Merge remote-tracking branch 'zhefox/main' into zhefox-main

# Conflicts:
#	crates/aether-admin/src/provider/quota.rs
#	crates/aether-ai/formats/src/formats/openai/chat/stream.rs
#	crates/aether-ai/formats/src/formats/openai/responses/mod.rs
#	crates/aether-provider/pool/src/provider.rs
#	crates/aether-provider/pool/src/quota.rs

apps/aether-gateway/src/handlers/admin/provider/pool/config.rs

@@ -167,6 +167,14 @@ fn parse_pool_score_rules(pool_advanced: &Map<String, Value>) -> PoolMemberScore
 
 fn normalize_pool_preset_mode(preset: &str, raw_mode: Option<&Value>) -> Option<String> {
     match preset {
+        "cache_affinity" => Some(
+            raw_mode
+                .and_then(Value::as_str)
+                .map(str::trim)
+                .filter(|value| matches!(*value, "single_account" | "lru"))
+                .unwrap_or("single_account")
+                .to_string(),
+        ),
         "free_team_first" | "free_first" | "team_first" | "plus_first" | "pro_first" => {
             let default_mode = match preset {
                 "free_team_first" => "both",

apps/aether-gateway/src/handlers/admin/provider/pool_admin/payloads.rs

@@ -1342,6 +1342,7 @@ pub(super) fn build_admin_pool_key_payload(
         json!(key.internal_priority),
     );
     payload.insert("rpm_limit".to_string(), json!(key.rpm_limit));
+    payload.insert("concurrent_limit".to_string(), json!(key.concurrent_limit));
     payload.insert(
         "cache_ttl_minutes".to_string(),
         json!(key.cache_ttl_minutes),

apps/aether-gateway/src/handlers/admin/provider/query/models/model_test.rs

@@ -3177,6 +3177,7 @@ async fn provider_query_execute_standard_test_candidate(
                     crate::ai_serving::openai_responses_reasoning_replay_policy(
                         transport.provider.provider_type.as_str(),
                         transport.endpoint.base_url.as_str(),
+                        request_model,
                     ),
                 )
             else {
@@ -3238,6 +3239,7 @@ async fn provider_query_execute_standard_test_candidate(
         crate::ai_serving::openai_responses_reasoning_replay_policy(
             transport.provider.provider_type.as_str(),
             transport.endpoint.base_url.as_str(),
+            request_model,
         ),
     )
     .is_err()

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

@@ -34,6 +34,22 @@ fn admin_user_id_from_billing_path(request_path: &str, suffix: &str) -> Option<S
     }
 }
 
+fn admin_user_entitlement_ids_from_path(request_path: &str) -> Option<(String, String)> {
+    let rest = request_path
+        .trim_end_matches('/')
+        .strip_prefix("/api/admin/users/")?;
+    let mut parts = rest.split('/');
+    let user_id = parts.next()?.trim();
+    if parts.next()? != "billing" || parts.next()? != "entitlements" {
+        return None;
+    }
+    let entitlement_id = parts.next()?.trim();
+    if user_id.is_empty() || entitlement_id.is_empty() || parts.next().is_some() {
+        return None;
+    }
+    Some((user_id.to_string(), entitlement_id.to_string()))
+}
+
 fn admin_user_billing_operator_id(request_context: &AdminRequestContext<'_>) -> Option<String> {
     request_context
         .decision()
@@ -202,6 +218,60 @@ pub(in super::super) async fn build_admin_list_user_billing_entitlements_respons
     }
 }
 
+pub(in super::super) async fn build_admin_revoke_user_billing_entitlement_response(
+    state: &AdminAppState<'_>,
+    request_context: &AdminRequestContext<'_>,
+) -> Result<Response<Body>, GatewayError> {
+    let Some((user_id, entitlement_id)) =
+        admin_user_entitlement_ids_from_path(request_context.path())
+    else {
+        return Ok(build_admin_users_bad_request_response("缺少套餐权益 ID"));
+    };
+    if state.find_user_auth_by_id(&user_id).await?.is_none() {
+        return Ok((
+            http::StatusCode::NOT_FOUND,
+            Json(json!({ "detail": "用户不存在" })),
+        )
+            .into_response());
+    }
+    match state
+        .app()
+        .revoke_user_plan_entitlement(&user_id, &entitlement_id)
+        .await?
+    {
+        crate::LocalMutationOutcome::Applied(()) => {}
+        crate::LocalMutationOutcome::NotFound => {
+            return Ok((
+                http::StatusCode::NOT_FOUND,
+                Json(json!({ "detail": "套餐权益不存在或已失效" })),
+            )
+                .into_response());
+        }
+        crate::LocalMutationOutcome::Invalid(detail) => {
+            return Ok(build_admin_users_bad_request_response(detail));
+        }
+        crate::LocalMutationOutcome::Unavailable => {
+            return Ok(build_admin_users_data_unavailable_response());
+        }
+    }
+    let entitlements = match load_admin_user_entitlements_payload(state, &user_id).await? {
+        Some(value) => value,
+        None => return Ok(build_admin_users_data_unavailable_response()),
+    };
+    Ok(attach_admin_audit_response(
+        Json(json!({
+            "items": entitlements["items"].clone(),
+            "entitlements": entitlements["items"].clone(),
+            "total": entitlements["total"].clone(),
+        }))
+        .into_response(),
+        "admin_user_plan_revoked",
+        "revoke_user_billing_entitlement",
+        "user_plan_entitlement",
+        &entitlement_id,
+    ))
+}
+
 pub(in super::super) async fn build_admin_grant_user_billing_plan_response(
     state: &AdminAppState<'_>,
     request_context: &AdminRequestContext<'_>,

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

@@ -28,6 +28,7 @@ use self::batch::{
 use self::billing::{
     build_admin_grant_user_billing_plan_response,
     build_admin_list_user_billing_entitlements_response,
+    build_admin_revoke_user_billing_entitlement_response,
 };
 use self::groups::{
     build_admin_create_user_group_response, build_admin_delete_user_group_response,

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

@@ -8,10 +8,11 @@ use super::{
     build_admin_list_user_group_members_response, build_admin_list_user_groups_response,
     build_admin_list_user_sessions_response, build_admin_list_users_response,
     build_admin_replace_user_group_members_response, build_admin_resolve_user_selection_response,
-    build_admin_reveal_user_api_key_response, build_admin_set_default_user_group_response,
-    build_admin_toggle_user_api_key_lock_response, build_admin_update_user_api_key_response,
-    build_admin_update_user_group_response, build_admin_update_user_response,
-    build_admin_user_batch_action_response, build_admin_users_data_unavailable_response,
+    build_admin_reveal_user_api_key_response, build_admin_revoke_user_billing_entitlement_response,
+    build_admin_set_default_user_group_response, build_admin_toggle_user_api_key_lock_response,
+    build_admin_update_user_api_key_response, build_admin_update_user_group_response,
+    build_admin_update_user_response, build_admin_user_batch_action_response,
+    build_admin_users_data_unavailable_response,
 };
 use crate::handlers::admin::request::{AdminAppState, AdminRequestContext};
 use crate::GatewayError;
@@ -58,6 +59,10 @@ fn is_admin_users_route(request_context: &AdminRequestContext<'_>) -> bool {
             && path.starts_with("/api/admin/users/")
             && path.ends_with("/billing/grant-plan")
             && path.matches('/').count() == 6)
+        || (request_context.method() == http::Method::DELETE
+            && path.starts_with("/api/admin/users/")
+            && path.contains("/billing/entitlements/")
+            && path.matches('/').count() == 7)
         || ((request_context.method() == http::Method::GET
             || request_context.method() == http::Method::PUT
             || request_context.method() == http::Method::DELETE)
@@ -155,6 +160,9 @@ pub(super) async fn maybe_build_local_admin_users_routes_response(
             build_admin_grant_user_billing_plan_response(state, request_context, request_body)
                 .await?,
         )),
+        Some("revoke_user_billing_entitlement") => Ok(Some(
+            build_admin_revoke_user_billing_entitlement_response(state, request_context).await?,
+        )),
         Some("get_user") => Ok(Some(
             build_admin_get_user_response(state, request_context).await?,
         )),