test(heal): cover suspended owner production path

.github/actions/schedule-failure-issue/action.yml

@@ -14,10 +14,9 @@
 
 name: "Schedule Failure Issue"
 description: >-
-  Open (or update) a tracking issue when a scheduled workflow run fails or
-  does not complete normally.
+  Open (or update) a tracking issue when a scheduled workflow run fails.
   Dedupes by workflow name: if an open issue titled
-  "[scheduled-failure] <workflow name>" already exists, the result is
+  "[scheduled-failure] <workflow name>" already exists, the failure is
   appended as a comment; otherwise a new issue is created. This is the
   single alerting mechanism for all scheduled pipelines (backlog#1149 ci-8).
 
@@ -39,26 +38,6 @@ inputs:
       Set to an empty string to skip labeling.
     required: false
     default: "infrastructure"
-  source-run-id:
-    description: "Run ID to report. Defaults to the current workflow run."
-    required: false
-    default: ${{ github.run_id }}
-  source-run-attempt:
-    description: "Run attempt to report. Defaults to the current attempt."
-    required: false
-    default: ${{ github.run_attempt }}
-  source-event:
-    description: "Trigger event of the run being reported."
-    required: false
-    default: ${{ github.event_name }}
-  source-ref-name:
-    description: "Ref name of the run being reported."
-    required: false
-    default: ${{ github.ref_name }}
-  source-sha:
-    description: "Commit SHA of the run being reported."
-    required: false
-    default: ${{ github.sha }}
 
 runs:
   using: "composite"
@@ -69,21 +48,17 @@ runs:
         GH_TOKEN: ${{ inputs.github-token }}
         WORKFLOW_NAME: ${{ inputs.workflow-name }}
         ISSUE_LABEL: ${{ inputs.label }}
-        SOURCE_RUN_ID: ${{ inputs.source-run-id }}
-        SOURCE_RUN_ATTEMPT: ${{ inputs.source-run-attempt }}
-        SOURCE_EVENT: ${{ inputs.source-event }}
-        SOURCE_REF_NAME: ${{ inputs.source-ref-name }}
-        SOURCE_SHA: ${{ inputs.source-sha }}
       run: |
         set -euo pipefail
 
         title="[scheduled-failure] ${WORKFLOW_NAME}"
-        run_url="${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${SOURCE_RUN_ID}"
+        run_url="${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}"
 
-        # Inspect the reported run attempt. It can be the current in-workflow
-        # failure or a completed run observed by the external watchdog.
+        # Failed job names for this run attempt. The alert job runs while the
+        # run as a whole is still in progress, so inspect the jobs that have
+        # already completed with a non-success conclusion.
         failed_jobs="$(gh api \
-          "repos/${GITHUB_REPOSITORY}/actions/runs/${SOURCE_RUN_ID}/attempts/${SOURCE_RUN_ATTEMPT}/jobs" \
+          "repos/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/attempts/${GITHUB_RUN_ATTEMPT}/jobs" \
           --paginate \
           --jq '.jobs[]
                 | select(.conclusion == "failure" or .conclusion == "timed_out" or .conclusion == "cancelled")
@@ -93,13 +68,13 @@ runs:
         fi
 
         body="$(cat <<EOF
-        Scheduled run of **${WORKFLOW_NAME}** did not complete successfully.
+        Scheduled run of **${WORKFLOW_NAME}** failed.
 
-        - Run: ${run_url} (attempt ${SOURCE_RUN_ATTEMPT})
-        - Event: \`${SOURCE_EVENT}\`
-        - Ref: \`${SOURCE_REF_NAME}\` @ \`${SOURCE_SHA}\`
+        - Run: ${run_url} (attempt ${GITHUB_RUN_ATTEMPT})
+        - Event: \`${GITHUB_EVENT_NAME}\`
+        - Ref: \`${GITHUB_REF_NAME}\` @ \`${GITHUB_SHA}\`
 
-        Non-success jobs:
+        Failed jobs:
         ${failed_jobs}
         EOF
         )"

.github/workflows/build.yml

@@ -1032,23 +1032,3 @@ jobs:
 
           echo "🎉 Released $TAG successfully!"
           echo "📄 Release URL: ${{ needs.create-release.outputs.release_url }}"
-
-  alert-on-failure:
-    name: Alert on scheduled failure
-    needs: [build-check, prepare-platform-matrix, build-rustfs, build-summary]
-    if: >-
-      always() && github.event_name == 'schedule' &&
-      (contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled'))
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-    permissions:
-      contents: read
-      issues: write
-    steps:
-      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
-        with:
-          persist-credentials: false
-      - name: Open or update failure-tracking issue
-        uses: ./.github/actions/schedule-failure-issue
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/ci.yml

@@ -1032,37 +1032,3 @@ jobs:
           path: artifacts/s3tests-single/**
           if-no-files-found: ignore
           retention-days: 3
-
-  alert-on-failure:
-    name: Alert on scheduled failure
-    needs:
-      - typos
-      - quick-checks
-      - test-and-lint
-      - test-ilm-integration-serial
-      - test-and-lint-rio-v2
-      - test-and-lint-protocols
-      - build-rustfs-debug-binary
-      - build-rustfs-debug-binary-rio-v2
-      - uring-integration
-      - e2e-tests
-      - e2e-full
-      - e2e-tests-rio-v2
-      - s3-implemented-tests
-      - s3-lifecycle-behavior-tests
-    if: >-
-      always() && github.event_name == 'schedule' &&
-      (contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled'))
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-    permissions:
-      contents: read
-      issues: write
-    steps:
-      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
-        with:
-          persist-credentials: false
-      - name: Open or update failure-tracking issue
-        uses: ./.github/actions/schedule-failure-issue
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/minio-interop.yml

@@ -121,21 +121,3 @@ jobs:
           cargo nextest run --run-ignored ignored-only --no-tests=fail \
             -p "$INTEROP_PACKAGE" --features "$INTEROP_FEATURES" \
             -E "$INTEROP_FILTER"
-
-  alert-on-failure:
-    name: Alert on scheduled failure
-    needs: [minio-interop]
-    if: always() && github.event_name == 'schedule' && contains(needs.*.result, 'failure')
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-    permissions:
-      contents: read
-      issues: write
-    steps:
-      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
-        with:
-          persist-credentials: false
-      - name: Open or update failure-tracking issue
-        uses: ./.github/actions/schedule-failure-issue
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/nightly-gnu.yml

@@ -194,23 +194,3 @@ jobs:
 
       - name: Run HA leader failover live checks (three-node Raft cluster in Docker)
         run: bash scripts/test/vault_ha_kms_live.sh
-
-  alert-on-failure:
-    name: Alert on scheduled failure
-    needs: [build, kms-vault-lane, kms-vault-ha-failover]
-    if: >-
-      always() && github.event_name == 'schedule' &&
-      (contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled'))
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-    permissions:
-      contents: read
-      issues: write
-    steps:
-      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
-        with:
-          persist-credentials: false
-      - name: Open or update failure-tracking issue
-        uses: ./.github/actions/schedule-failure-issue
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/scheduled-validation-watchdog.yml

@@ -1,63 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#      http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-name: Scheduled Validation Watchdog
-
-on:
-  workflow_run:
-    workflows:
-      - "Security Audit"
-      - "Build and Release"
-      - "Continuous Integration"
-      - "coverage"
-      - "e2e-nightly"
-      - "e2e-s3tests"
-      - "Fuzz"
-      - "mint"
-      - "minio-interop"
-      - "Nightly GNU Build"
-      - "Performance A/B"
-      - "Runner Hygiene"
-    types: [completed]
-
-permissions:
-  contents: read
-
-jobs:
-  alert-on-incomplete-run:
-    name: Alert on incomplete scheduled run
-    if: >-
-      github.event.workflow_run.event == 'schedule' &&
-      github.event.workflow_run.conclusion != 'success' &&
-      github.event.workflow_run.conclusion != 'failure'
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-    permissions:
-      actions: read
-      contents: read
-      issues: write
-    steps:
-      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
-        with:
-          persist-credentials: false
-      - name: Open or update incomplete-run issue
-        uses: ./.github/actions/schedule-failure-issue
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          workflow-name: ${{ github.event.workflow_run.name }}
-          source-run-id: ${{ github.event.workflow_run.id }}
-          source-run-attempt: ${{ github.event.workflow_run.run_attempt }}
-          source-event: ${{ github.event.workflow_run.event }}
-          source-ref-name: ${{ github.event.workflow_run.head_branch }}
-          source-sha: ${{ github.event.workflow_run.head_sha }}

crates/ecstore/src/cluster/rpc/remote_disk.rs

@@ -50,10 +50,10 @@ use rustfs_protos::evict_failed_connection;
 use rustfs_protos::proto_gen::node_service::RenamePartRequest;
 use rustfs_protos::proto_gen::node_service::{
     BatchReadVersionRequest, BatchReadVersionResponse, CheckPartsRequest, DeletePathsRequest, DeleteRequest,
-    DeleteVersionRequest, DeleteVersionsRequest, DeleteVersionsResponse, DeleteVolumeRequest, DiskInfoRequest, ListDirRequest,
-    ListVolumesRequest, MakeVolumeRequest, MakeVolumesRequest, PreparePartTransactionRequest, ReadAllRequest,
-    ReadMetadataRequest, ReadMultipleRequest, ReadMultipleResponse, ReadPartsRequest, ReadVersionRequest, ReadXlRequest,
-    RenameDataRequest, RenameFileRequest, SettlePartTransactionRequest, SnapshotLeaseReleaseRequest, SnapshotLeaseRenewRequest,
+    DeleteVersionRequest, DeleteVersionsRequest, DeleteVolumeRequest, DiskInfoRequest, ListDirRequest, ListVolumesRequest,
+    MakeVolumeRequest, MakeVolumesRequest, PreparePartTransactionRequest, ReadAllRequest, ReadMetadataRequest,
+    ReadMultipleRequest, ReadMultipleResponse, ReadPartsRequest, ReadVersionRequest, ReadXlRequest, RenameDataRequest,
+    RenameFileRequest, SettlePartTransactionRequest, SnapshotLeaseReleaseRequest, SnapshotLeaseRenewRequest,
     SnapshotLeaseRequest, SnapshotLeaseResponse, StatVolumeRequest, UpdateMetadataRequest, VerifyFileRequest, WriteAllRequest,
     WriteMetadataRequest, node_service_client::NodeServiceClient,
 };
@@ -112,28 +112,6 @@ const EVENT_REMOTE_DISK_RPC: &str = "remote_disk_rpc";
 const SNAPSHOT_LEASE_PROTOCOL_VERSION: u32 = 1;
 pub const REMOTE_SNAPSHOT_LEASE_TTL: Duration = Duration::from_secs(60);
 
-fn decode_delete_versions_errors(response: DeleteVersionsResponse, expected_len: usize) -> Vec<Option<Error>> {
-    if !response.item_errors.is_empty() {
-        if response.item_errors.len() != expected_len {
-            return vec![Some(Error::other("malformed delete_versions item errors")); expected_len];
-        }
-        return response
-            .item_errors
-            .into_iter()
-            .map(|error| (error.code != 0).then(|| error.into()))
-            .collect();
-    }
-
-    if response.errors.len() != expected_len {
-        return vec![Some(Error::other("malformed delete_versions errors")); expected_len];
-    }
-    response
-        .errors
-        .into_iter()
-        .map(|error| (!error.is_empty()).then(|| Error::other(error)))
-        .collect()
-}
-
 fn snapshot_lease_token_from_response(response: SnapshotLeaseResponse) -> Result<SnapshotLeaseToken> {
     if !response.success {
         return Err(response.error.unwrap_or_default().into());
@@ -2428,6 +2406,8 @@ impl DiskAPI for RemoteDisk {
             return errors;
         }
 
+        // TODO(backlog): replace string errors with typed `StorageError` variants
+
         let result = self
             .execute_with_timeout(
                 || async {
@@ -2459,7 +2439,17 @@ impl DiskAPI for RemoteDisk {
             }
             return errors;
         }
-        decode_delete_versions_errors(response, versions.len())
+        response
+            .errors
+            .iter()
+            .map(|error| {
+                if error.is_empty() {
+                    None
+                } else {
+                    Some(Error::other(error.to_string()))
+                }
+            })
+            .collect()
     }
 
     #[tracing::instrument(level = "trace", skip_all)]
@@ -3770,63 +3760,6 @@ mod tests {
 
     static INIT: Once = Once::new();
 
-    #[test]
-    fn delete_versions_response_preserves_typed_item_errors() {
-        let errors = decode_delete_versions_errors(
-            DeleteVersionsResponse {
-                success: true,
-                errors: vec!["file not found".to_string(), String::new()],
-                error: None,
-                item_errors: vec![
-                    rustfs_protos::proto_gen::node_service::Error {
-                        code: DiskError::FileNotFound.to_u32(),
-                        error_info: "file not found".to_string(),
-                    },
-                    rustfs_protos::proto_gen::node_service::Error::default(),
-                ],
-            },
-            2,
-        );
-
-        assert!(matches!(errors.as_slice(), [Some(DiskError::FileNotFound), None]));
-    }
-
-    #[test]
-    fn delete_versions_response_accepts_legacy_string_errors() {
-        let errors = decode_delete_versions_errors(
-            DeleteVersionsResponse {
-                success: true,
-                errors: vec!["legacy error".to_string(), String::new()],
-                error: None,
-                item_errors: Vec::new(),
-            },
-            2,
-        );
-
-        assert_eq!(errors.len(), 2);
-        assert_eq!(errors[0].as_ref().map(ToString::to_string).as_deref(), Some("io error legacy error"));
-        assert!(errors[1].is_none());
-    }
-
-    #[test]
-    fn delete_versions_response_rejects_misaligned_item_errors() {
-        let errors = decode_delete_versions_errors(
-            DeleteVersionsResponse {
-                success: true,
-                errors: vec!["file not found".to_string()],
-                error: None,
-                item_errors: vec![rustfs_protos::proto_gen::node_service::Error {
-                    code: DiskError::FileNotFound.to_u32(),
-                    error_info: "file not found".to_string(),
-                }],
-            },
-            2,
-        );
-
-        assert_eq!(errors.len(), 2);
-        assert!(errors.iter().all(Option::is_some));
-    }
-
     #[test]
     fn disk_mutation_digest_marks_rolling_compatibility() {
         let mut request = Request::new(());

crates/ecstore/src/store/heal.rs

@@ -297,10 +297,16 @@ impl ECStore {
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::bucket::metadata_sys;
     use crate::core::pools::{PoolDecommissionInfo, PoolStatus};
-    use crate::disk::{DiskOption, format::FormatV3, new_disk};
-    use crate::layout::endpoints::{Endpoints, PoolEndpoints};
+    use crate::disk::{DeleteOptions, DiskOption, format::FormatV3, new_disk};
+    use crate::layout::endpoints::{EndpointServerPools, Endpoints, PoolEndpoints};
+    use crate::runtime::instance::InstanceContext;
+    use crate::storage_api_contracts::bucket::{BucketOperations, MakeBucketOptions};
+    use crate::storage_api_contracts::object::{ObjectIO as _, ObjectOperations};
     use crate::store::init_format::{load_format_erasure, save_format_file};
+    use crate::store::init_local_disks_with_instance_ctx;
+    use tokio_util::sync::CancellationToken;
 
     async fn minimal_heal_pool(pool_idx: usize) -> Arc<Sets> {
         let format = FormatV3::new(1, 1);
@@ -347,6 +353,51 @@ mod tests {
         }
     }
 
+    async fn multi_pool_heal_store() -> (tempfile::TempDir, Arc<ECStore>, CancellationToken) {
+        let temp_dir = tempfile::tempdir().expect("multi-pool heal test directory should be created");
+        let mut pool_endpoints = Vec::new();
+        for pool_index in 0..2 {
+            let mut endpoints = Vec::new();
+            for disk_index in 0..4 {
+                let disk_path = temp_dir.path().join(format!("pool{pool_index}-disk{disk_index}"));
+                tokio::fs::create_dir_all(&disk_path)
+                    .await
+                    .expect("multi-pool heal test disk should be created");
+                let mut endpoint = Endpoint::try_from(disk_path.to_str().expect("disk path should be utf8"))
+                    .expect("test endpoint should parse");
+                endpoint.set_pool_index(pool_index);
+                endpoint.set_set_index(0);
+                endpoint.set_disk_index(disk_index);
+                endpoints.push(endpoint);
+            }
+            pool_endpoints.push(PoolEndpoints {
+                legacy: false,
+                set_count: 1,
+                drives_per_set: 4,
+                endpoints: Endpoints::from(endpoints),
+                cmd_line: format!("heal-owner-pool-{pool_index}"),
+                platform: "test".to_string(),
+            });
+        }
+
+        let endpoint_pools = EndpointServerPools::from(pool_endpoints);
+        let instance_ctx = Arc::new(InstanceContext::new());
+        init_local_disks_with_instance_ctx(&instance_ctx, endpoint_pools.clone())
+            .await
+            .expect("multi-pool local disks should initialize");
+        let shutdown = CancellationToken::new();
+        let store = ECStore::new_with_instance_ctx(
+            "127.0.0.1:0".parse().expect("test address should parse"),
+            endpoint_pools,
+            shutdown.clone(),
+            instance_ctx,
+        )
+        .await
+        .expect("multi-pool test store should initialize");
+        metadata_sys::init_bucket_metadata_sys(store.clone(), Vec::new()).await;
+        (temp_dir, store, shutdown)
+    }
+
     #[tokio::test]
     async fn heal_object_pool_scope_selects_only_requested_pool() {
         let store = minimal_heal_store().await;
@@ -506,6 +557,229 @@ mod tests {
         }
     }
 
+    #[tokio::test]
+    #[serial_test::serial]
+    async fn unscoped_heal_object_suspended_owner_semantics() {
+        let (_temp_dir, store, shutdown) = multi_pool_heal_store().await;
+        let bucket = format!("heal-owner-{}", Uuid::new_v4().simple());
+        let active_object = "active-owner";
+        let suspended_only_object = "suspended-only";
+        let duplicate_object = "duplicate-owner";
+        let marker_object = "marker-owner";
+        let quorum_object = "quorum-owner";
+        store
+            .make_bucket(&bucket, &MakeBucketOptions::default())
+            .await
+            .expect("bucket should be created in all pools");
+
+        let mut active_reader = PutObjReader::from_vec(b"active owner".to_vec());
+        store.pools[0]
+            .put_object(&bucket, active_object, &mut active_reader, &ObjectOptions::default())
+            .await
+            .expect("active owner object should be written");
+        let active_disks = store.pools[0].disk_set[0].disks.read().await.clone();
+        let missing_active_disk = active_disks[0].clone().expect("active disk should be online");
+        missing_active_disk
+            .delete(
+                &bucket,
+                active_object,
+                DeleteOptions {
+                    recursive: true,
+                    immediate: true,
+                    ..Default::default()
+                },
+            )
+            .await
+            .expect("active owner shard should be removed for repair");
+        assert!(
+            missing_active_disk.read_xl(&bucket, active_object, false).await.is_err(),
+            "the active owner fixture must start with one missing metadata copy"
+        );
+
+        let mut suspended_reader = PutObjReader::from_vec(b"suspended owner".to_vec());
+        store.pools[1]
+            .put_object(&bucket, suspended_only_object, &mut suspended_reader, &ObjectOptions::default())
+            .await
+            .expect("suspended owner object should be written");
+        for (pool_index, mod_time) in [1_i64, 2_i64].into_iter().enumerate() {
+            let mut duplicate_reader = PutObjReader::from_vec(format!("duplicate-pool-{pool_index}").into_bytes());
+            store.pools[pool_index]
+                .put_object(
+                    &bucket,
+                    duplicate_object,
+                    &mut duplicate_reader,
+                    &ObjectOptions {
+                        mod_time: Some(OffsetDateTime::UNIX_EPOCH + time::Duration::seconds(mod_time)),
+                        ..Default::default()
+                    },
+                )
+                .await
+                .expect("duplicate owner object should be written");
+        }
+        let duplicate_missing_disk = store.pools[0].disk_set[0].disks.read().await[0]
+            .clone()
+            .expect("duplicate active owner disk should be online");
+        duplicate_missing_disk
+            .delete(
+                &bucket,
+                duplicate_object,
+                DeleteOptions {
+                    recursive: true,
+                    immediate: true,
+                    ..Default::default()
+                },
+            )
+            .await
+            .expect("duplicate active owner shard should be removed for repair");
+        let history_version = Uuid::new_v4();
+        let mut history_reader = PutObjReader::from_vec(b"marker history".to_vec());
+        store.pools[0]
+            .put_object(
+                &bucket,
+                marker_object,
+                &mut history_reader,
+                &ObjectOptions {
+                    versioned: true,
+                    version_id: Some(history_version.to_string()),
+                    mod_time: Some(OffsetDateTime::UNIX_EPOCH + time::Duration::seconds(1)),
+                    ..Default::default()
+                },
+            )
+            .await
+            .expect("versioned marker history should be written");
+        store.pools[0]
+            .delete_object(
+                &bucket,
+                marker_object,
+                ObjectOptions {
+                    versioned: true,
+                    mod_time: Some(OffsetDateTime::UNIX_EPOCH + time::Duration::seconds(2)),
+                    ..Default::default()
+                },
+            )
+            .await
+            .expect("delete marker should be written");
+        let mut quorum_reader = PutObjReader::from_vec(b"quorum boundary".to_vec());
+        store.pools[0]
+            .put_object(&bucket, quorum_object, &mut quorum_reader, &ObjectOptions::default())
+            .await
+            .expect("quorum boundary object should be written");
+        {
+            let mut pool_meta = store.pool_meta.write().await;
+            let mut next = PoolMeta::new(&store.pools, &pool_meta);
+            next.pools[1].decommission = Some(PoolDecommissionInfo {
+                start_time: Some(OffsetDateTime::UNIX_EPOCH),
+                ..Default::default()
+            });
+            *pool_meta = next;
+        }
+
+        let (_, duplicate_owner) = store
+            .get_latest_object_info_with_idx(&bucket, duplicate_object, &ObjectOptions::default())
+            .await
+            .expect("duplicate owner should resolve");
+        assert_eq!(duplicate_owner, 1, "latest duplicate must win when all pools are eligible");
+        let (_, active_duplicate_owner) = store
+            .get_latest_object_info_with_idx(
+                &bucket,
+                duplicate_object,
+                &ObjectOptions {
+                    skip_decommissioned: true,
+                    ..Default::default()
+                },
+            )
+            .await
+            .expect("active duplicate owner should resolve");
+        assert_eq!(
+            active_duplicate_owner, 0,
+            "suspended duplicate must be excluded from active owner selection"
+        );
+        let (duplicate_result, duplicate_err) = store
+            .handle_heal_object(&bucket, duplicate_object, "", &HealOpts::default())
+            .await
+            .expect("duplicate owner heal should complete through the production path");
+        assert_eq!(duplicate_result.object, duplicate_object);
+        assert!(duplicate_err.is_none(), "active duplicate should be repaired: {duplicate_err:?}");
+        assert!(
+            duplicate_missing_disk.read_xl(&bucket, duplicate_object, false).await.is_ok(),
+            "production heal must repair the active duplicate owner rather than the suspended owner"
+        );
+        let (marker_info, marker_owner) = store
+            .get_latest_object_info_with_idx(
+                &bucket,
+                marker_object,
+                &ObjectOptions {
+                    skip_decommissioned: true,
+                    versioned: true,
+                    ..Default::default()
+                },
+            )
+            .await
+            .expect("latest delete marker should resolve");
+        assert_eq!(marker_owner, 0);
+        assert!(marker_info.delete_marker, "latest version must preserve delete-marker semantics");
+
+        let (active_result, active_err) = store
+            .handle_heal_object(&bucket, active_object, "", &HealOpts::default())
+            .await
+            .expect("unscoped active-owner heal should complete");
+        assert_eq!(active_result.object, active_object);
+        assert!(active_err.is_none(), "active owner must be selected even with a suspended pool");
+        assert!(
+            missing_active_disk.read_xl(&bucket, active_object, false).await.is_ok(),
+            "active owner heal must write the missing disk metadata: result={active_result:?}, err={active_err:?}"
+        );
+        assert!(
+            store.pools[1]
+                .get_object_info(&bucket, active_object, &ObjectOptions::default())
+                .await
+                .is_err(),
+            "the suspended pool must not be written for an active-owner object"
+        );
+
+        let (suspended_result, suspended_err) = store
+            .handle_heal_object(&bucket, suspended_only_object, "", &HealOpts::default())
+            .await
+            .expect("unscoped suspended-only heal should return a terminal result");
+        assert!(suspended_result.object.is_empty());
+        assert!(matches!(suspended_err, Some(Error::FileNotFound)));
+        assert!(
+            store.pools[1]
+                .get_object_info(&bucket, suspended_only_object, &ObjectOptions::default())
+                .await
+                .is_ok(),
+            "suspended-only data must remain untouched when unscoped heal reports absent"
+        );
+
+        let (_, explicit_err) = store
+            .handle_heal_object(
+                &bucket,
+                suspended_only_object,
+                "",
+                &HealOpts {
+                    pool: Some(1),
+                    ..Default::default()
+                },
+            )
+            .await
+            .expect("explicit suspended-owner heal should return a mapped error");
+        assert!(matches!(explicit_err, Some(Error::SlowDown)));
+
+        let original_quorum_disks = store.pools[0].disk_set[0].disks.read().await.clone();
+        let surviving_quorum_disk = original_quorum_disks[3].clone();
+        *store.pools[0].disk_set[0].disks.write().await = vec![None, None, None, surviving_quorum_disk];
+        let (_, quorum_err) = store
+            .handle_heal_object(&bucket, quorum_object, "", &HealOpts::default())
+            .await
+            .expect("quorum boundary heal should return a mapped result");
+        *store.pools[0].disk_set[0].disks.write().await = original_quorum_disks;
+        assert!(
+            matches!(quorum_err, Some(Error::ErasureReadQuorum)),
+            "quorum-boundary heal must preserve quorum error, got {quorum_err:?}"
+        );
+        shutdown.cancel();
+    }
+
     #[tokio::test]
     async fn handle_heal_format_continues_after_a_pool_error() {
         let canonical_format = FormatV3::new(1, 3);

crates/heal/src/heal/channel.rs

@@ -1640,60 +1640,6 @@ mod tests {
         assert_eq!(payload["items"].as_array().expect("items should be an array").len(), 0);
     }
 
-    #[tokio::test]
-    async fn test_process_query_request_reports_displaced_terminal_detail() {
-        let heal_manager = Arc::new(HealManager::new(
-            Arc::new(MockStorage),
-            Some(HealConfig {
-                queue_size: 1,
-                ..HealConfig::default()
-            }),
-        ));
-        let mut displaced = HealRequest::new(
-            HealType::Bucket {
-                bucket: "displaced-channel".to_string(),
-            },
-            HealOptions::default(),
-            HealPriority::Low,
-        );
-        displaced.id = "displaced-channel-task".to_string();
-        let displaced_id = displaced.id.clone();
-        heal_manager
-            .submit_heal_request(displaced)
-            .await
-            .expect("initial channel task should queue");
-        heal_manager
-            .submit_heal_request(HealRequest::new(
-                HealType::Bucket {
-                    bucket: "successor-channel".to_string(),
-                },
-                HealOptions::default(),
-                HealPriority::High,
-            ))
-            .await
-            .expect("successor channel task should displace the initial task");
-
-        let processor = HealChannelProcessor::new(heal_manager);
-        let (tx, rx) = oneshot::channel();
-        processor
-            .process_query_request("displaced-channel".to_string(), displaced_id, None, tx)
-            .await
-            .expect("displaced query should process");
-        let response = rx
-            .await
-            .expect("query response should be returned")
-            .expect("displaced query should remain successful");
-        let payload: serde_json::Value = serde_json::from_slice(response.data.as_deref().expect("status payload should exist"))
-            .expect("status payload should be json");
-        assert_eq!(payload["summary"], "stopped");
-        assert!(
-            response
-                .error
-                .as_deref()
-                .is_some_and(|detail| detail.contains("reason=displaced"))
-        );
-    }
-
     #[tokio::test]
     async fn test_process_query_request_reports_running_for_queued_task() {
         let heal_manager = create_test_heal_manager();

crates/heal/src/heal/manager.rs

@@ -40,7 +40,6 @@ use tracing::{debug, error, info, warn};
 use super::{DiskError, Endpoint, HealDiskExt as _, local_disk_map_read};
 
 const KEEP_HEAL_TASK_STATUS_DURATION: Duration = Duration::from_secs(10 * 60);
-const DISPLACED_HEAL_REASON: &str = "reason=displaced; retry_hint=submit_again";
 const LOG_COMPONENT_HEAL: &str = "heal";
 const LOG_SUBSYSTEM_DISK_SCANNER: &str = "disk_scanner";
 const LOG_SUBSYSTEM_MANAGER: &str = "manager";
@@ -121,30 +120,26 @@ struct MrfRepairNoticeTarget {
     version_id: Option<[u8; 16]>,
 }
 
-#[derive(Debug, Clone)]
+#[derive(Debug, Clone, PartialEq, Eq)]
 struct HealAdmissionDecision {
     result: HealAdmissionResult,
-    displaced_request: Option<HealRequest>,
+    displaced_task_id: Option<String>,
 }
 
 impl HealAdmissionDecision {
     const fn new(result: HealAdmissionResult) -> Self {
         Self {
             result,
-            displaced_request: None,
+            displaced_task_id: None,
         }
     }
 
-    fn accepted_with_displacement(displaced_request: HealRequest) -> Self {
+    fn accepted_with_displacement(displaced_task_id: String) -> Self {
         Self {
             result: HealAdmissionResult::Accepted,
-            displaced_request: Some(displaced_request),
+            displaced_task_id: Some(displaced_task_id),
         }
     }
-
-    fn displaced_task_id(&self) -> Option<&str> {
-        self.displaced_request.as_ref().map(|request| request.id.as_str())
-    }
 }
 
 fn lock_mrf_repair_notice_targets(
@@ -156,55 +151,6 @@ fn lock_mrf_repair_notice_targets(
     }
 }
 
-fn lock_displaced_terminals(
-    registry: &StdMutex<HashMap<String, Arc<CompletedHealStatus>>>,
-) -> StdMutexGuard<'_, HashMap<String, Arc<CompletedHealStatus>>> {
-    match registry.lock() {
-        Ok(guard) => guard,
-        Err(poisoned) => poisoned.into_inner(),
-    }
-}
-
-fn record_displaced_terminal(
-    registry: &StdMutex<HashMap<String, Arc<CompletedHealStatus>>>,
-    request: &HealRequest,
-) -> Arc<CompletedHealStatus> {
-    let terminal = Arc::new(CompletedHealStatus {
-        heal_type: request.heal_type.clone(),
-        status: HealTaskStatus::Failed {
-            error: format!("heal task displaced by a higher-priority request ({DISPLACED_HEAL_REASON})"),
-        },
-        result_items_truncated: false,
-        completed_at: SystemTime::now(),
-        seqed_items: Vec::new(),
-        next_seq: 0,
-        min_seq: 0,
-    });
-    let mut terminals = lock_displaced_terminals(registry);
-    prune_completed_heal_statuses(&mut terminals);
-    terminals.insert(request.id.clone(), Arc::clone(&terminal));
-    terminal
-}
-
-async fn remove_displaced_task_aliases(
-    aliases: &Arc<Mutex<HashMap<String, HealTaskAlias>>>,
-    terminals: &StdMutex<HashMap<String, Arc<CompletedHealStatus>>>,
-    task_id: &str,
-    terminal: &Arc<CompletedHealStatus>,
-) {
-    let mut aliases = aliases.lock().await;
-    let alias_ids = aliases
-        .iter()
-        .filter_map(|(alias_id, alias)| (alias.task_id == task_id).then_some(alias_id.clone()))
-        .collect::<Vec<_>>();
-    let mut displaced_terminals = lock_displaced_terminals(terminals);
-    prune_completed_heal_statuses(&mut displaced_terminals);
-    for alias_id in alias_ids {
-        displaced_terminals.insert(alias_id, Arc::clone(terminal));
-    }
-    aliases.retain(|alias_id, alias| alias_id != task_id && alias.task_id != task_id);
-}
-
 async fn remove_task_aliases_for_task(registry: &Arc<Mutex<HashMap<String, HealTaskAlias>>>, task_id: &str) {
     registry
         .lock()
@@ -672,14 +618,6 @@ pub struct HealManager {
     /// are shared so the lookup helper can hand a completed entry to a
     /// caller without cloning the retained result window.
     completed_heals: Arc<Mutex<HashMap<String, Arc<CompletedHealStatus>>>>,
-    /// Terminals for requests removed by priority displacement. An Accepted
-    /// task ID remains queryable for the same process lifetime and the normal
-    /// ten-minute status TTL; clients should treat `reason=displaced` as a
-    /// terminal result and submit a fresh request. This sidecar is synchronous
-    /// so admission can publish the terminal while the queue transition is
-    /// still under its lock, without awaiting another tokio lock. Queue state
-    /// is process-local, so this guarantee does not extend across restart.
-    displaced_terminals: Arc<StdMutex<HashMap<String, Arc<CompletedHealStatus>>>>,
     /// Client tokens merged into an existing task id.
     task_aliases: Arc<Mutex<HashMap<String, HealTaskAlias>>>,
     /// Heal tasks waiting for a retry backoff to expire.
@@ -721,7 +659,6 @@ struct HealQueueContext<'a> {
     heal_queue: &'a Arc<Mutex<PriorityHealQueue>>,
     active_heals: &'a Arc<Mutex<HashMap<String, Arc<HealTask>>>>,
     completed_heals: &'a Arc<Mutex<HashMap<String, Arc<CompletedHealStatus>>>>,
-    displaced_terminals: &'a Arc<StdMutex<HashMap<String, Arc<CompletedHealStatus>>>>,
     task_aliases: &'a Arc<Mutex<HashMap<String, HealTaskAlias>>>,
     retrying_heals: &'a Arc<Mutex<HashMap<String, RetryingHeal>>>,
     mrf_repair_notice_targets: &'a Arc<StdMutex<HashMap<String, Vec<MrfRepairNoticeTarget>>>>,
@@ -937,7 +874,7 @@ impl HealManager {
                         result = "accepted_by_displacement",
                         "Heal queue request accepted by displacement"
                     });
-                    return HealAdmissionDecision::accepted_with_displacement(displaced);
+                    return HealAdmissionDecision::accepted_with_displacement(displaced.id);
                 }
 
                 demote_to_debug_when!(per_object_request, warn, target: "rustfs::heal::manager", {
@@ -1168,7 +1105,6 @@ impl HealManager {
             active_heals: Arc::new(Mutex::new(HashMap::new())),
             heal_queue: Arc::new(Mutex::new(PriorityHealQueue::new())),
             completed_heals: Arc::new(Mutex::new(HashMap::new())),
-            displaced_terminals: Arc::new(StdMutex::new(HashMap::new())),
             task_aliases: Arc::new(Mutex::new(HashMap::new())),
             retrying_heals: Arc::new(Mutex::new(HashMap::new())),
             mrf_repair_notice_targets: Arc::new(StdMutex::new(HashMap::new())),
@@ -1273,10 +1209,6 @@ impl HealManager {
         active_heals.clear();
         publish_active_heal_count(&active_heals);
         self.completed_heals.lock().await.clear();
-        // Do not let the synchronous guard live across the following async lock.
-        {
-            lock_displaced_terminals(&self.displaced_terminals).clear();
-        }
         self.task_aliases.lock().await.clear();
         self.retrying_heals.lock().await.clear();
         lock_mrf_repair_notice_targets(&self.mrf_repair_notice_targets).clear();
@@ -1527,11 +1459,7 @@ impl HealManager {
             task_id = queued_id.to_owned();
         }
         let should_notify = matches!(admission, HealAdmissionResult::Accepted) && config.event_driven_scheduler_enable;
-        let displaced_task_id = admission_decision.displaced_task_id().map(ToOwned::to_owned);
-        let displaced_terminal = admission_decision
-            .displaced_request
-            .as_ref()
-            .map(|request| record_displaced_terminal(&self.displaced_terminals, request));
+        let displaced_task_id = admission_decision.displaced_task_id;
         if matches!(admission, HealAdmissionResult::Accepted | HealAdmissionResult::Merged)
             && let Some(target) = mrf_notice_target
         {
@@ -1545,12 +1473,8 @@ impl HealManager {
         drop(queue);
         drop(active_heals);
 
-        if let (Some(displaced_task_id), Some(displaced_terminal)) = (displaced_task_id, displaced_terminal) {
-            // The queue has already removed the displaced request, so the
-            // synchronous terminal sidecar was published before aliases and
-            // MRF ownership are cleaned up.
-            remove_displaced_task_aliases(&self.task_aliases, &self.displaced_terminals, &displaced_task_id, &displaced_terminal)
-                .await;
+        if let Some(displaced_task_id) = displaced_task_id {
+            self.remove_aliases_for_task(&displaced_task_id).await;
         }
 
         if should_notify {
@@ -1625,15 +1549,6 @@ impl HealManager {
             }
         }
 
-        if terminal_completed.is_none() {
-            let mut displaced_terminals = lock_displaced_terminals(&self.displaced_terminals);
-            prune_completed_heal_statuses(&mut displaced_terminals);
-            terminal_completed = displaced_terminals
-                .get(canonical_task_id)
-                .filter(|terminal| matches_path(&terminal.heal_type))
-                .cloned();
-        }
-
         match terminal_completed {
             Some(completed) => TaskStateLookup::Completed(completed),
             None => TaskStateLookup::NotFound,
@@ -1754,19 +1669,9 @@ impl HealManager {
 
         let mut completed_heals = self.completed_heals.lock().await;
         prune_completed_heal_statuses(&mut completed_heals);
-        if completed_heals
+        completed_heals
             .values()
             .any(|completed| heal_type_matches_path(&completed.heal_type, heal_path))
-        {
-            return true;
-        }
-        drop(completed_heals);
-
-        let mut displaced_terminals = lock_displaced_terminals(&self.displaced_terminals);
-        prune_completed_heal_statuses(&mut displaced_terminals);
-        displaced_terminals
-            .values()
-            .any(|terminal| heal_type_matches_path(&terminal.heal_type, heal_path))
     }
 
     /// Get task progress

crates/heal/src/heal/manager/auto_scan.rs

@@ -21,7 +21,6 @@ impl HealManager {
         let heal_queue = self.heal_queue.clone();
         let active_heals = self.active_heals.clone();
         let task_aliases = self.task_aliases.clone();
-        let displaced_terminals = self.displaced_terminals.clone();
         let mrf_repair_notice_targets = self.mrf_repair_notice_targets.clone();
         let storage = self.storage.clone();
         let replacement_recovery_anchors = self.replacement_recovery_anchors.clone();
@@ -482,10 +481,6 @@ impl HealManager {
                             let admission = admission_decision.result;
                             let should_notify =
                                 matches!(admission, HealAdmissionResult::Accepted) && config.event_driven_scheduler_enable;
-                            let displaced_terminal = admission_decision
-                                .displaced_request
-                                .as_ref()
-                                .map(|request| record_displaced_terminal(&displaced_terminals, request));
                             if matches!(admission, HealAdmissionResult::Accepted)
                                 && let Some(anchor) = recovery_anchor
                             {
@@ -496,16 +491,8 @@ impl HealManager {
                             }
                             drop(queue);
                             drop(config);
-                            if let (Some(displaced_task_id), Some(displaced_terminal)) =
-                                (admission_decision.displaced_task_id().map(ToOwned::to_owned), displaced_terminal)
-                            {
-                                remove_displaced_task_aliases(
-                                    &task_aliases,
-                                    &displaced_terminals,
-                                    &displaced_task_id,
-                                    &displaced_terminal,
-                                )
-                                .await;
+                            if let Some(displaced_task_id) = admission_decision.displaced_task_id {
+                                remove_task_aliases_for_task(&task_aliases, &displaced_task_id).await;
                                 lock_mrf_repair_notice_targets(&mrf_repair_notice_targets).remove(&displaced_task_id);
                             }
                             if matches!(admission, HealAdmissionResult::Accepted) {

crates/heal/src/heal/manager/scheduler.rs

@@ -21,7 +21,6 @@ impl HealManager {
         let heal_queue = self.heal_queue.clone();
         let active_heals = self.active_heals.clone();
         let completed_heals = self.completed_heals.clone();
-        let displaced_terminals = self.displaced_terminals.clone();
         let task_aliases = self.task_aliases.clone();
         let retrying_heals = self.retrying_heals.clone();
         let mrf_repair_notice_targets = self.mrf_repair_notice_targets.clone();
@@ -54,7 +53,6 @@ impl HealManager {
                             heal_queue: &heal_queue,
                             active_heals: &active_heals,
                             completed_heals: &completed_heals,
-                            displaced_terminals: &displaced_terminals,
                             task_aliases: &task_aliases,
                             retrying_heals: &retrying_heals,
                             mrf_repair_notice_targets: &mrf_repair_notice_targets,
@@ -73,7 +71,6 @@ impl HealManager {
                             heal_queue: &heal_queue,
                             active_heals: &active_heals,
                             completed_heals: &completed_heals,
-                            displaced_terminals: &displaced_terminals,
                             task_aliases: &task_aliases,
                             retrying_heals: &retrying_heals,
                             mrf_repair_notice_targets: &mrf_repair_notice_targets,
@@ -101,7 +98,6 @@ impl HealManager {
             heal_queue,
             active_heals,
             completed_heals,
-            displaced_terminals,
             task_aliases,
             retrying_heals,
             mrf_repair_notice_targets,
@@ -187,7 +183,6 @@ impl HealManager {
                 let active_heals_clone = active_heals.clone();
                 let heal_queue_clone = heal_queue.clone();
                 let completed_heals_clone = completed_heals.clone();
-                let displaced_terminals_clone = displaced_terminals.clone();
                 let task_aliases_clone = task_aliases.clone();
                 let retrying_heals_clone = retrying_heals.clone();
                 let mrf_repair_notice_targets_clone = mrf_repair_notice_targets.clone();
@@ -368,7 +363,6 @@ impl HealManager {
                         let retry_heal_queue = heal_queue_clone.clone();
                         let retrying_heals_for_spawn = retrying_heals_clone.clone();
                         let retry_task_aliases = task_aliases_clone.clone();
-                        let retry_displaced_terminals = displaced_terminals_clone.clone();
                         let retry_mrf_repair_notice_targets = mrf_repair_notice_targets_clone.clone();
                         let retry_completed_heals = completed_heals_clone.clone();
                         let retry_notify = notify_clone.clone();
@@ -436,14 +430,6 @@ impl HealManager {
                                 let admission = admission_decision.result;
                                 let should_notify = matches!(admission, HealAdmissionResult::Accepted)
                                     && retry_config.event_driven_scheduler_enable;
-                                // Publish the terminal synchronously while the
-                                // queue transition is protected. The subsequent
-                                // queue -> retrying handoff retains the lock order
-                                // used by operations_snapshot.
-                                let displaced_terminal = admission_decision
-                                    .displaced_request
-                                    .as_ref()
-                                    .map(|request| record_displaced_terminal(&retry_displaced_terminals, request));
                                 match admission {
                                     HealAdmissionResult::Accepted => {
                                         // Transfer ownership while holding queue -> retrying,
@@ -451,18 +437,10 @@ impl HealManager {
                                         #[cfg(test)]
                                         pause_retry_ownership_transition(&retry_request_id, true).await;
                                         retrying_heals_for_spawn.lock().await.remove(&retry_request_id);
-                                        let displaced_task_id = admission_decision.displaced_task_id().map(ToOwned::to_owned);
+                                        let displaced_task_id = admission_decision.displaced_task_id;
                                         drop(queue);
-                                        if let (Some(displaced_task_id), Some(displaced_terminal)) =
-                                            (displaced_task_id, displaced_terminal)
-                                        {
-                                            remove_displaced_task_aliases(
-                                                &retry_task_aliases,
-                                                &retry_displaced_terminals,
-                                                &displaced_task_id,
-                                                &displaced_terminal,
-                                            )
-                                            .await;
+                                        if let Some(displaced_task_id) = displaced_task_id {
+                                            remove_task_aliases_for_task(&retry_task_aliases, &displaced_task_id).await;
                                             remove_mrf_repair_notice_targets(
                                                 &retry_mrf_repair_notice_targets,
                                                 &displaced_task_id,

crates/heal/src/heal/manager/tests.rs

@@ -84,7 +84,6 @@ async fn process_manager_queue_once(manager: &HealManager) {
         heal_queue: &manager.heal_queue,
         active_heals: &manager.active_heals,
         completed_heals: &manager.completed_heals,
-        displaced_terminals: &manager.displaced_terminals,
         task_aliases: &manager.task_aliases,
         retrying_heals: &manager.retrying_heals,
         mrf_repair_notice_targets: &manager.mrf_repair_notice_targets,
@@ -2779,10 +2778,7 @@ async fn test_high_priority_request_displaces_lower_priority_when_queue_full() {
         HealAdmissionResult::Accepted
     );
     assert_eq!(manager.get_queue_length().await, 1);
-    assert!(matches!(
-        manager.get_task_status(&low_id).await,
-        Ok(HealTaskStatus::Failed { error }) if error.contains("reason=displaced")
-    ));
+    assert!(matches!(manager.get_task_status(&low_id).await, Err(Error::TaskNotFound { .. })));
     assert_eq!(
         manager
             .get_task_status(&high_id)
@@ -2792,263 +2788,6 @@ async fn test_high_priority_request_displaces_lower_priority_when_queue_full() {
     );
 }
 
-#[tokio::test]
-async fn displaced_task_remains_queryable() {
-    let manager = HealManager::new(
-        Arc::new(MockStorage),
-        Some(HealConfig {
-            queue_size: 1,
-            ..HealConfig::default()
-        }),
-    );
-    let mut displaced = HealRequest::new(
-        HealType::Bucket {
-            bucket: "displaced-bucket".to_string(),
-        },
-        HealOptions::default(),
-        HealPriority::Low,
-    );
-    displaced.id = "displaced-task".to_string();
-    let displaced_id = displaced.id.clone();
-    manager
-        .submit_heal_request(displaced)
-        .await
-        .expect("displaced request should queue");
-
-    let successor = HealRequest::new(
-        HealType::Bucket {
-            bucket: "successor-bucket".to_string(),
-        },
-        HealOptions::default(),
-        HealPriority::High,
-    );
-    manager
-        .submit_heal_request(successor)
-        .await
-        .expect("successor should displace low work");
-
-    let report = manager
-        .get_task_report(&displaced_id)
-        .await
-        .expect("displaced report should remain queryable");
-    assert!(matches!(report.status, HealTaskStatus::Failed { ref error } if error.contains("reason=displaced")));
-}
-
-#[tokio::test]
-async fn displaced_archive_failure_keeps_queryable_terminal() {
-    let manager = HealManager::new(Arc::new(MockStorage), None);
-    let mut request = HealRequest::new(
-        HealType::Bucket {
-            bucket: "archive-failure".to_string(),
-        },
-        HealOptions::default(),
-        HealPriority::Low,
-    );
-    request.id = "archive-failure-task".to_string();
-    let request_id = request.id.clone();
-    // The synchronous sidecar is the authoritative fallback when the normal
-    // completed-task archive has no entry (the failure window that must not
-    // turn an Accepted ID into NotFound).
-    record_displaced_terminal(&manager.displaced_terminals, &request);
-    assert!(manager.completed_heals.lock().await.is_empty());
-    assert!(matches!(
-        manager.get_task_status(&request_id).await,
-        Ok(HealTaskStatus::Failed { error }) if error.contains("reason=displaced")
-    ));
-}
-
-#[tokio::test]
-async fn scheduler_retry_displacement_keeps_evicted_task_queryable() {
-    let manager = Arc::new(HealManager::new(
-        Arc::new(MockStorage),
-        Some(HealConfig {
-            queue_size: 1,
-            event_driven_scheduler_enable: false,
-            ..HealConfig::default()
-        }),
-    ));
-    let mut retry_request = HealRequest::object("retry-transition".to_string(), "object".to_string(), None);
-    retry_request.priority = HealPriority::High;
-    let retry_id = retry_request.id.clone();
-    manager
-        .submit_heal_request(retry_request)
-        .await
-        .expect("retry request should queue");
-
-    // Process exactly one queue cycle so the retry task is spawned without a
-    // background scheduler consuming the filler request before the retry wakes.
-    process_manager_queue_once(&manager).await;
-    tokio::time::timeout(Duration::from_secs(1), async {
-        loop {
-            if manager.retrying_heals.lock().await.contains_key(&retry_id) {
-                break;
-            }
-            tokio::task::yield_now().await;
-        }
-    })
-    .await
-    .expect("retry request should enter backoff");
-
-    let filler = HealRequest::new(
-        HealType::Bucket {
-            bucket: "retry-displaced-filler".to_string(),
-        },
-        HealOptions::default(),
-        HealPriority::Low,
-    );
-    let filler_id = filler.id.clone();
-    manager
-        .submit_heal_request(filler)
-        .await
-        .expect("filler request should occupy the queue");
-
-    tokio::time::timeout(Duration::from_secs(5), async {
-        loop {
-            if matches!(
-                manager.get_task_status(&filler_id).await,
-                Ok(HealTaskStatus::Failed { ref error }) if error.contains("reason=displaced")
-            ) {
-                break;
-            }
-            tokio::time::sleep(Duration::from_millis(10)).await;
-        }
-    })
-    .await
-    .expect("retry admission should displace the filler request");
-    assert_eq!(manager.get_queue_length().await, 1);
-    assert_eq!(
-        manager.get_task_status(&retry_id).await.expect("retry should be queued"),
-        HealTaskStatus::Pending
-    );
-}
-
-#[tokio::test]
-async fn concurrent_displacers_produce_one_terminal_generation() {
-    let manager = Arc::new(HealManager::new(
-        Arc::new(MockStorage),
-        Some(HealConfig {
-            queue_size: 1,
-            ..HealConfig::default()
-        }),
-    ));
-    let mut displaced = HealRequest::new(
-        HealType::Bucket {
-            bucket: "concurrent-displaced".to_string(),
-        },
-        HealOptions::default(),
-        HealPriority::Low,
-    );
-    displaced.id = "concurrent-displaced-task".to_string();
-    let displaced_id = displaced.id.clone();
-    manager
-        .submit_heal_request(displaced)
-        .await
-        .expect("initial request should queue");
-
-    let first = HealRequest::new(
-        HealType::Bucket {
-            bucket: "concurrent-successor-a".to_string(),
-        },
-        HealOptions::default(),
-        HealPriority::High,
-    );
-    let second = HealRequest::new(
-        HealType::Bucket {
-            bucket: "concurrent-successor-b".to_string(),
-        },
-        HealOptions::default(),
-        HealPriority::High,
-    );
-    let (first_result, second_result) = tokio::join!(manager.submit_heal_request(first), manager.submit_heal_request(second));
-    let accepted = [&first_result, &second_result]
-        .into_iter()
-        .filter(|result| matches!(result, Ok(HealAdmissionResult::Accepted)))
-        .count();
-    assert_eq!(accepted, 1, "exactly one concurrent displacer should win the full queue");
-    assert!(
-        first_result.is_ok() && second_result.is_ok(),
-        "the losing request should receive a typed Full result"
-    );
-    let terminals = lock_displaced_terminals(&manager.displaced_terminals);
-    assert_eq!(terminals.len(), 1);
-    assert!(terminals.contains_key(&displaced_id));
-}
-
-#[tokio::test]
-async fn successor_chain_is_bounded_and_authorized() {
-    let manager = HealManager::new(
-        Arc::new(MockStorage),
-        Some(HealConfig {
-            queue_size: 1,
-            ..HealConfig::default()
-        }),
-    );
-    let mut original = HealRequest::new(
-        HealType::Bucket {
-            bucket: "authorized-original".to_string(),
-        },
-        HealOptions::default(),
-        HealPriority::Low,
-    );
-    original.id = "authorized-original-task".to_string();
-    let original_id = original.id.clone();
-    manager.submit_heal_request(original).await.expect("original should queue");
-    let mut duplicate = HealRequest::new(
-        HealType::Bucket {
-            bucket: "authorized-original".to_string(),
-        },
-        HealOptions::default(),
-        HealPriority::Low,
-    );
-    duplicate.id = "authorized-duplicate-task".to_string();
-    let duplicate_id = duplicate.id.clone();
-    manager
-        .submit_heal_request(duplicate)
-        .await
-        .expect("same-target duplicate should merge");
-    let successor = HealRequest::new(
-        HealType::Bucket {
-            bucket: "authorized-successor".to_string(),
-        },
-        HealOptions::default(),
-        HealPriority::High,
-    );
-    let successor_id = successor.id.clone();
-    manager.submit_heal_request(successor).await.expect("successor should queue");
-    assert!(manager.task_aliases.lock().await.is_empty());
-    assert!(matches!(manager.get_task_status(&original_id).await, Ok(HealTaskStatus::Failed { .. })));
-    assert!(matches!(manager.get_task_status(&duplicate_id).await, Ok(HealTaskStatus::Failed { .. })));
-    assert_eq!(
-        manager
-            .get_task_status(&successor_id)
-            .await
-            .expect("successor should remain queued"),
-        HealTaskStatus::Pending
-    );
-}
-
-#[tokio::test]
-async fn displaced_terminal_expires_after_bounded_ttl() {
-    let manager = HealManager::new(Arc::new(MockStorage), None);
-    let mut request = HealRequest::new(
-        HealType::Bucket {
-            bucket: "expires".to_string(),
-        },
-        HealOptions::default(),
-        HealPriority::Low,
-    );
-    request.id = "expires-task".to_string();
-    let request_id = request.id.clone();
-    record_displaced_terminal(&manager.displaced_terminals, &request);
-    {
-        let mut terminals = lock_displaced_terminals(&manager.displaced_terminals);
-        let entry =
-            Arc::get_mut(terminals.get_mut(&request_id).expect("terminal should be retained")).expect("test owns terminal entry");
-        entry.completed_at = SystemTime::now() - KEEP_HEAL_TASK_STATUS_DURATION - Duration::from_secs(1);
-    }
-    assert!(matches!(manager.get_task_status(&request_id).await, Err(Error::TaskNotFound { .. })));
-}
-
 #[tokio::test]
 async fn test_displacing_registered_mrf_task_drops_notice_ownership() {
     let storage: Arc<dyn HealStorageAPI> = Arc::new(MockStorage);

crates/protos/src/generated/proto_gen/node_service.rs

@@ -722,10 +722,6 @@ pub struct DeleteVersionsResponse {
     pub errors: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
     #[prost(message, optional, tag = "3")]
     pub error: ::core::option::Option<Error>,
-    /// Senders dual-write the legacy strings and typed entries. Receivers prefer typed entries
-    /// when present and fall back to strings for peers that predate this field. Code zero means success.
-    #[prost(message, repeated, tag = "4")]
-    pub item_errors: ::prost::alloc::vec::Vec<Error>,
 }
 #[derive(Clone, PartialEq, Eq, Hash, ::prost::Message)]
 pub struct ReadMultipleRequest {

crates/protos/src/node.proto

@@ -493,9 +493,6 @@ message DeleteVersionsResponse {
   bool success = 1;
   repeated string errors = 2;
   optional Error error = 3;
-  // Senders dual-write the legacy strings and typed entries. Receivers prefer typed entries
-  // when present and fall back to strings for peers that predate this field. Code zero means success.
-  repeated Error item_errors = 4;
 }
 
 message ReadMultipleRequest {

rustfs/src/storage/rpc/node_service/disk.rs

@@ -146,29 +146,6 @@ fn encode_file_info_msgpack(value: &FileInfo) -> std::result::Result<Vec<u8>, Di
     encode_msgpack_with_capacity(value, "FileInfo", FILE_INFO_MSGPACK_ENCODE_CAPACITY_HINT)
 }
 
-fn encode_delete_versions_errors(disk_errors: Vec<Option<DiskError>>) -> (Vec<String>, Vec<Error>) {
-    let mut errors = Vec::with_capacity(disk_errors.len());
-    let mut item_errors = Vec::with_capacity(disk_errors.len());
-    for error in disk_errors {
-        match error {
-            Some(error) => {
-                let code = match &error {
-                    DiskError::Io(source) if source.kind() == std::io::ErrorKind::NotFound => DiskError::FileNotFound.to_u32(),
-                    _ => error.to_u32(),
-                };
-                let error_info = error.to_string();
-                errors.push(error_info.clone());
-                item_errors.push(Error { code, error_info });
-            }
-            None => {
-                errors.push(String::new());
-                item_errors.push(Error::default());
-            }
-        }
-    }
-    (errors, item_errors)
-}
-
 fn encode_msgpack_named<T: serde::Serialize>(value: &T, value_name: &str) -> std::result::Result<Vec<u8>, DiskError> {
     let mut serializer = rmp_serde::Serializer::new(Vec::with_capacity(MSGPACK_ENCODE_CAPACITY_HINT)).with_struct_map();
     value
@@ -575,7 +552,6 @@ impl NodeService {
                             success: false,
                             errors: Vec::new(),
                             error: Some(DiskError::other(format!("decode FileInfoVersions failed: {err}")).into()),
-                            item_errors: Vec::new(),
                         }));
                     }
                 };
@@ -587,26 +563,30 @@ impl NodeService {
                         success: false,
                         errors: Vec::new(),
                         error: Some(DiskError::other(format!("decode DeleteOptions failed: {err}")).into()),
-                        item_errors: Vec::new(),
                     }));
                 }
             };
 
-            let (errors, item_errors) =
-                encode_delete_versions_errors(disk.delete_versions(&request.volume, versions, opts).await);
+            let errors = disk
+                .delete_versions(&request.volume, versions, opts)
+                .await
+                .into_iter()
+                .map(|error| match error {
+                    Some(e) => e.to_string(),
+                    None => "".to_string(),
+                })
+                .collect();
 
             Ok(Response::new(DeleteVersionsResponse {
                 success: true,
                 errors,
                 error: None,
-                item_errors,
             }))
         } else {
             Ok(Response::new(DeleteVersionsResponse {
                 success: false,
                 errors: Vec::new(),
                 error: Some(DiskError::other("cannot find disk".to_string()).into()),
-                item_errors: Vec::new(),
             }))
         }
     }
@@ -1632,8 +1612,8 @@ impl NodeService {
 mod tests {
     use super::{
         compat_response_json, decode_msgpack_or_json, decode_rename_data_request_file_info,
-        encode_batch_read_version_response_payloads, encode_delete_versions_errors, encode_file_info_msgpack, encode_msgpack,
-        encode_msgpack_named, encode_read_multiple_response_payloads, encode_rename_data_response_payloads,
+        encode_batch_read_version_response_payloads, encode_file_info_msgpack, encode_msgpack, encode_msgpack_named,
+        encode_read_multiple_response_payloads, encode_rename_data_response_payloads,
     };
     use crate::storage::rpc::node_service::make_server;
     use crate::storage::storage_api::ReadMultipleResp;
@@ -1652,18 +1632,6 @@ mod tests {
         count: u32,
     }
 
-    #[test]
-    fn delete_versions_response_dual_writes_typed_item_errors() {
-        let raw_not_found = super::DiskError::Io(std::io::Error::from(std::io::ErrorKind::NotFound));
-        let (errors, item_errors) = encode_delete_versions_errors(vec![Some(raw_not_found), None]);
-
-        assert!(errors[0].starts_with("io error "));
-        assert!(errors[1].is_empty());
-        assert_eq!(item_errors[0].code, super::DiskError::FileNotFound.to_u32());
-        assert_eq!(item_errors[0].error_info, errors[0]);
-        assert_eq!(item_errors[1].code, 0);
-    }
-
     #[tokio::test]
     #[serial]
     async fn handle_read_version_records_attribution_for_missing_disk() {

scripts/check_test_wiring.py

@@ -15,20 +15,6 @@ from pathlib import Path
 
 
 ROOT = Path(__file__).resolve().parents[1]
-SCHEDULED_ALERT_WORKFLOWS = (
-    ".github/workflows/audit.yml",
-    ".github/workflows/build.yml",
-    ".github/workflows/ci.yml",
-    ".github/workflows/coverage.yml",
-    ".github/workflows/e2e-replication-nightly.yml",
-    ".github/workflows/e2e-s3tests.yml",
-    ".github/workflows/fuzz.yml",
-    ".github/workflows/mint.yml",
-    ".github/workflows/minio-interop.yml",
-    ".github/workflows/nightly-gnu.yml",
-    ".github/workflows/performance-ab.yml",
-    ".github/workflows/runner-hygiene.yml",
-)
 
 
 def words(value: str) -> set[str]:
@@ -266,72 +252,6 @@ def check_profile_definitions(root: Path) -> list[str]:
     return errors
 
 
-def check_scheduled_alerts(root: Path) -> list[str]:
-    errors: list[str] = []
-    for relative in SCHEDULED_ALERT_WORKFLOWS:
-        path = root / relative
-        try:
-            lines = path.read_text().splitlines()
-        except FileNotFoundError:
-            errors.append(f"{relative}: missing scheduled validation workflow")
-            continue
-
-        try:
-            start = lines.index("  alert-on-failure:") + 1
-        except ValueError:
-            errors.append(f"{relative}: missing alert-on-failure job")
-            continue
-        end = next(
-            (index for index in range(start, len(lines)) if re.fullmatch(r"  [A-Za-z0-9_-]+:", lines[index])),
-            len(lines),
-        )
-        job = "\n".join(line.split("#", 1)[0] for line in lines[start:end])
-        required = (
-            "always()",
-            "github.event_name == 'schedule'",
-            "contains(needs.*.result, 'failure')",
-            "issues: write",
-            "uses: ./.github/actions/schedule-failure-issue",
-            "github-token: ${{ secrets.GITHUB_TOKEN }}",
-        )
-        missing = [token for token in required if token not in job]
-        if missing:
-            errors.append(f"{relative}: alert-on-failure missing {', '.join(missing)}")
-
-    watchdog_path = root / ".github/workflows/scheduled-validation-watchdog.yml"
-    try:
-        watchdog = "\n".join(
-            line.split("#", 1)[0] for line in watchdog_path.read_text().splitlines()
-        )
-    except FileNotFoundError:
-        errors.append(".github/workflows/scheduled-validation-watchdog.yml: missing completion watchdog")
-        return errors
-    for relative in SCHEDULED_ALERT_WORKFLOWS:
-        path = root / relative
-        if not path.is_file():
-            continue
-        source = path.read_text()
-        match = re.search(r"^name:\s*[\"']?([^\"'\n]+)", source, re.MULTILINE)
-        if not match:
-            errors.append(f"{relative}: missing workflow name")
-        elif f'- "{match.group(1).strip()}"' not in watchdog:
-            errors.append(f"{relative}: missing from scheduled completion watchdog")
-    required = (
-        "github.event.workflow_run.event == 'schedule'",
-        "github.event.workflow_run.conclusion != 'success'",
-        "github.event.workflow_run.conclusion != 'failure'",
-        "workflow-name: ${{ github.event.workflow_run.name }}",
-        "source-run-id: ${{ github.event.workflow_run.id }}",
-        "source-run-attempt: ${{ github.event.workflow_run.run_attempt }}",
-    )
-    missing = [token for token in required if token not in watchdog]
-    if missing:
-        errors.append(
-            ".github/workflows/scheduled-validation-watchdog.yml: missing " + ", ".join(missing)
-        )
-    return errors
-
-
 def check_profile_listing(root: Path, profile: str, listing: Path) -> list[str]:
     try:
         expected_digest = profile_selection(root, profile)
@@ -361,7 +281,6 @@ def validate(root: Path) -> list[str]:
     errors.extend(check_runner_selection(root))
     errors.extend(check_s3_tests_runner(root))
     errors.extend(check_profile_definitions(root))
-    errors.extend(check_scheduled_alerts(root))
     return errors
 
 
@@ -444,7 +363,6 @@ class SelfTests(unittest.TestCase):
                 mock.patch(__name__ + ".check_fuzz_targets", return_value=[]),
                 mock.patch(__name__ + ".check_runner_selection", return_value=[]),
                 mock.patch(__name__ + ".check_profile_definitions", return_value=[]),
-                mock.patch(__name__ + ".check_scheduled_alerts", return_value=[]),
             ):
                 self.assertEqual(len(validate(root)), 1)
 
@@ -495,54 +413,6 @@ class SelfTests(unittest.TestCase):
             with mock.patch.object(sys, "platform", "linux"):
                 self.assertEqual(len(check_profile_listing(root, "e2e-full", listing)), 1)
 
-    def test_scheduled_alerts_require_completion_watchdog(self) -> None:
-        with tempfile.TemporaryDirectory() as tmp:
-            root = Path(tmp)
-            alert = (
-                "  alert-on-failure:\n"
-                "    if: always() && github.event_name == 'schedule' && "
-                "contains(needs.*.result, 'failure')\n"
-                "    permissions:\n"
-                "      issues: write\n"
-                "    steps:\n"
-                "      - uses: ./.github/actions/schedule-failure-issue\n"
-                "        with:\n"
-                "          github-token: ${{ secrets.GITHUB_TOKEN }}\n"
-            )
-            names: list[str] = []
-            for relative in SCHEDULED_ALERT_WORKFLOWS:
-                path = root / relative
-                path.parent.mkdir(parents=True, exist_ok=True)
-                names.append(path.stem)
-                path.write_text(f'name: "{path.stem}"\n{alert}')
-            watchdog = root / ".github/workflows/scheduled-validation-watchdog.yml"
-            watchdog.write_text(
-                "\n".join(f'- "{name}"' for name in names)
-                + "\ngithub.event.workflow_run.event == 'schedule'\n"
-                + "github.event.workflow_run.conclusion != 'success'\n"
-                + "github.event.workflow_run.conclusion != 'failure'\n"
-                + "workflow-name: ${{ github.event.workflow_run.name }}\n"
-                + "source-run-id: ${{ github.event.workflow_run.id }}\n"
-                + "source-run-attempt: ${{ github.event.workflow_run.run_attempt }}\n"
-            )
-            self.assertEqual(check_scheduled_alerts(root), [])
-
-            first = root / SCHEDULED_ALERT_WORKFLOWS[0]
-            mutations = (
-                ("contains(needs.*.result, 'failure')", "false"),
-                ("issues: write", "issues: read"),
-                ("uses: ./.github/actions/schedule-failure-issue", "uses: actions/checkout@v7"),
-                ("github-token: ${{ secrets.GITHUB_TOKEN }}", "github-token: missing"),
-            )
-            for required, replacement in mutations:
-                original = first.read_text()
-                first.write_text(original.replace(required, replacement))
-                self.assertEqual(len(check_scheduled_alerts(root)), 1)
-                first.write_text(original)
-
-            watchdog.write_text(watchdog.read_text().replace(f'- "{names[0]}"\n', ""))
-            self.assertEqual(len(check_scheduled_alerts(root)), 1)
-
 def main() -> int:
     if sys.argv[1:] == ["--self-test"]:
         suite = unittest.defaultTestLoader.loadTestsFromTestCase(SelfTests)
@@ -566,7 +436,7 @@ def main() -> int:
         for error in errors:
             print(f"ERROR: {error}", file=sys.stderr)
         return 1
-    print("OK: e2e modules, runner selection, fuzz matrices, profiles, and scheduled alerts are wired")
+    print("OK: e2e modules, runner selection, fuzz matrices, profiles, and bounded diagnostics are wired")
     return 0