Merge remote-tracking branch 'upstream/main' into codex/fix-antigravity-quota

.env.example

@@ -51,7 +51,7 @@ JWT_SECRET_KEY=change-this-to-a-secure-random-string
 ENCRYPTION_KEY=change-this-to-another-secure-random-string
 
 # 启动自举管理员（仅在当前库里还没有活动管理员时生效）
-# 手动部署时取消注释并设置；install.sh 首次生成配置时会提示输入。
+# 首次启动前必须设置 ADMIN_PASSWORD；install.sh 首次生成配置时会提示输入。
 ADMIN_EMAIL=admin@example.com
 ADMIN_USERNAME=admin123456
 # ADMIN_PASSWORD=
@@ -69,8 +69,8 @@ ADMIN_USERNAME=admin123456
 # AETHER_VSCODEX_PUBLIC_WS_URL=wss://aether.example.com/api/vscodex/ws
 # AETHER_VSCODEX_ALLOWED_ORIGINS=https://aether.example.com
 
-# docker compose 下 app 启动前自动执行 pending migration/backfill（默认 true）
-# AETHER_GATEWAY_AUTO_PREPARE_DATABASE=true
+# 启动时的数据库准备策略：auto（默认）或 verify-only
+# AETHER_GATEWAY_DATABASE_MODE=auto
 
 # PostgreSQL 连接池配置（默认每核 4 条、总池至少 32 条且最多 100 条；多实例部署应显式分配每实例预算）
 # AETHER_GATEWAY_DATA_POSTGRES_MIN_CONNECTIONS=12

Makefile

@@ -6,7 +6,7 @@ DEV_RUST_LOG := $(RUST_LOG)
 endif
 export DEV_RUST_LOG
 
-.PHONY: dev dev-backend dev-frontend migration backfill
+.PHONY: dev dev-backend dev-frontend db-status db-prepare migration backfill
 
 define DEV_BACKEND_SCRIPT
 set -euo pipefail
@@ -20,6 +20,13 @@ set -a
 source .env
 set +a
 
+if [[ -n "$${ADMIN_EMAIL:-}" || -n "$${ADMIN_USERNAME:-}" || -n "$${ADMIN_PASSWORD:-}" ]]; then
+	if [[ -z "$${ADMIN_USERNAME:-}" || -z "$${ADMIN_PASSWORD:-}" ]]; then
+		echo "=> 管理员自举配置不完整，请在 .env 中设置 ADMIN_USERNAME 和 ADMIN_PASSWORD"
+		exit 1
+	fi
+fi
+
 dotenv_has_key() {
 	local key="$$1"
 	grep -Eq "^[[:space:]]*$${key}=" .env
@@ -201,12 +208,17 @@ print_startup_failure_hint() {
 
 	if [ -n "$${log_file}" ] && [ -f "$${log_file}" ]; then
 		if grep -Eq "database schema is behind" "$${log_file}"; then
-			echo "=> 检测到数据库 schema 落后，请执行: make migration"
+			echo "=> 检测到数据库尚未准备完成，请执行: make db-prepare"
 			return
 		fi
 
 		if grep -Eq "database backfills are behind" "$${log_file}"; then
-			echo "=> 检测到待执行 backfills，请执行: make backfill"
+			echo "=> 检测到数据库尚未准备完成，请执行: make db-prepare"
+			return
+		fi
+
+		if grep -Eq "bootstrap admin env is partially configured.*ADMIN_PASSWORD" "$${log_file}"; then
+			echo "=> 首次启动需要管理员密码，请在 .env 中设置 ADMIN_PASSWORD"
 			return
 		fi
 	fi
@@ -352,8 +364,8 @@ create_gateway_log_file
 
 echo "=> 启动 aether-gateway (Rust frontdoor: 0.0.0.0:$${APP_PORT})..."
 echo "=> 日志过滤: $${RUST_LOG}"
-echo "=> 执行命令: cargo run -p aether-gateway -- --app-port $${APP_PORT}"
-cargo run -p aether-gateway -- --app-port "$${APP_PORT}" > >(
+echo "=> 执行命令: cargo run -p aether-gateway --bin aether-gateway -- --app-port $${APP_PORT}"
+cargo run -p aether-gateway --bin aether-gateway -- --app-port "$${APP_PORT}" > >(
 	tee -a "$${GATEWAY_LOG_FILE}"
 ) 2>&1 &
 GATEWAY_PID=$$!
@@ -444,7 +456,7 @@ if [ -f .env ]; then
 fi
 export APP_PORT="$${APP_PORT:-8084}"
 
-echo "=> 启动后端: RUST_LOG=$${DEV_RUST_LOG} cargo run -p aether-gateway -- --app-port $${APP_PORT:-8084}"
+echo "=> 启动后端: RUST_LOG=$${DEV_RUST_LOG} cargo run -p aether-gateway --bin aether-gateway -- --app-port $${APP_PORT:-8084}"
 /bin/bash -euo pipefail -c "$$DEV_BACKEND_SCRIPT" &
 backend_pid=$$!
 
@@ -494,8 +506,14 @@ export DEV_SCRIPT
 define DB_TASK_SCRIPT
 set -euo pipefail
 
-if [ -z "$${DB_TASK_FLAG:-}" ] || [ -z "$${DB_TASK_LABEL:-}" ]; then
-	echo "=> 内部错误: DB_TASK_FLAG / DB_TASK_LABEL 未设置"
+if [ -z "$${DB_TASK_COMMAND:-}" ] || [ -z "$${DB_TASK_LABEL:-}" ]; then
+	echo "=> 内部错误: DB_TASK_COMMAND / DB_TASK_LABEL 未设置"
+	exit 1
+fi
+
+read -r -a db_task_args <<< "$${DB_TASK_COMMAND}"
+if [ "$${#db_task_args[@]}" -eq 0 ]; then
+	echo "=> 内部错误: DB_TASK_COMMAND 为空"
 	exit 1
 fi
 
@@ -546,8 +564,8 @@ if ! command -v cargo >/dev/null 2>&1; then
 	exit 1
 fi
 
-echo "=> 执行 $${DB_TASK_LABEL}: cargo run -p aether-gateway -- $${DB_TASK_FLAG}"
-exec cargo run -p aether-gateway -- "$${DB_TASK_FLAG}"
+echo "=> 执行 $${DB_TASK_LABEL}: cargo run -p aether-gateway --bin aether-gateway -- $${db_task_args[*]}"
+exec cargo run -p aether-gateway --bin aether-gateway -- "$${db_task_args[@]}"
 endef
 export DB_TASK_SCRIPT
 
@@ -560,8 +578,14 @@ dev-backend:
 dev-frontend:
 	@cd frontend && npm run dev
 
+db-status:
+	@DB_TASK_COMMAND="db status" DB_TASK_LABEL="数据库状态检查" $(SHELL) -euo pipefail -c "$$DB_TASK_SCRIPT"
+
+db-prepare:
+	@DB_TASK_COMMAND="db prepare" DB_TASK_LABEL="数据库准备" $(SHELL) -euo pipefail -c "$$DB_TASK_SCRIPT"
+
 migration:
-	@DB_TASK_FLAG=--migrate DB_TASK_LABEL="数据库迁移" $(SHELL) -euo pipefail -c "$$DB_TASK_SCRIPT"
+	@DB_TASK_COMMAND="--migrate" DB_TASK_LABEL="数据库迁移" $(SHELL) -euo pipefail -c "$$DB_TASK_SCRIPT"
 
 backfill:
-	@DB_TASK_FLAG=--apply-backfills DB_TASK_LABEL="数据库 backfill" $(SHELL) -euo pipefail -c "$$DB_TASK_SCRIPT"
+	@DB_TASK_COMMAND="--apply-backfills" DB_TASK_LABEL="数据库 backfill" $(SHELL) -euo pipefail -c "$$DB_TASK_SCRIPT"

README.md

@@ -128,6 +128,7 @@ Docker Compose 用户可在部署目录的 `.env` 中设置 `APP_IMAGE=ghcr.io/f
 ## 本地开发
 
 依赖 Docker、Rust toolchain、Node.js 和 make。
+首次启动前需要在 `.env` 中设置 `ADMIN_PASSWORD`，用于创建本地管理员。
 
 ```bash
 make dev
@@ -135,6 +136,12 @@ make dev
 
 `make dev` 会同时启动后端 `aether-gateway` 和前端 `frontend` 的 Vite dev server。需要单独启动时可使用 `make dev-backend` 或 `make dev-frontend`。
 Postgres / Redis 本地依赖未就绪时，`make dev` 会自动执行 `docker compose up -d postgres redis`。
+数据库 schema 和历史数据准备也会在启动时自动完成；通常不需要手动区分 migration 与 backfill。排查或部署前预执行时可使用：
+
+```bash
+make db-status
+make db-prepare
+```
 
 ## Codex 远程协同
 
@@ -173,7 +180,8 @@ Aether Tunnel 是配套的正向代理节点，部署在海外 VPS 上，为墙
 - `AETHER_MAX_REDACTED_SYNC_RESPONSE_BODY_MB`：可选的 PII 恢复同步响应缓冲上限；未配置或设为 `0` 时不限制
 - `REDIS_URL`：Redis 连接串；仅 Postgres + Redis 的 Docker Compose 部署需要配置
 - `AETHER_RUNTIME_BACKEND=memory|redis`：运行时缓存/协调后端。SQLite 默认用 `memory`，不会连接 Redis；多节点部署和需要跨 gateway 重启恢复 OpenAI Responses continuation history 的部署必须使用共享 Redis
-- `AETHER_GATEWAY_AUTO_PREPARE_DATABASE`：常规启动前自动执行挂起的 schema migration 和 backfill；仓库自带的 `docker-compose.yml` 默认开启
+- `AETHER_GATEWAY_DATABASE_MODE=auto|verify-only`：数据库启动策略，默认 `auto`，自动完成挂起的 schema migration 和 backfill；`verify-only` 仅检查并在数据库落后时拒绝启动
+- `AETHER_GATEWAY_AUTO_PREPARE_DATABASE`：旧版兼容开关；新配置请使用 `AETHER_GATEWAY_DATABASE_MODE`
 - `JWT_SECRET_KEY` / `ENCRYPTION_KEY`：认证和敏感数据加密所需密钥
 - `API_KEY_PREFIX`：用户和管理员新建 API Key 时使用的前缀，默认 `sk`
 - `ADMIN_USERNAME` / `ADMIN_PASSWORD` / `ADMIN_EMAIL`：首次启动时自举首个本地管理员；`install.sh` 会提示输入管理员密码

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

@@ -9,7 +9,7 @@ use aether_ai_serving::{
 use aether_dispatch_core::{DispatchSequence, DispatchSequenceItem};
 use aether_routing_core::{
     rank_vector_for_candidate, CandidateKind, ResolvedRoutingPolicy, RoutingCandidateFacts,
-    RoutingCandidateTrace, RoutingDecisionTrace,
+    RoutingCandidateTrace, RoutingDecisionTrace, RoutingExecutionPolicy,
 };
 use aether_scheduler_core::{
     ClientSessionAffinity, SchedulerMinimalCandidateSelectionCandidate, SchedulerRankingOutcome,
@@ -79,6 +79,13 @@ type DecorateSkippedCandidateFn<'a> = Arc<
 pub(crate) trait LocalExecutionAttemptSource<T>: Send {
     async fn next_execution_attempt(&mut self) -> Result<Option<T>, GatewayError>;
 
+    /// Returns the request-scoped execution behaviour selected by routing.
+    /// Execution wrappers use this snapshot before consuming the first
+    /// attempt, avoiding a second lookup against mutable system settings.
+    fn routing_execution_policy(&self) -> Option<RoutingExecutionPolicy> {
+        None
+    }
+
     async fn drain_execution_attempts(&mut self) -> Result<Vec<T>, GatewayError>;
 
     async fn skip_credential(&mut self, key_id: &str) -> Result<(), GatewayError>;
@@ -1237,9 +1244,7 @@ async fn scheduler_cache_affinity_enabled(
     state: PlannerAppState<'_>,
     routing_policy: Option<&ResolvedRoutingPolicy>,
 ) -> bool {
-    scheduler_ordering_config_for_routing_policy(state, routing_policy)
-        .await
-        .scheduling_mode
+    scheduler_ordering_config_for_routing_policy(routing_policy).scheduling_mode
         == SchedulerSchedulingMode::CacheAffinity
 }
 

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

@@ -6,14 +6,11 @@ use aether_ai_serving::{
 use aether_routing_core::ResolvedRoutingPolicy;
 use async_trait::async_trait;
 use tokio::sync::Mutex;
-use tracing::warn;
 
 use crate::ai_serving::{GatewayAuthApiKeySnapshot, PlannerAppState};
 use crate::clock::current_unix_ms;
 use crate::handlers::shared::provider_pool::admin_provider_pool_config_from_config_value;
-use crate::scheduler::config::{
-    read_scheduler_ordering_config, SchedulerOrderingConfig, SchedulerSchedulingMode,
-};
+use crate::scheduler::config::{SchedulerOrderingConfig, SchedulerSchedulingMode};
 use aether_scheduler_core::{
     matches_affinity_target, ClientSessionAffinity, SchedulerAffinityTarget,
     SchedulerMinimalCandidateSelectionCandidate, SchedulerPriorityMode, SchedulerRankableCandidate,
@@ -133,7 +130,7 @@ pub(crate) async fn rank_eligible_local_execution_candidates(
     required_capabilities: Option<&serde_json::Value>,
     routing_policy: Option<&ResolvedRoutingPolicy>,
 ) -> Vec<EligibleLocalExecutionCandidate> {
-    let ordering_config = scheduler_ordering_config_for_routing_policy(state, routing_policy).await;
+    let ordering_config = scheduler_ordering_config_for_routing_policy(routing_policy);
     let port = GatewayLocalCandidateRankingPort {
         state,
         requested_model,
@@ -184,16 +181,24 @@ fn ai_ranking_scheduling_mode(mode: SchedulerSchedulingMode) -> AiRankingSchedul
     }
 }
 
-/// Ordering config for a request. A resolved routing policy is authoritative
-/// and is never merged with legacy system-config values; without a policy the
-/// effective default (system-default routing group, then legacy keys) applies.
-pub(crate) async fn scheduler_ordering_config_for_routing_policy(
-    state: PlannerAppState<'_>,
+/// Return the immutable scheduler snapshot carried by a resolved routing
+/// policy. A missing policy is a programming error in production request
+/// paths; unit tests may use the scheduler default for isolated ranking tests.
+pub(crate) fn scheduler_ordering_config_for_routing_policy(
     routing_policy: Option<&ResolvedRoutingPolicy>,
 ) -> SchedulerOrderingConfig {
     match routing_policy {
         Some(policy) => SchedulerOrderingConfig::from_routing_policy(policy),
-        None => read_scheduler_ordering_config_or_default(state).await,
+        None => {
+            #[cfg(test)]
+            {
+                SchedulerOrderingConfig::default()
+            }
+            #[cfg(not(test))]
+            {
+                panic!("resolved routing policy is required before candidate scheduling")
+            }
+        }
     }
 }
 
@@ -238,23 +243,6 @@ fn routing_overlaid_candidate(
     overlaid
 }
 
-async fn read_scheduler_ordering_config_or_default(
-    state: PlannerAppState<'_>,
-) -> SchedulerOrderingConfig {
-    match read_scheduler_ordering_config(state.app()).await {
-        Ok(config) => config,
-        Err(error) => {
-            warn!(
-                event_name = "planner_scheduler_ordering_config_load_failed",
-                log_type = "event",
-                error = ?error,
-                "failed to load scheduler ordering config while ranking local execution candidates"
-            );
-            SchedulerOrderingConfig::default()
-        }
-    }
-}
-
 #[cfg(test)]
 mod tests {
     use std::collections::BTreeMap;
@@ -263,10 +251,16 @@ mod tests {
     use aether_ai_serving::{
         ai_ranking_context, build_ai_rankable_candidate, AiRankableCandidateParts,
     };
-    use aether_data::repository::provider_catalog::InMemoryProviderCatalogReadRepository;
+    use aether_data::repository::{
+        provider_catalog::InMemoryProviderCatalogReadRepository,
+        routing_profiles::InMemoryRoutingGroupRepository,
+    };
     use aether_data_contracts::repository::provider_catalog::{
         StoredProviderCatalogEndpoint, StoredProviderCatalogKey, StoredProviderCatalogProvider,
     };
+    use aether_data_contracts::repository::routing_profiles::{
+        CreateRoutingGroupRecord, RoutingGroupWriteRepository,
+    };
     use aether_scheduler_core::{
         apply_scheduler_candidate_ranking,
         build_scheduler_affinity_cache_key_for_api_key_id_with_client_session,
@@ -296,7 +290,11 @@ mod tests {
         required_capabilities: Option<&serde_json::Value>,
     ) -> Vec<SchedulerMinimalCandidateSelectionCandidate> {
         let normalized_client_api_format = client_api_format.trim().to_ascii_lowercase();
-        let ordering_config = super::read_scheduler_ordering_config_or_default(state).await;
+        let ordering_config =
+            crate::scheduler::config::read_system_default_routing_ordering_config(state.app())
+                .await
+                .expect("routing strategy should load")
+                .unwrap_or_default();
         let mut candidates = candidates;
         let mut rankables = Vec::with_capacity(candidates.len());
         let mut ordering_cache = CandidateTransportRankingFactsCache::default();
@@ -372,6 +370,7 @@ mod tests {
             scheduling_mode: aether_routing_core::RoutingSchedulingMode::CacheAffinity,
             keep_priority_on_conversion: false,
             sticky_key_attempts: aether_routing_core::DEFAULT_STICKY_KEY_ATTEMPTS,
+            execution_policy: Default::default(),
             ranking_overlay: aether_routing_core::RankingOverlay::default(),
             mutation_plan: Default::default(),
             pool_policy_overrides: BTreeMap::new(),
@@ -408,17 +407,14 @@ mod tests {
             scheduling_mode: aether_routing_core::RoutingSchedulingMode::FixedOrder,
             keep_priority_on_conversion: false,
             sticky_key_attempts: aether_routing_core::DEFAULT_STICKY_KEY_ATTEMPTS,
+            execution_policy: Default::default(),
             ranking_overlay: Default::default(),
             mutation_plan: Default::default(),
             pool_policy_overrides: Default::default(),
             matched_rules: Vec::new(),
         };
 
-        let ordering = super::scheduler_ordering_config_for_routing_policy(
-            PlannerAppState::new(&state),
-            Some(&policy),
-        )
-        .await;
+        let ordering = super::scheduler_ordering_config_for_routing_policy(Some(&policy));
 
         assert_eq!(
             ordering.scheduling_mode,
@@ -446,6 +442,7 @@ mod tests {
             scheduling_mode: aether_routing_core::RoutingSchedulingMode::CacheAffinity,
             keep_priority_on_conversion: false,
             sticky_key_attempts: aether_routing_core::DEFAULT_STICKY_KEY_ATTEMPTS,
+            execution_policy: Default::default(),
             ranking_overlay: aether_routing_core::RankingOverlay {
                 pool_priority_overrides: BTreeMap::from([("provider-1".to_string(), 4)]),
                 key_priority_overrides: BTreeMap::from([("representative-key".to_string(), 1)]),
@@ -917,7 +914,8 @@ mod tests {
     }
 
     #[tokio::test]
-    async fn local_execution_ranking_keeps_cross_format_priority_when_global_override_is_enabled() {
+    async fn local_execution_ranking_keeps_cross_format_priority_when_strategy_override_is_enabled()
+    {
         let provider_catalog = InMemoryProviderCatalogReadRepository::seed(
             vec![
                 sample_provider_with_options("provider-same", false, 10),
@@ -932,14 +930,32 @@ mod tests {
                 sample_key_for_provider("provider-cross", "key-cross", ""),
             ],
         );
+        let routing_repository = std::sync::Arc::new(InMemoryRoutingGroupRepository::default());
+        routing_repository
+            .create_routing_group(CreateRoutingGroupRecord {
+                id: "strategy-default".to_string(),
+                name: "strategy-default".to_string(),
+                description: None,
+                enabled: true,
+                is_system_default: true,
+                sort_order: 0,
+                config_json: json!({
+                    "default_policy": {
+                        "keep_priority_on_conversion": true
+                    }
+                }),
+                version: 1,
+                created_at: 1,
+                updated_at: 1,
+                published_at: None,
+            })
+            .await
+            .expect("routing strategy should be created");
         let data_state = GatewayDataState::with_provider_transport_reader_for_tests(
             std::sync::Arc::new(provider_catalog),
             "development-key",
         )
-        .with_system_config_values_for_tests(vec![(
-            "keep_priority_on_conversion".to_string(),
-            json!(true),
-        )]);
+        .with_routing_group_repository_for_tests(routing_repository);
         let state = AppState::new()
             .expect("state should build")
             .with_data_state_for_tests(data_state);

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

@@ -384,8 +384,7 @@ async fn resolve_and_rank_local_execution_candidates_with_pool_expansion(
                 None
             } else {
                 Some(
-                    scheduler_ordering_config_for_routing_policy(state, routing_policy)
-                        .await
+                    scheduler_ordering_config_for_routing_policy(routing_policy)
                         .sticky_key_attempts,
                 )
             };

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

@@ -174,8 +174,9 @@ impl AiCandidatePreselectionPort for GatewayLocalCandidatePreselectionPort<'_> {
                 self.ranking_seed,
                 false,
                 self.request_operation,
-                self.routing_policy
-                    .map(SchedulerOrderingConfig::from_routing_policy),
+                super::candidate_ranking::scheduler_ordering_config_for_routing_policy(
+                    self.routing_policy,
+                ),
             )
             .await?;
 
@@ -427,11 +428,7 @@ impl<'a> LocalCandidatePreselectionPageCursor<'a> {
         );
 
         let ordering_config =
-            super::candidate_ranking::scheduler_ordering_config_for_routing_policy(
-                state,
-                routing_policy,
-            )
-            .await;
+            super::candidate_ranking::scheduler_ordering_config_for_routing_policy(routing_policy);
 
         Self {
             state,
@@ -1293,9 +1290,7 @@ impl<'a> LocalCandidatePreselectionPageCursor<'a> {
                     .then_some(self.client_session_affinity.as_ref())
                     .flatten(),
                 self.ranking_seed,
-                self.routing_policy
-                    .as_ref()
-                    .map(SchedulerOrderingConfig::from_routing_policy),
+                self.ordering_config,
             )
             .await?;
         let skipped_candidates = skipped_candidates
@@ -1890,6 +1885,7 @@ mod tests {
             scheduling_mode: aether_routing_core::RoutingSchedulingMode::FixedOrder,
             keep_priority_on_conversion: false,
             sticky_key_attempts: aether_routing_core::DEFAULT_STICKY_KEY_ATTEMPTS,
+            execution_policy: Default::default(),
             ranking_overlay: Default::default(),
             mutation_plan: Default::default(),
             pool_policy_overrides: Default::default(),
@@ -1954,6 +1950,7 @@ mod tests {
             scheduling_mode: aether_routing_core::RoutingSchedulingMode::FixedOrder,
             keep_priority_on_conversion: false,
             sticky_key_attempts: aether_routing_core::DEFAULT_STICKY_KEY_ATTEMPTS,
+            execution_policy: Default::default(),
             ranking_overlay: Default::default(),
             mutation_plan: Default::default(),
             pool_policy_overrides: Default::default(),
@@ -2692,6 +2689,7 @@ mod tests {
             scheduling_mode: aether_routing_core::RoutingSchedulingMode::FixedOrder,
             keep_priority_on_conversion: true,
             sticky_key_attempts: aether_routing_core::DEFAULT_STICKY_KEY_ATTEMPTS,
+            execution_policy: Default::default(),
             ranking_overlay: Default::default(),
             mutation_plan: Default::default(),
             pool_policy_overrides: Default::default(),

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

@@ -625,21 +625,17 @@ pub(crate) async fn attach_routing_policy_to_local_requested_model_input(
                     GatewayRoutingSelectionError::NotFound(explicit_group.unwrap_or_default()),
                 ));
             }
-            None
+            return Err(routing_selection_error(
+                GatewayRoutingSelectionError::NoDefault,
+            ));
         }
     };
 
     let Some((group_id, group_version, group_config_json, selection_source)) = selected_group
     else {
-        input.client_session_affinity = client_session_affinity_from_api_request(
-            client_api_format,
-            &parts.headers,
-            Some(body_json),
-        );
-        input.routing_policy = None;
-        input.routing_trace_seed = None;
-        input.routing_context = None;
-        return Ok(());
+        return Err(routing_selection_error(
+            GatewayRoutingSelectionError::NoDefault,
+        ));
     };
 
     if try_attach_static_default_routing_policy_to_input(
@@ -863,6 +859,10 @@ fn routing_selection_error(error: GatewayRoutingSelectionError) -> GatewayError
         GatewayRoutingSelectionError::Repository(message) => {
             GatewayError::Internal(format!("routing group repository lookup failed: {message}"))
         }
+        GatewayRoutingSelectionError::NoDefault => GatewayError::Client {
+            status: StatusCode::SERVICE_UNAVAILABLE,
+            message: "no enabled routing strategy is configured for this request".to_string(),
+        },
         error => GatewayError::Client {
             status: StatusCode::FORBIDDEN,
             message: error.to_string(),
@@ -1207,6 +1207,7 @@ mod tests {
                 description: None,
                 enabled: true,
                 is_system_default: false,
+                sort_order: 0,
                 config_json: json!({}),
                 version: 1,
                 created_at: 1,

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

@@ -26,7 +26,6 @@ use crate::ai_serving::{
 };
 use crate::client_session_affinity::client_session_affinity_from_api_request;
 use crate::clock::current_unix_secs;
-use crate::scheduler::config::SchedulerOrderingConfig;
 use crate::{AppState, GatewayError};
 
 use super::{
@@ -141,10 +140,9 @@ pub(crate) async fn materialize_local_same_format_provider_candidate_attempts(
             current_unix_secs(),
             false,
             spec.operation.map(|operation| operation.as_str()),
-            input
-                .routing_policy
-                .as_ref()
-                .map(SchedulerOrderingConfig::from_routing_policy),
+            crate::ai_serving::planner::candidate_ranking::scheduler_ordering_config_for_routing_policy(
+                input.routing_policy.as_ref(),
+            ),
         )
         .await?;
     let outcome = materialize_local_execution_candidates_with_serving(
@@ -251,10 +249,9 @@ pub(crate) async fn build_local_same_format_provider_candidate_attempt_source<'a
             current_unix_secs(),
             false,
             spec.operation.map(|operation| operation.as_str()),
-            input
-                .routing_policy
-                .as_ref()
-                .map(SchedulerOrderingConfig::from_routing_policy),
+            crate::ai_serving::planner::candidate_ranking::scheduler_ordering_config_for_routing_policy(
+                input.routing_policy.as_ref(),
+            ),
         )
         .await?;
 

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

@@ -26,6 +26,7 @@ use super::{
     LocalSameFormatProviderCandidateAttemptSource, LocalSameFormatProviderDecisionInput,
     LocalSameFormatProviderSpec,
 };
+use aether_routing_core::RoutingExecutionPolicy;
 
 pub(crate) struct LocalSameFormatProviderSyncAttemptSource<'a> {
     state: &'a AppState,
@@ -189,6 +190,13 @@ pub(crate) async fn build_local_stream_attempt_source<'a>(
 
 #[async_trait]
 impl LocalExecutionAttemptSource<AiSyncAttempt> for LocalSameFormatProviderSyncAttemptSource<'_> {
+    fn routing_execution_policy(&self) -> Option<RoutingExecutionPolicy> {
+        self.input
+            .routing_policy
+            .as_ref()
+            .map(|policy| policy.execution_policy)
+    }
+
     async fn next_execution_attempt(&mut self) -> Result<Option<AiSyncAttempt>, GatewayError> {
         while let Some(attempt) = self.candidates.next_attempt().await? {
             match self.build_sync_attempt(attempt).await? {
@@ -234,6 +242,13 @@ impl LocalExecutionAttemptSource<AiSyncAttempt> for LocalSameFormatProviderSyncA
 impl LocalExecutionAttemptSource<AiStreamAttempt>
     for LocalSameFormatProviderStreamAttemptSource<'_>
 {
+    fn routing_execution_policy(&self) -> Option<RoutingExecutionPolicy> {
+        self.input
+            .routing_policy
+            .as_ref()
+            .map(|policy| policy.execution_policy)
+    }
+
     async fn next_execution_attempt(&mut self) -> Result<Option<AiStreamAttempt>, GatewayError> {
         while let Some(attempt) = self.candidates.next_attempt().await? {
             match self.build_stream_attempt(attempt).await? {

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

@@ -21,7 +21,8 @@ use crate::client_session_affinity::{
 };
 use crate::orchestration::{
     insert_pool_key_lease_report_context_fields, ExecutionAttemptIdentity,
-    ROUTING_POOL_POLICY_OVERRIDE_REPORT_FIELD, SCHEDULER_AFFINITY_EPOCH_REPORT_FIELD,
+    ROUTING_EXECUTION_POLICY_REPORT_FIELD, ROUTING_POOL_POLICY_OVERRIDE_REPORT_FIELD,
+    SCHEDULER_AFFINITY_EPOCH_REPORT_FIELD,
 };
 use crate::scheduler::affinity::insert_scheduler_affinity_policy_report_context_field;
 
@@ -112,6 +113,11 @@ pub(crate) fn build_local_execution_report_context(
     }
     insert_pool_key_lease_report_context_fields(&mut extra_fields, parts.pool_key_lease);
     insert_scheduler_affinity_policy_report_context_field(&mut extra_fields, parts.routing_policy);
+    if let Some(policy) = parts.routing_policy {
+        if let Ok(value) = serde_json::to_value(policy.execution_policy) {
+            extra_fields.insert(ROUTING_EXECUTION_POLICY_REPORT_FIELD.to_string(), value);
+        }
+    }
     if let Some(override_policy) = parts
         .routing_policy
         .and_then(|policy| policy.pool_policy_overrides.get(parts.provider_id))

apps/aether-gateway/src/ai_serving/planner/specialized/files.rs

@@ -17,6 +17,7 @@ use crate::ai_serving::{
     resolve_gemini_files_sync_spec as resolve_sync_spec, LocalGeminiFilesSpec,
 };
 use crate::{AiExecutionDecision, AppState, GatewayError};
+use aether_routing_core::RoutingExecutionPolicy;
 
 use self::decision::maybe_build_local_gemini_files_decision_payload_for_candidate;
 use self::support::{
@@ -174,6 +175,13 @@ pub(crate) async fn build_local_gemini_files_stream_attempt_source_for_kind<'a>(
 
 #[async_trait]
 impl LocalExecutionAttemptSource<AiSyncAttempt> for LocalGeminiFilesSyncAttemptSource<'_> {
+    fn routing_execution_policy(&self) -> Option<RoutingExecutionPolicy> {
+        self.input
+            .routing_policy
+            .as_ref()
+            .map(|policy| policy.execution_policy)
+    }
+
     async fn next_execution_attempt(&mut self) -> Result<Option<AiSyncAttempt>, GatewayError> {
         while let Some(attempt) = self.candidates.next_attempt().await? {
             match self.build_sync_attempt(attempt).await? {
@@ -212,6 +220,13 @@ impl LocalExecutionAttemptSource<AiSyncAttempt> for LocalGeminiFilesSyncAttemptS
 
 #[async_trait]
 impl LocalExecutionAttemptSource<AiStreamAttempt> for LocalGeminiFilesStreamAttemptSource<'_> {
+    fn routing_execution_policy(&self) -> Option<RoutingExecutionPolicy> {
+        self.input
+            .routing_policy
+            .as_ref()
+            .map(|policy| policy.execution_policy)
+    }
+
     async fn next_execution_attempt(&mut self) -> Result<Option<AiStreamAttempt>, GatewayError> {
         while let Some(attempt) = self.candidates.next_attempt().await? {
             match self.build_stream_attempt(attempt).await? {

apps/aether-gateway/src/ai_serving/planner/specialized/files/support.rs

@@ -26,7 +26,6 @@ use crate::ai_serving::{
 };
 use crate::client_session_affinity::client_session_affinity_from_parts;
 use crate::clock::current_unix_secs;
-use crate::scheduler::config::SchedulerOrderingConfig;
 use crate::{AppState, GatewayError};
 
 pub(super) use crate::ai_serving::planner::candidate_materialization::LocalExecutionCandidateAttempt as LocalGeminiFilesCandidateAttempt;
@@ -109,10 +108,9 @@ pub(super) async fn materialize_local_gemini_files_candidate_attempts(
             Some(&input.auth_snapshot),
             input.client_session_affinity.as_ref(),
             current_unix_secs(),
-            input
-                .routing_policy
-                .as_ref()
-                .map(SchedulerOrderingConfig::from_routing_policy),
+            crate::ai_serving::planner::candidate_ranking::scheduler_ordering_config_for_routing_policy(
+                input.routing_policy.as_ref(),
+            ),
         )
         .await?;
     let outcome = materialize_local_execution_candidates_with_serving(
@@ -186,10 +184,9 @@ pub(super) async fn build_local_gemini_files_candidate_attempt_source<'a>(
             Some(&input.auth_snapshot),
             input.client_session_affinity.as_ref(),
             current_unix_secs(),
-            input
-                .routing_policy
-                .as_ref()
-                .map(SchedulerOrderingConfig::from_routing_policy),
+            crate::ai_serving::planner::candidate_ranking::scheduler_ordering_config_for_routing_policy(
+                input.routing_policy.as_ref(),
+            ),
         )
         .await?;
     Ok(build_local_execution_candidate_attempt_source_with_serving(

apps/aether-gateway/src/ai_serving/planner/specialized/image.rs

@@ -19,6 +19,7 @@ use crate::ai_serving::{
     resolve_local_image_sync_spec as resolve_sync_spec,
 };
 use crate::{AiExecutionDecision, AppState, GatewayError};
+use aether_routing_core::RoutingExecutionPolicy;
 
 use self::decision::maybe_build_local_openai_image_decision_payload_for_candidate;
 use self::support::{
@@ -252,6 +253,13 @@ pub(crate) async fn build_local_image_stream_attempt_source_for_kind<'a>(
 
 #[async_trait]
 impl LocalExecutionAttemptSource<AiSyncAttempt> for LocalOpenAiImageSyncAttemptSource<'_> {
+    fn routing_execution_policy(&self) -> Option<RoutingExecutionPolicy> {
+        self.input
+            .routing_policy
+            .as_ref()
+            .map(|policy| policy.execution_policy)
+    }
+
     async fn next_execution_attempt(&mut self) -> Result<Option<AiSyncAttempt>, GatewayError> {
         while let Some(attempt) = self.candidates.next_attempt().await? {
             match self.build_sync_attempt(attempt).await? {
@@ -290,6 +298,13 @@ impl LocalExecutionAttemptSource<AiSyncAttempt> for LocalOpenAiImageSyncAttemptS
 
 #[async_trait]
 impl LocalExecutionAttemptSource<AiStreamAttempt> for LocalOpenAiImageStreamAttemptSource<'_> {
+    fn routing_execution_policy(&self) -> Option<RoutingExecutionPolicy> {
+        self.input
+            .routing_policy
+            .as_ref()
+            .map(|policy| policy.execution_policy)
+    }
+
     async fn next_execution_attempt(&mut self) -> Result<Option<AiStreamAttempt>, GatewayError> {
         while let Some(attempt) = self.candidates.next_attempt().await? {
             match self.build_stream_attempt(attempt).await? {

apps/aether-gateway/src/ai_serving/planner/specialized/image/support.rs

@@ -27,7 +27,6 @@ use crate::ai_serving::{
 };
 use crate::client_session_affinity::client_session_affinity_from_parts;
 use crate::clock::current_unix_secs;
-use crate::scheduler::config::SchedulerOrderingConfig;
 use crate::{AppState, GatewayError};
 use aether_scheduler_core::SchedulerMinimalCandidateSelectionCandidate;
 
@@ -128,10 +127,9 @@ pub(super) async fn list_local_openai_image_candidate_attempts(
                 input.client_session_affinity.as_ref(),
                 current_unix_secs(),
                 false,
-                input
-                    .routing_policy
-                    .as_ref()
-                    .map(SchedulerOrderingConfig::from_routing_policy),
+                crate::ai_serving::planner::candidate_ranking::scheduler_ordering_config_for_routing_policy(
+                    input.routing_policy.as_ref(),
+                ),
             )
             .await
         {
@@ -206,10 +204,9 @@ pub(super) async fn build_local_openai_image_candidate_attempt_source<'a>(
                 input.client_session_affinity.as_ref(),
                 current_unix_secs(),
                 false,
-                input
-                    .routing_policy
-                    .as_ref()
-                    .map(SchedulerOrderingConfig::from_routing_policy),
+                crate::ai_serving::planner::candidate_ranking::scheduler_ordering_config_for_routing_policy(
+                    input.routing_policy.as_ref(),
+                ),
             )
             .await
         {

apps/aether-gateway/src/ai_serving/planner/specialized/video.rs

@@ -16,6 +16,7 @@ use crate::ai_serving::{
     LocalVideoCreateSpec,
 };
 use crate::{AiExecutionDecision, AppState, GatewayError};
+use aether_routing_core::RoutingExecutionPolicy;
 
 use self::decision::maybe_build_local_video_create_decision_payload_for_candidate;
 use self::support::{
@@ -104,6 +105,13 @@ pub(crate) async fn build_local_video_sync_attempt_source_for_kind<'a>(
 
 #[async_trait]
 impl LocalExecutionAttemptSource<AiSyncAttempt> for LocalVideoCreateSyncAttemptSource<'_> {
+    fn routing_execution_policy(&self) -> Option<RoutingExecutionPolicy> {
+        self.input
+            .routing_policy
+            .as_ref()
+            .map(|policy| policy.execution_policy)
+    }
+
     async fn next_execution_attempt(&mut self) -> Result<Option<AiSyncAttempt>, GatewayError> {
         while let Some(attempt) = self.candidates.next_attempt().await? {
             match self.build_sync_attempt(attempt).await? {

apps/aether-gateway/src/ai_serving/planner/specialized/video/support.rs

@@ -29,7 +29,6 @@ use crate::ai_serving::{
 };
 use crate::client_session_affinity::client_session_affinity_from_parts;
 use crate::clock::current_unix_secs;
-use crate::scheduler::config::SchedulerOrderingConfig;
 use crate::{AppState, GatewayError};
 
 pub(super) use crate::ai_serving::planner::candidate_materialization::LocalExecutionCandidateAttempt as LocalVideoCreateCandidateAttempt;
@@ -134,10 +133,9 @@ pub(super) async fn list_local_video_create_candidate_attempts(
             input.client_session_affinity.as_ref(),
             current_unix_secs(),
             false,
-            input
-                .routing_policy
-                .as_ref()
-                .map(SchedulerOrderingConfig::from_routing_policy),
+            crate::ai_serving::planner::candidate_ranking::scheduler_ordering_config_for_routing_policy(
+                input.routing_policy.as_ref(),
+            ),
         )
         .await
     {
@@ -195,10 +193,9 @@ pub(super) async fn build_local_video_create_candidate_attempt_source<'a>(
             input.client_session_affinity.as_ref(),
             current_unix_secs(),
             false,
-            input
-                .routing_policy
-                .as_ref()
-                .map(SchedulerOrderingConfig::from_routing_policy),
+            crate::ai_serving::planner::candidate_ranking::scheduler_ordering_config_for_routing_policy(
+                input.routing_policy.as_ref(),
+            ),
         )
         .await
     {

apps/aether-gateway/src/ai_serving/planner/standard/family/build.rs

@@ -18,6 +18,7 @@ use crate::ai_serving::planner::spec_metadata::{
 };
 use crate::ai_serving::GatewayControlDecision;
 use crate::{AiExecutionDecision, AppState, GatewayError};
+use aether_routing_core::RoutingExecutionPolicy;
 
 use super::candidates::{
     build_local_standard_candidate_attempt_source, resolve_local_standard_decision_input,
@@ -177,6 +178,13 @@ pub(crate) async fn build_local_stream_attempt_source<'a>(
 
 #[async_trait]
 impl LocalExecutionAttemptSource<AiSyncAttempt> for LocalStandardSyncAttemptSource<'_> {
+    fn routing_execution_policy(&self) -> Option<RoutingExecutionPolicy> {
+        self.input
+            .routing_policy
+            .as_ref()
+            .map(|policy| policy.execution_policy)
+    }
+
     async fn next_execution_attempt(&mut self) -> Result<Option<AiSyncAttempt>, GatewayError> {
         while let Some(attempt) = self.candidates.next_attempt().await? {
             match self.build_sync_attempt(attempt).await? {
@@ -220,6 +228,13 @@ impl LocalExecutionAttemptSource<AiSyncAttempt> for LocalStandardSyncAttemptSour
 
 #[async_trait]
 impl LocalExecutionAttemptSource<AiStreamAttempt> for LocalStandardStreamAttemptSource<'_> {
+    fn routing_execution_policy(&self) -> Option<RoutingExecutionPolicy> {
+        self.input
+            .routing_policy
+            .as_ref()
+            .map(|policy| policy.execution_policy)
+    }
+
     async fn next_execution_attempt(&mut self) -> Result<Option<AiStreamAttempt>, GatewayError> {
         while let Some(attempt) = self.candidates.next_attempt().await? {
             match self.build_stream_attempt(attempt).await? {

apps/aether-gateway/src/ai_serving/planner/standard/openai/chat/plans/stream.rs

@@ -1,3 +1,4 @@
+use aether_routing_core::RoutingExecutionPolicy;
 use async_trait::async_trait;
 use std::collections::VecDeque;
 use tracing::warn;
@@ -119,6 +120,13 @@ pub(crate) async fn build_local_openai_chat_stream_attempt_source<'a>(
 
 #[async_trait]
 impl LocalExecutionAttemptSource<AiStreamAttempt> for LocalOpenAiChatStreamAttemptSource<'_> {
+    fn routing_execution_policy(&self) -> Option<RoutingExecutionPolicy> {
+        self.input
+            .routing_policy
+            .as_ref()
+            .map(|policy| policy.execution_policy)
+    }
+
     async fn next_execution_attempt(&mut self) -> Result<Option<AiStreamAttempt>, GatewayError> {
         let select_started_at = std::time::Instant::now();
         let selected = self.next_execution_attempt_with_target_select().await?;

apps/aether-gateway/src/ai_serving/planner/standard/openai/chat/plans/sync.rs

@@ -1,3 +1,4 @@
+use aether_routing_core::RoutingExecutionPolicy;
 use async_trait::async_trait;
 use tracing::warn;
 
@@ -92,6 +93,13 @@ pub(crate) async fn build_local_openai_chat_sync_attempt_source<'a>(
 
 #[async_trait]
 impl LocalExecutionAttemptSource<AiSyncAttempt> for LocalOpenAiChatSyncAttemptSource<'_> {
+    fn routing_execution_policy(&self) -> Option<RoutingExecutionPolicy> {
+        self.input
+            .routing_policy
+            .as_ref()
+            .map(|policy| policy.execution_policy)
+    }
+
     async fn next_execution_attempt(&mut self) -> Result<Option<AiSyncAttempt>, GatewayError> {
         while let Some(attempt) = self.candidates.next_attempt().await? {
             match self.build_sync_attempt(attempt).await? {

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

@@ -1,3 +1,4 @@
+use aether_routing_core::RoutingExecutionPolicy;
 use async_trait::async_trait;
 use tracing::warn;
 
@@ -161,6 +162,13 @@ pub(super) async fn build_local_stream_attempt_source<'a>(
 
 #[async_trait]
 impl LocalExecutionAttemptSource<AiSyncAttempt> for LocalOpenAiResponsesSyncAttemptSource<'_> {
+    fn routing_execution_policy(&self) -> Option<RoutingExecutionPolicy> {
+        self.input
+            .routing_policy
+            .as_ref()
+            .map(|policy| policy.execution_policy)
+    }
+
     async fn next_execution_attempt(&mut self) -> Result<Option<AiSyncAttempt>, GatewayError> {
         while let Some(attempt) = self.candidates.next_attempt().await? {
             match self.build_sync_attempt(attempt).await? {
@@ -204,6 +212,13 @@ impl LocalExecutionAttemptSource<AiSyncAttempt> for LocalOpenAiResponsesSyncAtte
 
 #[async_trait]
 impl LocalExecutionAttemptSource<AiStreamAttempt> for LocalOpenAiResponsesStreamAttemptSource<'_> {
+    fn routing_execution_policy(&self) -> Option<RoutingExecutionPolicy> {
+        self.input
+            .routing_policy
+            .as_ref()
+            .map(|policy| policy.execution_policy)
+    }
+
     async fn next_execution_attempt(&mut self) -> Result<Option<AiStreamAttempt>, GatewayError> {
         while let Some(attempt) = self.candidates.next_attempt().await? {
             match self.build_stream_attempt(attempt).await? {

apps/aether-gateway/src/ai_serving/planner/state/scheduler.rs

@@ -12,9 +12,8 @@ use crate::scheduler::config::SchedulerOrderingConfig;
 use crate::GatewayError;
 
 impl<'a> PlannerAppState<'a> {
-    /// `ordering_config` is the request's routing-policy derived scheduler
-    /// config (see `SchedulerOrderingConfig::from_routing_policy`). `None`
-    /// falls back to the runtime default.
+    /// `ordering_config` is the immutable scheduler snapshot derived from the
+    /// request's resolved routing policy.
     #[allow(clippy::too_many_arguments)]
     pub(crate) async fn list_selectable_candidates(
         self,
@@ -26,7 +25,7 @@ impl<'a> PlannerAppState<'a> {
         client_session_affinity: Option<&ClientSessionAffinity>,
         now_unix_secs: u64,
         enable_model_directives: bool,
-        ordering_config: Option<SchedulerOrderingConfig>,
+        ordering_config: SchedulerOrderingConfig,
     ) -> Result<Vec<SchedulerMinimalCandidateSelectionCandidate>, GatewayError> {
         crate::scheduler::candidate::list_selectable_candidates(
             self.app().data.as_ref(),
@@ -55,7 +54,7 @@ impl<'a> PlannerAppState<'a> {
         client_session_affinity: Option<&ClientSessionAffinity>,
         now_unix_secs: u64,
         enable_model_directives: bool,
-        ordering_config: Option<SchedulerOrderingConfig>,
+        ordering_config: SchedulerOrderingConfig,
     ) -> Result<
         (
             Vec<SchedulerMinimalCandidateSelectionCandidate>,
@@ -90,7 +89,7 @@ impl<'a> PlannerAppState<'a> {
         now_unix_secs: u64,
         enable_model_directives: bool,
         request_operation: Option<&str>,
-        ordering_config: Option<SchedulerOrderingConfig>,
+        ordering_config: SchedulerOrderingConfig,
     ) -> Result<
         (
             Vec<SchedulerMinimalCandidateSelectionCandidate>,
@@ -146,7 +145,7 @@ impl<'a> PlannerAppState<'a> {
         auth_snapshot: Option<&GatewayAuthApiKeySnapshot>,
         client_session_affinity: Option<&ClientSessionAffinity>,
         now_unix_secs: u64,
-        ordering_config: Option<SchedulerOrderingConfig>,
+        ordering_config: SchedulerOrderingConfig,
     ) -> Result<
         (
             Vec<SchedulerMinimalCandidateSelectionCandidate>,
@@ -177,7 +176,7 @@ impl<'a> PlannerAppState<'a> {
         auth_snapshot: Option<&GatewayAuthApiKeySnapshot>,
         client_session_affinity: Option<&ClientSessionAffinity>,
         now_unix_secs: u64,
-        ordering_config: Option<SchedulerOrderingConfig>,
+        ordering_config: SchedulerOrderingConfig,
     ) -> Result<Vec<SchedulerMinimalCandidateSelectionCandidate>, GatewayError> {
         let wait_timeout = Duration::from_millis(API_KEY_CONCURRENCY_WAIT_TIMEOUT_MS);
         let wait_interval = Duration::from_millis(API_KEY_CONCURRENCY_WAIT_POLL_INTERVAL_MS.max(1));

apps/aether-gateway/src/dispatch/pool_scheduler.rs

@@ -5171,6 +5171,7 @@ mod tests {
             scheduling_mode: RoutingSchedulingMode::CacheAffinity,
             keep_priority_on_conversion: false,
             sticky_key_attempts: aether_routing_core::DEFAULT_STICKY_KEY_ATTEMPTS,
+            execution_policy: Default::default(),
             ranking_overlay: RankingOverlay {
                 allowed_keys: key_ids.into_iter().map(str::to_string).collect(),
                 ..RankingOverlay::default()

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

@@ -118,8 +118,7 @@ use crate::execution_runtime::{
 use crate::log_ids::short_request_id;
 use crate::orchestration::{
     apply_local_execution_effect, build_local_error_flow_metadata, classify_failure_disposition,
-    cyber_continue_failover_enabled, spawn_local_oauth_success_effect,
-    trace_upstream_response_body, with_error_flow_report_context,
+    spawn_local_oauth_success_effect, trace_upstream_response_body, with_error_flow_report_context,
     with_upstream_response_report_context, FailureDisposition, FailureTokenAction,
     LocalAdaptiveRateLimitEffect, LocalAdaptiveSuccessEffect, LocalAttemptFailureEffect,
     LocalExecutionEffect, LocalExecutionEffectContext, LocalFailoverAnalysis,
@@ -6173,7 +6172,10 @@ async fn execute_stream_from_frame_stream_with_retry_scope(
     }
     let prefetch_for_cyber_failover =
         is_openai_responses_family_format(plan.provider_api_format.as_str())
-            && cyber_continue_failover_enabled(state).await;
+            && crate::orchestration::routing_execution_policy_from_report_context(
+                report_context.as_ref(),
+            )
+            .is_some_and(|policy| policy.cyber_continue_failover);
     let stream_commit_policy = StreamCommitPolicy::for_response(
         direct_stream_finalize_kind.is_some(),
         upstream_content_type,
@@ -8501,14 +8503,6 @@ mod tests {
             Arc::new(provider_catalog),
             "development-key",
         );
-        let data_state = if continue_failover {
-            data_state.with_system_config_values_for_tests([(
-                crate::orchestration::CYBER_CONTINUE_FAILOVER_CONFIG_KEY.to_string(),
-                json!(true),
-            )])
-        } else {
-            data_state
-        };
         let state = AppState::new()
             .expect("app state should build")
             .with_data_state_for_tests(data_state);
@@ -8557,7 +8551,10 @@ mod tests {
                 "candidate_index": 0,
                 "retry_index": 0,
                 "provider_api_format": "openai:responses",
-                "client_api_format": "openai:responses"
+                "client_api_format": "openai:responses",
+                "routing_execution_policy": {
+                    "cyber_continue_failover": continue_failover
+                }
             })),
             crate::clock::current_unix_ms(),
             Instant::now(),
@@ -10515,7 +10512,7 @@ mod tests {
     }
 
     #[tokio::test]
-    async fn prefetched_codex_cyber_policy_violation_retries_when_system_setting_is_enabled() {
+    async fn prefetched_codex_cyber_policy_violation_retries_when_routing_strategy_is_enabled() {
         assert!(
             execute_prefetched_codex_cyber_policy_failure(true)
                 .await

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

@@ -54,13 +54,10 @@ use crate::executor::{
     record_failed_usage_for_exhausted_request, LocalExecutionExhaustion,
     LocalExecutionRequestOutcome,
 };
-use crate::handlers::shared::system_config_bool;
 use crate::request_diagnostics::{current_request_diagnostics, scope_request_diagnostics_with};
 use crate::stage_metrics::observe_gateway_stage_ms;
 use crate::{AiExecutionDecision, AppState, GatewayError};
 
-const ENABLE_OPENAI_IMAGE_SYNC_HEARTBEAT_CONFIG_KEY: &str = "enable_openai_image_sync_heartbeat";
-const ENABLE_STANDARD_TEXT_SYNC_HEARTBEAT_CONFIG_KEY: &str = "enable_standard_text_sync_heartbeat";
 const OPENAI_IMAGE_SYNC_HEARTBEAT_INTERNAL_ERROR_STATUS: u16 = 502;
 const OPENAI_IMAGE_SYNC_HEARTBEAT_EXHAUSTED_STATUS: u16 = 503;
 const OPENAI_IMAGE_SYNC_HEARTBEAT_ERROR_MESSAGE_LIMIT: usize = 4096;
@@ -107,7 +104,10 @@ pub(crate) async fn maybe_execute_sync_via_local_decision(
         return Ok(LocalExecutionRequestOutcome::NoPath);
     };
 
-    if standard_text_sync_heartbeat_should_wrap(state, plan_kind).await {
+    if standard_text_sync_heartbeat_should_wrap(
+        plan_kind,
+        attempt_source.routing_execution_policy(),
+    ) {
         let parts_for_task = parts.clone();
         let body_json_for_task = body_json.clone();
         let transfer_tracker_for_task = transfer_tracker.clone();
@@ -264,7 +264,10 @@ pub(crate) async fn maybe_execute_sync_via_local_openai_responses_decision(
         return Ok(LocalExecutionRequestOutcome::NoPath);
     };
 
-    if standard_text_sync_heartbeat_should_wrap(state, plan_kind).await {
+    if standard_text_sync_heartbeat_should_wrap(
+        plan_kind,
+        attempt_source.routing_execution_policy(),
+    ) {
         let parts_for_task = parts.clone();
         let body_json_for_task = body_json.clone();
         let transfer_tracker_for_task = transfer_tracker.clone();
@@ -381,7 +384,10 @@ pub(crate) async fn maybe_execute_sync_via_standard_family_decision(
         return Ok(LocalExecutionRequestOutcome::NoPath);
     };
 
-    if standard_text_sync_heartbeat_should_wrap(state, plan_kind).await {
+    if standard_text_sync_heartbeat_should_wrap(
+        plan_kind,
+        attempt_source.routing_execution_policy(),
+    ) {
         let parts_for_task = parts.clone();
         let body_json_for_task = body_json.clone();
         let transfer_tracker_for_task = transfer_tracker.clone();
@@ -609,7 +615,10 @@ pub(crate) async fn maybe_execute_sync_via_local_same_format_provider_decision(
         return Ok(LocalExecutionRequestOutcome::NoPath);
     };
 
-    if standard_text_sync_heartbeat_should_wrap(state, plan_kind).await {
+    if standard_text_sync_heartbeat_should_wrap(
+        plan_kind,
+        attempt_source.routing_execution_policy(),
+    ) {
         let parts_for_task = parts.clone();
         let body_json_for_task = body_json.clone();
         let transfer_tracker_for_task = transfer_tracker.clone();
@@ -746,42 +755,6 @@ pub(crate) async fn maybe_execute_sync_via_local_gemini_files_decision(
     .await
 }
 
-async fn openai_image_sync_heartbeat_enabled(state: &AppState) -> bool {
-    match state
-        .read_system_config_json_value(ENABLE_OPENAI_IMAGE_SYNC_HEARTBEAT_CONFIG_KEY)
-        .await
-    {
-        Ok(value) => system_config_bool(value.as_ref(), false),
-        Err(err) => {
-            tracing::warn!(
-                event_name = "openai_image_sync_heartbeat_config_read_failed",
-                log_type = "ops",
-                error = ?err,
-                "gateway failed to read sync image heartbeat config; defaulting disabled"
-            );
-            false
-        }
-    }
-}
-
-async fn standard_text_sync_heartbeat_enabled(state: &AppState) -> bool {
-    match state
-        .read_system_config_json_value(ENABLE_STANDARD_TEXT_SYNC_HEARTBEAT_CONFIG_KEY)
-        .await
-    {
-        Ok(value) => system_config_bool(value.as_ref(), false),
-        Err(err) => {
-            tracing::warn!(
-                event_name = "standard_text_sync_heartbeat_config_read_failed",
-                log_type = "ops",
-                error = ?err,
-                "gateway failed to read standard text sync heartbeat config; defaulting disabled"
-            );
-            false
-        }
-    }
-}
-
 fn standard_text_sync_heartbeat_applies_to_plan_kind(plan_kind: &str) -> bool {
     matches!(
         plan_kind,
@@ -795,9 +768,12 @@ fn standard_text_sync_heartbeat_applies_to_plan_kind(plan_kind: &str) -> bool {
     )
 }
 
-async fn standard_text_sync_heartbeat_should_wrap(state: &AppState, plan_kind: &str) -> bool {
+fn standard_text_sync_heartbeat_should_wrap(
+    plan_kind: &str,
+    execution_policy: Option<aether_routing_core::RoutingExecutionPolicy>,
+) -> bool {
     standard_text_sync_heartbeat_applies_to_plan_kind(plan_kind)
-        && standard_text_sync_heartbeat_enabled(state).await
+        && execution_policy.is_some_and(|policy| policy.enable_cf_heartbeat)
 }
 
 fn standard_text_sync_heartbeat_client_api_format_for_plan_kind(plan_kind: &str) -> &'static str {
@@ -1329,7 +1305,10 @@ pub(crate) async fn maybe_execute_sync_via_local_image_decision(
         return Ok(LocalExecutionRequestOutcome::NoPath);
     };
 
-    if openai_image_sync_heartbeat_enabled(state).await {
+    if attempt_source
+        .routing_execution_policy()
+        .is_some_and(|policy| policy.enable_cf_heartbeat)
+    {
         let mut attempts = Vec::new();
         while let Some(attempt) = attempt_source.next_execution_attempt().await? {
             attempts.push(attempt);
@@ -1867,11 +1846,10 @@ mod tests {
         assert_eq!(body, json!({"data": [{"b64_json": "x"}]}));
     }
 
-    #[tokio::test]
-    async fn openai_image_sync_heartbeat_missing_config_defaults_disabled() {
-        let state = AppState::new().expect("state should build");
-
-        assert!(!openai_image_sync_heartbeat_enabled(&state).await);
+    #[test]
+    fn openai_image_sync_heartbeat_missing_routing_policy_defaults_disabled() {
+        assert!(!Option::<aether_routing_core::RoutingExecutionPolicy>::None
+            .is_some_and(|policy| policy.enable_cf_heartbeat));
     }
 
     #[tokio::test]
@@ -2149,23 +2127,9 @@ mod tests {
         assert_eq!(body, json!({"data": [{"b64_json": "fallback-provider"}]}));
     }
 
-    #[tokio::test]
-    async fn standard_text_sync_heartbeat_missing_config_defaults_disabled() {
-        let state = AppState::new().expect("state should build");
-
-        assert!(!standard_text_sync_heartbeat_enabled(&state).await);
-    }
-
     #[tokio::test]
     async fn standard_text_sync_heartbeat_no_local_candidates_preserves_no_path() {
-        let state = AppState::new()
-            .expect("state should build")
-            .with_data_state_for_tests(
-                crate::data::GatewayDataState::disabled().with_system_config_values_for_tests([(
-                    ENABLE_STANDARD_TEXT_SYNC_HEARTBEAT_CONFIG_KEY.to_string(),
-                    json!(true),
-                )]),
-            );
+        let state = AppState::new().expect("state should build");
         let (parts, _) = http::Request::builder()
             .method(http::Method::POST)
             .uri("/v1/responses")

apps/aether-gateway/src/handlers/admin/model/routing.rs

@@ -67,11 +67,14 @@ pub(crate) async fn build_admin_global_model_routing_payload(
             .push(key);
     }
 
-    // Effective default scheduling: system-default routing group first, then
-    // legacy system-config keys.
-    let ordering_config = crate::scheduler::config::read_scheduler_ordering_config(state.app())
-        .await
-        .unwrap_or_default();
+    // The admin view reports the system-default routing strategy.
+    let ordering_config =
+        match crate::scheduler::config::read_system_default_routing_ordering_config(state.app())
+            .await
+        {
+            Ok(Some(config)) => config,
+            Ok(None) | Err(_) => crate::scheduler::config::SchedulerOrderingConfig::default(),
+        };
     let scheduling_mode = ordering_config.scheduling_mode_str().to_string();
     let priority_mode = ordering_config.priority_mode_str().to_string();
     let keep_priority_on_conversion = ordering_config.keep_priority_on_conversion;

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

@@ -265,7 +265,9 @@ pub(super) async fn build_admin_monitoring_cache_snapshot(
     state: &AdminAppState<'_>,
 ) -> Result<AdminMonitoringCacheSnapshot, GatewayError> {
     let ordering_config =
-        crate::scheduler::config::read_scheduler_ordering_config(state.app()).await?;
+        crate::scheduler::config::read_system_default_routing_ordering_config(state.app())
+            .await?
+            .unwrap_or_default();
     let scheduling_mode = ordering_config.scheduling_mode_str().to_string();
     let provider_priority_mode = ordering_config.priority_mode_str().to_string();
 

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

@@ -44,6 +44,8 @@ struct AdminRoutingGroupCreateRequest {
     #[serde(default)]
     is_system_default: bool,
     #[serde(default)]
+    sort_order: i64,
+    #[serde(default)]
     config_json: Option<Value>,
 }
 
@@ -137,6 +139,7 @@ async fn maybe_build_routing_groups_response(
                 description: payload.description,
                 enabled: payload.enabled,
                 is_system_default: payload.is_system_default,
+                sort_order: payload.sort_order,
                 config_json,
                 version: 1,
                 created_at: now,
@@ -464,6 +467,9 @@ fn build_routing_group_update_patch(
     if let Some(value) = object.get("is_system_default") {
         patch.is_system_default = Some(required_bool(value, "is_system_default")?);
     }
+    if let Some(value) = object.get("sort_order") {
+        patch.sort_order = Some(required_i64(value, "sort_order")?.max(0));
+    }
     if let Some(value) = object.get("config_json") {
         validate_config_json(value)?;
         patch.config_json = Some(value.clone());
@@ -604,6 +610,7 @@ fn routing_group_payload(group: &StoredRoutingGroup) -> Value {
         "description": group.description,
         "enabled": group.enabled,
         "is_system_default": group.is_system_default,
+        "sort_order": group.sort_order,
         "config_json": group.config_json,
         "version": group.version,
         "created_at": group.created_at,

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

@@ -68,7 +68,6 @@ use crate::scheduler::candidate::{
     is_auth_api_key_concurrency_limit_skip_reason, AUTH_API_KEY_CONCURRENCY_LIMIT_SKIP_REASON,
     LEGACY_API_KEY_CONCURRENCY_LIMIT_SKIP_REASON,
 };
-use crate::scheduler::config::{read_scheduler_ordering_config, SchedulerSchedulingMode};
 use crate::stage_metrics::observe_gateway_stage_ms;
 use crate::{
     AppState, FrontdoorUserRpmOutcome, GatewayError, GatewayFallbackMetricKind,
@@ -411,27 +410,7 @@ async fn maybe_forward_public_request_to_tunnel_owner(
             policy_context,
         )
     } else {
-        let cache_affinity_enabled = match read_scheduler_ordering_config(state).await {
-            Ok(config) => config.scheduling_mode == SchedulerSchedulingMode::CacheAffinity,
-            Err(err) => {
-                warn!(
-                    trace_id = %request_context.trace_id,
-                    error = ?err,
-                    "gateway failed to load scheduler config while checking tunnel affinity forwarding mode"
-                );
-                SchedulerSchedulingMode::default() == SchedulerSchedulingMode::CacheAffinity
-            }
-        };
-        if !cache_affinity_enabled {
-            return Ok(None);
-        }
-        crate::scheduler::affinity::read_cached_scheduler_affinity_target(
-            state,
-            &auth_context.api_key_id,
-            affinity_context.client_session_affinity.as_ref(),
-            api_format,
-            &affinity_context.requested_model,
-        )
+        return Ok(None);
     };
     let Some(target) = target else {
         return Ok(None);

apps/aether-gateway/src/main.rs

@@ -76,6 +76,29 @@ enum DatabaseDriverArg {
     Postgres,
 }
 
+#[derive(Copy, Clone, Debug, Eq, PartialEq, ValueEnum)]
+enum DatabaseModeArg {
+    Auto,
+    VerifyOnly,
+}
+
+fn resolve_database_mode(
+    configured: Option<DatabaseModeArg>,
+    legacy_auto_prepare: Option<bool>,
+) -> DatabaseModeArg {
+    if let Some(configured) = configured {
+        return configured;
+    }
+    if let Some(legacy_auto_prepare) = legacy_auto_prepare {
+        return if legacy_auto_prepare {
+            DatabaseModeArg::Auto
+        } else {
+            DatabaseModeArg::VerifyOnly
+        };
+    }
+    DatabaseModeArg::Auto
+}
+
 #[derive(Copy, Clone, Debug, Eq, PartialEq, ValueEnum)]
 enum ExportDomainArg {
     Users,
@@ -538,46 +561,71 @@ fn automatic_sql_pool_config_for_parallelism(
 
 #[derive(ClapArgs, Debug, Clone)]
 struct GatewayDataArgs {
-    #[arg(long, env = "AETHER_DATABASE_DRIVER")]
+    #[arg(long, env = "AETHER_DATABASE_DRIVER", global = true)]
     database_driver: Option<DatabaseDriverArg>,
 
-    #[arg(long, env = "AETHER_DATABASE_URL")]
+    #[arg(long, env = "AETHER_DATABASE_URL", global = true)]
     database_url: Option<String>,
 
-    #[arg(long, env = "AETHER_GATEWAY_DATA_POSTGRES_URL")]
+    #[arg(long, env = "AETHER_GATEWAY_DATA_POSTGRES_URL", global = true)]
     postgres_url: Option<String>,
 
-    #[arg(long, env = "AETHER_GATEWAY_DATA_ENCRYPTION_KEY")]
+    #[arg(long, env = "AETHER_GATEWAY_DATA_ENCRYPTION_KEY", global = true)]
     encryption_key: Option<String>,
 
-    #[arg(long, env = "AETHER_GATEWAY_DATA_REDIS_URL")]
+    #[arg(long, env = "AETHER_GATEWAY_DATA_REDIS_URL", global = true)]
     redis_url: Option<String>,
 
-    #[arg(long, env = "AETHER_GATEWAY_DATA_REDIS_KEY_PREFIX")]
+    #[arg(long, env = "AETHER_GATEWAY_DATA_REDIS_KEY_PREFIX", global = true)]
     redis_key_prefix: Option<String>,
 
-    #[arg(long, env = "AETHER_GATEWAY_DATA_POSTGRES_MIN_CONNECTIONS")]
+    #[arg(
+        long,
+        env = "AETHER_GATEWAY_DATA_POSTGRES_MIN_CONNECTIONS",
+        global = true
+    )]
     postgres_min_connections: Option<u32>,
 
-    #[arg(long, env = "AETHER_GATEWAY_DATA_POSTGRES_MAX_CONNECTIONS")]
+    #[arg(
+        long,
+        env = "AETHER_GATEWAY_DATA_POSTGRES_MAX_CONNECTIONS",
+        global = true
+    )]
     postgres_max_connections: Option<u32>,
 
-    #[arg(long, env = "AETHER_GATEWAY_DATA_POSTGRES_ACQUIRE_TIMEOUT_MS")]
+    #[arg(
+        long,
+        env = "AETHER_GATEWAY_DATA_POSTGRES_ACQUIRE_TIMEOUT_MS",
+        global = true
+    )]
     postgres_acquire_timeout_ms: Option<u64>,
 
-    #[arg(long, env = "AETHER_GATEWAY_DATA_POSTGRES_IDLE_TIMEOUT_MS")]
+    #[arg(
+        long,
+        env = "AETHER_GATEWAY_DATA_POSTGRES_IDLE_TIMEOUT_MS",
+        global = true
+    )]
     postgres_idle_timeout_ms: Option<u64>,
 
-    #[arg(long, env = "AETHER_GATEWAY_DATA_POSTGRES_MAX_LIFETIME_MS")]
+    #[arg(
+        long,
+        env = "AETHER_GATEWAY_DATA_POSTGRES_MAX_LIFETIME_MS",
+        global = true
+    )]
     postgres_max_lifetime_ms: Option<u64>,
 
-    #[arg(long, env = "AETHER_GATEWAY_DATA_POSTGRES_STATEMENT_CACHE_CAPACITY")]
+    #[arg(
+        long,
+        env = "AETHER_GATEWAY_DATA_POSTGRES_STATEMENT_CACHE_CAPACITY",
+        global = true
+    )]
     postgres_statement_cache_capacity: Option<usize>,
 
     #[arg(
         long,
         env = "AETHER_GATEWAY_DATA_POSTGRES_REQUIRE_SSL",
-        default_value_t = false
+        default_value_t = false,
+        global = true
     )]
     postgres_require_ssl: bool,
 }
@@ -1144,13 +1192,26 @@ enum DataCommand {
     Import(DataImportArgs),
     /// Copy persistent SQL data directly between two databases without a JSONL file.
     Copy(DataCopyArgs),
+    /// Inspect or prepare the configured database.
+    Db(DatabaseCommandArgs),
+}
+
+#[derive(ClapArgs, Debug, Clone)]
+struct DatabaseCommandArgs {
+    #[command(subcommand)]
+    command: DatabaseCommand,
+}
+
+#[derive(Subcommand, Debug, Clone)]
+enum DatabaseCommand {
+    /// Show whether schema migrations and data backfills are current.
+    Status,
+    /// Apply pending schema migrations and data backfills.
+    Prepare,
 }
 
 #[derive(ClapArgs, Debug, Clone)]
 struct DataExportArgs {
-    #[command(flatten)]
-    data: GatewayDataArgs,
-
     #[arg(long)]
     output: PathBuf,
 
@@ -1160,9 +1221,6 @@ struct DataExportArgs {
 
 #[derive(ClapArgs, Debug, Clone)]
 struct DataImportArgs {
-    #[command(flatten)]
-    data: GatewayDataArgs,
-
     #[arg(long)]
     input: PathBuf,
 }
@@ -1284,18 +1342,25 @@ struct Args {
     )]
     node_role: NodeRoleArg,
 
-    #[arg(long, default_value_t = false)]
+    #[arg(long, hide = true, default_value_t = false)]
     migrate: bool,
 
-    #[arg(long, default_value_t = false)]
+    #[arg(long, hide = true, default_value_t = false)]
     apply_backfills: bool,
 
+    /// Database startup policy. Defaults to auto when neither this nor the legacy setting is set.
+    #[arg(long, env = "AETHER_GATEWAY_DATABASE_MODE", value_enum)]
+    database_mode: Option<DatabaseModeArg>,
+
+    /// Legacy compatibility switch. Prefer --database-mode.
     #[arg(
         long,
         env = "AETHER_GATEWAY_AUTO_PREPARE_DATABASE",
-        default_value_t = false
+        hide = true,
+        num_args = 0..=1,
+        default_missing_value = "true"
     )]
-    auto_prepare_database: bool,
+    auto_prepare_database: Option<bool>,
 
     /// Path to frontend static files directory (SPA). When set, the gateway
     /// serves the frontend directly without nginx.
@@ -1405,6 +1470,10 @@ struct Args {
 }
 
 impl Args {
+    fn effective_database_mode(&self) -> DatabaseModeArg {
+        resolve_database_mode(self.database_mode, self.auto_prepare_database)
+    }
+
     fn effective_runtime_backend(
         &self,
         database: Option<&SqlDatabaseConfig>,
@@ -1475,15 +1544,7 @@ impl Args {
     }
 
     fn runtime_config(&self) -> Result<ServiceRuntimeConfig, std::io::Error> {
-        let default_log_filter = if self.command.is_some()
-            || self.migrate
-            || self.apply_backfills
-            || self.auto_prepare_database
-        {
-            "aether_gateway=info,aether_data=info"
-        } else {
-            "aether_gateway=info"
-        };
+        let default_log_filter = "aether_gateway=info,aether_data=info";
         let config = self
             .logging
             .apply_to_runtime_config(ServiceRuntimeConfig::new(
@@ -1786,7 +1847,7 @@ async fn run() -> Result<(), Box<dyn std::error::Error>> {
     let args = Args::parse();
     if let Some(command) = args.command.as_ref() {
         init_service_runtime(args.runtime_config()?)?;
-        return run_data_command(command).await;
+        return run_data_command(command, &args.data).await;
     }
     if args.migrate {
         init_service_runtime(args.runtime_config()?)?;
@@ -2086,7 +2147,7 @@ async fn run() -> Result<(), Box<dyn std::error::Error>> {
         execution_runtime_configured = state.execution_runtime_configured(),
         "aether-gateway data layer configured"
     );
-    prepare_database_startup_requirements(&state, args.auto_prepare_database).await?;
+    prepare_database_startup_requirements(&state, args.effective_database_mode()).await?;
     state.warm_database_pools().await?;
     let reset_stale_proxy_nodes = state.reset_stale_proxy_node_tunnel_statuses().await?;
     if reset_stale_proxy_nodes > 0 {
@@ -2101,16 +2162,11 @@ async fn run() -> Result<(), Box<dyn std::error::Error>> {
             info!(
                 group_id = %group.id,
                 group_name = %group.name,
-                "created system default routing group from legacy scheduler config"
+                "created system default routing group from routing strategy defaults"
             );
         }
         Ok(None) => {}
-        Err(err) => {
-            warn!(
-                error = %err,
-                "failed to bootstrap system default routing group; scheduler falls back to legacy system config"
-            );
-        }
+        Err(err) => return Err(err.into()),
     }
     match state.prewarm_chat_pii_redaction_runtime_config().await {
         Ok(enabled) => {
@@ -2208,14 +2264,77 @@ async fn run() -> Result<(), Box<dyn std::error::Error>> {
     Ok(())
 }
 
-async fn run_data_command(command: &DataCommand) -> Result<(), Box<dyn std::error::Error>> {
+async fn run_data_command(
+    command: &DataCommand,
+    data: &GatewayDataArgs,
+) -> Result<(), Box<dyn std::error::Error>> {
     match command {
-        DataCommand::Export(args) => run_data_export(args).await,
-        DataCommand::Import(args) => run_data_import(args).await,
+        DataCommand::Export(args) => run_data_export(args, data).await,
+        DataCommand::Import(args) => run_data_import(args, data).await,
         DataCommand::Copy(args) => run_data_copy(args).await,
+        DataCommand::Db(args) => run_database_command(args, data).await,
     }
 }
 
+async fn run_database_command(
+    args: &DatabaseCommandArgs,
+    data: &GatewayDataArgs,
+) -> Result<(), Box<dyn std::error::Error>> {
+    match args.command {
+        DatabaseCommand::Status => run_database_status(data).await,
+        DatabaseCommand::Prepare => run_database_prepare(data).await,
+    }
+}
+
+fn database_maintenance_state(
+    data: &GatewayDataArgs,
+) -> Result<(DatabaseDriver, AppState), Box<dyn std::error::Error>> {
+    let database = required_sql_database_config(data)?;
+    let driver = database.driver;
+    let state = AppState::new()?.with_data_config(data.to_config())?;
+    Ok((driver, state))
+}
+
+async fn run_database_status(data: &GatewayDataArgs) -> Result<(), Box<dyn std::error::Error>> {
+    let (driver, state) = database_maintenance_state(data)?;
+    let pending_migrations = state
+        .pending_database_migrations()
+        .await?
+        .unwrap_or_default();
+
+    if let Some(next) = pending_migrations.first() {
+        println!("database {driver}: preparation required");
+        println!("pending migrations: {}", pending_migrations.len());
+        println!("next migration: {} ({})", next.version, next.description);
+        println!("pending backfills: not checked until migrations are current");
+        println!("run `aether-gateway db prepare`");
+        return Ok(());
+    }
+
+    let pending_backfills = state
+        .pending_database_backfills()
+        .await?
+        .unwrap_or_default();
+    if let Some(next) = pending_backfills.first() {
+        println!("database {driver}: preparation required");
+        println!("pending migrations: 0");
+        println!("pending backfills: {}", pending_backfills.len());
+        println!("next backfill: {} ({})", next.version, next.description);
+        println!("run `aether-gateway db prepare`");
+        return Ok(());
+    }
+
+    println!("database {driver}: ready (schema and backfills are current)");
+    Ok(())
+}
+
+async fn run_database_prepare(data: &GatewayDataArgs) -> Result<(), Box<dyn std::error::Error>> {
+    let (driver, state) = database_maintenance_state(data)?;
+    prepare_database_startup_requirements(&state, DatabaseModeArg::Auto).await?;
+    println!("database {driver}: ready (schema and backfills are current)");
+    Ok(())
+}
+
 fn required_sql_database_config(
     data: &GatewayDataArgs,
 ) -> Result<SqlDatabaseConfig, Box<dyn std::error::Error>> {
@@ -2242,8 +2361,11 @@ fn current_unix_secs() -> Result<u64, std::time::SystemTimeError> {
         .as_secs())
 }
 
-async fn run_data_export(args: &DataExportArgs) -> Result<(), Box<dyn std::error::Error>> {
-    let database = required_sql_database_config(&args.data)?;
+async fn run_data_export(
+    args: &DataExportArgs,
+    data: &GatewayDataArgs,
+) -> Result<(), Box<dyn std::error::Error>> {
+    let database = required_sql_database_config(data)?;
     let driver = database.driver;
     let domains = requested_export_domains(args);
     let created_at_unix_secs = current_unix_secs()?;
@@ -2265,8 +2387,11 @@ async fn run_data_export(args: &DataExportArgs) -> Result<(), Box<dyn std::error
     Ok(())
 }
 
-async fn run_data_import(args: &DataImportArgs) -> Result<(), Box<dyn std::error::Error>> {
-    let database = required_sql_database_config(&args.data)?;
+async fn run_data_import(
+    args: &DataImportArgs,
+    data: &GatewayDataArgs,
+) -> Result<(), Box<dyn std::error::Error>> {
+    let database = required_sql_database_config(data)?;
     let driver = database.driver;
     let input = tokio::fs::read_to_string(&args.input).await?;
     let imported = import_database_jsonl(database, &input).await?;
@@ -2426,17 +2551,15 @@ async fn run_explicit_backfills(args: &Args) -> Result<(), Box<dyn std::error::E
 
 async fn prepare_database_startup_requirements(
     state: &AppState,
-    auto_prepare_database: bool,
+    database_mode: DatabaseModeArg,
 ) -> Result<(), Box<dyn std::error::Error>> {
-    if !auto_prepare_database {
+    if matches!(database_mode, DatabaseModeArg::VerifyOnly) {
         ensure_database_schema_is_current(state).await?;
         ensure_database_backfills_are_current(state).await?;
         return Ok(());
     }
 
-    info!(
-        "auto database preparation enabled; applying pending migrations and backfills before serving traffic"
-    );
+    info!("database preparation enabled; applying pending migrations and backfills");
 
     let Some(pending_migrations) = state.prepare_database_for_startup().await? else {
         return Ok(());
@@ -2450,10 +2573,10 @@ async fn prepare_database_startup_requirements(
             next_version = next.version,
             next_description = %next.description,
             pending_versions = %format_pending_migrations(&pending_migrations),
-            "running database migrations during service startup..."
+            "running database migrations during database preparation..."
         );
         if state.run_database_migrations().await? {
-            info!("database migrations complete during service startup");
+            info!("database migrations complete");
         }
     }
 
@@ -2472,10 +2595,10 @@ async fn prepare_database_startup_requirements(
         next_version = next.version,
         next_description = %next.description,
         pending_versions = %format_pending_backfills(&pending_backfills),
-        "running database backfills during service startup..."
+        "running database backfills during database preparation..."
     );
     if state.run_database_backfills().await? {
-        info!("database backfills complete during service startup");
+        info!("database backfills complete");
     }
 
     Ok(())
@@ -2520,7 +2643,7 @@ async fn ensure_database_backfills_are_current(
 async fn ensure_database_schema_is_current(
     state: &AppState,
 ) -> Result<(), Box<dyn std::error::Error>> {
-    let Some(pending) = state.prepare_database_for_startup().await? else {
+    let Some(pending) = state.pending_database_migrations().await? else {
         return Ok(());
     };
     if pending.is_empty() {
@@ -2539,7 +2662,7 @@ fn pending_schema_error(
     next_description: &str,
 ) -> std::io::Error {
     std::io::Error::other(format!(
-        "database schema is behind by {} migration(s); next pending migration is {} ({})\nrun `aether-gateway --migrate` before starting the service",
+        "database schema is behind by {} migration(s); next pending migration is {} ({})\nrun `aether-gateway db prepare` before starting the service",
         pending_count, next_version, next_description
     ))
 }
@@ -2550,7 +2673,7 @@ fn pending_backfills_error(
     next_description: &str,
 ) -> std::io::Error {
     std::io::Error::other(format!(
-        "database backfills are behind by {} backfill(s); next pending backfill is {} ({})\nrun `aether-gateway --apply-backfills` before starting the service",
+        "database backfills are behind by {} backfill(s); next pending backfill is {} ({})\nrun `aether-gateway db prepare` before starting the service",
         pending_count, next_version, next_description
     ))
 }
@@ -2562,8 +2685,9 @@ mod tests {
         automatic_gateway_request_concurrency_for_parallelism, automatic_sql_pool_config,
         automatic_sql_pool_config_for_parallelism, automatic_usage_queue_workers_for_parallelism,
         ensure_database_backfills_are_current, ensure_database_schema_is_current,
-        pending_backfills_error, pending_schema_error, resolve_healthcheck_url,
-        usage_database_config_for_role, Args, DatabaseDriverArg, DeploymentTopologyArg,
+        pending_backfills_error, pending_schema_error, resolve_database_mode,
+        resolve_healthcheck_url, usage_database_config_for_role, Args, DataCommand,
+        DatabaseCommand, DatabaseDriverArg, DatabaseModeArg, DeploymentTopologyArg,
         GatewayDataArgs, GatewayFrontdoorArgs, GatewayLogDestinationArg, GatewayLogFormatArg,
         GatewayLogRotationArg, GatewayLoggingArgs, GatewayRateLimitArgs, GatewayUsageArgs,
         NodeRoleArg, RuntimeBackendArg, VideoTaskTruthSourceArg,
@@ -2574,6 +2698,7 @@ mod tests {
     };
     use aether_data::{DatabaseDriver, SqlDatabaseConfig, SqlPoolConfig};
     use aether_gateway::AppState;
+    use clap::Parser;
 
     fn test_args() -> Args {
         Args {
@@ -2588,7 +2713,8 @@ mod tests {
             node_role: NodeRoleArg::All,
             migrate: false,
             apply_backfills: false,
-            auto_prepare_database: false,
+            database_mode: None,
+            auto_prepare_database: None,
             static_dir: None,
             video_task_truth_source_mode: VideoTaskTruthSourceArg::PythonSyncReport,
             video_task_poller_interval_ms: 5_000,
@@ -2690,6 +2816,19 @@ mod tests {
         .expect("test database config should build")
     }
 
+    fn temporary_sqlite_args(label: &str) -> (Args, std::path::PathBuf) {
+        let mut args = test_args();
+        let nonce = std::time::SystemTime::now()
+            .duration_since(std::time::UNIX_EPOCH)
+            .expect("clock should be available")
+            .as_nanos();
+        let database_path =
+            std::env::temp_dir().join(format!("aether-{label}-{}-{nonce}.db", std::process::id()));
+        args.data.database_driver = Some(DatabaseDriverArg::Sqlite);
+        args.data.database_url = Some(format!("sqlite://{}", database_path.display()));
+        (args, database_path)
+    }
+
     #[test]
     fn resolves_healthcheck_url_from_app_port() {
         assert_eq!(
@@ -2801,11 +2940,14 @@ mod tests {
     }
 
     #[test]
-    fn normal_runtime_config_keeps_gateway_only_logs() {
+    fn normal_runtime_config_includes_database_lifecycle_logs() {
         let config = test_args()
             .runtime_config()
             .expect("runtime config should build");
-        assert_eq!(config.default_log_filter, "aether_gateway=info");
+        assert_eq!(
+            config.default_log_filter,
+            "aether_gateway=info,aether_data=info"
+        );
     }
 
     #[test]
@@ -2822,7 +2964,7 @@ mod tests {
     #[test]
     fn auto_prepare_database_runtime_config_enables_data_logs() {
         let mut args = test_args();
-        args.auto_prepare_database = true;
+        args.auto_prepare_database = Some(true);
         let config = args.runtime_config().expect("runtime config should build");
         assert_eq!(
             config.default_log_filter,
@@ -2830,6 +2972,87 @@ mod tests {
         );
     }
 
+    #[test]
+    fn database_mode_defaults_to_auto_and_preserves_legacy_false() {
+        assert_eq!(resolve_database_mode(None, None), DatabaseModeArg::Auto);
+        assert_eq!(
+            resolve_database_mode(None, Some(false)),
+            DatabaseModeArg::VerifyOnly
+        );
+        assert_eq!(
+            resolve_database_mode(Some(DatabaseModeArg::Auto), Some(false)),
+            DatabaseModeArg::Auto
+        );
+    }
+
+    #[test]
+    fn parses_database_commands_and_verify_only_mode() {
+        let status = Args::try_parse_from(["aether-gateway", "db", "status"])
+            .expect("db status should parse");
+        assert!(matches!(
+            status.command,
+            Some(DataCommand::Db(args))
+                if matches!(args.command, DatabaseCommand::Status)
+        ));
+
+        let verify_only =
+            Args::try_parse_from(["aether-gateway", "--database-mode", "verify-only"])
+                .expect("verify-only mode should parse");
+        assert_eq!(
+            verify_only.effective_database_mode(),
+            DatabaseModeArg::VerifyOnly
+        );
+
+        let legacy_false =
+            Args::try_parse_from(["aether-gateway", "--auto-prepare-database=false"])
+                .expect("legacy false setting should parse");
+        assert_eq!(
+            legacy_false.effective_database_mode(),
+            DatabaseModeArg::VerifyOnly
+        );
+
+        let prepare = Args::try_parse_from(["aether-gateway", "db", "prepare"])
+            .expect("db prepare should parse");
+        assert!(matches!(
+            prepare.command,
+            Some(DataCommand::Db(args))
+                if matches!(args.command, DatabaseCommand::Prepare)
+        ));
+    }
+
+    #[test]
+    fn database_arguments_are_global_for_database_commands() {
+        let before = Args::try_parse_from([
+            "aether-gateway",
+            "--database-driver",
+            "sqlite",
+            "--database-url",
+            "sqlite:///tmp/before.db",
+            "db",
+            "status",
+        ])
+        .expect("database arguments before db should parse");
+        assert_eq!(
+            before.data.database_url.as_deref(),
+            Some("sqlite:///tmp/before.db")
+        );
+
+        let after = Args::try_parse_from([
+            "aether-gateway",
+            "db",
+            "prepare",
+            "--database-driver",
+            "sqlite",
+            "--database-url",
+            "sqlite:///tmp/after.db",
+        ])
+        .expect("database arguments after db prepare should parse");
+        assert_eq!(
+            after.data.database_url.as_deref(),
+            Some("sqlite:///tmp/after.db")
+        );
+    }
+
     #[test]
     fn gateway_data_pool_auto_sizes_sqlite_to_single_connection() {
         let mut args = test_args();
@@ -3500,17 +3723,17 @@ mod tests {
     }
 
     #[test]
-    fn pending_schema_error_mentions_explicit_migrate_command() {
+    fn pending_schema_error_mentions_database_prepare_command() {
         let error = pending_schema_error(2, 20260413020000, "squash usage schema split");
         let message = error.to_string();
         assert!(message.contains("database schema is behind by 2 migration(s)"));
         assert!(message.contains("20260413020000"));
         assert!(message.contains("squash usage schema split"));
-        assert!(message.contains("aether-gateway --migrate"));
+        assert!(message.contains("aether-gateway db prepare"));
     }
 
     #[test]
-    fn pending_backfills_error_mentions_explicit_apply_backfills_command() {
+    fn pending_backfills_error_mentions_database_prepare_command() {
         let message = pending_backfills_error(
             1,
             20260422110000,
@@ -3520,7 +3743,7 @@ mod tests {
         assert!(message.contains("database backfills are behind by 1 backfill(s)"));
         assert!(message.contains("20260422110000"));
         assert!(message.contains("backfill stats aggregate read path support"));
-        assert!(message.contains("aether-gateway --apply-backfills"));
+        assert!(message.contains("aether-gateway db prepare"));
         assert!(message.contains("before starting the service"));
     }
 
@@ -3543,11 +3766,79 @@ mod tests {
     #[tokio::test]
     async fn auto_prepare_database_is_noop_without_database_pool() {
         let state = AppState::new().expect("state should build");
-        super::prepare_database_startup_requirements(&state, true)
+        super::prepare_database_startup_requirements(&state, DatabaseModeArg::Auto)
             .await
             .expect("disabled data backend should not block startup");
     }
 
+    #[tokio::test]
+    async fn verify_only_does_not_prepare_fresh_sqlite_database() {
+        let (args, database_path) = temporary_sqlite_args("verify-only");
+        let state = AppState::new()
+            .expect("state should build")
+            .with_data_config(args.data.to_config())
+            .expect("sqlite state should build");
+        let pending_before = state
+            .pending_database_migrations()
+            .await
+            .expect("pending migrations should load")
+            .expect("sqlite should expose migration state");
+        assert!(!pending_before.is_empty());
+
+        let error =
+            super::prepare_database_startup_requirements(&state, DatabaseModeArg::VerifyOnly)
+                .await
+                .expect_err("verify-only should reject a fresh database");
+        assert!(error.to_string().contains("aether-gateway db prepare"));
+
+        let pending_after = state
+            .pending_database_migrations()
+            .await
+            .expect("pending migrations should reload")
+            .expect("sqlite should expose migration state");
+        assert_eq!(pending_after, pending_before);
+        drop(state);
+        let _ = std::fs::remove_file(database_path);
+    }
+
+    #[tokio::test]
+    async fn auto_mode_prepares_fresh_sqlite_database() {
+        let (args, database_path) = temporary_sqlite_args("auto-prepare");
+        let state = AppState::new()
+            .expect("state should build")
+            .with_data_config(args.data.to_config())
+            .expect("sqlite state should build");
+
+        super::prepare_database_startup_requirements(&state, DatabaseModeArg::Auto)
+            .await
+            .expect("auto mode should prepare a fresh database");
+        assert!(state
+            .pending_database_migrations()
+            .await
+            .expect("pending migrations should load")
+            .expect("sqlite should expose migration state")
+            .is_empty());
+        assert!(state
+            .pending_database_backfills()
+            .await
+            .expect("pending backfills should load")
+            .expect("sqlite should expose backfill state")
+            .is_empty());
+        drop(state);
+        let _ = std::fs::remove_file(database_path);
+    }
+
+    #[tokio::test]
+    async fn database_prepare_requires_database_url() {
+        let data = test_args().data;
+        let error = super::run_database_prepare(&data)
+            .await
+            .expect_err("missing database URL should fail");
+        assert!(error
+            .to_string()
+            .contains("AETHER_DATABASE_DRIVER/AETHER_DATABASE_URL"));
+    }
+
     #[tokio::test]
     async fn explicit_migrate_requires_database_url() {
         let args = test_args();

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

@@ -53,7 +53,6 @@ use crate::scheduler::affinity::{
     scheduler_affinity_policy_context_from_report_context, SCHEDULER_AFFINITY_POLICY_REPORT_FIELD,
     SCHEDULER_AFFINITY_TTL,
 };
-use crate::scheduler::config::{read_scheduler_ordering_config, SchedulerSchedulingMode};
 use crate::AppState;
 
 const POOL_SCORE_FEEDBACK_GATE_MAX_ENTRIES: usize = 50_000;
@@ -763,36 +762,19 @@ async fn local_scheduler_affinity_matches_failed_target(
     local_execution_plan_uses_pool(state, plan).await
 }
 
-async fn scheduler_cache_affinity_enabled(
-    state: &AppState,
-    report_context: Option<&Value>,
-) -> bool {
-    if report_context
+fn scheduler_cache_affinity_enabled(report_context: Option<&Value>) -> bool {
+    report_context
         .and_then(|context| context.get(SCHEDULER_AFFINITY_POLICY_REPORT_FIELD))
         .is_some()
-    {
-        return scheduler_affinity_policy_context_from_report_context(report_context)
-            .is_some_and(|context| context.cache_affinity_enabled());
-    }
-    match read_scheduler_ordering_config(state).await {
-        Ok(config) => config.scheduling_mode == SchedulerSchedulingMode::CacheAffinity,
-        Err(error) => {
-            warn!(
-                event_name = "orchestration_scheduler_affinity_config_load_failed",
-                log_type = "event",
-                error = ?error,
-                "failed to load scheduler config while checking cache affinity mode"
-            );
-            SchedulerSchedulingMode::default() == SchedulerSchedulingMode::CacheAffinity
-        }
-    }
+        && scheduler_affinity_policy_context_from_report_context(report_context)
+            .is_some_and(|context| context.cache_affinity_enabled())
 }
 
 async fn remember_successful_local_scheduler_affinity(
     state: &AppState,
     context: LocalExecutionEffectContext<'_>,
 ) {
-    if !scheduler_cache_affinity_enabled(state, context.report_context).await {
+    if !scheduler_cache_affinity_enabled(context.report_context) {
         return;
     }
     let Some(cache_key) = local_scheduler_affinity_cache_key(context.report_context) else {

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

@@ -56,10 +56,11 @@ pub(crate) use self::oauth_error::{
 };
 pub(crate) use self::policy::{
     append_local_failover_policy_to_value, codex_cyber_flag_passthrough_enabled,
-    cyber_continue_failover_enabled, local_failover_policy_from_report_context,
-    local_failover_policy_from_transport, resolve_local_failover_policy,
-    responses_websocket_adapter, LocalFailoverPolicy, LocalFailoverRegexRule,
-    ResponsesWebSocketAdapter, CYBER_CONTINUE_FAILOVER_CONFIG_KEY, RESPONSES_WEBSOCKET_CONFIG_KEY,
+    local_failover_policy_from_report_context, local_failover_policy_from_transport,
+    resolve_local_failover_policy, responses_websocket_adapter,
+    routing_execution_policy_from_report_context, LocalFailoverPolicy, LocalFailoverRegexRule,
+    ResponsesWebSocketAdapter, RESPONSES_WEBSOCKET_CONFIG_KEY,
+    ROUTING_EXECUTION_POLICY_REPORT_FIELD,
 };
 pub(crate) use self::recovery::{
     analyze_local_failover, analyze_local_transport_error, apply_provider_failure_disposition,

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

@@ -4,11 +4,13 @@ use aether_contracts::ExecutionPlan;
 use serde_json::{json, Value};
 use tracing::debug;
 
+use aether_routing_core::RoutingExecutionPolicy;
+
 use crate::provider_transport::GatewayProviderTransportSnapshot;
 use crate::AppState;
 
-pub(crate) const CYBER_CONTINUE_FAILOVER_CONFIG_KEY: &str = "cyber_continue_failover";
 pub(crate) const RESPONSES_WEBSOCKET_CONFIG_KEY: &str = "responses_websocket";
+pub(crate) const ROUTING_EXECUTION_POLICY_REPORT_FIELD: &str = "routing_execution_policy";
 
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub(crate) struct LocalFailoverPolicy {
@@ -50,7 +52,7 @@ pub(crate) struct LocalFailoverRegexRule {
 pub(crate) async fn resolve_local_failover_policy(
     state: &AppState,
     plan: &ExecutionPlan,
-    _report_context: Option<&serde_json::Value>,
+    report_context: Option<&serde_json::Value>,
 ) -> LocalFailoverPolicy {
     let mut policy = match state
         .read_provider_transport_snapshot(&plan.provider_id, &plan.endpoint_id, &plan.key_id)
@@ -59,7 +61,8 @@ pub(crate) async fn resolve_local_failover_policy(
         Ok(Some(transport)) => local_failover_policy_from_transport(&transport),
         Ok(None) | Err(_) => LocalFailoverPolicy::default(),
     };
-    let cyber_continue_failover = cyber_continue_failover_enabled(state).await;
+    let cyber_continue_failover = routing_execution_policy_from_report_context(report_context)
+        .is_some_and(|policy| policy.cyber_continue_failover);
     policy.stop_cyber_policy_errors = !cyber_continue_failover;
     debug!(
         event_name = "local_failover_policy_loaded",
@@ -83,15 +86,13 @@ pub(crate) async fn resolve_local_failover_policy(
     policy
 }
 
-pub(crate) async fn cyber_continue_failover_enabled(state: &AppState) -> bool {
-    state
-        .read_system_config_json_value(CYBER_CONTINUE_FAILOVER_CONFIG_KEY)
-        .await
-        .ok()
-        .flatten()
-        .as_ref()
-        .and_then(Value::as_bool)
-        .unwrap_or(false)
+pub(crate) fn routing_execution_policy_from_report_context(
+    report_context: Option<&Value>,
+) -> Option<RoutingExecutionPolicy> {
+    report_context
+        .and_then(Value::as_object)
+        .and_then(|object| object.get(ROUTING_EXECUTION_POLICY_REPORT_FIELD))
+        .and_then(|value| serde_json::from_value(value.clone()).ok())
 }
 
 pub(crate) fn local_failover_policy_from_transport(

apps/aether-gateway/src/routing/resolver.rs

@@ -95,6 +95,7 @@ pub(crate) fn resolve_gateway_static_default_routing_policy(
         scheduling_mode: default_policy.scheduling_mode,
         keep_priority_on_conversion: default_policy.keep_priority_on_conversion,
         sticky_key_attempts: default_policy.sticky_key_attempts,
+        execution_policy: default_policy.execution_policy,
         ranking_overlay: RankingOverlay::default(),
         mutation_plan: MutationPlan::default(),
         pool_policy_overrides: BTreeMap::new(),
@@ -108,8 +109,10 @@ fn static_default_policy_fields(
     let Some(object) = config_json.as_object() else {
         return Ok(None);
     };
-    if !routing_array_field_is_missing_or_empty(object, "allowed_models")
-        || !routing_array_field_is_missing_or_empty(object, "model_policies")
+    // A strategy's default policy applies to every model. Only model policies
+    // and rules require the request-context-aware resolver; unknown legacy
+    // fields (including the removed group allowlist) are intentionally ignored.
+    if !routing_array_field_is_missing_or_empty(object, "model_policies")
         || !routing_array_field_is_missing_or_empty(object, "rules")
     {
         return Ok(None);
@@ -145,15 +148,47 @@ fn static_default_policy_fields(
             })?,
         None => DEFAULT_STICKY_KEY_ATTEMPTS,
     };
+    let enable_cf_heartbeat = routing_bool_field(
+        default_policy.get("enable_cf_heartbeat"),
+        "enable_cf_heartbeat",
+    )?;
+    // Older strategies stored separate image/text heartbeat flags. Treat
+    // either legacy flag as enabling the unified CF heartbeat setting while
+    // allowing newly saved strategies to use only the canonical key.
+    let legacy_image_heartbeat = routing_bool_field(
+        default_policy.get("enable_openai_image_sync_heartbeat"),
+        "enable_openai_image_sync_heartbeat",
+    )?;
+    let legacy_text_heartbeat = routing_bool_field(
+        default_policy.get("enable_standard_text_sync_heartbeat"),
+        "enable_standard_text_sync_heartbeat",
+    )?;
+    let execution_policy = aether_routing_core::RoutingExecutionPolicy {
+        enable_cf_heartbeat: enable_cf_heartbeat || legacy_image_heartbeat || legacy_text_heartbeat,
+        cyber_continue_failover: routing_bool_field(
+            default_policy.get("cyber_continue_failover"),
+            "cyber_continue_failover",
+        )?,
+    };
 
     Ok(Some(RoutingDefaultPolicy {
         priority_mode,
         scheduling_mode,
         keep_priority_on_conversion,
         sticky_key_attempts,
+        execution_policy,
     }))
 }
 
+fn routing_bool_field(value: Option<&Value>, field: &str) -> Result<bool, GatewayError> {
+    match value {
+        Some(value) => value
+            .as_bool()
+            .ok_or_else(|| invalid_routing_group_config(format!("{field} must be a boolean"))),
+        None => Ok(false),
+    }
+}
+
 fn routing_array_field_is_missing_or_empty(
     object: &serde_json::Map<String, Value>,
     key: &str,
@@ -201,7 +236,7 @@ mod tests {
                 "scheduling_mode": "load_balance",
                 "keep_priority_on_conversion": true
             },
-            "allowed_models": [],
+            "allowed_models": ["legacy-model"],
             "model_policies": [],
             "rules": []
         });

apps/aether-gateway/src/routing/selection.rs

@@ -8,6 +8,8 @@ pub(crate) const ROUTING_GROUP_HEADER: &str = "x-aether-scheduler-group";
 
 #[derive(Debug, Error, Clone, PartialEq, Eq)]
 pub(crate) enum GatewayRoutingSelectionError {
+    #[error("no enabled routing strategy is configured for this request")]
+    NoDefault,
     #[error("routing group was explicitly requested but was not found: {0}")]
     NotFound(String),
     #[error("routing group was explicitly requested but is not enabled: {0}")]
@@ -239,6 +241,7 @@ mod tests {
                 description: None,
                 enabled: true,
                 is_system_default: false,
+                sort_order: 0,
                 config_json: json!({}),
                 version: 1,
                 created_at: 1,
@@ -287,6 +290,7 @@ mod tests {
                 description: None,
                 enabled: true,
                 is_system_default: true,
+                sort_order: 0,
                 config_json: json!({}),
                 version: 1,
                 created_at: 1,
@@ -322,6 +326,7 @@ mod tests {
                 description: None,
                 enabled: true,
                 is_system_default: false,
+                sort_order: 0,
                 config_json: json!({}),
                 version: 1,
                 created_at: 1,
@@ -444,6 +449,7 @@ mod tests {
                 description: None,
                 enabled: false,
                 is_system_default: false,
+                sort_order: 0,
                 config_json: json!({}),
                 version: 1,
                 created_at: 1,
@@ -481,6 +487,7 @@ mod tests {
                 description: None,
                 enabled: true,
                 is_system_default: false,
+                sort_order: 0,
                 config_json: json!({}),
                 version: 1,
                 created_at: 1,

apps/aether-gateway/src/scheduler/candidate/mod.rs

@@ -1,7 +1,6 @@
 use self::selection::{
     collect_selectable_candidates, collect_selectable_candidates_with_skip_reasons_and_ordering,
     collect_selectable_enumerated_candidates_with_skip_reasons,
-    resolve_preselection_ordering_config,
 };
 use super::config::SchedulerOrderingConfig;
 use super::state::SchedulerRuntimeState;
@@ -56,8 +55,7 @@ enum RequiredCapabilityMatchMode {
 }
 
 /// `ordering_config` carries the request's routing-policy derived scheduler
-/// config. `None` falls back to the runtime default (system-default routing
-/// group, then legacy system-config keys).
+/// config. Every production scheduling pass must provide this snapshot.
 #[allow(clippy::too_many_arguments)]
 pub(crate) async fn list_selectable_candidates(
     selection_row_source: &(impl MinimalCandidateSelectionRowSource + Sync),
@@ -70,7 +68,7 @@ pub(crate) async fn list_selectable_candidates(
     client_session_affinity: Option<&ClientSessionAffinity>,
     now_unix_secs: u64,
     enable_model_directives: bool,
-    ordering_config: Option<SchedulerOrderingConfig>,
+    ordering_config: SchedulerOrderingConfig,
 ) -> Result<Vec<SchedulerMinimalCandidateSelectionCandidate>, GatewayError> {
     collect_selectable_candidates(
         selection_row_source,
@@ -107,7 +105,7 @@ pub(crate) async fn list_selectable_candidates_with_skip_reasons(
     client_session_affinity: Option<&ClientSessionAffinity>,
     now_unix_secs: u64,
     enable_model_directives: bool,
-    ordering_config: Option<SchedulerOrderingConfig>,
+    ordering_config: SchedulerOrderingConfig,
 ) -> Result<
     (
         Vec<SchedulerMinimalCandidateSelectionCandidate>,
@@ -145,7 +143,7 @@ pub(crate) async fn list_selectable_candidates_with_skip_reasons_for_request_ope
     now_unix_secs: u64,
     enable_model_directives: bool,
     request_operation: Option<&str>,
-    ordering_config: Option<SchedulerOrderingConfig>,
+    ordering_config: SchedulerOrderingConfig,
 ) -> Result<
     (
         Vec<SchedulerMinimalCandidateSelectionCandidate>,
@@ -180,7 +178,7 @@ pub(crate) async fn list_selectable_enumerated_candidates_with_skip_reasons(
     auth_snapshot: Option<&GatewayAuthApiKeySnapshot>,
     client_session_affinity: Option<&ClientSessionAffinity>,
     now_unix_secs: u64,
-    ordering_config: Option<SchedulerOrderingConfig>,
+    ordering_config: SchedulerOrderingConfig,
 ) -> Result<
     (
         Vec<SchedulerMinimalCandidateSelectionCandidate>,
@@ -188,8 +186,6 @@ pub(crate) async fn list_selectable_enumerated_candidates_with_skip_reasons(
     ),
     GatewayError,
 > {
-    let ordering_config =
-        resolve_preselection_ordering_config(runtime_state, ordering_config).await?;
     let priority_affinity_key = selection::scheduling_priority_affinity_key(
         auth_snapshot,
         client_session_affinity,
@@ -220,7 +216,7 @@ pub(crate) async fn list_selectable_candidates_for_required_capability_without_r
     auth_snapshot: Option<&GatewayAuthApiKeySnapshot>,
     client_session_affinity: Option<&ClientSessionAffinity>,
     now_unix_secs: u64,
-    ordering_config: Option<SchedulerOrderingConfig>,
+    ordering_config: SchedulerOrderingConfig,
 ) -> Result<Vec<SchedulerMinimalCandidateSelectionCandidate>, GatewayError> {
     Ok(
         list_selectable_candidates_for_required_capability_without_requested_model_with_auth_limit_signal(
@@ -249,7 +245,7 @@ pub(crate) async fn list_selectable_candidates_for_required_capability_without_r
     auth_snapshot: Option<&GatewayAuthApiKeySnapshot>,
     client_session_affinity: Option<&ClientSessionAffinity>,
     now_unix_secs: u64,
-    ordering_config: Option<SchedulerOrderingConfig>,
+    ordering_config: SchedulerOrderingConfig,
 ) -> Result<(Vec<SchedulerMinimalCandidateSelectionCandidate>, bool), GatewayError> {
     let normalized_api_format = normalize_api_format(candidate_api_format);
     if normalized_api_format.is_empty() {

apps/aether-gateway/src/scheduler/candidate/selection.rs

@@ -47,7 +47,7 @@ pub(super) fn is_exact_all_skipped_by_auth_limit(
             .all(|candidate| is_auth_api_key_concurrency_limit_skip_reason(candidate.skip_reason))
 }
 
-#[cfg_attr(not(test), allow(dead_code))]
+#[cfg(test)]
 pub(super) async fn select_minimal_candidate(
     selection_row_source: &(impl MinimalCandidateSelectionRowSource + Sync),
     runtime_state: &impl SchedulerRuntimeState,
@@ -59,20 +59,8 @@ pub(super) async fn select_minimal_candidate(
     client_session_affinity: Option<&ClientSessionAffinity>,
     now_unix_secs: u64,
     enable_model_directives: bool,
+    ordering_config: SchedulerOrderingConfig,
 ) -> Result<Option<SchedulerMinimalCandidateSelectionCandidate>, GatewayError> {
-    let affinity_epoch = runtime_state.scheduler_affinity_epoch();
-    let ordering_config = runtime_state.read_scheduler_ordering_config().await?;
-    let affinity_cache_key = build_scheduler_affinity_cache_key(
-        auth_snapshot,
-        api_format,
-        global_model_name,
-        client_session_affinity,
-    );
-    let priority_affinity_key = scheduling_priority_affinity_key(
-        auth_snapshot,
-        client_session_affinity,
-        ordering_config.scheduling_mode,
-    );
     let candidates = enumerate_scheduler_candidates(
         selection_row_source,
         api_format,
@@ -84,7 +72,7 @@ pub(super) async fn select_minimal_candidate(
         None,
     )
     .await?;
-    let selected = collect_selectable_enumerated_candidates_with_skip_reasons(
+    Ok(collect_selectable_enumerated_candidates_with_skip_reasons(
         runtime_state,
         api_format,
         global_model_name,
@@ -94,25 +82,16 @@ pub(super) async fn select_minimal_candidate(
         client_session_affinity,
         now_unix_secs,
         ordering_config,
-        priority_affinity_key,
+        scheduling_priority_affinity_key(
+            auth_snapshot,
+            client_session_affinity,
+            ordering_config.scheduling_mode,
+        ),
     )
     .await?
     .0
     .into_iter()
-    .next();
-    if ordering_config.scheduling_mode == SchedulerSchedulingMode::CacheAffinity
-        && has_explicit_session_affinity(client_session_affinity)
-    {
-        if let Some(candidate) = selected.as_ref() {
-            remember_scheduler_affinity(
-                affinity_cache_key.as_deref(),
-                runtime_state,
-                candidate,
-                Some(affinity_epoch),
-            );
-        }
-    }
-    Ok(selected)
+    .next())
 }
 
 #[allow(clippy::too_many_arguments)]
@@ -127,7 +106,7 @@ pub(super) async fn collect_selectable_candidates(
     client_session_affinity: Option<&ClientSessionAffinity>,
     now_unix_secs: u64,
     enable_model_directives: bool,
-    ordering_config: Option<SchedulerOrderingConfig>,
+    ordering_config: SchedulerOrderingConfig,
 ) -> Result<Vec<SchedulerMinimalCandidateSelectionCandidate>, GatewayError> {
     Ok(
         collect_selectable_candidates_with_skip_reasons_and_ordering(
@@ -149,10 +128,8 @@ pub(super) async fn collect_selectable_candidates(
     )
 }
 
-/// Legacy-shaped entrypoint that resolves the ordering config from the
-/// runtime state. Prefer `collect_selectable_candidates_with_skip_reasons_and_ordering`
-/// and pass the request's routing-policy config explicitly.
 #[allow(clippy::too_many_arguments)]
+#[cfg(test)]
 pub(super) async fn collect_selectable_candidates_with_skip_reasons(
     selection_row_source: &(impl MinimalCandidateSelectionRowSource + Sync),
     runtime_state: &impl SchedulerRuntimeState,
@@ -184,24 +161,11 @@ pub(super) async fn collect_selectable_candidates_with_skip_reasons(
         now_unix_secs,
         enable_model_directives,
         request_operation,
-        None,
+        SchedulerOrderingConfig::default(),
     )
     .await
 }
 
-/// Resolve the ordering config for a preselection pass: the routing-policy
-/// derived config wins when the caller has one; otherwise fall back to the
-/// runtime default (system-default routing group, then legacy keys).
-pub(super) async fn resolve_preselection_ordering_config(
-    runtime_state: &impl SchedulerRuntimeState,
-    ordering_config: Option<SchedulerOrderingConfig>,
-) -> Result<SchedulerOrderingConfig, GatewayError> {
-    match ordering_config {
-        Some(config) => Ok(config),
-        None => runtime_state.read_scheduler_ordering_config().await,
-    }
-}
-
 #[allow(clippy::too_many_arguments)]
 pub(super) async fn collect_selectable_candidates_with_skip_reasons_and_ordering(
     selection_row_source: &(impl MinimalCandidateSelectionRowSource + Sync),
@@ -215,7 +179,7 @@ pub(super) async fn collect_selectable_candidates_with_skip_reasons_and_ordering
     now_unix_secs: u64,
     enable_model_directives: bool,
     request_operation: Option<&str>,
-    ordering_config: Option<SchedulerOrderingConfig>,
+    ordering_config: SchedulerOrderingConfig,
 ) -> Result<
     (
         Vec<SchedulerMinimalCandidateSelectionCandidate>,
@@ -223,8 +187,6 @@ pub(super) async fn collect_selectable_candidates_with_skip_reasons_and_ordering
     ),
     GatewayError,
 > {
-    let ordering_config =
-        resolve_preselection_ordering_config(runtime_state, ordering_config).await?;
     let priority_affinity_key = scheduling_priority_affinity_key(
         auth_snapshot,
         client_session_affinity,

apps/aether-gateway/src/scheduler/candidate/tests/affinity.rs

@@ -23,6 +23,7 @@ use crate::data::candidate_selection::{
     read_requested_model_rows, MinimalCandidateSelectionRowSource,
 };
 use crate::data::GatewayDataState;
+use crate::scheduler::config::SchedulerOrderingConfig;
 use crate::{AppState, GatewayError};
 
 use super::super::affinity::build_scheduler_affinity_cache_key;
@@ -50,6 +51,7 @@ async fn select_candidate(
         client_session_affinity,
         now_unix_secs,
         false,
+        SchedulerOrderingConfig::default(),
     )
     .await
 }

apps/aether-gateway/src/scheduler/candidate/tests/required_capability.rs

@@ -65,7 +65,7 @@ async fn compatible_required_capability_prefers_matching_keys_without_hard_filte
         None,
         None,
         100,
-        None,
+        crate::scheduler::config::SchedulerOrderingConfig::default(),
     )
     .await
     .expect("selection should succeed");
@@ -121,7 +121,7 @@ async fn exclusive_required_capability_keeps_hard_filtering_only_matching_keys()
         None,
         None,
         100,
-        None,
+        crate::scheduler::config::SchedulerOrderingConfig::default(),
     )
     .await
     .expect("selection should succeed");
@@ -198,7 +198,7 @@ async fn required_capability_without_model_uses_session_scoped_affinity() {
         Some(&auth_snapshot),
         Some(&client_session_affinity),
         100,
-        None,
+        crate::scheduler::config::SchedulerOrderingConfig::default(),
     )
     .await
     .expect("selection should succeed");
@@ -276,7 +276,7 @@ async fn required_capability_reports_auth_limit_signal_when_every_model_is_block
             Some(&auth_snapshot),
             None,
             100,
-            None,
+            crate::scheduler::config::SchedulerOrderingConfig::default(),
         )
         .await
         .expect("selection should succeed");

apps/aether-gateway/src/scheduler/candidate/tests/selection.rs

@@ -5,6 +5,7 @@ use aether_data::repository::candidate_selection::InMemoryMinimalCandidateSelect
 use aether_data::repository::candidates::InMemoryRequestCandidateRepository;
 use aether_data::repository::provider_catalog::InMemoryProviderCatalogReadRepository;
 use aether_data::repository::quota::InMemoryProviderQuotaRepository;
+use aether_data::repository::routing_profiles::InMemoryRoutingGroupRepository;
 use aether_data_contracts::repository::candidate_selection::{
     StoredMinimalCandidateSelectionRow, StoredProviderModelMapping,
 };
@@ -13,6 +14,9 @@ use aether_data_contracts::repository::candidates::{
 };
 use aether_data_contracts::repository::provider_catalog::StoredProviderCatalogKey;
 use aether_data_contracts::repository::quota::StoredProviderQuotaSnapshot;
+use aether_data_contracts::repository::routing_profiles::{
+    CreateRoutingGroupRecord, RoutingGroupWriteRepository,
+};
 use aether_scheduler_core::{ClientSessionAffinity, SchedulerMinimalCandidateSelectionCandidate};
 use serde_json::json;
 
@@ -20,6 +24,7 @@ use crate::cache::SchedulerAffinityTarget;
 use crate::data::auth::GatewayAuthApiKeySnapshot;
 use crate::data::candidate_selection::MinimalCandidateSelectionRowSource;
 use crate::data::GatewayDataState;
+use crate::scheduler::config::SchedulerOrderingConfig;
 use crate::{AppState, GatewayError};
 
 use super::super::affinity::build_scheduler_affinity_cache_key;
@@ -31,6 +36,39 @@ use super::super::selection::{
 };
 use super::support::{sample_auth_snapshot, sample_key, sample_provider, sample_row};
 
+async fn state_with_routing_default_policy(
+    data_state: GatewayDataState,
+    default_policy: serde_json::Value,
+) -> AppState {
+    let repository = Arc::new(InMemoryRoutingGroupRepository::default());
+    repository
+        .create_routing_group(CreateRoutingGroupRecord {
+            id: "selection-test-default".to_string(),
+            name: "selection-test-default".to_string(),
+            description: None,
+            enabled: true,
+            is_system_default: true,
+            sort_order: 0,
+            config_json: json!({"default_policy": default_policy}),
+            version: 1,
+            created_at: 1,
+            updated_at: 1,
+            published_at: None,
+        })
+        .await
+        .expect("routing strategy should be created");
+    AppState::new()
+        .expect("state should build")
+        .with_data_state_for_tests(data_state.with_routing_group_repository_for_tests(repository))
+}
+
+async fn ordering_config(state: &AppState) -> SchedulerOrderingConfig {
+    crate::scheduler::config::read_system_default_routing_ordering_config(state)
+        .await
+        .expect("routing strategy should load")
+        .unwrap_or_default()
+}
+
 async fn select_candidate(
     selection_row_source: &(impl MinimalCandidateSelectionRowSource + Sync),
     runtime_state: &AppState,
@@ -40,6 +78,7 @@ async fn select_candidate(
     auth_snapshot: Option<&GatewayAuthApiKeySnapshot>,
     now_unix_secs: u64,
 ) -> Result<Option<SchedulerMinimalCandidateSelectionCandidate>, GatewayError> {
+    let ordering_config = ordering_config(runtime_state).await;
     select_candidate_impl(
         selection_row_source,
         runtime_state,
@@ -51,6 +90,7 @@ async fn select_candidate(
         None,
         now_unix_secs,
         false,
+        ordering_config,
     )
     .await
 }
@@ -64,6 +104,7 @@ async fn collect_selectable_candidates(
     auth_snapshot: Option<&GatewayAuthApiKeySnapshot>,
     now_unix_secs: u64,
 ) -> Result<Vec<SchedulerMinimalCandidateSelectionCandidate>, GatewayError> {
+    let ordering_config = ordering_config(runtime_state).await;
     collect_selectable_candidates_impl(
         selection_row_source,
         runtime_state,
@@ -75,7 +116,7 @@ async fn collect_selectable_candidates(
         None,
         now_unix_secs,
         false,
-        None,
+        ordering_config,
     )
     .await
 }
@@ -289,15 +330,11 @@ async fn selects_by_provider_priority_when_priority_mode_is_provider() {
         global_key_first,
     ]));
     let quotas = Arc::new(InMemoryProviderQuotaRepository::seed(vec![]));
-    let state = AppState::new()
-        .expect("state should build")
-        .with_data_state_for_tests(
-            GatewayDataState::with_candidate_selection_and_quota_for_tests(candidates, quotas)
-                .with_system_config_values_for_tests(vec![(
-                    "provider_priority_mode".to_string(),
-                    json!("provider"),
-                )]),
-        );
+    let state = state_with_routing_default_policy(
+        GatewayDataState::with_candidate_selection_and_quota_for_tests(candidates, quotas),
+        json!({"priority_mode": "provider"}),
+    )
+    .await;
 
     let selected = select_candidate(
         state.data.as_ref(),
@@ -343,15 +380,11 @@ async fn selects_by_global_key_priority_when_priority_mode_is_global_key() {
         global_key_first,
     ]));
     let quotas = Arc::new(InMemoryProviderQuotaRepository::seed(vec![]));
-    let state = AppState::new()
-        .expect("state should build")
-        .with_data_state_for_tests(
-            GatewayDataState::with_candidate_selection_and_quota_for_tests(candidates, quotas)
-                .with_system_config_values_for_tests(vec![(
-                    "provider_priority_mode".to_string(),
-                    json!("global_key"),
-                )]),
-        );
+    let state = state_with_routing_default_policy(
+        GatewayDataState::with_candidate_selection_and_quota_for_tests(candidates, quotas),
+        json!({"priority_mode": "global_key"}),
+    )
+    .await;
 
     let selected = select_candidate(
         state.data.as_ref(),
@@ -415,6 +448,7 @@ async fn scheduler_selection_prefers_required_capability_matches_before_priority
         None,
         100,
         false,
+        SchedulerOrderingConfig::default(),
     )
     .await
     .expect("selection should succeed")
@@ -450,15 +484,11 @@ async fn fixed_order_ignores_cached_scheduler_affinity_promotion() {
         first, second,
     ]));
     let quotas = Arc::new(InMemoryProviderQuotaRepository::seed(vec![]));
-    let state = AppState::new()
-        .expect("state should build")
-        .with_data_state_for_tests(
-            GatewayDataState::with_candidate_selection_and_quota_for_tests(candidates, quotas)
-                .with_system_config_values_for_tests(vec![(
-                    "scheduling_mode".to_string(),
-                    json!("fixed_order"),
-                )]),
-        );
+    let state = state_with_routing_default_policy(
+        GatewayDataState::with_candidate_selection_and_quota_for_tests(candidates, quotas),
+        json!({"scheduling_mode": "fixed_order"}),
+    )
+    .await;
 
     let auth_snapshot = sample_auth_snapshot("affinity-key-1");
     state.remember_scheduler_affinity_target(
@@ -515,15 +545,11 @@ async fn fixed_order_disables_same_priority_affinity_hash_tiebreaker() {
         first, second,
     ]));
     let quotas = Arc::new(InMemoryProviderQuotaRepository::seed(vec![]));
-    let state = AppState::new()
-        .expect("state should build")
-        .with_data_state_for_tests(
-            GatewayDataState::with_candidate_selection_and_quota_for_tests(candidates, quotas)
-                .with_system_config_values_for_tests(vec![(
-                    "scheduling_mode".to_string(),
-                    json!("fixed_order"),
-                )]),
-        );
+    let state = state_with_routing_default_policy(
+        GatewayDataState::with_candidate_selection_and_quota_for_tests(candidates, quotas),
+        json!({"scheduling_mode": "fixed_order"}),
+    )
+    .await;
 
     let auth_snapshot = sample_auth_snapshot("affinity-key-1");
     let selection = collect_selectable_candidates(
@@ -569,15 +595,11 @@ async fn cache_affinity_promotes_cached_scheduler_affinity_candidate_when_enable
         first, second,
     ]));
     let quotas = Arc::new(InMemoryProviderQuotaRepository::seed(vec![]));
-    let state = AppState::new()
-        .expect("state should build")
-        .with_data_state_for_tests(
-            GatewayDataState::with_candidate_selection_and_quota_for_tests(candidates, quotas)
-                .with_system_config_values_for_tests(vec![(
-                    "scheduling_mode".to_string(),
-                    json!("cache_affinity"),
-                )]),
-        );
+    let state = state_with_routing_default_policy(
+        GatewayDataState::with_candidate_selection_and_quota_for_tests(candidates, quotas),
+        json!({"scheduling_mode": "cache_affinity"}),
+    )
+    .await;
 
     let auth_snapshot = sample_auth_snapshot("affinity-key-1");
     let client_session_affinity = ClientSessionAffinity::from_session_key("session-1");
@@ -610,6 +632,7 @@ async fn cache_affinity_promotes_cached_scheduler_affinity_candidate_when_enable
         Some(&client_session_affinity),
         100,
         false,
+        ordering_config(&state).await,
     )
     .await
     .expect("selection should succeed")
@@ -645,15 +668,11 @@ async fn cache_affinity_ignores_cached_scheduler_affinity_without_client_session
         first, second,
     ]));
     let quotas = Arc::new(InMemoryProviderQuotaRepository::seed(vec![]));
-    let state = AppState::new()
-        .expect("state should build")
-        .with_data_state_for_tests(
-            GatewayDataState::with_candidate_selection_and_quota_for_tests(candidates, quotas)
-                .with_system_config_values_for_tests(vec![(
-                    "scheduling_mode".to_string(),
-                    json!("cache_affinity"),
-                )]),
-        );
+    let state = state_with_routing_default_policy(
+        GatewayDataState::with_candidate_selection_and_quota_for_tests(candidates, quotas),
+        json!({"scheduling_mode": "cache_affinity"}),
+    )
+    .await;
 
     let auth_snapshot = sample_auth_snapshot("affinity-key-1");
     state.remember_scheduler_affinity_target(
@@ -691,15 +710,11 @@ async fn load_balance_selection_does_not_remember_scheduler_affinity() {
         row,
     ]));
     let quotas = Arc::new(InMemoryProviderQuotaRepository::seed(vec![]));
-    let state = AppState::new()
-        .expect("state should build")
-        .with_data_state_for_tests(
-            GatewayDataState::with_candidate_selection_and_quota_for_tests(candidates, quotas)
-                .with_system_config_values_for_tests(vec![(
-                    "scheduling_mode".to_string(),
-                    json!("load_balance"),
-                )]),
-        );
+    let state = state_with_routing_default_policy(
+        GatewayDataState::with_candidate_selection_and_quota_for_tests(candidates, quotas),
+        json!({"scheduling_mode": "load_balance"}),
+    )
+    .await;
     let auth_snapshot = sample_auth_snapshot("affinity-key-1");
     let client_session_affinity = ClientSessionAffinity::from_session_key("session-1");
     let cache_key = build_scheduler_affinity_cache_key(
@@ -721,6 +736,7 @@ async fn load_balance_selection_does_not_remember_scheduler_affinity() {
         Some(&client_session_affinity),
         100,
         false,
+        ordering_config(&state).await,
     )
     .await
     .expect("selection should succeed")
@@ -758,15 +774,11 @@ async fn load_balance_ignores_provider_priority_and_cached_affinity() {
         first, second,
     ]));
     let quotas = Arc::new(InMemoryProviderQuotaRepository::seed(vec![]));
-    let state = AppState::new()
-        .expect("state should build")
-        .with_data_state_for_tests(
-            GatewayDataState::with_candidate_selection_and_quota_for_tests(candidates, quotas)
-                .with_system_config_values_for_tests(vec![(
-                    "scheduling_mode".to_string(),
-                    json!("load_balance"),
-                )]),
-        );
+    let state = state_with_routing_default_policy(
+        GatewayDataState::with_candidate_selection_and_quota_for_tests(candidates, quotas),
+        json!({"scheduling_mode": "load_balance"}),
+    )
+    .await;
 
     let auth_snapshot = sample_auth_snapshot("affinity-key-1");
     state.remember_scheduler_affinity_target(

apps/aether-gateway/src/scheduler/config.rs

@@ -55,7 +55,7 @@ impl Default for SchedulerOrderingConfig {
 
 impl SchedulerOrderingConfig {
     /// Ordering config derived from a resolved routing policy. The policy is
-    /// the single source of truth: no legacy system-config value is merged in.
+    /// the single source of truth for request scheduling.
     pub(crate) fn from_routing_policy(policy: &ResolvedRoutingPolicy) -> Self {
         Self {
             priority_mode: scheduler_priority_mode_from_routing(policy.priority_mode),
@@ -87,6 +87,7 @@ impl SchedulerOrderingConfig {
             },
             keep_priority_on_conversion: self.keep_priority_on_conversion,
             sticky_key_attempts: self.sticky_key_attempts,
+            execution_policy: aether_routing_core::RoutingExecutionPolicy::default(),
         }
     }
 
@@ -114,61 +115,6 @@ fn scheduler_scheduling_mode_from_routing(mode: RoutingSchedulingMode) -> Schedu
     }
 }
 
-pub(crate) fn parse_scheduler_priority_mode(
-    value: Option<&serde_json::Value>,
-) -> SchedulerPriorityMode {
-    match value
-        .and_then(serde_json::Value::as_str)
-        .map(str::trim)
-        .filter(|value| !value.is_empty())
-        .map(|value| value.to_ascii_lowercase())
-        .as_deref()
-    {
-        Some("global_key") => SchedulerPriorityMode::GlobalKey,
-        _ => SchedulerPriorityMode::Provider,
-    }
-}
-
-pub(crate) fn parse_keep_priority_on_conversion(value: Option<&serde_json::Value>) -> bool {
-    value.and_then(serde_json::Value::as_bool).unwrap_or(false)
-}
-
-pub(crate) fn parse_scheduler_scheduling_mode(
-    value: Option<&serde_json::Value>,
-) -> SchedulerSchedulingMode {
-    match value
-        .and_then(serde_json::Value::as_str)
-        .map(str::trim)
-        .filter(|value| !value.is_empty())
-        .map(|value| value.to_ascii_lowercase())
-        .as_deref()
-    {
-        Some("fixed_order") => SchedulerSchedulingMode::FixedOrder,
-        Some("load_balance") => SchedulerSchedulingMode::LoadBalance,
-        _ => SchedulerSchedulingMode::CacheAffinity,
-    }
-}
-
-/// Effective scheduler ordering config for requests that carry no resolved
-/// routing policy.
-///
-/// Resolution order:
-/// 1. the enabled system-default routing group's `default_policy`;
-/// 2. the legacy system-config keys (`provider_priority_mode`,
-///    `scheduling_mode`, `keep_priority_on_conversion`).
-///
-/// Step 2 only exists so deployments that never created a routing group keep
-/// their behaviour; once the legacy keys are removed this function collapses
-/// to step 1 plus `SchedulerOrderingConfig::default()`.
-pub(crate) async fn read_scheduler_ordering_config(
-    state: &AppState,
-) -> Result<SchedulerOrderingConfig, GatewayError> {
-    if let Some(config) = read_system_default_routing_ordering_config(state).await? {
-        return Ok(config);
-    }
-    read_legacy_scheduler_ordering_config(state).await
-}
-
 /// Ordering config from the enabled system-default routing group, if any.
 pub(crate) async fn read_system_default_routing_ordering_config(
     state: &AppState,
@@ -201,38 +147,6 @@ pub(crate) async fn read_system_default_routing_ordering_config(
     )))
 }
 
-/// Legacy system-config based ordering config. Kept only as a migration
-/// fallback; see `read_scheduler_ordering_config`.
-pub(crate) async fn read_legacy_scheduler_ordering_config(
-    state: &AppState,
-) -> Result<SchedulerOrderingConfig, GatewayError> {
-    let priority_mode = parse_scheduler_priority_mode(
-        state
-            .read_system_config_json_value("provider_priority_mode")
-            .await?
-            .as_ref(),
-    );
-    let scheduling_mode = parse_scheduler_scheduling_mode(
-        state
-            .read_system_config_json_value("scheduling_mode")
-            .await?
-            .as_ref(),
-    );
-    let keep_priority_on_conversion = parse_keep_priority_on_conversion(
-        state
-            .read_system_config_json_value("keep_priority_on_conversion")
-            .await?
-            .as_ref(),
-    );
-    Ok(SchedulerOrderingConfig {
-        priority_mode,
-        scheduling_mode,
-        keep_priority_on_conversion,
-        // Legacy config never carried a sticky-key setting; use the routing default.
-        sticky_key_attempts: DEFAULT_STICKY_KEY_ATTEMPTS,
-    })
-}
-
 #[cfg(test)]
 mod tests {
     use std::sync::Arc;
@@ -247,14 +161,6 @@ mod tests {
     use super::*;
     use crate::data::GatewayDataState;
 
-    fn legacy_values() -> [(String, serde_json::Value); 3] {
-        [
-            ("provider_priority_mode".to_string(), json!("global_key")),
-            ("scheduling_mode".to_string(), json!("load_balance")),
-            ("keep_priority_on_conversion".to_string(), json!(true)),
-        ]
-    }
-
     async fn create_system_default(
         repository: &InMemoryRoutingGroupRepository,
         enabled: bool,
@@ -267,6 +173,7 @@ mod tests {
                 description: None,
                 enabled,
                 is_system_default: true,
+                sort_order: 0,
                 config_json,
                 version: 1,
                 created_at: 1,
@@ -278,7 +185,7 @@ mod tests {
     }
 
     #[tokio::test]
-    async fn system_default_routing_group_overrides_legacy_keys() {
+    async fn system_default_routing_group_exposes_strategy_ordering() {
         let repository = Arc::new(InMemoryRoutingGroupRepository::default());
         create_system_default(
             &repository,
@@ -293,12 +200,13 @@ mod tests {
         )
         .await;
         let state = AppState::new().unwrap().with_data_state_for_tests(
-            GatewayDataState::disabled()
-                .with_system_config_values_for_tests(legacy_values())
-                .with_routing_group_repository_for_tests(repository),
+            GatewayDataState::disabled().with_routing_group_repository_for_tests(repository),
         );
 
-        let config = read_scheduler_ordering_config(&state).await.unwrap();
+        let config = read_system_default_routing_ordering_config(&state)
+            .await
+            .unwrap()
+            .unwrap();
 
         assert_eq!(config.priority_mode, SchedulerPriorityMode::Provider);
         assert_eq!(config.scheduling_mode, SchedulerSchedulingMode::FixedOrder);
@@ -310,18 +218,19 @@ mod tests {
         let repository = Arc::new(InMemoryRoutingGroupRepository::default());
         create_system_default(&repository, true, json!({})).await;
         let state = AppState::new().unwrap().with_data_state_for_tests(
-            GatewayDataState::disabled()
-                .with_system_config_values_for_tests(legacy_values())
-                .with_routing_group_repository_for_tests(repository),
+            GatewayDataState::disabled().with_routing_group_repository_for_tests(repository),
         );
 
-        let config = read_scheduler_ordering_config(&state).await.unwrap();
+        let config = read_system_default_routing_ordering_config(&state)
+            .await
+            .unwrap()
+            .unwrap();
 
         assert_eq!(config, SchedulerOrderingConfig::default());
     }
 
     #[tokio::test]
-    async fn disabled_or_missing_system_default_group_falls_back_to_legacy_keys() {
+    async fn disabled_or_missing_system_default_group_uses_routing_defaults() {
         let repository = Arc::new(InMemoryRoutingGroupRepository::default());
         create_system_default(
             &repository,
@@ -330,28 +239,25 @@ mod tests {
         )
         .await;
         let with_disabled_group = AppState::new().unwrap().with_data_state_for_tests(
-            GatewayDataState::disabled()
-                .with_system_config_values_for_tests(legacy_values())
-                .with_routing_group_repository_for_tests(repository),
-        );
-        let without_repository = AppState::new().unwrap().with_data_state_for_tests(
-            GatewayDataState::disabled().with_system_config_values_for_tests(legacy_values()),
+            GatewayDataState::disabled().with_routing_group_repository_for_tests(repository),
         );
+        let without_repository = AppState::new()
+            .unwrap()
+            .with_data_state_for_tests(GatewayDataState::disabled());
 
         for state in [with_disabled_group, without_repository] {
-            let config = read_scheduler_ordering_config(&state).await.unwrap();
-            assert_eq!(config.priority_mode, SchedulerPriorityMode::GlobalKey);
-            assert_eq!(config.scheduling_mode, SchedulerSchedulingMode::LoadBalance);
-            assert!(config.keep_priority_on_conversion);
+            let config = read_system_default_routing_ordering_config(&state)
+                .await
+                .unwrap();
+            assert!(config.is_none());
         }
     }
 
     #[tokio::test]
-    async fn bootstrap_creates_system_default_group_from_legacy_keys_once() {
+    async fn bootstrap_creates_system_default_group_from_routing_defaults_once() {
         let repository = Arc::new(InMemoryRoutingGroupRepository::default());
         let state = AppState::new().unwrap().with_data_state_for_tests(
             GatewayDataState::disabled()
-                .with_system_config_values_for_tests(legacy_values())
                 .with_routing_group_repository_for_tests(repository.clone()),
         );
 
@@ -365,9 +271,9 @@ mod tests {
         assert_eq!(
             created.config_json["default_policy"],
             json!({
-                "priority_mode": "global_key",
-                "scheduling_mode": "load_balance",
-                "keep_priority_on_conversion": true,
+                "priority_mode": "provider",
+                "scheduling_mode": "cache_affinity",
+                "keep_priority_on_conversion": false,
                 "sticky_key_attempts": DEFAULT_STICKY_KEY_ATTEMPTS
             })
         );
@@ -386,9 +292,39 @@ mod tests {
             Some(created.id)
         );
 
-        let config = read_scheduler_ordering_config(&state).await.unwrap();
-        assert_eq!(config.priority_mode, SchedulerPriorityMode::GlobalKey);
-        assert_eq!(config.scheduling_mode, SchedulerSchedulingMode::LoadBalance);
-        assert!(config.keep_priority_on_conversion);
+        let config = read_system_default_routing_ordering_config(&state)
+            .await
+            .unwrap()
+            .unwrap();
+        assert_eq!(config, SchedulerOrderingConfig::default());
+    }
+
+    #[tokio::test]
+    async fn bootstrap_does_not_migrate_legacy_scheduler_keys() {
+        let repository = Arc::new(InMemoryRoutingGroupRepository::default());
+        let state = AppState::new().unwrap().with_data_state_for_tests(
+            GatewayDataState::disabled()
+                .with_system_config_values_for_tests([
+                    ("provider_priority_mode".to_string(), json!("global_key")),
+                    ("scheduling_mode".to_string(), json!("load_balance")),
+                    ("keep_priority_on_conversion".to_string(), json!(true)),
+                ])
+                .with_routing_group_repository_for_tests(repository),
+        );
+
+        let created = state
+            .ensure_system_default_routing_group_inner()
+            .await
+            .unwrap()
+            .expect("bootstrap should create the strategy");
+        assert_eq!(
+            created.config_json["default_policy"],
+            json!({
+                "priority_mode": "provider",
+                "scheduling_mode": "cache_affinity",
+                "keep_priority_on_conversion": false,
+                "sticky_key_attempts": DEFAULT_STICKY_KEY_ATTEMPTS
+            })
+        );
     }
 }

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

@@ -10,8 +10,6 @@ use async_trait::async_trait;
 
 use crate::GatewayError;
 
-use super::config::SchedulerOrderingConfig;
-
 #[async_trait]
 pub(crate) trait SchedulerRuntimeState {
     async fn read_provider_quota_snapshot(
@@ -60,7 +58,4 @@ pub(crate) trait SchedulerRuntimeState {
         max_entries: usize,
         expected_epoch: Option<u64>,
     ) -> bool;
-
-    async fn read_scheduler_ordering_config(&self)
-        -> Result<SchedulerOrderingConfig, GatewayError>;
 }

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

@@ -79,12 +79,7 @@ const SYSTEM_CONFIG_CACHE_TTL: Duration = Duration::from_secs(30);
 // five minutes of total age. Direct database edits that bypass AppState
 // invalidation can therefore take at most this bounded interval to appear.
 const SYSTEM_CONFIG_CACHE_MAX_STALENESS: Duration = Duration::from_secs(5 * 60);
-const SCHEDULER_AFFECTING_SYSTEM_CONFIG_KEYS: &[&str] = &[
-    "enable_format_conversion",
-    "keep_priority_on_conversion",
-    "provider_priority_mode",
-    "scheduling_mode",
-];
+const SCHEDULER_AFFECTING_SYSTEM_CONFIG_KEYS: &[&str] = &["enable_format_conversion"];
 const AUTH_AFFECTING_SYSTEM_CONFIG_KEYS: &[&str] = &[
     crate::constants::DEFAULT_USER_GROUP_CONFIG_KEY,
     crate::constants::ANTIGRAVITY_BEARER_BRIDGE_CONFIG_KEY,
@@ -4350,12 +4345,13 @@ mod tests {
     }
 
     #[tokio::test]
-    async fn system_config_entry_write_refreshes_cache_and_scheduler_affinity_for_routing_keys() {
+    async fn system_config_entry_write_refreshes_cache_and_scheduler_affinity_for_format_conversion(
+    ) {
         let state = AppState::new()
             .expect("app state should build")
             .with_data_state_for_tests(
                 GatewayDataState::disabled().with_system_config_values_for_tests([(
-                    "keep_priority_on_conversion".to_string(),
+                    "enable_format_conversion".to_string(),
                     json!(false),
                 )]),
             );
@@ -4364,7 +4360,7 @@ mod tests {
 
         assert_eq!(
             state
-                .read_system_config_json_value("keep_priority_on_conversion")
+                .read_system_config_json_value("enable_format_conversion")
                 .await
                 .expect("system config read should succeed"),
             Some(json!(false))
@@ -4385,13 +4381,13 @@ mod tests {
 
         let initial_epoch = state.scheduler_affinity_epoch();
         state
-            .upsert_system_config_entry("keep_priority_on_conversion", &json!(true), None)
+            .upsert_system_config_entry("enable_format_conversion", &json!(true), None)
             .await
             .expect("admin config write should succeed");
 
         assert_eq!(
             state
-                .read_system_config_json_value("keep_priority_on_conversion")
+                .read_system_config_json_value("enable_format_conversion")
                 .await
                 .expect("system config read should use refreshed cache"),
             Some(json!(true))

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

@@ -680,10 +680,4 @@ impl SchedulerRuntimeState for AppState {
             expected_epoch,
         )
     }
-
-    async fn read_scheduler_ordering_config(
-        &self,
-    ) -> Result<crate::scheduler::config::SchedulerOrderingConfig, GatewayError> {
-        crate::scheduler::config::read_scheduler_ordering_config(self).await
-    }
 }

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

@@ -15,10 +15,9 @@ const BOOTSTRAP_SYSTEM_DEFAULT_ROUTING_GROUP_NAME: &str = "system-default";
 impl AppState {
     /// Make sure an enabled system-default routing group exists.
     ///
-    /// When none exists, one is created from the legacy scheduler system-config
-    /// keys so that removing those keys later does not change behaviour. Returns
-    /// the created group, or `None` when nothing had to be created (no routing
-    /// storage, no writer, or a system default already exists).
+    /// When none exists, one is created from the routing defaults.
+    /// Returns the created group, or `None` when nothing had to be created (no
+    /// routing storage, no writer, or a system default already exists).
     pub async fn ensure_system_default_routing_group(
         &self,
     ) -> Result<Option<StoredRoutingGroup>, std::io::Error> {
@@ -44,16 +43,12 @@ impl AppState {
             warn!(
                 event_name = "routing_system_default_bootstrap_skipped",
                 log_type = "event",
-                "no system default routing group exists and routing storage is read-only; scheduler falls back to legacy system config"
+                "no system default routing group exists and routing storage is read-only; scheduler uses routing defaults"
             );
             return Ok(None);
         }
 
-        let legacy = crate::scheduler::config::read_legacy_scheduler_ordering_config(self).await?;
-        let config = RoutingGroupConfig {
-            default_policy: legacy.to_routing_default_policy(),
-            ..RoutingGroupConfig::default()
-        };
+        let config = RoutingGroupConfig::default();
         let config_json = serde_json::to_value(config)
             .map_err(|err| GatewayError::Internal(format!("serialize routing config: {err}")))?;
 
@@ -75,9 +70,10 @@ impl AppState {
         self.create_routing_group(CreateRoutingGroupRecord {
             id: uuid::Uuid::new_v4().to_string(),
             name,
-            description: Some("自动从旧版调度配置迁移生成的系统默认策略".to_string()),
+            description: Some("系统默认调度策略".to_string()),
             enabled: true,
             is_system_default: true,
+            sort_order: 0,
             config_json,
             version: 1,
             created_at: now,

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

@@ -780,6 +780,14 @@ async fn gateway_updates_admin_provider_locally_with_trusted_admin_principal() {
     let provider_catalog_repository = Arc::new(InMemoryProviderCatalogReadRepository::seed(
         vec![
             sample_provider("provider-openai", "openai", 10)
+                .with_billing_fields(
+                    Some("free_tier".to_string()),
+                    None,
+                    None,
+                    Some(30),
+                    None,
+                    None,
+                )
                 .with_transport_fields(
                     true,
                     false,
@@ -974,6 +982,7 @@ async fn gateway_updates_admin_provider_locally_with_trusted_admin_principal() {
         .iter()
         .find(|provider| provider.id == "provider-openai")
         .expect("provider should exist");
+    assert_eq!(updated_provider.billing_type.as_deref(), Some("free_tier"));
     assert_eq!(
         updated_provider.request_timeout_secs,
         Some(aether_contracts::MAX_EXECUTION_REQUEST_TIMEOUT_SECS as f64)
@@ -1106,6 +1115,7 @@ async fn gateway_creates_admin_provider_locally_with_trusted_admin_principal() {
         .find(|provider| provider.id == "provider-existing")
         .expect("existing provider should remain");
     assert_eq!(created.provider_type, "codex");
+    assert_eq!(created.billing_type.as_deref(), Some("pay_as_you_go"));
     assert_eq!(created.provider_priority, 0);
     assert_eq!(existing.provider_priority, 1);
     assert_eq!(created.website.as_deref(), Some("https://codex.example"));

crates/aether-admin/src/system.rs

@@ -1725,8 +1725,6 @@ pub fn admin_system_config_default_value(key: &str) -> Option<serde_json::Value>
         "proxy_node_metrics_cleanup_batch_size" => Some(json!(5000)),
         "enable_provider_checkin" => Some(json!(true)),
         "provider_checkin_time" => Some(json!("01:05")),
-        "provider_priority_mode" => Some(json!("provider")),
-        "scheduling_mode" => Some(json!("cache_affinity")),
         "auto_delete_expired_keys" => Some(json!(false)),
         "turnstile_enabled" => Some(json!(false)),
         "turnstile_site_key" => Some(serde_json::Value::Null),
@@ -1754,10 +1752,8 @@ pub fn admin_system_config_default_value(key: &str) -> Option<serde_json::Value>
         "email_suffix_mode" => Some(json!("none")),
         "email_suffix_list" => Some(json!([])),
         "enable_format_conversion" => Some(json!(false)),
-        "cyber_continue_failover" => Some(json!(false)),
         "enable_model_directives" => Some(json!(false)),
         "model_directives" => Some(aether_ai_formats::default_model_directives_config()),
-        "keep_priority_on_conversion" => Some(json!(false)),
         "audit_log_retention_days" => Some(json!(30)),
         "enable_db_maintenance" => Some(json!(true)),
         "system_proxy_node_id" => Some(serde_json::Value::Null),
@@ -2236,8 +2232,7 @@ pub fn parse_admin_system_config_update(
     }
 
     match normalized_key.as_str() {
-        "cyber_continue_failover"
-        | "enable_model_directives"
+        "enable_model_directives"
         | "module.important_notification.enabled"
         | "module.important_notification.email_enabled"
         | "module.server_chan_push.enabled"
@@ -3508,28 +3503,6 @@ mod tests {
         );
     }
 
-    #[test]
-    fn cyber_continue_failover_defaults_to_disabled() {
-        assert_eq!(
-            admin_system_config_default_value("cyber_continue_failover"),
-            Some(json!(false))
-        );
-    }
-
-    #[test]
-    fn cyber_continue_failover_update_requires_a_boolean() {
-        let update =
-            parse_admin_system_config_update("cyber_continue_failover", br#"{"value":true}"#)
-                .expect("boolean Cyber failover setting should parse");
-        assert_eq!(update.value, json!(true));
-
-        assert!(parse_admin_system_config_update(
-            "cyber_continue_failover",
-            br#"{"value":"true"}"#,
-        )
-        .is_err());
-    }
-
     #[test]
     fn model_directives_update_accepts_legacy_and_current_config_shapes() {
         for body in [

crates/aether-data/adapters/mysql/migrations/20260903000000_add_routing_group_sort_order.sql

@@ -0,0 +1,3 @@
+ALTER TABLE routing_groups
+    ADD COLUMN sort_order BIGINT NOT NULL DEFAULT 0,
+    ADD KEY routing_groups_enabled_sort_idx (enabled, sort_order, name, id);

crates/aether-data/adapters/mysql/src/routing_profiles.rs

@@ -15,6 +15,7 @@ SELECT
   description,
   enabled,
   is_system_default,
+  sort_order,
   config_json,
   version,
   created_at,
@@ -61,10 +62,12 @@ impl MysqlRoutingGroupRepository {
 #[async_trait]
 impl RoutingGroupReadRepository for MysqlRoutingGroupRepository {
     async fn list_routing_groups(&self) -> Result<Vec<StoredRoutingGroup>, DataLayerError> {
-        let rows = sqlx::query(&format!("{ROUTING_GROUP_SELECT} ORDER BY name ASC, id ASC"))
-            .fetch_all(&self.pool)
-            .await
-            .map_sql_err()?;
+        let rows = sqlx::query(&format!(
+            "{ROUTING_GROUP_SELECT} ORDER BY enabled DESC, sort_order ASC, name ASC, id ASC"
+        ))
+        .fetch_all(&self.pool)
+        .await
+        .map_sql_err()?;
         rows.iter().map(map_group_row).collect()
     }
 
@@ -173,10 +176,10 @@ impl RoutingGroupWriteRepository for MysqlRoutingGroupRepository {
         sqlx::query(
             r#"
 INSERT INTO routing_groups (
-  id, name, description, enabled, is_system_default, config_json,
+  id, name, description, enabled, is_system_default, sort_order, config_json,
   version, created_at, updated_at, published_at
 )
-VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
 "#,
         )
         .bind(&group.id)
@@ -184,6 +187,7 @@ VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
         .bind(&group.description)
         .bind(group.enabled)
         .bind(group.is_system_default)
+        .bind(group.sort_order)
         .bind(json_to_string(
             &group.config_json,
             "routing_groups.config_json",
@@ -241,6 +245,7 @@ SET name = ?,
     description = ?,
     enabled = ?,
     is_system_default = ?,
+    sort_order = ?,
     config_json = ?,
     version = ?,
     updated_at = ?,
@@ -252,6 +257,7 @@ WHERE id = ?
         .bind(&group.description)
         .bind(group.enabled)
         .bind(group.is_system_default)
+        .bind(group.sort_order)
         .bind(json_to_string(
             &group.config_json,
             "routing_groups.config_json",
@@ -460,6 +466,7 @@ fn map_group_row(row: &MySqlRow) -> Result<StoredRoutingGroup, DataLayerError> {
         description: row.try_get("description").map_sql_err()?,
         enabled: row.try_get("enabled").map_sql_err()?,
         is_system_default: row.try_get("is_system_default").map_sql_err()?,
+        sort_order: row.try_get("sort_order").map_sql_err()?,
         config_json: json_from_string(
             row.try_get("config_json").map_sql_err()?,
             "routing_groups.config_json",

crates/aether-data/adapters/postgres/migrations/20260528010000_repair_missing_routing_profiles.sql

@@ -79,4 +79,4 @@ BEGIN
     END IF;
 END $$;
 CREATE INDEX IF NOT EXISTS routing_group_versions_group_id_idx
-    ON public.routing_group_versions USING btree (group_id);
+    ON public.routing_group_versions USING btree (group_id);

crates/aether-data/adapters/postgres/migrations/20260903000000_add_routing_group_sort_order.sql

@@ -0,0 +1,5 @@
+ALTER TABLE public.routing_groups
+    ADD COLUMN sort_order bigint NOT NULL DEFAULT 0;
+
+CREATE INDEX IF NOT EXISTS routing_groups_enabled_sort_idx
+    ON public.routing_groups (enabled DESC, sort_order, name, id);

crates/aether-data/adapters/postgres/src/routing_profiles.rs

@@ -22,6 +22,7 @@ SELECT
   description,
   enabled,
   is_system_default,
+  sort_order,
   config_json,
   version,
   created_at,
@@ -68,7 +69,9 @@ impl PostgresRoutingGroupRepository {
 #[async_trait]
 impl RoutingGroupReadRepository for PostgresRoutingGroupRepository {
     async fn list_routing_groups(&self) -> Result<Vec<StoredRoutingGroup>, DataLayerError> {
-        let sql = format!("{ROUTING_GROUP_SELECT} ORDER BY name ASC, id ASC");
+        let sql = format!(
+            "{ROUTING_GROUP_SELECT} ORDER BY enabled DESC, sort_order ASC, name ASC, id ASC"
+        );
         let mut rows = sqlx::query(&sql).fetch(&self.pool);
         let mut groups = Vec::new();
         while let Some(row) = rows.try_next().await.map_postgres_err()? {
@@ -178,10 +181,10 @@ impl RoutingGroupWriteRepository for PostgresRoutingGroupRepository {
         sqlx::query(
             r#"
 INSERT INTO routing_groups (
-  id, name, description, enabled, is_system_default, config_json,
+  id, name, description, enabled, is_system_default, sort_order, config_json,
   version, created_at, updated_at, published_at
 )
-VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10)
+VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10, $11)
 "#,
         )
         .bind(&group.id)
@@ -189,6 +192,7 @@ VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10)
         .bind(&group.description)
         .bind(group.enabled)
         .bind(group.is_system_default)
+        .bind(group.sort_order)
         .bind(&group.config_json)
         .bind(group.version)
         .bind(group.created_at)
@@ -238,10 +242,11 @@ SET name = $2,
     description = $3,
     enabled = $4,
     is_system_default = $5,
-    config_json = $6,
-    version = $7,
-    updated_at = $8,
-    published_at = $9
+    sort_order = $6,
+    config_json = $7,
+    version = $8,
+    updated_at = $9,
+    published_at = $10
 WHERE id = $1
 "#,
         )
@@ -250,6 +255,7 @@ WHERE id = $1
         .bind(&group.description)
         .bind(group.enabled)
         .bind(group.is_system_default)
+        .bind(group.sort_order)
         .bind(&group.config_json)
         .bind(group.version)
         .bind(group.updated_at)
@@ -441,6 +447,7 @@ fn map_group_row(row: &PgRow) -> Result<StoredRoutingGroup, DataLayerError> {
         description: row.try_get("description").map_postgres_err()?,
         enabled: row.try_get("enabled").map_postgres_err()?,
         is_system_default: row.try_get("is_system_default").map_postgres_err()?,
+        sort_order: row.try_get("sort_order").map_postgres_err()?,
         config_json: row.try_get("config_json").map_postgres_err()?,
         version: row.try_get("version").map_postgres_err()?,
         created_at: row.try_get("created_at").map_postgres_err()?,

crates/aether-data/adapters/sqlite/migrations/20260903000000_add_routing_group_sort_order.sql

@@ -0,0 +1,4 @@
+ALTER TABLE routing_groups ADD COLUMN sort_order INTEGER NOT NULL DEFAULT 0;
+
+CREATE INDEX IF NOT EXISTS routing_groups_enabled_sort_idx
+    ON routing_groups (enabled, sort_order, name, id);

crates/aether-data/adapters/sqlite/src/routing_profiles.rs

@@ -15,6 +15,7 @@ SELECT
   description,
   enabled,
   is_system_default,
+  sort_order,
   config_json,
   version,
   created_at,
@@ -61,10 +62,12 @@ impl SqliteRoutingGroupRepository {
 #[async_trait]
 impl RoutingGroupReadRepository for SqliteRoutingGroupRepository {
     async fn list_routing_groups(&self) -> Result<Vec<StoredRoutingGroup>, DataLayerError> {
-        let rows = sqlx::query(&format!("{ROUTING_GROUP_SELECT} ORDER BY name ASC, id ASC"))
-            .fetch_all(&self.pool)
-            .await
-            .map_sql_err()?;
+        let rows = sqlx::query(&format!(
+            "{ROUTING_GROUP_SELECT} ORDER BY enabled DESC, sort_order ASC, name ASC, id ASC"
+        ))
+        .fetch_all(&self.pool)
+        .await
+        .map_sql_err()?;
         rows.iter().map(map_group_row).collect()
     }
 
@@ -168,10 +171,10 @@ impl RoutingGroupWriteRepository for SqliteRoutingGroupRepository {
         sqlx::query(
             r#"
 INSERT INTO routing_groups (
-  id, name, description, enabled, is_system_default, config_json,
+  id, name, description, enabled, is_system_default, sort_order, config_json,
   version, created_at, updated_at, published_at
 )
-VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
 "#,
         )
         .bind(&group.id)
@@ -179,6 +182,7 @@ VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
         .bind(&group.description)
         .bind(group.enabled)
         .bind(group.is_system_default)
+        .bind(group.sort_order)
         .bind(json_to_string(
             &group.config_json,
             "routing_groups.config_json",
@@ -229,6 +233,7 @@ SET name = ?,
     description = ?,
     enabled = ?,
     is_system_default = ?,
+    sort_order = ?,
     config_json = ?,
     version = ?,
     updated_at = ?,
@@ -240,6 +245,7 @@ WHERE id = ?
         .bind(&group.description)
         .bind(group.enabled)
         .bind(group.is_system_default)
+        .bind(group.sort_order)
         .bind(json_to_string(
             &group.config_json,
             "routing_groups.config_json",
@@ -438,6 +444,7 @@ fn map_group_row(row: &SqliteRow) -> Result<StoredRoutingGroup, DataLayerError>
         description: row.try_get("description").map_sql_err()?,
         enabled: row.try_get("enabled").map_sql_err()?,
         is_system_default: row.try_get("is_system_default").map_sql_err()?,
+        sort_order: row.try_get("sort_order").map_sql_err()?,
         config_json: json_from_string(
             row.try_get("config_json").map_sql_err()?,
             "routing_groups.config_json",
@@ -514,6 +521,7 @@ mod tests {
                 description: Some("initial".to_string()),
                 enabled: true,
                 is_system_default: true,
+                sort_order: 0,
                 config_json: json!({"allowed_models": ["gpt-*"]}),
                 version: 1,
                 created_at: 10,
@@ -790,6 +798,7 @@ SET is_default = 1,
             description: None,
             enabled: true,
             is_system_default,
+            sort_order: 0,
             config_json: json!({}),
             version: 1,
             created_at: 1,

crates/aether-data/contracts/src/repository/routing_profiles/types.rs

@@ -10,6 +10,9 @@ pub struct StoredRoutingGroup {
     pub description: Option<String>,
     pub enabled: bool,
     pub is_system_default: bool,
+    /// Stable administrator-defined display order. This is intentionally not
+    /// consulted by request routing or candidate selection.
+    pub sort_order: i64,
     pub config_json: Value,
     pub version: i64,
     pub created_at: i64,
@@ -28,6 +31,7 @@ impl StoredRoutingGroup {
             description: record.description,
             enabled: record.enabled,
             is_system_default: record.is_system_default,
+            sort_order: record.sort_order.max(0),
             config_json: record.config_json,
             version: record.version.max(1),
             created_at: record.created_at,
@@ -44,6 +48,7 @@ pub struct CreateRoutingGroupRecord {
     pub description: Option<String>,
     pub enabled: bool,
     pub is_system_default: bool,
+    pub sort_order: i64,
     pub config_json: Value,
     pub version: i64,
     pub created_at: i64,
@@ -57,6 +62,7 @@ pub struct UpdateRoutingGroupRecord {
     pub description: Option<Option<String>>,
     pub enabled: Option<bool>,
     pub is_system_default: Option<bool>,
+    pub sort_order: Option<i64>,
     pub config_json: Option<Value>,
     pub version: Option<i64>,
     pub updated_at: i64,
@@ -255,6 +261,9 @@ pub fn apply_group_patch(
     if let Some(is_system_default) = patch.is_system_default {
         group.is_system_default = is_system_default;
     }
+    if let Some(sort_order) = patch.sort_order {
+        group.sort_order = sort_order.max(0);
+    }
     if let Some(config_json) = patch.config_json {
         if !config_json.is_object() {
             return Err(crate::DataLayerError::InvalidInput(

crates/aether-data/runtime/schema/bootstrap/postgres/160_routing_profiles.sql

@@ -4,6 +4,7 @@ CREATE TABLE IF NOT EXISTS public.routing_groups (
     description text,
     enabled boolean DEFAULT true NOT NULL,
     is_system_default boolean DEFAULT false NOT NULL,
+    sort_order bigint DEFAULT 0 NOT NULL,
     config_json jsonb NOT NULL,
     version bigint DEFAULT 1 NOT NULL,
     created_at bigint NOT NULL,
@@ -31,6 +32,8 @@ CREATE INDEX IF NOT EXISTS routing_groups_system_default_idx
 CREATE UNIQUE INDEX IF NOT EXISTS routing_groups_one_system_default_key
     ON public.routing_groups (is_system_default)
     WHERE is_system_default = TRUE;
+CREATE INDEX IF NOT EXISTS routing_groups_enabled_sort_idx
+    ON public.routing_groups (enabled DESC, sort_order, name, id);
 
 CREATE TABLE IF NOT EXISTS public.routing_group_bindings (
     id character varying(64) NOT NULL,
@@ -85,4 +88,4 @@ BEGIN
     END IF;
 END $$;
 CREATE INDEX IF NOT EXISTS routing_group_versions_group_id_idx
-    ON public.routing_group_versions USING btree (group_id);
+    ON public.routing_group_versions USING btree (group_id);

crates/aether-data/runtime/schema/generated/mysql/baseline/002_provider_catalog.sql

@@ -391,6 +391,7 @@ CREATE TABLE IF NOT EXISTS routing_groups (
     `description` LONGTEXT,
     `enabled` TINYINT(1) NOT NULL DEFAULT 1,
     `is_system_default` TINYINT(1) NOT NULL DEFAULT 0,
+    `sort_order` BIGINT NOT NULL DEFAULT 0,
     `config_json` JSON NOT NULL,
     `version` BIGINT NOT NULL DEFAULT 1,
     `created_at` BIGINT NOT NULL,
@@ -398,7 +399,8 @@ CREATE TABLE IF NOT EXISTS routing_groups (
     `published_at` BIGINT,
     PRIMARY KEY (`id`),
     UNIQUE KEY routing_groups_name_key (`name`),
-    KEY routing_groups_system_default_idx (`is_system_default`, `enabled`)
+    KEY routing_groups_system_default_idx (`is_system_default`, `enabled`),
+    KEY routing_groups_enabled_sort_idx (`enabled`, `sort_order`, `name`, `id`)
 );
 
 CREATE TABLE IF NOT EXISTS routing_group_bindings (

crates/aether-data/runtime/schema/generated/postgres/baseline/002_provider_catalog.sql

@@ -404,6 +404,7 @@ CREATE TABLE IF NOT EXISTS public.routing_groups (
     description text,
     enabled boolean DEFAULT true NOT NULL,
     is_system_default boolean DEFAULT false NOT NULL,
+    sort_order bigint DEFAULT 0 NOT NULL,
     config_json jsonb NOT NULL,
     version bigint DEFAULT 1 NOT NULL,
     created_at bigint NOT NULL,
@@ -414,6 +415,7 @@ CREATE TABLE IF NOT EXISTS public.routing_groups (
 ALTER TABLE ONLY public.routing_groups ADD CONSTRAINT routing_groups_pkey PRIMARY KEY (id);
 ALTER TABLE ONLY public.routing_groups ADD CONSTRAINT routing_groups_name_key UNIQUE (name);
 CREATE INDEX IF NOT EXISTS routing_groups_system_default_idx ON public.routing_groups USING btree (is_system_default, enabled);
+CREATE INDEX IF NOT EXISTS routing_groups_enabled_sort_idx ON public.routing_groups USING btree (enabled, sort_order, name, id);
 
 CREATE TABLE IF NOT EXISTS public.routing_group_bindings (
     id character varying(64) NOT NULL,

crates/aether-data/runtime/schema/generated/sqlite/baseline/002_provider_catalog.sql

@@ -378,6 +378,7 @@ CREATE TABLE IF NOT EXISTS routing_groups (
     description TEXT,
     enabled INTEGER NOT NULL DEFAULT 1,
     is_system_default INTEGER NOT NULL DEFAULT 0,
+    sort_order INTEGER NOT NULL DEFAULT 0,
     config_json TEXT NOT NULL,
     version INTEGER NOT NULL DEFAULT 1,
     created_at INTEGER NOT NULL,
@@ -386,6 +387,7 @@ CREATE TABLE IF NOT EXISTS routing_groups (
     UNIQUE (name)
 );
 CREATE INDEX IF NOT EXISTS routing_groups_system_default_idx ON routing_groups (is_system_default, enabled);
+CREATE INDEX IF NOT EXISTS routing_groups_enabled_sort_idx ON routing_groups (enabled, sort_order, name, id);
 
 CREATE TABLE IF NOT EXISTS routing_group_bindings (
     id TEXT PRIMARY KEY NOT NULL,

crates/aether-data/runtime/schema/logical/002_provider_catalog.toml

@@ -1733,6 +1733,11 @@ name = "is_system_default"
 type = "bool"
 default = false
 
+[[table.routing_groups.columns]]
+name = "sort_order"
+type = "int64"
+default = 0
+
 [[table.routing_groups.columns]]
 name = "config_json"
 type = "json"
@@ -1763,6 +1768,10 @@ columns = ["name"]
 name = "routing_groups_system_default_idx"
 columns = ["is_system_default", "enabled"]
 
+[[table.routing_groups.indexes]]
+name = "routing_groups_enabled_sort_idx"
+columns = ["enabled", "sort_order", "name", "id"]
+
 [table.routing_group_bindings]
 domain = "provider_catalog"
 order = 111

crates/aether-data/runtime/src/lifecycle/backfill/mysql.rs

@@ -2,7 +2,7 @@ use std::collections::{HashMap, HashSet};
 
 use sqlx::{
     migrate::{Migrate, MigrateError, Migrator},
-    query, Connection, MySqlConnection, Row,
+    query, query_scalar, Connection, MySqlConnection, Row,
 };
 use tracing::{error, info, warn};
 
@@ -11,6 +11,7 @@ use crate::driver::mysql::MysqlPool;
 
 static BACKFILL_MIGRATOR: Migrator = sqlx::migrate!("./backfills/mysql");
 
+const SCHEMA_BACKFILLS_TABLE_EXISTS_SQL: &str = "SELECT COUNT(*) FROM information_schema.tables WHERE table_schema = DATABASE() AND table_name = 'schema_backfills'";
 const ENSURE_SCHEMA_BACKFILLS_TABLE_SQL: &str = r#"
 CREATE TABLE IF NOT EXISTS schema_backfills (
     version BIGINT NOT NULL,
@@ -161,12 +162,21 @@ async fn run_backfills_locked(conn: &mut MySqlConnection) -> Result<(), MigrateE
 async fn pending_backfills_locked(
     conn: &mut MySqlConnection,
 ) -> Result<Vec<PendingBackfillInfo>, MigrateError> {
-    ensure_schema_backfills_table(conn).await?;
+    if !schema_backfills_table_exists(conn).await? {
+        return Ok(pending_backfills_from_applied(&[]));
+    }
     let applied_backfills = list_applied_backfills(conn).await?;
     validate_applied_backfills(&applied_backfills)?;
     Ok(pending_backfills_from_applied(&applied_backfills))
 }
 
+async fn schema_backfills_table_exists(conn: &mut MySqlConnection) -> Result<bool, MigrateError> {
+    let total: i64 = query_scalar(SCHEMA_BACKFILLS_TABLE_EXISTS_SQL)
+        .fetch_one(&mut *conn)
+        .await?;
+    Ok(total > 0)
+}
+
 async fn ensure_schema_backfills_table(conn: &mut MySqlConnection) -> Result<(), MigrateError> {
     query(ENSURE_SCHEMA_BACKFILLS_TABLE_SQL)
         .execute(&mut *conn)

crates/aether-data/runtime/src/lifecycle/backfill/postgres.rs

@@ -157,17 +157,23 @@ async fn run_backfills_locked(conn: &mut PgConnection) -> Result<(), MigrateErro
 async fn pending_backfills_locked(
     conn: &mut PgConnection,
 ) -> Result<Vec<PendingBackfillInfo>, MigrateError> {
-    ensure_schema_backfills_table(conn).await?;
+    if !schema_backfills_table_exists(conn).await? {
+        return Ok(pending_backfills_from_applied(&[]));
+    }
     let applied_backfills = list_applied_backfills(conn).await?;
     validate_applied_backfills(&applied_backfills)?;
     Ok(pending_backfills_from_applied(&applied_backfills))
 }
 
-async fn ensure_schema_backfills_table(conn: &mut PgConnection) -> Result<(), MigrateError> {
-    let exists: bool = query_scalar(SCHEMA_BACKFILLS_TABLE_EXISTS_SQL)
+async fn schema_backfills_table_exists(conn: &mut PgConnection) -> Result<bool, MigrateError> {
+    query_scalar(SCHEMA_BACKFILLS_TABLE_EXISTS_SQL)
         .fetch_one(&mut *conn)
-        .await?;
-    if exists {
+        .await
+        .map_err(Into::into)
+}
+
+async fn ensure_schema_backfills_table(conn: &mut PgConnection) -> Result<(), MigrateError> {
+    if schema_backfills_table_exists(conn).await? {
         return Ok(());
     }
     query(ENSURE_SCHEMA_BACKFILLS_TABLE_SQL)

crates/aether-data/runtime/src/lifecycle/backfill/sqlite.rs

@@ -2,7 +2,7 @@ use std::collections::{HashMap, HashSet};
 
 use sqlx::{
     migrate::{Migrate, MigrateError, Migrator},
-    query, Connection, Row, SqliteConnection,
+    query, query_scalar, Connection, Row, SqliteConnection,
 };
 use tracing::{error, info, warn};
 
@@ -11,6 +11,8 @@ use crate::driver::sqlite::SqlitePool;
 
 static BACKFILL_MIGRATOR: Migrator = sqlx::migrate!("./backfills/sqlite");
 
+const SCHEMA_BACKFILLS_TABLE_EXISTS_SQL: &str =
+    "SELECT COUNT(*) FROM sqlite_master WHERE type = 'table' AND name = 'schema_backfills'";
 const ENSURE_SCHEMA_BACKFILLS_TABLE_SQL: &str = r#"
 CREATE TABLE IF NOT EXISTS schema_backfills (
     version INTEGER NOT NULL PRIMARY KEY,
@@ -162,12 +164,21 @@ async fn run_backfills_locked(conn: &mut SqliteConnection) -> Result<(), Migrate
 async fn pending_backfills_locked(
     conn: &mut SqliteConnection,
 ) -> Result<Vec<PendingBackfillInfo>, MigrateError> {
-    ensure_schema_backfills_table(conn).await?;
+    if !schema_backfills_table_exists(conn).await? {
+        return Ok(pending_backfills_from_applied(&[]));
+    }
     let applied_backfills = list_applied_backfills(conn).await?;
     validate_applied_backfills(&applied_backfills)?;
     Ok(pending_backfills_from_applied(&applied_backfills))
 }
 
+async fn schema_backfills_table_exists(conn: &mut SqliteConnection) -> Result<bool, MigrateError> {
+    let total: i64 = query_scalar(SCHEMA_BACKFILLS_TABLE_EXISTS_SQL)
+        .fetch_one(&mut *conn)
+        .await?;
+    Ok(total > 0)
+}
+
 async fn ensure_schema_backfills_table(conn: &mut SqliteConnection) -> Result<(), MigrateError> {
     query(ENSURE_SCHEMA_BACKFILLS_TABLE_SQL)
         .execute(&mut *conn)

crates/aether-data/runtime/src/lifecycle/backfill/tests.rs

@@ -310,6 +310,31 @@ INSERT INTO usage_settlement_snapshots (
     }
 }
 
+#[tokio::test]
+async fn pending_sqlite_backfills_does_not_create_tracking_table() {
+    let pool = sqlx::sqlite::SqlitePoolOptions::new()
+        .max_connections(1)
+        .connect("sqlite::memory:")
+        .await
+        .expect("sqlite backfill status pool should connect");
+    run_sqlite_migrations(&pool)
+        .await
+        .expect("sqlite schema should migrate");
+
+    let pending = pending_sqlite_backfills(&pool)
+        .await
+        .expect("sqlite pending backfills should load");
+    assert!(!pending.is_empty());
+
+    let tracking_tables: i64 = query_scalar(
+        "SELECT COUNT(*) FROM sqlite_master WHERE type = 'table' AND name = 'schema_backfills'",
+    )
+    .fetch_one(&pool)
+    .await
+    .expect("sqlite tracking table state should load");
+    assert_eq!(tracking_tables, 0);
+}
+
 #[tokio::test]
 async fn sqlite_backfills_apply_portable_repairs_and_record_versions() {
     let pool = sqlx::sqlite::SqlitePoolOptions::new()

crates/aether-data/runtime/src/lifecycle/bootstrap/postgres.rs

@@ -7,7 +7,7 @@ use tracing::info;
 // Generated by build.rs from schema/bootstrap/postgres.
 pub(crate) static EMPTY_DATABASE_SNAPSHOT_SQL: &str =
     include_str!(concat!(env!("OUT_DIR"), "/empty_database_snapshot.sql"));
-pub(crate) const EMPTY_DATABASE_SNAPSHOT_CUTOFF_VERSION: i64 = 20260821000000;
+pub(crate) const EMPTY_DATABASE_SNAPSHOT_CUTOFF_VERSION: i64 = 20260903000000;
 
 const PUBLIC_BASE_TABLE_COUNT_SQL: &str = r#"
 SELECT COUNT(*)::BIGINT

crates/aether-data/runtime/src/lifecycle/migrate/tests.rs

@@ -412,6 +412,7 @@ fn empty_database_snapshot_covers_current_cutoff_versions() {
             20260727000000,
             20260731000000,
             20260821000000,
+            20260903000000,
         ]
     );
 }
@@ -1066,6 +1067,7 @@ fn mysql_and_sqlite_migrations_include_enabled_incrementals() {
             20260727000000,
             20260731000000,
             20260821000000,
+            20260903000000,
         ]
     );
     assert_eq!(
@@ -1101,6 +1103,7 @@ fn mysql_and_sqlite_migrations_include_enabled_incrementals() {
             20260727000000,
             20260731000000,
             20260821000000,
+            20260903000000,
         ]
     );
 }
@@ -2208,6 +2211,7 @@ fn pending_migrations_from_applied_skips_versions_already_applied() {
             20260727000000,
             20260731000000,
             20260821000000,
+            20260903000000,
         ]
     );
 }

crates/aether-data/runtime/src/repository/routing_profiles/memory.rs

@@ -59,7 +59,14 @@ impl RoutingGroupReadRepository for InMemoryRoutingGroupRepository {
             .values()
             .cloned()
             .collect::<Vec<_>>();
-        groups.sort_by(|left, right| left.name.cmp(&right.name).then(left.id.cmp(&right.id)));
+        groups.sort_by(|left, right| {
+            right
+                .enabled
+                .cmp(&left.enabled)
+                .then(left.sort_order.cmp(&right.sort_order))
+                .then(left.name.cmp(&right.name))
+                .then(left.id.cmp(&right.id))
+        });
         Ok(groups)
     }
 
@@ -273,6 +280,7 @@ mod tests {
                 description: None,
                 enabled: true,
                 is_system_default: true,
+                sort_order: 0,
                 config_json: json!({}),
                 version: 1,
                 created_at: 1,
@@ -320,6 +328,49 @@ mod tests {
         );
     }
 
+    #[tokio::test]
+    async fn lists_enabled_groups_first_and_respects_sort_order() {
+        let repository = InMemoryRoutingGroupRepository::default();
+        for (id, enabled, sort_order) in [
+            ("disabled-first", false, 0),
+            ("enabled-second", true, 20),
+            ("enabled-first", true, 10),
+        ] {
+            repository
+                .create_routing_group(CreateRoutingGroupRecord {
+                    id: id.to_string(),
+                    name: id.to_string(),
+                    description: None,
+                    enabled,
+                    is_system_default: false,
+                    sort_order,
+                    config_json: json!({}),
+                    version: 1,
+                    created_at: 1,
+                    updated_at: 1,
+                    published_at: None,
+                })
+                .await
+                .expect("group should store");
+        }
+
+        let ids = repository
+            .list_routing_groups()
+            .await
+            .expect("groups should list")
+            .into_iter()
+            .map(|group| group.id)
+            .collect::<Vec<_>>();
+        assert_eq!(
+            ids,
+            vec![
+                "enabled-first".to_string(),
+                "enabled-second".to_string(),
+                "disabled-first".to_string(),
+            ]
+        );
+    }
+
     #[tokio::test]
     async fn keeps_system_and_subject_defaults_unique() {
         let repository = InMemoryRoutingGroupRepository::default();
@@ -414,6 +465,7 @@ mod tests {
             description: None,
             enabled: true,
             is_system_default,
+            sort_order: 0,
             config_json: json!({}),
             version: 1,
             created_at: 1,

crates/aether-routing-core/src/lib.rs

@@ -13,9 +13,9 @@ pub use actions::{
 };
 pub use conditions::{RoutingCondition, RoutingConditionContext, RoutingConditionOp};
 pub use model::{
-    RoutingDefaultPolicy, RoutingGroupBinding, RoutingGroupBindingSubject, RoutingGroupConfig,
-    RoutingGroupRecord, RoutingGroupVersionRecord, RoutingModelPolicy, RoutingPoolPolicyOverride,
-    RoutingRule, RoutingSchedulingPreset, DEFAULT_STICKY_KEY_ATTEMPTS,
+    RoutingDefaultPolicy, RoutingExecutionPolicy, RoutingGroupBinding, RoutingGroupBindingSubject,
+    RoutingGroupConfig, RoutingGroupRecord, RoutingGroupVersionRecord, RoutingModelPolicy,
+    RoutingPoolPolicyOverride, RoutingRule, RoutingSchedulingPreset, DEFAULT_STICKY_KEY_ATTEMPTS,
 };
 pub use mutations::{
     apply_json_patch_operations, validate_header_patch, validate_json_patch_operations,

crates/aether-routing-core/src/model.rs

@@ -27,6 +27,47 @@ pub struct RoutingPoolPolicyOverride {
 /// failing over: one retry on the same key.
 pub const DEFAULT_STICKY_KEY_ATTEMPTS: u32 = 2;
 
+/// Request-independent execution behaviours selected by a routing strategy.
+///
+/// These flags deliberately live beside scheduling rather than in provider
+/// transport configuration. A resolved policy is snapshotted for the request
+/// and can therefore be consumed by execution without rereading mutable
+/// system settings.
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Default)]
+pub struct RoutingExecutionPolicy {
+    #[serde(default, skip_serializing_if = "is_false")]
+    pub enable_cf_heartbeat: bool,
+    #[serde(default, skip_serializing_if = "is_false")]
+    pub cyber_continue_failover: bool,
+}
+
+impl<'de> Deserialize<'de> for RoutingExecutionPolicy {
+    fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
+    where
+        D: serde::Deserializer<'de>,
+    {
+        #[derive(Deserialize, Default)]
+        struct LegacyCompatibleExecutionPolicy {
+            #[serde(default)]
+            enable_cf_heartbeat: bool,
+            #[serde(default)]
+            enable_openai_image_sync_heartbeat: bool,
+            #[serde(default)]
+            enable_standard_text_sync_heartbeat: bool,
+            #[serde(default)]
+            cyber_continue_failover: bool,
+        }
+
+        let value = LegacyCompatibleExecutionPolicy::deserialize(deserializer)?;
+        Ok(Self {
+            enable_cf_heartbeat: value.enable_cf_heartbeat
+                || value.enable_openai_image_sync_heartbeat
+                || value.enable_standard_text_sync_heartbeat,
+            cyber_continue_failover: value.cyber_continue_failover,
+        })
+    }
+}
+
 #[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
 pub struct RoutingDefaultPolicy {
     #[serde(default)]
@@ -40,6 +81,10 @@ pub struct RoutingDefaultPolicy {
     /// `0` and `1` both mean no same-key retry.
     #[serde(default = "default_sticky_key_attempts")]
     pub sticky_key_attempts: u32,
+    /// Strategy-scoped execution behaviour. Flattened for a stable JSON
+    /// shape and backwards-compatible migration from system settings.
+    #[serde(flatten)]
+    pub execution_policy: RoutingExecutionPolicy,
 }
 
 impl Default for RoutingDefaultPolicy {
@@ -49,6 +94,7 @@ impl Default for RoutingDefaultPolicy {
             scheduling_mode: RoutingSchedulingMode::default(),
             keep_priority_on_conversion: false,
             sticky_key_attempts: DEFAULT_STICKY_KEY_ATTEMPTS,
+            execution_policy: RoutingExecutionPolicy::default(),
         }
     }
 }
@@ -57,6 +103,10 @@ fn default_sticky_key_attempts() -> u32 {
     DEFAULT_STICKY_KEY_ATTEMPTS
 }
 
+fn is_false(value: &bool) -> bool {
+    !*value
+}
+
 #[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
 pub struct RoutingModelPolicy {
     pub model: String,
@@ -100,8 +150,8 @@ pub struct RoutingRule {
 
 #[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
 pub struct RoutingGroupConfig {
-    #[serde(default)]
-    pub allowed_models: Vec<String>,
+    /// The default policy is global for the selected strategy group. Model
+    /// differences are expressed through `model_policies` and `rules`.
     #[serde(default)]
     pub default_policy: RoutingDefaultPolicy,
     #[serde(default)]

crates/aether-routing-core/src/policy.rs

@@ -8,7 +8,9 @@ use crate::actions::{
     RoutingAction, RoutingRulePhase, RoutingSchedulingMode, RoutingSetPriorityMode,
 };
 use crate::conditions::RoutingConditionContext;
-use crate::model::{RoutingGroupConfig, RoutingModelPolicy, RoutingPoolPolicyOverride};
+use crate::model::{
+    RoutingExecutionPolicy, RoutingGroupConfig, RoutingModelPolicy, RoutingPoolPolicyOverride,
+};
 use crate::mutations::{validate_header_patch, validate_json_patch_operations, MutationPlan};
 use crate::ranking::RankingOverlay;
 use crate::validation::validate_routing_group_config;
@@ -17,7 +19,7 @@ use crate::validation::validate_routing_group_config;
 pub enum RoutingPolicyError {
     #[error("routing group config is invalid: {0}")]
     InvalidConfig(String),
-    #[error("model is not allowed by routing group: {0}")]
+    #[error("model is not allowed by routing rule: {0}")]
     ModelNotAllowed(String),
     #[error("mutation action is invalid: {0}")]
     InvalidMutation(String),
@@ -60,6 +62,8 @@ pub struct ResolvedRoutingPolicy {
     /// See `RoutingDefaultPolicy::sticky_key_attempts`.
     #[serde(default = "default_sticky_key_attempts")]
     pub sticky_key_attempts: u32,
+    #[serde(flatten)]
+    pub execution_policy: RoutingExecutionPolicy,
     pub ranking_overlay: RankingOverlay,
     pub mutation_plan: MutationPlan,
     #[serde(default)]
@@ -75,14 +79,6 @@ pub fn resolve_routing_policy(
     validate_routing_group_config(config)
         .map_err(|error| RoutingPolicyError::InvalidConfig(error.to_string()))?;
 
-    if !model_allowed(&config.allowed_models, input.requested_model)
-        && !model_allowed(&config.allowed_models, input.resolved_model)
-    {
-        return Err(RoutingPolicyError::ModelNotAllowed(
-            input.requested_model.to_string(),
-        ));
-    }
-
     let mut policy = ResolvedRoutingPolicy {
         group_id: input.group_id.map(str::to_string),
         group_version: input.group_version,
@@ -93,6 +89,7 @@ pub fn resolve_routing_policy(
         scheduling_mode: config.default_policy.scheduling_mode,
         keep_priority_on_conversion: config.default_policy.keep_priority_on_conversion,
         sticky_key_attempts: config.default_policy.sticky_key_attempts,
+        execution_policy: config.default_policy.execution_policy,
         ranking_overlay: RankingOverlay::default(),
         mutation_plan: MutationPlan::default(),
         pool_policy_overrides: BTreeMap::new(),
@@ -322,7 +319,6 @@ mod tests {
     #[test]
     fn resolves_model_policy_and_matching_rule() {
         let config = RoutingGroupConfig {
-            allowed_models: vec!["gpt-*".to_string()],
             default_policy: RoutingDefaultPolicy::default(),
             model_policies: vec![RoutingModelPolicy {
                 model: "gpt-5".to_string(),
@@ -389,14 +385,14 @@ mod tests {
     }
 
     #[test]
-    fn empty_allowlist_keeps_default_policy_for_models_without_an_override() {
+    fn default_policy_applies_to_models_without_an_override() {
         let config = RoutingGroupConfig {
-            allowed_models: vec![],
             default_policy: RoutingDefaultPolicy {
                 priority_mode: RoutingSetPriorityMode::GlobalKey,
                 scheduling_mode: RoutingSchedulingMode::LoadBalance,
                 keep_priority_on_conversion: true,
                 sticky_key_attempts: 3,
+                execution_policy: Default::default(),
             },
             model_policies: vec![RoutingModelPolicy {
                 model: "special-model".to_string(),
@@ -471,6 +467,38 @@ mod tests {
             .is_empty());
     }
 
+    #[test]
+    fn legacy_group_model_allowlist_is_ignored() {
+        let config: RoutingGroupConfig = serde_json::from_value(json!({
+            "allowed_models": ["gpt-5"],
+            "default_policy": {
+                "priority_mode": "provider",
+                "scheduling_mode": "cache_affinity"
+            },
+            "model_policies": [],
+            "rules": []
+        }))
+        .expect("legacy routing config should remain readable");
+
+        resolve_routing_policy(
+            &config,
+            RoutingPolicyInput {
+                group_id: Some("group-1"),
+                group_version: Some(1),
+                selection_source: "system_default",
+                requested_model: "claude-sonnet",
+                resolved_model: "claude-sonnet",
+                api_format: "openai:chat",
+                user_id: None,
+                api_key_id: None,
+                headers: &json!({}),
+                body: &json!({}),
+                phase: RoutingRulePhase::ClientRequest,
+            },
+        )
+        .expect("the legacy allowlist must not reject another model");
+    }
+
     #[test]
     fn sticky_key_attempts_defaults_to_two_and_can_be_overridden_by_rule() {
         let default_config = RoutingGroupConfig::default();
@@ -541,41 +569,9 @@ mod tests {
         assert_eq!(policy.sticky_key_attempts, 1);
     }
 
-    #[test]
-    fn rejects_disallowed_model() {
-        let config = RoutingGroupConfig {
-            allowed_models: vec!["gpt-5".to_string()],
-            ..RoutingGroupConfig::default()
-        };
-
-        let err = resolve_routing_policy(
-            &config,
-            RoutingPolicyInput {
-                group_id: None,
-                group_version: None,
-                selection_source: "test",
-                requested_model: "claude",
-                resolved_model: "claude",
-                api_format: "openai:chat",
-                user_id: None,
-                api_key_id: None,
-                headers: &json!({}),
-                body: &json!({}),
-                phase: RoutingRulePhase::ClientRequest,
-            },
-        )
-        .unwrap_err();
-
-        assert_eq!(
-            err,
-            RoutingPolicyError::ModelNotAllowed("claude".to_string())
-        );
-    }
-
     #[test]
     fn restrict_model_action_rejects_matching_request() {
         let config = RoutingGroupConfig {
-            allowed_models: vec!["*".to_string()],
             rules: vec![RoutingRule {
                 id: "restrict".to_string(),
                 priority: 1,

deploy.sh

@@ -228,6 +228,6 @@ docker image prune -f >/dev/null 2>&1 || true
 
 echo ">>> Done!"
 echo ">>> Note: empty databases auto-bootstrap on first start."
-echo ">>> Note: docker compose now defaults to auto-running pending migrations/backfills on app startup."
-echo ">>> Note: set AETHER_GATEWAY_AUTO_PREPARE_DATABASE=false if you want to keep manual rollout."
+echo ">>> Note: database schema and data preparation run automatically before app startup."
+echo ">>> Note: set AETHER_GATEWAY_DATABASE_MODE=verify-only to require a separate database prepare step."
 "${DC[@]}" ps

frontend/src/api/routing-profiles.ts

@@ -13,6 +13,7 @@ export interface RoutingGroupRecord {
   description?: string | null
   enabled: boolean
   is_system_default: boolean
+  sort_order: number
   config_json: RoutingGroupConfig
   version: number
   created_at: number
@@ -61,6 +62,7 @@ export interface RoutingGroupCreateRequest {
   description?: string | null
   enabled?: boolean
   is_system_default?: boolean
+  sort_order?: number
   config_json?: RoutingGroupConfig
 }
 
@@ -69,6 +71,7 @@ export interface RoutingGroupUpdateRequest {
   description?: string | null
   enabled?: boolean
   is_system_default?: boolean
+  sort_order?: number
   config_json?: RoutingGroupConfig
   version?: number
   published_at?: number | null

frontend/src/components/common/HelpHint.vue

@@ -0,0 +1,33 @@
+<script setup lang="ts">
+import { ref } from 'vue'
+import { CircleHelp } from 'lucide-vue-next'
+
+const props = defineProps<{
+  label: string
+  text: string
+}>()
+
+const open = ref(false)
+</script>
+
+<template>
+  <span class="group relative inline-flex">
+    <button
+      type="button"
+      class="inline-flex items-center justify-center rounded-sm p-0.5 text-muted-foreground/60 transition-colors hover:bg-muted/60 hover:text-foreground focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring"
+      :aria-label="`${props.label}说明`"
+      :aria-expanded="open"
+      :title="props.text"
+      @click.stop="open = !open"
+    >
+      <CircleHelp class="h-3.5 w-3.5" />
+    </button>
+    <span
+      role="tooltip"
+      class="pointer-events-none invisible absolute left-1/2 top-full z-[230] mt-2 w-max max-w-xs -translate-x-1/2 rounded-md border bg-popover px-3 py-2 text-xs leading-5 text-popover-foreground opacity-0 shadow-md transition-opacity group-hover:visible group-hover:opacity-100 group-focus-within:visible group-focus-within:opacity-100"
+      :class="open ? 'visible opacity-100' : ''"
+    >
+      {{ props.text }}
+    </span>
+  </span>
+</template>

frontend/src/features/providers/components/ProviderDetailDrawer.vue

@@ -37,6 +37,7 @@
               :provider-proxy-node-name="getProviderProxyNodeName()"
               :saving-provider-proxy="savingProviderProxy"
               @toggle-format-conversion="toggleFormatConversion"
+              @toggle-keep-priority-on-conversion="toggleKeepPriorityOnConversion"
               @open-failover-rules="failoverRulesDialogOpen = true"
               @set-provider-proxy="setProviderProxy"
               @clear-provider-proxy="clearProviderProxy"
@@ -1412,6 +1413,24 @@ async function toggleFormatConversion() {
   }
 }
 
+async function toggleKeepPriorityOnConversion() {
+  if (!provider.value) return
+  const formatConversionAvailable =
+    provider.value.enable_format_conversion || systemFormatConversionEnabled.value
+  if (!formatConversionAvailable) return
+  const newValue = !provider.value.keep_priority_on_conversion
+  try {
+    const updated = await updateProvider(provider.value.id, {
+      keep_priority_on_conversion: newValue,
+    })
+    applyProviderSnapshot(updated)
+    showSuccess(legacyT(newValue ? '已启用格式转换保持优先级' : '已禁用格式转换保持优先级'))
+    emit('refresh')
+  } catch {
+    showError(legacyT('切换格式转换保持优先级失败'))
+  }
+}
+
 function getProviderProxyNodeName(): string {
   const nodeId = provider.value?.proxy?.node_id
   if (!nodeId) return legacyT('未知节点')

frontend/src/features/providers/components/ProviderDetailHeader.vue

@@ -24,6 +24,17 @@
             <Shuffle class="w-4 h-4" />
           </Button>
         </span>
+        <span :title="keepPriorityTitle">
+          <Button
+            variant="ghost"
+            size="icon"
+            :class="provider.keep_priority_on_conversion ? 'text-primary' : ''"
+            :disabled="!formatConversionAvailable"
+            @click="$emit('toggleKeepPriorityOnConversion')"
+          >
+            <Layers class="w-4 h-4" />
+          </Button>
+        </span>
         <span :title="legacyT(hasFailoverRules ? '已配置故障转移规则（点击编辑）' : '配置故障转移规则')">
           <Button
             variant="ghost"
@@ -163,7 +174,7 @@
 
 <script setup lang="ts">
 import { computed } from 'vue'
-import { Edit, GitBranch, Globe, Loader2, Plus, Power, Shuffle, X } from 'lucide-vue-next'
+import { Edit, GitBranch, Globe, Layers, Loader2, Plus, Power, Shuffle, X } from 'lucide-vue-next'
 import Button from '@/components/ui/button.vue'
 import Badge from '@/components/ui/badge.vue'
 import { Popover, PopoverTrigger, PopoverContent } from '@/components/ui'
@@ -185,6 +196,7 @@ const props = defineProps<{
 
 defineEmits<{
   (e: 'toggleFormatConversion'): void
+  (e: 'toggleKeepPriorityOnConversion'): void
   (e: 'openFailoverRules'): void
   (e: 'update:providerProxyPopoverOpen', value: boolean): void
   (e: 'setProviderProxy', value: string): void
@@ -203,4 +215,15 @@ const formatConversionTitle = computed(() => {
   if (props.provider.enable_format_conversion) return legacyT('已启用格式转换（点击关闭）')
   return legacyT('启用格式转换')
 })
+
+const formatConversionAvailable = computed(() => (
+  props.provider.enable_format_conversion || props.systemFormatConversionEnabled
+))
+
+const keepPriorityTitle = computed(() => {
+  if (!formatConversionAvailable.value) return legacyT('请先启用格式转换')
+  return props.provider.keep_priority_on_conversion
+    ? legacyT('已启用格式转换保持优先级（点击关闭）')
+    : legacyT('启用格式转换保持优先级')
+})
 </script>

frontend/src/features/providers/components/ProviderFormDialog.vue

@@ -123,39 +123,11 @@
         </div>
       </div>
 
-      <!-- 计费与限流 / 请求配置 -->
+      <!-- 请求配置 -->
       <div class="space-y-3">
-        <div class="grid grid-cols-2 gap-4">
-          <h3 class="text-sm font-medium border-b pb-2">
-            {{ legacyT('计费与限流') }}
-          </h3>
-          <h3 class="text-sm font-medium border-b pb-2">
-            {{ legacyT('请求配置') }}
-          </h3>
-        </div>
-        <div class="grid grid-cols-2 gap-4">
-          <div class="space-y-1.5">
-            <Label>{{ legacyT('计费类型') }}</Label>
-            <Select
-              v-model="form.billing_type"
-            >
-              <SelectTrigger>
-                <SelectValue />
-              </SelectTrigger>
-              <SelectContent>
-                <SelectItem value="monthly_quota">
-                  {{ legacyT('月卡额度') }}
-                </SelectItem>
-                <SelectItem value="pay_as_you_go">
-                  {{ legacyT('按量付费') }}
-                </SelectItem>
-                <SelectItem value="free_tier">
-                  {{ legacyT('免费套餐') }}
-                </SelectItem>
-              </SelectContent>
-            </Select>
-          </div>
-        </div>
+        <h3 class="text-sm font-medium border-b pb-2">
+          {{ legacyT('请求配置') }}
+        </h3>
 
         <!-- 超时配置 -->
         <div class="grid grid-cols-2 gap-4">
@@ -229,49 +201,6 @@
             />
           </div>
         </div>
-
-        <!-- 月卡配置 -->
-        <div
-          v-if="form.billing_type === 'monthly_quota'"
-          class="grid grid-cols-2 gap-4 p-3 border rounded-lg bg-muted/50"
-        >
-          <div class="space-y-1.5">
-            <Label class="text-xs">{{ legacyT('周期额度 (USD)') }}</Label>
-            <Input
-              :model-value="form.monthly_quota_usd ?? ''"
-              type="number"
-              step="0.01"
-              min="0"
-              @update:model-value="(v) => form.monthly_quota_usd = parseNumberInput(v, { allowFloat: true })"
-            />
-          </div>
-          <div class="space-y-1.5">
-            <Label class="text-xs">{{ legacyT('重置周期 (天)') }}</Label>
-            <Input
-              :model-value="form.quota_reset_day ?? ''"
-              type="number"
-              min="1"
-              max="365"
-              @update:model-value="(v) => form.quota_reset_day = parseNumberInput(v) ?? 30"
-            />
-          </div>
-          <div class="space-y-1.5">
-            <Label class="text-xs">
-              {{ legacyT('周期开始时间') }} <span class="text-red-500">*</span>
-            </Label>
-            <Input
-              v-model="form.quota_last_reset_at"
-              type="datetime-local"
-            />
-          </div>
-          <div class="space-y-1.5">
-            <Label class="text-xs">{{ legacyT('过期时间') }}</Label>
-            <Input
-              v-model="form.quota_expires_at"
-              type="datetime-local"
-            />
-          </div>
-        </div>
       </div>
 
       <!-- 功能开关 -->
@@ -280,19 +209,6 @@
           {{ legacyT('功能开关') }}
         </h3>
 
-        <div class="flex items-center justify-between p-3 border rounded-lg bg-muted/50">
-          <div class="space-y-0.5">
-            <span class="text-sm font-medium">{{ legacyT('格式转换保持优先级') }}</span>
-            <p class="text-xs text-muted-foreground">
-              {{ legacyT('跨格式请求时保持原优先级排名，不降级到格式匹配的提供商之后') }}
-            </p>
-          </div>
-          <Switch
-            :model-value="form.keep_priority_on_conversion"
-            @update:model-value="(v: boolean) => form.keep_priority_on_conversion = v"
-          />
-        </div>
-
         <div class="flex items-center justify-between p-3 border rounded-lg bg-muted/50">
           <div class="space-y-0.5">
             <span class="text-sm font-medium">{{ legacyT('号池调度模式') }}</span>
@@ -426,7 +342,6 @@ import {
 } from '@/api/endpoints'
 import { parseApiError } from '@/utils/errorParser'
 import { parseNumberInput } from '@/utils/form'
-import { dateTimeLocalToRfc3339, formatDateTimeLocalInput } from '@/utils/date'
 
 const props = defineProps<{
   modelValue: boolean
@@ -468,14 +383,7 @@ const form = ref({
   provider_type: 'custom' as ProviderType,
   description: '',
   website: '',
-  // 计费配置
-  billing_type: 'pay_as_you_go' as 'monthly_quota' | 'pay_as_you_go' | 'free_tier',
-  monthly_quota_usd: undefined as number | undefined,
-  quota_reset_day: 30,
-  quota_last_reset_at: '',  // 周期开始时间
-  quota_expires_at: '',
   provider_priority: 100,
-  keep_priority_on_conversion: false,  // 格式转换时是否保持优先级
   // 状态配置
   is_active: true,
   rate_limit: undefined as number | undefined,
@@ -504,13 +412,7 @@ function resetForm() {
     provider_type: 'custom',
     description: '',
     website: '',
-    billing_type: 'pay_as_you_go',
-    monthly_quota_usd: undefined,
-    quota_reset_day: 30,
-    quota_last_reset_at: '',
-    quota_expires_at: '',
     provider_priority: defaultPriority.value,
-    keep_priority_on_conversion: false,
     is_active: true,
     rate_limit: undefined,
     concurrent_limit: undefined,
@@ -542,13 +444,7 @@ function loadProviderData() {
     provider_type: props.provider.provider_type || 'custom',
     description: props.provider.description || '',
     website: props.provider.website || '',
-    billing_type: (props.provider.billing_type as 'monthly_quota' | 'pay_as_you_go' | 'free_tier') || 'pay_as_you_go',
-    monthly_quota_usd: props.provider.monthly_quota_usd || undefined,
-    quota_reset_day: props.provider.quota_reset_day || 30,
-    quota_last_reset_at: formatDateTimeLocalInput(props.provider.quota_last_reset_at),
-    quota_expires_at: formatDateTimeLocalInput(props.provider.quota_expires_at),
     provider_priority: props.provider.provider_priority || 999,
-    keep_priority_on_conversion: props.provider.keep_priority_on_conversion ?? false,
     is_active: props.provider.is_active,
     rate_limit: undefined,
     concurrent_limit: undefined,
@@ -595,23 +491,6 @@ watch(() => form.value.provider_type, () => {
 
 // 提交表单
 const handleSubmit = async () => {
-  // 月卡类型必须设置周期开始时间
-  if (form.value.billing_type === 'monthly_quota' && !form.value.quota_last_reset_at) {
-    showError(legacyT('月卡类型必须设置周期开始时间'), legacyT('验证失败'))
-    return
-  }
-
-  const quotaLastResetAt = dateTimeLocalToRfc3339(form.value.quota_last_reset_at)
-  if (form.value.billing_type === 'monthly_quota' && !quotaLastResetAt) {
-    showError(legacyT('周期开始时间必须是合法时间'), legacyT('验证失败'))
-    return
-  }
-  const quotaExpiresAt = dateTimeLocalToRfc3339(form.value.quota_expires_at)
-  if (form.value.quota_expires_at && !quotaExpiresAt) {
-    showError(legacyT('过期时间必须是合法时间'), legacyT('验证失败'))
-    return
-  }
-
   loading.value = true
   try {
     const currentPoolAdvanced = normalizePoolAdvancedConfig(props.provider?.pool_advanced)
@@ -620,12 +499,6 @@ const handleSubmit = async () => {
       provider_type: form.value.provider_type,
       description: form.value.description || undefined,
       website: form.value.website || undefined,
-      billing_type: form.value.billing_type,
-      monthly_quota_usd: form.value.monthly_quota_usd,
-      quota_reset_day: form.value.quota_reset_day,
-      quota_last_reset_at: quotaLastResetAt,
-      quota_expires_at: quotaExpiresAt,
-      keep_priority_on_conversion: form.value.keep_priority_on_conversion,
       responses_websocket_enabled: form.value.responses_websocket_enabled,
       is_active: form.value.is_active,
       // 请求配置

frontend/src/features/providers/components/ProviderTableHeader.vue

@@ -98,19 +98,6 @@
 
         <div class="hidden sm:block h-4 w-px bg-border" />
 
-        <!-- 调度策略 -->
-        <button
-          class="group inline-flex items-center gap-1.5 px-2.5 h-8 rounded-md border border-border/50 bg-muted/20 hover:bg-muted/40 hover:border-primary/40 transition-all duration-200 text-xs"
-          :title="legacyT('点击调整调度策略')"
-          @click="$emit('openPriorityDialog')"
-        >
-          <span class="text-muted-foreground/80 hidden sm:inline">{{ legacyT('调度:') }}</span>
-          <span class="font-medium text-foreground/90">{{ priorityModeLabel }}</span>
-          <ChevronDown class="w-3 h-3 text-muted-foreground/70 group-hover:text-foreground transition-colors" />
-        </button>
-
-        <div class="hidden sm:block h-4 w-px bg-border" />
-
         <!-- 操作按钮 -->
         <Button
           variant="ghost"
@@ -141,7 +128,7 @@
 </template>
 
 <script setup lang="ts">
-import { Search, Plus, ChevronDown, FilterX, Users } from 'lucide-vue-next'
+import { Search, Plus, FilterX, Users } from 'lucide-vue-next'
 import Button from '@/components/ui/button.vue'
 import Input from '@/components/ui/input.vue'
 import Select from '@/components/ui/select.vue'
@@ -162,7 +149,6 @@ defineProps<{
   apiFormatFilters: FilterOption[]
   modelFilters: FilterOption[]
   hasActiveFilters: boolean
-  priorityModeLabel: string
   loading: boolean
 }>()
 
@@ -172,7 +158,6 @@ defineEmits<{
   'update:filterApiFormat': [value: string]
   'update:filterModel': [value: string]
   'resetFilters': []
-  'openPriorityDialog': []
   'batchProcess': []
   'addProvider': []
   'refresh': []

frontend/src/features/providers/components/__tests__/ProviderFormDialog.transfer-limits.spec.ts

@@ -137,6 +137,36 @@ function clickButton(text: string) {
   button.click()
 }
 
+const billingFieldNames = [
+  'billing_type',
+  'monthly_quota_usd',
+  'quota_reset_day',
+  'quota_last_reset_at',
+  'quota_expires_at',
+] as const
+
+function expectBillingConfigurationHidden() {
+  for (const text of [
+    '计费类型',
+    '月卡额度',
+    '按量付费',
+    '免费套餐',
+    '周期额度 (USD)',
+    '重置周期 (天)',
+    '周期开始时间',
+    '过期时间',
+  ]) {
+    expect(document.body.textContent).not.toContain(text)
+  }
+}
+
+function expectBillingFieldsOmitted(payload: unknown) {
+  expect(payload).toEqual(expect.any(Object))
+  for (const field of billingFieldNames) {
+    expect(payload).not.toHaveProperty(field)
+  }
+}
+
 beforeEach(() => {
   endpointMocks.createProvider.mockReset()
   endpointMocks.createProvider.mockResolvedValue({ id: 'provider-new', name: 'New Provider' })
@@ -226,6 +256,41 @@ describe('ProviderFormDialog transfer limits', () => {
   })
 })
 
+describe('ProviderFormDialog billing configuration', () => {
+  it('hides billing configuration and omits billing fields when creating', async () => {
+    mountDialog(null)
+    await settle()
+
+    expectBillingConfigurationHidden()
+
+    await setInput('#name', 'New Provider')
+    clickButton('创建')
+    await settle()
+
+    expect(endpointMocks.createProvider).toHaveBeenCalledTimes(1)
+    expectBillingFieldsOmitted(endpointMocks.createProvider.mock.calls[0]?.[0])
+  })
+
+  it('hides existing monthly quota configuration and preserves it when editing', async () => {
+    mountDialog(makeProvider({
+      billing_type: 'monthly_quota',
+      monthly_quota_usd: 200,
+      quota_reset_day: 30,
+      quota_last_reset_at: '2026-08-01T00:00:00Z',
+      quota_expires_at: '2026-09-01T00:00:00Z',
+    }))
+    await settle()
+
+    expectBillingConfigurationHidden()
+
+    clickButton('保存')
+    await settle()
+
+    expect(endpointMocks.updateProvider).toHaveBeenCalledTimes(1)
+    expectBillingFieldsOmitted(endpointMocks.updateProvider.mock.calls[0]?.[1])
+  })
+})
+
 describe('ProviderFormDialog provider types', () => {
   it('creates an experimental Claude Code provider from the add dialog', async () => {
     mountDialog(null)

frontend/src/features/providers/components/index.ts

@@ -9,7 +9,6 @@ export { default as EndpointFormDialog } from './EndpointFormDialog.vue'
 export { default as KeyFormDialog } from './KeyFormDialog.vue'
 export { default as KeyAllowedModelsDialog } from './KeyAllowedModelsDialog.vue'
 export { default as KeyAllowedModelsEditDialog } from './KeyAllowedModelsEditDialog.vue'
-export { default as PriorityManagementDialog } from './PriorityManagementDialog.vue'
 export { default as ProviderModelFormDialog } from './ProviderModelFormDialog.vue'
 export { default as ProviderDetailDrawer } from './ProviderDetailDrawer.vue'
 export { default as EndpointHealthTimeline } from './EndpointHealthTimeline.vue'

frontend/src/features/routing/__tests__/routingPolicy.spec.ts

@@ -2,27 +2,17 @@ import { describe, expect, it } from 'vitest'
 
 import {
   DEFAULT_ROUTING_POLICY_MODEL,
-  allowedModelsMirrorPerModelPolicies,
-  clearAllowedModels,
-  copyPerModelRoutingConfig,
   createEmptyModelPolicy,
   createEmptyRoutingGroupConfig,
-  formatAllowedModelsInput,
   getDefaultModelPolicy,
   getModelScheduling,
   modelSchedulingRuleId,
   normalizeRoutingGroupConfig,
   normalizeStickyKeyAttempts,
-  parseAllowedModelsInput,
-  removePerModelRoutingConfig,
   resolveModelKeyPriorityOverride,
-  routingModelScopeLabel,
-  savePerModelRoutingConfig,
   setDefaultPoolPriorityOverrides,
   setDefaultProviderPriorityOverrides,
   setModelKeyPriorityOverridesForFormat,
-  setRoutingSortingScope,
-  updateAllowedModelsFromInput,
   upsertModelSchedulingRule,
   upsertModelPolicy,
 } from '../utils/routingPolicy'
@@ -30,13 +20,18 @@ import { sortCandidateTraces, summarizeRoutingTrace, type RoutingDecisionTrace }
 
 describe('routingPolicy', () => {
   it('normalizes partial configs with stable defaults', () => {
-    const config = normalizeRoutingGroupConfig({
-      allowed_models: ['gpt-5'],
-    })
+    const config = normalizeRoutingGroupConfig({})
 
     expect(config.default_policy.priority_mode).toBe('provider')
     expect(config.default_policy.scheduling_mode).toBe('cache_affinity')
-    expect(config.allowed_models).toEqual(['gpt-5'])
+  })
+
+  it('drops the legacy group model allowlist while normalizing config', () => {
+    const config = normalizeRoutingGroupConfig({
+      allowed_models: ['legacy-model'],
+    } as unknown as Parameters<typeof normalizeRoutingGroupConfig>[0])
+
+    expect(config).not.toHaveProperty('allowed_models')
   })
 
   it('upserts model policies by model name', () => {
@@ -155,115 +150,6 @@ describe('routingPolicy', () => {
       scheduling_mode: 'fixed_order',
     })
   })
-
-  it('updates the model allowlist only through explicit scope controls', () => {
-    const config = normalizeRoutingGroupConfig({
-      allowed_models: ['legacy-model'],
-    })
-
-    expect(parseAllowedModelsInput(' gpt-5\nclaude-*\nlegacy-model\ngpt-5 ')).toEqual([
-      'gpt-5',
-      'claude-*',
-      'legacy-model',
-    ])
-
-    const restricted = updateAllowedModelsFromInput(
-      config,
-      'gpt-5\nclaude-*\nlegacy-model\ngpt-5',
-    )
-    expect(restricted.allowed_models).toEqual(['gpt-5', 'claude-*', 'legacy-model'])
-    expect(formatAllowedModelsInput(restricted.allowed_models)).toBe('gpt-5\nclaude-*\nlegacy-model')
-    expect(routingModelScopeLabel(restricted)).toBe('3 个模型')
-
-    const unrestricted = clearAllowedModels(restricted)
-    expect(unrestricted.allowed_models).toEqual([])
-    expect(routingModelScopeLabel(unrestricted)).toBe('全部模型')
-  })
-
-  it('round-trips selectors containing commas and labels wildcard scope as unrestricted', () => {
-    const selectors = ['vendor,model', 'gpt-*']
-    expect(parseAllowedModelsInput(formatAllowedModelsInput(selectors))).toEqual(selectors)
-
-    const wildcard = normalizeRoutingGroupConfig({ allowed_models: ['gpt-*', '*'] })
-    expect(routingModelScopeLabel(wildcard)).toBe('全部模型')
-  })
-
-  it('preserves historical empty selectors until unrestricted scope is explicit', () => {
-    const legacy = normalizeRoutingGroupConfig({ allowed_models: ['', '  '] })
-
-    expect(updateAllowedModelsFromInput(legacy, '  \n')).toMatchObject({
-      allowed_models: ['', '  '],
-    })
-    expect(clearAllowedModels(legacy).allowed_models).toEqual([])
-  })
-
-  it('preserves an explicit model allowlist across per-model editing actions', () => {
-    const allowlist = ['gpt-*', 'legacy-model']
-    let config = normalizeRoutingGroupConfig({
-      allowed_models: allowlist,
-      model_policies: [{
-        ...createEmptyModelPolicy('special-model'),
-        allowed_providers: ['provider-special'],
-      }],
-    })
-    config = upsertModelSchedulingRule(config, 'special-model', {
-      priority_mode: 'global_key',
-      scheduling_mode: 'fixed_order',
-    })
-
-    const perModel = setRoutingSortingScope(config, 'per_model')
-    expect(perModel.allowed_models).toEqual(allowlist)
-    expect(getModelScheduling(perModel, 'special-model')).toMatchObject({
-      priority_mode: 'global_key',
-      scheduling_mode: 'fixed_order',
-    })
-
-    const saved = savePerModelRoutingConfig(perModel, 'new-special-model')
-    expect(saved.allowed_models).toEqual(allowlist)
-    expect(saved.model_policies.map(policy => policy.model)).toContain('new-special-model')
-
-    const copied = copyPerModelRoutingConfig(
-      saved,
-      saved,
-      'special-model',
-      'copied-special-model',
-    )
-    expect(copied.allowed_models).toEqual(allowlist)
-    expect(copied.model_policies.find(policy => policy.model === 'copied-special-model'))
-      .toMatchObject({ allowed_providers: ['provider-special'] })
-    expect(getModelScheduling(copied, 'copied-special-model')).toMatchObject({
-      priority_mode: 'global_key',
-      scheduling_mode: 'fixed_order',
-    })
-
-    const removed = removePerModelRoutingConfig(copied, 'special-model')
-    expect(removed.allowed_models).toEqual(allowlist)
-    expect(removed.model_policies.map(policy => policy.model)).not.toContain('special-model')
-    expect(removed.rules.map(rule => rule.id)).not.toContain(modelSchedulingRuleId('special-model'))
-
-    const unified = setRoutingSortingScope(removed, 'unified')
-    expect(unified.allowed_models).toEqual(allowlist)
-    expect(unified.model_policies.filter(policy => policy.model !== DEFAULT_ROUTING_POLICY_MODEL))
-      .toEqual([])
-    expect(unified.rules.some(rule => rule.id.startsWith('ui_model_scheduling:'))).toBe(false)
-  })
-
-  it('recognizes legacy allowlist mirrors without mutating historical values', () => {
-    const config = normalizeRoutingGroupConfig({
-      allowed_models: [' model-b ', 'model-a', 'model-a'],
-      model_policies: [
-        createEmptyModelPolicy('model-a'),
-        createEmptyModelPolicy('model-b'),
-      ],
-    })
-
-    expect(allowedModelsMirrorPerModelPolicies(config)).toBe(true)
-    expect(config.allowed_models).toEqual([' model-b ', 'model-a', 'model-a'])
-    expect(allowedModelsMirrorPerModelPolicies({
-      ...config,
-      allowed_models: ['model-*'],
-    })).toBe(false)
-  })
 })
 
 describe('routingTrace', () => {

frontend/src/features/routing/components/RoutingGroupEditor.vue

@@ -1,16 +1,5 @@
 <template>
   <section class="space-y-4">
-    <div class="grid gap-3">
-      <label class="space-y-1 text-sm">
-        <span class="text-muted-foreground">允许模型</span>
-        <input
-          v-model="allowedModelsText"
-          class="h-10 w-full rounded-md border border-border bg-background px-3 text-sm"
-          placeholder="gpt-5, claude-sonnet-*"
-        >
-      </label>
-    </div>
-
     <RoutingModelPolicyEditor
       :model-policies="config.model_policies"
       @update:model-policies="updateModelPolicies"
@@ -34,16 +23,6 @@ const emit = defineEmits<{
 
 const config = computed(() => normalizeRoutingGroupConfig(props.config))
 
-const allowedModelsText = computed({
-  get: () => config.value.allowed_models.join(', '),
-  set: value => {
-    emit('update:config', {
-      ...config.value,
-      allowed_models: value.split(',').map(item => item.trim()).filter(Boolean),
-    })
-  },
-})
-
 function updateModelPolicies(modelPolicies: RoutingModelPolicy[]) {
   emit('update:config', {
     ...config.value,

frontend/src/features/routing/utils/routingPolicy.ts

@@ -10,6 +10,8 @@ export interface RoutingDefaultPolicy {
   priority_mode: RoutingPriorityMode
   scheduling_mode: RoutingSchedulingMode
   keep_priority_on_conversion: boolean
+  enable_cf_heartbeat: boolean
+  cyber_continue_failover: boolean
   /** 首个候选的总尝试次数；后续候选始终只尝试 1 次。0 或 1 表示不重试 */
   sticky_key_attempts: number
 }
@@ -60,7 +62,6 @@ export interface RoutingSetSchedulingAction {
 }
 
 export interface RoutingGroupConfig {
-  allowed_models: string[]
   default_policy: RoutingDefaultPolicy
   model_policies: RoutingModelPolicy[]
   rules: RoutingRule[]
@@ -71,11 +72,12 @@ export const MODEL_SCHEDULING_RULE_PREFIX = 'ui_model_scheduling:'
 
 export function createEmptyRoutingGroupConfig(): RoutingGroupConfig {
   return {
-    allowed_models: [],
     default_policy: {
       priority_mode: 'provider',
       scheduling_mode: 'cache_affinity',
       keep_priority_on_conversion: false,
+      enable_cf_heartbeat: false,
+      cyber_continue_failover: false,
       sticky_key_attempts: DEFAULT_STICKY_KEY_ATTEMPTS,
     },
     model_policies: [],
@@ -104,14 +106,25 @@ export function createEmptyModelPolicy(model = ''): RoutingModelPolicy {
 
 export function normalizeRoutingGroupConfig(value: Partial<RoutingGroupConfig> | null | undefined): RoutingGroupConfig {
   const base = createEmptyRoutingGroupConfig()
+  const rawDefaultPolicy = (value?.default_policy ?? {}) as Partial<RoutingDefaultPolicy> & {
+    enable_openai_image_sync_heartbeat?: boolean
+    enable_standard_text_sync_heartbeat?: boolean
+  }
+  const {
+    enable_openai_image_sync_heartbeat: legacyImageHeartbeat,
+    enable_standard_text_sync_heartbeat: legacyTextHeartbeat,
+    ...defaultPolicyWithoutLegacyHeartbeat
+  } = rawDefaultPolicy
 
   return {
-    allowed_models: Array.isArray(value?.allowed_models) ? [...value.allowed_models] : base.allowed_models,
     default_policy: {
       ...base.default_policy,
-      ...(value?.default_policy ?? {}),
+      ...defaultPolicyWithoutLegacyHeartbeat,
+      enable_cf_heartbeat: Boolean(
+        rawDefaultPolicy.enable_cf_heartbeat || legacyImageHeartbeat || legacyTextHeartbeat,
+      ),
       sticky_key_attempts: normalizeStickyKeyAttempts(
-        value?.default_policy?.sticky_key_attempts ?? DEFAULT_STICKY_KEY_ATTEMPTS,
+        rawDefaultPolicy.sticky_key_attempts ?? DEFAULT_STICKY_KEY_ATTEMPTS,
       ),
     },
     model_policies: Array.isArray(value?.model_policies)
@@ -133,74 +146,6 @@ export function normalizeRoutingGroupConfig(value: Partial<RoutingGroupConfig> |
   }
 }
 
-export function parseAllowedModelsInput(value: string): string[] {
-  const seen = new Set<string>()
-  return value
-    .split(/\r\n?|\n/u)
-    .map(item => item.trim())
-    .filter(Boolean)
-    .filter((model) => {
-      if (seen.has(model)) return false
-      seen.add(model)
-      return true
-    })
-}
-
-export function formatAllowedModelsInput(models: string[]): string {
-  return models.join('\n')
-}
-
-export function updateAllowedModelsFromInput(
-  config: RoutingGroupConfig,
-  value: string,
-): RoutingGroupConfig {
-  const next = normalizeRoutingGroupConfig(config)
-  // Preserve the historical "empty selector" form until the user explicitly
-  // chooses the unrestricted scope. It is distinct from an empty allowlist in
-  // the routing core, where it matches no normal model.
-  const hasHistoricalEmptySelector = next.allowed_models.length > 0
-    && next.allowed_models.every(model => model.trim() === '')
-  if (value.trim() === '' && hasHistoricalEmptySelector) {
-    return next
-  }
-  next.allowed_models = parseAllowedModelsInput(value)
-  return next
-}
-
-export function clearAllowedModels(config: RoutingGroupConfig): RoutingGroupConfig {
-  const next = normalizeRoutingGroupConfig(config)
-  next.allowed_models = []
-  return next
-}
-
-export function routingModelScopeLabel(config: RoutingGroupConfig): string {
-  const models = normalizeRoutingGroupConfig(config).allowed_models
-  if (models.length === 0 || models.some(model => model.trim() === '*')) {
-    return '全部模型'
-  }
-  return `${models.length} 个模型`
-}
-
-export function allowedModelsMirrorPerModelPolicies(config: RoutingGroupConfig): boolean {
-  const normalized = normalizeRoutingGroupConfig(config)
-  const allowedModels = normalized.allowed_models
-    .map(model => model.trim())
-    .filter(Boolean)
-  const perModelNames = normalized.model_policies
-    .map(policy => policy.model)
-    .map(model => model.trim())
-    .filter(Boolean)
-    .filter(model => model !== DEFAULT_ROUTING_POLICY_MODEL)
-
-  if (allowedModels.length === 0 || perModelNames.length === 0) return false
-  if (allowedModels.some(model => model.includes('*'))) return false
-
-  const allowedSet = new Set(allowedModels)
-  const perModelSet = new Set(perModelNames)
-  return allowedSet.size === perModelSet.size
-    && [...allowedSet].every(model => perModelSet.has(model))
-}
-
 export function upsertModelPolicy(config: RoutingGroupConfig, policy: RoutingModelPolicy): RoutingGroupConfig {
   const model = policy.model.trim()
   if (!model) {
@@ -427,6 +372,8 @@ export function getModelScheduling(
     priority_mode: action?.priority_mode ?? normalized.default_policy.priority_mode,
     scheduling_mode: action?.scheduling_mode ?? normalized.default_policy.scheduling_mode,
     keep_priority_on_conversion: normalized.default_policy.keep_priority_on_conversion,
+    enable_cf_heartbeat: normalized.default_policy.enable_cf_heartbeat,
+    cyber_continue_failover: normalized.default_policy.cyber_continue_failover,
     sticky_key_attempts: action?.sticky_key_attempts ?? normalized.default_policy.sticky_key_attempts,
   }
 }

frontend/src/i18n/messages.ts

@@ -3264,7 +3264,6 @@ const legacyFallbackTokens: Array<[string, string]> = [
   ['策略分组', 'policy groups'],
   ['策略', 'policy'],
   ['维度', 'dimension'],
-  ['模型范围', 'model scope'],
   ['默认策略', 'default policy'],
   ['更新时间', 'updated at'],
   ['回溯时间', 'lookback time'],

frontend/src/views/admin/ProviderManagement.vue

@@ -24,14 +24,12 @@
         :api-format-filters="apiFormatFilters"
         :model-filters="modelFilters"
         :has-active-filters="hasActiveFilters"
-        :priority-mode-label="priorityModeConfig.label"
         :loading="loading"
         @update:search-query="searchQuery = $event"
         @update:filter-status="filterStatus = $event"
         @update:filter-api-format="filterApiFormat = $event"
         @update:filter-model="filterModel = $event"
         @reset-filters="resetFilters"
-        @open-priority-dialog="openPriorityDialog"
         @batch-process="openProviderBatchDialog"
         @add-provider="openAddProviderDialog"
         @refresh="loadProviders"
@@ -215,11 +213,6 @@
     @changed="handleProviderBatchChanged"
   />
 
-  <PriorityManagementDialog
-    v-model="priorityDialogOpen"
-    @saved="handlePrioritySaved"
-  />
-
   <ProviderDetailDrawer
     v-if="providerDrawerMounted"
     :open="providerDrawerOpen"
@@ -250,7 +243,7 @@ import TableHead from '@/components/ui/table-head.vue'
 import SortableTableHead from '@/components/ui/sortable-table-head.vue'
 import TableFilterMenu from '@/components/ui/table-filter-menu.vue'
 import Pagination from '@/components/ui/pagination.vue'
-import { ProviderFormDialog, PriorityManagementDialog, ProviderAuthDialog } from '@/features/providers/components'
+import { ProviderFormDialog, ProviderAuthDialog } from '@/features/providers/components'
 import ProviderBatchActionDialog from '@/features/providers/components/ProviderBatchActionDialog.vue'
 import ProviderTableHeader from '@/features/providers/components/ProviderTableHeader.vue'
 import ProviderTableRow from '@/features/providers/components/ProviderTableRow.vue'
@@ -271,9 +264,6 @@ import {
   getGlobalModels,
   type ProviderWithEndpointsSummary,
 } from '@/api/endpoints'
-import { adminApi } from '@/api/admin'
-import { listRoutingGroups } from '@/api/routing-profiles'
-import { normalizeRoutingGroupConfig } from '@/features/routing/utils/routingPolicy'
 import { parseApiError } from '@/utils/errorParser'
 import { useI18n } from '@/i18n'
 
@@ -309,8 +299,6 @@ let providersRequestId = 0
 const providerDialogOpen = ref(false)
 const providerBatchDialogOpen = ref(false)
 const providerToEdit = ref<ProviderWithEndpointsSummary | null>(null)
-const priorityDialogOpen = ref(false)
-const priorityMode = ref<'provider' | 'global_key'>('provider')
 const providerDrawerOpen = ref(false)
 const providerDrawerMounted = ref(false)
 const selectedProviderId = ref<string | null>(null)
@@ -325,7 +313,6 @@ const DELETE_POLL_INTERVAL_MS = 2000
 const DELETE_POLL_MAX_MS = 30 * 60 * 1000
 const DELETE_POLL_MAX_FAILURES = 3
 const PROVIDER_SUMMARY_CACHE_TTL_MS = 10 * 1000
-const PROVIDER_PRIORITY_MODE_CACHE_TTL_MS = 30 * 1000
 const PROVIDER_MODEL_FILTER_CACHE_TTL_MS = 10 * 1000
 
 async function pollProviderDeleteTask(providerId: string, taskId: string) {
@@ -519,13 +506,6 @@ async function saveDescription(_event: Event, provider: ProviderWithEndpointsSum
   }
 }
 
-// 优先级模式配置
-const priorityModeConfig = computed(() => {
-  return {
-    label: legacyT(priorityMode.value === 'global_key' ? '全局 Key 优先' : '提供商优先'),
-  }
-})
-
 // 当前已有提供商的最大优先级
 const maxProviderPriority = computed(() => {
   if (providers.value.length === 0) return undefined
@@ -535,30 +515,6 @@ const maxProviderPriority = computed(() => {
   return priorities.length > 0 ? Math.max(...priorities) : undefined
 })
 
-// 加载优先级模式：优先使用启用中的系统默认调度策略，旧的系统配置键仅作兜底
-async function loadPriorityMode(options: { cacheTtlMs?: number } = {}) {
-  try {
-    const groups = await listRoutingGroups()
-    const systemDefault = groups.items.find(group => group.is_system_default && group.enabled)
-    if (systemDefault) {
-      priorityMode.value = normalizeRoutingGroupConfig(systemDefault.config_json).default_policy.priority_mode
-      return
-    }
-  } catch {
-    // 路由策略不可用时继续尝试旧配置
-  }
-  try {
-    const response = await adminApi.getSystemConfig('provider_priority_mode', {
-      cacheTtlMs: options.cacheTtlMs ?? 0,
-    })
-    if (response.value) {
-      priorityMode.value = response.value as 'provider' | 'global_key'
-    }
-  } catch {
-    priorityMode.value = 'provider'
-  }
-}
-
 // 加载全局模型列表（用于模型筛选下拉）
 async function loadGlobalModelList(options: { cacheTtlMs?: number } = {}) {
   try {
@@ -636,11 +592,6 @@ function openAddProviderDialog() {
   providerDialogOpen.value = true
 }
 
-// 打开优先级管理对话框
-function openPriorityDialog() {
-  priorityDialogOpen.value = true
-}
-
 function openProviderBatchDialog() {
   providerBatchDialogOpen.value = true
 }
@@ -709,12 +660,6 @@ async function handleDrawerRefresh() {
   await refreshProviderSnapshot(selectedProviderId.value)
 }
 
-// 优先级保存成功回调
-async function handlePrioritySaved() {
-  await loadProviders()
-  await loadPriorityMode()
-}
-
 // 处理提供商添加
 function handleProviderAdded() {
   void loadProviders()
@@ -791,7 +736,6 @@ function handleGlobalClick(event: MouseEvent) {
 
 onMounted(() => {
   void loadProviders({ cacheTtlMs: PROVIDER_SUMMARY_CACHE_TTL_MS })
-  void loadPriorityMode({ cacheTtlMs: PROVIDER_PRIORITY_MODE_CACHE_TTL_MS })
   void loadGlobalModelList({ cacheTtlMs: PROVIDER_MODEL_FILTER_CACHE_TTL_MS })
   void loadArchitectureSchemas()
   document.addEventListener('click', handleGlobalClick, true)

frontend/src/views/admin/SystemSettings.vue

@@ -81,9 +81,6 @@
             :registration-privacy-policy-version="systemConfig.registration_privacy_policy_version"
             :auto-delete-expired-keys="systemConfig.auto_delete_expired_keys"
             :enable-format-conversion="systemConfig.enable_format_conversion"
-            :enable-openai-image-sync-heartbeat="systemConfig.enable_openai_image_sync_heartbeat"
-            :enable-standard-text-sync-heartbeat="systemConfig.enable_standard_text_sync_heartbeat"
-            :cyber-continue-failover="systemConfig.cyber_continue_failover"
             :loading="systemConfigLoading || basicConfigLoading"
             :has-changes="hasBasicConfigChanges"
             @save="saveBasicConfig"
@@ -107,9 +104,6 @@
             @update:registration-privacy-policy-version="systemConfig.registration_privacy_policy_version = $event"
             @update:auto-delete-expired-keys="systemConfig.auto_delete_expired_keys = $event"
             @update:enable-format-conversion="systemConfig.enable_format_conversion = $event"
-            @update:enable-openai-image-sync-heartbeat="systemConfig.enable_openai_image_sync_heartbeat = $event"
-            @update:enable-standard-text-sync-heartbeat="systemConfig.enable_standard_text_sync_heartbeat = $event"
-            @update:cyber-continue-failover="systemConfig.cyber_continue_failover = $event"
           />
 
           <!-- 请求记录配置 -->

frontend/src/views/admin/__tests__/RoutingProfiles.allowed-models.spec.ts

@@ -1,519 +0,0 @@
-import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
-import { createApp, defineComponent, h, nextTick, type App } from 'vue'
-
-import RoutingProfiles from '../RoutingProfiles.vue'
-import type {
-  RoutingGroupCreateRequest,
-  RoutingGroupRecord,
-  RoutingGroupUpdateRequest,
-} from '@/api/routing-profiles'
-
-const apiMocks = vi.hoisted(() => ({
-  listRoutingGroups: vi.fn(),
-  createRoutingGroup: vi.fn(),
-  updateRoutingGroup: vi.fn(),
-  deleteRoutingGroup: vi.fn(),
-  getGlobalModels: vi.fn(),
-}))
-const routeMocks = vi.hoisted(() => ({
-  route: null as null | { name: string; params: Record<string, string> },
-  push: vi.fn(),
-  replace: vi.fn(),
-}))
-const toastMocks = vi.hoisted(() => ({ success: vi.fn(), error: vi.fn() }))
-
-vi.mock('vue-router', async () => {
-  const { reactive } = await import('vue')
-  routeMocks.route = reactive({
-    name: 'RoutingProfileDetail',
-    params: { groupId: 'group-1' },
-  })
-  return {
-    useRoute: () => routeMocks.route,
-    useRouter: () => ({ push: routeMocks.push, replace: routeMocks.replace }),
-  }
-})
-
-vi.mock('@/api/routing-profiles', () => ({
-  listRoutingGroups: apiMocks.listRoutingGroups,
-  createRoutingGroup: apiMocks.createRoutingGroup,
-  updateRoutingGroup: apiMocks.updateRoutingGroup,
-  deleteRoutingGroup: apiMocks.deleteRoutingGroup,
-}))
-
-vi.mock('@/api/global-models', () => ({ getGlobalModels: apiMocks.getGlobalModels }))
-vi.mock('@/composables/useToast', () => ({ useToast: () => toastMocks }))
-vi.mock('@/utils/logger', () => ({ log: { error: vi.fn() } }))
-
-vi.mock('@/components/layout', async () => {
-  const { defineComponent, h } = await import('vue')
-  return {
-    PageContainer: defineComponent({
-      setup(_, { slots }) {
-        return () => h('main', slots.default?.())
-      },
-    }),
-  }
-})
-
-vi.mock('@/components/ui', async () => {
-  const { defineComponent, h } = await import('vue')
-
-  const wrapper = (tag = 'div') => defineComponent({
-    inheritAttrs: false,
-    props: { class: String },
-    setup(props, { attrs, slots }) {
-      return () => h(tag, { ...attrs, class: props.class }, [
-        slots.header?.(),
-        slots.default?.(),
-      ])
-    },
-  })
-
-  const Input = defineComponent({
-    inheritAttrs: false,
-    props: {
-      modelValue: { type: [String, Number], default: '' },
-      class: String,
-      disabled: Boolean,
-    },
-    emits: ['update:modelValue'],
-    setup(props, { attrs, emit }) {
-      return () => h('input', {
-        ...attrs,
-        class: props.class,
-        disabled: props.disabled,
-        value: props.modelValue,
-        onInput: (event: Event) => emit(
-          'update:modelValue',
-          (event.target as HTMLInputElement).value,
-        ),
-      })
-    },
-  })
-
-  const Textarea = defineComponent({
-    inheritAttrs: false,
-    props: {
-      modelValue: { type: String, default: '' },
-      class: String,
-      disabled: Boolean,
-    },
-    emits: ['update:modelValue'],
-    setup(props, { attrs, emit }) {
-      return () => h('textarea', {
-        ...attrs,
-        class: props.class,
-        disabled: props.disabled,
-        value: props.modelValue,
-        onInput: (event: Event) => emit(
-          'update:modelValue',
-          (event.target as HTMLTextAreaElement).value,
-        ),
-      })
-    },
-  })
-
-  const Button = defineComponent({
-    inheritAttrs: false,
-    props: {
-      class: String,
-      disabled: Boolean,
-      type: { type: String, default: 'button' },
-    },
-    setup(props, { attrs, slots }) {
-      return () => h('button', {
-        ...attrs,
-        class: props.class,
-        disabled: props.disabled,
-        type: props.type,
-      }, slots.default?.())
-    },
-  })
-
-  const Switch = defineComponent({
-    inheritAttrs: false,
-    props: {
-      modelValue: { type: Boolean, default: false },
-      disabled: Boolean,
-    },
-    emits: ['update:modelValue'],
-    setup(props, { attrs, emit }) {
-      return () => h('button', {
-        ...attrs,
-        type: 'button',
-        role: 'switch',
-        'aria-checked': props.modelValue,
-        disabled: props.disabled,
-        onClick: () => emit('update:modelValue', !props.modelValue),
-      })
-    },
-  })
-
-  return {
-    Badge: wrapper(),
-    Button,
-    Card: wrapper('section'),
-    Input,
-    Switch,
-    Table: wrapper('table'),
-    TableBody: wrapper('tbody'),
-    TableCard: wrapper(),
-    TableCell: wrapper('td'),
-    TableHead: wrapper('th'),
-    TableHeader: wrapper('thead'),
-    TableRow: wrapper('tr'),
-    Textarea,
-  }
-})
-
-vi.mock('@/components/ui/dropdown-menu', async () => {
-  const { defineComponent, h } = await import('vue')
-  const wrapper = defineComponent({
-    setup(_, { slots }) {
-      return () => h('div', slots.default?.())
-    },
-  })
-  return {
-    DropdownMenu: wrapper,
-    DropdownMenuContent: wrapper,
-    DropdownMenuItem: wrapper,
-    DropdownMenuTrigger: wrapper,
-  }
-})
-
-vi.mock('@/components/common', async () => {
-  const { defineComponent, h } = await import('vue')
-  return { AlertDialog: defineComponent({ setup: () => () => h('div') }) }
-})
-
-vi.mock('@/features/routing/components', async () => {
-  const { defineComponent, h } = await import('vue')
-  return {
-    RoutingPriorityPolicyEditor: defineComponent({
-      setup: () => () => h('div', { 'data-testid': 'routing-policy-editor' }),
-    }),
-  }
-})
-
-let app: App | undefined
-let root: HTMLElement | undefined
-
-function routingGroup(
-  allowedModels: string[] = [],
-  overrides: Partial<RoutingGroupRecord> = {},
-): RoutingGroupRecord {
-  return {
-    id: 'group-1',
-    name: 'Default routing',
-    description: null,
-    enabled: true,
-    is_system_default: true,
-    config_json: {
-      allowed_models: allowedModels,
-      default_policy: {
-        priority_mode: 'provider',
-        scheduling_mode: 'cache_affinity',
-        keep_priority_on_conversion: false,
-        sticky_key_attempts: 2,
-      },
-      model_policies: [],
-      rules: [],
-    },
-    version: 1,
-    created_at: 1,
-    updated_at: 1,
-    published_at: null,
-    ...overrides,
-  }
-}
-
-async function flushPromises(iterations = 5): Promise<void> {
-  for (let index = 0; index < iterations; index += 1) {
-    await Promise.resolve()
-  }
-  await nextTick()
-}
-
-async function mountPage(
-  input: RoutingGroupRecord | RoutingGroupRecord[] = routingGroup(),
-): Promise<void> {
-  const groups = Array.isArray(input) ? input : [input]
-  apiMocks.listRoutingGroups.mockResolvedValue({ items: groups, total: groups.length })
-  apiMocks.getGlobalModels.mockResolvedValue({ models: [] })
-  apiMocks.updateRoutingGroup.mockImplementation(
-    async (groupId: string, payload: RoutingGroupUpdateRequest) => {
-      const group = groups.find(item => item.id === groupId)
-      if (!group) throw new Error(`unknown routing group: ${groupId}`)
-      return {
-        ...group,
-        ...payload,
-        config_json: payload.config_json ?? group.config_json,
-        updated_at: 2,
-      }
-    },
-  )
-
-  root = document.createElement('div')
-  document.body.appendChild(root)
-  app = createApp(defineComponent({
-    setup: () => () => h(RoutingProfiles),
-  }))
-  app.mount(root)
-  await flushPromises()
-}
-
-function setTextareaValue(textarea: HTMLTextAreaElement, value: string): void {
-  textarea.value = value
-  textarea.dispatchEvent(new Event('input', { bubbles: true }))
-}
-
-beforeEach(() => {
-  vi.clearAllMocks()
-  if (!routeMocks.route) throw new Error('route mock was not initialized')
-  routeMocks.route.name = 'RoutingProfileDetail'
-  routeMocks.route.params = { groupId: 'group-1' }
-})
-
-afterEach(() => {
-  app?.unmount()
-  root?.remove()
-  app = undefined
-  root = undefined
-})
-
-describe('RoutingProfiles model allowlist', () => {
-  it('saves one selector per line without an extra apply step', async () => {
-    await mountPage()
-
-    const textarea = root?.querySelector(
-      '[data-testid="allowed-models-input"]',
-    ) as HTMLTextAreaElement
-    expect(textarea).toBeInstanceOf(HTMLTextAreaElement)
-
-    setTextareaValue(textarea, 'gpt-5\nclaude-*\nvendor,model')
-    await nextTick()
-
-    const saveButton = root?.querySelector(
-      'button[aria-label="保存"]',
-    ) as HTMLButtonElement
-    expect(saveButton.disabled).toBe(false)
-    saveButton.click()
-    await flushPromises()
-
-    expect(apiMocks.updateRoutingGroup).toHaveBeenCalledWith(
-      'group-1',
-      expect.objectContaining({
-        config_json: expect.objectContaining({
-          allowed_models: ['gpt-5', 'claude-*', 'vendor,model'],
-        }),
-      }),
-    )
-  })
-
-  it('locks the editor while a save is in flight', async () => {
-    const group = routingGroup(['model-a'])
-    let resolveUpdate: ((value: RoutingGroupRecord) => void) | undefined
-    let submittedPayload: RoutingGroupUpdateRequest | undefined
-
-    await mountPage(group)
-    apiMocks.updateRoutingGroup.mockImplementationOnce(
-      async (_groupId: string, payload: RoutingGroupUpdateRequest) => {
-        submittedPayload = payload
-        return await new Promise<RoutingGroupRecord>((resolve) => {
-          resolveUpdate = resolve
-        })
-      },
-    )
-
-    const textarea = root?.querySelector(
-      '[data-testid="allowed-models-input"]',
-    ) as HTMLTextAreaElement
-    setTextareaValue(textarea, 'model-a\nmodel-b')
-    await nextTick()
-
-    const saveButton = root?.querySelector(
-      'button[aria-label="保存"]',
-    ) as HTMLButtonElement
-    saveButton.click()
-    await nextTick()
-
-    const editor = root?.querySelector('[aria-busy="true"]') as HTMLElement
-    const clearButton = root?.querySelector(
-      '[data-testid="clear-allowed-models"]',
-    ) as HTMLButtonElement
-    expect(editor.hasAttribute('inert')).toBe(true)
-    expect(textarea.disabled).toBe(true)
-    expect(clearButton.disabled).toBe(true)
-    expect(saveButton.disabled).toBe(true)
-
-    setTextareaValue(textarea, 'model-c')
-    await nextTick()
-    expect(submittedPayload?.config_json?.allowed_models).toEqual(['model-a', 'model-b'])
-
-    if (!resolveUpdate || !submittedPayload) throw new Error('save request did not start')
-    resolveUpdate({
-      ...group,
-      ...submittedPayload,
-      config_json: submittedPayload.config_json ?? group.config_json,
-      updated_at: 2,
-    })
-    await flushPromises()
-
-    expect(root?.querySelector('[aria-busy="true"]')).toBeNull()
-    expect((root?.querySelector(
-      '[data-testid="allowed-models-input"]',
-    ) as HTMLTextAreaElement).value).toBe('model-a\nmodel-b')
-    expect(apiMocks.updateRoutingGroup).toHaveBeenCalledTimes(1)
-  })
-
-  it('keeps another group selected when an earlier save response arrives', async () => {
-    const firstGroup = routingGroup(['model-a'], {
-      id: 'group-1',
-      name: 'First routing',
-    })
-    const secondGroup = routingGroup(['model-b'], {
-      id: 'group-2',
-      name: 'Second routing',
-      is_system_default: false,
-    })
-    let resolveUpdate: ((value: RoutingGroupRecord) => void) | undefined
-    let submittedPayload: RoutingGroupUpdateRequest | undefined
-
-    await mountPage([firstGroup, secondGroup])
-    apiMocks.updateRoutingGroup.mockImplementationOnce(
-      async (_groupId: string, payload: RoutingGroupUpdateRequest) => {
-        submittedPayload = payload
-        return await new Promise<RoutingGroupRecord>((resolve) => {
-          resolveUpdate = resolve
-        })
-      },
-    )
-
-    const textarea = root?.querySelector(
-      '[data-testid="allowed-models-input"]',
-    ) as HTMLTextAreaElement
-    setTextareaValue(textarea, 'model-a\nmodel-a-new')
-    await nextTick()
-    ;(root?.querySelector('button[aria-label="保存"]') as HTMLButtonElement).click()
-    await nextTick()
-
-    if (!routeMocks.route) throw new Error('route mock was not initialized')
-    routeMocks.route.params = { groupId: 'group-2' }
-    await nextTick()
-    expect((root?.querySelector(
-      '[data-testid="allowed-models-input"]',
-    ) as HTMLTextAreaElement).value).toBe('model-b')
-
-    if (!resolveUpdate || !submittedPayload) throw new Error('save request did not start')
-    resolveUpdate({
-      ...firstGroup,
-      ...submittedPayload,
-      config_json: submittedPayload.config_json ?? firstGroup.config_json,
-      updated_at: 2,
-    })
-    await flushPromises()
-
-    expect(root?.querySelector('h2')?.textContent).toContain('Second routing')
-    expect((root?.querySelector(
-      '[data-testid="allowed-models-input"]',
-    ) as HTMLTextAreaElement).value).toBe('model-b')
-    expect(routeMocks.replace).not.toHaveBeenCalled()
-  })
-
-  it('refreshes a clean draft when returning to the saved group before the response arrives', async () => {
-    const group = routingGroup(['model-a'])
-    let resolveUpdate: ((value: RoutingGroupRecord) => void) | undefined
-    let submittedPayload: RoutingGroupUpdateRequest | undefined
-
-    await mountPage(group)
-    apiMocks.updateRoutingGroup.mockImplementationOnce(
-      async (_groupId: string, payload: RoutingGroupUpdateRequest) => {
-        submittedPayload = payload
-        return await new Promise<RoutingGroupRecord>((resolve) => {
-          resolveUpdate = resolve
-        })
-      },
-    )
-
-    const textarea = root?.querySelector(
-      '[data-testid="allowed-models-input"]',
-    ) as HTMLTextAreaElement
-    setTextareaValue(textarea, 'model-a\nmodel-b')
-    await nextTick()
-    ;(root?.querySelector('button[aria-label="保存"]') as HTMLButtonElement).click()
-    await nextTick()
-
-    if (!routeMocks.route) throw new Error('route mock was not initialized')
-    routeMocks.route.name = 'RoutingProfiles'
-    routeMocks.route.params = {}
-    await nextTick()
-    routeMocks.route.name = 'RoutingProfileDetail'
-    routeMocks.route.params = { groupId: 'group-1' }
-    await nextTick()
-    expect((root?.querySelector(
-      '[data-testid="allowed-models-input"]',
-    ) as HTMLTextAreaElement).value).toBe('model-a')
-
-    if (!resolveUpdate || !submittedPayload) throw new Error('save request did not start')
-    resolveUpdate({
-      ...group,
-      ...submittedPayload,
-      config_json: submittedPayload.config_json ?? group.config_json,
-      updated_at: 2,
-    })
-    await flushPromises()
-
-    expect((root?.querySelector(
-      '[data-testid="allowed-models-input"]',
-    ) as HTMLTextAreaElement).value).toBe('model-a\nmodel-b')
-    expect((root?.querySelector(
-      'button[aria-label="保存"]',
-    ) as HTMLButtonElement).disabled).toBe(true)
-  })
-
-  it('does not attach an old create response to a recreated draft', async () => {
-    if (!routeMocks.route) throw new Error('route mock was not initialized')
-    routeMocks.route.name = 'RoutingProfileCreate'
-    routeMocks.route.params = {}
-
-    let resolveCreate: ((value: RoutingGroupRecord) => void) | undefined
-    let submittedPayload: RoutingGroupCreateRequest | undefined
-    await mountPage([])
-    apiMocks.createRoutingGroup.mockImplementationOnce(
-      async (payload: RoutingGroupCreateRequest) => {
-        submittedPayload = payload
-        return await new Promise<RoutingGroupRecord>((resolve) => {
-          resolveCreate = resolve
-        })
-      },
-    )
-
-    ;(root?.querySelector('button[aria-label="保存"]') as HTMLButtonElement).click()
-    await nextTick()
-
-    routeMocks.route.name = 'RoutingProfiles'
-    await nextTick()
-    routeMocks.route.name = 'RoutingProfileCreate'
-    await nextTick()
-    expect(root?.querySelector('h2')?.textContent).toContain('新建调度策略')
-
-    if (!resolveCreate || !submittedPayload) throw new Error('create request did not start')
-    const config = submittedPayload.config_json
-    resolveCreate({
-      ...routingGroup(config?.allowed_models ?? [], {
-        id: 'created-group',
-        name: submittedPayload.name,
-        description: submittedPayload.description,
-        enabled: submittedPayload.enabled ?? false,
-        is_system_default: submittedPayload.is_system_default ?? false,
-      }),
-      config_json: config ?? routingGroup().config_json,
-    })
-    await flushPromises()
-
-    expect(root?.querySelector('h2')?.textContent).toContain('新建调度策略')
-    expect(routeMocks.replace).not.toHaveBeenCalled()
-    expect(apiMocks.createRoutingGroup).toHaveBeenCalledTimes(1)
-  })
-})

frontend/src/views/admin/system-settings/BasicConfigSection.vue

@@ -151,69 +151,6 @@
         </div>
       </div>
 
-      <div class="flex items-center h-full">
-        <div class="flex items-center space-x-2">
-          <Checkbox
-            id="enable-openai-image-sync-heartbeat"
-            :checked="enableOpenaiImageSyncHeartbeat"
-            @update:checked="$emit('update:enableOpenaiImageSyncHeartbeat', $event)"
-          />
-          <div>
-            <Label
-              for="enable-openai-image-sync-heartbeat"
-              class="cursor-pointer"
-            >
-              同步生图心跳
-            </Label>
-            <p class="text-xs text-muted-foreground">
-              开启后同步生图外层 HTTP 状态固定为 200，上游失败需读取响应体 error.upstream_status
-            </p>
-          </div>
-        </div>
-      </div>
-
-      <div class="flex items-center h-full">
-        <div class="flex items-center space-x-2">
-          <Checkbox
-            id="enable-standard-text-sync-heartbeat"
-            :checked="enableStandardTextSyncHeartbeat"
-            @update:checked="$emit('update:enableStandardTextSyncHeartbeat', $event)"
-          />
-          <div>
-            <Label
-              for="enable-standard-text-sync-heartbeat"
-              class="cursor-pointer"
-            >
-              标准文本非流式心跳
-            </Label>
-            <p class="text-xs text-muted-foreground">
-              开启后标准文本非流式接口外层 HTTP 状态固定为 200，上游失败需读取响应体 error.upstream_status
-            </p>
-          </div>
-        </div>
-      </div>
-
-      <div class="flex items-center h-full">
-        <div class="flex items-center space-x-2">
-          <Checkbox
-            id="cyber-continue-failover"
-            :checked="cyberContinueFailover"
-            @update:checked="$emit('update:cyberContinueFailover', $event)"
-          />
-          <div>
-            <Label
-              for="cyber-continue-failover"
-              class="cursor-pointer"
-            >
-              Cyber继续转移
-            </Label>
-            <p class="text-xs text-muted-foreground">
-              关闭时Cyber Policy错误直接返回客户端；开启后在响应内容开始前按普通错误继续故障转移，可能增加首字等待时间
-            </p>
-          </div>
-        </div>
-      </div>
-
       <div class="md:col-span-2 grid grid-cols-1 md:grid-cols-2 gap-4 border-t pt-5">
         <div class="flex items-center h-full">
           <div class="flex items-center space-x-2">
@@ -539,9 +476,6 @@ defineProps<{
   registrationPrivacyPolicyVersion: string
   autoDeleteExpiredKeys: boolean
   enableFormatConversion: boolean
-  enableOpenaiImageSyncHeartbeat: boolean
-  enableStandardTextSyncHeartbeat: boolean
-  cyberContinueFailover: boolean
   loading: boolean
   hasChanges: boolean
 }>()
@@ -568,8 +502,5 @@ defineEmits<{
   'update:registrationPrivacyPolicyVersion': [value: string]
   'update:autoDeleteExpiredKeys': [value: boolean]
   'update:enableFormatConversion': [value: boolean]
-  'update:enableOpenaiImageSyncHeartbeat': [value: boolean]
-  'update:enableStandardTextSyncHeartbeat': [value: boolean]
-  'update:cyberContinueFailover': [value: boolean]
 }>()
 </script>

frontend/src/views/admin/system-settings/__tests__/useSystemConfig.spec.ts

@@ -59,7 +59,6 @@ describe('useSystemConfig', () => {
     resolveConfigs?.([
       { key: 'request_record_level', value: 'basic' },
       { key: 'proxy_node_metrics_cleanup_batch_size', value: 5000 },
-      { key: 'enable_standard_text_sync_heartbeat', value: false },
     ])
     await loadPromise
 
@@ -71,50 +70,6 @@ describe('useSystemConfig', () => {
     expect(state.hasLogConfigChanges.value).toBe(true)
   })
 
-  it('loads and saves the standard text sync heartbeat flag as a basic config item', async () => {
-    getAllSystemConfigsMock.mockResolvedValue([
-      { key: 'enable_standard_text_sync_heartbeat', value: false },
-    ])
-    updateSystemConfigMock.mockResolvedValue({})
-
-    const state = useSystemConfig()
-    await state.loadSystemConfig()
-
-    expect(state.systemConfig.value.enable_standard_text_sync_heartbeat).toBe(false)
-    state.systemConfig.value.enable_standard_text_sync_heartbeat = true
-    expect(state.hasBasicConfigChanges.value).toBe(true)
-
-    await state.saveBasicConfig()
-
-    expect(updateSystemConfigMock).toHaveBeenCalledWith(
-      'enable_standard_text_sync_heartbeat',
-      true,
-      '标准文本非流式心跳开关：开启后外层 HTTP 状态固定为 200，上游失败写入响应体'
-    )
-    expect(state.hasBasicConfigChanges.value).toBe(false)
-  })
-
-  it('keeps Cyber failover disabled by default and saves the enabled state', async () => {
-    getAllSystemConfigsMock.mockResolvedValue([])
-    updateSystemConfigMock.mockResolvedValue({})
-
-    const state = useSystemConfig()
-    await state.loadSystemConfig()
-
-    expect(state.systemConfig.value.cyber_continue_failover).toBe(false)
-    state.systemConfig.value.cyber_continue_failover = true
-    expect(state.hasBasicConfigChanges.value).toBe(true)
-
-    await state.saveBasicConfig()
-
-    expect(updateSystemConfigMock).toHaveBeenCalledWith(
-      'cyber_continue_failover',
-      true,
-      'Cyber继续转移开关：开启后在响应内容开始前将Cyber Policy错误按普通错误继续故障转移，可能增加首字等待时间'
-    )
-    expect(state.hasBasicConfigChanges.value).toBe(false)
-  })
-
   it('uses backend-compatible defaults when config rows have not been persisted yet', async () => {
     getAllSystemConfigsMock.mockResolvedValue([])
 

frontend/src/views/admin/system-settings/composables/useSystemConfig.ts

@@ -33,12 +33,6 @@ export interface SystemConfig {
   auto_delete_expired_keys: boolean
   // 格式转换
   enable_format_conversion: boolean
-  // 同步生图心跳
-  enable_openai_image_sync_heartbeat: boolean
-  // 标准文本非流式心跳
-  enable_standard_text_sync_heartbeat: boolean
-  // Cyber Policy 错误继续故障转移
-  cyber_continue_failover: boolean
   // 请求记录
   request_record_level: string
   sensitive_headers: string[]
@@ -89,12 +83,6 @@ const CONFIG_KEYS = [
   'auto_delete_expired_keys',
   // 格式转换
   'enable_format_conversion',
-  // 同步生图心跳
-  'enable_openai_image_sync_heartbeat',
-  // 标准文本非流式心跳
-  'enable_standard_text_sync_heartbeat',
-  // Cyber Policy 错误继续故障转移
-  'cyber_continue_failover',
   // 请求记录
   'request_record_level',
   'sensitive_headers',
@@ -147,12 +135,6 @@ function createDefaultConfig(): SystemConfig {
     auto_delete_expired_keys: false,
     // 格式转换
     enable_format_conversion: false,
-    // 同步生图心跳
-    enable_openai_image_sync_heartbeat: false,
-    // 标准文本非流式心跳
-    enable_standard_text_sync_heartbeat: false,
-    // Cyber Policy 错误继续故障转移
-    cyber_continue_failover: false,
     // 请求记录
     request_record_level: 'full',
     sensitive_headers: ['authorization', 'x-api-key', 'api-key', 'cookie', 'set-cookie'],
@@ -235,13 +217,7 @@ export function useSystemConfig() {
       systemConfig.value.registration_privacy_policy_version !==
       originalConfig.value.registration_privacy_policy_version ||
       systemConfig.value.auto_delete_expired_keys !== originalConfig.value.auto_delete_expired_keys ||
-      systemConfig.value.enable_format_conversion !== originalConfig.value.enable_format_conversion ||
-      systemConfig.value.enable_openai_image_sync_heartbeat !==
-      originalConfig.value.enable_openai_image_sync_heartbeat ||
-      systemConfig.value.enable_standard_text_sync_heartbeat !==
-      originalConfig.value.enable_standard_text_sync_heartbeat ||
-      systemConfig.value.cyber_continue_failover !==
-      originalConfig.value.cyber_continue_failover
+      systemConfig.value.enable_format_conversion !== originalConfig.value.enable_format_conversion
     )
   })
 
@@ -490,21 +466,6 @@ export function useSystemConfig() {
           value: systemConfig.value.enable_format_conversion,
           description: '全局格式转换开关：开启时强制允许所有提供商的格式转换',
         },
-        {
-          key: 'enable_openai_image_sync_heartbeat',
-          value: systemConfig.value.enable_openai_image_sync_heartbeat,
-          description: '同步生图心跳开关：开启后外层 HTTP 状态固定为 200，上游失败写入响应体',
-        },
-        {
-          key: 'enable_standard_text_sync_heartbeat',
-          value: systemConfig.value.enable_standard_text_sync_heartbeat,
-          description: '标准文本非流式心跳开关：开启后外层 HTTP 状态固定为 200，上游失败写入响应体',
-        },
-        {
-          key: 'cyber_continue_failover',
-          value: systemConfig.value.cyber_continue_failover,
-          description: 'Cyber继续转移开关：开启后在响应内容开始前将Cyber Policy错误按普通错误继续故障转移，可能增加首字等待时间',
-        },
       ]
       const turnstileSecret = systemConfig.value.turnstile_secret_key.trim()
       if (turnstileSecret) {
@@ -555,12 +516,6 @@ export function useSystemConfig() {
           systemConfig.value.auto_delete_expired_keys
         originalConfig.value.enable_format_conversion =
           systemConfig.value.enable_format_conversion
-        originalConfig.value.enable_openai_image_sync_heartbeat =
-          systemConfig.value.enable_openai_image_sync_heartbeat
-        originalConfig.value.enable_standard_text_sync_heartbeat =
-          systemConfig.value.enable_standard_text_sync_heartbeat
-        originalConfig.value.cyber_continue_failover =
-          systemConfig.value.cyber_continue_failover
       }
       success('基础配置已保存')
     } catch (err) {

frontend/src/views/public/guide/ConceptsGuide.vue

@@ -68,14 +68,6 @@ import { BookOpen } from 'lucide-vue-next'
       <div class="space-y-4 mt-4 text-[#666663] dark:text-[#a3a094] text-sm">
         <ul class="list-decimal pl-5 space-y-2">
           <li><strong class="text-[#262624] dark:text-[#f1ead8] font-medium">提供商类型：</strong>自定义或反代；一般自定义即可，反代请进入反代章节。</li>
-          <li>
-            <strong class="text-[#262624] dark:text-[#f1ead8] font-medium">计费类型：</strong>
-            <ul class="list-disc pl-5 mt-1 space-y-1">
-              <li>按量付费：持续使用</li>
-              <li>月卡额度：按周期(天)限额</li>
-              <li>免费套餐：不计入成本即倍率为0</li>
-            </ul>
-          </li>
           <li><strong class="text-[#262624] dark:text-[#f1ead8] font-medium">最大重试次数：</strong>在缓存亲和调度模式下，首次请求失败后的重试次数。</li>
           <li>
             <strong class="text-[#262624] dark:text-[#f1ead8] font-medium">超时时间：</strong>

frontend/src/views/public/guide/content/concepts.md

@@ -15,16 +15,12 @@
 
 ## 2. 添加提供商
 1. **提供商类型**: 自定义或反代; 一般自定义即可, 反代请进入反代章节
-2. **计费类型**:
-   - 按量付费: 持续使用
-   - 月卡额度: 按周期(天)限额
-   - 免费套餐: 不计入成本即倍率为0
-3. **最大重试次数**
+2. **最大重试次数**
    - 在缓存亲和调度模式下, 首次请求失败后的重试次数。
-4. **超时时间**
+3. **超时时间**
    - 流式首字超时时间: 流式请求收到首字前的超时时间
    - 非流请求超时时间: 非流请求的总超时时间
-5. **保持优先级**
+4. **保持优先级**
    - 通过格式转换的请求, 是否保持当前优先级。
 
 ![image.png](/Aether%E4%BD%BF%E7%94%A8%E6%95%99%E7%A8%8B/image%2010.png)

install.sh

@@ -1153,7 +1153,7 @@ AETHER_BASE_DIR=${INSTALL_ROOT}
 AETHER_UPDATE_STRATEGY=self
 AETHER_GATEWAY_STATIC_DIR=${INSTALL_ROOT}/current/frontend
 AETHER_GATEWAY_VIDEO_TASK_TRUTH_SOURCE_MODE=rust-authoritative
-AETHER_GATEWAY_AUTO_PREPARE_DATABASE=true
+AETHER_GATEWAY_DATABASE_MODE=auto
 AETHER_RUNTIME_BACKEND=memory
 API_KEY_PREFIX=sk
 
@@ -1196,7 +1196,7 @@ AETHER_GATEWAY_DEPLOYMENT_TOPOLOGY=multi-node
 AETHER_GATEWAY_NODE_ROLE=${role}
 AETHER_GATEWAY_STATIC_DIR=${INSTALL_ROOT}/current/frontend
 AETHER_GATEWAY_VIDEO_TASK_TRUTH_SOURCE_MODE=rust-authoritative
-AETHER_GATEWAY_AUTO_PREPARE_DATABASE=true
+AETHER_GATEWAY_DATABASE_MODE=auto
 AETHER_RUNTIME_BACKEND=redis
 API_KEY_PREFIX=sk
 
@@ -1283,7 +1283,7 @@ generate_compose_env() {
     replace_or_append_env "${output}" "AETHER_UPDATE_STRATEGY" "docker"
     replace_or_append_env "${output}" "AETHER_DOCKER_UPDATE_COMMAND" "./update.sh"
     append_compose_log_env_defaults "${output}"
-    replace_or_append_env "${output}" "AETHER_GATEWAY_AUTO_PREPARE_DATABASE" "true"
+    replace_or_append_env "${output}" "AETHER_GATEWAY_DATABASE_MODE" "auto"
 }
 
 generate_compose_single_node_env() {
@@ -1305,7 +1305,7 @@ AETHER_UPDATE_STRATEGY=docker
 AETHER_DOCKER_UPDATE_COMMAND=./update.sh
 AETHER_GATEWAY_STATIC_DIR=${COMPOSE_RELEASE_FRONTEND_DIR}
 AETHER_GATEWAY_VIDEO_TASK_TRUTH_SOURCE_MODE=rust-authoritative
-AETHER_GATEWAY_AUTO_PREPARE_DATABASE=true
+AETHER_GATEWAY_DATABASE_MODE=auto
 AETHER_RUNTIME_BACKEND=memory
 API_KEY_PREFIX=sk
 
@@ -1945,8 +1945,7 @@ EOF
 
     cat <<EOF
 Database:
-  empty database: first service start auto-bootstraps to the current baseline
-  later schema upgrades: ${INSTALL_ROOT}/current/bin/aether-gateway --migrate
+  schema migrations and data backfills are prepared automatically before startup
 
 Current release:
   ${INSTALL_ROOT}/current
@@ -2129,8 +2128,7 @@ EOF
 
     cat <<EOF
 Database:
-  empty database: first service start auto-bootstraps to the current baseline
-  later schema upgrades: ${INSTALL_ROOT}/current/bin/aether-gateway --migrate
+  schema migrations and data backfills are prepared automatically before startup
 
 Current release:
   ${INSTALL_ROOT}/current