fix(pool): keep schedulable keys when stale inactive scores exist

- delete pool member scores when a provider key is deactivated
- fall through to the catalog key scan when the pool score page is empty
- log skipped local candidates with a skip_reason for diagnosis
- add regressions for inactive keys with stale available scores

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

@@ -93,6 +93,16 @@ impl AiCandidateResolutionPort for GatewayLocalCandidateResolutionPort<'_> {
         &self,
         candidate: Self::Candidate,
     ) -> Self::Skipped {
+        warn!(
+            event_name = "local_candidate_skipped",
+            log_type = "event",
+            provider_id = %candidate.provider_id,
+            endpoint_id = %candidate.endpoint_id,
+            key_id = %candidate.key_id,
+            api_format = %candidate.endpoint_api_format,
+            skip_reason = "transport_snapshot_missing",
+            "local execution candidate skipped during planning"
+        );
         SkippedLocalExecutionCandidate {
             candidate,
             skip_reason: "transport_snapshot_missing",
@@ -145,6 +155,16 @@ impl AiCandidateResolutionPort for GatewayLocalCandidateResolutionPort<'_> {
         transport: Self::Transport,
         skip_reason: &'static str,
     ) -> Self::Skipped {
+        warn!(
+            event_name = "local_candidate_skipped",
+            log_type = "event",
+            provider_id = %candidate.provider_id,
+            endpoint_id = %candidate.endpoint_id,
+            key_id = %candidate.key_id,
+            api_format = %candidate.endpoint_api_format,
+            skip_reason,
+            "local execution candidate skipped during planning"
+        );
         SkippedLocalExecutionCandidate {
             candidate,
             skip_reason,

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

@@ -634,7 +634,9 @@ impl<'a> PoolKeyCursor<'a> {
 
         if !self.score_phase_exhausted {
             if let Some(score_candidates) = self.next_score_candidates().await {
-                return Some(score_candidates);
+                if !score_candidates.is_empty() {
+                    return Some(score_candidates);
+                }
             }
         }
 
@@ -4168,6 +4170,111 @@ mod tests {
         );
     }
 
+    #[tokio::test]
+    async fn inactive_pool_key_with_stale_score_does_not_exhaust_pool() {
+        let provider_config = Some(json!({
+            "pool_advanced": {
+                "score_top_n": 128,
+                "scheduling_presets": [
+                    {"preset": "single_account", "enabled": true},
+                    {"preset": "priority_first", "enabled": true}
+                ]
+            }
+        }));
+        let (provider, endpoint, mut keys, mut rows) =
+            large_pool_fixture(2, provider_config.clone());
+        keys[1].is_active = false;
+        rows.retain(|row| row.key_id != "key-00001");
+        let scores = vec![
+            sample_provider_key_pool_score("provider-pool", "key-00000", 5.0),
+            sample_provider_key_pool_score("provider-pool", "key-00001", 20.0),
+        ];
+        let data_state =
+            GatewayDataState::with_provider_catalog_and_minimal_candidate_selection_for_tests(
+                Arc::new(InMemoryProviderCatalogReadRepository::seed(
+                    vec![provider],
+                    vec![endpoint],
+                    keys,
+                )),
+                Arc::new(InMemoryMinimalCandidateSelectionReadRepository::seed(rows)),
+            )
+            .with_pool_score_repository_for_tests(Arc::new(
+                InMemoryPoolMemberScoreRepository::seed(scores),
+            ))
+            .with_encryption_key_for_tests(aether_crypto::DEVELOPMENT_ENCRYPTION_KEY);
+        let app = AppState::new()
+            .expect("state should build")
+            .with_data_state_for_tests(data_state);
+        let group = sample_eligible_candidate(
+            "provider-pool",
+            "endpoint-1",
+            "pool-group",
+            10,
+            provider_config,
+        );
+        let mut cursor = PoolKeyCursor::new(PlannerAppState::new(&app), group, None, None, None);
+
+        let candidate = cursor
+            .next_key()
+            .await
+            .expect("active key must stay schedulable beside a stale inactive score");
+
+        assert_eq!(candidate.candidate.key_id, "key-00000");
+        assert_eq!(
+            cursor.skip_reason_counts.get("pool_score_member_missing"),
+            Some(&1)
+        );
+    }
+
+    #[tokio::test]
+    async fn stale_inactive_score_only_does_not_exhaust_pool() {
+        let provider_config = Some(json!({
+            "pool_advanced": {
+                "score_top_n": 128,
+                "scheduling_presets": [
+                    {"preset": "single_account", "enabled": true},
+                    {"preset": "priority_first", "enabled": true}
+                ]
+            }
+        }));
+        let (provider, endpoint, mut keys, mut rows) =
+            large_pool_fixture(2, provider_config.clone());
+        keys[1].is_active = false;
+        rows.retain(|row| row.key_id != "key-00001");
+        let scores = vec![sample_provider_key_pool_score("provider-pool", "key-00001", 20.0)];
+        let data_state =
+            GatewayDataState::with_provider_catalog_and_minimal_candidate_selection_for_tests(
+                Arc::new(InMemoryProviderCatalogReadRepository::seed(
+                    vec![provider],
+                    vec![endpoint],
+                    keys,
+                )),
+                Arc::new(InMemoryMinimalCandidateSelectionReadRepository::seed(rows)),
+            )
+            .with_pool_score_repository_for_tests(Arc::new(
+                InMemoryPoolMemberScoreRepository::seed(scores),
+            ))
+            .with_encryption_key_for_tests(aether_crypto::DEVELOPMENT_ENCRYPTION_KEY);
+        let app = AppState::new()
+            .expect("state should build")
+            .with_data_state_for_tests(data_state);
+        let group = sample_eligible_candidate(
+            "provider-pool",
+            "endpoint-1",
+            "pool-group",
+            10,
+            provider_config,
+        );
+        let mut cursor = PoolKeyCursor::new(PlannerAppState::new(&app), group, None, None, None);
+
+        let candidate = cursor
+            .next_key()
+            .await
+            .expect("catalog rows must remain schedulable when the only score is stale");
+
+        assert_eq!(candidate.candidate.key_id, "key-00000");
+    }
+
     #[tokio::test]
     async fn score_candidates_continue_across_pool_windows() {
         let provider_config = Some(json!({

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

@@ -23,6 +23,16 @@ pub(super) fn resolve_scheduler_candidate_selectability(
         if let Some(skip_reason) =
             current_candidate_runtime_skip_reason(&candidate, runtime_snapshot, now_unix_secs)
         {
+            tracing::debug!(
+                event_name = "scheduler_candidate_skipped",
+                log_type = "event",
+                provider_id = %candidate.provider_id,
+                endpoint_id = %candidate.endpoint_id,
+                key_id = %candidate.key_id,
+                api_format = %candidate.endpoint_api_format,
+                skip_reason,
+                "scheduler candidate skipped during runtime selectability resolution"
+            );
             if emitted_skipped_keys.insert(key) {
                 skipped.push(SchedulerSkippedCandidate {
                     candidate,

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

@@ -804,12 +804,43 @@ impl AppState {
         if updated.is_some() {
             self.invalidate_provider_routing_caches();
         }
+        if let Some(key) = updated.as_ref().filter(|key| !key.is_active) {
+            self.delete_inactive_provider_catalog_key_pool_scores(
+                key.provider_id.as_str(),
+                key.id.as_str(),
+            )
+            .await;
+        }
         match updated {
             Some(key) => self.open_provider_catalog_key(key).await.map(Some),
             None => Ok(None),
         }
     }
 
+    async fn delete_inactive_provider_catalog_key_pool_scores(
+        &self,
+        provider_id: &str,
+        key_id: &str,
+    ) {
+        if let Err(err) = self
+            .data
+            .delete_pool_member_scores_for_member(
+                &pool_scores::PoolMemberIdentity::provider_api_key(
+                    provider_id.to_string(),
+                    key_id.to_string(),
+                ),
+            )
+            .await
+        {
+            warn!(
+                provider_id,
+                key_id,
+                error = ?err,
+                "gateway provider catalog key deactivate: failed to delete pool member scores"
+            );
+        }
+    }
+
     pub(crate) async fn compare_and_update_provider_catalog_key_admin_state(
         &self,
         update: &provider_catalog::ProviderCatalogKeyAdminCasUpdate,
@@ -843,6 +874,15 @@ impl AppState {
         if updated.as_ref().is_some_and(|keys| !keys.is_empty()) {
             self.invalidate_provider_routing_caches();
         }
+        if let Some(keys) = updated.as_ref() {
+            for key in keys.iter().filter(|key| !key.is_active) {
+                self.delete_inactive_provider_catalog_key_pool_scores(
+                    key.provider_id.as_str(),
+                    key.id.as_str(),
+                )
+                .await;
+            }
+        }
         match updated {
             Some(keys) => self.open_provider_catalog_keys(keys).await.map(Some),
             None => Ok(None),