ci: render step results and version in workflow reports (#7141)

* ci(upgrade): render an upgrade matrix in the report; fix from default

The upgrade report only ever showed the requested deb URLs and a case
table. The nightly chain runs died installing the OLD package (default
from_version 1.0.0-rc.4-preview.1 has no .deb asset on its release, and
release 1.0.0-rc.4 ships none either), leaving an empty Total: 0 report
with no indication of what was upgraded.

- Default from_version is now 1.0.0-rc.3 (ships rustfs_1.0.0.rc.3_amd64.deb).
  Matches the auto-testing default from PR #32.
- The report generator also parses the [UPG-TOPO] lines the suite now
  emits and renders an 'Upgrade Matrix' section: per topology and KMS
  backend, the versions actually in place before/after (captured via
  'rustfs --version' on the node) and the aggregated result. When the
  suite dies before any topology completes, the matrix says so instead
  of silently showing nothing.

* fix(ci): use English headers in the upgrade matrix table

* ci(heal,pool): render step results and version in the reports

The heal and pool-expansion reports were only a raw log tail: no
structured indication of which steps passed, no overall verdict, and no
version information for the cluster under test.

The suites now emit machine-readable lines (auto-testing PR):
  [HEAL-STEP] <n> <desc> PASS|FAIL     [POOL-STEP] <n> <desc> PASS|FAIL
  [HEAL-VERSION] <ver> (node <n>)      [POOL-VERSION] <ver> (node <n>)
  [HEAL-RESULT] PASS|FAIL <detail>     [POOL-RESULT] PASS|FAIL <detail>

Both report generators parse them and emit a '## Step Results' section
before the log tail: the version captured in place via 'rustfs --version'
on a node, the overall verdict, and a per-step table. When a run dies
before any step reports (old script or early crash), the table shows a
NOT RUN placeholder row instead of silently showing nothing.

.github/workflows/rustfs-heal-test.yml

@@ -152,6 +152,60 @@ jobs:
           else
             PACKAGE_SOURCE="${RUSTFS_NIGHTLY_PACKAGE_URL}"
           fi
+          STEPS_TABLE="/tmp/rustfs-heal-steps.md"
+          python3 - "${LOG_FILE}" "${STEPS_TABLE}" <<'PY'
+          import re
+          import sys
+
+          log_file, out_file = sys.argv[1], sys.argv[2]
+          ansi = re.compile(r'\x1b\[[0-9;]*m')
+          step_re = re.compile(r'^\[HEAL-STEP\]\s+(\d+)\s+(.+?)\s+(PASS|FAIL|SKIP)\s*$')
+          ver_re = re.compile(r'^\[HEAL-VERSION\]\s+(\S+)(?:\s+\(node\s+(\S+)\))?\s*$')
+          result_re = re.compile(r'^\[HEAL-RESULT\]\s+(PASS|FAIL)\s+(.*)$')
+
+          steps = {}
+          order = []
+          version = None
+          version_node = None
+          verdict = None
+          verdict_detail = ''
+          try:
+              with open(log_file, 'r', encoding='utf-8', errors='replace') as fh:
+                  for raw in fh:
+                      line = ansi.sub('', raw).strip()
+                      m = step_re.match(line)
+                      if m:
+                          n, desc, status = m.group(1), m.group(2), m.group(3)
+                          if n not in steps:
+                              order.append(n)
+                          steps[n] = (desc, status)  # later lines win (fail after pass)
+                          continue
+                      m = ver_re.match(line)
+                      if m:
+                          version, version_node = m.group(1), m.group(2)
+                          continue
+                      m = result_re.match(line)
+                      if m:
+                          verdict, verdict_detail = m.group(1), m.group(2)
+          except FileNotFoundError:
+              pass
+
+          with open(out_file, 'w', encoding='utf-8') as out:
+              out.write('## Step Results\n\n')
+              if version:
+                  node_note = f' (captured via `rustfs --version` on {version_node})' if version_node else ''
+                  out.write(f'- Version under test: **{version}**{node_note}\n')
+              if verdict:
+                  out.write(f'- Overall result: **{verdict}** — {verdict_detail}\n')
+              out.write('\n')
+              out.write('| Step | Description | Result |\n')
+              out.write('| --- | --- | --- |\n')
+              for n in sorted(order, key=int):
+                  desc, status = steps[n]
+                  out.write(f'| {n} | {desc} | {status} |\n')
+              if not order:
+                  out.write('| - | - | NOT RUN (no step result lines found) |\n')
+          PY
           {
             echo "# RustFS heal test report"
             echo ""
@@ -160,6 +214,8 @@ jobs:
             echo "- Package: ${PACKAGE_SOURCE}"
             echo "- Test Step Outcome: ${{ steps.test.outcome }}"
             echo ""
+            cat "${STEPS_TABLE}" || true
+            echo ""
             echo "## Log tail"
             echo '```text'
             tail -n 200 "${LOG_FILE}" || true

.github/workflows/rustfs-pool-expand-test.yml

@@ -380,6 +380,60 @@ jobs:
           else
             PACKAGE_SOURCE="${RUSTFS_NIGHTLY_PACKAGE_URL}"
           fi
+          STEPS_TABLE="${POOL_ARTIFACT_DIR}/pool-steps.md"
+          python3 - "${LOG_FILE}" "${STEPS_TABLE}" <<'PY'
+          import re
+          import sys
+
+          log_file, out_file = sys.argv[1], sys.argv[2]
+          ansi = re.compile(r'\x1b\[[0-9;]*m')
+          step_re = re.compile(r'^\[POOL-STEP\]\s+(\d+)\s+(.+?)\s+(PASS|FAIL|SKIP)\s*$')
+          ver_re = re.compile(r'^\[POOL-VERSION\]\s+(\S+)(?:\s+\(node\s+(\S+)\))?\s*$')
+          result_re = re.compile(r'^\[POOL-RESULT\]\s+(PASS|FAIL)\s+(.*)$')
+
+          steps = {}
+          order = []
+          version = None
+          version_node = None
+          verdict = None
+          verdict_detail = ''
+          try:
+              with open(log_file, 'r', encoding='utf-8', errors='replace') as fh:
+                  for raw in fh:
+                      line = ansi.sub('', raw).strip()
+                      m = step_re.match(line)
+                      if m:
+                          n, desc, status = m.group(1), m.group(2), m.group(3)
+                          if n not in steps:
+                              order.append(n)
+                          steps[n] = (desc, status)  # later lines win (fail after pass)
+                          continue
+                      m = ver_re.match(line)
+                      if m:
+                          version, version_node = m.group(1), m.group(2)
+                          continue
+                      m = result_re.match(line)
+                      if m:
+                          verdict, verdict_detail = m.group(1), m.group(2)
+          except FileNotFoundError:
+              pass
+
+          with open(out_file, 'w', encoding='utf-8') as out:
+              out.write('## Step Results\n\n')
+              if version:
+                  node_note = f' (captured via `rustfs --version` on {version_node})' if version_node else ''
+                  out.write(f'- Version under test: **{version}**{node_note}\n')
+              if verdict:
+                  out.write(f'- Overall result: **{verdict}** — {verdict_detail}\n')
+              out.write('\n')
+              out.write('| Step | Description | Result |\n')
+              out.write('| --- | --- | --- |\n')
+              for n in sorted(order, key=int):
+                  desc, status = steps[n]
+                  out.write(f'| {n} | {desc} | {status} |\n')
+              if not order:
+                  out.write('| - | - | NOT RUN (no step result lines found) |\n')
+          PY
           {
             echo "# RustFS pool expansion test report"
             echo ""
@@ -389,6 +443,8 @@ jobs:
             echo "- Warp concurrent: ${{ inputs.warp_concurrent || '32' }}"
             echo "- Test Step Outcome: ${{ steps.pool_test.outcome }}"
             echo ""
+            cat "${STEPS_TABLE}" || true
+            echo ""
             echo "## Log tail"
             echo '```text'
             tail -n 200 "${LOG_FILE}" || true

.github/workflows/rustfs-upgrade-test.yml

@@ -18,9 +18,9 @@ on:
   workflow_dispatch:
     inputs:
       from_version:
-        description: 'OLD RustFS release tag (e.g. 1.0.0-rc.4-preview.1)'
+        description: 'OLD RustFS release tag (must ship a .deb asset, e.g. 1.0.0-rc.3)'
         required: false
-        default: '1.0.0-rc.4-preview.1'
+        default: '1.0.0-rc.3'
       from_url:
         description: 'OLD .deb URL. Overrides from_version.'
         required: false
@@ -203,54 +203,75 @@ jobs:
             TO_SOURCE="${RUSTFS_NIGHTLY_PACKAGE_URL}"
           fi
           CASE_TABLE="/tmp/rustfs-upgrade-cases.md"
-          python3 - "${LOG_FILE}" "${CASE_TABLE}" <<'PY'
+          MATRIX_TABLE="/tmp/rustfs-upgrade-matrix.md"
+          python3 - "${LOG_FILE}" "${CASE_TABLE}" "${MATRIX_TABLE}" <<'PY'
           import re
           import sys
 
-          log_file, out_file = sys.argv[1], sys.argv[2]
+          log_file, out_file, matrix_file = sys.argv[1], sys.argv[2], sys.argv[3]
           ansi = re.compile(r'\x1b\[[0-9;]*m')
           start_re = re.compile(r'^---\s+([A-Z]+-[0-9]+)\s+(.+?)\s+---$')
           done_re = re.compile(r'^\[(PASS|FAIL|UNSUPPORTED)\]\s+([A-Z]+-[0-9]+)\b')
+          topo_re = re.compile(
+              r'^\[UPG-TOPO\]\s+(\S+)\s+(\S+)\s+(\S+)\s+(\S+)\s+PASS=(\d+)\s+FAIL=(\d+)\s*$')
 
           rows = []
           index = {}
+          topo_rows = []
           try:
-            with open(log_file, 'r', encoding='utf-8', errors='replace') as fh:
-              for raw in fh:
-                line = ansi.sub('', raw).strip()
-                m = start_re.match(line)
-                if m:
-                  case_id, name = m.group(1), m.group(2)
-                  if case_id not in index:
-                    index[case_id] = len(rows)
-                    rows.append([case_id, name, 'RUNNING'])
-                  continue
-                m = done_re.match(line)
-                if m:
-                  status, case_id = m.group(1), m.group(2)
-                  if case_id in index:
-                    rows[index[case_id]][2] = status
-                  else:
-                    rows.append([case_id, case_id, status])
-                    index[case_id] = len(rows) - 1
+              with open(log_file, 'r', encoding='utf-8', errors='replace') as fh:
+                  for raw in fh:
+                      line = ansi.sub('', raw).strip()
+                      m = topo_re.match(line)
+                      if m:
+                          topo_rows.append(m.groups())
+                          continue
+                      m = start_re.match(line)
+                      if m:
+                          case_id, name = m.group(1), m.group(2)
+                          if case_id not in index:
+                              index[case_id] = len(rows)
+                              rows.append([case_id, name, 'RUNNING'])
+                          continue
+                      m = done_re.match(line)
+                      if m:
+                          status, case_id = m.group(1), m.group(2)
+                          if case_id in index:
+                              rows[index[case_id]][2] = status
+                          else:
+                              rows.append([case_id, case_id, status])
+                              index[case_id] = len(rows) - 1
           except FileNotFoundError:
-            rows = []
+              rows = []
 
           counts = {'PASS': 0, 'FAIL': 0, 'UNSUPPORTED': 0, 'RUNNING': 0}
           for _, _, status in rows:
-            counts[status] = counts.get(status, 0) + 1
+              counts[status] = counts.get(status, 0) + 1
 
           with open(out_file, 'w', encoding='utf-8') as out:
-            out.write('## Case Summary\n\n')
-            out.write(f"- Total: {len(rows)}\\n")
-            out.write(f"- PASS: {counts.get('PASS', 0)}\\n")
-            out.write(f"- FAIL: {counts.get('FAIL', 0)}\\n")
-            out.write(f"- UNSUPPORTED: {counts.get('UNSUPPORTED', 0)}\\n")
-            out.write('\\n')
-            out.write('| Case | Name | Status |\\n')
-            out.write('| --- | --- | --- |\\n')
-            for case_id, name, status in rows:
-              out.write(f'| {case_id} | {name} | {status} |\\n')
+              out.write('## Case Summary\n\n')
+              out.write(f"- Total: {len(rows)}\\n")
+              out.write(f"- PASS: {counts.get('PASS', 0)}\\n")
+              out.write(f"- FAIL: {counts.get('FAIL', 0)}\\n")
+              out.write(f"- UNSUPPORTED: {counts.get('UNSUPPORTED', 0)}\\n")
+              out.write('\\n')
+              out.write('| Case | Name | Status |\\n')
+              out.write('| --- | --- | --- |\\n')
+              for case_id, name, status in rows:
+                  out.write(f'| {case_id} | {name} | {status} |\\n')
+
+          # Upgrade matrix: one row per topology/backend with the versions
+          # captured on the nodes (rustfs --version) and the aggregated
+          # result. The dashboard renders this table directly.
+          with open(matrix_file, 'w', encoding='utf-8') as out:
+              out.write('## Upgrade Matrix\n\n')
+              out.write('| Topology | KMS Backend | From Version | To Version | Result |\n')
+              out.write('| --- | --- | --- | --- | --- |\n')
+              for topo, backend, old_v, new_v, npass, nfail in topo_rows:
+                  result = 'PASS' if nfail == '0' else 'FAIL'
+                  out.write(f'| {topo} | {backend} | {old_v} | {new_v} | {result} (PASS={npass} FAIL={nfail}) |\n')
+              if not topo_rows:
+                  out.write('| - | - | - | - | NOT RUN (suite failed before upgrade) |\n')
           PY
           {
             echo "# RustFS upgrade compatibility report"
@@ -261,6 +282,8 @@ jobs:
             echo "- To: ${TO_SOURCE}"
             echo "- Test Step Outcome: ${{ steps.test.outcome }}"
             echo ""
+            cat "${MATRIX_TABLE}" || true
+            echo ""
             cat "${CASE_TABLE}" || true
             echo ""
             echo "## Log tail"

crates/scanner/src/scanner_io.rs

@@ -105,6 +105,12 @@ struct DirtyUsageSnapshot {
     covers_all_pending: bool,
 }
 
+#[derive(Clone, Debug, Default)]
+pub(crate) struct ScannerBucketScanScope {
+    selected_buckets: Option<Arc<HashSet<String>>>,
+    baseline_scan_plan_digest: Option<DataUsageScanPlanDigest>,
+}
+
 pub(crate) fn is_scanner_metadata_corrupt_error(err: &StorageError) -> bool {
     matches!(err, StorageError::Io(io) if io.to_string().starts_with(SCANNER_METADATA_CORRUPT_ERROR))
 }
@@ -146,6 +152,7 @@ fn object_lock_config_enabled(config: &ObjectLockConfiguration) -> bool {
 pub struct ScannerBucketScanPlan {
     buckets: Vec<BucketInfo>,
     all_buckets: Arc<Vec<BucketInfo>>,
+    scope: ScannerBucketScanScope,
     digest: DataUsageScanPlanDigest,
     leader_epoch: u64,
     tier_registry_generation: u64,
@@ -732,6 +739,8 @@ mod dirty_usage;
 mod guards;
 mod io_cache;
 mod io_cycle;
+#[cfg(test)]
+use io_cache::{ScannerSetCacheGeneration, prepare_scoped_set_scan};
 pub(crate) use io_cycle::nsscanner_with_storage_status;
 mod io_disk;
 #[cfg(test)]

crates/scanner/src/scanner_io/io_cache.rs

@@ -14,6 +14,93 @@
 /// ScannerIOCache implementation for SetDisks: bucket ordering, worker fan-out, merge, and publish.
 use super::*;
 
+#[derive(Clone, Copy)]
+pub(super) struct ScannerSetCacheGeneration {
+    pub(super) want_cycle: u64,
+    pub(super) leader_epoch: u64,
+    pub(super) tier_registry_generation: u64,
+    pub(super) source: DataUsageCacheSource,
+    pub(super) scan_plan_digest: DataUsageScanPlanDigest,
+}
+
+pub(super) struct PreparedScopedSetScan {
+    pub(super) buckets: Vec<BucketInfo>,
+    pub(super) cache: DataUsageCache,
+}
+
+pub(super) fn prepare_scoped_set_scan(
+    old_cache: &DataUsageCache,
+    set_buckets: &[BucketInfo],
+    all_buckets: &[BucketInfo],
+    scope: &ScannerBucketScanScope,
+    generation: ScannerSetCacheGeneration,
+) -> Option<PreparedScopedSetScan> {
+    let (Some(selected_buckets), Some(baseline_scan_plan_digest)) = (&scope.selected_buckets, scope.baseline_scan_plan_digest)
+    else {
+        return None;
+    };
+    if selected_buckets.is_empty()
+        || !old_cache.info.snapshot_complete
+        || old_cache.info.last_update.is_none()
+        || old_cache.info.name != DATA_USAGE_ROOT
+        || old_cache.info.next_cycle > generation.want_cycle
+        || old_cache.info.leader_epoch != generation.leader_epoch
+        || old_cache.info.tier_registry_generation != Some(generation.tier_registry_generation)
+        || old_cache.info.source != Some(generation.source)
+        || old_cache.info.scan_plan_digest != Some(baseline_scan_plan_digest)
+        || old_cache.info.cache_key_format != DATA_USAGE_CACHE_KEY_FORMAT
+        || old_cache.checked_flatten_complete_scope(DATA_USAGE_ROOT).is_none()
+    {
+        return None;
+    }
+
+    let mut cache = DataUsageCache {
+        info: DataUsageCacheInfo {
+            name: DATA_USAGE_ROOT.to_string(),
+            next_cycle: generation.want_cycle,
+            leader_epoch: generation.leader_epoch,
+            tier_registry_generation: Some(generation.tier_registry_generation),
+            source: Some(generation.source),
+            snapshot_complete: false,
+            scan_plan_digest: Some(generation.scan_plan_digest),
+            cache_key_format: DATA_USAGE_CACHE_KEY_FORMAT,
+            lkg_snapshot_complete: true,
+            lkg_next_cycle: Some(old_cache.info.next_cycle),
+            lkg_last_update: old_cache.info.last_update,
+            lkg_leader_epoch: Some(old_cache.info.leader_epoch),
+            lkg_scan_plan_digest: old_cache.info.scan_plan_digest,
+            ..Default::default()
+        },
+        cache: HashMap::new(),
+    };
+    cache.replace(DATA_USAGE_ROOT, "", DataUsageEntry::default());
+    let root_hash = crate::hash_path(DATA_USAGE_ROOT);
+    let mut current_bucket_names = HashSet::with_capacity(all_buckets.len());
+    for bucket in all_buckets {
+        if !current_bucket_names.insert(bucket.name.as_str()) {
+            return None;
+        }
+        if selected_buckets.contains(&bucket.name) {
+            cache.replace(&bucket.name, DATA_USAGE_ROOT, DataUsageEntry::default());
+            continue;
+        }
+
+        let bucket_hash = crate::hash_path(&bucket.name);
+        old_cache.find(&bucket.name)?;
+        cache.copy_with_children(old_cache, &bucket_hash, &Some(root_hash.clone()));
+        cache.find(&bucket.name)?;
+    }
+
+    Some(PreparedScopedSetScan {
+        buckets: set_buckets
+            .iter()
+            .filter(|bucket| selected_buckets.contains(&bucket.name))
+            .cloned()
+            .collect(),
+        cache,
+    })
+}
+
 #[async_trait::async_trait]
 impl ScannerIOCache for SetDisks {
     #[tracing::instrument(skip(self, budget, scan_plan, updates))]
@@ -27,8 +114,9 @@ impl ScannerIOCache for SetDisks {
         scan_mode: HealScanMode,
     ) -> Result<()> {
         let ScannerBucketScanPlan {
-            buckets,
+            mut buckets,
             all_buckets,
+            scope,
             digest: scan_plan_digest,
             leader_epoch,
             tier_registry_generation,
@@ -63,26 +151,57 @@ impl ScannerIOCache for SetDisks {
                 "Scanner old data usage cache load failed; rebuilding from bucket caches"
             );
         }
+        let scoped_scan = prepare_scoped_set_scan(
+            &old_cache,
+            &buckets,
+            &all_buckets,
+            &scope,
+            ScannerSetCacheGeneration {
+                want_cycle,
+                leader_epoch,
+                tier_registry_generation,
+                source,
+                scan_plan_digest,
+            },
+        );
+        let mut scoped_cache = scoped_scan.map(|prepared| {
+            buckets = prepared.buckets;
+            prepared.cache
+        });
         if buckets.is_empty() {
             let now = SystemTime::now();
-            let mut cache = DataUsageCache {
-                info: DataUsageCacheInfo {
-                    name: DATA_USAGE_ROOT.to_string(),
-                    next_cycle: want_cycle,
-                    last_update: Some(now),
-                    leader_epoch,
-                    tier_registry_generation: Some(tier_registry_generation),
-                    source: Some(source),
-                    snapshot_complete: true,
-                    scan_plan_digest: Some(scan_plan_digest),
-                    cache_key_format: DATA_USAGE_CACHE_KEY_FORMAT,
-                    ..Default::default()
-                },
-                cache: HashMap::new(),
+            let mut cache = match scoped_cache.take() {
+                Some(cache) => cache,
+                None => {
+                    let mut cache = DataUsageCache {
+                        info: DataUsageCacheInfo {
+                            name: DATA_USAGE_ROOT.to_string(),
+                            next_cycle: want_cycle,
+                            leader_epoch,
+                            tier_registry_generation: Some(tier_registry_generation),
+                            source: Some(source),
+                            scan_plan_digest: Some(scan_plan_digest),
+                            cache_key_format: DATA_USAGE_CACHE_KEY_FORMAT,
+                            ..Default::default()
+                        },
+                        cache: HashMap::new(),
+                    };
+                    cache.replace(DATA_USAGE_ROOT, "", DataUsageEntry::default());
+                    for bucket in all_buckets.iter() {
+                        cache.replace(&bucket.name, DATA_USAGE_ROOT, DataUsageEntry::default());
+                    }
+                    cache
+                }
             };
-            cache.replace(DATA_USAGE_ROOT, "", DataUsageEntry::default());
-            for bucket in all_buckets.iter() {
-                cache.replace(&bucket.name, DATA_USAGE_ROOT, DataUsageEntry::default());
+            cache.info.last_update = Some(now);
+            cache.info.snapshot_complete = true;
+            cache.info.lkg_snapshot_complete = false;
+            cache.info.lkg_next_cycle = None;
+            cache.info.lkg_last_update = None;
+            cache.info.lkg_leader_epoch = None;
+            cache.info.lkg_scan_plan_digest = None;
+            if cache.find(DATA_USAGE_ROOT).is_none() {
+                cache.replace(DATA_USAGE_ROOT, "", DataUsageEntry::default());
             }
             reset_disk_bucket_scan_gauges(&pool_label, &set_label);
             return persist_and_publish_cache_snapshot(
@@ -269,92 +388,102 @@ impl ScannerIOCache for SetDisks {
         record_disk_bucket_scans_active(0, &pool_label, &set_label);
         let _reset_disk_bucket_scan_gauges = DiskBucketScanGaugeReset::new(pool_label.clone(), set_label.clone());
 
-        // Fence a stale set aggregate before copying entries into per-bucket work caches.
-        if old_cache.info.next_cycle <= want_cycle
-            && old_cache.info.leader_epoch <= leader_epoch
-            && old_cache.info.tier_registry_generation != Some(tier_registry_generation)
-        {
-            old_cache.info.scan_plan_digest = None;
-        }
-        let old_lkg = old_cache.info.snapshot_complete.then_some({
-            (
-                old_cache.info.next_cycle,
-                old_cache.info.last_update,
-                old_cache.info.leader_epoch,
-                old_cache.info.scan_plan_digest,
-            )
-        });
-        let prepare_outcome = match old_cache.prepare_for_scan(
-            DATA_USAGE_ROOT,
-            want_cycle,
-            leader_epoch,
-            source,
-            scan_plan_digest,
-            require_cache_source,
-        ) {
-            DataUsageCachePrepareOutcome::RejectedNewerCycle => {
-                cache_cycle_floor.fetch_max(old_cache.info.next_cycle, Ordering::AcqRel);
-                warn!(
-                    target: "rustfs::scanner::io",
-                    event = EVENT_SCANNER_CACHE_PERSIST_STATE,
-                    component = LOG_COMPONENT_SCANNER,
-                    subsystem = LOG_SUBSYSTEM_IO,
-                    pool = self.pool_index,
-                    set = self.set_index,
-                    cache_name = DATA_USAGE_CACHE_NAME,
-                    requested_cycle = want_cycle,
-                    cached_cycle = old_cache.info.next_cycle,
-                    state = "stale_cycle_rejected",
-                    "Scanner rejected a set cache cycle regression"
-                );
-                return Ok(());
+        let mut cache = if let Some(cache) = scoped_cache.take() {
+            cache
+        } else {
+            // Fence a stale set aggregate before copying entries into per-bucket work caches.
+            if old_cache.info.next_cycle <= want_cycle
+                && old_cache.info.leader_epoch <= leader_epoch
+                && old_cache.info.tier_registry_generation != Some(tier_registry_generation)
+            {
+                old_cache.info.scan_plan_digest = None;
             }
-            DataUsageCachePrepareOutcome::RejectedNewerLeader => {
-                warn!(
-                    target: "rustfs::scanner::io",
-                    event = EVENT_SCANNER_CACHE_PERSIST_STATE,
-                    component = LOG_COMPONENT_SCANNER,
-                    subsystem = LOG_SUBSYSTEM_IO,
-                    pool = self.pool_index,
-                    set = self.set_index,
-                    cache_name = DATA_USAGE_CACHE_NAME,
-                    requested_epoch = leader_epoch,
-                    cached_epoch = old_cache.info.leader_epoch,
-                    state = "stale_leader_rejected",
-                    "Scanner rejected work from an older leader epoch"
-                );
-                return Ok(());
-            }
-            outcome => outcome,
-        };
-        if matches!(prepare_outcome, DataUsageCachePrepareOutcome::Reused)
-            && let Some((cycle, last_update, epoch, digest)) = old_lkg
-        {
-            old_cache.info.lkg_snapshot_complete = true;
-            old_cache.info.lkg_next_cycle = Some(cycle);
-            old_cache.info.lkg_last_update = last_update;
-            old_cache.info.lkg_leader_epoch = Some(epoch);
-            old_cache.info.lkg_scan_plan_digest = digest;
-        }
-
-        let mut cache = DataUsageCache {
-            info: DataUsageCacheInfo {
-                name: DATA_USAGE_ROOT.to_string(),
-                next_cycle: want_cycle,
+            let old_lkg = old_cache.info.snapshot_complete.then_some({
+                (
+                    old_cache.info.next_cycle,
+                    old_cache.info.last_update,
+                    old_cache.info.leader_epoch,
+                    old_cache.info.scan_plan_digest,
+                )
+            });
+            let prepare_outcome = match old_cache.prepare_for_scan(
+                DATA_USAGE_ROOT,
+                want_cycle,
                 leader_epoch,
-                tier_registry_generation: Some(tier_registry_generation),
-                source: Some(source),
-                snapshot_complete: false,
-                scan_plan_digest: Some(scan_plan_digest),
-                cache_key_format: DATA_USAGE_CACHE_KEY_FORMAT,
-                ..Default::default()
-            },
-            cache: HashMap::new(),
+                source,
+                scan_plan_digest,
+                require_cache_source,
+            ) {
+                DataUsageCachePrepareOutcome::RejectedNewerCycle => {
+                    cache_cycle_floor.fetch_max(old_cache.info.next_cycle, Ordering::AcqRel);
+                    warn!(
+                        target: "rustfs::scanner::io",
+                        event = EVENT_SCANNER_CACHE_PERSIST_STATE,
+                        component = LOG_COMPONENT_SCANNER,
+                        subsystem = LOG_SUBSYSTEM_IO,
+                        pool = self.pool_index,
+                        set = self.set_index,
+                        cache_name = DATA_USAGE_CACHE_NAME,
+                        requested_cycle = want_cycle,
+                        cached_cycle = old_cache.info.next_cycle,
+                        state = "stale_cycle_rejected",
+                        "Scanner rejected a set cache cycle regression"
+                    );
+                    return Ok(());
+                }
+                DataUsageCachePrepareOutcome::RejectedNewerLeader => {
+                    warn!(
+                        target: "rustfs::scanner::io",
+                        event = EVENT_SCANNER_CACHE_PERSIST_STATE,
+                        component = LOG_COMPONENT_SCANNER,
+                        subsystem = LOG_SUBSYSTEM_IO,
+                        pool = self.pool_index,
+                        set = self.set_index,
+                        cache_name = DATA_USAGE_CACHE_NAME,
+                        requested_epoch = leader_epoch,
+                        cached_epoch = old_cache.info.leader_epoch,
+                        state = "stale_leader_rejected",
+                        "Scanner rejected work from an older leader epoch"
+                    );
+                    return Ok(());
+                }
+                outcome => outcome,
+            };
+            if matches!(prepare_outcome, DataUsageCachePrepareOutcome::Reused)
+                && let Some((cycle, last_update, epoch, digest)) = old_lkg
+            {
+                old_cache.info.lkg_snapshot_complete = true;
+                old_cache.info.lkg_next_cycle = Some(cycle);
+                old_cache.info.lkg_last_update = last_update;
+                old_cache.info.lkg_leader_epoch = Some(epoch);
+                old_cache.info.lkg_scan_plan_digest = digest;
+            }
+
+            let mut cache = DataUsageCache {
+                info: DataUsageCacheInfo {
+                    name: DATA_USAGE_ROOT.to_string(),
+                    next_cycle: want_cycle,
+                    leader_epoch,
+                    tier_registry_generation: Some(tier_registry_generation),
+                    source: Some(source),
+                    snapshot_complete: false,
+                    scan_plan_digest: Some(scan_plan_digest),
+                    cache_key_format: DATA_USAGE_CACHE_KEY_FORMAT,
+                    lkg_snapshot_complete: old_cache.info.lkg_snapshot_complete,
+                    lkg_next_cycle: old_cache.info.lkg_next_cycle,
+                    lkg_last_update: old_cache.info.lkg_last_update,
+                    lkg_leader_epoch: old_cache.info.lkg_leader_epoch,
+                    lkg_scan_plan_digest: old_cache.info.lkg_scan_plan_digest,
+                    ..Default::default()
+                },
+                cache: HashMap::new(),
+            };
+            cache.replace(DATA_USAGE_ROOT, "", DataUsageEntry::default());
+            for bucket in all_buckets.iter() {
+                cache.replace(&bucket.name, DATA_USAGE_ROOT, DataUsageEntry::default());
+            }
+            cache
         };
-        cache.replace(DATA_USAGE_ROOT, "", DataUsageEntry::default());
-        for bucket in all_buckets.iter() {
-            cache.replace(&bucket.name, DATA_USAGE_ROOT, DataUsageEntry::default());
-        }
 
         let (bucket_tx, bucket_rx) = mpsc::channel::<BucketInfo>(buckets.len());
 
@@ -1257,11 +1386,6 @@ impl ScannerIOCache for SetDisks {
             incomplete_scope.info.snapshot_complete = false;
             incomplete_scope.info.scan_plan_digest = Some(scan_plan_digest);
             incomplete_scope.info.cache_key_format = DATA_USAGE_CACHE_KEY_FORMAT;
-            incomplete_scope.info.lkg_snapshot_complete = old_cache.info.lkg_snapshot_complete;
-            incomplete_scope.info.lkg_next_cycle = old_cache.info.lkg_next_cycle;
-            incomplete_scope.info.lkg_last_update = old_cache.info.lkg_last_update;
-            incomplete_scope.info.lkg_leader_epoch = old_cache.info.lkg_leader_epoch;
-            incomplete_scope.info.lkg_scan_plan_digest = old_cache.info.lkg_scan_plan_digest;
             if let Err(e) = updates.send(incomplete_scope).await {
                 error!(
                     target: "rustfs::scanner::io",

crates/scanner/src/scanner_io/io_cycle.rs

@@ -63,6 +63,41 @@ pub(crate) async fn nsscanner_with_storage_status<S>(
 where
     S: ScannerStorage,
 {
+    let request = ScannerCycleRequest {
+        ctx,
+        budget,
+        updates,
+        want_cycle,
+        leader_epoch,
+        scan_mode,
+        scan_scope: ScannerBucketScanScope::default(),
+    };
+    nsscanner_with_storage_status_scoped(store, request).await
+}
+
+pub(crate) struct ScannerCycleRequest {
+    pub(crate) ctx: CancellationToken,
+    pub(crate) budget: Arc<ScannerCycleBudget>,
+    pub(crate) updates: mpsc::Sender<DataUsageInfo>,
+    pub(crate) want_cycle: u64,
+    pub(crate) leader_epoch: u64,
+    pub(crate) scan_mode: HealScanMode,
+    pub(crate) scan_scope: ScannerBucketScanScope,
+}
+
+pub(crate) async fn nsscanner_with_storage_status_scoped<S>(store: &S, request: ScannerCycleRequest) -> Result<ScannerCycleResult>
+where
+    S: ScannerStorage,
+{
+    let ScannerCycleRequest {
+        ctx,
+        budget,
+        updates,
+        want_cycle,
+        leader_epoch,
+        scan_mode,
+        scan_scope,
+    } = request;
     let child_token = ctx.child_token();
     let _tier_cycle_guard = begin_tier_registry_cycle(want_cycle, leader_epoch);
 
@@ -280,6 +315,7 @@ where
         let scan_plan = ScannerBucketScanPlan {
             buckets: set_buckets,
             all_buckets: Arc::clone(&all_buckets),
+            scope: scan_scope.clone(),
             digest: scan_plan_digest,
             leader_epoch,
             tier_registry_generation,

crates/scanner/src/scanner_io/tests.rs

@@ -765,6 +765,155 @@ fn bucket_usage_scan_order_prioritizes_dirty_buckets() {
     assert_eq!(names, vec!["dirty", "missing", "cached"]);
 }
 
+fn complete_set_usage_cache(buckets: &[(&str, usize)], scan_plan_digest: DataUsageScanPlanDigest) -> DataUsageCache {
+    let mut cache = DataUsageCache {
+        info: DataUsageCacheInfo {
+            name: DATA_USAGE_ROOT.to_string(),
+            next_cycle: 7,
+            last_update: Some(SystemTime::now()),
+            leader_epoch: 11,
+            source: Some(DataUsageCacheSource::new(1, 2)),
+            snapshot_complete: true,
+            scan_plan_digest: Some(scan_plan_digest),
+            cache_key_format: DATA_USAGE_CACHE_KEY_FORMAT,
+            tier_registry_generation: Some(13),
+            ..Default::default()
+        },
+        ..Default::default()
+    };
+    cache.replace(DATA_USAGE_ROOT, "", DataUsageEntry::default());
+    for (bucket, size) in buckets {
+        cache.replace(
+            bucket,
+            DATA_USAGE_ROOT,
+            DataUsageEntry {
+                size: *size,
+                objects: 1,
+                ..Default::default()
+            },
+        );
+    }
+    cache
+}
+
+#[test]
+fn scoped_set_scan_preserves_unselected_usage_and_drops_deleted_buckets() {
+    let baseline_digest = DataUsageScanPlanDigest([1; 32]);
+    let current_digest = DataUsageScanPlanDigest([2; 32]);
+    let mut old_cache = complete_set_usage_cache(&[("stable", 10), ("dirty", 20), ("deleted", 30)], baseline_digest);
+    old_cache.replace(
+        "stable/prefix",
+        "stable",
+        DataUsageEntry {
+            size: 5,
+            objects: 1,
+            ..Default::default()
+        },
+    );
+    let all_buckets = vec![bucket_info("stable"), bucket_info("dirty")];
+    let selected_buckets = Arc::new(HashSet::from(["dirty".to_string(), "deleted".to_string()]));
+
+    let prepared = prepare_scoped_set_scan(
+        &old_cache,
+        &all_buckets,
+        &all_buckets,
+        &ScannerBucketScanScope {
+            selected_buckets: Some(selected_buckets),
+            baseline_scan_plan_digest: Some(baseline_digest),
+        },
+        ScannerSetCacheGeneration {
+            want_cycle: 8,
+            leader_epoch: 11,
+            tier_registry_generation: 13,
+            source: DataUsageCacheSource::new(1, 2),
+            scan_plan_digest: current_digest,
+        },
+    )
+    .expect("complete matching set cache should support a scoped scan");
+
+    assert_eq!(prepared.buckets.iter().map(|bucket| bucket.name.as_str()).collect::<Vec<_>>(), ["dirty"]);
+    let stable = prepared
+        .cache
+        .checked_flatten("stable")
+        .expect("unselected bucket subtree should be retained");
+    assert_eq!((stable.size, stable.objects), (15, 2));
+    assert_eq!(prepared.cache.find("dirty").map(|entry| (entry.size, entry.objects)), Some((0, 0)));
+    assert!(prepared.cache.find("deleted").is_none());
+    assert_eq!(prepared.cache.info.scan_plan_digest, Some(current_digest));
+    assert_eq!(prepared.cache.info.next_cycle, 8);
+    assert!(!prepared.cache.info.snapshot_complete);
+    assert!(prepared.cache.info.lkg_snapshot_complete);
+    assert_eq!(prepared.cache.info.lkg_next_cycle, Some(7));
+    assert_eq!(prepared.cache.info.lkg_scan_plan_digest, Some(baseline_digest));
+}
+
+#[test]
+fn scoped_set_scan_falls_back_when_an_unselected_bucket_has_no_baseline() {
+    let baseline_digest = DataUsageScanPlanDigest([3; 32]);
+    let old_cache = complete_set_usage_cache(&[("stable", 10)], baseline_digest);
+    let all_buckets = vec![bucket_info("stable"), bucket_info("new")];
+
+    assert!(
+        prepare_scoped_set_scan(
+            &old_cache,
+            &all_buckets,
+            &all_buckets,
+            &ScannerBucketScanScope {
+                selected_buckets: Some(Arc::new(HashSet::from(["dirty".to_string()]))),
+                baseline_scan_plan_digest: Some(baseline_digest),
+            },
+            ScannerSetCacheGeneration {
+                want_cycle: 8,
+                leader_epoch: 11,
+                tier_registry_generation: 13,
+                source: DataUsageCacheSource::new(1, 2),
+                scan_plan_digest: DataUsageScanPlanDigest([4; 32]),
+            },
+        )
+        .is_none()
+    );
+}
+
+#[test]
+fn scoped_set_scan_requires_an_exact_complete_baseline() {
+    let baseline_digest = DataUsageScanPlanDigest([5; 32]);
+    let all_buckets = vec![bucket_info("dirty")];
+    let scope = ScannerBucketScanScope {
+        selected_buckets: Some(Arc::new(HashSet::from(["dirty".to_string()]))),
+        baseline_scan_plan_digest: Some(baseline_digest),
+    };
+    let generation = ScannerSetCacheGeneration {
+        want_cycle: 8,
+        leader_epoch: 11,
+        tier_registry_generation: 13,
+        source: DataUsageCacheSource::new(1, 2),
+        scan_plan_digest: DataUsageScanPlanDigest([6; 32]),
+    };
+
+    let mut incomplete = complete_set_usage_cache(&[("dirty", 10)], baseline_digest);
+    incomplete.info.snapshot_complete = false;
+    assert!(prepare_scoped_set_scan(&incomplete, &all_buckets, &all_buckets, &scope, generation).is_none());
+
+    let mut not_durable = complete_set_usage_cache(&[("dirty", 10)], baseline_digest);
+    not_durable.info.last_update = None;
+    assert!(prepare_scoped_set_scan(&not_durable, &all_buckets, &all_buckets, &scope, generation).is_none());
+
+    let mut wrong_digest = complete_set_usage_cache(&[("dirty", 10)], baseline_digest);
+    wrong_digest.info.scan_plan_digest = Some(DataUsageScanPlanDigest([7; 32]));
+    assert!(prepare_scoped_set_scan(&wrong_digest, &all_buckets, &all_buckets, &scope, generation).is_none());
+
+    let empty_scope = ScannerBucketScanScope {
+        selected_buckets: Some(Arc::new(HashSet::new())),
+        baseline_scan_plan_digest: Some(baseline_digest),
+    };
+    let complete = complete_set_usage_cache(&[("dirty", 10)], baseline_digest);
+    assert!(prepare_scoped_set_scan(&complete, &all_buckets, &all_buckets, &empty_scope, generation).is_none());
+
+    let mut future_cache = complete_set_usage_cache(&[("dirty", 10)], baseline_digest);
+    future_cache.info.next_cycle = generation.want_cycle.saturating_add(1);
+    assert!(prepare_scoped_set_scan(&future_cache, &all_buckets, &all_buckets, &scope, generation).is_none());
+}
+
 #[test]
 fn record_set_scan_failure_preserves_first_error() {
     let mut first = None;

docs/architecture/ilm-tiering-persistence-contracts.md

@@ -41,7 +41,7 @@ All keys below are objects in the internal metadata bucket. The table gives the
 
 | Protocol | Current schema/version | Canonical key | Creator and cleanup owner | Authoritative identity and mutable fields | Current durability point |
 |---|---|---|---|---|---|
-| Transition transaction | `rustfs-transition-transaction-v1` | `ilm/transition-transactions/records/<aa>/<bb>/<transaction-id>.json` | The transition attempt creates it; transition commit/recovery cleans it | Immutable/fence identity: deployment, transaction, fixed `owner_epoch`, write, source identity, tier/backend fingerprint, canonical remote object, deadline. Mutable: state, remote version, revision. `TransitionCleanupProof` is only a transient admission input to `mark_cleanup_pending`; it is not persisted in the record | Maximum-parity config write. Current create/update/delete calls do not use ETag preconditions |
+| Transition transaction | `rustfs-transition-transaction-v1`; successor v2 is approved below but not implemented | `ilm/transition-transactions/records/<aa>/<bb>/<transaction-id>.json` | The transition attempt creates it; transition commit/recovery cleans it | Immutable/fence identity: deployment, transaction, fixed v1 `owner_epoch`, write, source identity, tier/backend fingerprint, canonical remote object, deadline. Mutable: state, remote version, revision. `TransitionCleanupProof` is only a transient admission input to `mark_cleanup_pending`; it is not persisted in the record | Create-only maximum-parity write; exact record and ETag read before successor `If-Match`; terminal receipt followed by exact ETag conditional delete |
 | Tier mutation peer intent | `rustfs-tier-mutation-intent-v1` | `tier/mutation-intents/records/<aa>/<bb>/<mutation-id>.json` | The receiving peer creates and converges it; the mutation recovery path cleans it | Immutable: mutation ID/kind, old config ETag, candidate digest, sorted affected target identities, expiry. Mutable: revision, state, committed config ETag | Create with `If-None-Match: *`; transition/delete with ETag `If-Match`; maximum parity |
 | Tier mutation coordinator intent | `rustfs-tier-mutation-intent-v1` | `tier/mutation-intents/coordinators/<aa>/<bb>/<mutation-id>.json` | The initiating node creates it; coordinator recovery cleans it after peer convergence | Same mutation identity and mutable fields as the peer record | Same conditional-write contract as the peer intent |
 | Manual job | `rustfs-manual-transition-job-v1` | `ilm/manual-transition/jobs/<aa>/<bb>/<job-id>.json` | The admin run creates it; the active owner or recovery lease advances it. There is no current record GC owner | Immutable: job ID, bucket-level scope, options, creation time. Mutable: owner/lease, state, cancel bit, cursor, progress/report, queue snapshot, timestamps/error | Initial UUID-key write uses maximum parity without create-only precondition; later updates use ETag CAS |
@@ -54,6 +54,7 @@ All keys below are objects in the internal metadata bucket. The table gives the
 | Tier-delete chunk parent | Version 1 with `record_type = "chunked_parent"` | `ilm/tier-delete-dispatch-manifests/<scope-digest>.json` | The over-limit prefix-delete coordinator creates and advances it; parent recovery advances completed children and removes the terminal parent | Immutable operation, bucket/incarnation/prefix/topology; mutable monotonic revision, next child sequence, completed journal count, one optional exact child binding, and `Active`/`Completed` state | Create-only and fenced ETag CAS. The parent binds a `Preparing` child before it can become `DispatchAuthorized`; final `Completed` follows an error-free, non-truncated empty-candidate rescan and local prefix deletion |
 | Decommission durable-namespace receipt | `v2` | `decommission/ilm-receipts/<run-token>/<source-path>/<id-kind>/<id>.json` | The decommission coordinator writes target/source proof and is the only cleanup owner for that run | Source path, namespace and record identity, monotonic checkpoint, optional terminal checkpoint, optional v6 topology generation | Create-only then ETag CAS merge; checksum envelope; maximum parity |
 | Decommission expected-receipt manifest | `v1` | `decommission/ilm-manifests/<run-token>.json` | The source-pool decommission coordinator creates and cleans it | Run token plus exact sorted receipt-path count/digest | Create-only, exact readback, and verification before pool removal |
+| Recovery control, export, and disposition | `rustfs-ilm-recovery-control-v1`, `rustfs-ilm-recovery-export-v1`, and `rustfs-ilm-recovery-disposition-v1` are approved below but not implemented | `ilm/recovery-controls/...`, `ilm/recovery-exports/...`, and `ilm/recovery-dispositions/...` under protocol/shard/operation identities | Recovery owns one control for an exact source generation; the authenticated operator creates immutable export/disposition evidence; their collectors never own remote DELETE | Source protocol/path, all-pool copy-set manifest, ETags/content digests, owner lease, retry state, redacted error code, action, actor/reason, and terminal proof | Create-only, ETag CAS, all-pool strong readback, terminal receipt when covered by decommission, and exact conditional cleanup |
 
 `durable_namespace.rs` registers exactly the two tier-journal namespaces, the dispatch-record namespace shared by single manifests, chunk children, and chunk parents, the transaction namespace, and four manual-job namespaces. A path beginning with `ilm/` that is not in that registry is an error during decommission rather than an ignorable object.
 
@@ -71,7 +72,7 @@ The internal config layer supplies maximum-parity writes, create-only writes, ET
 | Conditional delete | Removes only the verified terminal generation; if an active decommission covers it, its terminal receipt is written first |
 | Strong readback | Resolves a lost response only when key, schema, full immutable identity, state, and expected successor all match |
 
-Tier mutation intents and v6 journal/manifest records use the conditional primitives. Manual job updates, scope admission, and decommission receipts also use CAS after creation. The transition transaction currently carries a fixed `owner_epoch` fence identity and a mutable `revision`, but persists with unconditional writes and deletes; those fields therefore detect some in-memory misuse but are not yet a durable exclusion fence. Changing `owner_epoch` during takeover is not current behavior and remains an open design. The manual job's initial UUID-key write has the same create-only gap, although all later owner/lease updates are CAS-protected.
+Tier mutation intents and v6 journal/manifest records use the conditional primitives. Manual job updates, scope admission, and decommission receipts also use CAS after creation. Transition transaction v1 now uses create-only installation, exact record plus ETag read before each successor CAS, and exact ETag terminal deletion. Its `owner_epoch` and `not_after_unix_nanos` remain immutable, however, so an expired recovery worker claims only the next state generation rather than a renewable durable owner lease. The manual job's initial UUID-key write still lacks create-only installation, although all later owner/lease updates are CAS-protected.
 
 ### Approved target
 
@@ -81,7 +82,7 @@ Tier mutation intents and v6 journal/manifest records use the conditional primit
 - After a timeout, connection loss, or quorum-uncertain response, the caller must strongly reread. Only the exact intended successor is success; predecessor, absence, conflict, corruption, or unavailable readback retains the record and blocks destructive action.
 - A process-local mutex, cancellation token, task registry, or cached generation may reduce duplicate work but cannot authorize publication, rollback, or remote deletion.
 
-The exact transition-transaction lease/takeover fields and whether the existing `not_after` becomes the owner expiry are an **open design**. They must be settled with upgrade/downgrade behavior before the v1 schema changes.
+The approved transition-transaction successor, lease/takeover fields, v1 migration, and upgrade/downgrade gates are specified in [Bounded recovery control and operator disposition](#bounded-recovery-control-and-operator-disposition). They require implementation and fleet gating before any v2 writer or destructive v1 takeover is enabled.
 
 ## Lock and operation order
 
@@ -89,18 +90,19 @@ Lock ordering is part of the recovery contract. Callers acquire only the locks n
 
 | Path | Current acquisition order | Operations allowed while held | Operations forbidden while held |
 |---|---|---|---|
-| Tier edit/remove/clear | Tier-config namespace WRITE lock; dedicated owned `admin_updates` serialization mutex; short `TierConfigMgr` state locks only while accessing manager/runtime state | The dedicated `admin_updates` guard intentionally spans awaited backend validation/probes, peer Prepare/Commit/Abort RPC, reference scans, config CAS, and candidate publication in the current protocol | Ordinary manager `RwLock` and runtime-state `Mutex` guards must not cross awaited network I/O; that rule does not prohibit the dedicated `admin_updates` guard from spanning those awaits. Remote object DELETE is never part of mutation |
+| Tier add/edit/remove/clear | A short tier-config namespace WRITE lock captures the persisted config ETag, then releases before backend validation. After validation, namespace WRITE then `admin_updates` protect the ETag check and durable coordinator Prepared write. Both guards are released for lease drain, peer Prepare, and reference proof, then reacquired in the same order for final identity checks and config CAS. Both are released again after the coordinator becomes durably Committed | Backend validation, peer fanout, and reference proof run without either exclusive guard. Immediately before config CAS the coordinator revalidates the ETag, candidate digest, exact Prepared intent identity, and intent expiry. The durable Committed intent is recovery authority while peer Commit and local publication finish without the exclusive guards | Ordinary manager `RwLock` and runtime-state `Mutex` guards must not cross awaited network I/O. Recovery must retain an unexpired Prepared coordinator whose old ETag is still current; the old ETag alone is not abandonment proof. Remote object DELETE is never part of mutation |
 | v6 manifest prepare | Caller already holds the bucket-lifecycle WRITE fence; caller acquires a bucket-metadata transaction READ guard covering the Object Lock and bucket-incarnation snapshot and keeps it through local mutation; exact tier-generation leases; fleet/topology proof; for a single dispatch, synthetic manifest-operation WRITE; for a child, parent-operation WRITE then child-operation WRITE | Build and write one immutable bounded journal set and manifest, validate exact set/digest, then authorize local dispatch while both caller-held bucket guards and all leases remain current. A parent binding is durable before child authorization | Remote tier DELETE; per-object worker cleanup; releasing the metadata guard or a required lease before the authorized local mutation completes; child-to-parent nested lock acquisition |
 | v6 manifest/parent recovery | Fleet/topology proof; bucket-lifecycle WRITE lock; then exactly one synthetic manifest- or parent-operation WRITE lock | Read/write manifest, parent, and journal metadata; verify exact set/digest/binding; converge or roll back child records; advance a parent only after child completion | Remote tier DELETE; per-object worker cleanup; rollback after authorization; taking a child lock while holding a parent lock in background recovery |
 | v5 journal destructive recovery | Synthetic per-journal recovery lock; bucket-lifecycle READ lock; exact tier-generation lease; all physical object READ locks in stable pool/set order | Authoritative source/free-version scan; fenced state CAS; for an eligible terminal state, one bounded remote DELETE; conditional record cleanup | Any delete when a lock or lease is lost; publishing local metadata; selecting an arbitrary backend/version |
 | v6 journal destructive recovery | Synthetic per-journal recovery lock; fleet/topology proof; bucket-lifecycle READ lock; exact tier-generation lease; all physical object READ locks in stable pool/set order | Immutable manifest/topology validation, authoritative source/free-version scan, fenced state CAS, and, for an eligible terminal state, one bounded remote DELETE followed by record cleanup | Any delete when a lock, lease, or fleet proof is lost; publishing local metadata; selecting an arbitrary backend/version |
 | Free-version cleanup | Bucket-lifecycle READ lock; exact tier-generation lease; all physical object WRITE locks in stable pool/set order | Exact all-pool scan; bounded remote DELETE; local marker removal; post-delete rescan | Deleting before the free-version is the sole owner or after any fence changes |
 | Transition commit | Existing object commit locks plus exact source identity and tier-generation checks in the transition path | Publish the exact remote tuple into the matching local version | Publishing a tuple after the source identity or generation changes |
-| Transition transaction cleanup | Record validation; exact backend-generation lease inside the probe/delete helper. Current recovery has no explicit bucket-lifecycle/physical-set ownership fence or durable takeover CAS | Identity-bound provider probe and deletion of a known canonical candidate | A tier lease alone does not fence the creator. The approved target requires expired ownership, durable takeover, and exact local/source reread before DELETE |
+| Transition transaction cleanup | Record validation; expiry check; a next-state ETag CAS for cleanup ownership; exact backend-generation lease inside the probe/delete helper. Current recovery has no explicit renewable owner lease or bucket-lifecycle/physical-set ownership fence | Identity-bound provider probe and deletion of a known canonical candidate | The cleanup-state CAS fences a stale predecessor, but the approved target also requires an explicit recovery lease and exact all-pool source reread before DELETE |
+| Recovery artifact quota admission (approved target) | Cluster-scoped recovery-admission WRITE lock first; then the one canonical control/source operation lock and any source-protocol metadata/physical locks in that protocol's existing stable order | Bounded internal artifact inventory, exact source/control validation, and create-only installation plus strong readback of one fully encoded export or disposition candidate | Acquiring admission while holding a control, source, disposition, bucket, physical, migration, or decommission guard; remote backend I/O; source-journal deletion; disposition `Applying`; releasing admission before candidate installation/readback converges |
 | Manual job | Initial maximum-parity job write; then persisted bucket-level scope create/CAS; later short job/task/result metadata operations | List, checkpoint, append tasks before enqueue, append results after work, renew/take over lease | Holding metadata guards across remote transition PUT; treating the local active-job map as cluster authority. A crash between the job write and scope claim can leave `Running` without a scope record |
 | Decommission receipt | Decommission coordinator's source/target record workflow; record-specific conditional writes | Copy/validate durable record, advance receipts, construct and verify expected manifest, conditionally clean exact covered source | Remote tier DELETE; deleting an uncovered or divergent source record |
 
-The tier mutation lock scope is intentionally recorded as **current**, not ideal. Reducing it is allowed only after a durable `Prepared` intent blocks new reference creators across the fleet, existing tier-operation leases drain, and recovery can reconstruct that block without the initiating process. Which network validation can move outside the namespace lock is an **open design**.
+Tier mutation backend validation is outside both exclusive guards and is bound to the persisted ETag snapshot. The initiating task is detached from the admin request so cancellation cannot interrupt validation cleanup. Once the coordinator Prepared record and local fence are durable, lease drain, all-node peer Prepare, and reference proof run without the tier-config namespace or `admin_updates` guard. Recovery treats an unexpired Prepared record as active even while the old config ETag remains current. Both guards are reacquired in namespace-then-admin order, and the ETag, candidate digest, exact intent identity, and expiry are revalidated immediately before config CAS. After the coordinator advances to Committed, the guards are released again for peer Commit and local publication.
 
 ## Transition transaction
 
@@ -114,7 +116,7 @@ UploadStarted -> Uploaded -> LocalCommitStarted -> Committed
              \-> AbortedNoRemote
 ```
 
-Separately, `mark_cleanup_pending` permits proof-checked model edges from `Uploaded`, `UploadOutcomeUnknown`, and `LocalCommitStarted`. Current production code emits `CleanupPending` only when recovery probes `UploadOutcomeUnknown` as `UnversionedPresent` or as `VersionedPresent` with a non-nil identifier. The `Uploaded` abort/recovery path deletes its candidate and transaction record directly, and `LocalCommitStarted` mismatch or missing-source recovery retains the record. The `Uploaded` and `LocalCommitStarted` cleanup edges are currently exercised through the state-machine API and tests, not produced by runtime recovery. States that require a remote delete still require a known `TransitionRemoteVersion` kind. A probed versioned candidate whose identifier parses as a nil UUID is another current special case: recovery exact-deletes it and removes the record without first persisting `CleanupPending`.
+Separately, `mark_cleanup_pending` permits proof-checked model edges from `Uploaded`, `UploadOutcomeUnknown`, and `LocalCommitStarted`. Current production recovery emits `CleanupPending` after an expired `Uploaded` record wins the exact successor CAS, or when an expired `UploadOutcomeUnknown` probe returns `UnversionedPresent` or `VersionedPresent` with a non-nil identifier. `LocalCommitStarted` mismatch or missing-source recovery retains the record; that cleanup edge is currently exercised through the state-machine API and tests, not produced by runtime recovery. States that require a remote delete still require a known `TransitionRemoteVersion` kind. A probed versioned candidate whose identifier parses as a nil UUID is retained and never authorizes remote deletion.
 
 The remote candidate itself is named by `canonical_transition_remote_object` under `ilm/transition-transactions/<bucket-hash>/<transaction shards>/<transaction-id>/<write-id>`. That deterministic identity is what a provider probe or exact cleanup must bind; it is distinct from the internal transaction-record key.
 
@@ -124,13 +126,13 @@ The creator owns the canonical remote candidate until local metadata commits the
 
 | Observed durable state/input | Unique current owner | Current recovery decision | Approved destructive admission |
 |---|---|---|---|
-| `UploadStarted` | Originating transition attempt; current durable exclusion is incomplete | Retain | No delete. The upload may still publish |
-| `UploadOutcomeUnknown`; exact provider probe says missing | Transaction recovery, logically; current record writes do not durably exclude a concurrent worker | Delete the record | Strong probe identity must match transaction/backend; no remote delete occurs |
+| `UploadStarted` | Originating transition attempt; no current recovery successor is emitted | Retain | No delete. The upload may still publish |
+| `UploadOutcomeUnknown`; exact provider probe says missing | Transaction recovery under the exact record generation and recovery lock | Conditionally delete the record | Strong probe identity must match transaction/backend; no remote delete occurs |
 | `UploadOutcomeUnknown`; probe returns `UnversionedPresent` | Transaction recovery, with operator reconcile available after expiry | Persist `CleanupPending`, delete the unversioned candidate, delete the record | Exact transaction/canonical object/backend identity, explicitly unversioned state, durable takeover after owner expiry, current tier lease, and exact reread before cleanup |
 | `UploadOutcomeUnknown`; probe returns `VersionedPresent` with a non-nil exact identifier | Transaction recovery, with operator reconcile available after expiry | Persist `CleanupPending`, exact-delete that versioned candidate, delete the record | Exact transaction/canonical object/backend identity and remote version, durable takeover after owner expiry, current tier lease, and exact reread before cleanup |
-| `UploadOutcomeUnknown`; probe returns `VersionedPresent` whose identifier is a nil UUID | Transaction recovery | Current code directly exact-deletes that versioned candidate and deletes the record; it does not persist `CleanupPending` | This remains a versioned exact-delete candidate and must not be treated as `UnversionedPresent`. The approved target still requires durable takeover, a current tier lease, and exact reread |
+| `UploadOutcomeUnknown`; probe returns `VersionedPresent` whose identifier is a nil UUID | Transaction recovery retains ownership evidence | Retain | A nil identifier is invalid exact-version evidence and never becomes unversioned or remote-delete authority |
 | `UploadOutcomeUnknown`; probe ambiguous, unsupported, or errors | Transaction recovery retains ownership evidence | Retain | No destructive action; operator reconcile may inspect after expiry |
-| `Uploaded` | Originating transition attempt; current recovery can race it because the persisted fence is not CAS-protected | Current code immediately deletes the candidate and record | **Current safety gap:** approved behavior must first prove the creator cannot still commit by expired ownership plus durable takeover/CAS, then recheck that no matching local commit exists |
+| `Uploaded` | Originating transition attempt until expiry; after expiry, the worker that wins `Uploaded -> CleanupPending` by exact ETag CAS | Retain while active; after expiry, persist `CleanupPending`, then recheck and delete the unreferenced candidate or record | Current CAS fences the predecessor, but approved v2 also requires a durable recovery lease, full all-pool source/free-version proof, and before/after fence checks |
 | `LocalCommitStarted`; logical source lookup returns `TRANSITION_COMPLETE` with the same remote object, tier, and remote version | Transition committer until ownership transfers to `xl.meta` | Delete transaction record | Current recovery treats this tuple as ownership transfer. The approved target additionally compares recorded source version ID, data directory, modification time, size, and ETag before conditional terminal cleanup |
 | `LocalCommitStarted`; logical source is missing, its transition tuple differs, or the read is uncertain | Transaction record/recovery | Retain | No remote delete without a separate durable cleanup proof |
 | `CleanupPending`; logical source lookup returns the same current transition predicate | `xl.meta` is remote reachability owner; recovery owns only record cleanup | Delete transaction record | `xl.meta` is owner; do not delete remote. The approved target adds the full recorded source comparison |
@@ -148,12 +150,12 @@ The current background loop runs every 60 seconds, scans at most 1,000 records p
 
 ### Approved target and open design
 
-- Replace unconditional transaction create/update/delete with create-only, ETag CAS, and conditional terminal delete.
+- Preserve the current create-only transaction installation, exact record/ETag successor CAS, and conditional terminal delete, and add mandatory exact-successor strong readback for lost or uncertain responses. No v2 work may regress the existing v1 protections.
 - Recovery of `Uploaded` and cleanup-capable states must acquire durable ownership only after the prior owner's expiry. The recovery worker must reread the exact generation after takeover and before remote DELETE.
 - Preserve and compare source version ID, data directory, modification time, size, and ETag through local commit and recovery before accepting ownership transfer.
 - Recompute and require the exact lowercase sharded path in both transition-transaction and manual-job runtime recovery, and validate a truncated page's continuation token before processing any record from that page.
-- **Open:** owner lease duration, clock-skew allowance, takeover revision encoding, and compatibility for existing v1 records that have only `not_after`/`owner_epoch`.
-- **Open:** bounded retention and an operator disposition for permanently ambiguous records. Until defined, retained ambiguity is safer than collection.
+- The approved v2 owner lease uses the duration, clock-skew allowance, takeover revision, and v1 mapping in [Transition transaction v2 and v1 migration](#transition-transaction-v2-and-v1-migration).
+- Active automatic retries are bounded by the recovery-control policy below. Ambiguous evidence becomes explicit `retained_ambiguous` or `operator_required`; source evidence is never collected merely because it is old.
 
 ## Tier mutation intent
 
@@ -163,14 +165,15 @@ The current background loop runs every 60 seconds, scans at most 1,000 records p
 
 New intents use a 15-minute expiry. A peer-only terminal tombstone is retained until that expiry plus five minutes of clock-skew allowance and until no coordinator record remains. Expiry bounds replay protection; it is not config commit/abort evidence.
 
-The coordinator creates its durable record and peer `Prepare` blocks new reference creation, drains exact tier-operation leases, and proves that edit/remove/clear will not strand authoritative references. The coordinator then conditionally writes tier config, commits peers, publishes the runtime candidate, and clears the block. Per-mutation sharded mutexes serialize local phases only; persisted intent plus tier-config ETag is authoritative.
+The coordinator creates its durable record and peer `Prepare` blocks new reference creation, drains exact tier-operation leases, and proves that edit/remove/clear will not strand authoritative references. Prepare, Commit, and Abort use all-node fanout rather than quorum: independent peer calls use a work-conserving concurrency limit of four, a 30-second per-peer deadline, and a 30-second fanout-wide deadline; Prepare is additionally capped by the intent expiry. The coordinator collects every completed outcome. A timed-out or otherwise ambiguous started Prepare is included in compensating Abort because cancellation does not prove the peer failed to persist its fence; peers not started before the fanout deadline make Prepare fail but do not require Abort. The coordinator then conditionally writes tier config, durably commits the coordinator intent, releases its exclusive guards, requires every prepared peer to commit, publishes the runtime candidate, and clears the block. Per-mutation sharded mutexes serialize local phases only; persisted intent plus tier-config ETag is authoritative.
 
 ### Recovery decisions
 
 | Observed durable state/input | Unique current owner | Current recovery decision | Destructive/config admission |
 |---|---|---|---|
 | `Prepared`; current tier-config digest equals candidate | Coordinator recovery; each peer recovery owns only its matching peer record/block | CAS to `Committed`, replay peer Commit and publish | Exact mutation identity and candidate digest; never infer from expiry |
-| `Prepared`; current config still proves the old ETag/config | Coordinator recovery | Fan out canonical Abort, then CAS `Aborted` | Abort only the matching intent; a delayed matching Prepare converges to the tombstone |
+| `Prepared`; intent is unexpired and current config still proves the old ETag/config | The live coordinator remains owner | Retain `Prepared` and the runtime block | Recovery must not abort work that may still be in lock-free peer Prepare or reference proof |
+| `Prepared`; intent is expired and current config still proves the old ETag/config | Coordinator recovery | Fan out canonical Abort, then CAS `Aborted` | Abort only the matching intent; a delayed matching Prepare converges to the tombstone |
 | `Prepared`; config is a third generation, unreadable, or peer outcome is ambiguous | Coordinator record remains owner of the block | Retain `Prepared` and runtime block | No commit, abort, cleanup, or unblock |
 | `Committed` | Coordinator recovery, with peers owning convergence of their local records | Replay peer Commit/runtime publication; clean exact converged records | Config ETag/digest and peer identity must match |
 | `Aborted` | Coordinator recovery; peer recovery retains the local tombstone | Replay/confirm Abort and clear matching block; retain peer tombstone until expiry plus clock skew and no coordinator | Never roll back config based on timeout alone |
@@ -183,8 +186,8 @@ Intent transitions retry an ETag race at most three times before returning a ret
 ### Approved target and open design
 
 - Keep create-only, ETag CAS, exact identity comparison, canonical Abort tombstones, and lost-response readback.
-- Any shorter configuration-lock window must leave a durable `Prepared` fence installed on every required peer before releasing the broad exclusion scope and must prove recovery restores that fence before admitting reference creators.
-- **Open:** the exact split between backend validation, peer fanout, reference scan, config CAS, and publication; expiry must never replace config-generation proof.
+- The phase split is fixed: ETag snapshot, lock-free backend validation, ETag revalidation, all-node Prepare, reference proof, ETag/digest/intent revalidation, config CAS, all-node Commit, and local publication. Backend validation uses `(old_config_etag, candidate_digest)` as its stable config generation; the durable mutation identity adds `mutation_id`. Runtime driver revisions are not persistence identities and Add does not require one before publication.
+- Lease drain, peer Prepare, and reference proof run outside both exclusive guards after the coordinator Prepared record and local fence are durable. The commit path reacquires namespace WRITE then `admin_updates` and repeats the full generation/identity proof. Expiry is checked as an additional rejection boundary and never replaces config-generation proof.
 - **Open:** a dedicated operator reconcile/status surface and bounded retention for irreconcilable coordinator/peer records.
 
 ## Manual transition job, task, result, and checkpoint
@@ -311,7 +314,149 @@ Single and child manifest preparation is bounded by 200,000 journals and a 32 Mi
 - New destructive prefix paths use only v6 plus either one byte-compatible manifest or one parent-bound sequence of byte-compatible child manifests. No new v1-v5 sole-owner records may be created.
 - Preserve the two-phase authorization barrier: all prepared records, durable barrier, all dispatched records, durable `DispatchAuthorized`, local mutation, journals committed, durable `Completed`, then remote DELETE.
 - Do not downgrade every v6-aware recovery worker while v6 records remain. v5-and-older readers reject and retain v6 records; older nodes may continue producing fallback free-versions until the fleet is homogeneous.
-- **Open:** bounded age/count policy and operator disposition for quarantined v1/v2, incomplete manifests, and repeatedly failing exact deletes. Capacity rejection and recovery throughput must not be “fixed” by weakening ownership proof.
+- Quarantined v1/v2 records, incomplete manifests, and repeatedly failing exact deletes use the bounded retry, explicit operator state, and single-record control surface approved below. Capacity and recovery throughput must not be “fixed” by weakening ownership proof or age-deleting source evidence.
+
+## Bounded recovery control and operator disposition
+
+This section is an **approved target that is not implemented yet**. It closes the ownership, retry, and operator-disposition design required before backlog recovery work can change destructive behavior. It does not authorize an implementation to enable a v2 writer, take over a v1 transaction, or remove a legacy journal until the fleet and storage gates below exist.
+
+### Recovery-control record
+
+Retry scheduling is persisted separately from the source transaction or journal so legacy bytes remain readable and their cleanup ownership does not move. The control record uses schema `rustfs-ilm-recovery-control-v1`, a checksum envelope, a 16 KiB encoded-size limit, strict unknown-field rejection, and this canonical key:
+
+```text
+ilm/recovery-controls/<protocol>/<aa>/<bb>/<source-operation-digest>.json
+```
+
+Export envelopes use `ilm/recovery-exports/<protocol>/<aa>/<bb>/<export-id>.json`; disposition receipts use `ilm/recovery-dispositions/<protocol>/<aa>/<bb>/<disposition-id>.json`. `export-id` is the SHA-256 of the control ID plus exact observed source content/copy-set digests; `disposition-id` is the SHA-256 of the export ID plus the bounded action. Repeating an identical export or disposition reuses and strongly validates the same canonical object; different bytes at that ID are a conflict. Both use strict checksum envelopes and create-only installation. A control or disposition is limited to 16 KiB. An export is limited to the source protocol's own maximum encoded record size plus 64 KiB for its copy manifest and envelope; it stores the source bytes once rather than duplicating identical replica bytes.
+
+Admission is fail-closed and cluster-wide. One control may have at most one export creation and one disposition application in flight. The immutable candidate is fully encoded before quota admission. The cluster-scoped recovery-admission WRITE lock is always outermost; a caller already holding any control, source, disposition, bucket, physical, migration, or decommission guard must release it and restart in the order above. While admission is held, a complete artifact inventory must prove that the projected totals, including the candidate, are at most 10,000 export envelopes, 10,000 disposition receipts, 1 GiB of encoded export data, and 256 MiB of encoded control/disposition data. The create-only candidate installation and exact strong readback complete before the lock is released, so neither a single candidate nor a concurrent node can oversubscribe the pre-create snapshot. A crash before installation leaves no artifact; a lost create response is resolved by exact canonical readback while admission remains serialized or after reacquiring it in the same order. Replaying an existing canonical ID consumes no new count, byte, or rate token. New creations are limited to ten per authenticated actor per minute and 100 cluster-wide per minute, with at most 32 export creations and eight disposition applications executing cluster-wide. Exceeding a count, byte, rate, or concurrency limit returns a retryable capacity result before source mutation; it never evicts evidence, interrupts an admitted operation, or blocks ordinary object I/O. The collector examines at most 100 terminal artifacts per minute and never acquires the admission lock while holding an artifact/source guard.
+
+`source-operation-digest` is SHA-256 over the length-delimited source protocol, canonical source path, and stable semantic operation identity: transaction UUID, journal identity, or manifest operation ID. For corrupt bytes whose semantic ID cannot be trusted, the canonical path plus a `corrupt` domain separator is the stable identity; a replacement at that path conflicts with the existing control instead of resetting its history. The control's immutable identity repeats the protocol, path, stable identity, and record class. Its mutable `observed_source_generation` contains the source schema, source ETag/content SHA-256, and sorted all-pool copy-set digest. The copy set records each authoritative pool/set identity, canonical path, ETag, byte length, and content SHA-256; an unreachable pool, missing ETag, divergent copy, or incomplete listing cannot produce an actionable generation. The remaining mutable generation contains:
+
+- `revision`, an ETag-CAS successor counter;
+- `classification`: `retrying`, `retained_ambiguous`, `corrupt`, `operator_required`, `abandoned`, or `terminal`;
+- `owner_id`, `owner_epoch`, `lease_acquired_at_unix_nanos`, and `lease_expires_at_unix_nanos` while an attempt is owned;
+- monotonic `attempt_count`, `consecutive_failure_count`, `first_failure_at_unix_nanos`, `last_failure_at_unix_nanos`, and `next_attempt_at_unix_nanos`;
+- one bounded enum `last_error_code`; no free-form provider error, endpoint, credential material, request payload, or response body is persisted;
+- for an operator disposition only, the authenticated actor identifier, reason code, confirmation time, exported payload digest, and exact source/control ETags that were confirmed.
+
+The control record is a scheduler and audit fence, not a remote-object owner. It never substitutes for the source record's version, backend, manifest, source-identity, or absence proof. Before every source CAS, local cleanup, or remote request, the worker strongly rereads every authoritative source copy and the control, requires the current observed generation to match, and then applies the source protocol's own locks and proof. A missing, stale, corrupt, divergent, or unavailable control read cannot authorize work.
+
+Control creation is `If-None-Match: *`; every update is exact ETag `If-Match`; response loss requires exact strong readback. A legal source-state CAS does not create a new control. The stable control CAS advances `observed_source_generation` only from the exact predecessor to one source-protocol successor while preserving `first_failure_at_unix_nanos`, lifetime `attempt_count`, and first-seen lineage. If the source CAS succeeded before a crash, recovery accepts the new bytes only after validating that exact legal successor and then converges the old control generation by CAS. A multi-edge jump, semantic-identity change, replacement ETag/content, or unavailable predecessor proof is a conflict and cannot reset counters. Recovery conditionally removes a terminal control only after strongly proving the stable source operation resolved or absent, recording any active decommission terminal receipt, and confirming that no in-flight operator request still names its ETag. `durable_namespace.rs` must register every new namespace, path parser, decoder, size bound, successor relation, and terminal checkpoint before rollout.
+
+### Transition transaction v2 and v1 migration
+
+The successor envelope is `rustfs-transition-transaction-v2`. It preserves the v1 transaction ID, deployment ID, write ID, complete source identity, tier/backend identity, canonical remote object, remote-version state, operation state, and revision. It also records an immutable `origin_format` (`native_v2` or `migrated_v1`), the state-entry revision and predecessor state/revision, and, for migration, the exact source v1 state/revision. These fields make the state history needed for destructive authorization independently checkable instead of inferring it from the current state. The envelope and body reject unknown fields, checksum every field, use no default for a required v2 value, require the existing exact lowercase canonical path, and reject nil UUIDs, nonpositive timestamps, revision zero/overflow, lease inversion, impossible state/revision history, and illegal state/version combinations. It replaces the fixed ownership pair with:
+
+- immutable `creator_epoch` and `creator_not_after_unix_nanos`, copied exactly from v1 `owner_epoch` and `not_after_unix_nanos` during migration;
+- optional `created_at_unix_nanos`; migrated v1 records use `None` rather than inventing an age;
+- mutable `owner_role` (`creator` or `recovery`), `owner_id`, `owner_epoch`, `owner_generation`, `lease_acquired_at_unix_nanos`, and `lease_expires_at_unix_nanos`. `owner_id` is the authenticated stable fleet-node identity; `owner_epoch` is a fresh UUID for one process claim. A node without both identities cannot create, renew, take over, or act on v2.
+
+A native v2 create uses revision and owner generation 1, a fresh non-nil creator owner/epoch, `UploadStarted`, and an unknown remote version. The first rollout keeps the current seven-day creator ownership window. Creator leases are not renewable; a creator that cannot finish inside the safety window stops publishing and leaves the record for recovery. Recovery-owner leases are 15 minutes. The persisted clock-skew allowance is five minutes: an action may start only when its bounded deadline fits before `lease_expires_at - 5 minutes`, and another owner cannot take over until its local time is at least `lease_expires_at + 5 minutes`. A recovery attempt remains capped at five minutes and every remote call remains subject to its narrower client deadline. A recovery renewal is a same-owner, next-revision CAS that strictly extends expiry; a takeover changes `owner_role`, `owner_id`, and `owner_epoch`, increments `owner_generation` and `revision`, and uses the exact observed ETag. Takeover and state advancement are separate CAS operations; one revision cannot both acquire ownership and claim a recovery outcome.
+
+Before migration can be enabled, the fleet must first deploy a v1 creator fence that strongly rereads the exact transaction path, ETag, state, owner epoch, and source generation immediately before local metadata publication and refuses to publish after any migration/takeover change. The fleet then durably disables new v1 admission and proves that every captured creator/recovery process epoch has either acknowledged quiescence or terminated. A paused or unreachable epoch prevents migration. This drain barrier is distinct from format capability advertisement and remains in force until v2 writer admission is enabled.
+
+Only these checksum-valid v1 state/revision pairs are migration inputs: `UploadStarted@1`; `UploadOutcomeUnknown@2`; `AbortedNoRemote@2`; `Uploaded@2` or `Uploaded@3`; `LocalCommitStarted@3` or `LocalCommitStarted@4`; `Committed@4` or `Committed@5`; and `CleanupPending@3`, `CleanupPending@4`, or `CleanupPending@5`. Any other pair is `corrupt`, inspect-only, and cannot be migrated or authorize a probe, local cleanup, or remote DELETE. A native v2 record must prove a legal predecessor edge at its recorded state-entry revision; ownership-only revisions may increase the outer revision but cannot change the recorded state-entry history. Missing, contradictory, or skipped history is corrupt.
+
+An identity-preserving `v1 -> v2` conversion is one legal successor with `revision + 1` and an unchanged remote tuple. The state is unchanged except that every v1 `UploadStarted` maps conservatively to v2 `UploadOutcomeUnknown`. Historical v1 writers could issue PUT while still in `UploadStarted`; no age, fleet version, or current process observation proves that a retained record came from the later pre-PUT-fence writer. It is permitted only when:
+
+1. every node that can create, commit, recover, heal, or decommission the record advertises both `transition_transaction_v2` and `ilm_recovery_control_v1` for the captured fleet/topology generation, the durable v1-admission stop is active, and the process-epoch drain barrier above is complete;
+2. current time is at least the v1 `not_after_unix_nanos` plus five minutes of skew;
+3. the canonical path, checksum, full immutable identity, state, remote-version invariant, source record, and ETag all match the observed v1 generation;
+4. the migration CAS and strong readback install one fresh recovery lease before any state transition or side effect.
+
+The original creator must successfully CAS `UploadStarted -> UploadOutcomeUnknown` before issuing remote PUT, and must CAS the exact current owner generation to `LocalCommitStarted` before publishing local metadata. A v2 takeover therefore fences a delayed creator. An implementation that can issue PUT or publish after losing this CAS is not compatible with this protocol.
+
+After takeover, recovery applies this matrix:
+
+| State | Approved recovery after exact takeover | Required proof before side effect |
+|---|---|---|
+| native-v2 `UploadStarted` | CAS `AbortedNoRemote`, then conditionally remove the terminal transaction | Valid native-v2 history proves the creator was fenced before the mandatory pre-PUT `UploadOutcomeUnknown` CAS; migrated v1 never enters this row and no remote request is made |
+| `UploadOutcomeUnknown` | Probe under the exact backend lease. Missing becomes terminal cleanup; proven unversioned presence or one nonempty, non-nil exact version becomes `CleanupPending`; nil, ambiguous, or unsupported results become `retained_ambiguous` | Exact transaction/control generations, bounded live probe, current tier destination and lease |
+| `Uploaded` | If the exact transitioned tuple or its free-version owns the candidate, remove only the transaction. If the complete original source is still unchanged and no local commit/free-version exists, CAS `CleanupPending`. Otherwise retain | All-pool source/free-version read, full source tuple, bucket incarnation, tier generation, object locks, and post-probe revalidation |
+| `LocalCommitStarted` | Exact committed tuple/free-version means record-only cleanup. A fully unchanged original source with no partial committed tuple may move to `CleanupPending`. Missing, divergent, partial, or unavailable metadata is `retained_ambiguous` | Same all-pool proof, including data directory, modification time, size, ETag, transition transaction ID, remote tuple, and destination identity |
+| `CleanupPending` | Resume the same exact idempotent candidate delete, or remove only the transaction when local ownership transfer is proven | Current owner lease, source/free-version proof, exact tier lease, physical locks, and before/after fence checks |
+| `Committed` | Conditionally remove only the exact terminal transaction when complete local ownership transfer is proven; otherwise classify the record as corrupt or retain it as ambiguous | All-pool strong read matches the complete logical `xl.meta` source identity, transaction ID, remote tuple, destination identity, and any required decommission terminal receipt; no remote DELETE |
+| `AbortedNoRemote` | Conditionally remove the exact terminal transaction | Valid native-v2 pre-PUT history or exact migrated v1 `AbortedNoRemote@2`, exact terminal generation, and any required decommission terminal receipt; no remote DELETE |
+
+Remote DELETE is never admitted directly from `UploadStarted`, `UploadOutcomeUnknown`, `Uploaded`, or `LocalCommitStarted`; it first requires a CAS-protected `CleanupPending` generation with known remote-version semantics. A lost source read, mixed all-pool result, expired lease, failed renewal, or source/control CAS conflict retains the evidence and performs no destructive action.
+
+New writers emit v2 only after the homogeneous fleet gate, durable v1-admission stop, and process-epoch drain barrier are complete. During a rolling upgrade, new readers accept v1 but all writers continue v1 and no v1 takeover/migration occurs. A v1 reader rejects and retains v2. Downgrade is blocked until v2 creation is disabled and all v2 transactions and recovery-control records are drained or exported; live v2 bytes are never rewritten to v1.
+
+### Retry and retention policy
+
+An attempt that loses a CAS or discovers a newer source generation reloads instead of recording a remote failure. A retryable transport timeout, backend 5xx/throttle, metadata quorum outage, or bounded remote-delete failure increments the persisted counters and schedules:
+
+```text
+min(60 seconds * 2^min(consecutive_failure_count - 1, 6), 1 hour)
+```
+
+A deterministic multiplier from 80 to 100 percent, derived from the source-generation digest and attempt count, is applied to that capped base. The jitter can only shorten the delay and therefore never exceeds the one-hour cap; restarts reproduce the same deadline without synchronizing a fleet. Success or a proven source-state advance resets `consecutive_failure_count` but never decreases `attempt_count`. `next_attempt_at_unix_nanos` is only a not-before scheduler hint; ownership and destructive authority still require the lease and source proofs.
+
+After 32 consecutive retryable failures or seven days since `first_failure_at_unix_nanos`, whichever occurs first, the control CAS moves to `operator_required` and automatic attempts stop. Unsupported probes and unknown remote-version semantics move directly to `retained_ambiguous`; corrupt source bytes use `corrupt`; incomplete destructive evidence uses `operator_required`. None is periodically hot-looped. An operator may explicitly request another bounded attempt after the underlying capability or configuration changes, but the request creates a new owner lease and preserves the lifetime attempt count.
+
+This policy bounds automatic work, not evidence lifetime. A source transaction, journal, or manifest is never deleted solely because it is old, numerous, or over a byte threshold. `operator_required` source evidence remains until its protocol reaches a proven terminal state or the legacy-journal disposition below is completed.
+
+Resolved control tombstones are retained for at least 30 days, immutable export envelopes for at least 90 days, and compact completed disposition receipts for at least 365 days. A collector may conditionally remove only a terminal artifact past its floor after proving that the bound source generation is absent where required, no nonterminal successor or active decommission references it, and the terminal audit checkpoint is durable. Capacity pressure blocks new export/disposition work rather than evicting unexpired or nonterminal evidence. Uncertainty retains the artifact; collection never authorizes source or remote deletion.
+
+### Legacy journal and manifest disposition
+
+Journal v1 has neither backend identity nor remote-version authority; v2 has backend identity but still lacks remote-version semantics. Their automatic classification is `retained_ambiguous`, and neither recovery nor an operator action may instantiate a backend or issue remote PUT, GET, probe, or DELETE from those bytes. The approved single-record actions are:
+
+- **inspect**: strictly decode a server-reconstructed canonical journal identity, perform an all-pool strong read, and return a redacted copy-set/content digest, version, quarantine reason, control classification, age information when known, topology readiness, and decommission coverage; it changes nothing and does not return raw object/version fields by default;
+- **export**: after a fresh exact inspect, create-only persist an immutable `rustfs-ilm-recovery-export-v1` envelope containing the raw source bytes and sorted copy manifest, then strongly read it back. The response downloads that envelope rather than rereading the live journal, uses no-store/attachment semantics, and never adds credentials or backend configuration;
+- **abandon after export**: v1 or v2 only; create a `Prepared` `rustfs-ilm-recovery-disposition-v1` receipt bound to the immutable export and every source copy, conditionally remove only those exact local journal generations, prove every bound copy absent with no replacement, and advance the receipt through `Applying` to `Completed`. This accepts a possible remote storage leak and never asserts that cleanup occurred.
+
+Export and abandon require a fresh all-member capability/topology proof including each member's current process epoch; inspect may remain available in a mixed fleet but returns not-ready for mutation. `abandon after export` uses POST and requires `confirm: true`, `action: abandon_remote_cleanup`, `acknowledge_remote_cleanup_abandoned: true`, the export operation ID/digest, source content and copy-set digests, every source ETag, control ETag, and a bounded operator reason code. It is refused while an active decommission or migration receipt covers either record, while physical copy discovery is incomplete, or when the implementation cannot target every discovered copy with its own `If-Match` condition.
+
+The disposition receipt has immutable action/export/control identities and an immutable sorted copy manifest. Its ETag-CAS generation contains state `Prepared`, `Applying`, or `Completed` and a monotonic sorted `confirmed_absent` set naming only entries from that manifest. Before `Prepared -> Applying`, a fresh all-pool read must find every bound copy at its exact ETag/content digest and repeat the fleet, lock, migration, and decommission checks. The manifest can never be widened, reordered, or replaced.
+
+During `Applying`, recovery treats each manifest entry independently while retaining the original all-pool boundary. An entry already in `confirmed_absent` must still be strongly absent with no successor or replacement generation. For an unconfirmed entry, an exact ETag/content match may be conditionally deleted and then added to `confirmed_absent` only after strong absence readback. If a crash or lost response left that exact path absent before the progress CAS, recovery may add it only after the same strong absence, stable source/control generation, topology, process-epoch, migration, and decommission proofs establish that no replacement exists. A different ETag/content, an unbound copy, an unreadable member, or loss of any proof is a conflict and preserves the current progress. Thus a crash after deleting copy A but before recording its progress can converge and continue with copy B without requiring deleted copy A to reappear.
+
+Immediately before each local metadata deletion, the server repeats the applicable all-pool/fleet/lock checks and conditionally targets only the still-unconfirmed exact ETag. Completion requires every immutable manifest entry in `confirmed_absent`, a fresh all-pool proof that all remain absent without replacement, unchanged fleet/process epochs, and no active decommission or migration coverage. A lost final response is success only when strong readback proves the canonical receipt `Completed`. Recovery may repeat only this canonical operation and never creates a tier client or issues a backend request.
+
+Malformed or unsupported bytes whose outer v1/v2 identity cannot be proven are inspect-only and cannot use abandon. Versions v3-v6 never use `abandon after export`. Their known candidate or manifest ownership must converge through the normal exact protocol. An operator may inspect/export and request a bounded retry, but cannot bypass source/free-version proof, manifest membership, topology, or remote-version validation. `Preparing`/`Aborting` manifests may use their existing whole-set rollback; `DispatchAuthorized`/`Completed`, a missing member, a nonempty operation namespace, or any uncertain binding cannot be manually removed.
+
+### Admin and metrics contract
+
+The approved surface is single-record and uses a protocol-specific expected tuple; it does not reuse the legacy metadata-reconcile digest or create a bucket/prefix job:
+
+```text
+GET  /rustfs/admin/v3/ilm/recovery/records?protocol=<protocol>&classification=<classification>&limit=<n>&marker=<opaque>
+GET  /rustfs/admin/v3/ilm/recovery/records/<control-id>
+POST /rustfs/admin/v3/ilm/recovery/records/<control-id>
+GET  /rustfs/admin/v3/ilm/recovery/exports/<export-id>
+```
+
+List and redacted inspect require `admin:ListTier`. Raw export creation/download, retry, or abandon require `admin:SetTier` because legacy bytes can reveal bucket, object, tier, and remote-version information. The default page is 100 records and the hard maximum is 1,000. A truncated page without a continuation marker is an error, and counts from an incomplete scan are labeled incomplete rather than reported as zero or complete.
+
+Inspect returns a 15-minute opaque observation receipt bound to the authenticated actor, canonical record identity, source/copy ETags and digests, topology/fleet generation, every member process epoch, action class, issue/expiry time, and nonce. It is observation evidence, not mutation authority. POST requires that receipt and `confirm: true` for terminal actions, and binds the control ETag/revision/classification, requested action, and export digest when applicable. The server repeats all live proofs; a restarted member, membership change, or process-epoch mismatch invalidates the receipt. Client fields are concurrency guards, not authority. Export download reads the immutable envelope, uses TLS plus `Cache-Control: no-store` and attachment disposition, and never logs the raw payload.
+
+Metrics use bounded labels only:
+
+- `rustfs_ilm_recovery_records{protocol,classification,schema}` and `rustfs_ilm_recovery_oldest_age_seconds{protocol,classification,schema}`;
+- `rustfs_ilm_recovery_attempts_total{protocol,outcome,error_code}`;
+- `rustfs_ilm_recovery_operator_actions_total{protocol,action,outcome}`;
+- scan completeness, corrupt-record, and orphan-control counters.
+
+Every label value is a closed enum. `schema` exposes recognized schema identifiers only; an unrecognized raw value maps to `unknown`, while a recognized future schema disabled by the current fleet maps to `unsupported`. `protocol`, `classification`, `outcome`, `error_code`, and `action` likewise map unknown input to one bounded fallback and never expose decoded or operator-provided text.
+
+Object names, bucket names, tier names, transaction IDs, control IDs, endpoints, ETags, error text, and credentials are never metric labels. Admin output may identify the selected record but redacts credentials and raw backend configuration. Audit/log events use the repository ILM event fields, stable reason codes, authenticated actor, source/control generations, action, and outcome; they do not persist or log provider response bodies.
+
+One canonical source generation counts once regardless of its physical copy count or how many recovery passes observed it. Attempt counters increment once per coordinator attempt, not per replica, CAS retry, or page revisit. Aggregate totals and oldest age are authoritative only after a complete all-pool scan; partial coverage reports `incomplete` and never publishes a false zero. A legacy record's first-seen time comes from its durable control record rather than an inferred object modification time.
+
+### Required protocol fixtures
+
+Implementation acceptance requires deterministic crash/restart and mixed-version fixtures, not timing-only tests. At minimum they cover:
+
+- a historical v1 `UploadStarted@1` whose PUT may have reached the provider, proving migration yields `UploadOutcomeUnknown` and never `AbortedNoRemote` or a direct delete;
+- every accepted v1 state/revision pair above plus checksum-valid impossible pairs such as `CleanupPending@1`, proving impossible history is inspect-only and makes zero backend calls;
+- an in-flight v1 creator interleaved with admission stop, process-epoch drain, migration, takeover, and local publication, proving no stale creator can publish after takeover;
+- `Committed` with complete, missing, partial, divergent, and unavailable all-pool `xl.meta` ownership proof, proving only the complete exact tuple permits record cleanup;
+- an old reader retaining v2, a mixed fleet blocking v2 writer and migration, and downgrade refusing until v2/control records are drained or exported;
+- operator abandon across a crash after one per-copy delete, a lost delete response, a lost progress CAS, a replacement ETag, incomplete topology, and active decommission, proving progress is monotonic, replacements survive, unsafe cases retain evidence, and every case issues zero backend PUT, GET, probe, or DELETE calls;
+- canonical export replay, a crash before candidate installation, a lost create response, concurrent admission at the remaining-byte boundary, and actor/cluster count, byte, rate, and concurrency exhaustion, proving duplicate IDs consume no new quota, projected totals never oversubscribe, and admission failure mutates no source evidence.
 
 ## `xl.meta` free-version boundary
 
@@ -417,7 +562,7 @@ A bucket/prefix/fleet batch reconcile is still an **open design**. It requires a
 
 Decommission cannot treat durable ILM objects as ordinary configuration blobs. `validate_durable_ilm_record` validates namespace, size, schema/checksum, identity, and a protocol-specific checkpoint, and most protocol branches recompute the canonical path. Its transition-transaction branch currently inherits the weaker final-component parser: mismatched shard directories, extra components, and uppercase hex can pass when the final UUID and record contents agree. Exact transition-path validation is therefore an approved target, not a current decommission guarantee. Checkpoint successors enforce journal/manifest legal states, chunk-parent revision/sequence/count/binding progression, transition identity and revision progression, monotonic manual-job progress, scope ownership, and immutable task/result payloads.
 
-The decommission coordinator copies and validates a durable record on a target, persists a receipt for that exact source path/identity/checkpoint, and records the expected receipt set on the source. While a matching decommission operation is active, protocol writers advance receipts as records change and terminal cleanup records a terminal checkpoint before deleting a covered record. Without an active decommission operation, the receipt helper creates no terminal receipt and ordinary protocol recovery proceeds with that protocol's current delete primitive: v6 journal/manifest/parent cleanup uses the exact ETag, while transition-transaction cleanup remains unconditional as documented above. Completion verifies every expected receipt and target checkpoint before the source pool can be removed.
+The decommission coordinator copies and validates a durable record on a target, persists a receipt for that exact source path/identity/checkpoint, and records the expected receipt set on the source. While a matching decommission operation is active, protocol writers advance receipts as records change and terminal cleanup records a terminal checkpoint before deleting a covered record. Without an active decommission operation, the receipt helper creates no terminal receipt and ordinary protocol recovery proceeds with that protocol's current exact ETag conditional-delete primitive. Completion verifies every expected receipt and target checkpoint before the source pool can be removed.
 
 A terminal receipt is proof that an exact target copy reached a terminal checkpoint. It may authorize conditional removal of the matching source record when every active target copy is covered; it never authorizes remote DELETE. A terminal receipt on one target cannot hide a later nonterminal receipt on another target.
 
@@ -427,7 +572,7 @@ Receipts have no enum state. Their legal evolution is `absent -> checkpoint -> m
 
 | Observed state | Unique current owner | Current recovery decision | Destructive admission |
 |---|---|---|---|
-| No active decommission run | Underlying protocol owner | Protocol recovery proceeds normally and no receipt is created. An eligible v6 journal/manifest record is directly removed by exact ETag; transition-transaction cleanup follows its documented current unconditional path | Receipt state grants no remote-delete authority |
+| No active decommission run | Underlying protocol owner | Protocol recovery proceeds normally and no receipt is created. Eligible v6 journal/manifest and transition-transaction records are removed only by their exact observed ETag | Receipt state grants no remote-delete authority |
 | Source and target exact identity/checkpoint agree | Decommission coordinator for the run token | Create or CAS-advance the run-scoped receipt | Successor must be monotonic and topology-bound where required |
 | Receipt already covers the same successor | Decommission coordinator for the run token | Treat as idempotent | Exact identity/checkpoint only |
 | Conflicting receipt, checksum/schema/path error, divergent target record, missing ETag, or non-successor checkpoint | No decommission actor acquires cleanup authority | Fail decommission and retain source | Never overwrite or guess |
@@ -451,7 +596,7 @@ Receipt and expected-manifest create/CAS conflicts retry at most three times. Ex
 
 ### Approved target failure matrix
 
-The matrix below is the normative approved target, not a blanket description of current implementation. Current exceptions are authoritative only where each protocol section above labels them explicitly. In particular, transition-transaction initial and successor writes and deletes are currently unconditional, while the transition transaction's initial write and the manual job's initial write have neither create-only installation nor mandatory lost-response strong-readback convergence.
+The matrix below is the normative approved target, not a blanket description of current implementation. Current exceptions are authoritative only where each protocol section above labels them explicitly. Transition transaction v1 now has create-only installation, exact ETag successor CAS, and conditional terminal deletion, but it still lacks mandatory lost-response exact-successor readback and a renewable durable recovery lease. The manual job's initial write remains non-create-only.
 
 | Event | Approved result |
 |---|---|
@@ -462,19 +607,20 @@ The matrix below is the normative approved target, not a blanket description of
 | Crash after remote DELETE but before journal/free-version cleanup | Retry the same exact idempotent DELETE under the same fences, then conditionally clean local evidence |
 | Cancellation | Stop issuing new work, persist monotonic cancellation where the protocol has it, and leave ambiguous durable records for recovery. Cancellation is never rollback proof after authorization |
 | Rolling upgrade | Gate writers on the minimum capability required by the format. Known older journal/RPC versions follow their explicit compatibility rule; unknown formats are retained |
-| Downgrade | Drain v6 journals before removing all v6-aware workers. Do not write a new format until its downgrade reader behavior and writer gate are specified |
+| Downgrade | Drain v6 journals and any enabled transition-v2/control protocol before removing their capable workers. Do not write a new format until its downgrade reader behavior and writer gate are specified |
 | Corrupt or unknown input | Record a diagnosable failure, retain bytes, and block destructive action/completion |
 
-Transition transaction v1, manual job/task/result v1, and receipt v2 do not currently have a complete persisted-format negotiation for rolling downgrade. Until one is designed, caller/operator orchestration must not enable writers whose records required recovery nodes cannot decode. The manual async endpoint does not enforce that fleet gate and a direct request proceeds to job creation. This caller-side fail-closed rule is stricter than treating an unknown record as absent.
+Transition transaction v1, manual job/task/result v1, and receipt v2 do not currently have an implemented persisted-format negotiation for rolling downgrade. The approved transition-v2/control gate above is not current behavior. Until the applicable gate is implemented, caller/operator orchestration must not enable writers whose records required recovery nodes cannot decode. The manual async endpoint does not enforce that fleet gate and a direct request proceeds to job creation. This caller-side fail-closed rule is stricter than treating an unknown record as absent.
 
 ### Current format compatibility decisions
 
 | Family/version | Current reader and writer behavior | Upgrade, downgrade, and ignore rule |
 |---|---|---|
-| Transition transaction v1 | Writers emit v1; the payload decoder rejects another schema, bad checksum, unknown state, or inconsistent transaction/remote identity. The current record-path parser accepts any shard/extra-component layout and uppercase hex when the final 32-hex UUID parses and matches the payload | There is no intentional ignore path, but exact lowercase canonical-path rejection remains an approved fix. A future schema needs a fleet writer gate and an old-reader retention test before rollout; downgrade behavior is open |
+| Transition transaction v1 | Writers emit v1; the payload decoder rejects another schema, bad checksum, unknown state, or inconsistent transaction/remote identity. The current record-path parser accepts any shard/extra-component layout and uppercase hex when the final 32-hex UUID parses and matches the payload | There is no intentional ignore path, but exact lowercase canonical-path rejection remains an approved fix. V1 remains the only writer format until the approved v2 fleet gate is implemented; a v2 reader never rewrites an active v1 record |
+| Transition transaction v2 and recovery-control/export/disposition v1 | Approved target only; no current reader or writer emits these formats | Roll out read support before the homogeneous writer gate; old readers reject and retain. Disable creation and prove all active records drained before downgrade; never rewrite v2 to v1 |
 | Tier mutation intent v1; peer RPC v3/v4 | Durable readers/writers require intent v1. New peers accept signed/canonical v3 and v4 RPC; old v3 peers return an exact authenticated unsupported response to v4 | Pause and drain edit/remove/clear across the mixed interval; do not automatically retry v4 as v3. Unknown durable intent is retained and blocks recovery |
 | Manual job/scope/task/result v1 | Writers emit the v1 family. Manual-job runtime recovery accepts an uppercase UUID path when both shard strings match its uppercase prefix, then loads the lowercase canonical job by UUID; the decommission validator recomputes the canonical path and rejects that alias. Other decoder/path/checksum failures stop reconciliation. Runtime capabilities advertise `enqueue_only` and `async`, but the async run handler does not consult a fleet capability gate and a direct request creates a job | Runtime recovery still needs exact lowercase canonical-path validation to prevent alias-driven duplicate work. Caller/operator orchestration must verify every required node and fail closed when capability is unknown or unsupported. An automatic server-side fleet gate and persisted downgrade negotiation remain open; unknown records are never ignored as completed work |
-| Journal v1/v2 | Readers decode but quarantine because remote-version authority is missing; compatibility writers can preserve these forms | Retain indefinitely unless a separately approved, authoritative repair protocol resolves them; never translate empty version ID to known-disabled |
+| Journal v1/v2 | Readers decode but quarantine because remote-version authority is missing; compatibility writers can preserve these forms | Never translate empty version ID to known-disabled or authorize remote DELETE. Retain unless the approved exact inspect/export/abandon protocol conditionally removes only the local journal generation |
 | Journal v3/v4 | Readers recover supported committed records according to exact or explicit version-state semantics; current compatible writes use v4 for known state | Unknown/inconsistent state is retained. These legacy paths are not evidence that a new sole-owner operation may omit v5/v6 source proof |
 | Journal v5 | Readers use stable source/all-pool proof; decoded v5 can be checkpointed, while new online sole-owner transactions are not emitted as v5 | Retain and recover conservatively during upgrade. Do not manufacture v5 from older records or use it to bypass v6 manifest authorization |
 | Journal v6, dispatch manifest v1, and chunk parent v1 | v6-aware writers/readers require immutable manifest membership and topology. Complete sets at or below 200,000 retain the legacy root manifest bytes; larger sets install a strict parent at that root and operation-scoped v1 child payloads. Pre-chunking v6 readers reject the parent schema and child paths, while v5-and-older readers reject and retain v6 journals | Gate writers on the current fleet capability and retain the root parent for the entire active chunk sequence. Drain v6 before removing all v6-aware workers; do not downgrade by rewriting a live v6 operation |
@@ -484,10 +630,10 @@ Transition transaction v1, manual job/task/result v1, and receipt v2 do not curr
 
 | Protocol | Current operator/telemetry surface | Current retention | Required follow-up |
 |---|---|---|---|
-| Transition transaction | Expired unknown-upload inspect/delete/finalize routes; `lifecycle_transition_transaction_recovery` diagnostics | Terminal records are deleted; ambiguous and unsafe states may remain indefinitely | Backlog age/count/state metrics, bounded policy, and durable takeover status |
+| Transition transaction | Expired unknown-upload inspect/delete/finalize routes; `lifecycle_transition_transaction_recovery` diagnostics | Terminal records are deleted; ambiguous and unsafe states may remain indefinitely | Implement the approved v2 lease/takeover, recovery-control status, bounded retry, and backlog metrics |
 | Tier mutation intent | Admin mutation response plus recovery diagnostics; no dedicated reconcile API | Peer aborted tombstone through expiry plus skew; ambiguous coordinator/peer records retained | Status/reconcile view for mutation, peer convergence, config generation, and blocked tiers |
 | Manual job | POST run response, GET status, DELETE cancel; runtime capabilities advertise both modes | Job/task/result history is indefinite. Terminalizers only best-effort delete the exact scope; startup skips a terminal job with a leftover scope, which remains until a later admission claimant lazily replaces it | Age/count/bytes limit and a terminal-history/scope GC protocol that preserves recovery evidence |
-| Tier-delete journal/manifest | `lifecycle_tier_delete_journal` events, quarantined counter, remote-delete failure/breaker/inflight metrics | Terminal records converge; quarantined/ambiguous records are unbounded by age | Safe operator inspection/disposition, backlog age/count by version/state, bounded recovery without evidence loss |
+| Tier-delete journal/manifest | `lifecycle_tier_delete_journal` events, quarantined counter, remote-delete failure/breaker/inflight metrics | Terminal records converge; quarantined/ambiguous records are unbounded by age | Implement the approved single-record inspect/export/disposition, bounded retry controls, and logical backlog metrics |
 | Decommission receipt | Decommission state/events including `receipt_cleanup_failed` | Completion triggers only best-effort receipt/manifest cleanup. Delete failures reported as `receipt_cleanup_failed`, as well as abandoned runs, can leave run-scoped records behind | Run-scoped retention and resume-safe cleanup policy |
 
 Retention is a protocol transition, not raw deletion. Any collector must name its unique owner, minimum age/count/bytes bound, exact terminal or quarantine predicate, readback behavior, decommission interaction, and audit/metric output. It may not collect a record solely because it is old.

docs/operations/tier-ilm-debugging.md

@@ -154,6 +154,60 @@ Historical transition transactions in `upload_outcome_unknown` state can use an
 
 `finalize_missing` re-runs the provider probe and fails closed for `unversioned_present`, `versioned_present`, `ambiguous`, `unsupported`, or probe errors. It never accepts an operator assertion in place of a live `missing` result. Providers without an authoritative probe or exact version deletion remain pending; the endpoint does not infer provider capabilities, accept external absence assertions, or select a candidate automatically.
 
+## Inspect and disposition retained recovery records
+
+This section describes an **approved target that is not implemented yet**. Current servers do not expose the routes below and continue to quarantine tier-delete journal v1/v2 records. Do not remove internal metadata objects by hand: that loses ETag, all-pool, decommission, export, and audit guarantees.
+
+The approved read-only inventory is bounded and paginated:
+
+```text
+GET /rustfs/admin/v3/ilm/recovery/records?protocol=<protocol>&classification=<classification>&limit=<n>&marker=<opaque>
+GET /rustfs/admin/v3/ilm/recovery/records/<control-id>
+```
+
+List and redacted inspect require `admin:ListTier`. The server reconstructs the canonical source identity, strongly reads every authoritative copy, and reports one logical record with its schema, classification (`retrying`, `retained_ambiguous`, `corrupt`, `operator_required`, `abandoned`, or `terminal`), stable reason code, copy/content digests, retry deadline/counters, fleet readiness, scan completeness, and decommission coverage. It does not return raw legacy bytes, object/version names, endpoints, credentials, or provider error text in the default JSON. Incomplete pool coverage, divergent copies, a missing ETag, corruption, or a truncated page without a continuation marker is fail-closed and cannot produce an actionable receipt.
+
+Inspect returns a 15-minute opaque observation receipt. It binds the authenticated actor, canonical record, every source copy/ETag/digest, topology/fleet generation, requested action class, issue/expiry time, and nonce. The receipt prevents a stale request from widening its target; it is not cleanup authority.
+
+For a strictly decoded v1/v2 tier-delete journal, the approved evidence-preserving flow is:
+
+1. Inspect the exact record and independently decide whether retaining the local cleanup obligation is still useful.
+2. With `admin:SetTier`, create an immutable server-side export from the current observation receipt. The export contains the exact raw journal bytes and copy manifest, is installed create-only at the canonical digest-derived export ID, strongly read back, and downloaded through a no-store attachment response:
+
+   ```text
+   POST /rustfs/admin/v3/ilm/recovery/records/<control-id>
+   { "action": "export", "observation_receipt": "<opaque>" }
+
+   GET /rustfs/admin/v3/ilm/recovery/exports/<export-id>
+   ```
+
+3. Only after preserving that export, submit a fresh exact disposition with `admin:SetTier`:
+
+   ```json
+   POST /rustfs/admin/v3/ilm/recovery/records/<control-id>
+   {
+     "action": "abandon_remote_cleanup",
+     "confirm": true,
+     "acknowledge_remote_cleanup_abandoned": true,
+     "observation_receipt": "<opaque>",
+     "export_id": "<export-id>",
+     "export_sha256": "<sha256>",
+     "reason_code": "<bounded-operator-reason>"
+   }
+   ```
+
+The last action removes only the exact local v1/v2 journal generations by per-copy `If-Match` after a durable `Prepared` disposition receipt and fresh all-member capability proof. The receipt advances `Prepared -> Applying -> Completed` and records a monotonic per-copy `confirmed_absent` set. If the server deletes copy A and crashes before recording progress, recovery may confirm A absent under the unchanged source/control, topology, process-epoch, migration, and decommission proofs, persist that progress, and continue with still-exact copy B. A replacement ETag is always a conflict; recovery never widens the immutable copy manifest.
+
+The action never creates a tier client, probes a backend, or issues remote PUT/GET/DELETE. Its meaning is deliberately narrow: the operator accepts that remote storage may leak and abandons RustFS cleanup after preserving evidence. A changed copy, active decommission, missing member, topology/process restart, incomplete read, or uncertain replacement proof retains the evidence. Success requires every bound copy be durably confirmed absent, a fresh all-member/decommission proof, and the disposition receipt durably `Completed`; response loss resumes only the same canonical operation ID.
+
+Canonical replay of an identical export/disposition consumes no new quota. New operations require a complete artifact inventory and are refused before source mutation when the projected retained total, including the fully encoded candidate, would exceed 10,000 exports, 10,000 disposition receipts, 1 GiB of encoded export data, or 256 MiB of encoded control/disposition data. The quota decision, create-only installation, and exact readback share one cluster-scoped admission WRITE lock. That lock is always acquired before control/source/disposition and physical metadata locks and is released before disposition `Applying` or any source deletion; callers never acquire it while holding those inner guards. A crash before installation consumes no capacity, and lost installation response is resolved by canonical readback under the same serialized order, so concurrent nodes cannot oversubscribe a stale snapshot. Admission is also limited to ten new creations per actor per minute, 100 cluster-wide per minute, 32 concurrent exports, and eight concurrent dispositions. Capacity pressure never evicts recovery evidence or blocks ordinary object I/O; the collector examines at most 100 terminal artifacts per minute.
+
+Malformed/unsupported records and journal v3-v6 cannot use abandon. Known-version and v6 manifest ownership must converge through their normal exact recovery protocol. Operators may inspect, export, and request a bounded retry, but cannot bypass source/free-version proof, manifest membership, topology, or version semantics.
+
+Automatic retry state survives restart. Retryable transport/quorum failures use a 60-second exponential base capped at one hour and a deterministic 80-to-100-percent multiplier, so jitter never increases the capped delay. After 32 consecutive failures or seven days from the first persisted failure, automatic work stops at `operator_required`. Unsupported or ambiguous evidence goes directly to `retained_ambiguous`/`operator_required`; age alone never deletes it. Resolved controls, immutable exports, and completed disposition receipts have minimum 30-day, 90-day, and 365-day retention respectively, and are collected only after exact source absence, decommission, successor, and audit checks.
+
+The full schema, lease, mixed-version, retry, privacy, and metric requirements are in [../architecture/ilm-tiering-persistence-contracts.md](../architecture/ilm-tiering-persistence-contracts.md#bounded-recovery-control-and-operator-disposition).
+
 ## Reconcile legacy transition-version metadata
 
 This section describes an **approved target that is not implemented yet**. The current server has no admin route that backfills a missing `transitioned-version-state` in `xl.meta`. Do not use the transaction reconcile route above for this purpose: that route owns an upload transaction candidate and may delete it, while legacy metadata reconciliation is non-destructive and may update only the exact local metadata version.

rustfs/src/version.rs

@@ -14,8 +14,6 @@
 
 use const_str::concat;
 use shadow_rs::shadow;
-use std::path::Path;
-use std::process::Command;
 
 shadow!(build);
 
@@ -47,10 +45,6 @@ pub const DISPLAY_VERSION: &str = {
 
 type VersionParseResult = Result<(u32, u32, u32, Option<String>), Box<dyn std::error::Error>>;
 
-fn build_version_override() -> Option<&'static str> {
-    BUILD_VERSION_OVERRIDE.filter(|version| !version.is_empty())
-}
-
 fn version_ref(version: &str) -> String {
     if version.starts_with("refs/tags/") || version.starts_with('@') {
         version.to_string()
@@ -61,91 +55,7 @@ fn version_ref(version: &str) -> String {
 
 #[allow(clippy::const_is_empty)]
 pub fn get_version() -> String {
-    if let Some(version) = build_version_override() {
-        return version_ref(version);
-    }
-
-    // Get the latest tag
-    if let Ok(latest_tag) = get_latest_tag() {
-        // Check if current commit is newer than the latest tag
-        if is_head_newer_than_tag(&latest_tag) {
-            // If current commit is newer, increment the version number
-            if let Ok(new_version) = increment_version(&latest_tag) {
-                return format!("refs/tags/{new_version}");
-            }
-        }
-
-        // If current commit is the latest tag, or version increment failed, return current tag
-        return format!("refs/tags/{latest_tag}");
-    }
-
-    // If no tag exists, use original logic
-    if !build::TAG.is_empty() {
-        format!("refs/tags/{}", build::TAG)
-    } else if !build::SHORT_COMMIT.is_empty() {
-        format!("@{}", build::SHORT_COMMIT)
-    } else {
-        format!("refs/tags/{}", build::PKG_VERSION)
-    }
-}
-
-/// Get the latest git tag
-fn get_latest_tag() -> Result<String, Box<dyn std::error::Error>> {
-    let output = Command::new("git").args(["describe", "--tags", "--abbrev=0"]).output()?;
-
-    if output.status.success() {
-        let tag = String::from_utf8(output.stdout)?;
-        Ok(tag.trim().to_string())
-    } else {
-        Err("Failed to get latest tag".into())
-    }
-}
-
-/// Check if current HEAD is newer than specified tag
-fn is_head_newer_than_tag(tag: &str) -> bool {
-    is_head_newer_than_tag_in(Path::new("."), tag)
-}
-
-fn is_head_newer_than_tag_in(repo: &Path, tag: &str) -> bool {
-    let head = Command::new("git").current_dir(repo).args(["rev-parse", "HEAD"]).output();
-    let tag_commit = Command::new("git")
-        .current_dir(repo)
-        .args(["rev-list", "-n", "1", tag])
-        .output();
-
-    let (Ok(head), Ok(tag_commit)) = (head, tag_commit) else {
-        return false;
-    };
-
-    if !head.status.success() || !tag_commit.status.success() || head.stdout == tag_commit.stdout {
-        return false;
-    }
-
-    let output = Command::new("git")
-        .current_dir(repo)
-        .args(["merge-base", "--is-ancestor", tag, "HEAD"])
-        .output();
-
-    match output {
-        Ok(result) => result.status.success(),
-        Err(_) => false,
-    }
-}
-
-/// Increment version number (increase patch version)
-fn increment_version(version: &str) -> Result<String, Box<dyn std::error::Error>> {
-    // Parse version number, e.g. "1.0.0-alpha.19" -> (1, 0, 0, Some("alpha.19"))
-    let (major, minor, patch, pre_release) = parse_version(version)?;
-
-    // If there's a pre-release identifier, increment the pre-release version number
-    if let Some(pre) = pre_release
-        && let Some(new_pre) = increment_pre_release(&pre)
-    {
-        return Ok(format!("{major}.{minor}.{patch}-{new_pre}"));
-    }
-
-    // Otherwise increment patch version number
-    Ok(format!("{major}.{minor}.{}", patch + 1))
+    version_ref(DISPLAY_VERSION)
 }
 
 /// Parse version number
@@ -166,28 +76,6 @@ pub fn parse_version(version: &str) -> VersionParseResult {
     Ok((major, minor, patch, pre_release))
 }
 
-/// Increment pre-release version number
-fn increment_pre_release(pre_release: &str) -> Option<String> {
-    // Handle pre-release versions like "alpha.19"
-    let parts: Vec<&str> = pre_release.split('.').collect();
-    if parts.len() == 2
-        && let Ok(num) = parts[1].parse::<u32>()
-    {
-        return Some(format!("{}.{}", parts[0], num + 1));
-    }
-
-    // Handle pre-release versions like "alpha19"
-    if let Some(pos) = pre_release.rfind(|c: char| c.is_alphabetic()) {
-        let prefix = &pre_release[..=pos];
-        let suffix = &pre_release[pos + 1..];
-        if let Ok(num) = suffix.parse::<u32>() {
-            return Some(format!("{prefix}{}", num + 1));
-        }
-    }
-
-    None
-}
-
 /// Clean version string - removes common prefixes
 pub fn clean_version(version: &str) -> String {
     version
@@ -284,34 +172,6 @@ mod tests {
     use super::*;
     use tracing::debug;
 
-    fn run_git(repo: &Path, args: &[&str]) {
-        let status = Command::new("git").current_dir(repo).args(args).status().unwrap();
-        assert!(status.success(), "git command failed: git {}", args.join(" "));
-    }
-
-    #[test]
-    fn test_is_head_newer_than_tag_requires_strict_descendant() {
-        let repo = tempfile::tempdir().unwrap();
-        run_git(repo.path(), &["init", "--quiet"]);
-        run_git(repo.path(), &["config", "user.name", "RustFS Tests"]);
-        run_git(repo.path(), &["config", "user.email", "rustfs@example.com"]);
-        run_git(repo.path(), &["commit", "--allow-empty", "--quiet", "-m", "tagged commit"]);
-        run_git(repo.path(), &["tag", "--annotate", "1.2.3", "--message", "1.2.3"]);
-
-        assert!(!is_head_newer_than_tag_in(repo.path(), "1.2.3"));
-
-        run_git(repo.path(), &["commit", "--allow-empty", "--quiet", "-m", "newer commit"]);
-
-        assert!(is_head_newer_than_tag_in(repo.path(), "1.2.3"));
-    }
-
-    #[test]
-    fn build_version_override_is_used_for_current_version_when_set() {
-        if let Some(version) = build_version_override() {
-            assert_eq!(get_version(), version_ref(version));
-        }
-    }
-
     #[test]
     fn version_ref_keeps_existing_ref_prefixes() {
         assert_eq!(version_ref("1.2.3"), "refs/tags/1.2.3");
@@ -319,6 +179,11 @@ mod tests {
         assert_eq!(version_ref("@abc123"), "@abc123");
     }
 
+    #[test]
+    fn get_version_uses_build_metadata() {
+        assert_eq!(get_version(), version_ref(DISPLAY_VERSION));
+    }
+
     #[test]
     fn test_parse_version() {
         // Test standard version parsing
@@ -336,27 +201,6 @@ mod tests {
         assert_eq!(pre_release, Some("alpha.19".to_string()));
     }
 
-    #[test]
-    fn test_increment_pre_release() {
-        // Test alpha.19 -> alpha.20
-        assert_eq!(increment_pre_release("alpha.19"), Some("alpha.20".to_string()));
-
-        // Test beta.5 -> beta.6
-        assert_eq!(increment_pre_release("beta.5"), Some("beta.6".to_string()));
-
-        // Test unparsable case
-        assert_eq!(increment_pre_release("unknown"), None);
-    }
-
-    #[test]
-    fn test_increment_version() {
-        // Test pre-release version increment
-        assert_eq!(increment_version("1.0.0-alpha.19").unwrap(), "1.0.0-alpha.20");
-
-        // Test standard version increment
-        assert_eq!(increment_version("1.0.0").unwrap(), "1.0.1");
-    }
-
     #[test]
     fn test_version_format() {
         // Test if version format starts with refs/tags/