contracts::repository::usage::StoredUsageAnalytics, DataLayerError>
+    {
+        match &self.usage_reader {
+            Some(repository) => repository.query_usage_analytics(query).await,
+            None => Err(DataLayerError::InvalidInput(
+                "usage analytics repository is unavailable".into(),
+            )),
+        }
+    }
+
+    pub(crate) async fn summarize_health_observations(
+        &self,
+        query: &aether_data_contracts::repository::usage::HealthObservationQuery,
+    ) -> Result<aether_data_contracts::repository::usage::HealthObservationSummary, DataLayerError>
+    {
+        match &self.usage_reader {
+            Some(repository) => repository.summarize_health_observations(query).await,
+            None => Err(DataLayerError::InvalidInput(
+                "health observations repository is unavailable".into(),
+            )),
+        }
+    }
+
     pub(crate) async fn summarize_usage_audits(
         &self,
         query: &aether_data_contracts::repository::usage::UsageAuditSummaryQuery,
@@ -2817,6 +2906,35 @@ impl GatewayDataState {
         }
     }
 
+    pub(crate) async fn list_provider_expenses(
+        &self,
+        query: &ProviderExpenseQuery,
+    ) -> Result<Option<ProviderExpensePage>, DataLayerError> {
+        match &self.billing_reader {
+            Some(repo) => repo.list_provider_expenses(query).await,
+            None => Ok(None),
+        }
+    }
+    pub(crate) async fn create_provider_expense(
+        &self,
+        input: &ProviderExpenseInput,
+    ) -> Result<AdminBillingMutationOutcome<ProviderExpenseRecord>, DataLayerError> {
+        match &self.billing_reader {
+            Some(repo) => repo.create_provider_expense(input).await,
+            None => Ok(AdminBillingMutationOutcome::Unavailable),
+        }
+    }
+    pub(crate) async fn void_provider_expense(
+        &self,
+        id: &str,
+        operator: Option<&str>,
+    ) -> Result<AdminBillingMutationOutcome<ProviderExpenseRecord>, DataLayerError> {
+        match &self.billing_reader {
+            Some(repo) => repo.void_provider_expense(id, operator).await,
+            None => Ok(AdminBillingMutationOutcome::Unavailable),
+        }
+    }
+
     pub(crate) async fn list_billing_plans(
         &self,
         include_disabled: bool,
@@ -2889,6 +3007,21 @@ impl GatewayDataState {
         }
     }
 
+    pub(crate) async fn list_user_plan_entitlements_with_history(
+        &self,
+        user_id: &str,
+        include_inactive: bool,
+    ) -> Result<Option<Vec<UserPlanEntitlementRecord>>, DataLayerError> {
+        match &self.billing_reader {
+            Some(repository) => {
+                repository
+                    .list_user_plan_entitlements_with_history(user_id, include_inactive)
+                    .await
+            }
+            None => Ok(None),
+        }
+    }
+
     pub(crate) async fn revoke_user_plan_entitlement(
         &self,
         user_id: &str,

apps/aether-gateway/src/execution_activity.rs

@@ -0,0 +1,538 @@
+//! Node-local, request-deduplicated activity for provider and requested-model analysis.
+//!
+//! RPM counts distinct requests entering upstream execution in the last 60 seconds;
+//! it is never extrapolated from a shorter observation window. Concurrency follows
+//! guard lifetimes, including streams, independently of that window. Expiration is
+//! ordered rather than scanning request history on each lifecycle event.
+use std::cmp::Reverse;
+use std::collections::{BinaryHeap, HashMap};
+use std::sync::{Arc, Mutex};
+use std::time::Instant;
+
+use chrono::{DateTime, Utc};
+use serde_json::{json, Value};
+
+const WINDOW_US: u64 = 60_000_000;
+const MAX_REQUESTS: usize = 100_000;
+const MAX_REQUEST_DIMENSIONS: usize = 200_000;
+const MAX_LABEL_BYTES: usize = 512;
+
+#[derive(Debug, Default)]
+struct Counts {
+    recent: u64,
+    active: u64,
+    provider_name: Option<Arc<str>>,
+}
+
+impl Counts {
+    fn empty(&self) -> bool {
+        self.recent == 0 && self.active == 0
+    }
+}
+
+#[derive(Debug)]
+struct ProviderRequest {
+    active: u64,
+}
+
+#[derive(Debug)]
+struct Request {
+    model: Option<Arc<str>>,
+    active: u64,
+    providers: HashMap<Arc<str>, ProviderRequest>,
+    idle_since: Option<u64>,
+    cleanup_scheduled: bool,
+}
+
+#[derive(Debug, Eq, PartialEq, Ord, PartialOrd)]
+enum Expiration {
+    Model(Arc<str>),
+    Provider(Arc<str>, Arc<str>),
+    Request(Arc<str>),
+}
+
+#[derive(Debug, Default)]
+struct History {
+    through_us: u64,
+    requests: HashMap<Arc<str>, Request>,
+    providers: HashMap<Arc<str>, Counts>,
+    models: HashMap<Option<Arc<str>>, Counts>,
+    expirations: BinaryHeap<Reverse<(u64, Expiration)>>,
+    request_dimensions: usize,
+    untracked_active: u64,
+    incomplete_until_us: u64,
+}
+
+impl History {
+    fn advance(&mut self, now_us: u64) {
+        self.through_us = self.through_us.max(now_us);
+        while self
+            .expirations
+            .peek()
+            .is_some_and(|Reverse((expires_at, _))| *expires_at <= self.through_us)
+        {
+            let Reverse((_, expiration)) = self.expirations.pop().expect("expiration exists");
+            match expiration {
+                Expiration::Model(request_id) => {
+                    let Some(request) = self.requests.get_mut(&request_id) else {
+                        continue;
+                    };
+                    if let Some(counts) = self.models.get_mut(&request.model) {
+                        counts.recent = counts.recent.saturating_sub(1);
+                        if counts.empty() {
+                            self.models.remove(&request.model);
+                        }
+                    }
+                }
+                Expiration::Provider(request_id, provider_id) => {
+                    let Some(request) = self.requests.get(&request_id) else {
+                        continue;
+                    };
+                    if !request.providers.contains_key(&provider_id) {
+                        continue;
+                    }
+                    if let Some(counts) = self.providers.get_mut(&provider_id) {
+                        counts.recent = counts.recent.saturating_sub(1);
+                        if counts.empty() {
+                            self.providers.remove(&provider_id);
+                        }
+                    }
+                }
+                Expiration::Request(request_id) => {
+                    let Some(request) = self.requests.get_mut(&request_id) else {
+                        continue;
+                    };
+                    request.cleanup_scheduled = false;
+                    if let Some(idle_since) = request.idle_since {
+                        let expires_at = idle_since.saturating_add(WINDOW_US);
+                        if expires_at <= self.through_us {
+                            self.request_dimensions -= request.providers.len() + 1;
+                            self.requests.remove(&request_id);
+                        } else {
+                            // A retry reused the record while its first cleanup was
+                            // pending. Keep at most one cleanup entry per request.
+                            request.cleanup_scheduled = true;
+                            self.expirations
+                                .push(Reverse((expires_at, Expiration::Request(request_id))));
+                        }
+                    }
+                }
+            }
+        }
+    }
+
+    fn begin(
+        &mut self,
+        now_us: u64,
+        request_id: &str,
+        provider_id: &str,
+        provider_name: Option<&str>,
+        requested_model: Option<&str>,
+    ) -> GuardIdentity {
+        self.advance(now_us);
+        let existing = self.requests.get(request_id);
+        let new_request = existing.is_none();
+        let new_provider = existing.is_none_or(|r| !r.providers.contains_key(provider_id));
+        let new_dimensions = usize::from(new_request) + usize::from(new_provider);
+        let valid_labels = !request_id.is_empty()
+            && !provider_id.is_empty()
+            && [
+                Some(request_id),
+                Some(provider_id),
+                provider_name,
+                requested_model,
+            ]
+            .into_iter()
+            .flatten()
+            .all(|label| label.len() <= MAX_LABEL_BYTES);
+        if !valid_labels
+            || (new_request && self.requests.len() >= MAX_REQUESTS)
+            || self.request_dimensions.saturating_add(new_dimensions) > MAX_REQUEST_DIMENSIONS
+        {
+            // Telemetry must not affect admission. Explicitly mark incomplete
+            // coverage instead of silently returning plausible but partial counts.
+            self.untracked_active += 1;
+            self.incomplete_until_us = self.through_us.saturating_add(WINDOW_US);
+            return GuardIdentity::Untracked;
+        }
+
+        let request_id: Arc<str> = self
+            .requests
+            .get_key_value(request_id)
+            .map(|(key, _)| Arc::clone(key))
+            .unwrap_or_else(|| Arc::from(request_id));
+        let request = self
+            .requests
+            .entry(Arc::clone(&request_id))
+            .or_insert_with(|| Request {
+                model: requested_model
+                    .filter(|model| !model.is_empty())
+                    .map(Arc::from),
+                active: 0,
+                providers: HashMap::new(),
+                idle_since: None,
+                cleanup_scheduled: false,
+            });
+        let model_counts = self.models.entry(request.model.clone()).or_default();
+        if new_request {
+            model_counts.recent += 1;
+            self.expirations.push(Reverse((
+                self.through_us.saturating_add(WINDOW_US),
+                Expiration::Model(Arc::clone(&request_id)),
+            )));
+        }
+        if request.active == 0 {
+            model_counts.active += 1;
+        }
+        request.active += 1;
+        request.idle_since = None;
+
+        let provider_id: Arc<str> = request
+            .providers
+            .get_key_value(provider_id)
+            .map(|(key, _)| Arc::clone(key))
+            .unwrap_or_else(|| Arc::from(provider_id));
+        let provider = request
+            .providers
+            .entry(Arc::clone(&provider_id))
+            .or_insert(ProviderRequest { active: 0 });
+        let provider_counts = self.providers.entry(Arc::clone(&provider_id)).or_default();
+        if let Some(name) = provider_name.filter(|name| !name.is_empty()) {
+            provider_counts.provider_name = Some(Arc::from(name));
+        }
+        if new_provider {
+            provider_counts.recent += 1;
+            self.expirations.push(Reverse((
+                self.through_us.saturating_add(WINDOW_US),
+                Expiration::Provider(Arc::clone(&request_id), Arc::clone(&provider_id)),
+            )));
+        }
+        if provider.active == 0 {
+            provider_counts.active += 1;
+        }
+        provider.active += 1;
+        self.request_dimensions += new_dimensions;
+        GuardIdentity::Tracked {
+            request_id,
+            provider_id,
+        }
+    }
+
+    fn release(&mut self, now_us: u64, identity: GuardIdentity) {
+        self.advance(now_us);
+        let GuardIdentity::Tracked {
+            request_id,
+            provider_id,
+        } = identity
+        else {
+            self.untracked_active = self.untracked_active.saturating_sub(1);
+            return;
+        };
+        let Some(request) = self.requests.get_mut(&request_id) else {
+            return;
+        };
+        let Some(provider) = request.providers.get_mut(&provider_id) else {
+            return;
+        };
+        provider.active = provider.active.saturating_sub(1);
+        if provider.active == 0 {
+            if let Some(counts) = self.providers.get_mut(&provider_id) {
+                counts.active = counts.active.saturating_sub(1);
+                if counts.empty() {
+                    self.providers.remove(&provider_id);
+                }
+            }
+        }
+        request.active = request.active.saturating_sub(1);
+        if request.active == 0 {
+            if let Some(counts) = self.models.get_mut(&request.model) {
+                counts.active = counts.active.saturating_sub(1);
+                if counts.empty() {
+                    self.models.remove(&request.model);
+                }
+            }
+            // Retain deduplication briefly after completion as failover may begin
+            // after the old guard drops, including after a >60-second attempt.
+            request.idle_since = Some(self.through_us);
+            if !request.cleanup_scheduled {
+                request.cleanup_scheduled = true;
+                self.expirations.push(Reverse((
+                    self.through_us.saturating_add(WINDOW_US),
+                    Expiration::Request(request_id),
+                )));
+            }
+        }
+    }
+
+    fn snapshot(&mut self, now_us: u64, started_at_us: i64) -> Value {
+        self.advance(now_us);
+        let mut providers: Vec<_> = self.providers.iter().collect();
+        providers.sort_unstable_by_key(|(provider, _)| *provider);
+        let mut models: Vec<_> = self.models.iter().collect();
+        models.sort_unstable_by_key(|(model, _)| *model);
+        json!({
+            "observed_at": DateTime::from_timestamp_micros(started_at_us.saturating_add(self.through_us.min(i64::MAX as u64) as i64)),
+            "observed_from": DateTime::from_timestamp_micros(started_at_us),
+            "window_seconds": 60,
+            "observed_window_seconds": (self.through_us as f64 / 1_000_000.0).min(60.0),
+            "scope": {"kind": "node"},
+            "measurement": "http_and_responses_websocket_requests",
+            "coverage": if self.untracked_active > 0 || self.through_us < self.incomplete_until_us { "partial" } else { "complete" },
+            "providers": providers.into_iter().map(|(id, counts)| json!({
+                "provider_id": id.as_ref(),
+                "provider": counts.provider_name.as_deref().unwrap_or(id.as_ref()),
+                "requests_per_minute": counts.recent,
+                "current_concurrency": counts.active,
+            })).collect::<Vec<_>>(),
+            "models": models.into_iter().map(|(model, counts)| json!({
+                "model": model.as_deref(),
+                "requests_per_minute": counts.recent,
+                "current_concurrency": counts.active,
+            })).collect::<Vec<_>>(),
+        })
+    }
+}
+
+#[derive(Debug)]
+pub(crate) struct ExecutionActivity {
+    started_at: Instant,
+    started_at_us: i64,
+    history: Mutex<History>,
+}
+
+impl Default for ExecutionActivity {
+    fn default() -> Self {
+        Self {
+            started_at: Instant::now(),
+            started_at_us: Utc::now().timestamp_micros(),
+            history: Mutex::new(History::default()),
+        }
+    }
+}
+
+impl ExecutionActivity {
+    fn elapsed_us(&self) -> u64 {
+        self.started_at.elapsed().as_micros().min(u64::MAX as u128) as u64
+    }
+
+    pub(crate) fn begin(
+        self: &Arc<Self>,
+        request_id: &str,
+        provider_id: &str,
+        provider_name: Option<&str>,
+        requested_model: Option<&str>,
+    ) -> ExecutionActivityGuard {
+        let identity = self
+            .history
+            .lock()
+            .unwrap_or_else(|e| e.into_inner())
+            .begin(
+                self.elapsed_us(),
+                request_id,
+                provider_id,
+                provider_name,
+                requested_model,
+            );
+        ExecutionActivityGuard {
+            activity: Arc::clone(self),
+            identity: Some(identity),
+        }
+    }
+
+    pub(crate) fn snapshot(&self) -> Value {
+        self.history
+            .lock()
+            .unwrap_or_else(|e| e.into_inner())
+            .snapshot(self.elapsed_us(), self.started_at_us)
+    }
+}
+
+#[derive(Debug)]
+enum GuardIdentity {
+    Tracked {
+        request_id: Arc<str>,
+        provider_id: Arc<str>,
+    },
+    Untracked,
+}
+
+#[derive(Debug)]
+pub(crate) struct ExecutionActivityGuard {
+    activity: Arc<ExecutionActivity>,
+    identity: Option<GuardIdentity>,
+}
+
+impl Drop for ExecutionActivityGuard {
+    fn drop(&mut self) {
+        if let Some(identity) = self.identity.take() {
+            self.activity
+                .history
+                .lock()
+                .unwrap_or_else(|e| e.into_inner())
+                .release(self.activity.elapsed_us(), identity);
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn begin(history: &mut History, at_us: u64, id: &str, provider: &str) -> GuardIdentity {
+        history.begin(at_us, id, provider, Some(provider), Some("requested-model"))
+    }
+
+    fn value(history: &mut History, at_us: u64) -> Value {
+        history.snapshot(at_us, 0)
+    }
+
+    #[test]
+    fn rpm_has_an_exact_rolling_window_and_never_extrapolates_startup() {
+        let mut history = History::default();
+        let a = begin(&mut history, 0, "a", "provider");
+        history.release(1, a);
+        let b = begin(&mut history, 30_000_000, "b", "provider");
+        history.release(30_000_001, b);
+        let early = value(&mut history, 30_000_001);
+        assert_eq!(early["providers"][0]["requests_per_minute"], 2);
+        assert_eq!(early["coverage"], "complete");
+        assert!(early["observed_window_seconds"].as_f64().unwrap() < 60.0);
+        assert_eq!(
+            value(&mut history, WINDOW_US - 1)["providers"][0]["requests_per_minute"],
+            2
+        );
+        assert_eq!(
+            value(&mut history, WINDOW_US)["providers"][0]["requests_per_minute"],
+            1
+        );
+        assert!(value(&mut history, 90_000_000)["providers"]
+            .as_array()
+            .unwrap()
+            .is_empty());
+        assert_eq!(
+            value(&mut history, 90_000_000)["observed_window_seconds"],
+            60.0
+        );
+    }
+
+    #[test]
+    fn overlapping_guards_and_sequential_retries_count_one_request() {
+        let mut history = History::default();
+        let a = begin(&mut history, 0, "request", "provider");
+        let b = begin(&mut history, 1, "request", "provider");
+        let c = begin(&mut history, 2, "other-request", "provider");
+        assert_eq!(
+            value(&mut history, 2)["providers"][0]["current_concurrency"],
+            2
+        );
+        assert_eq!(
+            value(&mut history, 2)["providers"][0]["requests_per_minute"],
+            2
+        );
+        history.release(3, a);
+        assert_eq!(
+            value(&mut history, 3)["models"][0]["current_concurrency"],
+            2
+        );
+        history.release(4, b);
+        history.release(5, c);
+        let retry = begin(&mut history, 6, "request", "provider");
+        let result = value(&mut history, 6);
+        assert_eq!(result["providers"][0]["requests_per_minute"], 2);
+        assert_eq!(result["models"][0]["current_concurrency"], 1);
+        history.release(7, retry);
+    }
+
+    #[test]
+    fn failover_counts_each_provider_but_deduplicates_the_requested_model() {
+        let mut history = History::default();
+        let first = begin(&mut history, 0, "request", "first");
+        let second = begin(&mut history, 1, "request", "second");
+        let result = value(&mut history, 2);
+        assert_eq!(result["providers"].as_array().unwrap().len(), 2);
+        assert_eq!(result["providers"][0]["requests_per_minute"], 1);
+        assert_eq!(result["providers"][1]["current_concurrency"], 1);
+        assert_eq!(result["models"][0]["requests_per_minute"], 1);
+        assert_eq!(result["models"][0]["current_concurrency"], 1);
+        history.release(3, first);
+        history.release(4, second);
+    }
+
+    #[test]
+    fn long_stream_retains_concurrency_and_retry_does_not_restart_model_rpm() {
+        let mut history = History::default();
+        let stream = begin(&mut history, 0, "request", "provider");
+        let result = value(&mut history, 2 * WINDOW_US);
+        assert_eq!(result["providers"][0]["requests_per_minute"], 0);
+        assert_eq!(result["models"][0]["current_concurrency"], 1);
+        history.release(2 * WINDOW_US + 1, stream);
+        let retry = begin(&mut history, 2 * WINDOW_US + 2, "request", "provider");
+        let result = value(&mut history, 2 * WINDOW_US + 2);
+        assert_eq!(result["providers"][0]["requests_per_minute"], 0);
+        assert_eq!(result["models"][0]["requests_per_minute"], 0);
+        assert_eq!(result["models"][0]["current_concurrency"], 1);
+        history.release(2 * WINDOW_US + 3, retry);
+        assert!(value(&mut history, 3 * WINDOW_US + 3)["models"]
+            .as_array()
+            .unwrap()
+            .is_empty());
+        assert!(history.requests.is_empty());
+        assert!(history.expirations.is_empty());
+        assert_eq!(history.request_dimensions, 0);
+    }
+
+    #[test]
+    fn cancellation_drop_releases_concurrency_but_keeps_rpm() {
+        let activity = Arc::new(ExecutionActivity::default());
+        let guard = activity.begin("request", "provider", Some("Provider name"), None);
+        assert_eq!(
+            activity.snapshot()["providers"][0]["current_concurrency"],
+            1
+        );
+        drop(guard);
+        let result = activity.snapshot();
+        assert_eq!(result["providers"][0]["current_concurrency"], 0);
+        assert_eq!(result["providers"][0]["requests_per_minute"], 1);
+        assert_eq!(result["providers"][0]["provider"], "Provider name");
+        assert!(result["models"][0]["model"].is_null());
+    }
+
+    #[test]
+    fn retry_cleanup_entries_stay_bounded_and_idle_memory_is_released() {
+        let mut history = History::default();
+        for n in 0..1_000 {
+            let guard = begin(&mut history, n, "request", "provider");
+            history.release(n, guard);
+        }
+        assert_eq!(history.expirations.len(), 3);
+        value(&mut history, WINDOW_US);
+        assert_eq!(history.expirations.len(), 1);
+        assert_eq!(history.requests.len(), 1);
+        value(&mut history, WINDOW_US + 1_000);
+        assert!(history.requests.is_empty());
+        assert!(history.providers.is_empty());
+        assert!(history.models.is_empty());
+        assert!(history.expirations.is_empty());
+        assert_eq!(history.request_dimensions, 0);
+    }
+
+    #[test]
+    fn sampling_limits_report_incomplete_coverage_until_unobserved_work_expires() {
+        let mut history = History::default();
+        history.request_dimensions = MAX_REQUEST_DIMENSIONS;
+        let untracked = begin(&mut history, 0, "request", "provider");
+        assert_eq!(value(&mut history, 1)["coverage"], "partial");
+        assert_eq!(value(&mut history, 2 * WINDOW_US)["coverage"], "partial");
+        history.release(2 * WINDOW_US, untracked);
+        assert_eq!(value(&mut history, 2 * WINDOW_US)["coverage"], "complete");
+        history.request_dimensions = 0;
+        let long_id = "x".repeat(MAX_LABEL_BYTES + 1);
+        let untracked = begin(&mut history, 3 * WINDOW_US, &long_id, "provider");
+        history.release(3 * WINDOW_US, untracked);
+        assert_eq!(
+            value(&mut history, 4 * WINDOW_US - 1)["coverage"],
+            "partial"
+        );
+        assert_eq!(value(&mut history, 4 * WINDOW_US)["coverage"], "complete");
+    }
+}

apps/aether-gateway/src/execution_runtime/attempt_cancellation.rs

@@ -181,6 +181,12 @@ async fn settle_cancelled_attempt(
         usage_data.request_metadata.take(),
         request_diagnostics.as_ref(),
     );
+    usage_data.request_metadata = crate::usage::reporting::failure::with_analytics_failure(
+        usage_data.request_metadata.as_ref(),
+        "unknown",
+        "finalize",
+        "request_task_cancelled",
+    );
     usage_data.status_code = Some(CLIENT_CANCELLED_STATUS_CODE);
     usage_data.error_message = Some(error_message.to_string());
     usage_data.error_category = Some("cancelled".to_string());

apps/aether-gateway/src/execution_runtime/attempt_lifecycle.rs

@@ -668,8 +668,22 @@ impl ExecutionAttemptLifecycle {
         });
 
         // 1. usage terminal
+        let analytics_context = if facts.provider.cancelled_by_provider() {
+            crate::usage::reporting::failure::with_analytics_failure(
+                payload.report_context.as_ref(),
+                "upstream",
+                "stream_read",
+                "provider_cancelled",
+            )
+        } else {
+            crate::usage::reporting::failure::stream_analytics_context(
+                payload.report_context.as_ref(),
+                &payload,
+                facts.delivery.is_aborted() && !facts.provider.is_terminal(),
+            )
+        };
         let context_seed =
-            build_terminal_usage_context_seed(&self.plan, payload.report_context.as_ref());
+            build_terminal_usage_context_seed(&self.plan, analytics_context.as_ref());
         let payload_seed = build_stream_terminal_usage_payload_seed(&payload);
         let billing_void = settlement.billing.is_void();
         let usage_runtime = Arc::clone(&state.usage_runtime);

apps/aether-gateway/src/execution_runtime/fallback.rs

@@ -191,6 +191,7 @@ pub(crate) fn resolve_core_sync_error_finalize_report_kind(
     let report_kind = match plan_kind {
         "openai_chat_sync" => "openai_chat_sync_finalize",
         "openai_responses_sync" => "openai_responses_sync_finalize",
+        "openai_memories_sync" => "openai_memories_sync_finalize",
         "openai_responses_compact_sync" => "openai_responses_compact_sync_finalize",
         "claude_chat_sync" => "claude_chat_sync_finalize",
         "gemini_chat_sync" => "gemini_chat_sync_finalize",
@@ -576,6 +577,14 @@ mod tests {
             error: None,
         };
 
+        assert_eq!(
+            resolve_core_sync_error_finalize_report_kind(
+                "openai_memories_sync",
+                &result,
+                Some(&serde_json::json!({"error":{"message":"synthetic"}}))
+            ),
+            Some("openai_memories_sync_finalize".to_string())
+        );
         for body_json in [
             serde_json::json!({"status": "failed", "error": null}),
             serde_json::json!({"type": "error"}),

apps/aether-gateway/src/execution_runtime/grok.rs

@@ -1114,6 +1114,7 @@ fn grok_canonical_usage(usage: GrokUsageEstimate) -> StreamingCanonicalUsage {
 
 fn grok_standardized_usage(usage: GrokUsageEstimate) -> StandardizedUsage {
     let mut standardized = StandardizedUsage::new();
+    standardized.token_source = Some(aether_contracts::UsageTokenSource::Estimated);
     standardized.input_tokens = i64::try_from(usage.input_tokens).unwrap_or(i64::MAX);
     standardized.output_tokens = i64::try_from(usage.output_tokens).unwrap_or(i64::MAX);
     standardized.reasoning_tokens = i64::try_from(usage.reasoning_tokens).unwrap_or(i64::MAX);
@@ -4576,6 +4577,101 @@ mod tests {
         assert!(adapter.text.contains("[[1]](https://example.com/source"));
     }
 
+    #[test]
+    fn grok_usage_reports_preserve_estimated_provenance_after_wire_roundtrip() {
+        use aether_usage_runtime::{
+            build_stream_terminal_usage_event, build_sync_terminal_usage_event,
+            GatewayStreamReportRequest, GatewaySyncReportRequest, UsageEventType,
+        };
+
+        for (format, report_prefix) in [
+            ("openai:chat", "openai_chat"),
+            ("openai:responses", "openai_responses"),
+        ] {
+            let mut plan = sample_plan(
+                serde_json::json!({
+                    "messages": [{"role": "user", "content": "hello"}]
+                }),
+                format,
+            );
+            plan.stream = false;
+            plan.provider_api_format = format.to_string();
+            // The trusted planner binds this hint to the Grok runtime adapter.
+            // Exercise its transport through the same serialized report as usage.
+            let context = serde_json::json!({
+                "provider_type": "grok",
+                "provider_api_format": format,
+                "client_api_format": format,
+                "usage_token_source": "estimated"
+            });
+            let collected = GrokCollected {
+                status_code: 200,
+                text: "hello back".to_string(),
+                thinking: "short reasoning".to_string(),
+                ..GrokCollected::default()
+            };
+            let expected = grok_usage_estimate(&plan, &collected);
+            let result = grok_execution_result(&plan, collected, Some(&context));
+            let sync_report = GatewaySyncReportRequest {
+                trace_id: plan.request_id.clone(),
+                report_kind: format!("{report_prefix}_sync_success"),
+                report_context: Some(context.clone()),
+                status_code: result.status_code,
+                headers: result.headers,
+                body_json: result.body.and_then(|body| body.json_body),
+                client_body_json: None,
+                body_base64: None,
+                telemetry: result.telemetry,
+            };
+            let sync_report: GatewaySyncReportRequest =
+                serde_json::from_slice(&serde_json::to_vec(&sync_report).unwrap()).unwrap();
+            let sync_event = build_sync_terminal_usage_event(
+                &plan,
+                sync_report.report_context.as_ref(),
+                &sync_report,
+            )
+            .unwrap();
+
+            plan.stream = true;
+            let stream_report = GatewayStreamReportRequest {
+                trace_id: plan.request_id.clone(),
+                report_kind: format!("{report_prefix}_stream_success"),
+                report_context: Some(context),
+                status_code: 200,
+                headers: BTreeMap::new(),
+                provider_body_base64: None,
+                provider_body_state: None,
+                client_body_base64: None,
+                client_body_state: None,
+                terminal_summary: Some(super::grok_stream_terminal_summary(&plan, expected)),
+                telemetry: None,
+            };
+            let stream_report: GatewayStreamReportRequest =
+                serde_json::from_slice(&serde_json::to_vec(&stream_report).unwrap()).unwrap();
+            let stream_event = build_stream_terminal_usage_event(
+                &plan,
+                stream_report.report_context.as_ref(),
+                &stream_report,
+            )
+            .unwrap();
+
+            // Sync honors the response's explicit total. The existing stream
+            // summary has no explicit total, so its fallback also adds reasoning.
+            let sync_total = expected.input_tokens + expected.output_tokens;
+            let stream_total = sync_total + expected.reasoning_tokens;
+            for (event, expected_total) in [(sync_event, sync_total), (stream_event, stream_total)]
+            {
+                assert_eq!(event.event_type, UsageEventType::Completed, "{format}");
+                assert_eq!(event.data.input_tokens, Some(expected.input_tokens));
+                assert_eq!(event.data.output_tokens, Some(expected.output_tokens));
+                assert_eq!(event.data.total_tokens, Some(expected_total));
+                let metadata = event.data.request_metadata.unwrap();
+                assert_eq!(metadata["analytics_measurement"]["source"], "estimated");
+                assert!(metadata.get("usage_token_source").is_none());
+            }
+        }
+    }
+
     #[test]
     fn openai_chat_body_includes_estimated_usage() {
         let plan = sample_plan(

apps/aether-gateway/src/execution_runtime/stream/execution.rs

@@ -12,7 +12,7 @@ use std::time::{Duration, Instant};
 use aether_ai_serving::{AiAttemptExecutionOutcome, AiAttemptRetryScope};
 use aether_contracts::{
     ExecutionPlan, ExecutionResponseObservation, ExecutionStreamTerminalSummary,
-    ExecutionTelemetry, StandardizedUsage, StreamFrame, StreamFramePayload,
+    ExecutionTelemetry, StandardizedUsage, StreamFrame, StreamFramePayload, UsageTokenSource,
 };
 use aether_data_contracts::repository::candidates::{
     RequestCandidateStatus, UpsertRequestCandidateRecord,
@@ -445,11 +445,15 @@ fn build_sync_terminal_usage_seeds(
     report_context: Option<&serde_json::Value>,
     payload: &GatewaySyncReportRequest,
 ) -> (TerminalUsageContextSeed, SyncTerminalUsagePayloadSeed) {
+    let analytics_context =
+        crate::usage::reporting::failure::sync_analytics_context(report_context, payload);
     let report_context_with_diagnostics =
-        attach_current_request_diagnostics_to_report_context(report_context);
+        attach_current_request_diagnostics_to_report_context(analytics_context.as_ref());
     let context_seed = build_terminal_usage_context_seed(
         plan,
-        report_context_with_diagnostics.as_ref().or(report_context),
+        report_context_with_diagnostics
+            .as_ref()
+            .or(analytics_context.as_ref()),
     );
     let payload_seed = build_sync_terminal_usage_payload_seed(payload);
     (context_seed, payload_seed)
@@ -586,7 +590,12 @@ async fn record_stream_terminal_usage(
     cancelled: bool,
 ) {
     crate::execution_runtime::mark_stream_candidate_watchdog_terminal_started();
-    let context_seed = build_terminal_usage_context_seed(plan, report_context);
+    let analytics_context = crate::usage::reporting::failure::stream_analytics_context(
+        report_context,
+        payload,
+        cancelled,
+    );
+    let context_seed = build_terminal_usage_context_seed(plan, analytics_context.as_ref());
     let payload_seed = build_stream_terminal_usage_payload_seed(payload);
     state
         .usage_runtime
@@ -976,6 +985,9 @@ async fn maybe_apply_kiro_prompt_cache_usage_to_stream_summary(
         usage.cache_read_tokens = 0;
         if usage.input_tokens <= 0 {
             usage.input_tokens = estimated_input_tokens as i64;
+            if usage.input_tokens > 0 {
+                mark_kiro_stream_estimated_usage(usage, report_context, false);
+            }
         }
         return;
     }
@@ -984,6 +996,10 @@ async fn maybe_apply_kiro_prompt_cache_usage_to_stream_summary(
         usage.input_tokens = kiro_billed_input_tokens(estimated_input_tokens, cache_usage) as i64;
         usage.cache_creation_tokens = cache_usage.cache_creation_input_tokens as i64;
         usage.cache_read_tokens = cache_usage.cache_read_input_tokens as i64;
+        if usage.input_tokens > 0 || usage.cache_creation_tokens > 0 || usage.cache_read_tokens > 0
+        {
+            mark_kiro_stream_estimated_usage(usage, report_context, false);
+        }
         return;
     }
 
@@ -996,12 +1012,18 @@ async fn maybe_apply_kiro_prompt_cache_usage_to_stream_summary(
                     cache_read_input_tokens: usage.cache_read_tokens.max(0) as u64,
                 },
             ) as i64;
+            if usage.input_tokens > 0 {
+                mark_kiro_stream_estimated_usage(usage, report_context, true);
+            }
         }
         return;
     }
 
     if usage.input_tokens <= 0 {
         usage.input_tokens = estimated_input_tokens as i64;
+        if usage.input_tokens > 0 {
+            mark_kiro_stream_estimated_usage(usage, report_context, true);
+        }
     }
 
     let Some(profile) =
@@ -1024,6 +1046,35 @@ async fn maybe_apply_kiro_prompt_cache_usage_to_stream_summary(
     usage.input_tokens = billed_input_tokens as i64;
     usage.cache_creation_tokens = cache_usage.cache_creation_input_tokens as i64;
     usage.cache_read_tokens = cache_usage.cache_read_input_tokens as i64;
+    mark_kiro_stream_estimated_usage(usage, report_context, false);
+}
+
+fn mark_kiro_stream_estimated_usage(
+    usage: &mut StandardizedUsage,
+    report_context: &Value,
+    retains_cache: bool,
+) {
+    let retained_source = usage.token_source.unwrap_or_else(|| {
+        match report_context
+            .get("usage_token_source")
+            .and_then(Value::as_str)
+        {
+            Some("estimated") => UsageTokenSource::Estimated,
+            Some("mixed") => UsageTokenSource::Mixed,
+            _ => UsageTokenSource::Reported,
+        }
+    });
+    let retains_reported_tokens = retained_source != UsageTokenSource::Estimated
+        && (usage.output_tokens > 0
+            || usage.reasoning_tokens > 0
+            || usage.cache_creation_ephemeral_5m_tokens > 0
+            || usage.cache_creation_ephemeral_1h_tokens > 0
+            || (retains_cache && (usage.cache_creation_tokens > 0 || usage.cache_read_tokens > 0)));
+    usage.token_source = Some(if retains_reported_tokens {
+        UsageTokenSource::Mixed
+    } else {
+        UsageTokenSource::Estimated
+    });
 }
 
 fn append_stream_capture_bytes(
@@ -3963,7 +4014,7 @@ async fn execute_execution_runtime_stream_inner(
     let candidate_started_unix_secs = current_request_candidate_unix_ms();
     let provider_in_flight_started_at = Instant::now();
     let mut provider_pool_in_flight_guard =
-        match acquire_provider_pool_execution_guard(state, &plan).await? {
+        match acquire_provider_pool_execution_guard(state, &plan, report_context.as_ref()).await? {
             ProviderPoolInFlightAdmission::Acquired(guard) => guard,
             ProviderPoolInFlightAdmission::Saturated { limit } => {
                 record_local_runtime_candidate_skip_reason(
@@ -12412,6 +12463,10 @@ mod tests {
             .expect("first usage should exist");
         assert!(first_usage.cache_creation_tokens > 0);
         assert_eq!(first_usage.cache_read_tokens, 0);
+        assert_eq!(
+            first_usage.token_source,
+            Some(aether_contracts::UsageTokenSource::Mixed)
+        );
 
         let mut second_summary = Some(ExecutionStreamTerminalSummary {
             standardized_usage: Some(StandardizedUsage {
@@ -12436,6 +12491,10 @@ mod tests {
         assert_eq!(second_usage.cache_creation_tokens, 0);
         assert!(second_usage.input_tokens < 6_000);
         assert_eq!(second_usage.output_tokens, 19);
+        assert_eq!(
+            second_usage.token_source,
+            Some(aether_contracts::UsageTokenSource::Mixed)
+        );
     }
 
     #[tokio::test]
@@ -12631,6 +12690,49 @@ mod tests {
         assert_eq!(usage.cache_creation_tokens, 0);
         assert_eq!(usage.cache_read_tokens, 0);
         assert_eq!(usage.output_tokens, 13);
+        assert_eq!(
+            usage.token_source,
+            Some(aether_contracts::UsageTokenSource::Mixed)
+        );
+
+        use aether_contracts::UsageTokenSource::{Estimated, Mixed};
+        for (hint, source, input, output, cache, expected) in [
+            (Some("estimated"), None, 0, 13, 0, Some(Estimated)),
+            (None, Some(Estimated), 0, 13, 0, Some(Estimated)),
+            (None, None, 0, 0, 200, Some(Mixed)),
+            (None, None, 0, 0, 0, Some(Estimated)),
+            (None, None, 50, 13, 0, None),
+        ] {
+            let mut context = report_context.clone();
+            if let Some(hint) = hint {
+                context["usage_token_source"] = json!(hint);
+            }
+            let mut summary = Some(ExecutionStreamTerminalSummary {
+                standardized_usage: Some(StandardizedUsage {
+                    token_source: source,
+                    input_tokens: input,
+                    output_tokens: output,
+                    cache_read_tokens: cache,
+                    ..StandardizedUsage::new()
+                }),
+                ..Default::default()
+            });
+            maybe_apply_kiro_prompt_cache_usage_to_stream_summary(
+                &state,
+                &plan,
+                Some(&context),
+                &mut summary,
+            )
+            .await;
+            let usage = summary.unwrap().standardized_usage.unwrap();
+            assert!(usage.input_tokens > 0);
+            assert_eq!(usage.output_tokens, output);
+            assert_eq!(usage.cache_read_tokens, cache);
+            assert_eq!(
+                usage.token_source, expected,
+                "hint={hint:?}, source={source:?}"
+            );
+        }
     }
 
     #[tokio::test]
@@ -12870,6 +12972,10 @@ mod tests {
         assert_eq!(usage.cache_creation_tokens, 175);
         assert_eq!(usage.cache_read_tokens, 24_463);
         assert_eq!(usage.output_tokens, 167);
+        assert_eq!(
+            usage.token_source,
+            Some(aether_contracts::UsageTokenSource::Mixed)
+        );
     }
 
     #[tokio::test]

apps/aether-gateway/src/execution_runtime/stream/execution_failures.rs

@@ -45,6 +45,7 @@ pub(super) struct StreamFailureReport {
     honor_http_failover: bool,
     extra_error_fields: Map<String, Value>,
     provider_body_json: Option<Value>,
+    analytics_failure: Option<Value>,
 }
 
 #[derive(Serialize)]
@@ -133,6 +134,7 @@ impl StreamFailureReport {
             honor_http_failover: _,
             mut extra_error_fields,
             provider_body_json,
+            analytics_failure: _,
         } = self;
         extra_error_fields.insert("type".to_string(), Value::String(error_type));
         extra_error_fields.insert("message".to_string(), Value::String(error_message));
@@ -178,6 +180,7 @@ pub(super) fn build_stream_failure_report(
         honor_http_failover: false,
         extra_error_fields: Map::new(),
         provider_body_json: None,
+        analytics_failure: None,
     }
 }
 
@@ -196,6 +199,7 @@ pub(super) fn build_stream_transport_failure_report(
         honor_http_failover: false,
         extra_error_fields: Map::new(),
         provider_body_json: None,
+        analytics_failure: None,
     }
 }
 
@@ -241,6 +245,10 @@ pub(super) fn build_stream_failure_from_execution_error(
         honor_http_failover: error.upstream_status.is_some(),
         extra_error_fields: error_object,
         provider_body_json: None,
+        analytics_failure: crate::usage::reporting::failure::execution_error_analytics_context(
+            None, error,
+        )
+        .and_then(|context| context.get("analytics_failure").cloned()),
     }
 }
 
@@ -271,6 +279,7 @@ pub(super) fn build_stream_failure_from_provider_error_body(
         honor_http_failover: true,
         extra_error_fields: Map::new(),
         provider_body_json: Some(body_json.clone()),
+        analytics_failure: None,
     }
 }
 
@@ -334,6 +343,7 @@ fn build_stream_failure_sync_payload(
     let status_code = failure.status_code;
     let upstream_status_code = failure.upstream_status_code;
     let transport_error = failure.transport_error;
+    let analytics_failure = failure.analytics_failure.clone();
     let (body, client_body) = failure.into_body_jsons();
     headers.retain(|name, _| {
         !name.eq_ignore_ascii_case("content-encoding")
@@ -355,6 +365,9 @@ fn build_stream_failure_sync_payload(
         .or(report_context);
     let report_context = report_context.map(|mut context| {
         if let Some(object) = context.as_object_mut() {
+            if let Some(failure) = analytics_failure {
+                object.insert("analytics_failure".into(), failure);
+            }
             let response_headers = serde_json::to_value(&headers).unwrap_or(Value::Null);
             if upstream_status_code.is_some() {
                 object.insert(
@@ -499,9 +512,11 @@ async fn record_stream_sync_failure(
     );
     if !matches!(handling, StreamFailureHandling::HonorLocalFailover) || !retrying_next_candidate {
         crate::execution_runtime::mark_stream_candidate_watchdog_terminal_started();
+        let analytics_context =
+            crate::usage::reporting::failure::sync_analytics_context(report_context, payload);
         let report_context_with_diagnostics =
             attach_current_request_diagnostics_and_candidate_timing_to_report_context(
-                report_context,
+                analytics_context.as_ref(),
                 payload
                     .telemetry
                     .as_ref()
@@ -513,7 +528,9 @@ async fn record_stream_sync_failure(
             );
         let context_seed = build_terminal_usage_context_seed(
             plan,
-            report_context_with_diagnostics.as_ref().or(report_context),
+            report_context_with_diagnostics
+                .as_ref()
+                .or(analytics_context.as_ref()),
         );
         let payload_seed = build_sync_terminal_usage_payload_seed(payload);
         state
@@ -779,9 +796,13 @@ async fn handle_prefetch_transport_stream_failure(
         && matches!(analysis.decision, LocalFailoverDecision::RetryNextCandidate);
     if !retrying_next_candidate {
         crate::execution_runtime::mark_stream_candidate_watchdog_terminal_started();
+        let analytics_context = crate::usage::reporting::failure::sync_analytics_context(
+            payload.report_context.as_ref(),
+            &payload,
+        );
         let report_context_with_diagnostics =
             attach_current_request_diagnostics_and_candidate_timing_to_report_context(
-                payload.report_context.as_ref(),
+                analytics_context.as_ref(),
                 payload
                     .telemetry
                     .as_ref()
@@ -796,7 +817,7 @@ async fn handle_prefetch_transport_stream_failure(
             plan,
             report_context_with_diagnostics
                 .as_ref()
-                .or(payload.report_context.as_ref()),
+                .or(analytics_context.as_ref()),
         );
         let payload_seed = build_sync_terminal_usage_payload_seed(&payload);
         state

apps/aether-gateway/src/execution_runtime/sync/execution.rs

@@ -243,7 +243,10 @@ impl SyncAttemptTerminalGuard {
         record_sync_attempt_forced_terminal_state(
             self.state.clone(),
             self.plan.clone(),
-            self.report_context.clone(),
+            crate::usage::reporting::failure::gateway_error_analytics_context(
+                self.report_context.as_ref(),
+                error,
+            ),
             self.request_diagnostics.clone(),
             self.candidate_started_unix_ms,
             self.candidate_started_at,
@@ -317,6 +320,16 @@ async fn record_sync_attempt_forced_terminal_state(
     let error_message = error_message.into();
     let report_context =
         attach_request_diagnostics_to_report_context(report_context, request_diagnostics.as_ref());
+    let report_context = if matches!(usage_event_type, UsageEventType::Cancelled) {
+        crate::usage::reporting::failure::with_analytics_failure(
+            report_context.as_ref(),
+            "unknown",
+            "finalize",
+            "request_task_cancelled",
+        )
+    } else {
+        report_context
+    };
     let terminal_unix_ms = current_request_candidate_unix_ms();
     let latency_ms = elapsed_ms_since(candidate_started_at);
     record_local_request_candidate_status(
@@ -614,15 +627,19 @@ async fn record_sync_terminal_usage(
     candidate_started_at: Instant,
     candidate_first_byte_elapsed_ms: Option<u64>,
 ) {
+    let analytics_context =
+        crate::usage::reporting::failure::sync_analytics_context(report_context, payload);
     let report_context_with_diagnostics =
         attach_current_request_diagnostics_and_candidate_start_timing_to_report_context(
-            report_context,
+            analytics_context.as_ref(),
             candidate_started_at,
             candidate_first_byte_elapsed_ms,
         );
     let context_seed = build_terminal_usage_context_seed(
         plan,
-        report_context_with_diagnostics.as_ref().or(report_context),
+        report_context_with_diagnostics
+            .as_ref()
+            .or(analytics_context.as_ref()),
     );
     let payload_seed = build_sync_terminal_usage_payload_seed(payload);
     state
@@ -2074,37 +2091,38 @@ async fn execute_execution_runtime_sync_impl(
         .unwrap_or_else(|| "-".to_string());
     let candidate_started_at = Instant::now();
     let candidate_started_unix_secs = current_request_candidate_unix_ms();
-    let _provider_pool_in_flight_guard = match acquire_provider_pool_execution_guard(state, &plan)
-        .await?
-    {
-        ProviderPoolInFlightAdmission::Acquired(guard) => guard,
-        ProviderPoolInFlightAdmission::Saturated { limit } => {
-            record_local_runtime_candidate_skip_reason(
-                state,
-                trace_id,
-                "provider_key_concurrency_limit_reached",
-            );
-            if let Some(retry_scope) = retry_scope_out.as_deref_mut() {
-                *retry_scope = AiAttemptRetryScope::Candidate;
+    let _provider_pool_in_flight_guard =
+        match acquire_provider_pool_execution_guard(state, &plan, report_context.as_ref()).await? {
+            ProviderPoolInFlightAdmission::Acquired(guard) => guard,
+            ProviderPoolInFlightAdmission::Saturated { limit } => {
+                record_local_runtime_candidate_skip_reason(
+                    state,
+                    trace_id,
+                    "provider_key_concurrency_limit_reached",
+                );
+                if let Some(retry_scope) = retry_scope_out.as_deref_mut() {
+                    *retry_scope = AiAttemptRetryScope::Candidate;
+                }
+                record_local_request_candidate_status(
+                    state,
+                    &plan,
+                    report_context.as_ref(),
+                    SchedulerRequestCandidateStatusUpdate {
+                        status: RequestCandidateStatus::Skipped,
+                        status_code: Some(StatusCode::TOO_MANY_REQUESTS.as_u16()),
+                        error_type: Some("provider_key_concurrency_limit_reached".to_string()),
+                        error_message: Some(format!(
+                            "provider key concurrency limit reached: {limit}"
+                        )),
+                        latency_ms: Some(0),
+                        started_at_unix_ms: Some(candidate_started_unix_secs),
+                        finished_at_unix_ms: Some(candidate_started_unix_secs),
+                    },
+                )
+                .await;
+                return Ok(None);
             }
-            record_local_request_candidate_status(
-                state,
-                &plan,
-                report_context.as_ref(),
-                SchedulerRequestCandidateStatusUpdate {
-                    status: RequestCandidateStatus::Skipped,
-                    status_code: Some(StatusCode::TOO_MANY_REQUESTS.as_u16()),
-                    error_type: Some("provider_key_concurrency_limit_reached".to_string()),
-                    error_message: Some(format!("provider key concurrency limit reached: {limit}")),
-                    latency_ms: Some(0),
-                    started_at_unix_ms: Some(candidate_started_unix_secs),
-                    finished_at_unix_ms: Some(candidate_started_unix_secs),
-                },
-            )
-            .await;
-            return Ok(None);
-        }
-    };
+        };
     let lifecycle_seed = build_lifecycle_usage_seed(&plan, report_context.as_ref());
     let usage_data = state.usage_lifecycle_data_state().as_ref().clone();
     state
@@ -2804,6 +2822,9 @@ async fn execute_execution_runtime_sync_impl(
         provider_response_observation.response_headers_observed_at_unix_ms,
         &provider_response_observation.request_order_id,
     );
+    if let Some(error) = result.error.as_ref() {
+        report_context = crate::usage::reporting::failure::execution_error_analytics_context(report_context.as_ref(), error);
+    }
     if result.status_code >= 400 {
         apply_local_execution_effect(
             state,

apps/aether-gateway/src/execution_runtime/transport_failure.rs

@@ -130,6 +130,9 @@ pub(crate) async fn build_transport_error_stop_response(
             None => serde_json::Map::new(),
         };
         request_metadata.insert("transport_error".to_string(), Value::Bool(true));
+        request_metadata.insert("analytics_failure".into(), json!({
+            "origin": "transport", "stage": "connect", "reason": "upstream_transport_error", "schema_version": 1,
+        }));
         request_metadata.insert(
             "transport_error_type".to_string(),
             Value::String(error_type.to_string()),

apps/aether-gateway/src/executor/outcome.rs

@@ -111,6 +111,12 @@ pub(crate) fn record_failed_usage_for_deferred_response<'a>(
             return;
         };
         let mut data = build_usage_event_data_seed(&context.plan, context.report_context.as_ref());
+        data.request_metadata = crate::usage::reporting::failure::with_analytics_failure(
+            data.request_metadata.as_ref(),
+            "upstream",
+            "response",
+            "candidates_exhausted",
+        );
         data.status_code = Some(status_code);
         data.error_message =
             Some("all local candidates failed; returning preserved upstream error".to_string());
@@ -390,6 +396,15 @@ pub(crate) async fn record_failed_usage_for_exhausted_request(
         None => Map::new(),
     };
     request_metadata.insert("trace_id".to_string(), Value::String(request_id.clone()));
+    if !request_metadata.contains_key("analytics_failure") {
+        request_metadata.insert(
+            "analytics_failure".into(),
+            json!({
+                "origin": if upstream_status_code.is_some() { "upstream" } else { "gateway" },
+                "stage": "routing", "reason": "candidates_exhausted", "schema_version": 1,
+            }),
+        );
+    }
     apply_runtime_miss_usage_routing(
         &mut data,
         &mut request_metadata,
@@ -471,6 +486,9 @@ pub(crate) async fn record_failed_usage_for_runtime_miss_request(
     }
 
     let mut request_metadata = Map::new();
+    request_metadata.insert("analytics_failure".into(), json!({
+        "origin": "gateway", "stage": "routing", "reason": "execution_route_unavailable", "schema_version": 1,
+    }));
     request_metadata.insert(
         "trace_id".to_string(),
         Value::String(request_id.to_string()),

apps/aether-gateway/src/frontdoor_loop_guard.rs

@@ -45,6 +45,7 @@ pub(crate) fn frontdoor_self_loop_public_ai_path(path: &str) -> bool {
             | "/v1/rerank"
             | "/v1/responses"
             | "/v1/responses/compact"
+            | "/v1/memories/trace_summarize"
             | "/v1/realtime"
             | "/v1/realtime/calls"
             | "/v1/live"

apps/aether-gateway/src/handlers/admin/billing/mod.rs

@@ -16,6 +16,8 @@ mod collectors;
 mod payments;
 mod plans;
 mod presets;
+mod provider_accounts;
+mod provider_expenses;
 mod routes;
 mod rules;
 mod wallets;
@@ -207,6 +209,15 @@ pub(crate) async fn maybe_build_local_admin_billing_response(
         return Ok(None);
     }
 
+    if let Some(response) = provider_accounts::response(state, request_context).await? {
+        return Ok(Some(response));
+    }
+    if let Some(response) =
+        provider_expenses::response(state, request_context, request_body).await?
+    {
+        return Ok(Some(response));
+    }
+
     let path = request_context.path();
     let is_billing_route = (request_context.method() == http::Method::GET
         && matches!(

apps/aether-gateway/src/handlers/admin/billing/provider_accounts.rs

@@ -0,0 +1,159 @@
+//! Current provider finance snapshots. This endpoint never calls upstream services.
+use super::build_admin_billing_data_unavailable_response;
+use crate::handlers::admin::request::{AdminAppState, AdminRequestContext};
+use crate::GatewayError;
+use axum::{
+    body::Body,
+    http,
+    response::{IntoResponse, Response},
+    Json,
+};
+use serde_json::{json, Value};
+
+fn finite(value: Option<&Value>) -> Option<f64> {
+    value
+        .and_then(|v| {
+            v.as_f64()
+                .or_else(|| v.as_str().and_then(|v| v.parse::<f64>().ok()))
+        })
+        .filter(|v| v.is_finite())
+}
+fn text(value: Option<&Value>) -> Option<&str> {
+    value
+        .and_then(Value::as_str)
+        .map(str::trim)
+        .filter(|v| !v.is_empty() && v.len() <= 256 && !v.chars().any(char::is_control))
+}
+fn timestamp(value: Option<&Value>) -> Option<String> {
+    let value = value?;
+    if let Some(raw) = value.as_str() {
+        if let Ok(date) = chrono::DateTime::parse_from_rfc3339(raw) {
+            return Some(date.to_rfc3339_opts(chrono::SecondsFormat::Millis, true));
+        }
+    }
+    let secs = finite(Some(value))?;
+    if !(0.0..=253_402_300_799.0).contains(&secs) {
+        return None;
+    }
+    chrono::DateTime::from_timestamp(secs as i64, 0)
+        .map(|v| v.to_rfc3339_opts(chrono::SecondsFormat::Millis, true))
+}
+fn subscription(value: &Value) -> Value {
+    json!({
+        "group_name": text(value.get("group_name")),
+        "status": text(value.get("status")),
+        "daily_used_usd": finite(value.get("daily_used_usd")),
+        "daily_limit_usd": finite(value.get("daily_limit_usd")),
+        "weekly_used_usd": finite(value.get("weekly_used_usd")),
+        "weekly_limit_usd": finite(value.get("weekly_limit_usd")),
+        "monthly_used_usd": finite(value.get("monthly_used_usd")),
+        "monthly_limit_usd": finite(value.get("monthly_limit_usd")),
+        "expires_at": timestamp(value.get("expires_at")),
+    })
+}
+fn balance(value: &Value) -> Option<Value> {
+    if value.get("action_type").and_then(Value::as_str) != Some("query_balance") {
+        return None;
+    }
+    let status = text(value.get("status"))?;
+    if !matches!(status, "success" | "auth_expired" | "auth_failed") {
+        return None;
+    }
+    let data = value
+        .get("data")
+        .filter(|_| matches!(status, "success" | "auth_expired"));
+    let extra = data.and_then(|d| d.get("extra"));
+    let subscriptions = extra
+        .and_then(|e| e.get("subscriptions"))
+        .and_then(Value::as_array)
+        .map(|items| {
+            items
+                .iter()
+                .filter(|v| v.is_object())
+                .take(128)
+                .map(subscription)
+                .collect::<Vec<_>>()
+        })
+        .unwrap_or_default();
+    Some(json!({
+        "status": status,
+        "observed_at": timestamp(value.get("executed_at")),
+        "currency": data.and_then(|d| text(d.get("currency"))),
+        "available": data.and_then(|d| finite(d.get("total_available"))),
+        "used": data.and_then(|d| finite(d.get("total_used"))),
+        "granted": data.and_then(|d| finite(d.get("total_granted"))),
+        "plan_name": extra.and_then(|e| text(e.get("plan_name"))),
+        "subscriptions": subscriptions,
+    }))
+}
+pub(super) async fn response(
+    state: &AdminAppState<'_>,
+    context: &AdminRequestContext<'_>,
+) -> Result<Option<Response<Body>>, GatewayError> {
+    if context.method() != http::Method::GET
+        || context.path().trim_end_matches('/') != "/api/admin/billing/provider-accounts"
+        || context.route_family() != Some("billing_manage")
+    {
+        return Ok(None);
+    }
+    if !state.has_provider_catalog_data_reader() {
+        return Ok(Some(build_admin_billing_data_unavailable_response()));
+    }
+    let mut providers = state.list_provider_catalog_providers(false).await?;
+    providers.sort_by(|a, b| a.name.cmp(&b.name).then_with(|| a.id.cmp(&b.id)));
+    let keys = providers
+        .iter()
+        .map(|p| format!("provider_ops:balance:{}", p.id))
+        .collect::<Vec<_>>();
+    let (cached, unavailable) = if keys.is_empty() {
+        (Vec::new(), false)
+    } else {
+        match state.runtime_state().kv_get_many(&keys).await {
+            Ok(v) => (v, false),
+            Err(_) => (vec![None; keys.len()], true),
+        }
+    };
+    let items = providers.iter().enumerate().map(|(index, p)| {
+        let limit = p.monthly_quota_usd.filter(|v| v.is_finite() && *v >= 0.0);
+        let used = p.monthly_used_usd.filter(|v| v.is_finite() && *v >= 0.0);
+        let quota = if p.billing_type.as_deref() == Some("monthly_quota") || limit.is_some() {
+            json!({
+                "limit": limit, "used": used,
+                "remaining": limit.zip(used).map(|(l,u)| (l-u).max(0.0)),
+                "currency": "USD",
+                "period_start": p.quota_last_reset_at_unix_secs.and_then(|v| timestamp(Some(&json!(v)))),
+                "expires_at": p.quota_expires_at_unix_secs.and_then(|v| timestamp(Some(&json!(v)))),
+            })
+        } else { Value::Null };
+        let balance = cached.get(index).and_then(|v| v.as_deref())
+            .and_then(|v| serde_json::from_str::<Value>(v).ok()).and_then(|v| balance(&v));
+        json!({
+            "provider_id": p.id, "provider_name": p.name, "is_active": p.is_active,
+            "billing_type": p.billing_type, "quota": quota, "balance": balance,
+        })
+    }).collect::<Vec<_>>();
+    Ok(Some((
+        [(http::header::CACHE_CONTROL, "private, no-store")],
+        Json(json!({
+            "observed_at": chrono::Utc::now().to_rfc3339_opts(chrono::SecondsFormat::Millis,true),
+            "items": items, "balance_snapshot_unavailable": unavailable,
+        })),
+    ).into_response()))
+}
+#[cfg(test)]
+mod tests {
+    use super::*;
+    #[test]
+    fn provider_accounts_only_expose_finance_allowlist_and_preserve_unknown() {
+        let snapshot=balance(&json!({"status":"success","action_type":"query_balance","executed_at":"2026-09-20T00:00:00Z","data":{"currency":"USD","total_available":null,"extra":{"access_token":"secret","plan_name":"Pro","subscriptions":[{"group_name":"Team","monthly_used_usd":"12.25","expires_at":1800000000,"private_token":"secret"}]}}})).unwrap();
+        assert!(snapshot["available"].is_null());
+        assert_eq!(
+            snapshot["subscriptions"][0]["monthly_used_usd"],
+            json!(12.25)
+        );
+        assert!(!snapshot.to_string().contains("secret"));
+        assert!(!snapshot.to_string().contains("access_token"));
+        let failed=balance(&json!({"status":"auth_failed","action_type":"query_balance","data":{"total_available":999}})).unwrap();
+        assert!(failed["available"].is_null());
+    }
+}

apps/aether-gateway/src/handlers/admin/billing/provider_expenses.rs

@@ -0,0 +1,334 @@
+use super::{
+    build_admin_billing_bad_request_response as bad_request,
+    build_admin_billing_conflict_response as conflict,
+    build_admin_billing_data_unavailable_response as unavailable,
+    build_admin_billing_not_found_response as not_found,
+};
+use crate::handlers::admin::{
+    request::{AdminAppState, AdminRequestContext},
+    shared::{attach_admin_audit_response, query_param_value},
+};
+use crate::handlers::shared::normalize_payment_currency;
+use crate::GatewayError;
+use aether_data_contracts::repository::billing::*;
+use axum::{
+    body::{Body, Bytes},
+    http::{self, StatusCode},
+    response::{IntoResponse, Response},
+    Json,
+};
+use serde::Deserialize;
+use serde_json::{json, Value};
+
+#[derive(Deserialize)]
+#[serde(deny_unknown_fields)]
+struct ExpenseRequest {
+    client_request_id: String,
+    provider_id: String,
+    kind: String,
+    amount: String,
+    currency: String,
+    paid_at: String,
+    period_start: Option<String>,
+    period_end: Option<String>,
+    note: Option<String>,
+    external_reference: Option<String>,
+}
+fn datetime(value: u64) -> String {
+    chrono::DateTime::from_timestamp_millis(value as i64)
+        .expect("valid stored timestamp")
+        .to_rfc3339_opts(chrono::SecondsFormat::Millis, true)
+}
+fn parse_date(value: &str) -> Result<u64, String> {
+    chrono::DateTime::parse_from_rfc3339(value)
+        .ok()
+        .and_then(|v| u64::try_from(v.timestamp_millis()).ok())
+        .filter(|v| *v <= 253_402_300_799_000)
+        .ok_or_else(|| "timestamps must be RFC3339 dates on or after 1970".into())
+}
+fn optional_text(value: Option<String>) -> Option<String> {
+    value.map(|v| v.trim().to_owned()).filter(|v| !v.is_empty())
+}
+fn expense_json(record: &ProviderExpenseRecord) -> Value {
+    let e = &record.entry;
+    json!({
+        "id": record.id, "client_request_id": e.client_request_id,
+        "provider_id": e.provider_id, "provider_name": e.provider_name,
+        "kind": e.kind, "amount": e.amount, "currency": e.currency,
+        "paid_at": datetime(e.paid_at_unix_ms),
+        "period_start": e.period_start_unix_ms.map(datetime),
+        "period_end": e.period_end_unix_ms.map(datetime),
+        "note": e.note, "external_reference": e.external_reference,
+        "created_by": e.created_by, "created_at": datetime(record.created_at_unix_ms),
+        "status": if record.voided_at_unix_ms.is_some() { "void" } else { "recorded" },
+        "voided_at": record.voided_at_unix_ms.map(datetime), "voided_by": record.voided_by,
+    })
+}
+fn csv_cell(value: &str) -> String {
+    let value = if value.trim_start().starts_with(['=', '+', '-', '@'])
+        || value.starts_with(['\t', '\r', '\n'])
+    {
+        format!("'{value}")
+    } else {
+        value.to_string()
+    };
+    format!("\"{}\"", value.replace('"', "\"\""))
+}
+fn csv_report(items: &[ProviderExpenseRecord]) -> String {
+    let mut result=String::from("\u{feff}id,provider_id,provider_name,kind,amount,currency,paid_at,period_start,period_end,note,external_reference,created_by,created_at\r\n");
+    for r in items {
+        let e = &r.entry;
+        let fields = [
+            r.id.clone(),
+            e.provider_id.clone(),
+            e.provider_name.clone(),
+            e.kind.clone(),
+            e.amount.clone(),
+            e.currency.clone(),
+            datetime(e.paid_at_unix_ms),
+            e.period_start_unix_ms.map(datetime).unwrap_or_default(),
+            e.period_end_unix_ms.map(datetime).unwrap_or_default(),
+            e.note.clone().unwrap_or_default(),
+            e.external_reference.clone().unwrap_or_default(),
+            e.created_by.clone().unwrap_or_default(),
+            datetime(r.created_at_unix_ms),
+        ];
+        result.push_str(
+            &fields
+                .iter()
+                .map(|s| csv_cell(s))
+                .collect::<Vec<_>>()
+                .join(","),
+        );
+        result.push_str("\r\n");
+    }
+    result
+}
+fn query(context: &AdminRequestContext<'_>, csv: bool) -> Result<ProviderExpenseQuery, String> {
+    let q = context.query_string();
+    let now = chrono::Utc::now().timestamp_millis().max(0) as u64;
+    let from = query_param_value(q, "from")
+        .map(|v| parse_date(&v))
+        .transpose()?
+        .unwrap_or(now.saturating_sub(30 * 86_400_000));
+    let to = query_param_value(q, "to")
+        .map(|v| parse_date(&v))
+        .transpose()?
+        .unwrap_or(now);
+    let limit = if csv {
+        10_001
+    } else {
+        query_param_value(q, "limit")
+            .map(|v| v.parse::<u32>().map_err(|_| "invalid limit".to_string()))
+            .transpose()?
+            .unwrap_or(25)
+    };
+    let offset = if csv {
+        0
+    } else {
+        query_param_value(q, "offset")
+            .map(|v| v.parse::<u64>().map_err(|_| "invalid offset".to_string()))
+            .transpose()?
+            .unwrap_or(0)
+    };
+    if !csv && limit > 200 {
+        return Err("limit must be at most 200".into());
+    }
+    let q = ProviderExpenseQuery {
+        from_unix_ms: from,
+        to_unix_ms: to,
+        limit,
+        offset,
+    };
+    q.validate().map_err(|e| e.to_string())?;
+    Ok(q)
+}
+pub(super) async fn response(
+    state: &AdminAppState<'_>,
+    context: &AdminRequestContext<'_>,
+    body: Option<&Bytes>,
+) -> Result<Option<Response<Body>>, GatewayError> {
+    let path = context.path().trim_end_matches('/');
+    if context.route_family() != Some("billing_manage")
+        || !path.starts_with("/api/admin/billing/provider-expenses")
+    {
+        return Ok(None);
+    }
+    let operator = context
+        .decision()
+        .and_then(|d| d.admin_principal.as_ref())
+        .map(|p| p.user_id.clone());
+    if path == "/api/admin/billing/provider-expenses" && context.method() == http::Method::GET {
+        let csv = query_param_value(context.query_string(), "format").as_deref() == Some("csv");
+        let q = match query(context, csv) {
+            Ok(v) => v,
+            Err(e) => return Ok(Some(bad_request(e))),
+        };
+        let Some(page) = state
+            .app()
+            .data
+            .list_provider_expenses(&q)
+            .await
+            .map_err(|e| GatewayError::Internal(e.to_string()))?
+        else {
+            return Ok(Some(unavailable()));
+        };
+        if csv {
+            if page.total > 10_000 {
+                return Ok(Some(
+                    (
+                        StatusCode::UNPROCESSABLE_ENTITY,
+                        Json(json!({"detail":"导出超过 10000 条，请缩小时间范围"})),
+                    )
+                        .into_response(),
+                ));
+            }
+            return Ok(Some(
+                (
+                    [
+                        (http::header::CONTENT_TYPE, "text/csv; charset=utf-8"),
+                        (
+                            http::header::CONTENT_DISPOSITION,
+                            "attachment; filename=provider-expenses.csv",
+                        ),
+                        (http::header::CACHE_CONTROL, "private, no-store"),
+                    ],
+                    csv_report(&page.items),
+                )
+                    .into_response(),
+            ));
+        }
+        return Ok(Some(
+            (
+                [(http::header::CACHE_CONTROL, "private, no-store")],
+                Json(json!({
+                    "items": page.items.iter().map(expense_json).collect::<Vec<_>>(),
+                    "total": page.total, "totals": page.totals, "providers": page.providers,
+                    "limit": q.limit, "offset": q.offset,
+                    "from": datetime(q.from_unix_ms), "to": datetime(q.to_unix_ms),
+                    "time_basis": "paid_at", "source": "manual_ledger",
+                })),
+            )
+                .into_response(),
+        ));
+    }
+    if path == "/api/admin/billing/provider-expenses" && context.method() == http::Method::POST {
+        let Some(body) = body else {
+            return Ok(Some(bad_request("缺少请求体")));
+        };
+        let payload = match serde_json::from_slice::<ExpenseRequest>(body) {
+            Ok(v) => v,
+            Err(_) => return Ok(Some(bad_request("输入验证失败"))),
+        };
+        let input = (|| -> Result<ProviderExpenseInput, String> {
+            let units = provider_expense_amount_units(&payload.amount)
+                .ok_or("amount must be a positive decimal string with at most 8 decimal places")?;
+            let input = ProviderExpenseInput {
+                client_request_id: uuid::Uuid::parse_str(&payload.client_request_id)
+                    .map_err(|_| "client_request_id must be a UUID")?
+                    .to_string(),
+                provider_id: payload.provider_id.trim().into(),
+                provider_name: "pending".into(),
+                kind: payload.kind,
+                amount: format_provider_expense_amount(units),
+                currency: normalize_payment_currency(&payload.currency, "currency")?,
+                paid_at_unix_ms: parse_date(&payload.paid_at)?,
+                period_start_unix_ms: payload
+                    .period_start
+                    .as_deref()
+                    .map(parse_date)
+                    .transpose()?,
+                period_end_unix_ms: payload.period_end.as_deref().map(parse_date).transpose()?,
+                note: optional_text(payload.note),
+                external_reference: optional_text(payload.external_reference),
+                created_by: operator.clone(),
+            };
+            input.validate()?;
+            Ok(input)
+        })();
+        let mut input = match input {
+            Ok(v) => v,
+            Err(e) => return Ok(Some(bad_request(e))),
+        };
+        let providers = state
+            .read_provider_catalog_providers_by_ids(&[input.provider_id.clone()])
+            .await?;
+        let Some(provider) = providers.first() else {
+            return Ok(Some(not_found("Provider not found")));
+        };
+        input.provider_name = provider.name.clone();
+        let result = state
+            .app()
+            .data
+            .create_provider_expense(&input)
+            .await
+            .map_err(|e| GatewayError::Internal(e.to_string()))?;
+        return Ok(Some(mutation_response(
+            result,
+            "admin_provider_expense_recorded",
+            "record_provider_expense",
+        )));
+    }
+    if context.method() == http::Method::POST {
+        if let Some(id) = path
+            .strip_prefix("/api/admin/billing/provider-expenses/")
+            .and_then(|v| v.strip_suffix("/void"))
+            .filter(|v| !v.is_empty() && !v.contains('/'))
+        {
+            if uuid::Uuid::parse_str(id).is_err() {
+                return Ok(Some(bad_request("invalid expense id")));
+            }
+            let result = state
+                .app()
+                .data
+                .void_provider_expense(id, operator.as_deref())
+                .await
+                .map_err(|e| GatewayError::Internal(e.to_string()))?;
+            return Ok(Some(mutation_response(
+                result,
+                "admin_provider_expense_voided",
+                "void_provider_expense",
+            )));
+        }
+    }
+    Ok(None)
+}
+fn mutation_response(
+    outcome: AdminBillingMutationOutcome<ProviderExpenseRecord>,
+    event: &'static str,
+    action: &'static str,
+) -> Response<Body> {
+    match outcome {
+        AdminBillingMutationOutcome::Applied(record) => attach_admin_audit_response(
+            Json(json!({"item":expense_json(&record)})).into_response(),
+            event,
+            action,
+            "provider_expense",
+            &record.id,
+        ),
+        AdminBillingMutationOutcome::Invalid(e) => conflict(e),
+        AdminBillingMutationOutcome::NotFound => not_found("Provider expense not found"),
+        AdminBillingMutationOutcome::Unavailable => unavailable(),
+    }
+}
+#[cfg(test)]
+mod tests {
+    use super::*;
+    #[test]
+    fn provider_expense_csv_neutralizes_formulas_and_quotes_fields() {
+        assert_eq!(csv_cell("=cmd()"), "\"'=cmd()\"");
+        assert_eq!(csv_cell("  @cmd"), "\"'  @cmd\"");
+        assert_eq!(csv_cell("\tcmd"), "\"'\tcmd\"");
+        assert_eq!(csv_cell("a,\"b\"\nc"), "\"a,\"\"b\"\"\nc\"");
+        assert_eq!(csv_cell("12.34"), "\"12.34\"");
+    }
+    #[test]
+    fn provider_expense_dates_require_explicit_timezone_and_nonnegative_epoch() {
+        assert_eq!(
+            parse_date("2026-09-20T08:00:00+08:00"),
+            parse_date("2026-09-20T00:00:00Z")
+        );
+        assert!(parse_date("2026-09-20").is_err());
+        assert!(parse_date("1969-01-01T00:00:00Z").is_err());
+    }
+}

apps/aether-gateway/src/handlers/admin/billing/wallets/reads/list.rs

@@ -27,11 +27,18 @@ pub(in super::super) async fn build_admin_wallet_list_response(
         Ok(value) => value,
         Err(detail) => return Ok(build_admin_wallets_bad_request_response(detail)),
     };
+    let user_id = query_param_value(query, "user_id");
     let status = query_param_value(query, "status");
     let owner_type = parse_admin_wallets_owner_type_filter(query);
 
     let (wallets, total) = state
-        .list_admin_wallets(status.as_deref(), owner_type.as_deref(), limit, offset)
+        .list_admin_wallets(
+            user_id.as_deref(),
+            status.as_deref(),
+            owner_type.as_deref(),
+            limit,
+            offset,
+        )
         .await?;
     let mut items = Vec::with_capacity(wallets.len());
     for wallet in wallets {

apps/aether-gateway/src/handlers/admin/endpoint/health.rs

@@ -35,11 +35,39 @@ fn build_admin_endpoint_health_bad_request_response(detail: &str) -> Response<Bo
 pub(super) async fn maybe_build_local_admin_endpoints_health_response(
     state: &AdminAppState<'_>,
     request_context: &AdminRequestContext<'_>,
+    request_body: Option<&axum::body::Bytes>,
 ) -> Result<Option<Response<Body>>, GatewayError> {
     let Some(decision) = request_context.decision() else {
         return Ok(None);
     };
 
+    if decision.route_family.as_deref() == Some("endpoints_health") {
+        if decision.route_kind.as_deref() == Some("health_v2") {
+            return Ok(Some(
+                crate::handlers::shared::health_monitor::build_health_v2_response(
+                    state.app(),
+                    request_context.path(),
+                    request_context.query_string(),
+                    crate::handlers::shared::health_monitor::HealthAudience::Admin,
+                )
+                .await,
+            ));
+        }
+        if decision.route_kind.as_deref() == Some("health_v2_publication") {
+            return Ok(Some(
+                crate::handlers::shared::health_monitor::build_publication_response(
+                    state.app(),
+                    if request_context.method() == http::Method::PUT {
+                        Some(request_body.map_or(&[][..], |body| body.as_ref()))
+                    } else {
+                        None
+                    },
+                )
+                .await,
+            ));
+        }
+    }
+
     if decision.route_family.as_deref() == Some("endpoints_health")
         && decision.route_kind.as_deref() == Some("health_summary")
         && request_context.path() == "/api/admin/endpoints/health/summary"

apps/aether-gateway/src/handlers/admin/endpoint/routes.rs

@@ -8,6 +8,7 @@ pub(crate) async fn maybe_build_local_admin_endpoints_response(
     if let Some(response) = health::maybe_build_local_admin_endpoints_health_response(
         &request.state(),
         &request.request_context(),
+        request.request_body(),
     )
     .await?
     {

apps/aether-gateway/src/handlers/admin/observability/mod.rs

@@ -1,4 +1,5 @@
 mod monitoring;
+mod overview;
 mod routes;
 mod stats;
 mod usage;

apps/aether-gateway/src/handlers/admin/observability/monitoring/mod.rs

@@ -22,6 +22,8 @@ pub(crate) mod test_support;
 mod trace;
 mod usage_helpers;
 
+pub(super) use resilience::overview_resilience_payload;
+
 pub(crate) async fn maybe_build_local_admin_monitoring_response(
     state: &AdminAppState<'_>,
     request_context: &AdminRequestContext<'_>,

apps/aether-gateway/src/handlers/admin/observability/monitoring/resilience/mod.rs

@@ -6,3 +6,23 @@ mod status;
 pub(super) use history::build_admin_monitoring_resilience_circuit_history_response;
 pub(super) use reset::build_admin_monitoring_reset_error_stats_response;
 pub(super) use status::build_admin_monitoring_resilience_status_response;
+
+pub(in super::super) async fn overview_resilience_payload(
+    state: &crate::handlers::admin::request::AdminAppState<'_>,
+) -> Result<serde_json::Value, crate::GatewayError> {
+    let snapshot = snapshot::build_admin_monitoring_resilience_snapshot(state).await?;
+    let from = (snapshot.timestamp - chrono::Duration::hours(24))
+        .timestamp()
+        .max(
+            state
+                .admin_monitoring_error_stats_reset_at()
+                .unwrap_or_default() as i64,
+        );
+    Ok(serde_json::json!({
+        "scope": {"kind": "installation"},
+        "error_range": {"from": chrono::DateTime::from_timestamp(from, 0), "to": snapshot.timestamp},
+        "timestamp": snapshot.timestamp, "health_score": snapshot.health_score,
+        "status": snapshot.status, "error_statistics": snapshot.error_statistics,
+        "recent_errors": snapshot.recent_errors, "recommendations": snapshot.recommendations,
+    }))
+}

apps/aether-gateway/src/handlers/admin/observability/overview/dashboard.rs

@@ -0,0 +1,134 @@
+use crate::handlers::admin::request::{AdminAppState, AdminRequestContext};
+use crate::GatewayError;
+use aether_admin::observability::analytics::{dashboard_value, parse_dashboard_query};
+use axum::{
+    body::Body,
+    http::{self, StatusCode},
+    response::{IntoResponse, Response},
+    Json,
+};
+
+pub(super) async fn response(
+    state: &AdminAppState<'_>,
+    context: &AdminRequestContext<'_>,
+) -> Result<Response<Body>, GatewayError> {
+    let query = match parse_dashboard_query(context.query_string()) {
+        Ok(query) => query,
+        Err(detail) => return Ok(super::error(StatusCode::BAD_REQUEST, &detail)),
+    };
+    if !state.as_ref().has_usage_data_reader() {
+        return Ok(super::error(
+            StatusCode::SERVICE_UNAVAILABLE,
+            "usage analytics is unavailable",
+        ));
+    }
+    let snapshot = match tokio::time::timeout(
+        std::time::Duration::from_secs(15),
+        state.as_ref().query_dashboard_analytics(&query),
+    )
+    .await
+    {
+        Ok(result) => result?,
+        Err(_) => {
+            return Ok(super::error(
+                StatusCode::GATEWAY_TIMEOUT,
+                "dashboard query exceeded its time budget",
+            ))
+        }
+    };
+    let data = dashboard_value(&query, &snapshot).map_err(GatewayError::Internal)?;
+    Ok((
+        [(http::header::CACHE_CONTROL, "private, no-store")],
+        Json(data),
+    )
+        .into_response())
+}
+
+pub(super) async fn total_response(
+    state: &AdminAppState<'_>,
+    context: &AdminRequestContext<'_>,
+) -> Result<Response<Body>, GatewayError> {
+    use crate::cache::OverviewTotalRead;
+    use aether_data_contracts::repository::usage::UsageDashboardAnalyticsQuery;
+    use serde_json::json;
+    use std::sync::Arc;
+    use std::time::{Duration, Instant};
+
+    let query = match parse_dashboard_query(context.query_string()) {
+        Ok(query) => query,
+        Err(detail) => return Ok(super::error(StatusCode::BAD_REQUEST, &detail)),
+    };
+    if !state.as_ref().has_usage_data_reader() {
+        return Ok(super::error(
+            StatusCode::SERVICE_UNAVAILABLE,
+            "usage analytics is unavailable",
+        ));
+    }
+    let (cached, refresh) = state.as_ref().overview_total_cache.read(Instant::now());
+    if let Some(refresh) = refresh {
+        let app = state.as_ref();
+        let data = if app.background_data.has_usage_reader() {
+            Arc::clone(&app.background_data)
+        } else {
+            Arc::clone(&app.data)
+        };
+        // Lifetime boundaries do not depend on the viewer's timezone. Every
+        // administrator shares one refresh, including after a page reload.
+        tokio::spawn(async move {
+            let query = UsageDashboardAnalyticsQuery {
+                timezone: "UTC".into(),
+            };
+            let result = tokio::time::timeout(
+                Duration::from_secs(185),
+                data.query_dashboard_analytics(&query),
+            )
+            .await;
+            let snapshot = match result {
+                Ok(Ok(snapshot)) => Some(snapshot),
+                Ok(Err(error)) => {
+                    tracing::warn!(%error, "dashboard lifetime refresh failed");
+                    None
+                }
+                Err(_) => {
+                    tracing::warn!("dashboard lifetime refresh exceeded its time budget");
+                    None
+                }
+            };
+            refresh.finish(snapshot, Instant::now());
+        });
+    }
+    let (status, body, retry_after) = match cached {
+        OverviewTotalRead::Pending => {
+            (StatusCode::ACCEPTED, json!({"status":"pending"}), Some("3"))
+        }
+        OverviewTotalRead::Failed => (
+            StatusCode::SERVICE_UNAVAILABLE,
+            json!({"status":"failed", "detail":"cumulative dashboard totals are temporarily unavailable; retry shortly"}),
+            Some("10"),
+        ),
+        OverviewTotalRead::Ready { snapshot, stale } => {
+            let mut value = dashboard_value(&query, &snapshot).map_err(GatewayError::Internal)?;
+            (
+                StatusCode::OK,
+                json!({
+                    "status":"ready", "total": value["total"].take(),
+                    "history_complete": snapshot.history_complete, "stale": stale,
+                }),
+                None,
+            )
+        }
+    };
+    let mut response = (
+        status,
+        [(http::header::CACHE_CONTROL, "private, no-store")],
+        Json(body),
+    )
+        .into_response();
+    if let Some(retry_after) = retry_after {
+        response.headers_mut().insert(
+            http::header::RETRY_AFTER,
+            http::HeaderValue::from_static(retry_after),
+        );
+    }
+    Ok(response)
+}

apps/aether-gateway/src/handlers/admin/observability/overview/dashboard_summary.rs

@@ -0,0 +1,46 @@
+use crate::handlers::admin::request::{AdminAppState, AdminRequestContext};
+use crate::GatewayError;
+use aether_admin::observability::analytics::{dashboard_summary_value, parse_dashboard_query};
+use axum::{
+    body::Body,
+    http::{header, StatusCode},
+    response::{IntoResponse, Response},
+    Json,
+};
+
+pub(super) async fn response(
+    state: &AdminAppState<'_>,
+    context: &AdminRequestContext<'_>,
+) -> Result<Response<Body>, GatewayError> {
+    let query = match parse_dashboard_query(context.query_string()) {
+        Ok(query) => query,
+        Err(detail) => return Ok(super::error(StatusCode::BAD_REQUEST, &detail)),
+    };
+    if !state.as_ref().has_usage_data_reader() {
+        return Ok(super::error(
+            StatusCode::SERVICE_UNAVAILABLE,
+            "dashboard statistics are unavailable",
+        ));
+    }
+    let snapshot = match tokio::time::timeout(
+        std::time::Duration::from_secs(5),
+        state.as_ref().data.query_dashboard_summary(&query),
+    )
+    .await
+    {
+        Ok(Ok(snapshot)) => snapshot,
+        Ok(Err(error)) => return Err(GatewayError::Internal(error.to_string())),
+        Err(_) => {
+            return Ok(super::error(
+                StatusCode::GATEWAY_TIMEOUT,
+                "dashboard statistics exceeded their time budget",
+            ))
+        }
+    };
+    let mut value = dashboard_summary_value(&snapshot);
+    value["concurrency"] = state
+        .as_ref()
+        .today_concurrency(&query.timezone)
+        .map_err(GatewayError::Internal)?;
+    Ok(([(header::CACHE_CONTROL, "private, no-store")], Json(value)).into_response())
+}

apps/aether-gateway/src/handlers/admin/observability/overview/live.rs

@@ -0,0 +1,144 @@
+use super::error;
+use crate::handlers::admin::request::{AdminAppState, AdminRequestContext};
+use crate::GatewayError;
+use aether_admin::observability::analytics::{envelope, metrics_value, OverviewRequest};
+use aether_data_contracts::repository::usage::{UsageAnalyticsQuery, USAGE_ANALYTICS_VERSION};
+use axum::{
+    body::Body,
+    http::{header, HeaderValue, StatusCode},
+    response::{IntoResponse, Response},
+    Json,
+};
+use serde_json::json;
+
+pub(super) async fn response(
+    state: &AdminAppState<'_>,
+    context: &AdminRequestContext<'_>,
+) -> Result<Response<Body>, GatewayError> {
+    if context
+        .query_string()
+        .is_some_and(|query| !query.is_empty())
+    {
+        return Ok(error(
+            StatusCode::BAD_REQUEST,
+            "live diagnostics do not accept historical filters",
+        ));
+    }
+    let app = state.as_ref();
+    let _ = app.metric_samples().await;
+    let snapshot = app.metric_snapshot.read().await.clone();
+    let captured = snapshot.as_ref().map(|(captured, _)| *captured);
+    let now = chrono::Utc::now();
+    let observed_at = captured
+        .and_then(|captured| chrono::Duration::from_std(captured.elapsed()).ok())
+        .map(|age| now - age);
+    let mut unavailable = Vec::new();
+    let (resilience_result, recent_result) = tokio::join!(
+        tokio::time::timeout(
+            std::time::Duration::from_secs(3),
+            super::super::monitoring::overview_resilience_payload(state)
+        ),
+        tokio::time::timeout(
+            std::time::Duration::from_secs(3),
+            recent_activity(state, now)
+        ),
+    );
+    let resilience = match resilience_result {
+        Ok(Ok(value)) => Some(value),
+        _ => {
+            tracing::warn!("overview resilience snapshot unavailable");
+            unavailable.push("resilience");
+            None
+        }
+    };
+    let recent_activity = match recent_result {
+        Ok(Ok(value)) => Some(value),
+        _ => {
+            unavailable.push("recent_activity");
+            None
+        }
+    };
+    if captured.is_none() {
+        unavailable.push("metrics");
+    }
+    let mut response = Json(json!({
+        "meta": {
+            "schema_version": 1, "metric_version": USAGE_ANALYTICS_VERSION, "scope": {"kind": "node"},
+            "generated_at": now, "data_through": observed_at, "read_revision": observed_at.map(|value| value.timestamp_millis().to_string()),
+            "coverage": {"status": if unavailable.is_empty() {"complete"} else {"partial"}},
+        },
+        "data": {
+            "observed_at": observed_at, "window_seconds": null, "node_id": null,
+            "scope": {"kind": "node", "node_ids": []},
+            "metrics_text": snapshot.map(|(_, samples)| aether_runtime::metrics::render_prometheus_text(&samples)),
+            "resilience": resilience, "recent_activity": recent_activity,
+            "execution_activity": app.execution_activity.snapshot(),
+            "unavailable_sections": unavailable,
+        },
+    })).into_response();
+    response.headers_mut().insert(
+        header::CACHE_CONTROL,
+        HeaderValue::from_static("private, no-store"),
+    );
+    Ok(response)
+}
+
+async fn recent_activity(
+    state: &AdminAppState<'_>,
+    now: chrono::DateTime<chrono::Utc>,
+) -> Result<serde_json::Value, GatewayError> {
+    let to = now.timestamp_millis().max(60_000) as u64;
+    let request = OverviewRequest {
+        query: UsageAnalyticsQuery {
+            from_unix_ms: to - 60_000,
+            to_unix_ms: to,
+            timezone: "UTC".into(),
+            limit: 1,
+            ..Default::default()
+        },
+        amount_basis: "billable".into(),
+        csv: false,
+    };
+    let snapshot = state.as_ref().query_usage_analytics(&request.query).await?;
+    let data = recent_activity_data(&snapshot);
+    Ok(envelope(&request, &snapshot, data))
+}
+
+fn recent_activity_data(
+    snapshot: &aether_data_contracts::repository::usage::StoredUsageAnalytics,
+) -> serde_json::Value {
+    let mut data = metrics_value(&snapshot.summary);
+    data["requests_per_second"] = json!(snapshot.summary.request_count as f64 / 60.0);
+    data["requests_per_minute"] = json!(snapshot.summary.request_count);
+    data["tokens_per_minute"] = data["total_tokens"].clone();
+    data["window_seconds"] = json!(60);
+    data
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use aether_data_contracts::repository::usage::{StoredUsageAnalytics, UsageAnalyticsMetrics};
+
+    #[test]
+    fn recent_activity_reports_one_minute_rates_without_inventing_missing_tokens() {
+        let mut snapshot = StoredUsageAnalytics {
+            summary: UsageAnalyticsMetrics {
+                request_count: 120,
+                usage_available_count: 120,
+                total_tokens: 4200,
+                ..Default::default()
+            },
+            ..Default::default()
+        };
+        let value = recent_activity_data(&snapshot);
+        assert_eq!(value["window_seconds"], 60);
+        assert_eq!(value["requests_per_second"], 2.0);
+        assert_eq!(value["requests_per_minute"], 120);
+        assert_eq!(value["tokens_per_minute"], 4200);
+        snapshot.summary.usage_available_count = 0;
+        assert!(recent_activity_data(&snapshot)["tokens_per_minute"].is_null());
+        snapshot.summary = UsageAnalyticsMetrics::default();
+        assert_eq!(recent_activity_data(&snapshot)["tokens_per_minute"], 0);
+    }
+}

apps/aether-gateway/src/handlers/admin/observability/overview/mod.rs

@@ -0,0 +1,184 @@
+mod dashboard;
+mod dashboard_summary;
+mod live;
+
+use crate::handlers::admin::request::{AdminAppState, AdminRequestContext};
+use crate::GatewayError;
+use aether_admin::observability::analytics::{
+    costs_value, dashboard_charts_value, envelope, export_csv, metrics_value, page_value,
+    parse_dashboard_charts_query, parse_overview_query, performance_value, user_finance_value,
+    user_payments_value,
+};
+use aether_data_contracts::repository::usage::{UsageAnalyticsGranularity, UsageAnalyticsView};
+use axum::{
+    body::Body,
+    http::{self, StatusCode},
+    response::{IntoResponse, Response},
+    Json,
+};
+use serde_json::json;
+
+pub(crate) async fn maybe_build_overview_response(
+    state: &AdminAppState<'_>,
+    context: &AdminRequestContext<'_>,
+) -> Result<Option<Response<Body>>, GatewayError> {
+    if context.route_family() != Some("overview_manage") || context.method() != http::Method::GET {
+        return Ok(None);
+    }
+    let kind = context.route_kind().unwrap_or_default();
+    if kind == "dashboard_summary" {
+        return dashboard_summary::response(state, context).await.map(Some);
+    }
+    if kind == "dashboard_total" {
+        return dashboard::total_response(state, context).await.map(Some);
+    }
+    if kind == "dashboard" {
+        return dashboard::response(state, context).await.map(Some);
+    }
+    if matches!(kind, "operations_live" | "operations_resources") {
+        return live::response(state, context).await.map(Some);
+    }
+    let view = match kind {
+        "dashboard_charts" => UsageAnalyticsView::DashboardCharts,
+        "summary" => UsageAnalyticsView::Summary,
+        "timeseries" | "costs" => UsageAnalyticsView::Timeseries,
+        "operations_performance" => UsageAnalyticsView::Performance,
+        "users" | "user_detail" => UsageAnalyticsView::Users,
+        "breakdown" => UsageAnalyticsView::Breakdown,
+        "consumption" => UsageAnalyticsView::Consumption,
+        _ => return Ok(None),
+    };
+    let parsed = if kind == "dashboard_charts" {
+        parse_dashboard_charts_query(context.query_string())
+    } else {
+        parse_overview_query(context.query_string(), view)
+    };
+    let mut request = match parsed {
+        Ok(value) => value,
+        Err(detail) => return Ok(Some(error(StatusCode::BAD_REQUEST, &detail))),
+    };
+    if kind == "user_detail" {
+        let encoded = context
+            .path()
+            .trim_end_matches('/')
+            .rsplit('/')
+            .next()
+            .unwrap_or_default();
+        let Ok(id) = percent_encoding::percent_decode_str(encoded).decode_utf8() else {
+            return Ok(Some(error(
+                StatusCode::BAD_REQUEST,
+                "invalid user identifier",
+            )));
+        };
+        let id = id.as_ref();
+        if id.is_empty() || id.len() > 512 || id.contains('/') || id.chars().any(char::is_control) {
+            return Ok(Some(error(
+                StatusCode::BAD_REQUEST,
+                "invalid user identifier",
+            )));
+        }
+        if request
+            .query
+            .actor_user_id
+            .as_deref()
+            .is_some_and(|value| value != id)
+            || request
+                .query
+                .credential_owner_id
+                .as_deref()
+                .is_some_and(|value| value != id)
+        {
+            return Ok(Some(error(
+                StatusCode::BAD_REQUEST,
+                "user filter conflicts with the requested employee",
+            )));
+        }
+        if request.query.attribution_kind.as_deref() == Some("employee") {
+            request.query.actor_user_id = Some(id.into());
+        } else {
+            request.query.credential_owner_id = Some(id.into());
+        }
+        request.query.limit = 1;
+        request.query.offset = 0;
+    }
+    if matches!(
+        view,
+        UsageAnalyticsView::Timeseries | UsageAnalyticsView::Performance
+    ) {
+        request.query.limit = 10_000;
+        request.query.offset = 0;
+    }
+    if kind == "costs" {
+        request.query.granularity = UsageAnalyticsGranularity::Day;
+    }
+    if !state.as_ref().has_usage_data_reader() {
+        return Ok(Some(error(
+            StatusCode::SERVICE_UNAVAILABLE,
+            "usage analytics is unavailable",
+        )));
+    }
+    let snapshot = match tokio::time::timeout(
+        std::time::Duration::from_secs(if request.csv { 30 } else { 15 }),
+        state.as_ref().query_usage_analytics(&request.query),
+    )
+    .await
+    {
+        Ok(result) => result?,
+        Err(_) => {
+            return Ok(Some(error(
+                StatusCode::GATEWAY_TIMEOUT,
+                "report query exceeded its time budget; narrow the range or filters",
+            )))
+        }
+    };
+    if request.csv {
+        return Ok(Some(match export_csv(&request, &snapshot) {
+            Ok(csv) => (
+                [
+                    (http::header::CONTENT_TYPE, "text/csv; charset=utf-8"),
+                    (
+                        http::header::CONTENT_DISPOSITION,
+                        "attachment; filename=overview.csv",
+                    ),
+                    (http::header::CACHE_CONTROL, "private, no-store"),
+                ],
+                csv,
+            )
+                .into_response(),
+            Err(detail) => error(StatusCode::UNPROCESSABLE_ENTITY, &detail),
+        }));
+    }
+    let data = match kind {
+        "dashboard_charts" => dashboard_charts_value(&snapshot),
+        "summary" => metrics_value(&snapshot.summary),
+        "user_detail" => {
+            let Some(user) = snapshot.users.first() else {
+                return Ok(Some(error(StatusCode::NOT_FOUND, "employee not found")));
+            };
+            json!({
+                "user": { "id": user.user_id, "username": user.username, "email": user.email, "is_active": user.is_active },
+                "summary": metrics_value(&user.metrics),
+                "finance": user_finance_value(user.finance.as_ref()),
+                "payments": user_payments_value(snapshot.user_payments.as_ref()),
+            })
+        }
+        "costs" => costs_value(&request, &snapshot),
+        "timeseries" => {
+            let mut page = page_value(&request, &snapshot);
+            page["granularity"] = json!(request.query.granularity);
+            page
+        }
+        "operations_performance" => performance_value(&request, &snapshot),
+        _ => page_value(&request, &snapshot),
+    };
+    let mut response = Json(envelope(&request, &snapshot, data)).into_response();
+    response.headers_mut().insert(
+        http::header::CACHE_CONTROL,
+        http::HeaderValue::from_static("private, no-store"),
+    );
+    Ok(Some(response))
+}
+
+fn error(status: StatusCode, detail: &str) -> Response<Body> {
+    (status, Json(json!({"detail": detail}))).into_response()
+}

apps/aether-gateway/src/handlers/admin/observability/routes.rs

@@ -1,9 +1,15 @@
-use super::{monitoring, stats, usage};
+use super::{monitoring, overview, stats, usage};
 use crate::handlers::admin::request::{AdminRouteRequest, AdminRouteResult};
 
 pub(crate) async fn maybe_build_local_admin_observability_response(
     request: AdminRouteRequest<'_>,
 ) -> AdminRouteResult {
+    if let Some(response) =
+        overview::maybe_build_overview_response(&request.state(), &request.request_context())
+            .await?
+    {
+        return Ok(Some(response));
+    }
     if let Some(response) =
         stats::maybe_build_local_admin_stats_response(&request.state(), &request.request_context())
             .await?

apps/aether-gateway/src/handlers/admin/observability/stats/analytics_routes.rs

@@ -1,5 +1,8 @@
 use super::super::resolve_usage_user_group_scope;
-use super::range::{build_comparison_range, parse_bounded_u32};
+use super::range::{
+    build_comparison_range, parse_bounded_u32, precise_admin_stats_time_range,
+    resolve_precise_time_bounds,
+};
 use super::resolve_admin_usage_time_range;
 use crate::handlers::admin::request::{AdminAppState, AdminRequestContext};
 use crate::handlers::admin::shared::{
@@ -285,12 +288,36 @@ pub(super) async fn maybe_build_local_admin_stats_analytics_response(
             Ok(value) => value,
             Err(detail) => return Ok(Some(admin_stats_bad_request_response(detail))),
         };
-        let time_range = match resolve_admin_usage_time_range(request_context.query_string()) {
+        let legacy_time_range = match resolve_admin_usage_time_range(request_context.query_string())
+        {
             Ok(value) => value,
             Err(detail) => return Ok(Some(admin_stats_bad_request_response(detail))),
         };
-        if let Err(detail) = time_range.validate_for_time_series(granularity) {
-            return Ok(Some(admin_stats_bad_request_response(detail)));
+        let precise_bounds = match resolve_precise_time_bounds(request_context.query_string()) {
+            Ok(value) => value,
+            Err(detail) => return Ok(Some(admin_stats_bad_request_response(detail))),
+        };
+        let precise_time_range = match precise_bounds {
+            Some((from, to)) => {
+                match precise_admin_stats_time_range(request_context.query_string(), from, to) {
+                    Ok(value) => Some(value),
+                    Err(detail) => return Ok(Some(admin_stats_bad_request_response(detail))),
+                }
+            }
+            None => None,
+        };
+        let time_range = precise_time_range.as_ref().unwrap_or(&legacy_time_range);
+        if precise_bounds.is_none() {
+            if let Err(detail) = time_range.validate_for_time_series(granularity) {
+                return Ok(Some(admin_stats_bad_request_response(detail)));
+            }
+        } else if precise_bounds
+            .and_then(|(from, to)| to.checked_sub(from))
+            .is_some_and(|seconds| seconds > 90 * 86_400)
+        {
+            return Ok(Some(admin_stats_bad_request_response(
+                "Query range cannot exceed 90 days".to_string(),
+            )));
         }
         if !state.has_usage_data_reader() {
             return Ok(Some(admin_stats_time_series_empty_response()));
@@ -314,7 +341,8 @@ pub(super) async fn maybe_build_local_admin_stats_analytics_response(
             | AdminStatsGranularity::Week
             | AdminStatsGranularity::Month => UsageTimeSeriesGranularity::Day,
         };
-        let Some((created_from_unix_secs, created_until_unix_secs)) = time_range.to_unix_bounds()
+        let Some((created_from_unix_secs, created_until_unix_secs)) =
+            precise_bounds.or_else(|| time_range.to_unix_bounds())
         else {
             return Ok(Some(admin_stats_time_series_empty_response()));
         };
@@ -336,7 +364,7 @@ pub(super) async fn maybe_build_local_admin_stats_analytics_response(
             })
             .await?;
         return Ok(Some(build_admin_stats_time_series_response_from_summaries(
-            &time_range,
+            time_range,
             granularity,
             &buckets,
         )));

apps/aether-gateway/src/handlers/admin/observability/stats/leaderboard_routes.rs

@@ -5,7 +5,7 @@ use super::leaderboard::{
     build_user_leaderboard_items_from_summaries, compare_leaderboard_items,
     load_user_leaderboard_metadata, AdminStatsLeaderboardItem, AdminStatsLeaderboardNameMode,
 };
-use super::range::{parse_bounded_u32, parse_nonnegative_usize};
+use super::range::{parse_bounded_u32, parse_nonnegative_usize, resolve_precise_time_bounds};
 use super::resolve_admin_usage_time_range;
 use crate::handlers::admin::request::{AdminAppState, AdminRequestContext};
 use crate::handlers::admin::shared::{query_param_bool, query_param_value};
@@ -228,6 +228,10 @@ pub(super) async fn maybe_build_local_admin_stats_leaderboard_response(
             Ok(value) => value,
             Err(detail) => return Ok(Some(admin_stats_bad_request_response(detail))),
         };
+        let precise_bounds = match resolve_precise_time_bounds(query) {
+            Ok(value) => value,
+            Err(detail) => return Ok(Some(admin_stats_bad_request_response(detail))),
+        };
         let metric = match AdminStatsLeaderboardMetric::parse(query) {
             Ok(value) => value,
             Err(detail) => return Ok(Some(admin_stats_bad_request_response(detail))),
@@ -272,7 +276,8 @@ pub(super) async fn maybe_build_local_admin_stats_leaderboard_response(
                 "user_id is not supported for the user group leaderboard".to_string(),
             )));
         }
-        let Some((created_from_unix_secs, created_until_unix_secs)) = time_range.to_unix_bounds()
+        let Some((created_from_unix_secs, created_until_unix_secs)) =
+            precise_bounds.or_else(|| time_range.to_unix_bounds())
         else {
             return Ok(Some(build_admin_stats_user_group_leaderboard_response(
                 metric,
@@ -402,6 +407,10 @@ pub(super) async fn maybe_build_local_admin_stats_leaderboard_response(
             Ok(value) => value,
             Err(detail) => return Ok(Some(admin_stats_bad_request_response(detail))),
         };
+        let precise_bounds = match resolve_precise_time_bounds(query) {
+            Ok(value) => value,
+            Err(detail) => return Ok(Some(admin_stats_bad_request_response(detail))),
+        };
         let metric = match AdminStatsLeaderboardMetric::parse(query) {
             Ok(value) => value,
             Err(detail) => return Ok(Some(admin_stats_bad_request_response(detail))),
@@ -442,7 +451,8 @@ pub(super) async fn maybe_build_local_admin_stats_leaderboard_response(
                 Ok(value) => value,
                 Err(detail) => return Ok(Some(admin_stats_bad_request_response(detail))),
             };
-        let Some((created_from_unix_secs, created_until_unix_secs)) = time_range.to_unix_bounds()
+        let Some((created_from_unix_secs, created_until_unix_secs)) =
+            precise_bounds.or_else(|| time_range.to_unix_bounds())
         else {
             return Ok(Some(admin_stats_leaderboard_empty_response(
                 metric,

apps/aether-gateway/src/handlers/admin/observability/stats/mod.rs

@@ -8,7 +8,10 @@ mod leaderboard;
 mod leaderboard_routes;
 mod provider_quota_routes;
 mod range;
-pub(crate) use self::range::{parse_bounded_u32, resolve_admin_usage_time_range};
+pub(crate) use self::range::{
+    parse_bounded_u32, precise_admin_stats_time_range, resolve_admin_usage_time_range,
+    resolve_precise_time_bounds, resolve_usage_time_bounds,
+};
 pub(crate) use aether_admin::observability::stats::{
     admin_stats_bad_request_response, aggregate_usage_stats, round_to, AdminStatsTimeRange,
     AdminStatsUsageFilter,

apps/aether-gateway/src/handlers/admin/observability/stats/range.rs

@@ -4,10 +4,14 @@ pub(super) use aether_admin::observability::stats::{
     admin_usage_default_days, build_comparison_range, build_time_range_from_days, parse_naive_date,
     parse_nonnegative_usize, parse_tz_offset_minutes, resolve_preset_dates, user_today,
 };
+use chrono::{DateTime, Offset, TimeZone, Utc};
 
 pub(crate) fn resolve_admin_usage_time_range(
     query: Option<&str>,
 ) -> Result<AdminStatsTimeRange, String> {
+    if let Some((from, to)) = resolve_precise_time_bounds(query)? {
+        return precise_admin_stats_time_range(query, from, to);
+    }
     match AdminStatsTimeRange::resolve_optional(query)? {
         Some(time_range) => Ok(time_range),
         None => {
@@ -20,3 +24,153 @@ pub(crate) fn resolve_admin_usage_time_range(
         }
     }
 }
+
+/// Resolve an exact UTC range supplied by the shared admin range picker.
+///
+/// The older stats handlers use `start_date`/`end_date` and fixed offsets. Keep
+/// that parser intact and only opt into this path when both RFC 3339 endpoints
+/// are present, so existing callers retain their behavior.
+pub(crate) fn resolve_precise_time_bounds(
+    query: Option<&str>,
+) -> Result<Option<(u64, u64)>, String> {
+    let entries =
+        url::form_urlencoded::parse(query.unwrap_or_default().as_bytes()).collect::<Vec<_>>();
+    let from = entries
+        .iter()
+        .filter(|(key, _)| key == "from")
+        .collect::<Vec<_>>();
+    let to = entries
+        .iter()
+        .filter(|(key, _)| key == "to")
+        .collect::<Vec<_>>();
+    if from.is_empty() && to.is_empty() {
+        return Ok(None);
+    }
+    if from.len() != 1 || to.len() != 1 {
+        return Err("from and to must each be provided once".into());
+    }
+    if entries
+        .iter()
+        .any(|(key, _)| matches!(key.as_ref(), "start_date" | "end_date" | "preset" | "days"))
+    {
+        return Err("precise from/to cannot be combined with date presets".into());
+    }
+    if let Some(zone) = query_param_value(query, "timezone") {
+        zone.parse::<chrono_tz::Tz>()
+            .map_err(|_| "invalid timezone".to_string())?;
+    }
+    let parse = |value: &str| -> Result<u64, String> {
+        let value = DateTime::parse_from_rfc3339(value)
+            .map_err(|_| "from/to must be RFC 3339 timestamps".to_string())?;
+        if value.timestamp_subsec_nanos() != 0 {
+            return Err("request records support second-aligned ranges".into());
+        }
+        u64::try_from(value.timestamp()).map_err(|_| "from/to must not precede Unix epoch".into())
+    };
+    let bounds = (parse(&from[0].1)?, parse(&to[0].1)?);
+    if bounds.0 >= bounds.1 || bounds.1 - bounds.0 > 366 * 86_400 {
+        return Err("from/to must define a nonempty range of at most 366 days".into());
+    }
+    Ok(Some(bounds))
+}
+
+/// Return the exact range when present, otherwise preserve the legacy stats
+/// date/preset behavior.
+pub(crate) fn resolve_usage_time_bounds(query: Option<&str>) -> Result<Option<(u64, u64)>, String> {
+    if let Some(bounds) = resolve_precise_time_bounds(query)? {
+        return Ok(Some(bounds));
+    }
+    Ok(resolve_admin_usage_time_range(query)?.to_unix_bounds())
+}
+
+/// Build the date metadata used by the existing stats response builders for an
+/// exact range. The data query still uses the exact UTC bounds; this metadata
+/// only supplies the local date labels and offset expected by old clients.
+pub(crate) fn precise_admin_stats_time_range(
+    query: Option<&str>,
+    from: u64,
+    to: u64,
+) -> Result<AdminStatsTimeRange, String> {
+    let timezone_name = query_param_value(query, "timezone");
+    let (start_date, end_date, tz_offset_minutes) = if let Some(name) = timezone_name {
+        let timezone = name
+            .parse::<chrono_tz::Tz>()
+            .map_err(|_| "invalid timezone".to_string())?;
+        let start = Utc
+            .timestamp_opt(
+                i64::try_from(from).map_err(|_| "invalid from timestamp")?,
+                0,
+            )
+            .single()
+            .ok_or_else(|| "invalid from timestamp".to_string())?
+            .with_timezone(&timezone);
+        let end = Utc
+            .timestamp_opt(
+                i64::try_from(to.saturating_sub(1)).map_err(|_| "invalid to timestamp")?,
+                0,
+            )
+            .single()
+            .ok_or_else(|| "invalid to timestamp".to_string())?
+            .with_timezone(&timezone);
+        (
+            start.date_naive(),
+            end.date_naive(),
+            start.offset().fix().local_minus_utc() / 60,
+        )
+    } else {
+        let offset = parse_tz_offset_minutes(query)?;
+        let fixed = chrono::FixedOffset::east_opt(offset * 60)
+            .ok_or_else(|| "invalid timezone offset".to_string())?;
+        let start = Utc
+            .timestamp_opt(
+                i64::try_from(from).map_err(|_| "invalid from timestamp")?,
+                0,
+            )
+            .single()
+            .ok_or_else(|| "invalid from timestamp".to_string())?
+            .with_timezone(&fixed);
+        let end = Utc
+            .timestamp_opt(
+                i64::try_from(to.saturating_sub(1)).map_err(|_| "invalid to timestamp")?,
+                0,
+            )
+            .single()
+            .ok_or_else(|| "invalid to timestamp".to_string())?
+            .with_timezone(&fixed);
+        (start.date_naive(), end.date_naive(), offset)
+    };
+
+    Ok(AdminStatsTimeRange {
+        start_date,
+        end_date,
+        tz_offset_minutes,
+    })
+}
+
+fn query_param_value(query: Option<&str>, key: &str) -> Option<String> {
+    url::form_urlencoded::parse(query.unwrap_or_default().as_bytes())
+        .find(|(name, _)| name == key)
+        .map(|(_, value)| value.into_owned())
+}
+
+#[cfg(test)]
+mod tests {
+    use super::{precise_admin_stats_time_range, resolve_precise_time_bounds};
+
+    #[test]
+    fn precise_stats_range_preserves_subday_bounds_and_timezone_labels() {
+        let query = "from=2026-09-01T23:45:00Z&to=2026-09-02T00:15:00Z&timezone=Asia%2FShanghai";
+        let (from, to) = resolve_precise_time_bounds(Some(query)).unwrap().unwrap();
+        assert_eq!(to - from, 30 * 60);
+        let range = precise_admin_stats_time_range(Some(query), from, to).unwrap();
+        assert_eq!(range.start_date.to_string(), "2026-09-02");
+        assert_eq!(range.end_date.to_string(), "2026-09-02");
+        assert_eq!(range.tz_offset_minutes, 480);
+    }
+
+    #[test]
+    fn precise_stats_range_rejects_mixed_legacy_presets() {
+        let query = "from=2026-09-01T00:00:00Z&to=2026-09-02T00:00:00Z&preset=today";
+        assert!(resolve_precise_time_bounds(Some(query)).is_err());
+    }
+}

apps/aether-gateway/src/handlers/admin/observability/usage/analytics_routes/aggregation.rs

@@ -1,5 +1,5 @@
-use super::super::super::stats::resolve_admin_usage_time_range;
 use super::super::analytics::admin_usage_aggregation_by_user_json;
+use super::super::summary_routes::resolve_record_time_bounds;
 use crate::handlers::admin::request::{AdminAppState, AdminRequestContext};
 use crate::handlers::admin::shared::query_param_value;
 use crate::GatewayError;
@@ -159,12 +159,11 @@ pub(super) async fn build_admin_usage_aggregation_stats_response(
         Ok(value) => value,
         Err(detail) => return Ok(admin_usage_bad_request_response(detail)),
     };
-    let time_range = match resolve_admin_usage_time_range(query) {
+    let time_bounds = match resolve_record_time_bounds(query) {
         Ok(value) => value,
         Err(detail) => return Ok(admin_usage_bad_request_response(detail)),
     };
-    let Some((created_from_unix_secs, created_until_unix_secs)) = time_range.to_unix_bounds()
-    else {
+    let Some((created_from_unix_secs, created_until_unix_secs)) = time_bounds else {
         return Ok(Json(json!([])).into_response());
     };
     let group_by_query = match group_by.as_str() {

apps/aether-gateway/src/handlers/admin/observability/usage/summary_routes.rs

@@ -1,5 +1,5 @@
 use super::super::resolve_usage_user_group_scope;
-use super::super::stats::resolve_admin_usage_time_range;
+use super::super::stats::resolve_usage_time_bounds;
 use super::analytics::admin_usage_api_key_names;
 use super::analytics::admin_usage_provider_key_names;
 use crate::handlers::admin::request::{AdminAppState, AdminRequestContext};
@@ -34,6 +34,12 @@ use std::collections::{BTreeMap, BTreeSet};
 
 const ADMIN_USAGE_ACTIVE_LIMIT: usize = 50;
 
+pub(super) fn resolve_record_time_bounds(
+    query: Option<&str>,
+) -> Result<Option<(u64, u64)>, String> {
+    resolve_usage_time_bounds(query)
+}
+
 async fn load_admin_usage_by_ids(
     state: &AdminAppState<'_>,
     requested_ids: &BTreeSet<String>,
@@ -71,6 +77,7 @@ fn apply_admin_usage_status_filter(query: &mut UsageAuditListQuery, status: Opti
         }
         "websocket" | "ws" => query.is_websocket = Some(true),
         "error" | "failed" => query.error_only = true,
+        "success" => query.statuses = Some(vec!["completed".to_string()]),
         "active" => {
             query.statuses = Some(vec!["pending".to_string(), "streaming".to_string()]);
         }
@@ -565,12 +572,37 @@ fn build_admin_usage_records_query(
     query: Option<&str>,
     limit: Option<usize>,
     offset: Option<usize>,
-) -> UsageAuditListQuery {
+) -> Result<UsageAuditListQuery, String> {
+    let boolean = |key| match query_param_value(query, key).as_deref() {
+        None => Ok(None),
+        Some("true" | "1") => Ok(Some(true)),
+        Some("false" | "0") => Ok(Some(false)),
+        Some(_) => Err(format!("invalid {key}: expected true or false")),
+    };
+    let slow_threshold_ms = query_param_value(query, "slow_threshold_ms")
+        .map(|value| {
+            value
+                .parse::<u64>()
+                .ok()
+                .filter(|value| (1..=86_400_000).contains(value))
+                .ok_or_else(|| "slow_threshold_ms must be between 1 and 86400000".to_string())
+        })
+        .transpose()?;
     let mut list_query = UsageAuditListQuery {
         created_from_unix_secs: Some(created_from_unix_secs),
         created_until_unix_secs: Some(created_until_unix_secs),
         user_id: query_param_value(query, "user_id"),
         provider_name: query_param_value(query, "provider"),
+        provider_id: query_param_value(query, "provider_id"),
+        api_key_id: query_param_value(query, "api_key_id"),
+        request_id: query_param_value(query, "request_id"),
+        attribution_kind: query_param_value(query, "attribution_kind"),
+        actor_user_id: query_param_value(query, "actor_user_id"),
+        slow_threshold_ms,
+        endpoint_kind: query_param_value(query, "endpoint_kind"),
+        request_type: query_param_value(query, "request_type"),
+        has_format_conversion: boolean("has_format_conversion")?,
+        is_stream: boolean("is_stream")?,
         model: query_param_value(query, "model"),
         api_format: query_param_value(query, "api_format"),
         limit,
@@ -578,11 +610,23 @@ fn build_admin_usage_records_query(
         newest_first: true,
         ..Default::default()
     };
+    if list_query
+        .attribution_kind
+        .as_deref()
+        .is_some_and(|kind| !matches!(kind, "employee" | "standalone" | "unknown"))
+    {
+        return Err("invalid attribution_kind".into());
+    }
+    if list_query.attribution_kind.as_deref() == Some("employee")
+        && list_query.actor_user_id.is_none()
+    {
+        list_query.actor_user_id = list_query.user_id.take();
+    }
     apply_admin_usage_status_filter(
         &mut list_query,
         query_param_value(query, "status").as_deref(),
     );
-    list_query
+    Ok(list_query)
 }
 
 fn parse_admin_usage_search_keywords(search: &str) -> Vec<String> {
@@ -695,6 +739,15 @@ fn build_admin_usage_keyword_search_query(
         created_until_unix_secs: base_query.created_until_unix_secs,
         user_id: base_query.user_id.clone(),
         provider_name: base_query.provider_name.clone(),
+        provider_id: base_query.provider_id.clone(),
+        api_key_id: base_query.api_key_id.clone(),
+        request_id: base_query.request_id.clone(),
+        attribution_kind: base_query.attribution_kind.clone(),
+        actor_user_id: base_query.actor_user_id.clone(),
+        slow_threshold_ms: base_query.slow_threshold_ms,
+        endpoint_kind: base_query.endpoint_kind.clone(),
+        request_type: base_query.request_type.clone(),
+        has_format_conversion: base_query.has_format_conversion,
         model: base_query.model.clone(),
         api_format: base_query.api_format.clone(),
         client_family: base_query.client_family.clone(),
@@ -741,13 +794,11 @@ pub(super) async fn maybe_build_local_admin_usage_summary_response(
             }
 
             let query = request_context.request_query_string.as_deref();
-            let time_range = match resolve_admin_usage_time_range(query) {
+            let time_bounds = match resolve_record_time_bounds(query) {
                 Ok(value) => value,
                 Err(detail) => return Ok(Some(admin_usage_bad_request_response(detail))),
             };
-            let Some((created_from_unix_secs, created_until_unix_secs)) =
-                time_range.to_unix_bounds()
-            else {
+            let Some((created_from_unix_secs, created_until_unix_secs)) = time_bounds else {
                 return Ok(Some(build_admin_usage_summary_stats_response_from_summary(
                     &Default::default(),
                 )));
@@ -792,13 +843,11 @@ pub(super) async fn maybe_build_local_admin_usage_summary_response(
                 sort_usage_newest_first(&mut items);
                 items
             } else {
-                let time_range = match resolve_admin_usage_time_range(query) {
+                let time_bounds = match resolve_record_time_bounds(query) {
                     Ok(value) => value,
                     Err(detail) => return Ok(Some(admin_usage_bad_request_response(detail))),
                 };
-                let Some((created_from_unix_secs, created_until_unix_secs)) =
-                    time_range.to_unix_bounds()
-                else {
+                let Some((created_from_unix_secs, created_until_unix_secs)) = time_bounds else {
                     return Ok(Some(build_admin_usage_active_requests_response(
                         &[],
                         &BTreeMap::new(),
@@ -855,7 +904,7 @@ pub(super) async fn maybe_build_local_admin_usage_summary_response(
             }
 
             let query = request_context.request_query_string.as_deref();
-            let time_range = match resolve_admin_usage_time_range(query) {
+            let time_bounds = match resolve_record_time_bounds(query) {
                 Ok(value) => value,
                 Err(detail) => return Ok(Some(admin_usage_bad_request_response(detail))),
             };
@@ -876,9 +925,7 @@ pub(super) async fn maybe_build_local_admin_usage_summary_response(
                 Ok(value) => value,
                 Err(detail) => return Ok(Some(admin_usage_bad_request_response(detail))),
             };
-            let Some((created_from_unix_secs, created_until_unix_secs)) =
-                time_range.to_unix_bounds()
-            else {
+            let Some((created_from_unix_secs, created_until_unix_secs)) = time_bounds else {
                 return Ok(Some(build_admin_usage_records_response(
                     &[],
                     &BTreeMap::new(),
@@ -898,13 +945,16 @@ pub(super) async fn maybe_build_local_admin_usage_summary_response(
             let active_client_family_filter = client_family_filter
                 .as_deref()
                 .filter(|value| !value.trim().is_empty());
-            let mut base_query = build_admin_usage_records_query(
+            let mut base_query = match build_admin_usage_records_query(
                 created_from_unix_secs,
                 created_until_unix_secs,
                 query,
                 None,
                 None,
-            );
+            ) {
+                Ok(value) => value,
+                Err(detail) => return Ok(Some(admin_usage_bad_request_response(detail))),
+            };
             base_query.client_family = active_client_family_filter.map(str::to_owned);
             base_query.exclude_unknown_model_or_provider = hide_unknown_records;
             let (usage, total, total_is_estimated) = if attempt_status_filter.is_some() {
@@ -1077,6 +1127,89 @@ pub(super) async fn maybe_build_local_admin_usage_summary_response(
 
 #[cfg(test)]
 mod tests {
+    #[test]
+    fn precise_record_ranges_preserve_minutes_and_reject_mixed_presets() {
+        let range = "from=2026-09-01T23:45:00Z&to=2026-09-02T00:15:00Z&timezone=Asia%2FShanghai";
+        let (from, to) = super::resolve_record_time_bounds(Some(range))
+            .unwrap()
+            .unwrap();
+        assert_eq!(to - from, 30 * 60);
+        assert!(super::resolve_record_time_bounds(Some(&format!("{range}&preset=today"))).is_err());
+        assert!(super::resolve_record_time_bounds(Some("from=2026-09-01T00:00:00Z")).is_err());
+    }
+
+    #[test]
+    fn overview_record_drilldown_preserves_actor_and_performance_filters() {
+        let raw = "user_id=employee-1&attribution_kind=employee&provider_id=provider-1&api_key_id=key-1&request_id=request-1&endpoint_kind=chat&request_type=chat&is_stream=true&has_format_conversion=false&slow_threshold_ms=12000&status=success";
+        let query =
+            super::build_admin_usage_records_query(100, 200, Some(raw), None, None).unwrap();
+        assert_eq!(query.user_id, None);
+        assert_eq!(query.actor_user_id.as_deref(), Some("employee-1"));
+        assert_eq!(query.provider_id.as_deref(), Some("provider-1"));
+        assert_eq!(query.api_key_id.as_deref(), Some("key-1"));
+        assert_eq!(query.request_id.as_deref(), Some("request-1"));
+        assert_eq!(query.slow_threshold_ms, Some(12_000));
+        assert_eq!(query.is_stream, Some(true));
+        assert_eq!(query.has_format_conversion, Some(false));
+        assert_eq!(query.statuses, Some(vec!["completed".into()]));
+        let keyword = super::build_admin_usage_keyword_search_query(
+            &query,
+            vec!["example".into()],
+            None,
+            Default::default(),
+            false,
+            false,
+            None,
+            None,
+        );
+        assert_eq!(keyword.actor_user_id, query.actor_user_id);
+        assert_eq!(keyword.slow_threshold_ms, query.slow_threshold_ms);
+        assert_eq!(keyword.has_format_conversion, query.has_format_conversion);
+        for invalid in [
+            "is_stream=maybe",
+            "slow_threshold_ms=0",
+            "attribution_kind=owner",
+        ] {
+            assert!(
+                super::build_admin_usage_records_query(100, 200, Some(invalid), None, None)
+                    .is_err()
+            );
+        }
+    }
+
+    #[test]
+    fn overview_record_drilldown_preserves_standalone_key_ownership() {
+        let raw = "user_id=owner-1&attribution_kind=standalone&api_key_id=standalone-key";
+        let query =
+            super::build_admin_usage_records_query(100, 200, Some(raw), None, None).unwrap();
+        assert_eq!(query.attribution_kind.as_deref(), Some("standalone"));
+        assert_eq!(query.user_id.as_deref(), Some("owner-1"));
+        assert_eq!(query.actor_user_id, None);
+        assert_eq!(query.api_key_id.as_deref(), Some("standalone-key"));
+        let keyword = super::build_admin_usage_keyword_search_query(
+            &query,
+            vec!["example".into()],
+            None,
+            Default::default(),
+            false,
+            false,
+            None,
+            None,
+        );
+        assert_eq!(keyword.attribution_kind, query.attribution_kind);
+        assert_eq!(keyword.user_id, query.user_id);
+        assert_eq!(keyword.actor_user_id, query.actor_user_id);
+        assert_eq!(keyword.api_key_id, query.api_key_id);
+
+        for retired_kind in ["service", "shared"] {
+            let raw = format!("attribution_kind={retired_kind}");
+            assert!(
+                super::build_admin_usage_records_query(100, 200, Some(&raw), None, None).is_err(),
+                "{retired_kind}"
+            );
+        }
+    }
+
     use aether_data_contracts::repository::candidates::{
         RequestCandidateStatus, StoredRequestCandidate,
     };
@@ -1358,7 +1491,7 @@ mod tests {
         for status in ["websocket", "ws", "WS"] {
             let raw_query = format!("status={status}");
             let list_query =
-                build_admin_usage_records_query(100, 200, Some(&raw_query), None, None);
+                build_admin_usage_records_query(100, 200, Some(&raw_query), None, None).unwrap();
 
             assert_eq!(list_query.is_websocket, Some(true));
             assert_eq!(list_query.is_stream, None);
@@ -1379,7 +1512,7 @@ mod tests {
         for (status, expected_stream) in [("stream", true), ("standard", false)] {
             let raw_query = format!("status={status}");
             let list_query =
-                build_admin_usage_records_query(100, 200, Some(&raw_query), None, None);
+                build_admin_usage_records_query(100, 200, Some(&raw_query), None, None).unwrap();
             assert_eq!(list_query.is_stream, Some(expected_stream));
             assert_eq!(list_query.is_websocket, Some(false));
 

apps/aether-gateway/src/handlers/admin/request/billing.rs

@@ -121,6 +121,7 @@ impl<'a> AdminAppState<'a> {
 
     pub(crate) async fn list_admin_wallets(
         &self,
+        user_id: Option<&str>,
         status: Option<&str>,
         owner_type: Option<&str>,
         limit: usize,
@@ -133,7 +134,7 @@ impl<'a> AdminAppState<'a> {
         GatewayError,
     > {
         self.app
-            .list_admin_wallets(status, owner_type, limit, offset)
+            .list_admin_wallets(user_id, status, owner_type, limit, offset)
             .await
     }
 

apps/aether-gateway/src/handlers/admin/users/billing.rs

@@ -1,7 +1,9 @@
 use super::{build_admin_users_bad_request_response, build_admin_users_data_unavailable_response};
 use crate::handlers::admin::billing::admin_payment_gateway_response_projection;
 use crate::handlers::admin::request::{AdminAppState, AdminRequestContext};
-use crate::handlers::admin::shared::{attach_admin_audit_response, unix_secs_to_rfc3339};
+use crate::handlers::admin::shared::{
+    attach_admin_audit_response, query_param_value, unix_secs_to_rfc3339,
+};
 use crate::handlers::shared::unix_ms_to_rfc3339;
 use crate::GatewayError;
 use aether_data_contracts::repository::billing::{BillingPlanRecord, UserPlanEntitlementRecord};
@@ -177,8 +179,13 @@ fn entitlement_payload(
 async fn load_admin_user_entitlements_payload(
     state: &AdminAppState<'_>,
     user_id: &str,
+    include_inactive: bool,
 ) -> Result<Option<serde_json::Value>, GatewayError> {
-    let entitlements = match state.app().list_user_plan_entitlements(user_id).await? {
+    let entitlements = match state
+        .app()
+        .list_user_plan_entitlements_with_history(user_id, include_inactive)
+        .await?
+    {
         Some(value) => value,
         None => return Ok(None),
     };
@@ -214,7 +221,17 @@ pub(in super::super) async fn build_admin_list_user_billing_entitlements_respons
         )
             .into_response());
     }
-    match load_admin_user_entitlements_payload(state, &user_id).await? {
+    let include_inactive =
+        match query_param_value(request_context.query_string(), "include_inactive").as_deref() {
+            None | Some("false" | "0") => false,
+            Some("true" | "1") => true,
+            _ => {
+                return Ok(build_admin_users_bad_request_response(
+                    "include_inactive 必须为布尔值",
+                ))
+            }
+        };
+    match load_admin_user_entitlements_payload(state, &user_id, include_inactive).await? {
         Some(payload) => Ok(Json(payload).into_response()),
         None => Ok(build_admin_users_data_unavailable_response()),
     }
@@ -256,7 +273,7 @@ pub(in super::super) async fn build_admin_revoke_user_billing_entitlement_respon
             return Ok(build_admin_users_data_unavailable_response());
         }
     }
-    let entitlements = match load_admin_user_entitlements_payload(state, &user_id).await? {
+    let entitlements = match load_admin_user_entitlements_payload(state, &user_id, false).await? {
         Some(value) => value,
         None => return Ok(build_admin_users_data_unavailable_response()),
     };
@@ -401,7 +418,7 @@ pub(in super::super) async fn build_admin_grant_user_billing_plan_response(
             return Ok(build_admin_users_data_unavailable_response());
         }
     };
-    let entitlements = match load_admin_user_entitlements_payload(state, &user_id).await? {
+    let entitlements = match load_admin_user_entitlements_payload(state, &user_id, false).await? {
         Some(value) => value,
         None => return Ok(build_admin_users_data_unavailable_response()),
     };

apps/aether-gateway/src/handlers/proxy/mod.rs

@@ -1996,9 +1996,22 @@ async fn proxy_request_inner(
     request_permit = aether_runtime::AdmissionPermit::combine(
         request_permit.into_iter().chain(plan_usage_permit),
     );
-    if let Some(request_permit) = request_permit.as_ref() {
+    // The affinity-forwarding node already returned above. Observe only local
+    // AI execution, retaining the guard in both the body and detached execution.
+    let activity_permit = control_decision
+        .is_some_and(|decision| {
+            decision.route_class.as_deref() == Some("ai_public")
+                && decision.execution_runtime_candidate
+        })
+        .then(|| state.request_activity.begin().into_admission_permit());
+    if let Some(activity) = activity_permit.as_ref() {
+        crate::request_lifecycle::track_request_activity(activity.clone());
+    }
+    if let Some(background_permit) = aether_runtime::AdmissionPermit::combine(
+        request_permit.clone().into_iter().chain(activity_permit),
+    ) {
         parts.extensions.insert(
-            crate::executor::candidate_loop::BackgroundAdmissionPermit::new(request_permit.clone()),
+            crate::executor::candidate_loop::BackgroundAdmissionPermit::new(background_permit),
         );
     }
 

apps/aether-gateway/src/handlers/proxy/websocket/live/http.rs

@@ -376,6 +376,12 @@ async fn handle_live_http(
         state,
         &attempt.plan,
         request_context.trace_id.as_str(),
+        Some(
+            attempt
+                .report_context
+                .as_ref()
+                .unwrap_or(&serde_json::Value::Null),
+        ),
     )
     .await
     {

apps/aether-gateway/src/handlers/proxy/websocket/live/session.rs

@@ -1140,8 +1140,13 @@ async fn acquire_live_relay_admission(
             });
         }
     }
-    match ResponsesWebSocketTurnAdmission::acquire(state, &attempt.plan, context.trace_id.as_str())
-        .await
+    match ResponsesWebSocketTurnAdmission::acquire(
+        state,
+        &attempt.plan,
+        context.trace_id.as_str(),
+        None,
+    )
+    .await
     {
         Ok(capacity) => Ok(LiveRelayAdmission { capacity, audit }),
         Err(error) => Err(LiveRelayAdmissionFailure {

apps/aether-gateway/src/handlers/proxy/websocket/realtime/session.rs

@@ -136,6 +136,7 @@ pub(super) async fn prepare_realtime_websocket(
         state,
         &candidate.admission_plan,
         context.trace_id.as_str(),
+        None,
     )
     .await
     {

apps/aether-gateway/src/handlers/proxy/websocket/responses/adapter.rs

@@ -2,6 +2,7 @@
 
 use async_trait::async_trait;
 use serde_json::Value;
+use std::borrow::Cow;
 
 use super::adapters::CODEX_RESPONSES_WEBSOCKET_ADAPTER;
 use crate::ai_serving::AiExecutionDecision;
@@ -59,7 +60,7 @@ pub(super) enum ResponsesWebSocketRelayDirective<'a> {
     ForwardOriginal,
     /// The provider frame was a private batch envelope. Forward each retained
     /// event in document order by serializing the complete borrowed value.
-    ForwardEvents(Vec<&'a Value>),
+    ForwardEvents(Vec<Cow<'a, Value>>),
     /// The entire frame was an explicitly recognized provider-private
     /// envelope and therefore has no public event to relay.
     SuppressProviderPrivate,
@@ -88,8 +89,8 @@ pub(super) trait ResponsesWebSocketProtocolAdapter: Send + Sync {
     /// observably ambiguous to the client.
     fn rebind_safety_for_upstream_event(&self, event: &Value) -> ResponsesWebSocketRebindSafety;
 
-    /// Selects the public relay shape without projecting a provider event
-    /// through an Aether-owned field or event-type allowlist.
+    /// 公开事件保持完整；提供商私有元数据仅投影到客户端使用的公开字段，
+    /// 不公开账户信息。
     fn relay_directive_for_upstream_event<'a>(
         &self,
         _event: &'a Value,

apps/aether-gateway/src/handlers/proxy/websocket/responses/adapters/codex.rs

@@ -2,6 +2,7 @@
 
 use async_trait::async_trait;
 use serde_json::{Map, Value};
+use std::borrow::Cow;
 
 use super::super::adapter::{
     is_standard_responses_event, ResponsesWebSocketAdapterObservation,
@@ -222,7 +223,7 @@ fn codex_relay_directive(event: &Value) -> ResponsesWebSocketRelayDirective<'_>
         Some(Value::Array(chunks)) if is_explicit_codex_batch_envelope(event) => {
             let public_events = chunks
                 .iter()
-                .filter(|chunk| !is_codex_private_leaf_event(chunk))
+                .filter_map(codex_public_event)
                 .collect::<Vec<_>>();
             if public_events.is_empty() {
                 ResponsesWebSocketRelayDirective::SuppressProviderPrivate
@@ -233,13 +234,51 @@ fn codex_relay_directive(event: &Value) -> ResponsesWebSocketRelayDirective<'_>
         // A malformed or future shape is not proven private. Preserve it
         // opaquely rather than guessing at a provider schema.
         Some(_) => ResponsesWebSocketRelayDirective::ForwardOriginal,
-        None if is_codex_private_leaf_event(event) => {
-            ResponsesWebSocketRelayDirective::SuppressProviderPrivate
-        }
+        None if is_codex_private_leaf_event(event) => match codex_public_event(event) {
+            Some(projected) => ResponsesWebSocketRelayDirective::ForwardEvents(vec![projected]),
+            None => ResponsesWebSocketRelayDirective::SuppressProviderPrivate,
+        },
         None => ResponsesWebSocketRelayDirective::ForwardOriginal,
     }
 }
 
+fn codex_public_event(event: &Value) -> Option<Cow<'_, Value>> {
+    if !is_codex_private_leaf_event(event) {
+        return Some(Cow::Borrowed(event));
+    }
+    if event.get("type").and_then(Value::as_str) != Some("codex.response.metadata") {
+        // 配额属于选中的上游账户，不能代表网关用户配额；仅交给
+        // 账户级熔断和持久化路径处理。
+        return None;
+    }
+    let headers = event.get("headers")?.as_object()?;
+    let public_headers: Map<String, Value> = headers
+        .iter()
+        .filter_map(|(name, value)| {
+            let name = name.to_ascii_lowercase();
+            if matches!(
+                name.as_str(),
+                "x-models-etag"
+                    | "x-codex-turn-state"
+                    | "openai-model"
+                    | "x-codex-safety-buffering-enabled"
+                    | "x-codex-safety-buffering-faster-model"
+            ) && value.as_str().is_some()
+            {
+                Some((name, value.clone()))
+            } else {
+                None
+            }
+        })
+        .collect();
+    if public_headers.is_empty() {
+        return None;
+    }
+    Some(Cow::Owned(serde_json::json!({
+        "type": "codex.response.metadata", "headers": public_headers
+    })))
+}
+
 /// Recognizes only Codex's private batch container. A type-less object must
 /// contain exactly `chunks`; unknown siblings could be future public protocol
 /// data and therefore force opaque forwarding. A named Codex private root may
@@ -549,6 +588,55 @@ mod tests {
         }
     }
 
+    #[test]
+    fn codex_metadata_relays_cli_catalog_and_turn_state_without_account_fields() {
+        let event = json!({
+            "type": "codex.response.metadata",
+            "headers": {
+                "X-Models-Etag": "catalog-v2",
+                "x-codex-turn-state": "synthetic-turn-state",
+                "openai-model": "gpt-6.1-sol",
+                "x-codex-safety-buffering-enabled": "true",
+                "x-codex-safety-buffering-faster-model": "gpt-6-luna",
+                "chatgpt-account-id": "synthetic-private-account",
+                "set-cookie": "synthetic-private-cookie",
+                "authorization": "synthetic-private-token"
+            },
+            "account_hint": "private",
+            "metadata": {"user_id": "private"}
+        });
+        let ResponsesWebSocketRelayDirective::ForwardEvents(events) =
+            CodexResponsesWebSocketAdapter.relay_directive_for_upstream_event(&event)
+        else {
+            panic!("CLI metadata must reach the client");
+        };
+        assert_eq!(events.len(), 1);
+        assert_eq!(
+            *events[0],
+            json!({
+                "type": "codex.response.metadata",
+                "headers": {"x-models-etag": "catalog-v2", "x-codex-turn-state": "synthetic-turn-state", "openai-model": "gpt-6.1-sol", "x-codex-safety-buffering-enabled": "true", "x-codex-safety-buffering-faster-model": "gpt-6-luna"}
+            })
+        );
+    }
+
+    #[test]
+    fn codex_batch_retains_safe_metadata_in_public_event_order() {
+        let event = json!({"chunks": [
+            {"type": "codex.response.metadata", "headers": {"x-models-etag": "catalog-v3"}},
+            {"type": "codex.rate_limits", "plan_type": "private-plan"},
+            {"type": "response.created", "response": {"id": "resp_synthetic"}, "future": 42}
+        ]});
+        let ResponsesWebSocketRelayDirective::ForwardEvents(events) =
+            CodexResponsesWebSocketAdapter.relay_directive_for_upstream_event(&event)
+        else {
+            panic!("batch must retain public events");
+        };
+        assert_eq!(events.len(), 2);
+        assert_eq!(events[0]["headers"]["x-models-etag"], "catalog-v3");
+        assert_eq!(events[1]["future"], 42);
+    }
+
     #[test]
     fn mixed_codex_batch_forwards_whole_non_private_events_in_order() {
         let adapter = CodexResponsesWebSocketAdapter;

apps/aether-gateway/src/handlers/proxy/websocket/responses/admission.rs

@@ -11,7 +11,8 @@ use aether_contracts::ExecutionPlan;
 
 use crate::execution_runtime::acquire_upstream_execution_gate;
 use crate::provider_pool_demand::{
-    acquire_provider_pool_execution_guard, ProviderPoolInFlightAdmission, ProviderPoolInFlightGuard,
+    acquire_provider_pool_execution_guard, acquire_provider_pool_execution_guard_unobserved,
+    ProviderPoolInFlightAdmission, ProviderPoolInFlightGuard,
 };
 use crate::upstream_admission::UpstreamTargetAdmissionPermit;
 use crate::{AppState, GatewayError};
@@ -28,6 +29,7 @@ impl ResponsesWebSocketTurnAdmission {
         state: &AppState,
         plan: &ExecutionPlan,
         trace_id: &str,
+        observation_context: Option<&serde_json::Value>,
     ) -> Result<Self, GatewayError> {
         let upstream_execution = acquire_upstream_execution_gate(state, trace_id).await?;
         let upstream_target = match state
@@ -41,7 +43,13 @@ impl ResponsesWebSocketTurnAdmission {
                 return Err(error);
             }
         };
-        let provider_pool = match acquire_provider_pool_execution_guard(state, plan).await? {
+        let provider_admission = match observation_context {
+            Some(context) => {
+                acquire_provider_pool_execution_guard(state, plan, Some(context)).await?
+            }
+            None => acquire_provider_pool_execution_guard_unobserved(state, plan).await?,
+        };
+        let provider_pool = match provider_admission {
             ProviderPoolInFlightAdmission::Acquired(guard) => guard,
             ProviderPoolInFlightAdmission::Saturated { limit } => {
                 drop(upstream_target);

apps/aether-gateway/src/handlers/proxy/websocket/responses/connection.rs

@@ -610,6 +610,7 @@ pub(super) async fn relay_bound_connection(
                     }
                     Some(ResponsesWebSocketRelayDirective::ForwardEvents(events)) => {
                         for event in events {
+                            let event = event.as_ref();
                             let text = match bound
                                 .redaction_restorer
                                 .restore_provider_frame_text(event)

apps/aether-gateway/src/handlers/proxy/websocket/responses/control.rs

@@ -32,6 +32,8 @@ pub(super) struct ResponsesWebSocketTurnControl {
     pub(super) decision: GatewayControlDecision,
     pub(super) auth_snapshot: Option<GatewayAuthApiKeySnapshot>,
     pub(super) rpm_bypassed: bool,
+    // Shared across transparent retries and owned by LogicalTurn, not the socket.
+    pub(super) activity: std::sync::Arc<crate::request_activity::RequestActivityGuard>,
 }
 
 pub(super) async fn resolve_responses_websocket_turn_control(
@@ -124,6 +126,7 @@ pub(super) async fn resolve_responses_websocket_turn_control(
         decision,
         auth_snapshot,
         rpm_bypassed,
+        activity: std::sync::Arc::new(state.request_activity.begin()),
     })
 }
 

apps/aether-gateway/src/handlers/proxy/websocket/responses/turn.rs

@@ -606,6 +606,7 @@ pub(super) async fn begin_unowned_responses_websocket_turn(
         state,
         &plan,
         plan.request_id.as_str(),
+        Some(report_context.as_ref().unwrap_or(&Value::Null)),
     )
     .await
     {

apps/aether-gateway/src/handlers/proxy/websocket/responses/turn_state.rs

@@ -260,6 +260,52 @@ mod tests {
         )
     }
 
+    #[test]
+    fn concurrency_activity_survives_retry_and_ends_with_the_logical_turn() {
+        let activity = std::sync::Arc::new(crate::request_activity::RequestActivity::default());
+        let first = logical().with_turn_control(super::ResponsesWebSocketTurnControl {
+            decision: crate::control::GatewayControlDecision::synthetic(
+                "/v1/responses",
+                Some("ai_public".into()),
+                None,
+                None,
+                None,
+            ),
+            auth_snapshot: None,
+            rpm_bypassed: false,
+            activity: std::sync::Arc::new(activity.begin()),
+        });
+        let mut state = ResponsesTurnState::Idle;
+        state.begin(first, FakeAttempt(1));
+        assert_eq!(activity.active(), 1);
+        assert_eq!(state.detach_attempt(), Some(FakeAttempt(1)));
+        assert_eq!(
+            activity.active(),
+            1,
+            "transparent retry retains one logical request"
+        );
+        state.resume(FakeAttempt(2)).unwrap();
+        assert_eq!(activity.active(), 1);
+        assert_eq!(state.end(), Some(FakeAttempt(2)));
+        assert_eq!(activity.active(), 0);
+
+        let logical = logical().with_turn_control(super::ResponsesWebSocketTurnControl {
+            decision: crate::control::GatewayControlDecision::synthetic(
+                "/v1/responses",
+                Some("ai_public".into()),
+                None,
+                None,
+                None,
+            ),
+            auth_snapshot: None,
+            rpm_bypassed: false,
+            activity: std::sync::Arc::new(activity.begin()),
+        });
+        state.begin(logical, FakeAttempt(3));
+        drop(state);
+        assert_eq!(activity.active(), 0, "disconnect drops the logical request");
+    }
+
     /// 透明重试失败之后：旧 attempt 已经被 detach 并结算过，logical turn 仍停在
     /// `Replanning`。此时 `end()` 不能再交出 attempt，否则同一个 attempt 会被
     /// 结算两次（两条 usage terminal、两次 pool lease 释放）。

apps/aether-gateway/src/handlers/public/support.rs

@@ -166,6 +166,23 @@ async fn build_local_public_support_response(
         return None;
     }
 
+    if decision.route_family.as_deref() == Some("health_user") {
+        if let Err(response) =
+            resolve_authenticated_local_user(state, request_context, headers).await
+        {
+            return Some(response);
+        }
+        return Some(
+            crate::handlers::shared::health_monitor::build_health_v2_response(
+                state,
+                &request_context.request_path,
+                request_context.request_query_string.as_deref(),
+                crate::handlers::shared::health_monitor::HealthAudience::Authenticated,
+            )
+            .await,
+        );
+    }
+
     if decision.route_family.as_deref() == Some("auth") {
         return maybe_build_local_auth_response(
             state,
@@ -306,6 +323,17 @@ async fn build_local_public_support_response(
     }
 
     if decision.route_family.as_deref() == Some("public_catalog") {
+        if decision.route_kind.as_deref() == Some("health_v2") {
+            return Some(
+                crate::handlers::shared::health_monitor::build_health_v2_response(
+                    state,
+                    &request_context.request_path,
+                    request_context.request_query_string.as_deref(),
+                    crate::handlers::shared::health_monitor::HealthAudience::Public,
+                )
+                .await,
+            );
+        }
         if decision.route_kind.as_deref() == Some("site_info")
             && request_context.request_path == "/api/public/site-info"
         {

apps/aether-gateway/src/handlers/public/support/announcements/user_routes.rs

@@ -1,3 +1,4 @@
+use aether_data::repository::announcements::UserAnnouncementListQuery;
 use axum::{
     body::Body,
     http,
@@ -33,6 +34,40 @@ fn parse_announcement_read_status_request(
     }
 }
 
+fn parse_user_announcements_query(
+    raw: Option<&str>,
+    now_unix_secs: u64,
+) -> Result<UserAnnouncementListQuery, String> {
+    let mut query = UserAnnouncementListQuery {
+        unread_only: false,
+        offset: 0,
+        limit: 20,
+        now_unix_secs,
+    };
+    let mut seen = std::collections::BTreeSet::new();
+    for (key, value) in url::form_urlencoded::parse(raw.unwrap_or_default().as_bytes()) {
+        if !seen.insert(key.clone()) {
+            return Err(format!("duplicate announcement query parameter: {key}"));
+        }
+        match key.as_ref() {
+            "limit" => {
+                query.limit = value.parse().map_err(|_| "invalid announcement limit")?;
+            }
+            "offset" => {
+                query.offset = value.parse().map_err(|_| "invalid announcement offset")?;
+            }
+            "unread_only" => {
+                query.unread_only = value
+                    .parse()
+                    .map_err(|_| "unread_only must be true or false")?;
+            }
+            _ => return Err(format!("unsupported announcement query parameter: {key}")),
+        }
+    }
+    query.validate().map_err(|err| err.to_string())?;
+    Ok(query)
+}
+
 pub(crate) async fn maybe_build_local_announcement_user_response(
     state: &AppState,
     request_context: &GatewayPublicRequestContext,
@@ -54,6 +89,48 @@ pub(crate) async fn maybe_build_local_announcement_user_response(
     let now_unix_secs = chrono::Utc::now().timestamp().max(0) as u64;
 
     match decision.route_kind.as_deref() {
+        Some("list")
+            if request_context.request_method == http::Method::GET
+                && matches!(
+                    request_context.request_path.as_str(),
+                    "/api/announcements/users/me" | "/api/announcements/users/me/"
+                ) =>
+        {
+            let query = match parse_user_announcements_query(
+                request_context.request_query_string.as_deref(),
+                now_unix_secs,
+            ) {
+                Ok(query) => query,
+                Err(detail) => return Some(announcements_bad_request_response(detail)),
+            };
+            let page = match state.list_user_announcements(&auth.user.id, &query).await {
+                Ok(page) => page,
+                Err(err) => {
+                    return Some(announcements_internal_error_response(
+                        announcements_internal_detail(err),
+                    ))
+                }
+            };
+            let items = page
+                .items
+                .iter()
+                .map(|item| {
+                    let mut value = build_public_announcement_payload(&item.announcement);
+                    value["is_read"] = json!(item.is_read);
+                    value
+                })
+                .collect::<Vec<_>>();
+            Some(
+                Json(json!({
+                    "items": items,
+                    "total": page.total,
+                    "unread_count": page.unread_count,
+                    "limit": query.limit,
+                    "offset": query.offset,
+                }))
+                .into_response(),
+            )
+        }
         Some("unread_count")
             if request_context.request_method == http::Method::GET
                 && matches!(

apps/aether-gateway/src/handlers/public/support/user_me_usage.rs

@@ -1211,6 +1211,7 @@ pub(super) async fn handle_users_me_usage_get(
                 limit: None,
                 offset: None,
                 newest_first: true,
+                ..Default::default()
             };
             total_record_count = match state
                 .count_usage_audits_by_keyword_search(&keyword_query)
@@ -1261,6 +1262,7 @@ pub(super) async fn handle_users_me_usage_get(
                     limit: None,
                     offset: None,
                     newest_first: true,
+                    ..Default::default()
                 })
                 .await
             {
@@ -1291,6 +1293,7 @@ pub(super) async fn handle_users_me_usage_get(
                     limit: Some(limit),
                     offset: Some(offset),
                     newest_first: true,
+                    ..Default::default()
                 })
                 .await
             {
@@ -1436,6 +1439,7 @@ pub(super) async fn handle_users_me_usage_active_get(
                 limit: Some(50),
                 offset: None,
                 newest_first: true,
+                ..Default::default()
             })
             .await
         {
@@ -1926,6 +1930,29 @@ mod tests {
         assert_eq!(active["reasoning_effort"], "max");
     }
 
+    #[test]
+    fn user_usage_payloads_expose_gemini_thinking_config_reasoning_mapping() {
+        let item = StoredRequestUsageAudit {
+            request_body: Some(json!({
+                "generationConfig": {
+                    "thinkingConfig": { "includeThoughts": true, "thinkingLevel": "HIGH" }
+                }
+            })),
+            provider_request_body: Some(json!({
+                "generationConfig": { "thinkingConfig": { "thinkingBudget": 8192 } }
+            })),
+            ..sample_usage("completed")
+        };
+
+        let record = build_users_me_usage_record_payload(&item, false, &BTreeMap::new(), false);
+        let active = build_users_me_usage_active_payload(&item);
+
+        assert_eq!(record["requested_reasoning_effort"], "high");
+        assert_eq!(active["requested_reasoning_effort"], "high");
+        assert_eq!(record["reasoning_effort"], "xhigh");
+        assert_eq!(active["reasoning_effort"], "xhigh");
+    }
+
     #[test]
     fn user_usage_payloads_expose_websocket_transport() {
         let item = StoredRequestUsageAudit {

apps/aether-gateway/src/handlers/shared/catalog.rs

@@ -2681,6 +2681,84 @@ fn windsurf_quota_snapshot_has_stale_cooldown(quota_snapshot: &Map<String, Value
     has_capacity || !exhausted
 }
 
+/// 读取状态快照时，把已越过重置时间点的配额窗口按“已重置”口径归一化。
+///
+/// 背景：调度侧早已把到期窗口视为未耗尽（`provider_pool_reset_deadline_elapsed`），
+/// 账号额度文本也会按到期强制显示 100%，但列表读取此前直接返回存量快照，
+/// 导致管理端倒计时归零后进度条仍停留在旧的剩余百分比。这里让读取层与
+/// 调度侧、文本侧使用同一口径，避免三处状态互相矛盾。
+///
+/// 覆盖所有带重置时间的提供商窗口（codex/kiro/xai/grok/antigravity/
+/// gemini_cli/chatgpt_web/windsurf 等）：比例（used_ratio/remaining_ratio）、
+/// 数值（used_value/remaining_value）与窗口级耗尽标记会一起恢复为“已重置”。
+fn normalize_expired_quota_windows(snapshot: &mut serde_json::Map<String, Value>) {
+    let Some(quota) = snapshot.get_mut("quota").and_then(Value::as_object_mut) else {
+        return;
+    };
+    let now_unix_secs = SystemTime::now()
+        .duration_since(UNIX_EPOCH)
+        .ok()
+        .map(|duration| duration.as_secs())
+        .unwrap_or(0);
+    let fallback_observed_at = provider_quota_timestamp_unix_secs(quota.get("observed_at"))
+        .or_else(|| provider_quota_timestamp_unix_secs(quota.get("updated_at")));
+    let Some(windows) = quota.get_mut("windows").and_then(Value::as_array_mut) else {
+        return;
+    };
+
+    for window in windows.iter_mut().filter_map(Value::as_object_mut) {
+        // 与同类窗口处理保持一致：window_minutes=0 不是真实配额窗口。
+        if window.get("window_minutes").and_then(Value::as_u64) == Some(0) {
+            continue;
+        }
+        if !aether_provider_pool::provider_pool_reset_deadline_elapsed(
+            window,
+            fallback_observed_at,
+            now_unix_secs,
+        ) {
+            continue;
+        }
+        // 只归一化“观测完整”的窗口：要么有比例观测，要么有上限 + 用量数值。
+        // 这样既不会把无数据窗口凭空显示成 100%，也不会出现比例已恢复 100%
+        // 而数值仍停留在旧值的不一致（例如只有 remaining_value 却没有上限的窗口）。
+        let has_ratio_observation = ["used_ratio", "remaining_ratio"]
+            .into_iter()
+            .any(|field| window.get(field).is_some_and(Value::is_number));
+        let limit_value = window
+            .get("limit_value")
+            .and_then(admin_provider_quota_pure::coerce_json_f64)
+            .filter(|value| *value > 0.0);
+        let has_value_observation = limit_value.is_some()
+            && ["used_value", "remaining_value"]
+                .into_iter()
+                .any(|field| window.get(field).is_some_and(Value::is_number));
+        if !has_ratio_observation && !has_value_observation {
+            continue;
+        }
+        // 比例口径：已用清零、剩余 100%；字段原本为 null 时一并补齐，保证展示口径统一。
+        for (field, value) in [("used_ratio", 0.0), ("remaining_ratio", 1.0)] {
+            if window.contains_key(field) {
+                window.insert(field.to_string(), json!(value));
+            }
+        }
+        // 数值口径：已用清零；有上限时把剩余恢复到上限（用于“剩余 x/y”类文本展示）。
+        if window.contains_key("used_value") {
+            window.insert("used_value".to_string(), json!(0.0));
+        }
+        if window.contains_key("remaining_value") {
+            if let Some(limit_value) = limit_value {
+                window.insert("remaining_value".to_string(), json!(limit_value));
+            }
+        }
+        // 同步清掉窗口级耗尽标记，避免展示与调度口径互相矛盾。
+        for field in ["is_exhausted", "exhausted"] {
+            if let Some(slot) = window.get_mut(field) {
+                *slot = json!(false);
+            }
+        }
+    }
+}
+
 pub(crate) fn provider_key_status_snapshot_payload(
     key: &StoredProviderCatalogKey,
     provider_type: &str,
@@ -2722,9 +2800,8 @@ pub(crate) fn provider_key_status_snapshot_payload(
     // Legacy snapshots can retain an exhausted summary after a window reset or
     // newer quota observation. Use the same decision as scheduling so the
     // account list and its status filter do not keep displaying that stale block.
-    if provider_type.trim().eq_ignore_ascii_case("codex")
-        && !aether_provider_pool::provider_pool_key_account_quota_exhausted(key, provider_type)
-    {
+    // 对所有提供商生效：适配器判定已是“重置感知”的，与调度口径保持一致。
+    if !aether_provider_pool::provider_pool_key_account_quota_exhausted(key, provider_type) {
         if let Some(quota) = snapshot.get_mut("quota").and_then(Value::as_object_mut) {
             quota.insert("exhausted".to_string(), json!(false));
             if quota.get("code").and_then(Value::as_str) == Some("exhausted") {
@@ -2732,6 +2809,9 @@ pub(crate) fn provider_key_status_snapshot_payload(
             }
         }
     }
+    // 读取时归一化已到期的配额窗口，保证列表进度条、额度文字与调度侧、
+    // 账号额度文本使用同一“已重置”口径。
+    normalize_expired_quota_windows(&mut snapshot);
     snapshot.insert(
         "oauth".to_string(),
         build_provider_key_oauth_status_snapshot(key),
@@ -3780,6 +3860,421 @@ mod tests {
         assert_eq!(window.get("reset_seconds"), Some(&json!(3_600u64)));
     }
 
+    #[test]
+    fn provider_key_status_snapshot_payload_normalizes_expired_codex_quota_windows() {
+        let mut key = sample_catalog_key();
+        key.status_snapshot = Some(json!({
+            "quota": {
+                "version": 2,
+                "provider_type": "codex",
+                "code": "ok",
+                "exhausted": false,
+                "updated_at": 1_700_000_000u64,
+                "windows": [
+                    {
+                        "code": "5h",
+                        "label": "5H",
+                        "scope": "account",
+                        "unit": "percent",
+                        "used_ratio": 0.88,
+                        "remaining_ratio": 0.12,
+                        "reset_at": 1_700_003_600u64,
+                        "window_minutes": 300
+                    },
+                    {
+                        "code": "weekly",
+                        "label": "周",
+                        "scope": "account",
+                        "unit": "percent",
+                        "used_ratio": 0.5,
+                        "remaining_ratio": 0.5,
+                        "reset_at": 2_000_000_000u64,
+                        "window_minutes": 10_080
+                    },
+                    {
+                        "code": "spark_5h",
+                        "label": "Spark 5H",
+                        "scope": "account",
+                        "unit": "percent",
+                        "reset_at": 1_700_003_600u64,
+                        "window_minutes": 300
+                    },
+                    {
+                        "code": "unlimited",
+                        "label": "无限",
+                        "scope": "account",
+                        "unit": "percent",
+                        "used_ratio": 0.3,
+                        "remaining_ratio": 0.7,
+                        "reset_at": 1_700_003_600u64,
+                        "window_minutes": 0
+                    }
+                ]
+            }
+        }));
+
+        let payload = provider_key_status_snapshot_payload(&key, "codex");
+
+        // 已到期的窗口按“已重置”口径归一化：用量清零、剩余 100%。
+        assert_eq!(payload.pointer("/quota/windows/0/code"), Some(&json!("5h")));
+        assert_eq!(
+            payload.pointer("/quota/windows/0/used_ratio"),
+            Some(&json!(0.0))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/0/remaining_ratio"),
+            Some(&json!(1.0))
+        );
+        // 未到期的窗口保留原始观测值。
+        assert_eq!(
+            payload.pointer("/quota/windows/1/code"),
+            Some(&json!("weekly"))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/1/used_ratio"),
+            Some(&json!(0.5))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/1/remaining_ratio"),
+            Some(&json!(0.5))
+        );
+        // 没有用量观测的窗口不会被凭空补成 100%。
+        assert_eq!(
+            payload.pointer("/quota/windows/2/code"),
+            Some(&json!("spark_5h"))
+        );
+        assert_eq!(payload.pointer("/quota/windows/2/used_ratio"), None);
+        assert_eq!(payload.pointer("/quota/windows/2/remaining_ratio"), None);
+        // window_minutes=0 不是真实配额窗口，与同类 Codex 窗口处理保持一致，不归一化。
+        assert_eq!(
+            payload.pointer("/quota/windows/3/code"),
+            Some(&json!("unlimited"))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/3/used_ratio"),
+            Some(&json!(0.3))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/3/remaining_ratio"),
+            Some(&json!(0.7))
+        );
+    }
+
+    #[test]
+    fn provider_key_status_snapshot_payload_clears_expired_codex_window_exhausted_state() {
+        let mut key = sample_catalog_key();
+        key.status_snapshot = Some(json!({
+            "quota": {
+                "version": 2,
+                "provider_type": "codex",
+                "code": "exhausted",
+                "exhausted": true,
+                "usage_ratio": 1.0,
+                "updated_at": 1_700_000_000u64,
+                "windows": [
+                    {
+                        "code": "weekly",
+                        "label": "周",
+                        "scope": "account",
+                        "unit": "percent",
+                        "used_ratio": 1.0,
+                        "remaining_ratio": 0.0,
+                        "reset_at": 1_700_003_600u64,
+                        "window_minutes": 10_080,
+                        "is_exhausted": true
+                    }
+                ]
+            }
+        }));
+
+        let payload = provider_key_status_snapshot_payload(&key, "codex");
+
+        // 汇总标志沿用既有调度口径（窗口已到期 → 不再视为耗尽）。
+        assert_eq!(payload.pointer("/quota/exhausted"), Some(&json!(false)));
+        assert_eq!(payload.pointer("/quota/code"), Some(&json!("ok")));
+        // 窗口级耗尽标记与剩余比例同步归一化。
+        assert_eq!(
+            payload.pointer("/quota/windows/0/is_exhausted"),
+            Some(&json!(false))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/0/used_ratio"),
+            Some(&json!(0.0))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/0/remaining_ratio"),
+            Some(&json!(1.0))
+        );
+    }
+
+    #[test]
+    fn provider_key_status_snapshot_payload_normalizes_expired_quota_windows_for_other_providers() {
+        let mut key = sample_catalog_key();
+        key.status_snapshot = Some(json!({
+            "quota": {
+                "version": 2,
+                "provider_type": "kiro",
+                "code": "ok",
+                "exhausted": false,
+                "observed_at": 1_700_000_000u64,
+                "updated_at": 1_700_000_000u64,
+                "windows": [
+                    {
+                        "code": "usage",
+                        "label": "额度",
+                        "scope": "account",
+                        "unit": "count",
+                        "used_ratio": 0.4,
+                        "remaining_ratio": 0.6,
+                        "used_value": 60.0,
+                        "remaining_value": 90.0,
+                        "limit_value": 150.0,
+                        "reset_at": 1_700_003_600u64,
+                        "reset_seconds": 3_600u64
+                    },
+                    {
+                        "code": "usage_null_ratio",
+                        "label": "额度",
+                        "scope": "account",
+                        "unit": "count",
+                        "used_ratio": null,
+                        "remaining_ratio": null,
+                        "used_value": 60.0,
+                        "remaining_value": 90.0,
+                        "limit_value": 150.0,
+                        "reset_at": 1_700_003_600u64,
+                        "reset_seconds": 3_600u64
+                    },
+                    {
+                        "code": "usage_active",
+                        "label": "额度",
+                        "scope": "account",
+                        "unit": "count",
+                        "used_ratio": 0.4,
+                        "remaining_ratio": 0.6,
+                        "used_value": 60.0,
+                        "remaining_value": 90.0,
+                        "limit_value": 150.0,
+                        "reset_at": 2_000_000_000u64,
+                        "reset_seconds": 300_000_000u64
+                    },
+                    {
+                        "code": "usage_no_observation",
+                        "label": "额度",
+                        "scope": "account",
+                        "unit": "count",
+                        "reset_at": 1_700_003_600u64,
+                        "reset_seconds": 3_600u64
+                    },
+                    {
+                        "code": "usage_no_deadline",
+                        "label": "额度",
+                        "scope": "account",
+                        "unit": "count",
+                        "used_ratio": 0.4,
+                        "remaining_ratio": 0.6,
+                        "used_value": 60.0,
+                        "remaining_value": 90.0,
+                        "limit_value": 150.0
+                    },
+                    {
+                        "code": "usage_remaining_without_limit",
+                        "label": "额度",
+                        "scope": "account",
+                        "unit": "count",
+                        "used_ratio": null,
+                        "remaining_ratio": null,
+                        "remaining_value": 0.0,
+                        "reset_at": 1_700_003_600u64,
+                        "reset_seconds": 3_600u64
+                    }
+                ]
+            }
+        }));
+
+        let payload = provider_key_status_snapshot_payload(&key, "kiro");
+
+        // 已到期窗口：比例与数值一起按“已重置”归一化（不再只覆盖 Codex）。
+        assert_eq!(
+            payload.pointer("/quota/windows/0/used_ratio"),
+            Some(&json!(0.0))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/0/remaining_ratio"),
+            Some(&json!(1.0))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/0/used_value"),
+            Some(&json!(0.0))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/0/remaining_value"),
+            Some(&json!(150.0))
+        );
+        // 比例字段为 null 时补齐为已重置口径，保证优先读比例的展示实现一致。
+        assert_eq!(
+            payload.pointer("/quota/windows/1/used_ratio"),
+            Some(&json!(0.0))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/1/remaining_ratio"),
+            Some(&json!(1.0))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/1/used_value"),
+            Some(&json!(0.0))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/1/remaining_value"),
+            Some(&json!(150.0))
+        );
+        // 未到期窗口保留原始观测值。
+        assert_eq!(
+            payload.pointer("/quota/windows/2/used_ratio"),
+            Some(&json!(0.4))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/2/remaining_value"),
+            Some(&json!(90.0))
+        );
+        // 没有用量观测的窗口不会被凭空补成 100%。
+        assert_eq!(payload.pointer("/quota/windows/3/used_ratio"), None);
+        assert_eq!(payload.pointer("/quota/windows/3/remaining_ratio"), None);
+        // 没有重置时间的窗口无法判定是否已重置，保持原样。
+        assert_eq!(
+            payload.pointer("/quota/windows/4/used_ratio"),
+            Some(&json!(0.4))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/4/remaining_ratio"),
+            Some(&json!(0.6))
+        );
+        // 只有 remaining_value 却没有上限的窗口观测不完整，跳过归一化，
+        // 避免比例已恢复 100% 而数值仍停留在旧值。
+        assert_eq!(
+            payload.pointer("/quota/windows/5/remaining_ratio"),
+            Some(&json!(null))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/5/remaining_value"),
+            Some(&json!(0.0))
+        );
+    }
+
+    #[test]
+    fn provider_key_status_snapshot_payload_clears_expired_quota_exhausted_state_for_other_providers(
+    ) {
+        let mut key = sample_catalog_key();
+        key.status_snapshot = Some(json!({
+            "quota": {
+                "version": 2,
+                "provider_type": "kiro",
+                "code": "exhausted",
+                "label": "额度耗尽",
+                "reason": "额度已耗尽",
+                "exhausted": true,
+                "usage_ratio": 1.0,
+                "observed_at": 1_700_000_000u64,
+                "updated_at": 1_700_000_000u64,
+                "windows": [
+                    {
+                        "code": "usage",
+                        "label": "额度",
+                        "scope": "account",
+                        "unit": "count",
+                        "used_ratio": 1.0,
+                        "remaining_ratio": 0.0,
+                        "used_value": 150.0,
+                        "remaining_value": 0.0,
+                        "limit_value": 150.0,
+                        "reset_at": 1_700_003_600u64,
+                        "reset_seconds": 3_600u64,
+                        "is_exhausted": true
+                    }
+                ]
+            }
+        }));
+
+        let payload = provider_key_status_snapshot_payload(&key, "kiro");
+
+        // 汇总状态沿用调度口径（窗口已到期 → 不再视为耗尽），对所有提供商生效。
+        assert_eq!(payload.pointer("/quota/exhausted"), Some(&json!(false)));
+        assert_eq!(payload.pointer("/quota/code"), Some(&json!("ok")));
+        // 窗口比例、数值与耗尽标记同步归一化。
+        assert_eq!(
+            payload.pointer("/quota/windows/0/is_exhausted"),
+            Some(&json!(false))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/0/used_ratio"),
+            Some(&json!(0.0))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/0/remaining_ratio"),
+            Some(&json!(1.0))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/0/used_value"),
+            Some(&json!(0.0))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/0/remaining_value"),
+            Some(&json!(150.0))
+        );
+    }
+
+    #[test]
+    fn provider_key_status_snapshot_payload_keeps_active_quota_exhausted_state_for_other_providers()
+    {
+        let mut key = sample_catalog_key();
+        key.status_snapshot = Some(json!({
+            "quota": {
+                "version": 2,
+                "provider_type": "kiro",
+                "code": "exhausted",
+                "label": "额度耗尽",
+                "exhausted": true,
+                "usage_ratio": 1.0,
+                "observed_at": 1_700_000_000u64,
+                "updated_at": 1_700_000_000u64,
+                "windows": [
+                    {
+                        "code": "usage",
+                        "label": "额度",
+                        "scope": "account",
+                        "unit": "count",
+                        "used_ratio": 1.0,
+                        "remaining_ratio": 0.0,
+                        "used_value": 150.0,
+                        "remaining_value": 0.0,
+                        "limit_value": 150.0,
+                        "reset_at": 2_000_000_000u64,
+                        "reset_seconds": 300_000_000u64,
+                        "is_exhausted": true
+                    }
+                ]
+            }
+        }));
+
+        let payload = provider_key_status_snapshot_payload(&key, "kiro");
+
+        // 未到期的耗尽状态保留，不能被读取层提前“恢复”。
+        assert_eq!(payload.pointer("/quota/exhausted"), Some(&json!(true)));
+        assert_eq!(payload.pointer("/quota/code"), Some(&json!("exhausted")));
+        assert_eq!(
+            payload.pointer("/quota/windows/0/is_exhausted"),
+            Some(&json!(true))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/0/used_ratio"),
+            Some(&json!(1.0))
+        );
+        assert_eq!(
+            payload.pointer("/quota/windows/0/remaining_ratio"),
+            Some(&json!(0.0))
+        );
+    }
+
     #[test]
     fn provider_key_status_snapshot_payload_backfills_chatgpt_web_image_quota() {
         let mut key = sample_catalog_key();
@@ -3911,14 +4406,14 @@ mod tests {
                         "used_percent": 60.0,
                         "remaining": 60.0,
                         "total": 150.0,
-                        "reset_at": 1_778_157_172u64,
+                        "reset_at": 2_000_000_000u64,
                         "is_exhausted": false
                     },
                     "quota_heavy": {
                         "display_name": "heavy",
                         "remaining_fraction": 0.0,
                         "used_percent": 100.0,
-                        "reset_at": 1_778_157_172u64,
+                        "reset_at": 2_000_000_000u64,
                         "is_exhausted": true
                     }
                 }
@@ -3941,7 +4436,7 @@ mod tests {
         assert_eq!(quota.get("pool_tier"), Some(&json!("heavy")));
         assert_eq!(quota.get("exhausted"), Some(&json!(false)));
         assert_eq!(quota.get("usage_ratio"), Some(&json!(1.0)));
-        assert_eq!(quota.get("reset_at"), Some(&json!(1_778_157_172u64)));
+        assert_eq!(quota.get("reset_at"), Some(&json!(2_000_000_000u64)));
         assert_eq!(windows.len(), 2);
         assert!(windows.iter().any(|window| {
             window
@@ -4054,8 +4549,8 @@ mod tests {
                 "plan_name": "Pro",
                 "daily_remaining_percent": 40.0,
                 "weekly_remaining_percent": 65.0,
-                "daily_reset_at": 1_778_100_000u64,
-                "weekly_reset_at": 1_778_600_000u64,
+                "daily_reset_at": 2_000_000_000u64,
+                "weekly_reset_at": 2_000_600_000u64,
                 "prompt_used": 12.0,
                 "prompt_limit": 100.0,
                 "prompt_remaining": 88.0,
@@ -4090,13 +4585,13 @@ mod tests {
         assert_eq!(quota.get("code"), Some(&json!("ok")));
         assert_eq!(quota.get("plan_type"), Some(&json!("Pro")));
         assert_eq!(quota.get("usage_ratio"), Some(&json!(0.6)));
-        assert_eq!(quota.get("reset_at"), Some(&json!(1_778_100_000u64)));
+        assert_eq!(quota.get("reset_at"), Some(&json!(2_000_000_000u64)));
         assert_eq!(daily.get("remaining_ratio"), Some(&json!(0.4)));
         assert_eq!(daily.get("used_ratio"), Some(&json!(0.6)));
-        assert_eq!(daily.get("reset_seconds"), Some(&json!(32_754u64)));
+        assert_eq!(daily.get("reset_seconds"), Some(&json!(221_932_754u64)));
         assert_eq!(weekly.get("remaining_ratio"), Some(&json!(0.65)));
         assert_eq!(weekly.get("used_ratio"), Some(&json!(0.35)));
-        assert_eq!(weekly.get("reset_seconds"), Some(&json!(532_754u64)));
+        assert_eq!(weekly.get("reset_seconds"), Some(&json!(222_532_754u64)));
         assert_eq!(quota.get("allowed_models_count"), Some(&json!(82)));
     }
 

apps/aether-gateway/src/handlers/shared/health_monitor/api.rs

@@ -0,0 +1,511 @@
+use super::policy::{overall_status, HealthPolicy, HealthRatio, HealthStatus};
+use super::publication::{HealthPublication, PUBLICATION_KEY};
+use crate::handlers::shared::unix_ms_to_rfc3339;
+use crate::{AppState, GatewayError};
+use aether_data_contracts::repository::global_models::AdminGlobalModelListQuery;
+use aether_data_contracts::repository::usage::{
+    HealthObservationMetrics, HealthObservationObjectKind, HealthObservationQuery,
+};
+use axum::{body::Body, http::StatusCode, response::IntoResponse, response::Response, Json};
+use base64::{engine::general_purpose::URL_SAFE_NO_PAD, Engine};
+use chrono::Utc;
+use serde::Serialize;
+use serde_json::json;
+use std::collections::BTreeMap;
+
+#[derive(Clone, Copy, PartialEq, Eq)]
+pub(crate) enum HealthAudience {
+    Admin,
+    Authenticated,
+    Public,
+}
+
+#[derive(Clone, Debug)]
+pub(super) struct HealthRequest {
+    pub kind: HealthObservationObjectKind,
+    pub from_unix_ms: u64,
+    pub to_unix_ms: u64,
+    pub limit: usize,
+    pub offset: usize,
+}
+
+impl HealthRequest {
+    pub fn parse(query: Option<&str>, public: bool, now_ms: u64) -> Result<Self, &'static str> {
+        let mut params = BTreeMap::new();
+        for (key, value) in url::form_urlencoded::parse(query.unwrap_or_default().as_bytes()) {
+            if !matches!(key.as_ref(), "kind" | "window" | "limit" | "offset") {
+                return Err("Unsupported health query parameter");
+            }
+            if params
+                .insert(key.into_owned(), value.into_owned())
+                .is_some()
+            {
+                return Err("Duplicate health query parameter");
+            }
+        }
+        let kind = match params
+            .get("kind")
+            .map(String::as_str)
+            .unwrap_or("api_format")
+        {
+            "api_format" => HealthObservationObjectKind::ApiFormat,
+            "model" => HealthObservationObjectKind::Model,
+            "provider" if !public => HealthObservationObjectKind::Provider,
+            _ => return Err("Unsupported health object kind"),
+        };
+        let hours = match params.get("window").map(String::as_str).unwrap_or("6h") {
+            "1h" => 1,
+            "6h" => 6,
+            "24h" => 24,
+            "72h" => 72,
+            _ => return Err("Health window must be 1h, 6h, 24h or 72h"),
+        };
+        let parse_size = |name: &str, default: usize| -> Result<usize, &'static str> {
+            params
+                .get(name)
+                .map(|value| value.parse().map_err(|_| "Invalid pagination value"))
+                .unwrap_or(Ok(default))
+        };
+        let limit = parse_size("limit", 25)?;
+        let offset = parse_size("offset", 0)?;
+        if !(1..=100).contains(&limit) || offset > 10_000 {
+            return Err("Health pagination exceeds the supported range");
+        }
+        Ok(Self {
+            kind,
+            from_unix_ms: now_ms.saturating_sub(hours * 3_600_000),
+            to_unix_ms: now_ms,
+            limit,
+            offset,
+        })
+    }
+}
+
+#[derive(Clone, Debug, Serialize)]
+pub(super) struct HealthCoverage {
+    pub status: &'static str,
+    pub sample_status: &'static str,
+    pub classified_count: u64,
+    pub unknown_failure_count: u64,
+    pub excluded_count: u64,
+    pub exclusion_policy: &'static str,
+}
+
+#[derive(Clone, Debug, Serialize)]
+pub(super) struct PublicHealthObject {
+    pub id: String,
+    pub kind: HealthObservationObjectKind,
+    pub name: String,
+    pub status: HealthStatus,
+    pub request_count: u64,
+    pub request_success: HealthRatio,
+    pub service_availability: HealthRatio,
+    pub coverage: HealthCoverage,
+    pub average_latency_ms: Option<f64>,
+    pub latency_sample_count: u64,
+    pub last_request_at: Option<String>,
+    pub timeline: Vec<PublicHealthBucket>,
+}
+
+#[derive(Clone, Debug, Serialize)]
+pub(super) struct PublicHealthBucket {
+    pub from: String,
+    pub to: String,
+    pub status: HealthStatus,
+    pub service_availability: HealthRatio,
+    pub unknown_failure_count: u64,
+}
+
+#[derive(Clone, Debug, Serialize)]
+pub(super) struct AdminHealthObject {
+    #[serde(flatten)]
+    pub service: PublicHealthObject,
+    pub source_value: String,
+    pub attempts: AdminAttemptMetrics,
+}
+
+#[derive(Clone, Debug, Serialize)]
+pub(super) struct AdminAttemptMetrics {
+    pub succeeded_count: u64,
+    pub failed_count: u64,
+    pub in_progress_count: u64,
+    pub cancelled_count: u64,
+    pub success: HealthRatio,
+}
+
+pub(super) fn public_projection(
+    id: String,
+    kind: HealthObservationObjectKind,
+    name: String,
+    metrics: &HealthObservationMetrics,
+    policy: &HealthPolicy,
+) -> PublicHealthObject {
+    let classified = metrics
+        .service_succeeded_count
+        .saturating_add(metrics.service_failed_count);
+    PublicHealthObject {
+        id,
+        kind,
+        name,
+        status: policy.status(
+            metrics.service_succeeded_count,
+            metrics.service_failed_count,
+            metrics.unknown_failure_count,
+        ),
+        request_count: metrics.request_count,
+        request_success: HealthRatio::new(
+            metrics.succeeded_count,
+            metrics
+                .succeeded_count
+                .saturating_add(metrics.failed_count)
+                .saturating_add(metrics.cancelled_count),
+        ),
+        service_availability: HealthRatio::new(metrics.service_succeeded_count, classified),
+        coverage: HealthCoverage {
+            status: if metrics.unknown_failure_count > 0 {
+                "partial"
+            } else {
+                "complete"
+            },
+            sample_status: if classified == 0 {
+                "empty"
+            } else if classified < policy.minimum_samples {
+                "insufficient"
+            } else {
+                "sufficient"
+            },
+            classified_count: classified,
+            unknown_failure_count: metrics.unknown_failure_count,
+            excluded_count: metrics.excluded_count,
+            exclusion_policy: "client_cancelled_invalid_input_identity_or_quota_policy",
+        },
+        average_latency_ms: (metrics.latency_sample_count > 0)
+            .then(|| metrics.latency_sum_ms / metrics.latency_sample_count as f64),
+        latency_sample_count: metrics.latency_sample_count,
+        last_request_at: metrics.last_request_at_unix_ms.and_then(unix_ms_to_rfc3339),
+        timeline: Vec::new(),
+    }
+}
+
+fn response_error(status: StatusCode, detail: &str) -> Response<Body> {
+    (status, Json(json!({ "detail": detail }))).into_response()
+}
+
+async fn read_publication(state: &AppState) -> Result<HealthPublication, GatewayError> {
+    let config = match state
+        .read_system_config_json_value_strong(PUBLICATION_KEY)
+        .await?
+    {
+        Some(value) => serde_json::from_value(value).map_err(|error| {
+            GatewayError::Internal(format!("Invalid health publication configuration: {error}"))
+        })?,
+        None => HealthPublication::default(),
+    };
+    config
+        .validate()
+        .map_err(|error| GatewayError::Internal(error.to_string()))?;
+    Ok(config)
+}
+
+pub(crate) async fn build_publication_response(
+    state: &AppState,
+    body: Option<&[u8]>,
+) -> Response<Body> {
+    if let Some(body) = body {
+        let config: HealthPublication = match serde_json::from_slice(body) {
+            Ok(config) => config,
+            Err(_) => {
+                return response_error(
+                    StatusCode::BAD_REQUEST,
+                    "Invalid health publication configuration",
+                )
+            }
+        };
+        if let Err(error) = config.validate() {
+            return response_error(StatusCode::BAD_REQUEST, error);
+        }
+        let value = match serde_json::to_value(&config) {
+            Ok(value) => value,
+            Err(_) => {
+                return response_error(
+                    StatusCode::INTERNAL_SERVER_ERROR,
+                    "Could not encode health publication",
+                )
+            }
+        };
+        return match state
+            .upsert_system_config_json_value(
+                PUBLICATION_KEY,
+                &value,
+                Some("Public status object allowlist"),
+            )
+            .await
+        {
+            Ok(_) => Json(config).into_response(),
+            Err(_) => response_error(
+                StatusCode::SERVICE_UNAVAILABLE,
+                "Health publication is unavailable",
+            ),
+        };
+    }
+    match read_publication(state).await {
+        Ok(config) => Json(config).into_response(),
+        Err(_) => response_error(
+            StatusCode::SERVICE_UNAVAILABLE,
+            "Health publication is unavailable",
+        ),
+    }
+}
+
+pub(crate) async fn build_health_v2_response(
+    state: &AppState,
+    path: &str,
+    query: Option<&str>,
+    audience: HealthAudience,
+) -> Response<Body> {
+    let now_ms = Utc::now().timestamp_millis().max(0) as u64;
+    let request = match HealthRequest::parse(query, audience != HealthAudience::Admin, now_ms) {
+        Ok(request) => request,
+        Err(detail) => return response_error(StatusCode::BAD_REQUEST, detail),
+    };
+    let prefix = match audience {
+        HealthAudience::Public => "/api/public/health/v2/",
+        HealthAudience::Authenticated => "/api/users/me/health/v2/",
+        HealthAudience::Admin => "/api/admin/endpoints/health/v2/",
+    };
+    let tail = path.strip_prefix(prefix).unwrap_or_default();
+    if tail != "summary"
+        && tail != "objects"
+        && !tail
+            .strip_prefix("objects/")
+            .is_some_and(|id| !id.is_empty() && !id.contains('/'))
+    {
+        return response_error(StatusCode::NOT_FOUND, "Health resource not found");
+    }
+    match build_health_payload(state, &request, tail, audience, now_ms).await {
+        Ok(Some(payload)) => Json(payload).into_response(),
+        Ok(None) => response_error(
+            StatusCode::NOT_FOUND,
+            "Health object is not published or does not exist",
+        ),
+        Err(error) => {
+            tracing::warn!(error = %crate::error::redact_error_detail(&format!("{error:?}")), "health observation query failed");
+            response_error(
+                StatusCode::SERVICE_UNAVAILABLE,
+                "Health observations are temporarily unavailable",
+            )
+        }
+    }
+}
+
+async fn admin_objects(
+    state: &AppState,
+    kind: HealthObservationObjectKind,
+) -> Result<BTreeMap<String, String>, GatewayError> {
+    let mut objects = BTreeMap::new();
+    match kind {
+        HealthObservationObjectKind::ApiFormat => {
+            let providers = state.list_provider_catalog_providers(true).await?;
+            let ids: Vec<_> = providers
+                .iter()
+                .map(|provider| provider.id.clone())
+                .collect();
+            for endpoint in state
+                .list_provider_catalog_endpoints_by_provider_ids(&ids)
+                .await?
+            {
+                if endpoint.is_active {
+                    objects.insert(endpoint.api_format.clone(), endpoint.api_format);
+                }
+            }
+        }
+        HealthObservationObjectKind::Provider => {
+            for provider in state.list_provider_catalog_providers(false).await? {
+                objects.insert(provider.id, provider.name);
+            }
+        }
+        HealthObservationObjectKind::Model => {
+            let mut offset = 0;
+            loop {
+                let page = state
+                    .list_admin_global_models(&AdminGlobalModelListQuery {
+                        offset,
+                        limit: 500,
+                        ..Default::default()
+                    })
+                    .await?;
+                for model in &page.items {
+                    objects.insert(model.name.clone(), model.display_name.clone());
+                }
+                offset += page.items.len();
+                if offset >= page.total || page.items.is_empty() {
+                    break;
+                }
+                if offset >= 10_000 {
+                    return Err(GatewayError::Internal(
+                        "Health model catalog exceeds query budget".into(),
+                    ));
+                }
+            }
+        }
+    }
+    Ok(objects)
+}
+
+async fn build_health_payload(
+    state: &AppState,
+    request: &HealthRequest,
+    tail: &str,
+    audience: HealthAudience,
+    now_ms: u64,
+) -> Result<Option<serde_json::Value>, GatewayError> {
+    let policy = HealthPolicy::default();
+    let public = audience == HealthAudience::Public;
+    let redact_internal = audience != HealthAudience::Admin;
+    let publication = if public {
+        Some(read_publication(state).await?)
+    } else {
+        None
+    };
+    if publication.as_ref().is_some_and(|config| !config.enabled) {
+        return Ok(None);
+    }
+    let published: BTreeMap<_, _> = publication
+        .as_ref()
+        .map(|config| {
+            config
+                .objects
+                .iter()
+                .filter(|object| object.kind == request.kind)
+                .map(|object| (object.value.clone(), object))
+                .collect()
+        })
+        .unwrap_or_default();
+    let mut names = if public {
+        published
+            .iter()
+            .map(|(value, object)| (value.clone(), object.display_name.clone()))
+            .collect()
+    } else {
+        admin_objects(state, request.kind).await?
+    };
+    let observation = if public && published.is_empty() {
+        Default::default()
+    } else {
+        state
+            .data
+            .summarize_health_observations(&HealthObservationQuery {
+                from_unix_ms: request.from_unix_ms,
+                to_unix_ms: request.to_unix_ms,
+                object_kind: request.kind,
+                object_values: public.then(|| published.keys().cloned().collect()),
+                segments: 24,
+            })
+            .await
+            .map_err(|error| GatewayError::Internal(error.to_string()))?
+    };
+    let mut metrics_by_value = BTreeMap::new();
+    let mut timeline_by_value = BTreeMap::new();
+    for object in observation.objects {
+        if !public || published.contains_key(&object.object_value) {
+            names
+                .entry(object.object_value.clone())
+                .or_insert_with(|| object.object_value.clone());
+            timeline_by_value.insert(object.object_value.clone(), object.timeline);
+            metrics_by_value.insert(object.object_value, object.metrics);
+        }
+    }
+    let mut objects = Vec::new();
+    for (value, name) in names {
+        let metrics = metrics_by_value.remove(&value).unwrap_or_default();
+        let id = if public {
+            published[&value].public_id.clone()
+        } else {
+            URL_SAFE_NO_PAD.encode(value.as_bytes())
+        };
+        let mut service = public_projection(id, request.kind, name, &metrics, &policy);
+        service.timeline = timeline_by_value
+            .remove(&value)
+            .unwrap_or_default()
+            .into_iter()
+            .map(|bucket| PublicHealthBucket {
+                from: unix_ms_to_rfc3339(bucket.from_unix_ms).unwrap_or_default(),
+                to: unix_ms_to_rfc3339(bucket.to_unix_ms).unwrap_or_default(),
+                status: policy.status(
+                    bucket.metrics.service_succeeded_count,
+                    bucket.metrics.service_failed_count,
+                    bucket.metrics.unknown_failure_count,
+                ),
+                service_availability: HealthRatio::new(
+                    bucket.metrics.service_succeeded_count,
+                    bucket
+                        .metrics
+                        .service_succeeded_count
+                        .saturating_add(bucket.metrics.service_failed_count),
+                ),
+                unknown_failure_count: bucket.metrics.unknown_failure_count,
+            })
+            .collect();
+        objects.push(AdminHealthObject {
+            service,
+            source_value: value,
+            attempts: AdminAttemptMetrics {
+                succeeded_count: metrics.attempt_succeeded_count,
+                failed_count: metrics.attempt_failed_count,
+                in_progress_count: metrics.attempt_in_progress_count,
+                cancelled_count: metrics.attempt_cancelled_count,
+                success: HealthRatio::new(
+                    metrics.attempt_succeeded_count,
+                    metrics
+                        .attempt_succeeded_count
+                        .saturating_add(metrics.attempt_failed_count),
+                ),
+            },
+        });
+    }
+    let status = overall_status(objects.iter().map(|object| object.service.status));
+    let meta = json!({
+        "schema_version": 2, "metric_version": policy.version,
+        "scope": { "kind": match audience { HealthAudience::Public => "published", HealthAudience::Authenticated => "authenticated", HealthAudience::Admin => "installation" }, "object_kind": request.kind },
+        "range": { "from": unix_ms_to_rfc3339(request.from_unix_ms), "to": unix_ms_to_rfc3339(request.to_unix_ms), "timezone": "UTC", "time_basis": "request_started_at" },
+        "generated_at": unix_ms_to_rfc3339(now_ms),
+        "data_through": observation.data_through_unix_ms.and_then(unix_ms_to_rfc3339),
+        "freshness": if observation.data_through_unix_ms.is_some_and(|time| now_ms.saturating_sub(time) > 120_000) { "stale" } else if observation.data_through_unix_ms.is_some() { "current" } else { "unknown" },
+        "policy": policy,
+    });
+    let data = if tail == "summary" {
+        json!({ "status": status, "object_count": objects.len(),
+            "healthy_count": objects.iter().filter(|object| object.service.status == HealthStatus::Healthy).count(),
+            "degraded_count": objects.iter().filter(|object| object.service.status == HealthStatus::Degraded).count(),
+            "unavailable_count": objects.iter().filter(|object| object.service.status == HealthStatus::Unavailable).count(),
+            "unknown_count": objects.iter().filter(|object| object.service.status == HealthStatus::Unknown).count(),
+            "requests": public_projection(String::new(), request.kind, String::new(), &observation.overall, &policy),
+        })
+    } else if let Some(id) = tail.strip_prefix("objects/") {
+        let Some(object) = objects.iter().find(|object| object.service.id == id) else {
+            return Ok(None);
+        };
+        if redact_internal {
+            serde_json::to_value(&object.service)
+        } else {
+            serde_json::to_value(object)
+        }
+        .map_err(|error| GatewayError::Internal(error.to_string()))?
+    } else {
+        let items: Vec<serde_json::Value> = objects
+            .iter()
+            .skip(request.offset)
+            .take(request.limit)
+            .map(|object| {
+                if redact_internal {
+                    serde_json::to_value(&object.service)
+                } else {
+                    serde_json::to_value(object)
+                }
+            })
+            .collect::<Result<_, _>>()
+            .map_err(|error| GatewayError::Internal(error.to_string()))?;
+        json!({ "items": items, "total": objects.len(), "limit": request.limit, "offset": request.offset })
+    };
+    Ok(Some(json!({ "meta": meta, "data": data })))
+}

apps/aether-gateway/src/handlers/shared/health_monitor/mod.rs

@@ -0,0 +1,8 @@
+mod api;
+mod policy;
+mod publication;
+
+pub(crate) use api::{build_health_v2_response, build_publication_response, HealthAudience};
+
+#[cfg(test)]
+mod tests;

apps/aether-gateway/src/handlers/shared/health_monitor/policy.rs

@@ -0,0 +1,95 @@
+use serde::Serialize;
+
+pub(super) const POLICY_VERSION: &str = "service-health-v1";
+
+#[derive(Clone, Copy, Debug, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "snake_case")]
+pub(super) enum HealthStatus {
+    Healthy,
+    Degraded,
+    Unavailable,
+    Unknown,
+}
+
+#[derive(Clone, Debug, Serialize)]
+pub(super) struct HealthPolicy {
+    pub version: &'static str,
+    pub minimum_samples: u64,
+    pub healthy_threshold: f64,
+    pub degraded_threshold: f64,
+}
+
+impl Default for HealthPolicy {
+    fn default() -> Self {
+        Self {
+            version: POLICY_VERSION,
+            minimum_samples: 20,
+            healthy_threshold: 0.99,
+            degraded_threshold: 0.95,
+        }
+    }
+}
+
+#[derive(Clone, Debug, Serialize)]
+pub(super) struct HealthRatio {
+    pub numerator: u64,
+    pub denominator: u64,
+    pub value: Option<f64>,
+}
+
+impl HealthRatio {
+    pub fn new(numerator: u64, denominator: u64) -> Self {
+        Self {
+            numerator,
+            denominator,
+            value: (denominator > 0).then(|| numerator as f64 / denominator as f64),
+        }
+    }
+}
+
+impl HealthPolicy {
+    pub fn status(&self, successes: u64, failures: u64, unknown: u64) -> HealthStatus {
+        let samples = successes.saturating_add(failures);
+        if samples < self.minimum_samples {
+            return HealthStatus::Unknown;
+        }
+        if unknown > 0 {
+            let best_possible_rate =
+                successes.saturating_add(unknown) as f64 / samples.saturating_add(unknown) as f64;
+            return if best_possible_rate < self.degraded_threshold {
+                HealthStatus::Unavailable
+            } else {
+                HealthStatus::Unknown
+            };
+        }
+        let ratio = successes as f64 / samples as f64;
+        if ratio >= self.healthy_threshold {
+            HealthStatus::Healthy
+        } else if ratio >= self.degraded_threshold {
+            HealthStatus::Degraded
+        } else {
+            HealthStatus::Unavailable
+        }
+    }
+}
+
+pub(super) fn overall_status(statuses: impl Iterator<Item = HealthStatus>) -> HealthStatus {
+    let mut result = HealthStatus::Healthy;
+    let mut count = 0;
+    for status in statuses {
+        count += 1;
+        match status {
+            HealthStatus::Unavailable => return HealthStatus::Unavailable,
+            HealthStatus::Degraded => result = HealthStatus::Degraded,
+            HealthStatus::Unknown if result == HealthStatus::Healthy => {
+                result = HealthStatus::Unknown
+            }
+            _ => {}
+        }
+    }
+    if count == 0 {
+        HealthStatus::Unknown
+    } else {
+        result
+    }
+}

apps/aether-gateway/src/handlers/shared/health_monitor/publication.rs

@@ -0,0 +1,60 @@
+use aether_data_contracts::repository::usage::HealthObservationObjectKind;
+use serde::{Deserialize, Serialize};
+use std::collections::BTreeSet;
+
+pub(super) const PUBLICATION_KEY: &str = "health_publication_v1";
+
+#[derive(Clone, Debug, Default, Deserialize, Serialize)]
+#[serde(deny_unknown_fields)]
+pub(super) struct HealthPublication {
+    pub enabled: bool,
+    pub objects: Vec<PublishedHealthObject>,
+}
+
+#[derive(Clone, Debug, Deserialize, Serialize)]
+#[serde(deny_unknown_fields)]
+pub(super) struct PublishedHealthObject {
+    pub public_id: String,
+    pub kind: HealthObservationObjectKind,
+    pub value: String,
+    pub display_name: String,
+}
+
+impl HealthPublication {
+    pub fn validate(&self) -> Result<(), &'static str> {
+        if self.objects.len() > 200 {
+            return Err("At most 200 public health objects may be published");
+        }
+        let mut ids = BTreeSet::new();
+        let mut values = BTreeSet::new();
+        for object in &self.objects {
+            if object.public_id.is_empty()
+                || object.public_id.len() > 80
+                || !object
+                    .public_id
+                    .bytes()
+                    .all(|c| c.is_ascii_alphanumeric() || c == b'-' || c == b'_')
+            {
+                return Err(
+                    "Public IDs must contain 1 to 80 letters, digits, hyphens or underscores",
+                );
+            }
+            if object.kind == HealthObservationObjectKind::Provider {
+                return Err("Internal providers cannot be published as public health objects");
+            }
+            if object.value.trim().is_empty()
+                || object.value.len() > 256
+                || object.display_name.trim().is_empty()
+                || object.display_name.len() > 120
+            {
+                return Err("Every public object requires a bounded source value and display name");
+            }
+            if !ids.insert(object.public_id.clone())
+                || !values.insert(format!("{:?}:{}", object.kind, object.value))
+            {
+                return Err("Public IDs and health source objects must be unique");
+            }
+        }
+        Ok(())
+    }
+}

apps/aether-gateway/src/handlers/shared/health_monitor/tests.rs

@@ -0,0 +1,103 @@
+use super::api::{public_projection, AdminAttemptMetrics, AdminHealthObject, HealthRequest};
+use super::policy::{overall_status, HealthPolicy, HealthRatio, HealthStatus};
+use super::publication::HealthPublication;
+use aether_data_contracts::repository::usage::{
+    HealthObservationMetrics, HealthObservationObjectKind,
+};
+use serde_json::json;
+
+#[test]
+fn health_policy_distinguishes_unknown_and_insufficient_samples() {
+    let policy = HealthPolicy::default();
+    assert_eq!(policy.status(0, 0, 0), HealthStatus::Unknown);
+    assert_eq!(policy.status(19, 0, 0), HealthStatus::Unknown);
+    assert_eq!(policy.status(100, 0, 1), HealthStatus::Unknown);
+    assert_eq!(policy.status(0, 100, 1), HealthStatus::Unavailable);
+    assert_eq!(policy.status(99, 1, 0), HealthStatus::Healthy);
+    assert_eq!(policy.status(96, 4, 0), HealthStatus::Degraded);
+    assert_eq!(policy.status(90, 10, 0), HealthStatus::Unavailable);
+    assert_eq!(HealthRatio::new(0, 0).value, None);
+    assert_eq!(
+        overall_status([HealthStatus::Healthy, HealthStatus::Unknown].into_iter()),
+        HealthStatus::Unknown
+    );
+}
+
+#[test]
+fn health_query_rejects_ambiguous_and_internal_public_filters() {
+    assert!(HealthRequest::parse(Some("provider_id=secret"), true, 30_000_000).is_err());
+    assert!(HealthRequest::parse(Some("kind=provider"), true, 30_000_000).is_err());
+    assert!(HealthRequest::parse(Some("window=6h&window=24h"), false, 30_000_000).is_err());
+    assert!(HealthRequest::parse(Some("limit=101"), false, 30_000_000).is_err());
+    let query = HealthRequest::parse(
+        Some("kind=model&window=1h&limit=50&offset=25"),
+        true,
+        30_000_000,
+    )
+    .unwrap();
+    assert_eq!(query.from_unix_ms, 26_400_000);
+    assert_eq!(query.to_unix_ms, 30_000_000);
+    assert_eq!(query.offset, 25);
+}
+
+#[test]
+fn public_publication_is_explicit_and_rejects_provider_and_duplicate_sources() {
+    let config: HealthPublication = serde_json::from_value(json!({"enabled": true, "objects": [
+        {"public_id": "chat", "kind": "api_format", "value": "openai:chat", "display_name": "Chat"}
+    ]}))
+    .unwrap();
+    assert!(config.validate().is_ok());
+    let mut duplicated = config.clone();
+    duplicated.objects.push(duplicated.objects[0].clone());
+    assert!(duplicated.validate().is_err());
+    let mut provider = config;
+    provider.objects[0].kind = HealthObservationObjectKind::Provider;
+    assert!(provider.validate().is_err());
+    assert!(serde_json::from_value::<HealthPublication>(
+        json!({"enabled": true, "objects": [], "publish_all": true})
+    )
+    .is_err());
+}
+
+#[test]
+fn public_dto_cannot_serialize_internal_source_or_attempts() {
+    let metrics = HealthObservationMetrics {
+        request_count: 105,
+        succeeded_count: 100,
+        failed_count: 4,
+        cancelled_count: 1,
+        service_succeeded_count: 100,
+        service_failed_count: 2,
+        excluded_count: 2,
+        unknown_failure_count: 1,
+        ..Default::default()
+    };
+    let public = public_projection(
+        "chat".into(),
+        HealthObservationObjectKind::ApiFormat,
+        "Chat".into(),
+        &metrics,
+        &HealthPolicy::default(),
+    );
+    assert_eq!(public.request_success.denominator, 105);
+    assert_eq!(public.service_availability.denominator, 102);
+    let admin = AdminHealthObject {
+        service: public.clone(),
+        source_value: "internal-provider-id".into(),
+        attempts: AdminAttemptMetrics {
+            succeeded_count: 100,
+            failed_count: 20,
+            in_progress_count: 1,
+            cancelled_count: 1,
+            success: HealthRatio::new(100, 120),
+        },
+    };
+    let public_json = serde_json::to_value(public).unwrap();
+    assert!(public_json.get("source_value").is_none());
+    assert!(public_json.get("attempts").is_none());
+    assert!(!public_json.to_string().contains("internal-provider-id"));
+    assert!(serde_json::to_value(admin)
+        .unwrap()
+        .get("attempts")
+        .is_some());
+}

apps/aether-gateway/src/handlers/shared/mod.rs

@@ -4,6 +4,7 @@ mod auth_api_key_secret;
 mod catalog;
 mod email_templates;
 mod external_models;
+pub(crate) mod health_monitor;
 mod identity_oauth_provider_secret;
 mod multipart;
 mod normalize;

apps/aether-gateway/src/handlers/shared/request_utils.rs

@@ -232,6 +232,7 @@ pub(crate) fn admin_proxy_local_requires_buffered_body(
                 decision.route_kind.as_deref(),
             ) {
                 (Some("endpoints_manage"), http::Method::POST, Some("create_provider_key"))
+                | (Some("endpoints_health"), http::Method::PUT, Some("health_v2_publication"))
                 | (Some("endpoints_manage"), http::Method::POST, Some("create_endpoint"))
                 | (Some("endpoints_manage"), http::Method::POST, Some("batch_delete_keys"))
                 | (Some("endpoints_manage"), http::Method::POST, Some("refresh_quota"))
@@ -345,6 +346,7 @@ pub(crate) fn admin_proxy_local_requires_buffered_body(
                 | (Some("billing_manage"), http::Method::PUT, Some("update_rule"))
                 | (Some("billing_manage"), http::Method::POST, Some("create_collector"))
                 | (Some("billing_manage"), http::Method::PUT, Some("update_collector"))
+                | (Some("billing_manage"), http::Method::POST, Some("create_provider_expense"))
                 | (Some("billing_manage"), http::Method::POST, Some("create_plan"))
                 | (Some("billing_manage"), http::Method::PUT, Some("update_plan"))
                 | (Some("billing_manage"), http::Method::PATCH, Some("set_plan_status"))

apps/aether-gateway/src/lib.rs

@@ -44,6 +44,7 @@ mod data;
 mod dispatch;
 mod email_delivery;
 mod error;
+mod execution_activity;
 mod execution_runtime;
 mod executor;
 mod fallback_metrics;
@@ -69,6 +70,7 @@ mod provider_key_auth;
 mod provider_pool_demand;
 pub(crate) use aether_provider_transport as provider_transport;
 mod rate_limit;
+mod request_activity;
 mod request_candidate_queue;
 mod request_candidate_runtime;
 mod request_diagnostics;
@@ -90,6 +92,7 @@ mod upstream_admission;
 mod usage;
 mod video_tasks;
 mod wallet_runtime;
+mod xai_profile;
 
 pub use self::ai_serving::api::{codex_client_originator, codex_client_user_agent};
 pub(crate) use self::ai_serving::api::{

apps/aether-gateway/src/main.rs

@@ -2546,6 +2546,20 @@ async fn run() -> Result<(), Box<dyn std::error::Error>> {
             );
         }
     }
+    match state.prewarm_xai_client_profile().await {
+        Ok(version) => {
+            info!(
+                xai_client_version = %version,
+                "prewarmed Grok CLI client profile"
+            );
+        }
+        Err(err) => {
+            warn!(
+                error = %err,
+                "failed to refresh Grok CLI client profile; built-in or cached profile remains active"
+            );
+        }
+    }
     match prewarm_direct_h2c_sender_cache_from_env_for_startup().await {
         Ok(Some(report)) => {
             if report.failed_targets > 0 {

apps/aether-gateway/src/maintenance/runtime/oauth_token_refresh.rs

@@ -155,14 +155,17 @@ pub(crate) async fn perform_oauth_token_refresh_once(
                 Ok(None) => {
                     summary.skipped = summary.skipped.saturating_add(1);
                 }
-                Err(_) => {
+                Err(err) => {
                     summary.failed = summary.failed.saturating_add(1);
                     warn!(
                         event_name = "oauth_token_refresh_failed",
                         log_type = "ops",
                         worker = "oauth_token_refresh",
                         provider_id = %provider.id,
+                        provider_type = %provider.provider_type,
+                        endpoint_id = %endpoint.id,
                         key_id = %key.id,
+                        error = %crate::error::redact_error_debug(&err),
                         "gateway oauth token auto refresh failed"
                     );
                 }
@@ -440,6 +443,7 @@ mod tests {
         agent_identity_needs_task_recovery, auth_config_has_refresh_token,
         is_nonfatal_legacy_catalog_credential_error, oauth_refresh_candidate,
     };
+    use crate::error::redact_error_debug;
     use crate::GatewayError;
 
     #[test]
@@ -543,4 +547,18 @@ mod tests {
             )
         ));
     }
+
+    #[test]
+    fn oauth_refresh_failure_detail_preserves_context_without_credentials() {
+        let error = GatewayError::Internal(
+            r#"oauth request failed: status=503 token="refresh-secret" retry=2"#.to_string(),
+        );
+
+        let detail = redact_error_debug(&error);
+
+        assert!(detail.contains("oauth request failed"));
+        assert!(detail.contains("status=503"));
+        assert!(detail.contains("[REDACTED]"));
+        assert!(!detail.contains("refresh-secret"));
+    }
 }

apps/aether-gateway/src/maintenance/runtime/runners.rs

@@ -669,8 +669,24 @@ pub(super) async fn run_pending_cleanup_once(app: &AppState) -> Result<(), DataL
 pub(super) async fn run_stats_hourly_aggregation_once(
     data: &GatewayDataState,
 ) -> Result<bool, DataLayerError> {
-    let Some(summary) = perform_stats_hourly_aggregation_once(data).await? else {
-        return Ok(false);
+    let legacy = perform_stats_hourly_aggregation_once(data).await;
+    let overview_progress = match super::stats_hourly::perform_overview_rebuild_once(data).await {
+        Ok(progress) => progress,
+        Err(error) => {
+            warn!(event_name = "overview_rebuild_failed", error = ?error,
+                "overview rebuild deferred; legacy statistics remain available");
+            0
+        }
+    };
+    if overview_progress > 0 {
+        info!(
+            event_name = "overview_rebuild_progress",
+            progress = overview_progress,
+            "overview dirty projections rebuilt"
+        );
+    }
+    let Some(summary) = legacy? else {
+        return Ok(overview_progress > 0);
     };
 
     info!(

apps/aether-gateway/src/maintenance/runtime/stats_hourly.rs

@@ -22,3 +22,19 @@ pub(super) async fn perform_stats_hourly_aggregation_once(
     })
     .await
 }
+
+pub(super) async fn perform_overview_rebuild_once(
+    data: &GatewayDataState,
+) -> Result<usize, DataLayerError> {
+    if !data.has_stats_hourly_aggregation_backend()
+        || !system_config_bool(data, "enable_stats_aggregation", true).await?
+    {
+        return Ok(0);
+    }
+    let now_utc = Utc::now();
+    data.rebuild_overview_buckets(&StatsHourlyAggregationInput {
+        target_hour_utc: stats_hourly_aggregation_target_hour(now_utc),
+        aggregated_at: now_utc,
+    })
+    .await
+}

apps/aether-gateway/src/maintenance/runtime/workers.rs

@@ -772,57 +772,96 @@ pub(crate) fn spawn_stats_hourly_aggregation_worker(
         app,
         crate::task_runtime::TASK_KEY_STATS_HOURLY_AGG,
         |app| async move {
-            let data = app.data.clone();
-            let mut deferred_since = None;
-            tokio::time::sleep(STATS_AGGREGATION_STARTUP_GRACE).await;
-            loop {
-                let mut processed = 0_usize;
-                let mut deferred = false;
-                while processed < STATS_HOURLY_CATCH_UP_BURST_LIMIT {
-                    let permit = STATS_AGGREGATION_GATE
-                        .acquire()
-                        .await
-                        .expect("stats aggregation gate should remain open");
-                    if should_defer_stats_aggregation(
-                        &app,
+            // Both loops belong to the singleton lease future. Losing the
+            // lease/shutting down drops them together; no detached task survives.
+            let drain = async {
+                let data = app.data.clone();
+                let mut deferred_since = None;
+                let mut interval = tokio::time::interval(Duration::from_secs(10));
+                interval.set_missed_tick_behavior(tokio::time::MissedTickBehavior::Skip);
+                loop {
+                    interval.tick().await;
+                    if should_defer_for_database_pressure(
                         &data,
-                        "stats_hourly_aggregation",
+                        "overview_dirty_drain",
                         &mut deferred_since,
                     ) {
-                        drop(permit);
-                        deferred = true;
-                        break;
+                        continue;
                     }
-                    match run_stats_hourly_aggregation_once(&data).await {
-                        Ok(true) => {
-                            processed += 1;
-                            tokio::time::sleep(STATS_CATCH_UP_BUCKET_PAUSE).await;
-                            drop(permit);
+                    // At most ten batches per tick; normal traffic and idle
+                    // installations stop after the first empty batch.
+                    for _ in 0..10 {
+                        match data.drain_overview_dirty_events(Utc::now()).await {
+                            Ok(0) => break,
+                            Ok(_) => tokio::task::yield_now().await,
+                            Err(err) => {
+                                log_maintenance_worker_failure(
+                                    "overview_dirty_drain",
+                                    "tick",
+                                    &err,
+                                );
+                                break;
+                            }
                         }
-                        Ok(false) => break,
-                        Err(err) => {
-                            log_maintenance_worker_failure(
-                                "stats_hourly_aggregation",
-                                "tick",
-                                &err,
-                            );
+                    }
+                }
+            };
+            let hourly = async {
+                let data = app.data.clone();
+                let mut deferred_since = None;
+                tokio::time::sleep(STATS_AGGREGATION_STARTUP_GRACE).await;
+                loop {
+                    let mut processed = 0_usize;
+                    let mut deferred = false;
+                    while processed < STATS_HOURLY_CATCH_UP_BURST_LIMIT {
+                        let permit = STATS_AGGREGATION_GATE
+                            .acquire()
+                            .await
+                            .expect("stats aggregation gate should remain open");
+                        if should_defer_stats_aggregation(
+                            &app,
+                            &data,
+                            "stats_hourly_aggregation",
+                            &mut deferred_since,
+                        ) {
+                            drop(permit);
+                            deferred = true;
                             break;
                         }
+                        match run_stats_hourly_aggregation_once(&data).await {
+                            Ok(true) => {
+                                processed += 1;
+                                tokio::time::sleep(STATS_CATCH_UP_BUCKET_PAUSE).await;
+                                drop(permit);
+                            }
+                            Ok(false) => break,
+                            Err(err) => {
+                                log_maintenance_worker_failure(
+                                    "stats_hourly_aggregation",
+                                    "tick",
+                                    &err,
+                                );
+                                break;
+                            }
+                        }
                     }
-                }
 
-                if deferred {
-                    tokio::time::sleep(MAINTENANCE_PRESSURE_RETRY_INTERVAL).await;
-                    continue;
-                }
+                    if deferred {
+                        tokio::time::sleep(MAINTENANCE_PRESSURE_RETRY_INTERVAL).await;
+                        continue;
+                    }
 
-                if processed >= STATS_HOURLY_CATCH_UP_BURST_LIMIT {
-                    continue;
-                }
+                    if processed >= STATS_HOURLY_CATCH_UP_BURST_LIMIT {
+                        continue;
+                    }
 
-                tokio::time::sleep(duration_until_next_stats_hourly_aggregation_run(Utc::now()))
+                    tokio::time::sleep(
+                        duration_until_next_stats_hourly_aggregation_run(Utc::now()),
+                    )
                     .await;
-            }
+                }
+            };
+            tokio::join!(drain, hourly);
         },
     ))
 }

apps/aether-gateway/src/model_fetch/catalog.rs

@@ -2663,14 +2663,11 @@ mod tests {
         assert_eq!(plans.len(), 2);
         assert!(plans[0].url.ends_with("/models?client_version=0.145.2"));
         assert!(plans[1].url.ends_with("/models?client_version=0.146.0"));
-        assert_eq!(
-            plans[0].headers.get("user-agent").map(String::as_str),
-            Some("codex_cli_rs/0.145.2")
-        );
-        assert_eq!(
-            plans[1].headers.get("user-agent").map(String::as_str),
-            Some("codex_cli_rs/0.146.0")
-        );
+        for (plan, version) in plans.iter().zip(["0.145.2", "0.146.0"]) {
+            let ua = plan.headers.get("user-agent").expect("画像应包含 UA");
+            assert!(ua.starts_with(&format!("codex_cli_rs/{version} (")));
+            assert!(ua.ends_with(") unknown"));
+        }
 
         let target = target();
         assert_ne!(

apps/aether-gateway/src/orchestration/mod.rs

@@ -155,6 +155,17 @@ pub(crate) fn with_error_flow_report_context(
     error_flow: Value,
 ) -> Option<Value> {
     let mut object = report_context?.as_object()?.clone();
+    if !object.contains_key("analytics_failure")
+        && error_flow.get("source").and_then(Value::as_str) == Some("upstream_response")
+        && error_flow
+            .get("status_code")
+            .and_then(Value::as_u64)
+            .is_some_and(|status| status >= 400)
+    {
+        object.insert("analytics_failure".into(), json!({
+            "origin": "upstream", "stage": "response", "reason": "upstream_response_error", "schema_version": 1,
+        }));
+    }
     object.insert("error_flow".to_string(), error_flow);
     Some(Value::Object(object))
 }

apps/aether-gateway/src/provider_pool_demand.rs

@@ -49,6 +49,7 @@ pub(crate) struct ProviderPoolDemandSnapshot {
 pub(crate) struct ProviderPoolInFlightGuard {
     kind: ProviderPoolInFlightGuardKind,
     provider_key_permit: Option<RuntimeSemaphorePermit>,
+    observed_activity: Option<crate::execution_activity::ExecutionActivityGuard>,
     released: bool,
 }
 
@@ -73,11 +74,28 @@ enum ProviderPoolInFlightGuardKind {
 }
 
 impl ProviderPoolInFlightGuard {
+    fn observe_execution(
+        guard: Option<Self>,
+        activity: crate::execution_activity::ExecutionActivityGuard,
+    ) -> Self {
+        // Observability remains active when provider demand tracking is disabled.
+        let mut guard = guard.unwrap_or(Self {
+            kind: ProviderPoolInFlightGuardKind::Disabled,
+            provider_key_permit: None,
+            observed_activity: None,
+            released: false,
+        });
+        guard.observed_activity = Some(activity);
+        guard
+    }
+
     pub(crate) async fn release(mut self) {
         self.release_inner().await;
     }
 
     async fn release_inner(&mut self) {
+        // Observation ends with execution, before distributed permit cleanup can wait.
+        self.observed_activity.take();
         if self.released {
             return;
         }
@@ -358,6 +376,7 @@ pub(crate) async fn acquire_provider_pool_in_flight_guard_with_key_limit(
             provider_key_permit.map(|provider_key_permit| ProviderPoolInFlightGuard {
                 kind: ProviderPoolInFlightGuardKind::Disabled,
                 provider_key_permit: Some(provider_key_permit),
+                observed_activity: None,
                 released: false,
             }),
         );
@@ -369,6 +388,7 @@ pub(crate) async fn acquire_provider_pool_in_flight_guard_with_key_limit(
                 provider_key_permit.map(|provider_key_permit| ProviderPoolInFlightGuard {
                     kind: ProviderPoolInFlightGuardKind::Disabled,
                     provider_key_permit: Some(provider_key_permit),
+                    observed_activity: None,
                     released: false,
                 }),
             );
@@ -381,6 +401,7 @@ pub(crate) async fn acquire_provider_pool_in_flight_guard_with_key_limit(
                     counter,
                 },
                 provider_key_permit,
+                observed_activity: None,
                 released: false,
             }));
         }
@@ -392,6 +413,7 @@ pub(crate) async fn acquire_provider_pool_in_flight_guard_with_key_limit(
                     counter,
                 },
                 provider_key_permit,
+                observed_activity: None,
                 released: false,
             }));
         }
@@ -417,6 +439,7 @@ pub(crate) async fn acquire_provider_pool_in_flight_guard_with_key_limit(
                 provider_key_permit.map(|provider_key_permit| ProviderPoolInFlightGuard {
                     kind: ProviderPoolInFlightGuardKind::Disabled,
                     provider_key_permit: Some(provider_key_permit),
+                    observed_activity: None,
                     released: false,
                 }),
             );
@@ -431,6 +454,7 @@ pub(crate) async fn acquire_provider_pool_in_flight_guard_with_key_limit(
                 provider_key_permit.map(|provider_key_permit| ProviderPoolInFlightGuard {
                     kind: ProviderPoolInFlightGuardKind::Disabled,
                     provider_key_permit: Some(provider_key_permit),
+                    observed_activity: None,
                     released: false,
                 }),
             );
@@ -454,6 +478,7 @@ pub(crate) async fn acquire_provider_pool_in_flight_guard_with_key_limit(
             renew_handle: Some(renew_handle),
         },
         provider_key_permit,
+        observed_activity: None,
         released: false,
     }))
 }
@@ -461,6 +486,47 @@ pub(crate) async fn acquire_provider_pool_in_flight_guard_with_key_limit(
 pub(crate) async fn acquire_provider_pool_execution_guard(
     state: &AppState,
     plan: &ExecutionPlan,
+    report_context: Option<&serde_json::Value>,
+) -> Result<ProviderPoolInFlightAdmission, GatewayError> {
+    let admission = acquire_provider_pool_execution_guard_unobserved(state, plan).await?;
+    let ProviderPoolInFlightAdmission::Acquired(guard) = admission else {
+        return Ok(admission);
+    };
+    let requested_model = report_context
+        .and_then(|context| context.get("model"))
+        .and_then(serde_json::Value::as_str);
+    let observation_id = execution_observation_request_id(&plan.request_id, report_context);
+    let activity = state.execution_activity.begin(
+        observation_id.as_ref(),
+        &plan.provider_id,
+        plan.provider_name.as_deref(),
+        requested_model,
+    );
+    Ok(ProviderPoolInFlightAdmission::Acquired(Some(
+        ProviderPoolInFlightGuard::observe_execution(guard, activity),
+    )))
+}
+
+fn execution_observation_request_id<'a>(
+    request_id: &'a str,
+    report_context: Option<&serde_json::Value>,
+) -> std::borrow::Cow<'a, str> {
+    // Transparent Responses retries have distinct audit request IDs, but share
+    // one server-issued logical turn ID. Count that client request once.
+    report_context
+        .and_then(|context| context.get("websocket_logical_turn_id"))
+        .and_then(serde_json::Value::as_str)
+        .map(str::trim)
+        .filter(|value| !value.is_empty())
+        .map(|value| std::borrow::Cow::Owned(format!("ws:{value}")))
+        .unwrap_or(std::borrow::Cow::Borrowed(request_id))
+}
+
+/// Long-lived audio/live sockets use the same capacity permits, but are not
+/// individual requests and must not contribute to per-request RPM/concurrency.
+pub(crate) async fn acquire_provider_pool_execution_guard_unobserved(
+    state: &AppState,
+    plan: &ExecutionPlan,
 ) -> Result<ProviderPoolInFlightAdmission, GatewayError> {
     let concurrent_limit = state
         .read_provider_catalog_keys_by_ids(std::slice::from_ref(&plan.key_id))
@@ -751,6 +817,109 @@ mod tests {
         drop(replacement);
     }
 
+    #[test]
+    fn execution_observation_deduplicates_websocket_attempts_by_logical_turn() {
+        let context = serde_json::json!({"websocket_logical_turn_id": "logical-turn-1"});
+        assert_eq!(
+            execution_observation_request_id("attempt-1", Some(&context)),
+            execution_observation_request_id("attempt-2", Some(&context)),
+        );
+        assert_ne!(
+            execution_observation_request_id("logical-turn-1", None),
+            execution_observation_request_id("attempt-1", Some(&context)),
+        );
+        assert_eq!(
+            execution_observation_request_id("http-request", None),
+            "http-request"
+        );
+        assert_eq!(
+            execution_observation_request_id(
+                "http-request",
+                Some(&serde_json::json!({"websocket_logical_turn_id": " "}))
+            ),
+            "http-request",
+        );
+    }
+
+    #[tokio::test]
+    async fn execution_activity_survives_disabled_pool_tracking_and_clears_on_release_or_drop() {
+        let activity = Arc::new(crate::execution_activity::ExecutionActivity::default());
+        // Pool mode Off (without a key limit) returns None. Execution admission
+        // still attaches the independent observation to a disabled wrapper.
+        let mut guard = ProviderPoolInFlightGuard::observe_execution(
+            None,
+            activity.begin(
+                "request-1",
+                "provider-1",
+                Some("Provider"),
+                Some("client-model"),
+            ),
+        );
+        let snapshot = activity.snapshot();
+        assert_eq!(snapshot["providers"][0]["current_concurrency"], 1);
+        assert_eq!(snapshot["providers"][0]["requests_per_minute"], 1);
+        assert_eq!(snapshot["models"][0]["model"], "client-model");
+        guard.release_inner().await;
+        assert_eq!(
+            activity.snapshot()["providers"][0]["current_concurrency"],
+            0
+        );
+        assert!(guard.observed_activity.is_none());
+        drop(guard);
+
+        let guard = ProviderPoolInFlightGuard::observe_execution(
+            None,
+            activity.begin(
+                "request-2",
+                "provider-1",
+                Some("Provider"),
+                Some("client-model"),
+            ),
+        );
+        assert_eq!(activity.snapshot()["models"][0]["current_concurrency"], 1);
+        drop(guard);
+        let snapshot = activity.snapshot();
+        assert_eq!(snapshot["models"][0]["current_concurrency"], 0);
+        assert_eq!(snapshot["providers"][0]["requests_per_minute"], 2);
+    }
+
+    #[tokio::test]
+    async fn execution_activity_releases_with_an_existing_pool_guard() {
+        let runtime = Arc::new(RuntimeState::memory(MemoryRuntimeStateConfig::default()));
+        let activity = Arc::new(crate::execution_activity::ExecutionActivity::default());
+        let provider_id = "provider-observed-release";
+        let pool_guard = acquire_provider_pool_in_flight_guard(
+            runtime.clone(),
+            provider_id,
+            "request-1",
+            Some("candidate-1"),
+            "key-1",
+        )
+        .await
+        .expect("pool guard should be acquired");
+        let guard = ProviderPoolInFlightGuard::observe_execution(
+            Some(pool_guard),
+            activity.begin("request-1", provider_id, Some("Provider"), None),
+        );
+        assert_eq!(
+            provider_pool_live_in_flight_count(runtime.as_ref(), provider_id).await,
+            1
+        );
+        assert_eq!(
+            activity.snapshot()["providers"][0]["current_concurrency"],
+            1
+        );
+        guard.release().await;
+        assert_eq!(
+            provider_pool_live_in_flight_count(runtime.as_ref(), provider_id).await,
+            0
+        );
+        assert_eq!(
+            activity.snapshot()["providers"][0]["current_concurrency"],
+            0
+        );
+    }
+
     #[tokio::test]
     async fn demand_snapshot_uses_instant_in_flight_for_fast_rise_and_ema_for_fall() {
         let runtime = RuntimeState::memory(MemoryRuntimeStateConfig::default());

apps/aether-gateway/src/request_activity.rs

@@ -0,0 +1,302 @@
+//! Node-local request concurrency, integrated at lifecycle edges rather than sampled.
+//!
+//! Minute buckets bound memory independently of traffic volume. A request spanning
+//! a bucket/day boundary contributes to both sides, including while no API polls us.
+use std::collections::VecDeque;
+use std::sync::{Arc, Mutex};
+use std::time::Instant;
+
+use aether_data_contracts::repository::usage::UsageDashboardAnalyticsQuery;
+use aether_runtime::{AdmissionPermit, AdmissionPermitHealth};
+use chrono::{DateTime, Utc};
+use serde_json::{json, Value};
+
+const MINUTE_US: i64 = 60_000_000;
+const RETAIN_MINUTES: i64 = 48 * 60;
+
+#[derive(Debug, Default)]
+struct Minute {
+    start_us: i64,
+    request_microseconds: u128,
+    peak: u64,
+}
+
+#[derive(Debug)]
+struct History {
+    observed_from_us: i64,
+    through_us: i64,
+    active: u64,
+    minutes: VecDeque<Minute>,
+}
+
+impl History {
+    fn new(now_us: i64) -> Self {
+        Self {
+            observed_from_us: now_us,
+            through_us: now_us,
+            active: 0,
+            minutes: VecDeque::new(),
+        }
+    }
+
+    fn minute(&mut self, at_us: i64) -> &mut Minute {
+        let start_us = at_us.div_euclid(MINUTE_US) * MINUTE_US;
+        if self
+            .minutes
+            .back()
+            .is_none_or(|bucket| bucket.start_us != start_us)
+        {
+            self.minutes.push_back(Minute {
+                start_us,
+                ..Minute::default()
+            });
+        }
+        self.minutes.back_mut().expect("minute was inserted")
+    }
+
+    fn advance(&mut self, now_us: i64) {
+        let now_us = now_us.max(self.through_us);
+        let retained_from = (now_us.div_euclid(MINUTE_US) - RETAIN_MINUTES) * MINUTE_US;
+        let mut cursor = self.through_us.max(retained_from);
+        while cursor < now_us {
+            let end = ((cursor.div_euclid(MINUTE_US) + 1) * MINUTE_US).min(now_us);
+            let active = self.active;
+            let bucket = self.minute(cursor);
+            bucket.request_microseconds += u128::from(active) * (end - cursor) as u128;
+            bucket.peak = bucket.peak.max(active);
+            cursor = end;
+        }
+        self.through_us = now_us;
+        while self
+            .minutes
+            .front()
+            .is_some_and(|bucket| bucket.start_us < retained_from)
+        {
+            self.minutes.pop_front();
+        }
+    }
+
+    fn change(&mut self, now_us: i64, entering: bool) {
+        self.advance(now_us);
+        self.active = if entering {
+            self.active.saturating_add(1)
+        } else {
+            self.active.saturating_sub(1)
+        };
+        let active = self.active;
+        let at_us = self.through_us;
+        let bucket = self.minute(at_us);
+        bucket.peak = bucket.peak.max(active);
+    }
+
+    fn today(&mut self, timezone: &str, now_us: i64) -> Result<Value, String> {
+        self.advance(now_us);
+        let through = DateTime::from_timestamp_micros(self.through_us)
+            .ok_or_else(|| "invalid concurrency observation timestamp".to_string())?;
+        let day_start = UsageDashboardAnalyticsQuery {
+            timezone: timezone.into(),
+        }
+        .today_start(through)
+        .map_err(|error| error.to_string())?;
+        let day_start_us = day_start.timestamp_micros();
+        // Current IANA offsets/day boundaries are minute aligned. Refuse to
+        // misrepresent an unsupported sub-minute historical boundary as exact.
+        if day_start_us.rem_euclid(MINUTE_US) != 0 {
+            return Err("concurrency day boundary is not minute aligned".into());
+        }
+        let observed_from_us = self.observed_from_us.max(day_start_us);
+        let duration_us = self.through_us.saturating_sub(observed_from_us);
+        let (area, peak) = self
+            .minutes
+            .iter()
+            .filter(|minute| minute.start_us >= day_start_us && minute.start_us <= self.through_us)
+            .fold((0u128, self.active), |(area, peak), minute| {
+                (area + minute.request_microseconds, peak.max(minute.peak))
+            });
+        Ok(json!({
+            "avg": (duration_us > 0).then(|| area as f64 / duration_us as f64),
+            "peak": peak,
+            "observed_from": DateTime::from_timestamp_micros(observed_from_us),
+            "observed_through": through,
+            "scope": "node",
+            "measurement": "http_and_responses_websocket_requests",
+            "coverage": if self.observed_from_us <= day_start_us { "complete" } else { "partial" },
+        }))
+    }
+}
+
+#[derive(Debug)]
+pub(crate) struct RequestActivity {
+    started_at: Instant,
+    started_at_us: i64,
+    history: Mutex<History>,
+}
+
+impl Default for RequestActivity {
+    fn default() -> Self {
+        let started_at = Instant::now();
+        let started_at_us = Utc::now().timestamp_micros();
+        Self {
+            started_at,
+            started_at_us,
+            history: Mutex::new(History::new(started_at_us)),
+        }
+    }
+}
+
+impl RequestActivity {
+    fn now_us(&self) -> i64 {
+        self.started_at_us
+            .saturating_add(self.started_at.elapsed().as_micros().min(i64::MAX as u128) as i64)
+    }
+
+    pub(crate) fn begin(self: &Arc<Self>) -> RequestActivityGuard {
+        self.history
+            .lock()
+            .unwrap_or_else(|error| error.into_inner())
+            .change(self.now_us(), true);
+        RequestActivityGuard {
+            activity: Arc::clone(self),
+        }
+    }
+
+    pub(crate) fn today(&self, timezone: &str) -> Result<Value, String> {
+        self.history
+            .lock()
+            .unwrap_or_else(|error| error.into_inner())
+            .today(timezone, self.now_us())
+    }
+
+    #[cfg(test)]
+    pub(crate) fn active(&self) -> u64 {
+        self.history.lock().unwrap().active
+    }
+}
+
+#[derive(Debug)]
+pub(crate) struct RequestActivityGuard {
+    activity: Arc<RequestActivity>,
+}
+
+impl RequestActivityGuard {
+    pub(crate) fn into_admission_permit(self) -> AdmissionPermit {
+        // This guard observes lifecycle only; it neither limits nor cancels work.
+        AdmissionPermit::from_parts(None, Some(self)).expect("activity guard is present")
+    }
+}
+
+impl AdmissionPermitHealth for RequestActivityGuard {
+    fn is_healthy(&self) -> bool {
+        true
+    }
+    fn requires_health_poll(&self) -> bool {
+        false
+    }
+}
+
+impl Drop for RequestActivityGuard {
+    fn drop(&mut self) {
+        self.activity
+            .history
+            .lock()
+            .unwrap_or_else(|error| error.into_inner())
+            .change(self.activity.now_us(), false);
+    }
+}
+
+impl crate::AppState {
+    pub(crate) fn today_concurrency(&self, timezone: &str) -> Result<Value, String> {
+        self.request_activity.today(timezone)
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn at(value: &str) -> i64 {
+        DateTime::parse_from_rfc3339(value)
+            .unwrap()
+            .timestamp_micros()
+    }
+
+    #[test]
+    fn concurrency_integrates_time_instead_of_averaging_event_samples() {
+        let start = at("2026-09-19T00:00:00Z");
+        let mut history = History::new(start);
+        history.change(start, true);
+        history.change(start + 10_000_000, true);
+        history.change(start + 20_000_000, false);
+        history.change(start + 30_000_000, false);
+        let value = history.today("UTC", start + 100_000_000).unwrap();
+        assert_eq!(value["avg"], 0.4);
+        assert_eq!(value["peak"], 2);
+        assert_eq!(value["coverage"], "complete");
+    }
+
+    #[test]
+    fn concurrency_long_request_crosses_minutes_and_local_midnight() {
+        let start = at("2026-09-18T15:59:30Z");
+        let mut history = History::new(start);
+        history.change(start, true);
+        let value = history.today("Asia/Shanghai", start + 150_000_000).unwrap();
+        assert_eq!(value["avg"], 1.0);
+        assert_eq!(value["peak"], 1);
+        assert_eq!(value["observed_from"], "2026-09-18T16:00:00Z");
+        assert_eq!(value["coverage"], "complete");
+        history.change(start + 150_000_000, false);
+        let value = history.today("Asia/Shanghai", start + 270_000_000).unwrap();
+        assert_eq!(value["avg"], 0.5);
+    }
+
+    #[test]
+    fn concurrency_restart_only_claims_the_observed_part_of_the_day() {
+        let start = at("2026-09-19T12:00:00Z");
+        let mut history = History::new(start);
+        let value = history.today("UTC", start + 60_000_000).unwrap();
+        assert_eq!(value["avg"], 0.0);
+        assert_eq!(value["peak"], 0);
+        assert_eq!(value["coverage"], "partial");
+        assert_eq!(value["observed_from"], "2026-09-19T12:00:00Z");
+        assert!(History::new(start).today("UTC", start).unwrap()["avg"].is_null());
+        assert!(history.today("not/a/timezone", start).is_err());
+    }
+
+    #[test]
+    fn concurrency_does_not_carry_yesterdays_peak_into_today() {
+        let start = at("2026-09-18T23:59:30Z");
+        let mut history = History::new(start);
+        history.change(start, true);
+        history.change(start, true);
+        history.change(start + 20_000_000, false);
+        history.change(start + 30_000_000, false);
+        let value = history.today("UTC", start + 90_000_000).unwrap();
+        assert_eq!(value["avg"], 0.0);
+        assert_eq!(value["peak"], 0);
+    }
+
+    #[test]
+    fn concurrency_handles_dst_and_bounds_memory_after_a_long_idle_gap() {
+        let start = at("2026-10-30T00:00:00Z");
+        let mut history = History::new(start);
+        history.change(start, true);
+        let end = at("2026-11-02T04:30:00Z");
+        let value = history.today("America/New_York", end).unwrap();
+        assert_eq!(value["avg"], 1.0);
+        assert_eq!(value["observed_from"], "2026-11-01T04:00:00Z");
+        assert_eq!(value["coverage"], "complete");
+        assert!(history.minutes.len() <= RETAIN_MINUTES as usize + 1);
+    }
+
+    #[test]
+    fn concurrency_permit_clones_share_one_lifecycle() {
+        let activity = Arc::new(RequestActivity::default());
+        let permit = activity.begin().into_admission_permit();
+        let background = permit.clone();
+        assert_eq!(activity.active(), 1);
+        drop(permit);
+        assert_eq!(activity.active(), 1);
+        drop(background);
+        assert_eq!(activity.active(), 0);
+    }
+}

apps/aether-gateway/src/request_lifecycle.rs

@@ -1,7 +1,7 @@
 use std::future::Future;
 use std::pin::Pin;
 use std::sync::atomic::{AtomicBool, Ordering};
-use std::sync::Arc;
+use std::sync::{Arc, Mutex};
 use std::task::{Context, Poll};
 
 use aether_routing_core::RoutingExecutionPolicy;
@@ -16,6 +16,15 @@ use crate::GatewayError;
 
 tokio::task_local! {
     static CANCEL_ON_CLIENT_DISCONNECT: Arc<AtomicBool>;
+    static REQUEST_ACTIVITY: Arc<Mutex<Option<aether_runtime::AdmissionPermit>>>;
+}
+
+/// Begin observing only after routing chose local AI execution. The surrounding
+/// request/body lifecycle keeps this holder alive through disconnect draining.
+pub(crate) fn track_request_activity(permit: aether_runtime::AdmissionPermit) {
+    let _ = REQUEST_ACTIVITY.try_with(|activity| {
+        *activity.lock().unwrap_or_else(|error| error.into_inner()) = Some(permit);
+    });
 }
 
 pub(crate) fn configure_client_disconnect(policy: RoutingExecutionPolicy) {
@@ -59,23 +68,35 @@ where
     let diagnostics = Arc::new(RequestDiagnostics::default());
     let cancel_for_response = Arc::clone(&cancel);
     let producer_for_request = producer.clone();
-    let future = CANCEL_ON_CLIENT_DISCONNECT.scope(
-        Arc::clone(&cancel),
-        scope_request_diagnostics_with(Some(Arc::clone(&diagnostics)), async move {
-            let response = future.await?;
-            let complete_on_disconnect = !cancel_for_response.load(Ordering::Acquire);
-            if !complete_on_disconnect && producer.is_none() {
-                return Ok(response);
-            }
-            Ok(response.map(|body| {
-                Body::new(CompleteOnDisconnectBody {
-                    body: Some(body),
-                    diagnostics,
-                    complete_on_disconnect,
-                    producer,
-                })
-            }))
-        }),
+    let activity = Arc::new(Mutex::new(None));
+    let activity_for_response = Arc::clone(&activity);
+    let future = REQUEST_ACTIVITY.scope(
+        activity,
+        CANCEL_ON_CLIENT_DISCONNECT.scope(
+            Arc::clone(&cancel),
+            scope_request_diagnostics_with(Some(Arc::clone(&diagnostics)), async move {
+                let response = future.await?;
+                let complete_on_disconnect = !cancel_for_response.load(Ordering::Acquire);
+                if !complete_on_disconnect
+                    && producer.is_none()
+                    && activity_for_response
+                        .lock()
+                        .unwrap_or_else(|error| error.into_inner())
+                        .is_none()
+                {
+                    return Ok(response);
+                }
+                Ok(response.map(|body| {
+                    Body::new(CompleteOnDisconnectBody {
+                        body: Some(body),
+                        diagnostics,
+                        complete_on_disconnect,
+                        producer,
+                        activity: Some(activity_for_response),
+                    })
+                }))
+            }),
+        ),
     );
     CompleteOnDisconnectRequest {
         future: Some(Box::pin(future)),
@@ -142,6 +163,7 @@ struct CompleteOnDisconnectBody {
     complete_on_disconnect: bool,
     // Drop the body first so its terminal handoff registers before this guard ends.
     producer: Option<Arc<UsageProducerGuard>>,
+    activity: Option<Arc<Mutex<Option<aether_runtime::AdmissionPermit>>>>,
 }
 
 impl HttpBody for CompleteOnDisconnectBody {
@@ -159,6 +181,7 @@ impl HttpBody for CompleteOnDisconnectBody {
         if matches!(result, Poll::Ready(None | Some(Err(_)))) {
             self.body.take();
             self.producer.take();
+            self.activity.take();
         }
         result
     }
@@ -185,10 +208,12 @@ impl Drop for CompleteOnDisconnectBody {
         };
         if let Ok(runtime) = tokio::runtime::Handle::try_current() {
             let producer = self.producer.take();
+            let activity = self.activity.take();
             runtime.spawn(scope_request_diagnostics_with(
                 Some(Arc::clone(&self.diagnostics)),
                 async move {
                     let _producer = producer;
+                    let _activity = activity;
                     drain_body(body).await;
                 },
             ));
@@ -341,10 +366,13 @@ mod tests {
     #[tokio::test]
     async fn usage_shutdown_waits_for_a_disconnected_request_before_headers() {
         let usage = Arc::new(UsageRuntime::disabled());
+        let activity = Arc::new(crate::request_activity::RequestActivity::default());
+        let activity_permit = activity.begin().into_admission_permit();
         let (started_tx, started_rx) = oneshot::channel();
         let (release_tx, release_rx) = oneshot::channel::<()>();
         let request = tokio::spawn(run_request_with_usage(usage.clone(), async move {
             configure_client_disconnect(RoutingExecutionPolicy::default());
+            track_request_activity(activity_permit);
             started_tx.send(()).unwrap();
             release_rx.await.unwrap();
             Ok(Response::new(Body::empty()))
@@ -354,49 +382,79 @@ mod tests {
         assert!(request.await.unwrap_err().is_cancelled());
         assert!(usage.shutdown(Duration::from_millis(30)).await.is_err());
         assert_eq!(usage.metrics_snapshot().producers_in_flight, 1);
+        assert_eq!(activity.active(), 1);
         release_tx.send(()).unwrap();
         usage.shutdown(Duration::from_secs(1)).await.unwrap();
         assert_eq!(usage.metrics_snapshot().producers_in_flight, 0);
+        assert_eq!(activity.active(), 0);
+    }
+
+    #[tokio::test]
+    async fn request_activity_releases_when_the_handler_fails_before_headers() {
+        let activity = Arc::new(crate::request_activity::RequestActivity::default());
+        let permit = activity.begin().into_admission_permit();
+        let result = run_request(async move {
+            track_request_activity(permit);
+            Err(GatewayError::Internal("test failure".into()))
+        })
+        .await;
+        assert!(result.is_err());
+        assert_eq!(activity.active(), 0);
     }
 
     #[tokio::test]
     async fn usage_shutdown_waits_for_disconnected_body_drain() {
         let usage = Arc::new(UsageRuntime::disabled());
+        let activity = Arc::new(crate::request_activity::RequestActivity::default());
+        let activity_permit = activity.begin().into_admission_permit();
         let (sender, receiver) = mpsc::channel::<Result<Bytes, io::Error>>(1);
         let response = run_request_with_usage(usage.clone(), async move {
             configure_client_disconnect(RoutingExecutionPolicy::default());
-            Ok(Response::new(Body::from_stream(stream::unfold(
+            track_request_activity(activity_permit);
+            let response = Response::new(Body::from_stream(stream::unfold(
                 receiver,
                 |mut receiver| async { receiver.recv().await.map(|item| (item, receiver)) },
-            ))))
+            )));
+            Ok(response)
         })
         .await
         .unwrap();
         drop(response);
+        assert_eq!(
+            activity.active(),
+            1,
+            "background drain still owns the request"
+        );
         assert!(usage.shutdown(Duration::from_millis(30)).await.is_err());
         sender.send(Ok(Bytes::from_static(b"last"))).await.unwrap();
         drop(sender);
         usage.shutdown(Duration::from_secs(1)).await.unwrap();
         assert_eq!(usage.metrics_snapshot().producers_in_flight, 0);
+        assert_eq!(activity.active(), 0);
     }
 
     #[tokio::test]
     async fn tracked_bodies_release_shutdown_on_cancellation_or_eof() {
         for cancel_on_client_disconnect in [false, true] {
             let usage = Arc::new(UsageRuntime::disabled());
+            let activity = Arc::new(crate::request_activity::RequestActivity::default());
+            let activity_permit = activity.begin().into_admission_permit();
             let (sender, receiver) = mpsc::channel::<Result<Bytes, io::Error>>(1);
             let response = run_request_with_usage(usage.clone(), async move {
                 configure_client_disconnect(RoutingExecutionPolicy {
                     cancel_on_client_disconnect,
                     ..Default::default()
                 });
-                Ok(Response::new(Body::from_stream(stream::unfold(
+                track_request_activity(activity_permit);
+                let response = Response::new(Body::from_stream(stream::unfold(
                     receiver,
                     |mut receiver| async { receiver.recv().await.map(|item| (item, receiver)) },
-                ))))
+                )));
+                Ok(response)
             })
             .await
             .unwrap();
+            assert_eq!(activity.active(), 1);
             let mut body = response.into_body();
             if cancel_on_client_disconnect {
                 drop(body);
@@ -407,13 +465,17 @@ mod tests {
                 assert_eq!(usage.metrics_snapshot().producers_in_flight, 0);
             }
             usage.shutdown(Duration::from_secs(1)).await.unwrap();
+            assert_eq!(activity.active(), 0);
         }
     }
 
     #[tokio::test]
     async fn connected_response_preserves_headers_size_hint_and_trailers() {
-        let response = run_request(async {
+        let activity = Arc::new(crate::request_activity::RequestActivity::default());
+        let activity_permit = activity.begin().into_admission_permit();
+        let response = run_request(async move {
             configure_client_disconnect(RoutingExecutionPolicy::default());
+            track_request_activity(activity_permit);
             Ok(Response::builder()
                 .status(201)
                 .header("x-test", "unchanged")
@@ -429,11 +491,14 @@ mod tests {
             response.into_body().collect().await.unwrap().to_bytes(),
             "hello"
         );
+        assert_eq!(activity.active(), 0);
 
         let mut trailers = HeaderMap::new();
         trailers.insert("x-finished", "yes".parse().unwrap());
+        let activity_permit = activity.begin().into_admission_permit();
         let response = run_request(async move {
             configure_client_disconnect(RoutingExecutionPolicy::default());
+            track_request_activity(activity_permit);
             let frames = stream::iter([
                 Ok::<_, io::Error>(Frame::data(Bytes::from_static(b"hello"))),
                 Ok(Frame::trailers(trailers)),

apps/aether-gateway/src/state/app.rs

@@ -18,7 +18,7 @@ use super::super::async_task::{VideoTaskPollerConfig, VideoTaskService};
 use super::super::cache::{
     AuthApiKeyFeatureCacheKey, AuthApiKeyIdentityCacheKey, AuthApiKeyLastUsedCache,
     AuthContextCache, AuthSnapshotCache, DashboardResponseCache, DirectPlanBypassCache,
-    JsonValueCache, SchedulerAffinityCache, SystemConfigCache, ValueCache,
+    JsonValueCache, OverviewTotalCache, SchedulerAffinityCache, SystemConfigCache, ValueCache,
 };
 use super::super::data::GatewayDataState;
 use super::super::fallback_metrics;
@@ -388,6 +388,8 @@ pub struct AppState {
     pub(crate) runtime_state: Arc<RuntimeState>,
     pub(crate) internal_gateway_auth: Arc<crate::internal_gateway_auth::InternalGatewayAuthConfig>,
     pub(crate) usage_runtime: Arc<usage::UsageRuntime>,
+    pub(crate) request_activity: Arc<crate::request_activity::RequestActivity>,
+    pub(crate) execution_activity: Arc<crate::execution_activity::ExecutionActivity>,
     pub(crate) video_tasks: Arc<VideoTaskService>,
     pub(crate) video_task_poller: Option<VideoTaskPollerConfig>,
     pub(crate) frontdoor_runtime_guards: Arc<FrontdoorRuntimeGuardConfig>,
@@ -429,6 +431,7 @@ pub struct AppState {
     pub(crate) scheduler_affinity_cache: Arc<SchedulerAffinityCache>,
     pub(crate) scheduler_affinity_epoch: Arc<AtomicU64>,
     pub(crate) dashboard_response_cache: Arc<DashboardResponseCache>,
+    pub(crate) overview_total_cache: Arc<OverviewTotalCache>,
     pub(crate) system_config_cache: Arc<SystemConfigCache>,
     pub(crate) endpoint_response_header_rules_cache: Arc<JsonValueCache<String>>,
     pub(crate) candidate_row_page_cache: Arc<super::super::cache::CandidateRowPageCache>,

apps/aether-gateway/src/state/core.rs

@@ -38,8 +38,9 @@ use super::super::async_task::{
 };
 use super::super::cache::{
     AuthApiKeyLastUsedCache, AuthContextCache, AuthSnapshotCache, DashboardResponseCache,
-    DirectPlanBypassCache, JsonValueCache, SchedulerAffinityCache, SchedulerAffinitySnapshotEntry,
-    SchedulerAffinityTarget, SystemConfigCache, SystemConfigInflightRegistration, ValueCache,
+    DirectPlanBypassCache, JsonValueCache, OverviewTotalCache, SchedulerAffinityCache,
+    SchedulerAffinitySnapshotEntry, SchedulerAffinityTarget, SystemConfigCache,
+    SystemConfigInflightRegistration, ValueCache,
 };
 use super::super::data::{GatewayDataConfig, GatewayDataState};
 use super::super::fallback_metrics;
@@ -77,6 +78,7 @@ use crate::maintenance::spawn_stats_hourly_aggregation_worker;
 use crate::maintenance::spawn_usage_cleanup_worker;
 use crate::maintenance::spawn_usage_counter_flush_worker;
 use crate::maintenance::spawn_wallet_daily_usage_aggregation_worker;
+use crate::xai_profile::spawn_worker as spawn_xai_client_profile_worker;
 
 const SYSTEM_CONFIG_CACHE_TTL: Duration = Duration::from_secs(30);
 // Requests may use a stale value after the fresh window until the entry reaches
@@ -159,6 +161,10 @@ impl AppState {
         crate::cli_client_profile::prewarm(&CLAUDE_CODE_CLI_PROFILE, self.runtime_state()).await
     }
 
+    pub async fn prewarm_xai_client_profile(&self) -> Result<String, String> {
+        crate::xai_profile::prewarm(self.runtime_state()).await
+    }
+
     pub async fn prewarm_chat_pii_redaction_runtime_config(&self) -> Result<bool, String> {
         crate::privacy::read_chat_pii_redaction_runtime_config(self)
             .await
@@ -265,6 +271,7 @@ impl AppState {
     }
 
     fn replace_foreground_data_state(&mut self, data: Arc<GatewayDataState>) {
+        self.overview_total_cache = Arc::new(OverviewTotalCache::default());
         self.clear_provider_transport_snapshot_cache();
         self.invalidate_scheduler_affinity_cache();
         self.invalidate_auth_context_cache();
@@ -362,6 +369,8 @@ impl AppState {
             runtime_state: runtime_state.clone(),
             internal_gateway_auth,
             usage_runtime: Arc::new(usage::UsageRuntime::disabled()),
+            request_activity: Arc::new(crate::request_activity::RequestActivity::default()),
+            execution_activity: Arc::new(crate::execution_activity::ExecutionActivity::default()),
             video_tasks: Arc::new(VideoTaskService::new(
                 VideoTaskTruthSourceMode::PythonSyncReport,
             )),
@@ -413,6 +422,7 @@ impl AppState {
             scheduler_affinity_cache: Arc::new(SchedulerAffinityCache::default()),
             scheduler_affinity_epoch: Arc::new(AtomicU64::new(0)),
             dashboard_response_cache: Arc::new(DashboardResponseCache::default()),
+            overview_total_cache: Arc::new(OverviewTotalCache::default()),
             system_config_cache: Arc::new(SystemConfigCache::default()),
             endpoint_response_header_rules_cache: Arc::new(JsonValueCache::default()),
             candidate_row_page_cache: Arc::new(crate::cache::CandidateRowPageCache::default()),
@@ -2367,6 +2377,10 @@ impl AppState {
                 background_state.clone(),
             )),
         );
+        supervise_worker(
+            crate::task_runtime::TASK_KEY_XAI_CLIENT_PROFILE,
+            Some(spawn_xai_client_profile_worker(background_state.clone())),
+        );
         supervise_worker(
             crate::task_runtime::TASK_KEY_VIDEO_TASK_POLLER,
             spawn_video_task_poller(background_state.clone()),

apps/aether-gateway/src/state/oauth.rs

@@ -412,6 +412,17 @@ fn normalize_local_oauth_refresh_error_message(
         .unwrap_or_else(|| "Token 刷新失败".to_string())
 }
 
+fn local_oauth_refresh_gateway_error(
+    error: &provider_transport::LocalOAuthRefreshError,
+) -> GatewayError {
+    // Keep a bounded, credential-redacted reason for internal diagnostics.
+    // GatewayError::Internal still returns the generic error response to clients.
+    GatewayError::Internal(format!(
+        "local oauth refresh failed: {}",
+        crate::error::redact_error_detail(error)
+    ))
+}
+
 fn merge_local_oauth_refresh_failure_reason(
     current_reason: Option<&str>,
     refresh_reason: &str,
@@ -1556,10 +1567,8 @@ impl AppState {
                     }
                     return Ok(None);
                 }
-                Err(_) => {
-                    return Err(GatewayError::Internal(
-                        "local oauth refresh failed".to_string(),
-                    ));
+                Err(err) => {
+                    return Err(local_oauth_refresh_gateway_error(&err));
                 }
             };
 
@@ -3484,13 +3493,86 @@ mod tests {
     use tokio::sync::Notify;
 
     use super::{
-        AgentIdentityAuthConfigFence, AppState, CodexRuntimeOAuthObservation,
-        ProviderTransportSnapshotCacheKey, ProviderTransportSnapshotFlight,
-        ProviderTransportSnapshotFlightResult, ProviderTransportSnapshotInflightRegistration,
-        PROVIDER_TRANSPORT_SNAPSHOT_CACHE_STALE_TTL, PROVIDER_TRANSPORT_SNAPSHOT_CACHE_TTL,
+        local_oauth_refresh_gateway_error, AgentIdentityAuthConfigFence, AppState,
+        CodexRuntimeOAuthObservation, ProviderTransportSnapshotCacheKey,
+        ProviderTransportSnapshotFlight, ProviderTransportSnapshotFlightResult,
+        ProviderTransportSnapshotInflightRegistration, PROVIDER_TRANSPORT_SNAPSHOT_CACHE_STALE_TTL,
+        PROVIDER_TRANSPORT_SNAPSHOT_CACHE_TTL,
     };
     use crate::data::GatewayDataState;
 
+    #[test]
+    fn oauth_refresh_diagnostic_preserves_failure_reason_and_redacts_credentials() {
+        for (message, secret) in [
+            (
+                "connection refused refresh_token=refresh-secret",
+                "refresh-secret",
+            ),
+            (
+                "connection refused accessToken=access-secret",
+                "access-secret",
+            ),
+            (
+                "connection refused client_secret=client-secret",
+                "client-secret",
+            ),
+            (
+                "connection refused Authorization: Bearer bearer-secret",
+                "bearer-secret",
+            ),
+            (
+                "connection refused https://proxy-user:[email protected]",
+                "proxy-secret",
+            ),
+        ] {
+            let error = crate::provider_transport::LocalOAuthRefreshError::TransportMessage {
+                provider_type: "codex",
+                message: message.to_string(),
+            };
+            let diagnostic = local_oauth_refresh_gateway_error(&error).into_message();
+            assert!(diagnostic.contains("codex oauth refresh transport failed"));
+            assert!(diagnostic.contains("connection refused"));
+            assert!(!diagnostic.contains(secret), "diagnostic: {diagnostic}");
+        }
+    }
+
+    #[test]
+    fn oauth_refresh_diagnostic_keeps_http_status_without_provider_body() {
+        let error = crate::provider_transport::LocalOAuthRefreshError::HttpStatus {
+            provider_type: "codex",
+            status_code: 503,
+            body_excerpt: "unstructured-provider-secret".to_string(),
+        };
+        let diagnostic = local_oauth_refresh_gateway_error(&error).into_message();
+
+        assert!(diagnostic.contains("codex oauth refresh returned HTTP 503"));
+        assert!(!diagnostic.contains("unstructured-provider-secret"));
+    }
+
+    #[tokio::test]
+    async fn oauth_refresh_diagnostic_is_hidden_from_client_response() {
+        use axum::body::to_bytes;
+        use axum::response::IntoResponse;
+
+        let error = crate::provider_transport::LocalOAuthRefreshError::TransportMessage {
+            provider_type: "codex",
+            message: "connection refused".to_string(),
+        };
+        let response = local_oauth_refresh_gateway_error(&error).into_response();
+
+        assert_eq!(
+            response.status(),
+            axum::http::StatusCode::INTERNAL_SERVER_ERROR
+        );
+        let body = to_bytes(response.into_body(), usize::MAX)
+            .await
+            .expect("error response body should read");
+        assert_eq!(
+            serde_json::from_slice::<serde_json::Value>(&body).expect("error should be JSON"),
+            json!({"error": {"message": "internal server error"}}),
+        );
+    }
+
     fn sample_provider() -> StoredProviderCatalogProvider {
         StoredProviderCatalogProvider::new(
             "provider-1".to_string(),

apps/aether-gateway/src/state/runtime/announcements.rs

@@ -1,6 +1,18 @@
 use crate::{AppState, GatewayError};
 
 impl AppState {
+    pub(crate) async fn list_user_announcements(
+        &self,
+        user_id: &str,
+        query: &aether_data::repository::announcements::UserAnnouncementListQuery,
+    ) -> Result<aether_data::repository::announcements::StoredUserAnnouncementPage, GatewayError>
+    {
+        self.data
+            .list_user_announcements(user_id, query)
+            .await
+            .map_err(|err| GatewayError::Internal(err.to_string()))
+    }
+
     pub(crate) async fn list_announcements(
         &self,
         query: &aether_data::repository::announcements::AnnouncementListQuery,

apps/aether-gateway/src/state/runtime/billing/admin.rs

@@ -610,6 +610,17 @@ impl AppState {
             .map_err(data_error)
     }
 
+    pub(crate) async fn list_user_plan_entitlements_with_history(
+        &self,
+        user_id: &str,
+        include_inactive: bool,
+    ) -> Result<Option<Vec<UserPlanEntitlementRecord>>, GatewayError> {
+        self.data
+            .list_user_plan_entitlements_with_history(user_id, include_inactive)
+            .await
+            .map_err(data_error)
+    }
+
     pub(crate) async fn revoke_user_plan_entitlement(
         &self,
         user_id: &str,

apps/aether-gateway/src/state/runtime/billing/finance_queries.rs

@@ -14,6 +14,7 @@ use crate::{
 impl AppState {
     pub(crate) async fn list_admin_wallets(
         &self,
+        user_id: Option<&str>,
         status: Option<&str>,
         owner_type: Option<&str>,
         limit: usize,
@@ -22,6 +23,7 @@ impl AppState {
         let page = self
             .data
             .list_admin_wallets(&AdminWalletListQuery {
+                user_id: user_id.map(ToOwned::to_owned),
                 status: status.map(ToOwned::to_owned),
                 owner_type: owner_type.map(ToOwned::to_owned),
                 limit,

apps/aether-gateway/src/state/runtime/usage_queries.rs

@@ -3,6 +3,35 @@ use aether_data_contracts::repository::{candidates, usage};
 use usage::{StoredUsageDailySummary, UsageDailyHeatmapQuery};
 
 impl AppState {
+    pub(crate) async fn query_dashboard_analytics(
+        &self,
+        query: &usage::UsageDashboardAnalyticsQuery,
+    ) -> Result<usage::StoredUsageDashboardAnalytics, GatewayError> {
+        self.data
+            .query_dashboard_analytics(query)
+            .await
+            .map_err(|err| GatewayError::Internal(err.to_string()))
+    }
+
+    pub(crate) async fn query_usage_analytics(
+        &self,
+        query: &usage::UsageAnalyticsQuery,
+    ) -> Result<usage::StoredUsageAnalytics, GatewayError> {
+        self.data
+            .query_usage_analytics(query)
+            .await
+            .map_err(|err| match err {
+                aether_data_contracts::DataLayerError::InvalidInput(message)
+                    if query.view == usage::UsageAnalyticsView::DashboardCharts =>
+                {
+                    GatewayError::Client {
+                        status: http::StatusCode::UNPROCESSABLE_ENTITY,
+                        message,
+                    }
+                }
+                err => GatewayError::Internal(err.to_string()),
+            })
+    }
     #[allow(dead_code)]
     pub(crate) async fn rebuild_api_key_usage_stats(&self) -> Result<u64, GatewayError> {
         self.data

apps/aether-gateway/src/task_runtime/mod.rs

@@ -27,6 +27,7 @@ pub(crate) const TASK_KEY_MODEL_FETCH_WORKER: &str = "model.fetch.worker";
 pub(crate) const TASK_KEY_CODEX_CLIENT_PROFILE: &str = "maintenance.codex.client.profile";
 pub(crate) const TASK_KEY_CLAUDE_CODE_CLIENT_PROFILE: &str =
     "maintenance.claude_code.client.profile";
+pub(crate) const TASK_KEY_XAI_CLIENT_PROFILE: &str = "maintenance.xai.client.profile";
 pub(crate) const TASK_KEY_PROVIDER_QUOTA_RESET: &str = "provider.quota.reset.worker";
 pub(crate) const TASK_KEY_ACCOUNT_SELF_CHECK: &str = "account.self_check.worker";
 pub(crate) const TASK_KEY_POOL_SCORE_REBUILD: &str = "pool.score.rebuild.worker";
@@ -221,6 +222,14 @@ const TASK_DEFINITIONS: &[TaskDefinition] = &[
         true,
         RETRY_ONCE,
     ),
+    TaskDefinition::new(
+        TASK_KEY_XAI_CLIENT_PROFILE,
+        TaskKind::Scheduled,
+        "interval",
+        true,
+        true,
+        RETRY_ONCE,
+    ),
     TaskDefinition::new(
         TASK_KEY_PROVIDER_QUOTA_RESET,
         TaskKind::Scheduled,
@@ -958,3 +967,28 @@ mod worker_boot_run_id_tests {
         assert!(events.iter().all(|event| event.payload_json.is_none()));
     }
 }
+
+#[cfg(test)]
+mod client_profile_task_tests {
+    use super::*;
+
+    #[test]
+    fn all_cli_client_profile_tasks_are_registered_once() {
+        for (key, trigger) in [
+            (TASK_KEY_CODEX_CLIENT_PROFILE, "daily"),
+            (TASK_KEY_CLAUDE_CODE_CLIENT_PROFILE, "daily"),
+            (TASK_KEY_XAI_CLIENT_PROFILE, "interval"),
+        ] {
+            let definitions: Vec<_> = task_definitions()
+                .iter()
+                .filter(|definition| definition.key == key)
+                .collect();
+            assert_eq!(definitions.len(), 1, "task {key} must be registered once");
+            let definition = definitions[0];
+            assert_eq!(definition.kind, TaskKind::Scheduled);
+            assert_eq!(definition.trigger, trigger);
+            assert!(definition.singleton);
+            assert!(definition.persist_history);
+        }
+    }
+}

apps/aether-gateway/src/tests/ai_execute/sync/search.rs

@@ -45,6 +45,153 @@ where
     }
 }
 
+fn hash_api_key(value: &str) -> String {
+    let mut hasher = Sha256::new();
+    hasher.update(value.as_bytes());
+    format!("{:x}", hasher.finalize())
+}
+
+fn auth_snapshot() -> StoredAuthApiKeySnapshot {
+    StoredAuthApiKeySnapshot::new(
+        "user-search-1".to_string(),
+        "alice".to_string(),
+        Some("[email protected]".to_string()),
+        "user".to_string(),
+        "local".to_string(),
+        true,
+        false,
+        Some(json!(["openai", "codex"])),
+        Some(json!(["openai:responses"])),
+        None,
+        "api-key-search-1".to_string(),
+        Some("search-client".to_string()),
+        true,
+        false,
+        false,
+        Some(60),
+        Some(5),
+        Some(4_102_444_800_i64),
+        Some(json!(["openai", "codex"])),
+        Some(json!(["openai:responses"])),
+        None,
+    )
+    .expect("auth snapshot should build")
+}
+
+fn candidate_row(api_format: &str) -> StoredMinimalCandidateSelectionRow {
+    StoredMinimalCandidateSelectionRow {
+        provider_id: "provider-codex-search-1".to_string(),
+        provider_name: "codex".to_string(),
+        provider_type: "codex".to_string(),
+        provider_priority: 10,
+        provider_is_active: true,
+        endpoint_id: "endpoint-codex-search-1".to_string(),
+        endpoint_api_format: api_format.to_string(),
+        endpoint_api_family: Some("openai".to_string()),
+        endpoint_kind: Some(api_format.split_once(':').expect("format").1.to_string()),
+        endpoint_is_active: true,
+        key_id: "key-codex-search-1".to_string(),
+        key_name: "oauth".to_string(),
+        key_auth_type: "oauth".to_string(),
+        key_is_active: true,
+        key_api_formats: Some(vec!["openai:responses".to_string()]),
+        key_allowed_models: None,
+        key_capabilities: None,
+        key_internal_priority: 5,
+        key_global_priority_by_format: Some(json!({"openai:search": 1})),
+        model_id: "model-codex-search-1".to_string(),
+        global_model_id: "global-model-codex-search-1".to_string(),
+        global_model_name: "gpt-5.6-sol".to_string(),
+        global_model_mappings: None,
+        global_model_supports_streaming: Some(false),
+        model_provider_model_name: "gpt-5.6-sol".to_string(),
+        model_provider_model_mappings: Some(vec![StoredProviderModelMapping {
+            name: "gpt-5.6-sol".to_string(),
+            priority: 1,
+            api_formats: Some(vec!["openai:responses".to_string()]),
+            endpoint_ids: None,
+            operations: None,
+        }]),
+        model_supports_streaming: Some(false),
+        model_is_active: true,
+        model_is_available: true,
+    }
+}
+
+fn provider() -> StoredProviderCatalogProvider {
+    StoredProviderCatalogProvider::new(
+        "provider-codex-search-1".to_string(),
+        "codex".to_string(),
+        Some("https://chatgpt.com".to_string()),
+        "codex".to_string(),
+    )
+    .expect("provider should build")
+    .with_transport_fields(
+        true,
+        false,
+        false,
+        None,
+        Some(1),
+        None,
+        Some(900.0),
+        None,
+        None,
+    )
+}
+
+fn endpoint(api_format: &str) -> StoredProviderCatalogEndpoint {
+    StoredProviderCatalogEndpoint::new(
+        "endpoint-codex-search-1".to_string(),
+        "provider-codex-search-1".to_string(),
+        api_format.to_string(),
+        Some("openai".to_string()),
+        Some(api_format.split_once(':').expect("format").1.to_string()),
+        true,
+    )
+    .expect("endpoint should build")
+    .with_transport_fields(
+        "https://chatgpt.com/backend-api/codex".to_string(),
+        None,
+        None,
+        Some(1),
+        None,
+        None,
+        None,
+        None,
+    )
+    .expect("endpoint transport should build")
+}
+
+fn key() -> StoredProviderCatalogKey {
+    let auth_config = encrypt_python_fernet_plaintext(
+        DEVELOPMENT_ENCRYPTION_KEY,
+        r#"{"provider_type":"codex","account_id":"account-search-1","is_fedramp":true}"#,
+    )
+    .expect("auth config should encrypt");
+    StoredProviderCatalogKey::new(
+        "key-codex-search-1".to_string(),
+        "provider-codex-search-1".to_string(),
+        "oauth".to_string(),
+        "oauth".to_string(),
+        None,
+        true,
+    )
+    .expect("key should build")
+    .with_transport_fields(
+        Some(json!(["openai:responses"])),
+        encrypt_python_fernet_plaintext(DEVELOPMENT_ENCRYPTION_KEY, "codex-search-access-token")
+            .expect("access token should encrypt"),
+        Some(auth_config),
+        None,
+        Some(json!({"openai:search": 1})),
+        None,
+        Some(4_102_444_800),
+        None,
+        None,
+    )
+    .expect("key transport should build")
+}
+
 #[test]
 fn gateway_executes_codex_search_with_responses_permission_and_search_contract() {
     run_search_sync_test(
@@ -54,156 +201,6 @@ fn gateway_executes_codex_search_with_responses_permission_and_search_contract()
 }
 
 async fn gateway_executes_codex_search_with_responses_permission_and_search_contract_impl() {
-    fn hash_api_key(value: &str) -> String {
-        let mut hasher = Sha256::new();
-        hasher.update(value.as_bytes());
-        format!("{:x}", hasher.finalize())
-    }
-
-    fn auth_snapshot() -> StoredAuthApiKeySnapshot {
-        StoredAuthApiKeySnapshot::new(
-            "user-search-1".to_string(),
-            "alice".to_string(),
-            Some("[email protected]".to_string()),
-            "user".to_string(),
-            "local".to_string(),
-            true,
-            false,
-            Some(json!(["openai", "codex"])),
-            Some(json!(["openai:responses"])),
-            None,
-            "api-key-search-1".to_string(),
-            Some("search-client".to_string()),
-            true,
-            false,
-            false,
-            Some(60),
-            Some(5),
-            Some(4_102_444_800_i64),
-            Some(json!(["openai", "codex"])),
-            Some(json!(["openai:responses"])),
-            None,
-        )
-        .expect("auth snapshot should build")
-    }
-
-    fn candidate_row() -> StoredMinimalCandidateSelectionRow {
-        StoredMinimalCandidateSelectionRow {
-            provider_id: "provider-codex-search-1".to_string(),
-            provider_name: "codex".to_string(),
-            provider_type: "codex".to_string(),
-            provider_priority: 10,
-            provider_is_active: true,
-            endpoint_id: "endpoint-codex-search-1".to_string(),
-            endpoint_api_format: "openai:search".to_string(),
-            endpoint_api_family: Some("openai".to_string()),
-            endpoint_kind: Some("search".to_string()),
-            endpoint_is_active: true,
-            key_id: "key-codex-search-1".to_string(),
-            key_name: "oauth".to_string(),
-            key_auth_type: "oauth".to_string(),
-            key_is_active: true,
-            key_api_formats: Some(vec!["openai:responses".to_string()]),
-            key_allowed_models: None,
-            key_capabilities: None,
-            key_internal_priority: 5,
-            key_global_priority_by_format: Some(json!({"openai:search": 1})),
-            model_id: "model-codex-search-1".to_string(),
-            global_model_id: "global-model-codex-search-1".to_string(),
-            global_model_name: "gpt-5.6-sol".to_string(),
-            global_model_mappings: None,
-            global_model_supports_streaming: Some(false),
-            model_provider_model_name: "gpt-5.6-sol".to_string(),
-            model_provider_model_mappings: Some(vec![StoredProviderModelMapping {
-                name: "gpt-5.6-sol".to_string(),
-                priority: 1,
-                api_formats: Some(vec!["openai:responses".to_string()]),
-                endpoint_ids: None,
-                operations: None,
-            }]),
-            model_supports_streaming: Some(false),
-            model_is_active: true,
-            model_is_available: true,
-        }
-    }
-
-    fn provider() -> StoredProviderCatalogProvider {
-        StoredProviderCatalogProvider::new(
-            "provider-codex-search-1".to_string(),
-            "codex".to_string(),
-            Some("https://chatgpt.com".to_string()),
-            "codex".to_string(),
-        )
-        .expect("provider should build")
-        .with_transport_fields(
-            true,
-            false,
-            false,
-            None,
-            Some(1),
-            None,
-            Some(900.0),
-            None,
-            None,
-        )
-    }
-
-    fn endpoint() -> StoredProviderCatalogEndpoint {
-        StoredProviderCatalogEndpoint::new(
-            "endpoint-codex-search-1".to_string(),
-            "provider-codex-search-1".to_string(),
-            "openai:search".to_string(),
-            Some("openai".to_string()),
-            Some("search".to_string()),
-            true,
-        )
-        .expect("endpoint should build")
-        .with_transport_fields(
-            "https://chatgpt.com/backend-api/codex".to_string(),
-            None,
-            None,
-            Some(1),
-            None,
-            None,
-            None,
-            None,
-        )
-        .expect("endpoint transport should build")
-    }
-
-    fn key() -> StoredProviderCatalogKey {
-        let auth_config = encrypt_python_fernet_plaintext(
-            DEVELOPMENT_ENCRYPTION_KEY,
-            r#"{"provider_type":"codex","account_id":"account-search-1","is_fedramp":true}"#,
-        )
-        .expect("auth config should encrypt");
-        StoredProviderCatalogKey::new(
-            "key-codex-search-1".to_string(),
-            "provider-codex-search-1".to_string(),
-            "oauth".to_string(),
-            "oauth".to_string(),
-            None,
-            true,
-        )
-        .expect("key should build")
-        .with_transport_fields(
-            Some(json!(["openai:responses"])),
-            encrypt_python_fernet_plaintext(
-                DEVELOPMENT_ENCRYPTION_KEY,
-                "codex-search-access-token",
-            )
-            .expect("access token should encrypt"),
-            Some(auth_config),
-            None,
-            Some(json!({"openai:search": 1})),
-            None,
-            Some(4_102_444_800),
-            None,
-            None,
-        )
-        .expect("key transport should build")
-    }
-
     let seen_plans = Arc::new(Mutex::new(Vec::<serde_json::Value>::new()));
     let seen_plans_clone = Arc::clone(&seen_plans);
     let execution_runtime = Router::new().route(
@@ -316,7 +313,7 @@ async fn gateway_executes_codex_search_with_responses_permission_and_search_cont
         auth_snapshot(),
     )]));
     let candidate_repository = Arc::new(InMemoryMinimalCandidateSelectionReadRepository::seed({
-        let primary = candidate_row();
+        let primary = candidate_row("openai:search");
         let mut backup = primary.clone();
         backup.provider_id = "provider-codex-search-2".to_string();
         backup.provider_name = "codex-backup".to_string();
@@ -338,7 +335,7 @@ async fn gateway_executes_codex_search_with_responses_permission_and_search_cont
             vec![primary, backup]
         },
         {
-            let primary = endpoint();
+            let primary = endpoint("openai:search");
             let mut backup = primary.clone();
             backup.id = "endpoint-codex-search-2".to_string();
             backup.provider_id = "provider-codex-search-2".to_string();
@@ -598,3 +595,120 @@ async fn gateway_executes_codex_search_with_responses_permission_and_search_cont
     gateway_handle.abort();
     execution_runtime_handle.abort();
 }
+
+#[test]
+fn gateway_executes_codex_memories_with_responses_permission_and_native_json() {
+    run_search_sync_test(
+        "gateway_executes_codex_memories_with_responses_permission_and_native_json",
+        || async {
+            let response_body = json!({"output":[{"trace_summary":"synthetic trace", "memory_summary":"synthetic memory"}],"future_response_field":{"enabled":true}});
+            let seen = Arc::new(Mutex::new(None));
+            let captured = Arc::clone(&seen);
+            let expected = response_body.clone();
+            let runtime = Router::new().route("/v1/execute/sync", any(move |request: Request| {
+            let captured = Arc::clone(&captured);
+            let response_body = expected.clone();
+            async move {
+                let bytes = to_bytes(request.into_body(), usize::MAX).await.expect("read plan");
+                let plan: serde_json::Value = serde_json::from_slice(&bytes).expect("parse plan");
+                let request_id = plan["request_id"].clone();
+                *captured.lock().expect("capture lock") = Some(plan);
+                let (status_code, response_body) = if request_id == json!("trace-memory-error") {
+                    (400, json!({"error":{"type":"invalid_request_error","message":"synthetic invalid trace","code":"invalid_trace"},"future_error_field":{"enabled":true}}))
+                } else { (200, response_body) };
+                Json(json!({"request_id":request_id,"status_code":status_code,"headers":{"content-type":"application/json"},"body":{"json_body":response_body},"telemetry":{"elapsed_ms":1}}))
+            }
+        }));
+            let client_key = "sk-synthetic-memory-client";
+            let auth = Arc::new(InMemoryAuthApiKeySnapshotRepository::seed(vec![(
+                Some(hash_api_key(client_key)),
+                auth_snapshot(),
+            )]));
+            let candidates = Arc::new(InMemoryMinimalCandidateSelectionReadRepository::seed(vec![
+                candidate_row("openai:responses"),
+            ]));
+            let mut memory_provider = provider();
+            memory_provider.config = Some(
+                json!({"codex":{"fingerprint_convergence_enabled":true},"failover_rules":{"stop_status_codes":[400]}}),
+            );
+            let catalog = Arc::new(InMemoryProviderCatalogReadRepository::seed(
+                vec![memory_provider],
+                vec![endpoint("openai:responses")],
+                vec![key()],
+            ));
+            let request_candidates = Arc::new(InMemoryRequestCandidateRepository::default());
+            let data = crate::data::GatewayDataState::with_auth_candidate_selection_provider_catalog_and_request_candidate_repository_for_tests(auth,candidates,catalog,Arc::clone(&request_candidates),DEVELOPMENT_ENCRYPTION_KEY)
+            .with_system_config_values_for_tests([(crate::system_features::ENABLE_MODEL_DIRECTIVES_CONFIG_KEY.to_string(),json!(true))]);
+            let (runtime_url, runtime_handle) = start_server(runtime).await;
+            let state = build_state_with_execution_runtime_override(runtime_url)
+                .with_data_state_for_tests(data);
+            let (url, gateway_handle) = start_server(build_router_with_state(state)).await;
+            let input = json!({"model":"gpt-5.6-sol-max","traces":[{"id":"synthetic-trace","metadata":{"source_path":"/synthetic/trace.json"},"items":[{"type":"message","role":"user","content":[]}]}],"reasoning":{"effort":"low"},"future_request_field":{"enabled":true}});
+            let response = reqwest::Client::new()
+                .post(format!("{url}/v1/memories/trace_summarize"))
+                .header(http::header::AUTHORIZATION, format!("Bearer {client_key}"))
+                .header(TRACE_ID_HEADER, "trace-memory-1")
+                .json(&input)
+                .send()
+                .await
+                .expect("send request");
+            let status = response.status();
+            let body: serde_json::Value = response.json().await.expect("read response");
+            assert_eq!(status, StatusCode::OK, "{body}");
+            assert_eq!(body, response_body);
+            let plan = seen
+                .lock()
+                .expect("capture lock")
+                .clone()
+                .expect("captured plan");
+            assert_eq!(
+                plan["url"],
+                "https://chatgpt.com/backend-api/codex/memories/trace_summarize"
+            );
+            assert_eq!(plan["stream"], false);
+            assert_eq!(plan["client_api_format"], "openai:responses");
+            assert_eq!(plan["provider_api_format"], "openai:responses");
+            assert_eq!(plan["headers"]["originator"], "codex_cli_rs");
+            assert_eq!(
+                plan["headers"]["authorization"],
+                "Bearer codex-search-access-token"
+            );
+            assert_eq!(plan["headers"]["accept"], "application/json");
+            assert!(plan["headers"]
+                .get("x-openai-internal-codex-responses-lite")
+                .is_none());
+            let mut expected_input = input;
+            expected_input["model"] = json!("gpt-5.6-sol");
+            expected_input["reasoning"]["effort"] = json!("max");
+            assert_eq!(plan["body"]["json_body"], expected_input);
+            let stored = request_candidates
+                .list_by_request_id("trace-memory-1")
+                .await
+                .expect("read candidates");
+            assert_eq!(stored.len(), 1);
+            assert_eq!(stored[0].status, RequestCandidateStatus::Success);
+            let error = reqwest::Client::new()
+                .post(format!("{url}/v1/memories/trace_summarize"))
+                .header(http::header::AUTHORIZATION, format!("Bearer {client_key}"))
+                .header(TRACE_ID_HEADER, "trace-memory-error")
+                .json(&expected_input)
+                .send()
+                .await
+                .expect("error response");
+            let error_status = error.status();
+            assert_eq!(error_status, StatusCode::BAD_REQUEST);
+            assert_eq!(
+                error.json::<serde_json::Value>().await.expect("error JSON"),
+                json!({"error":{"type":"invalid_request_error","message":"synthetic invalid trace","code":"invalid_trace"},"future_error_field":{"enabled":true}})
+            );
+            let error_candidates = request_candidates
+                .list_by_request_id("trace-memory-error")
+                .await
+                .expect("error candidate");
+            assert_eq!(error_candidates.len(), 1);
+            assert_eq!(error_candidates[0].status, RequestCandidateStatus::Failed);
+            gateway_handle.abort();
+            runtime_handle.abort();
+        },
+    );
+}

apps/aether-gateway/src/tests/control/admin/api_keys.rs

@@ -616,6 +616,7 @@ async fn gateway_handles_admin_api_keys_create_locally_with_trusted_admin_princi
     let payload: serde_json::Value = response.json().await.expect("json body should parse");
     assert_eq!(payload["name"], json!("standalone-key"));
     assert_eq!(payload["is_standalone"], json!(true));
+    assert!(payload.get("credential_kind").is_none());
     assert_eq!(payload["rate_limit"], serde_json::Value::Null);
     assert_eq!(payload["concurrent_limit"], serde_json::Value::Null);
     assert_eq!(payload["allowed_providers"], json!(["openai"]));
@@ -646,6 +647,7 @@ async fn gateway_handles_admin_api_keys_create_locally_with_trusted_admin_princi
         list_response.json().await.expect("list json should parse");
     assert_eq!(list_payload["total"], json!(1));
     assert_eq!(list_payload["api_keys"][0]["name"], json!("standalone-key"));
+    assert!(list_payload["api_keys"][0].get("credential_kind").is_none());
 
     gateway_handle.abort();
     upstream_handle.abort();
@@ -702,6 +704,7 @@ async fn gateway_handles_admin_api_keys_update_locally_with_trusted_admin_princi
     let payload: serde_json::Value = response.json().await.expect("json body should parse");
     assert_eq!(payload["id"], json!("key-123"));
     assert_eq!(payload["name"], json!("renamed-key"));
+    assert!(payload.get("credential_kind").is_none());
     assert_eq!(payload["rate_limit"], serde_json::Value::Null);
     assert_eq!(payload["concurrent_limit"], json!(12));
     assert_eq!(payload["allowed_providers"], json!(["gemini"]));

apps/aether-gateway/src/tests/control/admin/billing.rs

@@ -72,6 +72,138 @@ async fn send_admin_billing_request(
     request.send().await.expect("request should succeed")
 }
 
+#[tokio::test]
+async fn user_account_history_http_filters_wallet_and_plan_history() {
+    use aether_data::repository::{
+        billing::{InMemoryBillingReadRepository, UserPlanEntitlementRecord},
+        users::StoredUserAuthRecord,
+        wallet::{InMemoryWalletRepository, StoredWalletSnapshot},
+    };
+
+    let users = ["user-1", "user-2"].map(|id| {
+        StoredUserAuthRecord::new(
+            id.to_string(),
+            Some(format!("{id}@example.com")),
+            true,
+            id.to_string(),
+            Some("hash".to_string()),
+            "user".to_string(),
+            "local".to_string(),
+            None,
+            None,
+            None,
+            true,
+            false,
+            None,
+            None,
+        )
+        .expect("user should build")
+    });
+    let wallets = ["user-1", "user-2"].map(|id| {
+        StoredWalletSnapshot::new(
+            format!("wallet-{id}"),
+            Some(id.to_string()),
+            None,
+            12.5,
+            2.5,
+            "finite".to_string(),
+            "USD".to_string(),
+            "active".to_string(),
+            30.0,
+            10.0,
+            3.0,
+            1.5,
+            1_710_000_000,
+        )
+        .expect("wallet should build")
+    });
+    let now = chrono::Utc::now().timestamp().max(0) as u64;
+    let entitlements = [
+        ("current", "user-1", "active"),
+        ("revoked", "user-1", "revoked"),
+        ("another-user", "user-2", "revoked"),
+    ]
+    .map(|(id, user_id, status)| UserPlanEntitlementRecord {
+        id: id.to_string(),
+        user_id: user_id.to_string(),
+        plan_id: "plan-1".to_string(),
+        payment_order_id: format!("order-{id}"),
+        status: status.to_string(),
+        starts_at_unix_secs: now - 60,
+        expires_at_unix_secs: now + 3600,
+        entitlements_snapshot: json!([]),
+        created_at_unix_secs: now - 60,
+        updated_at_unix_secs: now,
+    });
+    let state = AppState::new().unwrap().with_data_state_for_tests(
+        GatewayDataState::with_user_billing_and_wallet_for_tests(
+            Arc::new(InMemoryUserReadRepository::seed_auth_users(users)),
+            Arc::new(InMemoryBillingReadRepository::seed_user_plan_entitlements(
+                entitlements,
+            )),
+            Arc::new(InMemoryWalletRepository::seed(wallets)),
+        ),
+    );
+    let (url, handle) = start_server(build_router_with_state(state)).await;
+    let wallet_path = "/api/admin/wallets?user_id=user-1&owner_type=user&limit=1&offset=0";
+    let response = send_admin_billing_request(&url, http::Method::GET, wallet_path, None).await;
+    assert_eq!(response.status(), StatusCode::OK);
+    let wallet: serde_json::Value = response.json().await.unwrap();
+    assert_eq!(wallet["total"], 1);
+    assert_eq!(wallet["items"].as_array().unwrap().len(), 1);
+    assert_eq!(wallet["items"][0]["id"], "wallet-user-1");
+    assert_eq!(wallet["items"][0]["user_id"], "user-1");
+
+    let response = send_admin_billing_request(
+        &url,
+        http::Method::GET,
+        "/api/admin/wallets?user_id=missing-user&limit=1",
+        None,
+    )
+    .await;
+    assert_eq!(response.status(), StatusCode::OK);
+    let missing: serde_json::Value = response.json().await.unwrap();
+    assert_eq!(missing["total"], 0);
+    assert_eq!(missing["items"], json!([]));
+
+    let path = "/api/admin/users/user-1/billing/entitlements";
+    for query in ["", "?include_inactive=false"] {
+        let response =
+            send_admin_billing_request(&url, http::Method::GET, &format!("{path}{query}"), None)
+                .await;
+        assert_eq!(response.status(), StatusCode::OK);
+        let current: serde_json::Value = response.json().await.unwrap();
+        assert_eq!(current["total"], 1);
+        assert_eq!(current["items"][0]["id"], "current");
+        assert_eq!(current["items"][0]["active"], true);
+    }
+    let response = send_admin_billing_request(
+        &url,
+        http::Method::GET,
+        &format!("{path}?include_inactive=true"),
+        None,
+    )
+    .await;
+    assert_eq!(response.status(), StatusCode::OK);
+    let history: serde_json::Value = response.json().await.unwrap();
+    assert_eq!(history["total"], 2);
+    let items = history["items"].as_array().unwrap();
+    assert!(items.iter().all(|item| item["user_id"] == "user-1"));
+    assert!(items
+        .iter()
+        .any(|item| item["id"] == "revoked" && item["active"] == false));
+
+    let response = send_admin_billing_request(
+        &url,
+        http::Method::GET,
+        &format!("{path}?include_inactive=invalid"),
+        None,
+    )
+    .await;
+    assert_eq!(response.status(), StatusCode::BAD_REQUEST);
+    handle.abort();
+}
+
 #[tokio::test]
 async fn gateway_handles_admin_billing_presets_locally_with_trusted_admin_principal() {
     let upstream_hits = Arc::new(Mutex::new(0usize));
@@ -657,3 +789,110 @@ async fn gateway_handles_admin_billing_collector_routes_locally_with_trusted_adm
     gateway_handle.abort();
     upstream_handle.abort();
 }
+
+#[tokio::test]
+async fn provider_expense_http_contract_requires_admin_and_records_retries_only_once() {
+    use aether_data::repository::{
+        billing::InMemoryBillingReadRepository,
+        provider_catalog::InMemoryProviderCatalogReadRepository,
+    };
+    use aether_data_contracts::repository::provider_catalog::StoredProviderCatalogProvider;
+    let provider = StoredProviderCatalogProvider::new(
+        "provider-1".into(),
+        "=Supplier".into(),
+        None,
+        "custom".into(),
+    )
+    .unwrap();
+    let catalog = Arc::new(InMemoryProviderCatalogReadRepository::seed(
+        vec![provider],
+        vec![],
+        vec![],
+    ));
+    let state = AppState::new().unwrap().with_data_state_for_tests(
+        GatewayDataState::with_billing_reader_for_tests(Arc::new(
+            InMemoryBillingReadRepository::default(),
+        ))
+        .with_provider_catalog_reader(catalog),
+    );
+    let (url, handle) = start_server(build_router_with_state(state)).await;
+    let path = "/api/admin/billing/provider-expenses";
+    let client = reqwest::Client::new();
+    assert!(matches!(
+        client
+            .get(format!("{url}{path}"))
+            .send()
+            .await
+            .unwrap()
+            .status(),
+        StatusCode::UNAUTHORIZED | StatusCode::FORBIDDEN
+    ));
+    let payload = json!({"client_request_id":uuid::Uuid::new_v4().to_string(),"provider_id":"provider-1","kind":"subscription","amount":"12.30","currency":"USD","paid_at":"2026-09-20T00:00:00Z","period_start":"2026-09-20T00:00:00Z","period_end":"2026-10-20T00:00:00Z","note":"=SUM(1,2)"});
+    let first =
+        send_admin_billing_request(&url, http::Method::POST, path, Some(payload.clone())).await;
+    assert_eq!(first.status(), StatusCode::OK);
+    let first: serde_json::Value = first.json().await.unwrap();
+    assert_eq!(first["item"]["amount"], "12.30000000");
+    let again =
+        send_admin_billing_request(&url, http::Method::POST, path, Some(payload.clone())).await;
+    assert_eq!(again.status(), StatusCode::OK);
+    let again: serde_json::Value = again.json().await.unwrap();
+    assert_eq!(first["item"]["id"], again["item"]["id"]);
+    let mut conflict = payload.clone();
+    conflict["amount"] = json!("13");
+    assert_eq!(
+        send_admin_billing_request(&url, http::Method::POST, path, Some(conflict))
+            .await
+            .status(),
+        StatusCode::CONFLICT
+    );
+    let range = "?from=2026-09-01T00:00:00Z&to=2026-10-01T00:00:00Z&limit=1&offset=5";
+    let page =
+        send_admin_billing_request(&url, http::Method::GET, &format!("{path}{range}"), None).await;
+    assert_eq!(page.status(), StatusCode::OK);
+    let page: serde_json::Value = page.json().await.unwrap();
+    assert_eq!(page["total"], 1);
+    assert_eq!(page["items"], json!([]));
+    assert_eq!(page["totals"][0]["subscription_amount"], "12.30000000");
+    let csv = send_admin_billing_request(
+        &url,
+        http::Method::GET,
+        &format!("{path}{range}&format=csv"),
+        None,
+    )
+    .await;
+    assert_eq!(csv.status(), StatusCode::OK);
+    let csv = csv.text().await.unwrap();
+    assert!(csv.contains("'=Supplier"));
+    assert!(csv.contains("'=SUM(1,2)"));
+    assert!(csv.contains("12.30000000"));
+    let accounts = send_admin_billing_request(
+        &url,
+        http::Method::GET,
+        "/api/admin/billing/provider-accounts",
+        None,
+    )
+    .await;
+    assert_eq!(accounts.status(), StatusCode::OK);
+    let accounts: serde_json::Value = accounts.json().await.unwrap();
+    assert_eq!(accounts["items"][0]["provider_id"], "provider-1");
+    assert!(accounts["items"][0]["balance"].is_null());
+    let void_path = format!("{path}/{}/void", first["item"]["id"].as_str().unwrap());
+    let voided = send_admin_billing_request(&url, http::Method::POST, &void_path, None).await;
+    assert_eq!(voided.status(), StatusCode::OK);
+    let voided: serde_json::Value = voided.json().await.unwrap();
+    assert_eq!(voided["item"]["status"], "void");
+    let again = send_admin_billing_request(&url, http::Method::POST, &void_path, None).await;
+    assert_eq!(again.status(), StatusCode::OK);
+    let again: serde_json::Value = again.json().await.unwrap();
+    assert_eq!(voided, again);
+    let page: serde_json::Value =
+        send_admin_billing_request(&url, http::Method::GET, &format!("{path}{range}"), None)
+            .await
+            .json()
+            .await
+            .unwrap();
+    assert_eq!(page["total"], 0);
+    assert_eq!(page["totals"], json!([]));
+    handle.abort();
+}