fix(gateway): add provider key concurrency and cache affinity modes

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/proxy/websocket/responses/admission.rs

@@ -11,7 +11,7 @@ use aether_contracts::ExecutionPlan;
 
 use crate::execution_runtime::acquire_upstream_execution_gate;
 use crate::provider_pool_demand::{
-    acquire_provider_pool_in_flight_guard, ProviderPoolInFlightGuard,
+    acquire_provider_pool_execution_guard, ProviderPoolInFlightAdmission, ProviderPoolInFlightGuard,
 };
 use crate::upstream_admission::UpstreamTargetAdmissionPermit;
 use crate::{AppState, GatewayError};
@@ -41,14 +41,17 @@ impl ResponsesWebSocketTurnAdmission {
                 return Err(error);
             }
         };
-        let provider_pool = acquire_provider_pool_in_flight_guard(
-            state.runtime_state.clone(),
-            &plan.provider_id,
-            &plan.request_id,
-            plan.candidate_id.as_deref(),
-            &plan.key_id,
-        )
-        .await;
+        let provider_pool = match acquire_provider_pool_execution_guard(state, plan).await? {
+            ProviderPoolInFlightAdmission::Acquired(guard) => guard,
+            ProviderPoolInFlightAdmission::Saturated { limit } => {
+                drop(upstream_target);
+                drop(upstream_execution);
+                return Err(GatewayError::Client {
+                    status: http::StatusCode::TOO_MANY_REQUESTS,
+                    message: format!("上游账号并发已达上限 ({limit})"),
+                });
+            }
+        };
 
         Ok(Self {
             upstream_execution,