diff --git a/other/java/client/src/main/proto/filer.proto b/other/java/client/src/main/proto/filer.proto
index f0bf1d6371..99ee449afd 100644
--- a/other/java/client/src/main/proto/filer.proto
+++ b/other/java/client/src/main/proto/filer.proto
@@ -527,6 +527,11 @@ message DeleteEntryRequest {
     int64 if_not_modified_after = 9;    // unix time in seconds
     bool keep_remote_object = 10;
     int64 if_not_modified_after_ns = 11; // unix time in nanoseconds; overrides if_not_modified_after when set
+    // Optional precondition evaluated against the entry atomically with the
+    // delete, under the filer's per-path lock. The request is routed to the
+    // entry's owner filer for the check to be authoritative.
+    map<string, bytes> expected_extended = 12;
+    bool is_moved = 13;             // set on a forwarded request so the owner applies it locally
 }
 
 message DeleteEntryResponse {
diff --git a/seaweed-vector/crates/core/src/query.rs b/seaweed-vector/crates/core/src/query.rs
index 420afb69fb..89c33f3f0f 100644
--- a/seaweed-vector/crates/core/src/query.rs
+++ b/seaweed-vector/crates/core/src/query.rs
@@ -167,6 +167,9 @@ mod tests {
     use super::*;
     use crate::table::VectorTable;
     use crate::testing::{DIM, write_dataset};
+    use arrow_array::{FixedSizeListArray, RecordBatchIterator, types::Float32Type};
+    use arrow_schema::{DataType, Field, Schema};
+    use std::sync::Arc;
     use tempfile::TempDir;
 
     fn l2(a: &[f32], b: &[f32]) -> f32 {
@@ -240,6 +243,135 @@ mod tests {
         assert_eq!(hits[1].key, "k2");
     }
 
+    #[tokio::test]
+    async fn filter_matches_json_types_exactly() {
+        let dir = TempDir::new().unwrap();
+        let metas = vec![
+            r#"{"k": 3}"#,      // k0: number
+            r#"{"k": "3"}"#,    // k1: numeric string
+            r#"{"k": true}"#,   // k2: bool
+            r#"{"k": "abc"}"#,  // k3: non-numeric string
+            r#"{"x": 1}"#,      // k4: missing key
+            r#"{"k": [1, 2]}"#, // k5: array
+            r#"{"k": null}"#,   // k6: null
+            r#"{"k": 1}"#,      // k7: serializes to '1', castable to boolean
+            r#"{"k": 0}"#,      // k8: serializes to '0', castable to boolean
+        ];
+        let schema = Arc::new(Schema::new(vec![
+            Field::new("key", DataType::Utf8, false),
+            Field::new(
+                "vector",
+                DataType::FixedSizeList(
+                    Arc::new(Field::new("item", DataType::Float32, true)),
+                    DIM as i32,
+                ),
+                false,
+            ),
+            Field::new("metadata", DataType::Utf8, true).with_metadata(
+                [("ARROW:extension:name".to_string(), "arrow.json".to_string())]
+                    .into_iter()
+                    .collect(),
+            ),
+        ]));
+        let keys: Vec<String> = (0..metas.len()).map(|i| format!("k{i}")).collect();
+        let batch = RecordBatch::try_new(
+            schema.clone(),
+            vec![
+                Arc::new(StringArray::from(keys)),
+                Arc::new(
+                    FixedSizeListArray::from_iter_primitive::<Float32Type, _, _>(
+                        (0..metas.len())
+                            .map(|i| Some(vec![Some(i as f32); DIM]))
+                            .collect::<Vec<_>>(),
+                        DIM as i32,
+                    ),
+                ),
+                Arc::new(StringArray::from(
+                    metas
+                        .iter()
+                        .map(|m| Some(m.to_string()))
+                        .collect::<Vec<_>>(),
+                )),
+            ],
+        )
+        .unwrap();
+        let reader = RecordBatchIterator::new(vec![Ok(batch)].into_iter(), schema);
+        let dataset = Dataset::write(reader, dir.path().to_str().unwrap(), None)
+            .await
+            .unwrap();
+        let table = VectorTable::resolve(&dataset, None, None).unwrap();
+        async fn run(dataset: &Dataset, table: &VectorTable, filter: &str) -> Vec<Hit> {
+            flat(
+                dataset,
+                table,
+                &Query {
+                    vector: vec![1.0, 0.0, 0.0, 0.0],
+                    k: 10,
+                    filter: Some(filter.to_string()),
+                    postfilter: false,
+                    distance: DistanceType::L2,
+                    nprobes: None,
+                },
+            )
+            .await
+            .unwrap()
+        }
+        let keys_of = |hits: Vec<Hit>| {
+            let mut keys: Vec<String> = hits.into_iter().map(|h| h.key).collect();
+            keys.sort();
+            keys
+        };
+
+        // A stored string, boolean, array, or null must not satisfy a numeric
+        // comparison — nor fail the query, the way the converting json_get_*
+        // extractors do.
+        let hits = run(
+            &dataset,
+            &table,
+            "TRY_CAST(json_extract(`metadata`, '$[\"k\"]') AS DOUBLE) = 3",
+        )
+        .await;
+        assert_eq!(keys_of(hits), ["k0"]);
+        let hits = run(
+            &dataset,
+            &table,
+            "TRY_CAST(json_extract(`metadata`, '$[\"k\"]') AS DOUBLE) > 1",
+        )
+        .await;
+        assert_eq!(keys_of(hits), ["k0"]);
+
+        // Booleans compare the serialized form as well: '1' and '0' would
+        // satisfy a cast but not the text match.
+        let hits = run(
+            &dataset,
+            &table,
+            "json_extract(`metadata`, '$[\"k\"]') = 'true'",
+        )
+        .await;
+        assert_eq!(keys_of(hits), ["k2"]);
+
+        // The serialized extract is exact for strings too: the numeric 3 is
+        // not a match for '"3"', and comparing json_extract never trips on
+        // the array or null rows.
+        let hits = run(
+            &dataset,
+            &table,
+            "json_extract(`metadata`, '$[\"k\"]') = '\"3\"'",
+        )
+        .await;
+        assert_eq!(keys_of(hits), ["k1"]);
+        let hits = run(
+            &dataset,
+            &table,
+            "NOT COALESCE(json_extract(`metadata`, '$[\"k\"]') = '\"3\"', false)",
+        )
+        .await;
+        assert_eq!(
+            keys_of(hits),
+            ["k0", "k2", "k3", "k4", "k5", "k6", "k7", "k8"]
+        );
+    }
+
     #[tokio::test]
     async fn get_fetches_rows_by_key() {
         let dir = TempDir::new().unwrap();
diff --git a/weed/command/s3.go b/weed/command/s3.go
index 1cdf887ab9..2d3a0137ad 100644
--- a/weed/command/s3.go
+++ b/weed/command/s3.go
@@ -5,7 +5,7 @@ import (
 	"crypto/tls"
 	"crypto/x509"
 	"fmt"
-	"io/ioutil"
+	"net"
 	"net/http"
 	"os"
 	"runtime"
@@ -507,14 +507,9 @@ func (s3opt *S3Options) startS3Server() bool {
 		}
 		grace.OnInterrupt(certProvider.Close)
 
-		caCertPool := x509.NewCertPool()
-		if *s3opt.tlsCACertificate != "" {
-			// load CA certificate file and add it to list of client CAs
-			caCertFile, err := ioutil.ReadFile(*s3opt.tlsCACertificate)
-			if err != nil {
-				glog.Fatalf("error reading CA certificate: %v", err)
-			}
-			caCertPool.AppendCertsFromPEM(caCertFile)
+		caCertPool, err := loadClientCAPool(*s3opt.tlsCACertificate)
+		if err != nil {
+			glog.Fatalf("%v", err)
 		}
 
 		clientAuth := tls.NoClientCert
@@ -726,6 +721,48 @@ func (s3opt *S3Options) startVectorsServer(s3ApiServer *s3api.S3ApiServer, grpcD
 	vectorsServer.SetAccountID(s3tables.DefaultAccountID)
 	vectorsServer.RegisterRoutes(vectorsRouter)
 
+	// Mirror the main API: when TLS is configured the vectors port serves
+	// HTTPS, not a second plaintext endpoint. Build the TLS config before
+	// binding listeners so a certificate failure does not leave ports bound.
+	var tlsConfig *tls.Config
+	if *s3opt.tlsPrivateKey != "" {
+		// The reloading provider reads the key pair asynchronously, so validate
+		// it once up front: a missing or mismatched pair must fail here rather
+		// than after the listeners bind an endpoint that cannot handshake.
+		if _, err := tls.LoadX509KeyPair(*s3opt.tlsCertificate, *s3opt.tlsPrivateKey); err != nil {
+			glog.Errorf("S3 Vectors: load HTTPS certificate: %v", err)
+			conn.Close()
+			return nil
+		}
+		getCert, _, err := security.NewReloadingServerCertificate(*s3opt.tlsCertificate, *s3opt.tlsPrivateKey)
+		if err != nil {
+			glog.Errorf("S3 Vectors: load HTTPS certificate: %v", err)
+			conn.Close()
+			return nil
+		}
+		clientAuth := tls.NoClientCert
+		var caCertPool *x509.CertPool
+		if *s3opt.tlsVerifyClientCert {
+			clientAuth = tls.RequireAndVerifyClientCert
+			caCertPool, err = loadClientCAPool(*s3opt.tlsCACertificate)
+			if err != nil {
+				glog.Errorf("S3 Vectors: %v", err)
+				conn.Close()
+				return nil
+			}
+		}
+		tlsConfig = &tls.Config{
+			GetCertificate: getCert,
+			ClientAuth:     clientAuth,
+			ClientCAs:      caCertPool,
+		}
+		if err := security.FixTlsConfig(util.GetViper(), tlsConfig); err != nil {
+			glog.Errorf("S3 Vectors: tls config: %v", err)
+			conn.Close()
+			return nil
+		}
+	}
+
 	listenAddress := fmt.Sprintf("%s:%d", *s3opt.bindIp, *s3opt.portVectors)
 	vectorsListener, vectorsLocalListener, err := util.NewIpAndLocalListeners(
 		*s3opt.bindIp, *s3opt.portVectors, time.Duration(*s3opt.idleTimeout)*time.Second, listenOnLocalhost)
@@ -735,57 +772,51 @@ func (s3opt *S3Options) startVectorsServer(s3ApiServer *s3api.S3ApiServer, grpcD
 		return nil
 	}
 
-	// Mirror the main API: when TLS is configured the vectors port serves
-	// HTTPS, not a second plaintext endpoint.
-	if *s3opt.tlsPrivateKey != "" {
-		getCert, _, err := security.NewReloadingServerCertificate(*s3opt.tlsCertificate, *s3opt.tlsPrivateKey)
-		if err != nil {
-			glog.Errorf("S3 Vectors: load HTTPS certificate: %v", err)
-			return nil
-		}
-		clientAuth := tls.NoClientCert
-		if *s3opt.tlsVerifyClientCert {
-			clientAuth = tls.RequireAndVerifyClientCert
-		}
-		tlsConfig := &tls.Config{GetCertificate: getCert, ClientAuth: clientAuth}
-		if err := security.FixTlsConfig(util.GetViper(), tlsConfig); err != nil {
-			glog.Errorf("S3 Vectors: tls config: %v", err)
-			return nil
-		}
-		httpS := newHttpServer(vectorsRouter, tlsConfig)
-		if vectorsLocalListener != nil {
-			go func() {
-				if err := httpS.ServeTLS(vectorsLocalListener, "", ""); err != nil && err != http.ErrServerClosed {
-					glog.V(0).Infof("S3 Vectors localhost listener error: %v", err)
-				}
-			}()
-		}
-		go func() {
-			if err := httpS.ServeTLS(vectorsListener, "", ""); err != nil && err != http.ErrServerClosed {
-				glog.Errorf("S3 Vectors API Server Fail to serve: %v", err)
-			}
-		}()
-		return httpS
+	if tlsConfig != nil {
+		glog.V(0).Infof("Start S3 Vectors API Server at https://%s", listenAddress)
+	} else {
+		glog.V(0).Infof("Start S3 Vectors API Server at http://%s", listenAddress)
 	}
 
-	glog.V(0).Infof("Start S3 Vectors API Server at http://%s", listenAddress)
-
-	httpS := newHttpServer(vectorsRouter, nil)
+	httpS := newHttpServer(vectorsRouter, tlsConfig)
+	serve := func(listener net.Listener) error {
+		if tlsConfig != nil {
+			return httpS.ServeTLS(listener, "", "")
+		}
+		return httpS.Serve(listener)
+	}
 	if vectorsLocalListener != nil {
 		go func() {
-			if err := httpS.Serve(vectorsLocalListener); err != nil && err != http.ErrServerClosed {
+			if err := serve(vectorsLocalListener); err != nil && err != http.ErrServerClosed {
 				glog.V(0).Infof("S3 Vectors localhost listener error: %v", err)
 			}
 		}()
 	}
 	go func() {
-		if err := httpS.Serve(vectorsListener); err != nil && err != http.ErrServerClosed {
+		if err := serve(vectorsListener); err != nil && err != http.ErrServerClosed {
 			glog.Errorf("S3 Vectors API Server Fail to serve: %v", err)
 		}
 	}()
 	return httpS
 }
 
+// loadClientCAPool builds the client CA pool from -cacert.file, failing when
+// the file reads but carries no usable certificate.
+func loadClientCAPool(caCertFile string) (*x509.CertPool, error) {
+	pool := x509.NewCertPool()
+	if caCertFile == "" {
+		return pool, nil
+	}
+	pem, err := os.ReadFile(caCertFile)
+	if err != nil {
+		return nil, fmt.Errorf("error reading CA certificate: %w", err)
+	}
+	if !pool.AppendCertsFromPEM(pem) {
+		return nil, fmt.Errorf("no valid certificates found in %s", caCertFile)
+	}
+	return pool, nil
+}
+
 // deriveLanceStorageEndpoint picks the endpoint the Lance namespace puts in
 // storage_options. It falls back to the advertised -ip where the Iceberg
 // derivation gives up, because the two clients are not in the same position: a
diff --git a/weed/pb/filer.proto b/weed/pb/filer.proto
index 1fde04dfd2..b4024c9291 100644
--- a/weed/pb/filer.proto
+++ b/weed/pb/filer.proto
@@ -527,6 +527,11 @@ message DeleteEntryRequest {
     int64 if_not_modified_after = 9;    // unix time in seconds
     bool keep_remote_object = 10;
     int64 if_not_modified_after_ns = 11; // unix time in nanoseconds; overrides if_not_modified_after when set
+    // Optional precondition evaluated against the entry atomically with the
+    // delete, under the filer's per-path lock. The request is routed to the
+    // entry's owner filer for the check to be authoritative.
+    map<string, bytes> expected_extended = 12;
+    bool is_moved = 13;             // set on a forwarded request so the owner applies it locally
 }
 
 message DeleteEntryResponse {
diff --git a/weed/pb/filer_pb/filer.pb.go b/weed/pb/filer_pb/filer.pb.go
index 0cdfbadd48..163d9507eb 100644
--- a/weed/pb/filer_pb/filer.pb.go
+++ b/weed/pb/filer_pb/filer.pb.go
@@ -1,7 +1,7 @@
 // Code generated by protoc-gen-go. DO NOT EDIT.
 // versions:
 // 	protoc-gen-go v1.36.6
-// 	protoc        v3.21.12
+// 	protoc        v7.35.0
 // source: filer.proto
 
 package filer_pb
@@ -2783,8 +2783,13 @@ type DeleteEntryRequest struct {
 	IfNotModifiedAfter   int64   `protobuf:"varint,9,opt,name=if_not_modified_after,json=ifNotModifiedAfter,proto3" json:"if_not_modified_after,omitempty"` // unix time in seconds
 	KeepRemoteObject     bool    `protobuf:"varint,10,opt,name=keep_remote_object,json=keepRemoteObject,proto3" json:"keep_remote_object,omitempty"`
 	IfNotModifiedAfterNs int64   `protobuf:"varint,11,opt,name=if_not_modified_after_ns,json=ifNotModifiedAfterNs,proto3" json:"if_not_modified_after_ns,omitempty"` // unix time in nanoseconds; overrides if_not_modified_after when set
-	unknownFields        protoimpl.UnknownFields
-	sizeCache            protoimpl.SizeCache
+	// Optional precondition evaluated against the entry atomically with the
+	// delete, under the filer's per-path lock. The request is routed to the
+	// entry's owner filer for the check to be authoritative.
+	ExpectedExtended map[string][]byte `protobuf:"bytes,12,rep,name=expected_extended,json=expectedExtended,proto3" json:"expected_extended,omitempty" protobuf_key:"bytes,1,opt,name=key" protobuf_val:"bytes,2,opt,name=value"`
+	IsMoved          bool              `protobuf:"varint,13,opt,name=is_moved,json=isMoved,proto3" json:"is_moved,omitempty"` // set on a forwarded request so the owner applies it locally
+	unknownFields    protoimpl.UnknownFields
+	sizeCache        protoimpl.SizeCache
 }
 
 func (x *DeleteEntryRequest) Reset() {
@@ -2887,6 +2892,20 @@ func (x *DeleteEntryRequest) GetIfNotModifiedAfterNs() int64 {
 	return 0
 }
 
+func (x *DeleteEntryRequest) GetExpectedExtended() map[string][]byte {
+	if x != nil {
+		return x.ExpectedExtended
+	}
+	return nil
+}
+
+func (x *DeleteEntryRequest) GetIsMoved() bool {
+	if x != nil {
+		return x.IsMoved
+	}
+	return false
+}
+
 type DeleteEntryResponse struct {
 	state         protoimpl.MessageState     `protogen:"open.v1"`
 	Error         string                     `protobuf:"bytes,1,opt,name=error,proto3" json:"error,omitempty"`
@@ -7086,7 +7105,7 @@ type LocateBrokerResponse_Resource struct {
 
 func (x *LocateBrokerResponse_Resource) Reset() {
 	*x = LocateBrokerResponse_Resource{}
-	mi := &file_filer_proto_msgTypes[100]
+	mi := &file_filer_proto_msgTypes[101]
 	ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
 	ms.StoreMessageInfo(mi)
 }
@@ -7098,7 +7117,7 @@ func (x *LocateBrokerResponse_Resource) String() string {
 func (*LocateBrokerResponse_Resource) ProtoMessage() {}
 
 func (x *LocateBrokerResponse_Resource) ProtoReflect() protoreflect.Message {
-	mi := &file_filer_proto_msgTypes[100]
+	mi := &file_filer_proto_msgTypes[101]
 	if x != nil {
 		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
 		if ms.LoadMessageInfo() == nil {
@@ -7154,7 +7173,7 @@ type FilerConf_PathConf struct {
 
 func (x *FilerConf_PathConf) Reset() {
 	*x = FilerConf_PathConf{}
-	mi := &file_filer_proto_msgTypes[101]
+	mi := &file_filer_proto_msgTypes[102]
 	ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
 	ms.StoreMessageInfo(mi)
 }
@@ -7166,7 +7185,7 @@ func (x *FilerConf_PathConf) String() string {
 func (*FilerConf_PathConf) ProtoMessage() {}
 
 func (x *FilerConf_PathConf) ProtoReflect() protoreflect.Message {
-	mi := &file_filer_proto_msgTypes[101]
+	mi := &file_filer_proto_msgTypes[102]
 	if x != nil {
 		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
 		if ms.LoadMessageInfo() == nil {
@@ -7569,7 +7588,7 @@ const file_filer_proto_rawDesc = "" +
 	"\n" +
 	"entry_name\x18\x02 \x01(\tR\tentryName\x12+\n" +
 	"\x06chunks\x18\x03 \x03(\v2\x13.filer_pb.FileChunkR\x06chunks\"\x17\n" +
-	"\x15AppendToEntryResponse\"\xb1\x03\n" +
+	"\x15AppendToEntryResponse\"\xf2\x04\n" +
 	"\x12DeleteEntryRequest\x12\x1c\n" +
 	"\tdirectory\x18\x01 \x01(\tR\tdirectory\x12\x12\n" +
 	"\x04name\x18\x02 \x01(\tR\x04name\x12$\n" +
@@ -7583,7 +7602,12 @@ const file_filer_proto_rawDesc = "" +
 	"\x15if_not_modified_after\x18\t \x01(\x03R\x12ifNotModifiedAfter\x12,\n" +
 	"\x12keep_remote_object\x18\n" +
 	" \x01(\bR\x10keepRemoteObject\x126\n" +
-	"\x18if_not_modified_after_ns\x18\v \x01(\x03R\x14ifNotModifiedAfterNs\"w\n" +
+	"\x18if_not_modified_after_ns\x18\v \x01(\x03R\x14ifNotModifiedAfterNs\x12_\n" +
+	"\x11expected_extended\x18\f \x03(\v22.filer_pb.DeleteEntryRequest.ExpectedExtendedEntryR\x10expectedExtended\x12\x19\n" +
+	"\bis_moved\x18\r \x01(\bR\aisMoved\x1aC\n" +
+	"\x15ExpectedExtendedEntry\x12\x10\n" +
+	"\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n" +
+	"\x05value\x18\x02 \x01(\fR\x05value:\x028\x01\"w\n" +
 	"\x13DeleteEntryResponse\x12\x14\n" +
 	"\x05error\x18\x01 \x01(\tR\x05error\x12J\n" +
 	"\x0emetadata_event\x18\x02 \x01(\v2#.filer_pb.SubscribeMetadataResponseR\rmetadataEvent\"\xed\x01\n" +
@@ -8025,7 +8049,7 @@ func file_filer_proto_rawDescGZIP() []byte {
 }
 
 var file_filer_proto_enumTypes = make([]protoimpl.EnumInfo, 5)
-var file_filer_proto_msgTypes = make([]protoimpl.MessageInfo, 104)
+var file_filer_proto_msgTypes = make([]protoimpl.MessageInfo, 105)
 var file_filer_proto_goTypes = []any{
 	(SSEType)(0),                                    // 0: filer_pb.SSEType
 	(FilerError)(0),                                 // 1: filer_pb.FilerError
@@ -8131,11 +8155,12 @@ var file_filer_proto_goTypes = []any{
 	nil,                                             // 101: filer_pb.ObjectMutation.SetExtendedEntry
 	nil,                                             // 102: filer_pb.Recompute.CopyExtendedEntry
 	nil,                                             // 103: filer_pb.UpdateEntryRequest.ExpectedExtendedEntry
-	nil,                                             // 104: filer_pb.LookupVolumeResponse.LocationsMapEntry
-	(*LocateBrokerResponse_Resource)(nil),           // 105: filer_pb.LocateBrokerResponse.Resource
-	(*FilerConf_PathConf)(nil),                      // 106: filer_pb.FilerConf.PathConf
-	nil,                                             // 107: filer_pb.LookupDirectoryEntriesResponse.LocationsMapEntry
-	nil,                                             // 108: filer_pb.LookupDirectoryEntriesResponse.ReadAuthEntry
+	nil,                                             // 104: filer_pb.DeleteEntryRequest.ExpectedExtendedEntry
+	nil,                                             // 105: filer_pb.LookupVolumeResponse.LocationsMapEntry
+	(*LocateBrokerResponse_Resource)(nil),           // 106: filer_pb.LocateBrokerResponse.Resource
+	(*FilerConf_PathConf)(nil),                      // 107: filer_pb.FilerConf.PathConf
+	nil,                                             // 108: filer_pb.LookupDirectoryEntriesResponse.LocationsMapEntry
+	nil,                                             // 109: filer_pb.LookupDirectoryEntriesResponse.ReadAuthEntry
 }
 var file_filer_proto_depIdxs = []int32{
 	10,  // 0: filer_pb.LookupDirectoryEntryResponse.entry:type_name -> filer_pb.Entry
@@ -8175,118 +8200,119 @@ var file_filer_proto_depIdxs = []int32{
 	18,  // 34: filer_pb.UpdateEntryRequest.condition:type_name -> filer_pb.WriteCondition
 	59,  // 35: filer_pb.UpdateEntryResponse.metadata_event:type_name -> filer_pb.SubscribeMetadataResponse
 	13,  // 36: filer_pb.AppendToEntryRequest.chunks:type_name -> filer_pb.FileChunk
-	59,  // 37: filer_pb.DeleteEntryResponse.metadata_event:type_name -> filer_pb.SubscribeMetadataResponse
-	12,  // 38: filer_pb.StreamRenameEntryResponse.event_notification:type_name -> filer_pb.EventNotification
-	45,  // 39: filer_pb.AssignVolumeResponse.location:type_name -> filer_pb.Location
-	45,  // 40: filer_pb.AssignVolumeResponse.replicas:type_name -> filer_pb.Location
-	1,   // 41: filer_pb.AssignVolumeResponse.error_code:type_name -> filer_pb.FilerError
-	45,  // 42: filer_pb.Locations.locations:type_name -> filer_pb.Location
-	104, // 43: filer_pb.LookupVolumeResponse.locations_map:type_name -> filer_pb.LookupVolumeResponse.LocationsMapEntry
-	47,  // 44: filer_pb.CollectionListResponse.collections:type_name -> filer_pb.Collection
-	12,  // 45: filer_pb.SubscribeMetadataResponse.event_notification:type_name -> filer_pb.EventNotification
-	59,  // 46: filer_pb.SubscribeMetadataResponse.events:type_name -> filer_pb.SubscribeMetadataResponse
-	63,  // 47: filer_pb.SubscribeMetadataResponse.log_file_refs:type_name -> filer_pb.LogFileChunkRef
-	62,  // 48: filer_pb.ListMetadataSubscribersResponse.subscribers:type_name -> filer_pb.MetadataSubscriber
-	13,  // 49: filer_pb.LogFileChunkRef.chunks:type_name -> filer_pb.FileChunk
-	10,  // 50: filer_pb.TraverseBfsMetadataResponse.entry:type_name -> filer_pb.Entry
-	105, // 51: filer_pb.LocateBrokerResponse.resources:type_name -> filer_pb.LocateBrokerResponse.Resource
-	106, // 52: filer_pb.FilerConf.locations:type_name -> filer_pb.FilerConf.PathConf
-	10,  // 53: filer_pb.CacheRemoteObjectToLocalClusterResponse.entry:type_name -> filer_pb.Entry
-	59,  // 54: filer_pb.CacheRemoteObjectToLocalClusterResponse.metadata_event:type_name -> filer_pb.SubscribeMetadataResponse
-	84,  // 55: filer_pb.TransferLocksRequest.locks:type_name -> filer_pb.Lock
-	17,  // 56: filer_pb.StreamMutateEntryRequest.create_request:type_name -> filer_pb.CreateEntryRequest
-	29,  // 57: filer_pb.StreamMutateEntryRequest.update_request:type_name -> filer_pb.UpdateEntryRequest
-	35,  // 58: filer_pb.StreamMutateEntryRequest.delete_request:type_name -> filer_pb.DeleteEntryRequest
-	39,  // 59: filer_pb.StreamMutateEntryRequest.rename_request:type_name -> filer_pb.StreamRenameEntryRequest
-	28,  // 60: filer_pb.StreamMutateEntryResponse.create_response:type_name -> filer_pb.CreateEntryResponse
-	30,  // 61: filer_pb.StreamMutateEntryResponse.update_response:type_name -> filer_pb.UpdateEntryResponse
-	36,  // 62: filer_pb.StreamMutateEntryResponse.delete_response:type_name -> filer_pb.DeleteEntryResponse
-	40,  // 63: filer_pb.StreamMutateEntryResponse.rename_response:type_name -> filer_pb.StreamRenameEntryResponse
-	95,  // 64: filer_pb.MountListResponse.mounts:type_name -> filer_pb.MountInfo
-	5,   // 65: filer_pb.LookupDirectoryEntriesRequest.requests:type_name -> filer_pb.LookupDirectoryEntryRequest
-	10,  // 66: filer_pb.LookupDirectoryEntryResult.entry:type_name -> filer_pb.Entry
-	97,  // 67: filer_pb.LookupDirectoryEntriesResponse.results:type_name -> filer_pb.LookupDirectoryEntryResult
-	107, // 68: filer_pb.LookupDirectoryEntriesResponse.locations_map:type_name -> filer_pb.LookupDirectoryEntriesResponse.LocationsMapEntry
-	108, // 69: filer_pb.LookupDirectoryEntriesResponse.read_auth:type_name -> filer_pb.LookupDirectoryEntriesResponse.ReadAuthEntry
-	3,   // 70: filer_pb.WriteCondition.Clause.kind:type_name -> filer_pb.WriteCondition.Kind
-	10,  // 71: filer_pb.WriteCondition.Clause.expected_entry:type_name -> filer_pb.Entry
-	44,  // 72: filer_pb.LookupVolumeResponse.LocationsMapEntry.value:type_name -> filer_pb.Locations
-	44,  // 73: filer_pb.LookupDirectoryEntriesResponse.LocationsMapEntry.value:type_name -> filer_pb.Locations
-	5,   // 74: filer_pb.SeaweedFiler.LookupDirectoryEntry:input_type -> filer_pb.LookupDirectoryEntryRequest
-	96,  // 75: filer_pb.SeaweedFiler.LookupDirectoryEntries:input_type -> filer_pb.LookupDirectoryEntriesRequest
-	7,   // 76: filer_pb.SeaweedFiler.ListEntries:input_type -> filer_pb.ListEntriesRequest
-	17,  // 77: filer_pb.SeaweedFiler.CreateEntry:input_type -> filer_pb.CreateEntryRequest
-	29,  // 78: filer_pb.SeaweedFiler.UpdateEntry:input_type -> filer_pb.UpdateEntryRequest
-	31,  // 79: filer_pb.SeaweedFiler.TouchAccessTime:input_type -> filer_pb.TouchAccessTimeRequest
-	33,  // 80: filer_pb.SeaweedFiler.AppendToEntry:input_type -> filer_pb.AppendToEntryRequest
-	35,  // 81: filer_pb.SeaweedFiler.DeleteEntry:input_type -> filer_pb.DeleteEntryRequest
-	21,  // 82: filer_pb.SeaweedFiler.ObjectTransaction:input_type -> filer_pb.ObjectTransactionRequest
-	26,  // 83: filer_pb.SeaweedFiler.ObjectTransactionBatch:input_type -> filer_pb.ObjectTransactionBatchRequest
-	24,  // 84: filer_pb.SeaweedFiler.PosixLock:input_type -> filer_pb.PosixLockRequest
-	37,  // 85: filer_pb.SeaweedFiler.AtomicRenameEntry:input_type -> filer_pb.AtomicRenameEntryRequest
-	39,  // 86: filer_pb.SeaweedFiler.StreamRenameEntry:input_type -> filer_pb.StreamRenameEntryRequest
-	89,  // 87: filer_pb.SeaweedFiler.StreamMutateEntry:input_type -> filer_pb.StreamMutateEntryRequest
-	41,  // 88: filer_pb.SeaweedFiler.AssignVolume:input_type -> filer_pb.AssignVolumeRequest
-	43,  // 89: filer_pb.SeaweedFiler.LookupVolume:input_type -> filer_pb.LookupVolumeRequest
-	48,  // 90: filer_pb.SeaweedFiler.CollectionList:input_type -> filer_pb.CollectionListRequest
-	50,  // 91: filer_pb.SeaweedFiler.DeleteCollection:input_type -> filer_pb.DeleteCollectionRequest
-	52,  // 92: filer_pb.SeaweedFiler.Statistics:input_type -> filer_pb.StatisticsRequest
-	54,  // 93: filer_pb.SeaweedFiler.Ping:input_type -> filer_pb.PingRequest
-	56,  // 94: filer_pb.SeaweedFiler.GetFilerConfiguration:input_type -> filer_pb.GetFilerConfigurationRequest
-	64,  // 95: filer_pb.SeaweedFiler.TraverseBfsMetadata:input_type -> filer_pb.TraverseBfsMetadataRequest
-	58,  // 96: filer_pb.SeaweedFiler.SubscribeMetadata:input_type -> filer_pb.SubscribeMetadataRequest
-	58,  // 97: filer_pb.SeaweedFiler.SubscribeLocalMetadata:input_type -> filer_pb.SubscribeMetadataRequest
-	60,  // 98: filer_pb.SeaweedFiler.ListMetadataSubscribers:input_type -> filer_pb.ListMetadataSubscribersRequest
-	71,  // 99: filer_pb.SeaweedFiler.KvGet:input_type -> filer_pb.KvGetRequest
-	73,  // 100: filer_pb.SeaweedFiler.KvPut:input_type -> filer_pb.KvPutRequest
-	76,  // 101: filer_pb.SeaweedFiler.CacheRemoteObjectToLocalCluster:input_type -> filer_pb.CacheRemoteObjectToLocalClusterRequest
-	78,  // 102: filer_pb.SeaweedFiler.DistributedLock:input_type -> filer_pb.LockRequest
-	80,  // 103: filer_pb.SeaweedFiler.DistributedUnlock:input_type -> filer_pb.UnlockRequest
-	82,  // 104: filer_pb.SeaweedFiler.FindLockOwner:input_type -> filer_pb.FindLockOwnerRequest
-	85,  // 105: filer_pb.SeaweedFiler.TransferLocks:input_type -> filer_pb.TransferLocksRequest
-	87,  // 106: filer_pb.SeaweedFiler.ReplicateLock:input_type -> filer_pb.ReplicateLockRequest
-	91,  // 107: filer_pb.SeaweedFiler.MountRegister:input_type -> filer_pb.MountRegisterRequest
-	93,  // 108: filer_pb.SeaweedFiler.MountList:input_type -> filer_pb.MountListRequest
-	6,   // 109: filer_pb.SeaweedFiler.LookupDirectoryEntry:output_type -> filer_pb.LookupDirectoryEntryResponse
-	98,  // 110: filer_pb.SeaweedFiler.LookupDirectoryEntries:output_type -> filer_pb.LookupDirectoryEntriesResponse
-	8,   // 111: filer_pb.SeaweedFiler.ListEntries:output_type -> filer_pb.ListEntriesResponse
-	28,  // 112: filer_pb.SeaweedFiler.CreateEntry:output_type -> filer_pb.CreateEntryResponse
-	30,  // 113: filer_pb.SeaweedFiler.UpdateEntry:output_type -> filer_pb.UpdateEntryResponse
-	32,  // 114: filer_pb.SeaweedFiler.TouchAccessTime:output_type -> filer_pb.TouchAccessTimeResponse
-	34,  // 115: filer_pb.SeaweedFiler.AppendToEntry:output_type -> filer_pb.AppendToEntryResponse
-	36,  // 116: filer_pb.SeaweedFiler.DeleteEntry:output_type -> filer_pb.DeleteEntryResponse
-	22,  // 117: filer_pb.SeaweedFiler.ObjectTransaction:output_type -> filer_pb.ObjectTransactionResponse
-	27,  // 118: filer_pb.SeaweedFiler.ObjectTransactionBatch:output_type -> filer_pb.ObjectTransactionBatchResponse
-	25,  // 119: filer_pb.SeaweedFiler.PosixLock:output_type -> filer_pb.PosixLockResponse
-	38,  // 120: filer_pb.SeaweedFiler.AtomicRenameEntry:output_type -> filer_pb.AtomicRenameEntryResponse
-	40,  // 121: filer_pb.SeaweedFiler.StreamRenameEntry:output_type -> filer_pb.StreamRenameEntryResponse
-	90,  // 122: filer_pb.SeaweedFiler.StreamMutateEntry:output_type -> filer_pb.StreamMutateEntryResponse
-	42,  // 123: filer_pb.SeaweedFiler.AssignVolume:output_type -> filer_pb.AssignVolumeResponse
-	46,  // 124: filer_pb.SeaweedFiler.LookupVolume:output_type -> filer_pb.LookupVolumeResponse
-	49,  // 125: filer_pb.SeaweedFiler.CollectionList:output_type -> filer_pb.CollectionListResponse
-	51,  // 126: filer_pb.SeaweedFiler.DeleteCollection:output_type -> filer_pb.DeleteCollectionResponse
-	53,  // 127: filer_pb.SeaweedFiler.Statistics:output_type -> filer_pb.StatisticsResponse
-	55,  // 128: filer_pb.SeaweedFiler.Ping:output_type -> filer_pb.PingResponse
-	57,  // 129: filer_pb.SeaweedFiler.GetFilerConfiguration:output_type -> filer_pb.GetFilerConfigurationResponse
-	65,  // 130: filer_pb.SeaweedFiler.TraverseBfsMetadata:output_type -> filer_pb.TraverseBfsMetadataResponse
-	59,  // 131: filer_pb.SeaweedFiler.SubscribeMetadata:output_type -> filer_pb.SubscribeMetadataResponse
-	59,  // 132: filer_pb.SeaweedFiler.SubscribeLocalMetadata:output_type -> filer_pb.SubscribeMetadataResponse
-	61,  // 133: filer_pb.SeaweedFiler.ListMetadataSubscribers:output_type -> filer_pb.ListMetadataSubscribersResponse
-	72,  // 134: filer_pb.SeaweedFiler.KvGet:output_type -> filer_pb.KvGetResponse
-	74,  // 135: filer_pb.SeaweedFiler.KvPut:output_type -> filer_pb.KvPutResponse
-	77,  // 136: filer_pb.SeaweedFiler.CacheRemoteObjectToLocalCluster:output_type -> filer_pb.CacheRemoteObjectToLocalClusterResponse
-	79,  // 137: filer_pb.SeaweedFiler.DistributedLock:output_type -> filer_pb.LockResponse
-	81,  // 138: filer_pb.SeaweedFiler.DistributedUnlock:output_type -> filer_pb.UnlockResponse
-	83,  // 139: filer_pb.SeaweedFiler.FindLockOwner:output_type -> filer_pb.FindLockOwnerResponse
-	86,  // 140: filer_pb.SeaweedFiler.TransferLocks:output_type -> filer_pb.TransferLocksResponse
-	88,  // 141: filer_pb.SeaweedFiler.ReplicateLock:output_type -> filer_pb.ReplicateLockResponse
-	92,  // 142: filer_pb.SeaweedFiler.MountRegister:output_type -> filer_pb.MountRegisterResponse
-	94,  // 143: filer_pb.SeaweedFiler.MountList:output_type -> filer_pb.MountListResponse
-	109, // [109:144] is the sub-list for method output_type
-	74,  // [74:109] is the sub-list for method input_type
-	74,  // [74:74] is the sub-list for extension type_name
-	74,  // [74:74] is the sub-list for extension extendee
-	0,   // [0:74] is the sub-list for field type_name
+	104, // 37: filer_pb.DeleteEntryRequest.expected_extended:type_name -> filer_pb.DeleteEntryRequest.ExpectedExtendedEntry
+	59,  // 38: filer_pb.DeleteEntryResponse.metadata_event:type_name -> filer_pb.SubscribeMetadataResponse
+	12,  // 39: filer_pb.StreamRenameEntryResponse.event_notification:type_name -> filer_pb.EventNotification
+	45,  // 40: filer_pb.AssignVolumeResponse.location:type_name -> filer_pb.Location
+	45,  // 41: filer_pb.AssignVolumeResponse.replicas:type_name -> filer_pb.Location
+	1,   // 42: filer_pb.AssignVolumeResponse.error_code:type_name -> filer_pb.FilerError
+	45,  // 43: filer_pb.Locations.locations:type_name -> filer_pb.Location
+	105, // 44: filer_pb.LookupVolumeResponse.locations_map:type_name -> filer_pb.LookupVolumeResponse.LocationsMapEntry
+	47,  // 45: filer_pb.CollectionListResponse.collections:type_name -> filer_pb.Collection
+	12,  // 46: filer_pb.SubscribeMetadataResponse.event_notification:type_name -> filer_pb.EventNotification
+	59,  // 47: filer_pb.SubscribeMetadataResponse.events:type_name -> filer_pb.SubscribeMetadataResponse
+	63,  // 48: filer_pb.SubscribeMetadataResponse.log_file_refs:type_name -> filer_pb.LogFileChunkRef
+	62,  // 49: filer_pb.ListMetadataSubscribersResponse.subscribers:type_name -> filer_pb.MetadataSubscriber
+	13,  // 50: filer_pb.LogFileChunkRef.chunks:type_name -> filer_pb.FileChunk
+	10,  // 51: filer_pb.TraverseBfsMetadataResponse.entry:type_name -> filer_pb.Entry
+	106, // 52: filer_pb.LocateBrokerResponse.resources:type_name -> filer_pb.LocateBrokerResponse.Resource
+	107, // 53: filer_pb.FilerConf.locations:type_name -> filer_pb.FilerConf.PathConf
+	10,  // 54: filer_pb.CacheRemoteObjectToLocalClusterResponse.entry:type_name -> filer_pb.Entry
+	59,  // 55: filer_pb.CacheRemoteObjectToLocalClusterResponse.metadata_event:type_name -> filer_pb.SubscribeMetadataResponse
+	84,  // 56: filer_pb.TransferLocksRequest.locks:type_name -> filer_pb.Lock
+	17,  // 57: filer_pb.StreamMutateEntryRequest.create_request:type_name -> filer_pb.CreateEntryRequest
+	29,  // 58: filer_pb.StreamMutateEntryRequest.update_request:type_name -> filer_pb.UpdateEntryRequest
+	35,  // 59: filer_pb.StreamMutateEntryRequest.delete_request:type_name -> filer_pb.DeleteEntryRequest
+	39,  // 60: filer_pb.StreamMutateEntryRequest.rename_request:type_name -> filer_pb.StreamRenameEntryRequest
+	28,  // 61: filer_pb.StreamMutateEntryResponse.create_response:type_name -> filer_pb.CreateEntryResponse
+	30,  // 62: filer_pb.StreamMutateEntryResponse.update_response:type_name -> filer_pb.UpdateEntryResponse
+	36,  // 63: filer_pb.StreamMutateEntryResponse.delete_response:type_name -> filer_pb.DeleteEntryResponse
+	40,  // 64: filer_pb.StreamMutateEntryResponse.rename_response:type_name -> filer_pb.StreamRenameEntryResponse
+	95,  // 65: filer_pb.MountListResponse.mounts:type_name -> filer_pb.MountInfo
+	5,   // 66: filer_pb.LookupDirectoryEntriesRequest.requests:type_name -> filer_pb.LookupDirectoryEntryRequest
+	10,  // 67: filer_pb.LookupDirectoryEntryResult.entry:type_name -> filer_pb.Entry
+	97,  // 68: filer_pb.LookupDirectoryEntriesResponse.results:type_name -> filer_pb.LookupDirectoryEntryResult
+	108, // 69: filer_pb.LookupDirectoryEntriesResponse.locations_map:type_name -> filer_pb.LookupDirectoryEntriesResponse.LocationsMapEntry
+	109, // 70: filer_pb.LookupDirectoryEntriesResponse.read_auth:type_name -> filer_pb.LookupDirectoryEntriesResponse.ReadAuthEntry
+	3,   // 71: filer_pb.WriteCondition.Clause.kind:type_name -> filer_pb.WriteCondition.Kind
+	10,  // 72: filer_pb.WriteCondition.Clause.expected_entry:type_name -> filer_pb.Entry
+	44,  // 73: filer_pb.LookupVolumeResponse.LocationsMapEntry.value:type_name -> filer_pb.Locations
+	44,  // 74: filer_pb.LookupDirectoryEntriesResponse.LocationsMapEntry.value:type_name -> filer_pb.Locations
+	5,   // 75: filer_pb.SeaweedFiler.LookupDirectoryEntry:input_type -> filer_pb.LookupDirectoryEntryRequest
+	96,  // 76: filer_pb.SeaweedFiler.LookupDirectoryEntries:input_type -> filer_pb.LookupDirectoryEntriesRequest
+	7,   // 77: filer_pb.SeaweedFiler.ListEntries:input_type -> filer_pb.ListEntriesRequest
+	17,  // 78: filer_pb.SeaweedFiler.CreateEntry:input_type -> filer_pb.CreateEntryRequest
+	29,  // 79: filer_pb.SeaweedFiler.UpdateEntry:input_type -> filer_pb.UpdateEntryRequest
+	31,  // 80: filer_pb.SeaweedFiler.TouchAccessTime:input_type -> filer_pb.TouchAccessTimeRequest
+	33,  // 81: filer_pb.SeaweedFiler.AppendToEntry:input_type -> filer_pb.AppendToEntryRequest
+	35,  // 82: filer_pb.SeaweedFiler.DeleteEntry:input_type -> filer_pb.DeleteEntryRequest
+	21,  // 83: filer_pb.SeaweedFiler.ObjectTransaction:input_type -> filer_pb.ObjectTransactionRequest
+	26,  // 84: filer_pb.SeaweedFiler.ObjectTransactionBatch:input_type -> filer_pb.ObjectTransactionBatchRequest
+	24,  // 85: filer_pb.SeaweedFiler.PosixLock:input_type -> filer_pb.PosixLockRequest
+	37,  // 86: filer_pb.SeaweedFiler.AtomicRenameEntry:input_type -> filer_pb.AtomicRenameEntryRequest
+	39,  // 87: filer_pb.SeaweedFiler.StreamRenameEntry:input_type -> filer_pb.StreamRenameEntryRequest
+	89,  // 88: filer_pb.SeaweedFiler.StreamMutateEntry:input_type -> filer_pb.StreamMutateEntryRequest
+	41,  // 89: filer_pb.SeaweedFiler.AssignVolume:input_type -> filer_pb.AssignVolumeRequest
+	43,  // 90: filer_pb.SeaweedFiler.LookupVolume:input_type -> filer_pb.LookupVolumeRequest
+	48,  // 91: filer_pb.SeaweedFiler.CollectionList:input_type -> filer_pb.CollectionListRequest
+	50,  // 92: filer_pb.SeaweedFiler.DeleteCollection:input_type -> filer_pb.DeleteCollectionRequest
+	52,  // 93: filer_pb.SeaweedFiler.Statistics:input_type -> filer_pb.StatisticsRequest
+	54,  // 94: filer_pb.SeaweedFiler.Ping:input_type -> filer_pb.PingRequest
+	56,  // 95: filer_pb.SeaweedFiler.GetFilerConfiguration:input_type -> filer_pb.GetFilerConfigurationRequest
+	64,  // 96: filer_pb.SeaweedFiler.TraverseBfsMetadata:input_type -> filer_pb.TraverseBfsMetadataRequest
+	58,  // 97: filer_pb.SeaweedFiler.SubscribeMetadata:input_type -> filer_pb.SubscribeMetadataRequest
+	58,  // 98: filer_pb.SeaweedFiler.SubscribeLocalMetadata:input_type -> filer_pb.SubscribeMetadataRequest
+	60,  // 99: filer_pb.SeaweedFiler.ListMetadataSubscribers:input_type -> filer_pb.ListMetadataSubscribersRequest
+	71,  // 100: filer_pb.SeaweedFiler.KvGet:input_type -> filer_pb.KvGetRequest
+	73,  // 101: filer_pb.SeaweedFiler.KvPut:input_type -> filer_pb.KvPutRequest
+	76,  // 102: filer_pb.SeaweedFiler.CacheRemoteObjectToLocalCluster:input_type -> filer_pb.CacheRemoteObjectToLocalClusterRequest
+	78,  // 103: filer_pb.SeaweedFiler.DistributedLock:input_type -> filer_pb.LockRequest
+	80,  // 104: filer_pb.SeaweedFiler.DistributedUnlock:input_type -> filer_pb.UnlockRequest
+	82,  // 105: filer_pb.SeaweedFiler.FindLockOwner:input_type -> filer_pb.FindLockOwnerRequest
+	85,  // 106: filer_pb.SeaweedFiler.TransferLocks:input_type -> filer_pb.TransferLocksRequest
+	87,  // 107: filer_pb.SeaweedFiler.ReplicateLock:input_type -> filer_pb.ReplicateLockRequest
+	91,  // 108: filer_pb.SeaweedFiler.MountRegister:input_type -> filer_pb.MountRegisterRequest
+	93,  // 109: filer_pb.SeaweedFiler.MountList:input_type -> filer_pb.MountListRequest
+	6,   // 110: filer_pb.SeaweedFiler.LookupDirectoryEntry:output_type -> filer_pb.LookupDirectoryEntryResponse
+	98,  // 111: filer_pb.SeaweedFiler.LookupDirectoryEntries:output_type -> filer_pb.LookupDirectoryEntriesResponse
+	8,   // 112: filer_pb.SeaweedFiler.ListEntries:output_type -> filer_pb.ListEntriesResponse
+	28,  // 113: filer_pb.SeaweedFiler.CreateEntry:output_type -> filer_pb.CreateEntryResponse
+	30,  // 114: filer_pb.SeaweedFiler.UpdateEntry:output_type -> filer_pb.UpdateEntryResponse
+	32,  // 115: filer_pb.SeaweedFiler.TouchAccessTime:output_type -> filer_pb.TouchAccessTimeResponse
+	34,  // 116: filer_pb.SeaweedFiler.AppendToEntry:output_type -> filer_pb.AppendToEntryResponse
+	36,  // 117: filer_pb.SeaweedFiler.DeleteEntry:output_type -> filer_pb.DeleteEntryResponse
+	22,  // 118: filer_pb.SeaweedFiler.ObjectTransaction:output_type -> filer_pb.ObjectTransactionResponse
+	27,  // 119: filer_pb.SeaweedFiler.ObjectTransactionBatch:output_type -> filer_pb.ObjectTransactionBatchResponse
+	25,  // 120: filer_pb.SeaweedFiler.PosixLock:output_type -> filer_pb.PosixLockResponse
+	38,  // 121: filer_pb.SeaweedFiler.AtomicRenameEntry:output_type -> filer_pb.AtomicRenameEntryResponse
+	40,  // 122: filer_pb.SeaweedFiler.StreamRenameEntry:output_type -> filer_pb.StreamRenameEntryResponse
+	90,  // 123: filer_pb.SeaweedFiler.StreamMutateEntry:output_type -> filer_pb.StreamMutateEntryResponse
+	42,  // 124: filer_pb.SeaweedFiler.AssignVolume:output_type -> filer_pb.AssignVolumeResponse
+	46,  // 125: filer_pb.SeaweedFiler.LookupVolume:output_type -> filer_pb.LookupVolumeResponse
+	49,  // 126: filer_pb.SeaweedFiler.CollectionList:output_type -> filer_pb.CollectionListResponse
+	51,  // 127: filer_pb.SeaweedFiler.DeleteCollection:output_type -> filer_pb.DeleteCollectionResponse
+	53,  // 128: filer_pb.SeaweedFiler.Statistics:output_type -> filer_pb.StatisticsResponse
+	55,  // 129: filer_pb.SeaweedFiler.Ping:output_type -> filer_pb.PingResponse
+	57,  // 130: filer_pb.SeaweedFiler.GetFilerConfiguration:output_type -> filer_pb.GetFilerConfigurationResponse
+	65,  // 131: filer_pb.SeaweedFiler.TraverseBfsMetadata:output_type -> filer_pb.TraverseBfsMetadataResponse
+	59,  // 132: filer_pb.SeaweedFiler.SubscribeMetadata:output_type -> filer_pb.SubscribeMetadataResponse
+	59,  // 133: filer_pb.SeaweedFiler.SubscribeLocalMetadata:output_type -> filer_pb.SubscribeMetadataResponse
+	61,  // 134: filer_pb.SeaweedFiler.ListMetadataSubscribers:output_type -> filer_pb.ListMetadataSubscribersResponse
+	72,  // 135: filer_pb.SeaweedFiler.KvGet:output_type -> filer_pb.KvGetResponse
+	74,  // 136: filer_pb.SeaweedFiler.KvPut:output_type -> filer_pb.KvPutResponse
+	77,  // 137: filer_pb.SeaweedFiler.CacheRemoteObjectToLocalCluster:output_type -> filer_pb.CacheRemoteObjectToLocalClusterResponse
+	79,  // 138: filer_pb.SeaweedFiler.DistributedLock:output_type -> filer_pb.LockResponse
+	81,  // 139: filer_pb.SeaweedFiler.DistributedUnlock:output_type -> filer_pb.UnlockResponse
+	83,  // 140: filer_pb.SeaweedFiler.FindLockOwner:output_type -> filer_pb.FindLockOwnerResponse
+	86,  // 141: filer_pb.SeaweedFiler.TransferLocks:output_type -> filer_pb.TransferLocksResponse
+	88,  // 142: filer_pb.SeaweedFiler.ReplicateLock:output_type -> filer_pb.ReplicateLockResponse
+	92,  // 143: filer_pb.SeaweedFiler.MountRegister:output_type -> filer_pb.MountRegisterResponse
+	94,  // 144: filer_pb.SeaweedFiler.MountList:output_type -> filer_pb.MountListResponse
+	110, // [110:145] is the sub-list for method output_type
+	75,  // [75:110] is the sub-list for method input_type
+	75,  // [75:75] is the sub-list for extension type_name
+	75,  // [75:75] is the sub-list for extension extendee
+	0,   // [0:75] is the sub-list for field type_name
 }
 
 func init() { file_filer_proto_init() }
@@ -8307,14 +8333,14 @@ func file_filer_proto_init() {
 		(*StreamMutateEntryResponse_DeleteResponse)(nil),
 		(*StreamMutateEntryResponse_RenameResponse)(nil),
 	}
-	file_filer_proto_msgTypes[101].OneofWrappers = []any{}
+	file_filer_proto_msgTypes[102].OneofWrappers = []any{}
 	type x struct{}
 	out := protoimpl.TypeBuilder{
 		File: protoimpl.DescBuilder{
 			GoPackagePath: reflect.TypeOf(x{}).PkgPath(),
 			RawDescriptor: unsafe.Slice(unsafe.StringData(file_filer_proto_rawDesc), len(file_filer_proto_rawDesc)),
 			NumEnums:      5,
-			NumMessages:   104,
+			NumMessages:   105,
 			NumExtensions: 0,
 			NumServices:   1,
 		},
diff --git a/weed/pb/filer_pb/filer_grpc.pb.go b/weed/pb/filer_pb/filer_grpc.pb.go
index 8a330ce286..6a2b494a39 100644
--- a/weed/pb/filer_pb/filer_grpc.pb.go
+++ b/weed/pb/filer_pb/filer_grpc.pb.go
@@ -1,7 +1,7 @@
 // Code generated by protoc-gen-go-grpc. DO NOT EDIT.
 // versions:
 // - protoc-gen-go-grpc v1.6.2
-// - protoc             v3.21.12
+// - protoc             v7.35.0
 // source: filer.proto
 
 package filer_pb
diff --git a/weed/pb/filer_pb/filer_vtproto.pb.go b/weed/pb/filer_pb/filer_vtproto.pb.go
index 6621620bed..5c5becb7bb 100644
--- a/weed/pb/filer_pb/filer_vtproto.pb.go
+++ b/weed/pb/filer_pb/filer_vtproto.pb.go
@@ -2491,6 +2491,35 @@ func (m *DeleteEntryRequest) MarshalToSizedBufferVT(dAtA []byte) (int, error) {
 		i -= len(m.unknownFields)
 		copy(dAtA[i:], m.unknownFields)
 	}
+	if m.IsMoved {
+		i--
+		if m.IsMoved {
+			dAtA[i] = 1
+		} else {
+			dAtA[i] = 0
+		}
+		i--
+		dAtA[i] = 0x68
+	}
+	if len(m.ExpectedExtended) > 0 {
+		for k := range m.ExpectedExtended {
+			v := m.ExpectedExtended[k]
+			baseI := i
+			i -= len(v)
+			copy(dAtA[i:], v)
+			i = protohelpers.EncodeVarint(dAtA, i, uint64(len(v)))
+			i--
+			dAtA[i] = 0x12
+			i -= len(k)
+			copy(dAtA[i:], k)
+			i = protohelpers.EncodeVarint(dAtA, i, uint64(len(k)))
+			i--
+			dAtA[i] = 0xa
+			i = protohelpers.EncodeVarint(dAtA, i, uint64(baseI-i))
+			i--
+			dAtA[i] = 0x62
+		}
+	}
 	if m.IfNotModifiedAfterNs != 0 {
 		i = protohelpers.EncodeVarint(dAtA, i, uint64(m.IfNotModifiedAfterNs))
 		i--
@@ -7579,6 +7608,18 @@ func (m *DeleteEntryRequest) SizeVT() (n int) {
 	if m.IfNotModifiedAfterNs != 0 {
 		n += 1 + protohelpers.SizeOfVarint(uint64(m.IfNotModifiedAfterNs))
 	}
+	if len(m.ExpectedExtended) > 0 {
+		for k, v := range m.ExpectedExtended {
+			_ = k
+			_ = v
+			l = 1 + len(v) + protohelpers.SizeOfVarint(uint64(len(v)))
+			mapEntrySize := 1 + len(k) + protohelpers.SizeOfVarint(uint64(len(k))) + l
+			n += mapEntrySize + 1 + protohelpers.SizeOfVarint(uint64(mapEntrySize))
+		}
+	}
+	if m.IsMoved {
+		n += 2
+	}
 	n += len(m.unknownFields)
 	return n
 }
@@ -16232,6 +16273,154 @@ func (m *DeleteEntryRequest) UnmarshalVT(dAtA []byte) error {
 					break
 				}
 			}
+		case 12:
+			if wireType != 2 {
+				return fmt.Errorf("proto: wrong wireType = %d for field ExpectedExtended", wireType)
+			}
+			var msglen int
+			for shift := uint(0); ; shift += 7 {
+				if shift >= 64 {
+					return protohelpers.ErrIntOverflow
+				}
+				if iNdEx >= l {
+					return io.ErrUnexpectedEOF
+				}
+				b := dAtA[iNdEx]
+				iNdEx++
+				msglen |= int(b&0x7F) << shift
+				if b < 0x80 {
+					break
+				}
+			}
+			if msglen < 0 {
+				return protohelpers.ErrInvalidLength
+			}
+			postIndex := iNdEx + msglen
+			if postIndex < 0 {
+				return protohelpers.ErrInvalidLength
+			}
+			if postIndex > l {
+				return io.ErrUnexpectedEOF
+			}
+			if m.ExpectedExtended == nil {
+				m.ExpectedExtended = make(map[string][]byte)
+			}
+			var mapkey string
+			var mapvalue []byte
+			for iNdEx < postIndex {
+				entryPreIndex := iNdEx
+				var wire uint64
+				for shift := uint(0); ; shift += 7 {
+					if shift >= 64 {
+						return protohelpers.ErrIntOverflow
+					}
+					if iNdEx >= l {
+						return io.ErrUnexpectedEOF
+					}
+					b := dAtA[iNdEx]
+					iNdEx++
+					wire |= uint64(b&0x7F) << shift
+					if b < 0x80 {
+						break
+					}
+				}
+				fieldNum := int32(wire >> 3)
+				if fieldNum == 1 {
+					var stringLenmapkey uint64
+					for shift := uint(0); ; shift += 7 {
+						if shift >= 64 {
+							return protohelpers.ErrIntOverflow
+						}
+						if iNdEx >= l {
+							return io.ErrUnexpectedEOF
+						}
+						b := dAtA[iNdEx]
+						iNdEx++
+						stringLenmapkey |= uint64(b&0x7F) << shift
+						if b < 0x80 {
+							break
+						}
+					}
+					intStringLenmapkey := int(stringLenmapkey)
+					if intStringLenmapkey < 0 {
+						return protohelpers.ErrInvalidLength
+					}
+					postStringIndexmapkey := iNdEx + intStringLenmapkey
+					if postStringIndexmapkey < 0 {
+						return protohelpers.ErrInvalidLength
+					}
+					if postStringIndexmapkey > l {
+						return io.ErrUnexpectedEOF
+					}
+					mapkey = string(dAtA[iNdEx:postStringIndexmapkey])
+					iNdEx = postStringIndexmapkey
+				} else if fieldNum == 2 {
+					var mapbyteLen uint64
+					for shift := uint(0); ; shift += 7 {
+						if shift >= 64 {
+							return protohelpers.ErrIntOverflow
+						}
+						if iNdEx >= l {
+							return io.ErrUnexpectedEOF
+						}
+						b := dAtA[iNdEx]
+						iNdEx++
+						mapbyteLen |= uint64(b&0x7F) << shift
+						if b < 0x80 {
+							break
+						}
+					}
+					intMapbyteLen := int(mapbyteLen)
+					if intMapbyteLen < 0 {
+						return protohelpers.ErrInvalidLength
+					}
+					postbytesIndex := iNdEx + intMapbyteLen
+					if postbytesIndex < 0 {
+						return protohelpers.ErrInvalidLength
+					}
+					if postbytesIndex > l {
+						return io.ErrUnexpectedEOF
+					}
+					mapvalue = make([]byte, mapbyteLen)
+					copy(mapvalue, dAtA[iNdEx:postbytesIndex])
+					iNdEx = postbytesIndex
+				} else {
+					iNdEx = entryPreIndex
+					skippy, err := protohelpers.Skip(dAtA[iNdEx:])
+					if err != nil {
+						return err
+					}
+					if (skippy < 0) || (iNdEx+skippy) < 0 {
+						return protohelpers.ErrInvalidLength
+					}
+					if (iNdEx + skippy) > postIndex {
+						return io.ErrUnexpectedEOF
+					}
+					iNdEx += skippy
+				}
+			}
+			m.ExpectedExtended[mapkey] = mapvalue
+			iNdEx = postIndex
+		case 13:
+			if wireType != 0 {
+				return fmt.Errorf("proto: wrong wireType = %d for field IsMoved", wireType)
+			}
+			var v int
+			for shift := uint(0); ; shift += 7 {
+				if shift >= 64 {
+					return protohelpers.ErrIntOverflow
+				}
+				if iNdEx >= l {
+					return io.ErrUnexpectedEOF
+				}
+				b := dAtA[iNdEx]
+				iNdEx++
+				v |= int(b&0x7F) << shift
+				if b < 0x80 {
+					break
+				}
+			}
+			m.IsMoved = bool(v != 0)
 		default:
 			iNdEx = preIndex
 			skippy, err := protohelpers.Skip(dAtA[iNdEx:])
diff --git a/weed/s3api/s3tables/filer_ops.go b/weed/s3api/s3tables/filer_ops.go
index 4ed73cbc39..aec770ccc9 100644
--- a/weed/s3api/s3tables/filer_ops.go
+++ b/weed/s3api/s3tables/filer_ops.go
@@ -17,6 +17,7 @@ import (
 var (
 	ErrAttributeNotFound = errors.New("attribute not found")
 	ErrConcurrentUpdate  = errors.New("attribute changed concurrently")
+	ErrNameTaken         = errors.New("catalog name is taken")
 )
 
 // extendedAttributeUpdateAttempts bounds the read-modify-write retry loop in
@@ -179,6 +180,75 @@ func (h *S3TablesHandler) removeExtendedAttributesIf(
 	})
 }
 
+// claimCatalogEntry writes a new catalog entry's marker attributes in one
+// compare-checked update. Every catalog marker must still be absent: a
+// delete's restore or a competing create that landed since the caller's check
+// is a name conflict, not a record this write may overwrite — an overwrite
+// would leave the loser's tags, policy, and maintenance settings on the new
+// record.
+func (h *S3TablesHandler) claimCatalogEntry(ctx context.Context, client filer_pb.SeaweedFilerClient, path string, attrs map[string][]byte) error {
+	return h.mutateEntryExtended(ctx, client, path, func(extended map[string][]byte) error {
+		for _, key := range s3tablesExtendedKeys {
+			if _, ok := extended[key]; ok {
+				return fmt.Errorf("%w: %s set on %s", ErrNameTaken, key, path)
+			}
+		}
+		for key, data := range attrs {
+			extended[key] = data
+		}
+		return nil
+	})
+}
+
+// claimCatalogRecord reserves a catalog record for an in-flight delete or
+// rename under one compare-checked write: the entry must still hold exactly
+// expected. A record claimed by another kind of operation refuses the claim,
+// so the loser backs out before any data or destination entry is written;
+// a retry of the same kind may adopt its own earlier claim.
+func (h *S3TablesHandler) claimCatalogRecord(
+	ctx context.Context,
+	client filer_pb.SeaweedFilerClient,
+	path string,
+	expected map[string][]byte,
+	claim string,
+) error {
+	return h.mutateEntryExtended(ctx, client, path, func(extended map[string][]byte) error {
+		for key, want := range expected {
+			if key == ExtendedKeyDeleting {
+				continue
+			}
+			if !bytes.Equal(extended[key], want) {
+				return fmt.Errorf("%w: %s changed on %s", ErrConcurrentUpdate, key, path)
+			}
+		}
+		if cur, ok := extended[ExtendedKeyDeleting]; ok && string(cur) != claim {
+			return fmt.Errorf("%w: %s held on %s", ErrConcurrentUpdate, ExtendedKeyDeleting, path)
+		}
+		extended[ExtendedKeyDeleting] = []byte(claim)
+		return nil
+	})
+}
+
+// releaseCatalogRecord lifts a claimCatalogRecord reservation while the entry
+// still holds expected — which includes the claim itself — restoring the
+// record so the failed operation can be retried.
+func (h *S3TablesHandler) releaseCatalogRecord(
+	ctx context.Context,
+	client filer_pb.SeaweedFilerClient,
+	path string,
+	expected map[string][]byte,
+) error {
+	return h.mutateEntryExtended(ctx, client, path, func(extended map[string][]byte) error {
+		for key, want := range expected {
+			if !bytes.Equal(extended[key], want) {
+				return fmt.Errorf("%w: %s changed on %s", ErrConcurrentUpdate, key, path)
+			}
+		}
+		delete(extended, ExtendedKeyDeleting)
+		return nil
+	})
+}
+
 // updateExtendedAttribute applies mutate to the current value of key and writes
 // the result back. mutate runs again on each retry, so it always sees the
 // current value.
@@ -211,6 +281,7 @@ var s3tablesExtendedKeys = []string{
 	ExtendedKeyMaintenance,
 	ExtendedKeyMaintenanceStatus,
 	ExtendedKeyEntryType,
+	ExtendedKeyDeleting,
 }
 
 // SnapshotExtended captures an entry's attributes as an UpdateEntry
@@ -314,6 +385,27 @@ func (h *S3TablesHandler) deleteDirectory(ctx context.Context, client filer_pb.S
 	return filer_pb.DoRemove(ctx, client, dir, name, true, true, true, false, nil)
 }
 
+// deleteDirectoryIfMatches deletes a directory and all its contents only
+// while the entry still carries the extended attributes the caller captured:
+// the filer compares and removes in one operation under the path lock, so an
+// attribute write that keeps Mtime or a delete+recreate in between refuses the
+// delete with ErrConcurrentUpdate instead of losing the replacement.
+func (h *S3TablesHandler) deleteDirectoryIfMatches(ctx context.Context, client filer_pb.SeaweedFilerClient, path string, expected *filer_pb.Entry) error {
+	dir, name := splitPath(path)
+	_, err := filer_pb.DoRemoveRequest(ctx, client, &filer_pb.DeleteEntryRequest{
+		Directory:            dir,
+		Name:                 name,
+		IsDeleteData:         true,
+		IsRecursive:          true,
+		IgnoreRecursiveError: true,
+		ExpectedExtended:     snapshotExtended(expected.Extended),
+	})
+	if status.Code(err) == codes.FailedPrecondition {
+		return fmt.Errorf("%w: %s", ErrConcurrentUpdate, path)
+	}
+	return err
+}
+
 // entryExists checks if an entry exists at the given path
 func (h *S3TablesHandler) entryExists(ctx context.Context, client filer_pb.SeaweedFilerClient, path string) bool {
 	dir, name := splitPath(path)
diff --git a/weed/s3api/s3tables/handler.go b/weed/s3api/s3tables/handler.go
index 4bf960ca4f..eda5e9ae6c 100644
--- a/weed/s3api/s3tables/handler.go
+++ b/weed/s3api/s3tables/handler.go
@@ -32,6 +32,10 @@ const (
 	// contend on the same attribute.
 	ExtendedKeyMaintenanceStatus = s3_constants.ExtS3TablesPrefix + "maintenanceStatus"
 	ExtendedKeyEntryType         = s3_constants.ExtS3TablesPrefix + "entryType"
+	// ExtendedKeyDeleting marks a catalog record claimed by an in-flight
+	// delete or rename, so the claim survives until the operation finishes
+	// or releases it.
+	ExtendedKeyDeleting = s3_constants.ExtS3TablesPrefix + "deleting"
 
 	// Entry-type marker values for ExtendedKeyEntryType. Absent or "table" means
 	// a table; views are stored like tables but tagged "view".
diff --git a/weed/s3api/s3tables/handler_delete_decouple_test.go b/weed/s3api/s3tables/handler_delete_decouple_test.go
index f574caf63f..c22c433325 100644
--- a/weed/s3api/s3tables/handler_delete_decouple_test.go
+++ b/weed/s3api/s3tables/handler_delete_decouple_test.go
@@ -3,6 +3,7 @@ package s3tables
 import (
 	"context"
 	"encoding/json"
+	"net/http"
 	"path"
 	"testing"
 
@@ -21,6 +22,86 @@ func runDeleteTable(t *testing.T, m *Manager, fs *s3tablestest.MemFiler, namespa
 	}, nil, "")
 }
 
+// A write that lands between the delete's read and its conditional commit —
+// an xattr update keeps mtime — must turn a token delete into a conflict, not
+// get erased by it.
+func TestDeleteTableTokenDeleteLosesToConcurrentUpdate(t *testing.T) {
+	fs, m := startRenameManager(t)
+
+	token := "tok-ct"
+	meta, _ := json.Marshal(tableMetadataInternal{
+		Name:           "ct",
+		Namespace:      "ns",
+		Format:         "ICEBERG",
+		OwnerAccountID: DefaultAccountID,
+		VersionToken:   token,
+	})
+	fs.Put(GetNamespacePath(renameTestBucket, "ns"), "ct", map[string][]byte{
+		ExtendedKeyMetadata: meta,
+	})
+	tablePath := GetTablePath(renameTestBucket, "ns", "ct")
+	fs.Put(tablePath, "data", nil)
+
+	fs.BeforeDelete = func() {
+		fs.Put(GetNamespacePath(renameTestBucket, "ns"), "ct", map[string][]byte{
+			ExtendedKeyMetadata: meta,
+			ExtendedKeyTags:     []byte(`{"k":"v"}`),
+		})
+	}
+
+	status, resp := runHandler(t, m, fs.Client, "DeleteTable", &DeleteTableRequest{
+		TableBucketARN: mustBucketARN(t),
+		Namespace:      []string{"ns"},
+		Name:           "ct",
+		VersionToken:   token,
+	})
+	assert.Equal(t, http.StatusConflict, status)
+	assert.Equal(t, ErrCodeConflict, resp.Type)
+
+	assert.NotNil(t, fs.Get(GetNamespacePath(renameTestBucket, "ns"), "ct"), "the updated record must survive")
+	assert.NotNil(t, fs.Get(tablePath, "data"), "the table's data must survive")
+}
+
+// A create that checked the name while it was free must not write over a
+// delete's restore: the claim loses instead of layering new metadata over the
+// old tags, policy, and maintenance settings.
+func TestCreateTableLosesToRestoredMarkers(t *testing.T) {
+	fs, m := startRenameManager(t)
+
+	nsPath := GetNamespacePath(renameTestBucket, "ns")
+	fs.Put(nsPath, "newt", nil)
+
+	oldMeta, _ := json.Marshal(tableMetadataInternal{
+		Name:           "newt",
+		Namespace:      "ns",
+		Format:         "ICEBERG",
+		OwnerAccountID: DefaultAccountID,
+	})
+	restored := map[string][]byte{
+		ExtendedKeyMetadata:    oldMeta,
+		ExtendedKeyEntryType:   []byte(EntryTypeTable),
+		ExtendedKeyTags:        []byte(`{"old":"tag"}`),
+		ExtendedKeyMaintenance: []byte(`{"old":"maintenance"}`),
+	}
+	fs.BeforeUpdate = func() {
+		fs.Put(nsPath, "newt", restored)
+	}
+
+	status, resp := runHandler(t, m, fs.Client, "CreateTable", &CreateTableRequest{
+		TableBucketARN: mustBucketARN(t),
+		Namespace:      []string{"ns"},
+		Name:           "newt",
+		Format:         FormatIceberg,
+	})
+	assert.Equal(t, http.StatusConflict, status)
+	assert.Equal(t, ErrCodeTableAlreadyExists, resp.Type)
+
+	got := fs.Get(nsPath, "newt")
+	require.NotNil(t, got)
+	assert.Equal(t, restored[ExtendedKeyTags], got.Extended[ExtendedKeyTags], "restored markers must not be overwritten")
+	assert.Equal(t, restored[ExtendedKeyMetadata], got.Extended[ExtendedKeyMetadata])
+}
+
 // A table whose data was decoupled from its name (created over a leftover from a
 // rename): catalog marker at ns/newt, data at ns/newt-x, and ns/newt still holds
 // another table's leftover data. Dropping it must purge only its own data and
@@ -168,3 +249,77 @@ func TestDeleteTableRefusesNestedSiblingDataPath(t *testing.T) {
 	assert.NotNil(t, fs.Get(GetNamespacePath(renameTestBucket, "nsa"), "vtab"),
 		"the victim table's catalog entry must survive")
 }
+
+// A rename that completes in the token delete's check-to-claim window moves
+// the record to another name: the stale delete must lose on the claim instead
+// of purging the data the moved record still points at.
+func TestDeleteTableTokenDeleteLosesToCompletedRename(t *testing.T) {
+	fs, m := startRenameManager(t)
+
+	token := "tok-rn"
+	meta, _ := json.Marshal(tableMetadataInternal{
+		Name:             "rn",
+		Namespace:        "ns",
+		Format:           "ICEBERG",
+		OwnerAccountID:   DefaultAccountID,
+		VersionToken:     token,
+		MetadataLocation: "s3://" + renameTestBucket + "/ns/old-x/metadata/v1.metadata.json",
+	})
+	fs.Put(GetNamespacePath(renameTestBucket, "ns"), "rn", map[string][]byte{
+		ExtendedKeyMetadata:  meta,
+		ExtendedKeyEntryType: []byte(EntryTypeTable),
+	})
+	dataPath := GetTablePath(renameTestBucket, "ns", "old-x")
+	fs.Put(dataPath, "data", nil)
+
+	fs.BeforeUpdate = func() {
+		// The rename's source clear has already run by the time the delete's
+		// claim write lands.
+		fs.Put(GetNamespacePath(renameTestBucket, "ns"), "rn", nil)
+	}
+
+	status, resp := runHandler(t, m, fs.Client, "DeleteTable", &DeleteTableRequest{
+		TableBucketARN: mustBucketARN(t),
+		Namespace:      []string{"ns"},
+		Name:           "rn",
+		VersionToken:   token,
+	})
+	assert.Equal(t, http.StatusConflict, status)
+	assert.Equal(t, ErrCodeConflict, resp.Type)
+
+	assert.NotNil(t, fs.Get(dataPath, "data"), "the moved table's data must survive the stale delete")
+}
+
+// A delete's claim on the source must turn a rename into a conflict before
+// any destination entry exists: the claim is what keeps a losing rename from
+// leaving a destination marker pointing at data the delete went on to purge.
+func TestRenameTableLosesToDeleteClaim(t *testing.T) {
+	fs, m := startRenameManager(t)
+
+	nsPath := GetNamespacePath(renameTestBucket, "ns")
+	fs.BeforeUpdate = func() {
+		e := fs.Get(nsPath, "t")
+		claimed := map[string][]byte{}
+		for k, v := range e.Extended {
+			claimed[k] = v
+		}
+		claimed[ExtendedKeyDeleting] = []byte("delete")
+		fs.Put(nsPath, "t", claimed)
+	}
+
+	status, resp := runHandler(t, m, fs.Client, "RenameTable", &RenameTableRequest{
+		TableBucketARN:  mustBucketARN(t),
+		SourceNamespace: []string{"ns"},
+		SourceName:      "t",
+		DestNamespace:   []string{"ns"},
+		DestName:        "t2",
+	})
+	assert.Equal(t, http.StatusConflict, status)
+	assert.Equal(t, ErrCodeConflict, resp.Type)
+
+	assert.Nil(t, fs.Get(nsPath, "t2"), "a losing rename must not publish the destination")
+	src := fs.Get(nsPath, "t")
+	require.NotNil(t, src)
+	assert.NotNil(t, src.Extended[ExtendedKeyMetadata], "the claimed source record must survive")
+	assert.NotNil(t, fs.Get(GetTablePath(renameTestBucket, "ns", "t"), "data"))
+}
diff --git a/weed/s3api/s3tables/handler_table.go b/weed/s3api/s3tables/handler_table.go
index 5ee6f01391..79c41cf674 100644
--- a/weed/s3api/s3tables/handler_table.go
+++ b/weed/s3api/s3tables/handler_table.go
@@ -13,6 +13,7 @@ import (
 	"strings"
 	"time"
 
+	"github.com/seaweedfs/seaweedfs/weed/glog"
 	"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
 )
 
@@ -36,7 +37,7 @@ func (h *S3TablesHandler) handleCreateTable(w http.ResponseWriter, r *http.Reque
 		return fmt.Errorf("invalid format")
 	}
 
-	target, err := h.authorizeCreateTable(w, r, filerClient, req.TableBucketARN, req.Namespace, req.Name, req.Tags)
+	target, err := h.authorizeCreateTable(w, r, filerClient, req.TableBucketARN, req.Namespace, req.Name, req.Tags, false)
 	if err != nil {
 		return err
 	}
@@ -129,6 +130,14 @@ func (h *S3TablesHandler) handleCreateTable(w http.ResponseWriter, r *http.Reque
 		return fmt.Errorf("failed to marshal metadata: %w", err)
 	}
 
+	var tagsBytes []byte
+	if len(req.Tags) > 0 {
+		if tagsBytes, err = json.Marshal(req.Tags); err != nil {
+			h.writeError(w, http.StatusInternalServerError, ErrCodeInternalError, "failed to marshal tags")
+			return fmt.Errorf("failed to marshal tags: %w", err)
+		}
+	}
+
 	err = filerClient.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
 		// Ensure table directory exists (may already be created by object storage clients)
 		if err := h.ensureDirectory(r.Context(), client, tablePath); err != nil {
@@ -141,31 +150,21 @@ func (h *S3TablesHandler) handleCreateTable(w http.ResponseWriter, r *http.Reque
 			return err
 		}
 
-		// Set metadata as extended attribute
-		if err := h.setExtendedAttribute(r.Context(), client, tablePath, ExtendedKeyMetadata, metadataBytes); err != nil {
-			return err
+		attrs := map[string][]byte{
+			ExtendedKeyMetadata:  metadataBytes,
+			ExtendedKeyEntryType: []byte(EntryTypeTable),
 		}
-
-		// Tag the entry as a table so view listings can exclude it.
-		if err := h.setExtendedAttribute(r.Context(), client, tablePath, ExtendedKeyEntryType, []byte(EntryTypeTable)); err != nil {
-			return err
+		if len(tagsBytes) > 0 {
+			attrs[ExtendedKeyTags] = tagsBytes
 		}
-
-		// Set tags if provided
-		if len(req.Tags) > 0 {
-			tagsBytes, err := json.Marshal(req.Tags)
-			if err != nil {
-				return fmt.Errorf("failed to marshal tags: %w", err)
-			}
-			if err := h.setExtendedAttribute(r.Context(), client, tablePath, ExtendedKeyTags, tagsBytes); err != nil {
-				return err
-			}
-		}
-
-		return nil
+		return h.claimCatalogEntry(r.Context(), client, tablePath, attrs)
 	})
 
 	if err != nil {
+		if errors.Is(err, ErrNameTaken) {
+			h.writeError(w, http.StatusConflict, ErrCodeTableAlreadyExists, fmt.Sprintf("table %s already exists", tableName))
+			return err
+		}
 		h.writeError(w, http.StatusInternalServerError, ErrCodeInternalError, "failed to create table")
 		return err
 	}
@@ -228,7 +227,7 @@ func (h *S3TablesHandler) handleRegisterTable(w http.ResponseWriter, r *http.Req
 		return fmt.Errorf("metadataLocation is required")
 	}
 
-	target, err := h.authorizeCreateTable(w, r, filerClient, req.TableBucketARN, req.Namespace, req.Name, nil)
+	target, err := h.authorizeCreateTable(w, r, filerClient, req.TableBucketARN, req.Namespace, req.Name, nil, false)
 	if err != nil {
 		return err
 	}
@@ -282,9 +281,15 @@ func (h *S3TablesHandler) handleRegisterTable(w http.ResponseWriter, r *http.Req
 		if err := h.ensureDirectory(r.Context(), client, tablePath); err != nil {
 			return err
 		}
-		return h.setExtendedAttribute(r.Context(), client, tablePath, ExtendedKeyMetadata, metadataBytes)
+		return h.claimCatalogEntry(r.Context(), client, tablePath, map[string][]byte{
+			ExtendedKeyMetadata: metadataBytes,
+		})
 	})
 	if err != nil {
+		if errors.Is(err, ErrNameTaken) {
+			h.writeError(w, http.StatusConflict, ErrCodeTableAlreadyExists, fmt.Sprintf("table %s already exists", tableName))
+			return err
+		}
 		h.writeError(w, http.StatusInternalServerError, ErrCodeInternalError, "failed to register table")
 		return err
 	}
@@ -896,8 +901,16 @@ func (h *S3TablesHandler) handleDeleteTable(w http.ResponseWriter, r *http.Reque
 	var bucketTags map[string]string
 	var tableTags map[string]string
 	var bucketMetadata tableBucketMetadata
+	var tableEntry *filer_pb.Entry
 	err = filerClient.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
-		data, err := h.readTableMetadata(r.Context(), client, tablePath)
+		// One lookup feeds both the version-token check and the conditional
+		// delete below: a second read could land on a replacement entry while
+		// the token was validated against the old one.
+		tableEntry, err = h.lookupEntry(r.Context(), client, tablePath)
+		if err != nil {
+			return err
+		}
+		data, err := tableMetadata(tableEntry)
 		if err != nil {
 			return err
 		}
@@ -1035,6 +1048,40 @@ func (h *S3TablesHandler) handleDeleteTable(w http.ResponseWriter, r *http.Reque
 			// lives elsewhere. Purge the data, then clear the catalog marker
 			// without deleting the name path -- it may still hold another
 			// table's data that was left when this name was reused.
+			if req.VersionToken != "" && tableEntry != nil {
+				// A token caller owns exactly the record it read. Claim it
+				// under the captured attributes before any data is removed:
+				// a rename or delete+recreate that moved the record aborts
+				// here, while it still points at live data. The claim holds
+				// the name through the purge, a failed purge releases it so
+				// the intact record can be retried, and the marker comes off
+				// under a compare on the claimed record.
+				snapshot := snapshotExtended(tableEntry.Extended)
+				if err := h.claimCatalogRecord(r.Context(), client, tablePath, snapshot, "delete"); err != nil {
+					if errors.Is(err, ErrConcurrentUpdate) {
+						return ErrVersionTokenMismatch
+					}
+					return err
+				}
+				claimed := snapshotExtended(tableEntry.Extended)
+				claimed[ExtendedKeyDeleting] = []byte("delete")
+				if err := h.deleteDirectory(r.Context(), client, dataPath); err != nil {
+					if relErr := h.releaseCatalogRecord(r.Context(), client, tablePath, claimed); relErr != nil {
+						glog.Warningf("delete table %s: release claim: %v", tablePath, relErr)
+					}
+					return err
+				}
+				err := h.removeExtendedAttributesIf(r.Context(), client, tablePath, claimed,
+					ExtendedKeyMetadata, ExtendedKeyMetadataVersion, ExtendedKeyPolicy, ExtendedKeyTags, ExtendedKeyEntryType,
+					ExtendedKeyMaintenance, ExtendedKeyMaintenanceStatus, ExtendedKeyDeleting)
+				if err != nil {
+					if errors.Is(err, ErrConcurrentUpdate) {
+						return ErrVersionTokenMismatch
+					}
+					return err
+				}
+				return nil
+			}
 			if err := h.deleteDirectory(r.Context(), client, dataPath); err != nil {
 				return err
 			}
@@ -1042,11 +1089,27 @@ func (h *S3TablesHandler) handleDeleteTable(w http.ResponseWriter, r *http.Reque
 				ExtendedKeyMetadata, ExtendedKeyMetadataVersion, ExtendedKeyPolicy, ExtendedKeyTags, ExtendedKeyEntryType,
 				ExtendedKeyMaintenance, ExtendedKeyMaintenanceStatus)
 		}
-		// Colocated table: the name path holds the data.
+		// Colocated table: the name path holds the data. A token caller's
+		// delete carries the captured attributes as a filer precondition, so
+		// compare and removal are one operation under the path lock: an xattr
+		// write that keeps Mtime, or a delete+recreate in between, refuses it.
+		if req.VersionToken != "" && tableEntry != nil {
+			if err := h.deleteDirectoryIfMatches(r.Context(), client, tablePath, tableEntry); err != nil {
+				if errors.Is(err, ErrConcurrentUpdate) {
+					return ErrVersionTokenMismatch
+				}
+				return err
+			}
+			return nil
+		}
 		return h.deleteDirectory(r.Context(), client, tablePath)
 	})
 
 	if err != nil {
+		if errors.Is(err, ErrVersionTokenMismatch) {
+			h.writeError(w, http.StatusConflict, ErrCodeConflict, "version token mismatch")
+			return err
+		}
 		h.writeError(w, http.StatusInternalServerError, ErrCodeInternalError, "failed to delete table")
 		return err
 	}
@@ -1123,6 +1186,13 @@ func (h *S3TablesHandler) readTableMetadata(ctx context.Context, client filer_pb
 	if err != nil {
 		return nil, err
 	}
+	return tableMetadata(entry)
+}
+
+// tableMetadata extracts the table-metadata xattr from an entry. A view stored
+// at the same name is reported absent, the way GetTable and the renamer's
+// entry-type check already treat kind mismatches.
+func tableMetadata(entry *filer_pb.Entry) ([]byte, error) {
 	if EntryType(entry.Extended) == EntryTypeView {
 		return nil, filer_pb.ErrNotFound
 	}
@@ -1214,10 +1284,6 @@ func (h *S3TablesHandler) renameCatalogEntry(w http.ResponseWriter, r *http.Requ
 	var metadataVersionXattr []byte
 	var maintenanceXattr []byte
 	var maintenanceStatusXattr []byte
-	// The values the rename copies. The source is only cleared while it still
-	// holds exactly these, so a write that lands mid-rename is not deleted here
-	// after having missed the copy to the destination.
-	var copiedFromSource map[string][]byte
 	var tablePolicy string
 	var bucketPolicy string
 	var bucketTags map[string]string
@@ -1255,10 +1321,6 @@ func (h *S3TablesHandler) renameCatalogEntry(w http.ResponseWriter, r *http.Requ
 			return err
 		}
 		srcExtended = srcEntry.Extended
-		copiedFromSource = make(map[string][]byte, len(renamedTableAttributes))
-		for _, key := range renamedTableAttributes {
-			copiedFromSource[key] = srcEntry.Extended[key]
-		}
 
 		// The maintenance configuration and its last-run status belong to the
 		// table, so they move with it; leaving them behind re-enables
@@ -1421,52 +1483,69 @@ func (h *S3TablesHandler) renameCatalogEntry(w http.ResponseWriter, r *http.Requ
 		return fmt.Errorf("failed to marshal metadata: %w", err)
 	}
 
-	// Write the destination entry before deleting the source so a mid-rename
-	// failure can never lose the table.
+	// Claim the source record before publishing the destination: a delete or
+	// a second rename that wins the claim backs out here — while no
+	// destination entry exists — instead of leaving one behind pointing at
+	// data a delete already removed.
 	err = filerClient.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
-		if err := h.createDirectory(r.Context(), client, destPath); err != nil {
+		if err := h.claimCatalogRecord(r.Context(), client, srcPath, snapshotExtended(srcExtended), "rename"); err != nil {
 			return err
 		}
+		claimed := snapshotExtended(srcExtended)
+		claimed[ExtendedKeyDeleting] = []byte("rename")
+		releaseClaim := func(err error) error {
+			if relErr := h.releaseCatalogRecord(r.Context(), client, srcPath, claimed); relErr != nil {
+				glog.Warningf("rename %s: release claim: %v", srcPath, relErr)
+			}
+			return err
+		}
+		if err := h.createDirectory(r.Context(), client, destPath); err != nil {
+			return releaseClaim(err)
+		}
 		if err := h.setExtendedAttribute(r.Context(), client, destPath, ExtendedKeyMetadata, metadataBytes); err != nil {
-			return err
+			return releaseClaim(err)
 		}
 		if err := h.setExtendedAttribute(r.Context(), client, destPath, ExtendedKeyEntryType, []byte(kind.entryType)); err != nil {
-			return err
+			return releaseClaim(err)
 		}
 		if len(metadataVersionXattr) > 0 {
 			if err := h.setExtendedAttribute(r.Context(), client, destPath, ExtendedKeyMetadataVersion, metadataVersionXattr); err != nil {
-				return err
+				return releaseClaim(err)
 			}
 		}
 		if len(tableTags) > 0 {
 			tagsBytes, err := json.Marshal(tableTags)
 			if err != nil {
-				return fmt.Errorf("failed to marshal tags: %w", err)
+				return releaseClaim(fmt.Errorf("failed to marshal tags: %w", err))
 			}
 			if err := h.setExtendedAttribute(r.Context(), client, destPath, ExtendedKeyTags, tagsBytes); err != nil {
-				return err
+				return releaseClaim(err)
 			}
 		}
 		if tablePolicy != "" {
 			if err := h.setExtendedAttribute(r.Context(), client, destPath, ExtendedKeyPolicy, []byte(tablePolicy)); err != nil {
-				return err
+				return releaseClaim(err)
 			}
 		}
 		if len(maintenanceXattr) > 0 {
 			if err := h.setExtendedAttribute(r.Context(), client, destPath, ExtendedKeyMaintenance, maintenanceXattr); err != nil {
-				return err
+				return releaseClaim(err)
 			}
 		}
 		if len(maintenanceStatusXattr) > 0 {
 			if err := h.setExtendedAttribute(r.Context(), client, destPath, ExtendedKeyMaintenanceStatus, maintenanceStatusXattr); err != nil {
-				return err
+				return releaseClaim(err)
 			}
 		}
 		// Soft-delete the source catalog identity in place: drop its catalog xattrs
 		// so the name stops resolving while the metadata/ and data/ children stay put
 		// (manifests embed absolute paths, so the data must not move).
-		return h.removeExtendedAttributesIf(r.Context(), client, srcPath, copiedFromSource,
-			renamedTableAttributes...)
+		err := h.removeExtendedAttributesIf(r.Context(), client, srcPath, claimed,
+			append(append([]string{}, renamedTableAttributes...), ExtendedKeyDeleting)...)
+		if err != nil {
+			return releaseClaim(err)
+		}
+		return nil
 	})
 
 	if err != nil {
@@ -1750,7 +1829,7 @@ type createTableTarget struct {
 // Deferred creates (Iceberg stage-create) write into the table bucket before any
 // table is registered, so they run this same gate first through
 // Manager.AuthorizeCreateTable.
-func (h *S3TablesHandler) authorizeCreateTable(w http.ResponseWriter, r *http.Request, filerClient FilerClient, tableBucketARN string, namespace []string, name string, requestTags map[string]string) (*createTableTarget, error) {
+func (h *S3TablesHandler) authorizeCreateTable(w http.ResponseWriter, r *http.Request, filerClient FilerClient, tableBucketARN string, namespace []string, name string, requestTags map[string]string, allowMissingNamespace bool) (*createTableTarget, error) {
 	if tableBucketARN == "" {
 		h.writeError(w, http.StatusBadRequest, ErrCodeInvalidRequest, "tableBucketARN is required")
 		return nil, fmt.Errorf("tableBucketARN is required")
@@ -1781,14 +1860,21 @@ func (h *S3TablesHandler) authorizeCreateTable(w http.ResponseWriter, r *http.Re
 
 	// Check if namespace exists
 	namespacePath := GetNamespacePath(bucketName, namespaceName)
-	namespaceMetadata, err := h.loadNamespaceMetadata(r.Context(), filerClient, bucketName, namespaceName)
+	nsMetadata, err := h.loadNamespaceMetadata(r.Context(), filerClient, bucketName, namespaceName)
+	namespaceExists := err == nil
 	if err != nil {
-		if errors.Is(err, filer_pb.ErrNotFound) {
-			h.writeError(w, http.StatusNotFound, ErrCodeNoSuchNamespace, fmt.Sprintf("namespace %s not found", namespaceName))
+		if errors.Is(err, filer_pb.ErrNotFound) && allowMissingNamespace {
+			// An implicit namespace can be authorized before it is declared:
+			// evaluate the grant against the bucket alone.
+			err = nil
 		} else {
-			h.writeError(w, http.StatusInternalServerError, ErrCodeInternalError, fmt.Sprintf("failed to check namespace: %v", err))
+			if errors.Is(err, filer_pb.ErrNotFound) {
+				h.writeError(w, http.StatusNotFound, ErrCodeNoSuchNamespace, fmt.Sprintf("namespace %s not found", namespaceName))
+			} else {
+				h.writeError(w, http.StatusInternalServerError, ErrCodeInternalError, fmt.Sprintf("failed to check namespace: %v", err))
+			}
+			return nil, err
 		}
-		return nil, err
 	}
 
 	// Authorize table creation using policy framework (namespace + bucket policies)
@@ -1811,12 +1897,15 @@ func (h *S3TablesHandler) authorizeCreateTable(w http.ResponseWriter, r *http.Re
 		}
 
 		// Fetch namespace policy if it exists
-		policyData, err := h.getExtendedAttribute(r.Context(), client, namespacePath, ExtendedKeyPolicy)
-		if err == nil {
-			namespacePolicy = string(policyData)
-		} else if !errors.Is(err, ErrAttributeNotFound) {
-			return fmt.Errorf("failed to fetch namespace policy: %v", err)
+		if namespaceExists {
+			policyData, err := h.getExtendedAttribute(r.Context(), client, namespacePath, ExtendedKeyPolicy)
+			if err == nil {
+				namespacePolicy = string(policyData)
+			} else if !errors.Is(err, ErrAttributeNotFound) {
+				return fmt.Errorf("failed to fetch namespace policy: %v", err)
+			}
 		}
+		var policyData []byte
 
 		// Fetch bucket policy if it exists
 		policyData, err = h.getExtendedAttribute(r.Context(), client, bucketPath, ExtendedKeyPolicy)
@@ -1839,6 +1928,11 @@ func (h *S3TablesHandler) authorizeCreateTable(w http.ResponseWriter, r *http.Re
 		return nil, err
 	}
 
+	if !namespaceExists {
+		// The implicit namespace has no record yet: authorize it as the
+		// bucket owner's instead of dereferencing the absent metadata.
+		nsMetadata = &namespaceMetadata{OwnerAccountID: bucketMetadata.OwnerAccountID}
+	}
 	bucketARN := h.generateTableBucketARN(bucketMetadata.OwnerAccountID, bucketName)
 	identityActions := getIdentityActions(r)
 	policyContext := &PolicyContext{
@@ -1854,7 +1948,7 @@ func (h *S3TablesHandler) authorizeCreateTable(w http.ResponseWriter, r *http.Re
 		DefaultAllow:     h.defaultAllowFor(r),
 	}
 	if !CheckTableOrBucketPermission("CreateTable", accountID,
-		namespaceMetadata.OwnerAccountID, namespacePolicy, bucketARN,
+		nsMetadata.OwnerAccountID, namespacePolicy, bucketARN,
 		bucketMetadata.OwnerAccountID, bucketPolicy, bucketARN, policyContext) {
 		h.writeError(w, http.StatusForbidden, ErrCodeAccessDenied, "not authorized to create table in this namespace")
 		return nil, ErrAccessDenied
@@ -1865,6 +1959,6 @@ func (h *S3TablesHandler) authorizeCreateTable(w http.ResponseWriter, r *http.Re
 		namespaceName:  namespaceName,
 		tableName:      tableName,
 		bucketFormat:   bucketMetadata.Format,
-		ownerAccountID: namespaceMetadata.OwnerAccountID,
+		ownerAccountID: nsMetadata.OwnerAccountID,
 	}, nil
 }
diff --git a/weed/s3api/s3tables/handler_view.go b/weed/s3api/s3tables/handler_view.go
index 57bad00c5c..f1319c7c07 100644
--- a/weed/s3api/s3tables/handler_view.go
+++ b/weed/s3api/s3tables/handler_view.go
@@ -151,12 +151,16 @@ func (h *S3TablesHandler) handleCreateView(w http.ResponseWriter, r *http.Reques
 		if err := h.ensureDirectory(r.Context(), client, viewPath); err != nil {
 			return err
 		}
-		return h.setExtendedAttributes(r.Context(), client, viewPath, map[string][]byte{
+		return h.claimCatalogEntry(r.Context(), client, viewPath, map[string][]byte{
 			ExtendedKeyMetadata:  metadataBytes,
 			ExtendedKeyEntryType: []byte(EntryTypeView),
 		})
 	})
 	if err != nil {
+		if errors.Is(err, ErrNameTaken) {
+			h.writeError(w, http.StatusConflict, ErrCodeViewAlreadyExists, fmt.Sprintf("view %s already exists", viewName))
+			return err
+		}
 		h.writeError(w, http.StatusInternalServerError, ErrCodeInternalError, "failed to create view")
 		return err
 	}
diff --git a/weed/s3api/s3tables/manager.go b/weed/s3api/s3tables/manager.go
index 301be1eb59..da75b5d65f 100644
--- a/weed/s3api/s3tables/manager.go
+++ b/weed/s3api/s3tables/manager.go
@@ -71,7 +71,7 @@ func (m *Manager) AuthorizeCreateTable(ctx context.Context, filerClient FilerCli
 		return err
 	}
 	recorder := httptest.NewRecorder()
-	_, authErr := m.handler.authorizeCreateTable(recorder, httpReq, filerClient, req.TableBucketARN, req.Namespace, req.Name, req.Tags)
+	_, authErr := m.handler.authorizeCreateTable(recorder, httpReq, filerClient, req.TableBucketARN, req.Namespace, req.Name, req.Tags, req.AllowMissingNamespace)
 	if authErr == nil {
 		return nil
 	}
diff --git a/weed/s3api/s3tables/s3tablestest/memfiler.go b/weed/s3api/s3tables/s3tablestest/memfiler.go
index 5d4540771e..c1047ba9d0 100644
--- a/weed/s3api/s3tables/s3tablestest/memfiler.go
+++ b/weed/s3api/s3tables/s3tablestest/memfiler.go
@@ -34,6 +34,9 @@ type MemFiler struct {
 	// BeforeUpdate runs once, at the start of the next UpdateEntry, so a test
 	// can land a competing write in a handler's read-to-write window.
 	BeforeUpdate func()
+	// BeforeDelete runs once before the next DeleteEntry, so a test can land a
+	// competing write in a handler's check-to-delete window.
+	BeforeDelete func()
 	// RejectDelete returns the reason DeleteEntry refuses a path, answered the
 	// way the filer answers one: no transport error, the reason in the response.
 	RejectDelete func(dir, name string) string
@@ -170,6 +173,10 @@ func (f *MemFiler) UpdateEntry(_ context.Context, req *filer_pb.UpdateEntryReque
 }
 
 func (f *MemFiler) DeleteEntry(_ context.Context, req *filer_pb.DeleteEntryRequest) (*filer_pb.DeleteEntryResponse, error) {
+	if hook := f.BeforeDelete; hook != nil {
+		f.BeforeDelete = nil
+		hook()
+	}
 	if reject := f.RejectDelete; reject != nil {
 		if reason := reject(req.Directory, req.Name); reason != "" {
 			return &filer_pb.DeleteEntryResponse{Error: reason}, nil
@@ -177,6 +184,19 @@ func (f *MemFiler) DeleteEntry(_ context.Context, req *filer_pb.DeleteEntryReque
 	}
 	f.mu.Lock()
 	defer f.mu.Unlock()
+	// The real filer evaluates ExpectedExtended under the path lock and refuses
+	// the delete when the entry no longer matches what the caller captured.
+	for key, expected := range req.ExpectedExtended {
+		var actual []byte
+		if d, ok := f.entries[req.Directory]; ok {
+			if existing := d[req.Name]; existing != nil {
+				actual = existing.Extended[key]
+			}
+		}
+		if !bytes.Equal(actual, expected) {
+			return nil, status.Errorf(codes.FailedPrecondition, "extended attribute %q changed", key)
+		}
+	}
 	if d, ok := f.entries[req.Directory]; ok {
 		delete(d, req.Name)
 	}
diff --git a/weed/s3api/s3tables/types.go b/weed/s3api/s3tables/types.go
index 748abf62c8..261c724be0 100644
--- a/weed/s3api/s3tables/types.go
+++ b/weed/s3api/s3tables/types.go
@@ -195,6 +195,10 @@ type CreateTableRequest struct {
 	MetadataVersion  int               `json:"metadataVersion,omitempty"`
 	MetadataLocation string            `json:"metadataLocation,omitempty"`
 	Tags             map[string]string `json:"tags,omitempty"`
+	// AllowMissingNamespace lets an authorization gate evaluate a create whose
+	// namespace is implicit and not yet declared; the write path still
+	// validates existence. Never deserialized: internal callers set it.
+	AllowMissingNamespace bool `json:"-"`
 }
 
 type CreateTableResponse struct {
diff --git a/weed/s3api/s3vectors/handlers.go b/weed/s3api/s3vectors/handlers.go
index 583f51cb90..bc7b08d6bc 100644
--- a/weed/s3api/s3vectors/handlers.go
+++ b/weed/s3api/s3vectors/handlers.go
@@ -10,8 +10,12 @@ import (
 	"strings"
 	"time"
 
+	"github.com/google/uuid"
+	"github.com/seaweedfs/seaweedfs/weed/glog"
 	"github.com/seaweedfs/seaweedfs/weed/pb/vector_pb"
 	"github.com/seaweedfs/seaweedfs/weed/s3api/s3tables"
+	"google.golang.org/grpc/codes"
+	"google.golang.org/grpc/status"
 	"google.golang.org/protobuf/types/known/structpb"
 )
 
@@ -66,6 +70,9 @@ func arnParts(v *vectorBucketARNs, name, arn string) error {
 	rest := arn[i+len("bucket/"):]
 	parts := strings.Split(rest, "/index/")
 	v.bucket = parts[0]
+	if v.bucket == "" {
+		return fmt.Errorf("malformed ARN %q", arn)
+	}
 	if len(parts) == 2 {
 		v.index = parts[1]
 	}
@@ -83,17 +90,16 @@ func resolveIndexARNs(bucketName, bucketArn, indexName, indexArn string) (vector
 	} else if indexArn != "" {
 		return v, fmt.Errorf("indexArn must be an ARN, got %q", indexArn)
 	}
-	if strings.HasPrefix(bucketArn, "arn:") {
+	if bucketArn != "" {
+		if !strings.HasPrefix(bucketArn, "arn:") {
+			return v, fmt.Errorf("vectorBucketArn must be an ARN, got %q", bucketArn)
+		}
 		if err := arnParts(&v, "", bucketArn); err != nil {
 			return v, err
 		}
 	}
 	if v.bucket == "" {
-		if bucketArn != "" {
-			v.bucket = bucketArn
-		} else {
-			v.bucket = bucketName
-		}
+		v.bucket = bucketName
 	}
 	if v.index == "" {
 		v.index = indexName
@@ -120,46 +126,121 @@ func (s *Server) catalog(ctx context.Context, operation string, req, resp interf
 	return s.tables.Execute(ctx, s.filerClient, operation, req, resp, identityOf(r))
 }
 
-// catalogErrCode returns the error code the in-process catalog reports;
-// errors from other sources carry no code.
+// internalCatalog runs catalog bookkeeping under the trusted identity. It is
+// for reads and writes that accompany — never replace — the operation's own
+// permission check: bucket format lookups, the implicit index namespace, and
+// rollback of a record this request just created.
+func (s *Server) internalCatalog(ctx context.Context, operation string, req, resp interface{}) error {
+	return s.internal.Execute(ctx, s.filerClient, operation, req, resp, "")
+}
+
 func catalogErrCode(err error) string {
-	var e *s3tables.S3TablesError
-	if errors.As(err, &e) {
-		return e.Type
+	var apiErr *s3tables.S3TablesError
+	if errors.As(err, &apiErr) {
+		return apiErr.Type
 	}
 	return ""
 }
 
-func isNotFound(err error) bool {
-	switch catalogErrCode(err) {
-	case s3tables.ErrCodeNoSuchBucket, s3tables.ErrCodeNoSuchTable, s3tables.ErrCodeNoSuchNamespace:
-		return true
-	}
-	return err != nil && (strings.Contains(err.Error(), "NoSuchTableBucket") ||
-		strings.Contains(err.Error(), "NoSuchTable") ||
-		strings.Contains(err.Error(), "NotFoundException") ||
-		strings.Contains(err.Error(), "NoSuchBucket"))
-}
-
-func isAlreadyExists(err error) bool {
-	code := catalogErrCode(err)
-	return strings.HasSuffix(code, "AlreadyExists") || code == s3tables.ErrCodeConflict ||
-		(err != nil && (strings.Contains(err.Error(), "AlreadyExists") || strings.Contains(err.Error(), "Conflict")))
-}
-
 func catalogErr(w http.ResponseWriter, err error) {
-	msg := err.Error()
-	switch {
-	case isNotFound(err):
-		writeError(w, http.StatusNotFound, "NotFoundException", msg)
-	case catalogErrCode(err) == s3tables.ErrCodeAccessDenied ||
-		strings.Contains(msg, "AccessDenied") || strings.Contains(msg, "PermissionDenied"):
-		writeError(w, http.StatusForbidden, "AccessDeniedException", "access denied")
-	case isAlreadyExists(err):
-		writeError(w, http.StatusConflict, "ConflictException", msg)
-	default:
-		writeError(w, http.StatusBadRequest, "ValidationException", msg)
+	var apiErr *s3tables.S3TablesError
+	if !errors.As(err, &apiErr) {
+		writeError(w, http.StatusInternalServerError, "InternalFailure", "internal error")
+		return
 	}
+	switch {
+	case apiErr.Type == s3tables.ErrCodeAccessDenied:
+		writeError(w, http.StatusForbidden, "AccessDeniedException", "access denied")
+	case strings.HasPrefix(apiErr.Type, "NoSuch"):
+		writeError(w, http.StatusNotFound, "NotFoundException", apiErr.Message)
+	case strings.Contains(apiErr.Type, "AlreadyExists") || strings.Contains(apiErr.Type, "NotEmpty") ||
+		apiErr.Type == s3tables.ErrCodeConflict:
+		writeError(w, http.StatusConflict, "ConflictException", apiErr.Message)
+	case apiErr.Type == s3tables.ErrCodeInternalError:
+		writeError(w, http.StatusInternalServerError, "InternalFailure", apiErr.Message)
+	default:
+		writeError(w, http.StatusBadRequest, "ValidationException", apiErr.Message)
+	}
+}
+
+// vectorErr maps a VectorService gRPC status onto the API's error shape.
+// Engine messages reach clients only for codes that describe the request
+// itself; transport and internal details stay in the server log.
+func vectorErr(w http.ResponseWriter, err error) {
+	msg := status.Convert(err).Message()
+	switch status.Code(err) {
+	case codes.NotFound:
+		writeError(w, http.StatusNotFound, "NotFoundException", msg)
+	case codes.InvalidArgument, codes.FailedPrecondition, codes.OutOfRange:
+		writeError(w, http.StatusBadRequest, "ValidationException", msg)
+	case codes.PermissionDenied, codes.Unauthenticated:
+		writeError(w, http.StatusForbidden, "AccessDeniedException", "access denied")
+	case codes.Unavailable:
+		writeError(w, http.StatusServiceUnavailable, "ServiceUnavailableException", "vector service unavailable")
+	default:
+		glog.V(1).Infof("S3 Vectors: engine error: %v", err)
+		writeError(w, http.StatusInternalServerError, "InternalFailure", "internal error")
+	}
+}
+
+// lanceBucket reports whether bucket is a table bucket that can hold vector
+// indexes: a declared Lance bucket, or one made before formats existed. An
+// explicit ICEBERG bucket is not a vector bucket and reads as absent. The
+// lookup is internal so the call needs no read grant — the requested
+// operation's own permission still gates it.
+func (s *Server) lanceBucket(ctx context.Context, bucket string) error {
+	var resp struct {
+		Format string `json:"format"`
+	}
+	err := s.internalCatalog(ctx, "GetTableBucket",
+		&s3tables.GetTableBucketRequest{TableBucketARN: s.s3tablesArn(bucket)}, &resp)
+	if err != nil {
+		return err
+	}
+	if resp.Format != "" && resp.Format != s3tables.FormatLance {
+		return &s3tables.S3TablesError{
+			Type:    s3tables.ErrCodeNoSuchBucket,
+			Message: fmt.Sprintf("vector bucket %s not found", bucket),
+		}
+	}
+	return nil
+}
+
+// ensureIndexNamespace declares the implicit index namespace when absent. The
+// calls are internal: a caller's CreateTable grant is what authorizes the
+// index, so it must not also need namespace reads or writes.
+func (s *Server) ensureIndexNamespace(ctx context.Context, bucket string) error {
+	var resp map[string]interface{}
+	err := s.internalCatalog(ctx, "GetNamespace", &s3tables.GetNamespaceRequest{
+		TableBucketARN: s.s3tablesArn(bucket),
+		Namespace:      []string{indexNamespace},
+	}, &resp)
+	if err == nil {
+		return nil
+	}
+	if code := catalogErrCode(err); code != s3tables.ErrCodeNoSuchNamespace && code != s3tables.ErrCodeNoSuchBucket {
+		return err
+	}
+	err = s.internalCatalog(ctx, "CreateNamespace", &s3tables.CreateNamespaceRequest{
+		TableBucketARN: s.s3tablesArn(bucket),
+		Namespace:      []string{indexNamespace},
+	}, &resp)
+	// A concurrent CreateIndex may have won the create.
+	if err != nil && catalogErrCode(err) != s3tables.ErrCodeNamespaceAlreadyExists {
+		return err
+	}
+	return nil
+}
+
+// authorizeIndexWrite requires the update grant on the index's catalog table
+// — the same check credential vending uses — so a read-only GetTable grant
+// never reaches a mutation.
+func (s *Server) authorizeIndexWrite(ctx context.Context, r *http.Request, bucket, index string) error {
+	return s.tables.AuthorizeUpdateTable(ctx, s.filerClient, &s3tables.UpdateTableRequest{
+		TableBucketARN: s.s3tablesArn(bucket),
+		Namespace:      []string{indexNamespace},
+		Name:           index,
+	}, identityOf(r))
 }
 
 func (s *Server) handleCreateVectorBucket(w http.ResponseWriter, r *http.Request) {
@@ -172,6 +253,13 @@ func (s *Server) handleCreateVectorBucket(w http.ResponseWriter, r *http.Request
 		writeError(w, http.StatusBadRequest, "ValidationException", "vectorBucketName is required")
 		return
 	}
+	// The catalog has no encryption boundary to honor the configuration
+	// against; accepting it would silently promise semantics we do not keep.
+	if len(req.EncryptionConfiguration) > 0 {
+		writeError(w, http.StatusBadRequest, "ValidationException",
+			"encryptionConfiguration is not supported")
+		return
+	}
 	var resp map[string]interface{}
 	err := s.catalog(r.Context(), "CreateTableBucket",
 		&s3tables.CreateTableBucketRequest{Name: req.VectorBucketName, Format: s3tables.FormatLance}, &resp, r)
@@ -179,7 +267,7 @@ func (s *Server) handleCreateVectorBucket(w http.ResponseWriter, r *http.Request
 		catalogErr(w, err)
 		return
 	}
-	writeJSON(w, http.StatusOK, &CreateVectorBucketResponse{})
+	writeJSON(w, http.StatusOK, &CreateVectorBucketResponse{VectorBucketArn: s.vectorBucketArn(req.VectorBucketName)})
 }
 
 func (s *Server) handleGetVectorBucket(w http.ResponseWriter, r *http.Request) {
@@ -200,6 +288,12 @@ func (s *Server) handleGetVectorBucket(w http.ResponseWriter, r *http.Request) {
 		catalogErr(w, err)
 		return
 	}
+	// An explicit ICEBERG bucket is not a vector bucket.
+	if format, _ := resp["format"].(string); format != "" && format != s3tables.FormatLance {
+		writeError(w, http.StatusNotFound, "NotFoundException",
+			fmt.Sprintf("vector bucket %s not found", arns.bucket))
+		return
+	}
 	created, _ := time.Parse(time.RFC3339, fmt.Sprint(resp["createdAt"]))
 	writeJSON(w, http.StatusOK, &GetVectorBucketResponse{VectorBucket: &VectorBucket{
 		VectorBucketArn:  s.vectorBucketArn(arns.bucket),
@@ -231,10 +325,10 @@ func (s *Server) handleListVectorBuckets(w http.ResponseWriter, r *http.Request)
 		catalogErr(w, err)
 		return
 	}
+	// The catalog token continues the filtered page: ICEBERG buckets drop out
+	// of the listing, Lance and format-less legacy buckets stay.
 	out := &ListVectorBucketsResponse{NextToken: resp.ContinuationToken}
 	for _, b := range resp.TableBuckets {
-		// Buckets pre-dating declared formats accept any format; only a bucket
-		// that declared another format is excluded here.
 		if b.Format != "" && b.Format != s3tables.FormatLance {
 			continue
 		}
@@ -259,15 +353,32 @@ func (s *Server) handleDeleteVectorBucket(w http.ResponseWriter, r *http.Request
 		writeError(w, http.StatusBadRequest, "ValidationException", err.Error())
 		return
 	}
+	// The format check needs no read grant — the delete below is the
+	// authorization boundary — but an ICEBERG bucket is not a vector bucket.
+	if err := s.lanceBucket(r.Context(), arns.bucket); err != nil {
+		catalogErr(w, err)
+		return
+	}
 	var resp map[string]interface{}
-	// Indexes live in an implicit namespace; dropping it best-effort lets an
-	// emptied bucket delete, while surviving indexes keep it non-empty.
-	_ = s.catalog(r.Context(), "DeleteNamespace", &s3tables.DeleteNamespaceRequest{
-		TableBucketARN: s.s3tablesArn(arns.bucket),
-		Namespace:      []string{indexNamespace},
-	}, &resp, r)
 	err := s.catalog(r.Context(), "DeleteTableBucket",
 		&s3tables.DeleteTableBucketRequest{TableBucketARN: s.s3tablesArn(arns.bucket)}, &resp, r)
+	if err != nil && catalogErrCode(err) == s3tables.ErrCodeBucketNotEmpty {
+		// The implicit index namespace counts as bucket content even when it
+		// holds no indexes; drop it under the delete's own authorization and
+		// retry once. A namespace still holding indexes keeps the conflict.
+		var nsResp map[string]interface{}
+		nsErr := s.internalCatalog(context.WithoutCancel(r.Context()), "DeleteNamespace",
+			&s3tables.DeleteNamespaceRequest{
+				TableBucketARN: s.s3tablesArn(arns.bucket),
+				Namespace:      []string{indexNamespace},
+			}, &nsResp)
+		if nsErr == nil {
+			err = s.catalog(r.Context(), "DeleteTableBucket",
+				&s3tables.DeleteTableBucketRequest{TableBucketARN: s.s3tablesArn(arns.bucket)}, &resp, r)
+		} else if code := catalogErrCode(nsErr); code != s3tables.ErrCodeNoSuchNamespace {
+			glog.V(1).Infof("S3 Vectors: drop internal namespace in %s: %v", arns.bucket, nsErr)
+		}
+	}
 	if err != nil {
 		catalogErr(w, err)
 		return
@@ -315,42 +426,69 @@ func (s *Server) handleCreateIndex(w http.ResponseWriter, r *http.Request) {
 		writeError(w, http.StatusBadRequest, "ValidationException", "dimension must be 1..=4096")
 		return
 	}
+	if err := s.lanceBucket(r.Context(), arns.bucket); err != nil {
+		catalogErr(w, err)
+		return
+	}
+	// The create grant is exercised before any write: a denied caller must not
+	// leave even the implicit namespace behind. The namespace may not exist
+	// yet, so the check tolerates its absence.
+	if err := s.tables.AuthorizeCreateTable(r.Context(), s.filerClient, &s3tables.CreateTableRequest{
+		TableBucketARN:        s.s3tablesArn(arns.bucket),
+		Namespace:             []string{indexNamespace},
+		Name:                  arns.index,
+		AllowMissingNamespace: true,
+	}, identityOf(r)); err != nil {
+		catalogErr(w, err)
+		return
+	}
+	// The namespace is implicit on AWS and internal bookkeeping here.
+	if err := s.ensureIndexNamespace(r.Context(), arns.bucket); err != nil {
+		catalogErr(w, err)
+		return
+	}
+	// Only a caller who passed the create check may learn an index exists.
+	var existing map[string]interface{}
+	getErr := s.internalCatalog(r.Context(), "GetTable", &s3tables.GetTableRequest{
+		TableBucketARN: s.s3tablesArn(arns.bucket),
+		Namespace:      []string{indexNamespace},
+		Name:           arns.index,
+	}, &existing)
+	switch {
+	case getErr == nil:
+		writeError(w, http.StatusConflict, "ConflictException",
+			fmt.Sprintf("index %s already exists", arns.index))
+		return
+	case catalogErrCode(getErr) != s3tables.ErrCodeNoSuchTable:
+		catalogErr(w, getErr)
+		return
+	}
 	metadata := map[string]string{
 		"dimension":      fmt.Sprint(req.Dimension),
 		"distanceMetric": req.DistanceMetric,
+		// The nonce marks the record this request created, so a rollback after
+		// an engine failure can never erase a pre-existing index.
+		"createNonce": uuid.NewString(),
 	}
+	var nonFilterable []string
 	if req.MetadataConfiguration != nil {
-		if keys, err := json.Marshal(req.MetadataConfiguration.NonFilterableMetadataKeys); err == nil {
+		nonFilterable = req.MetadataConfiguration.NonFilterableMetadataKeys
+		if keys, err := json.Marshal(nonFilterable); err == nil {
 			metadata["nonFilterableMetadataKeys"] = string(keys)
 		}
 	}
 	metadataJSON, _ := json.Marshal(metadata)
-	var nsResp map[string]interface{}
-	// The index namespace is implicit on AWS; declare it, tolerating an
-	// already-existing namespace.
-	if err := s.catalog(r.Context(), "CreateNamespace", &s3tables.CreateNamespaceRequest{
-		TableBucketARN: s.s3tablesArn(arns.bucket),
-		Namespace:      []string{indexNamespace},
-	}, &nsResp, r); err != nil && !isAlreadyExists(err) {
-		catalogErr(w, err)
-		return
-	}
-	var resp map[string]interface{}
 	err = s.catalog(r.Context(), "CreateTable", &s3tables.CreateTableRequest{
 		TableBucketARN: s.s3tablesArn(arns.bucket),
 		Namespace:      []string{indexNamespace},
 		Name:           arns.index,
 		Format:         s3tables.FormatLance,
 		Metadata:       &s3tables.TableMetadata{FullMetadata: metadataJSON},
-	}, &resp, r)
+	}, nil, r)
 	if err != nil {
 		catalogErr(w, err)
 		return
 	}
-	var nonFilterable []string
-	if req.MetadataConfiguration != nil {
-		nonFilterable = req.MetadataConfiguration.NonFilterableMetadataKeys
-	}
 	_, err = s.vectors.CreateIndex(r.Context(), &vector_pb.CreateIndexRequest{
 		Table:                     tableID(arns.bucket, arns.index),
 		Dimension:                 uint32(req.Dimension),
@@ -359,16 +497,48 @@ func (s *Server) handleCreateIndex(w http.ResponseWriter, r *http.Request) {
 	})
 	if err != nil {
 		// Roll the index record back so a half-created index does not linger.
-		var delResp map[string]interface{}
-		_ = s.catalog(r.Context(), "DeleteTable", &s3tables.DeleteTableRequest{
+		// The delete runs past a client disconnect and only removes the record
+		// this request created: the nonce must match, and the versionToken
+		// compare-and-swap keeps a racing create from being erased.
+		ctx := context.WithoutCancel(r.Context())
+		var rec map[string]interface{}
+		if gerr := s.internalCatalog(ctx, "GetTable", &s3tables.GetTableRequest{
 			TableBucketARN: s.s3tablesArn(arns.bucket),
 			Namespace:      []string{indexNamespace},
 			Name:           arns.index,
-		}, &delResp, r)
-		writeError(w, http.StatusInternalServerError, "InternalFailure", err.Error())
+		}, &rec); gerr == nil && recordNonce(rec) == metadata["createNonce"] {
+			var delResp map[string]interface{}
+			if derr := s.internalCatalog(ctx, "DeleteTable", &s3tables.DeleteTableRequest{
+				TableBucketARN: s.s3tablesArn(arns.bucket),
+				Namespace:      []string{indexNamespace},
+				Name:           arns.index,
+				VersionToken:   recordVersionToken(rec),
+			}, &delResp); derr != nil {
+				glog.Errorf("S3 Vectors: rollback of catalog table %s/%s failed: %v", arns.bucket, arns.index, derr)
+			}
+		} else if gerr != nil {
+			glog.Errorf("S3 Vectors: rollback lookup for %s/%s failed: %v", arns.bucket, arns.index, gerr)
+		}
+		vectorErr(w, err)
 		return
 	}
-	writeJSON(w, http.StatusOK, &CreateIndexResponse{})
+	writeJSON(w, http.StatusOK, &CreateIndexResponse{IndexArn: s.indexArn(arns.bucket, arns.index)})
+}
+
+// recordNonce and recordVersionToken read the catalog record's internal
+// bookkeeping for the create-index rollback.
+func recordNonce(record map[string]interface{}) string {
+	if meta, ok := record["metadata"].(map[string]interface{}); ok {
+		if fm, ok := meta["fullMetadata"].(map[string]interface{}); ok {
+			return fmt.Sprint(fm["createNonce"])
+		}
+	}
+	return ""
+}
+
+func recordVersionToken(record map[string]interface{}) string {
+	token, _ := record["versionToken"].(string)
+	return token
 }
 
 func indexFromRecord(s *Server, bucket, name string, m map[string]interface{}) *Index {
@@ -423,7 +593,7 @@ func (s *Server) handleGetIndex(w http.ResponseWriter, r *http.Request) {
 		catalogErr(w, err)
 		return
 	}
-	writeJSON(w, http.StatusOK, &GetIndexResponse{Index: indexFromRecord(s, arns.bucket, req.IndexName, resp)})
+	writeJSON(w, http.StatusOK, &GetIndexResponse{Index: indexFromRecord(s, arns.bucket, arns.index, resp)})
 }
 
 func (s *Server) handleListIndexes(w http.ResponseWriter, r *http.Request) {
@@ -440,6 +610,7 @@ func (s *Server) handleListIndexes(w http.ResponseWriter, r *http.Request) {
 	var resp struct {
 		TableSummaries []struct {
 			Name      string `json:"name"`
+			Format    string `json:"format"`
 			CreatedAt string `json:"createdAt"`
 		} `json:"tables"`
 		ContinuationToken string `json:"continuationToken"`
@@ -455,9 +626,21 @@ func (s *Server) handleListIndexes(w http.ResponseWriter, r *http.Request) {
 		catalogErr(w, err)
 		return
 	}
+	// Summaries carry only what the catalog listing knows; a summary that
+	// asserted a dimension or metric without a record lookup would lie.
 	out := &ListIndexesResponse{NextToken: resp.ContinuationToken}
 	for _, t := range resp.TableSummaries {
-		out.Indexes = append(out.Indexes, indexFromRecord(s, arns.bucket, t.Name, nil))
+		// A non-Lance table in the index namespace is not an index.
+		if t.Format != "" && t.Format != s3tables.FormatLance {
+			continue
+		}
+		created, _ := time.Parse(time.RFC3339, t.CreatedAt)
+		out.Indexes = append(out.Indexes, &IndexSummary{
+			IndexName:        t.Name,
+			IndexArn:         s.indexArn(arns.bucket, t.Name),
+			VectorBucketName: arns.bucket,
+			CreationTime:     created,
+		})
 	}
 	writeJSON(w, http.StatusOK, out)
 }
@@ -473,9 +656,9 @@ func (s *Server) handleDeleteIndex(w http.ResponseWriter, r *http.Request) {
 		writeError(w, http.StatusBadRequest, "ValidationException", err.Error())
 		return
 	}
-	_, _ = s.vectors.DropIndex(r.Context(), &vector_pb.DropIndexRequest{
-		Table: tableID(arns.bucket, arns.index),
-	})
+	// Deleting the catalog record is the delete: the engine derives an index's
+	// existence from its table, and DropIndex is unimplemented on the shared
+	// service.
 	var resp map[string]interface{}
 	err = s.catalog(r.Context(), "DeleteTable", &s3tables.DeleteTableRequest{
 		TableBucketARN: s.s3tablesArn(arns.bucket),
@@ -518,12 +701,22 @@ func (s *Server) handlePutVectors(w http.ResponseWriter, r *http.Request) {
 		catalogErr(w, err)
 		return
 	}
+	// A read grant on the index does not carry a write: mutations require the
+	// catalog's update grant, the same check credential vending applies.
+	if err := s.authorizeIndexWrite(r.Context(), r, arns.bucket, arns.index); err != nil {
+		catalogErr(w, err)
+		return
+	}
 	vectors := make([]*vector_pb.Vector, 0, len(req.Vectors))
 	for _, v := range req.Vectors {
 		if v == nil {
 			writeError(w, http.StatusBadRequest, "ValidationException", "vectors contains a null element")
 			return
 		}
+		if v.Key == "" {
+			writeError(w, http.StatusBadRequest, "ValidationException", "vector key must not be empty")
+			return
+		}
 		metadata, err := metadataStruct(v.Metadata)
 		if err != nil {
 			writeError(w, http.StatusBadRequest, "ValidationException", err.Error())
@@ -540,7 +733,7 @@ func (s *Server) handlePutVectors(w http.ResponseWriter, r *http.Request) {
 		Vectors: vectors,
 	})
 	if err != nil {
-		writeError(w, http.StatusInternalServerError, "InternalFailure", err.Error())
+		vectorErr(w, err)
 		return
 	}
 	writeJSON(w, http.StatusOK, &PutVectorsResponse{})
@@ -583,7 +776,7 @@ func (s *Server) handleGetVectors(w http.ResponseWriter, r *http.Request) {
 		ReturnMetadata: req.ReturnMetadata,
 	})
 	if err != nil {
-		writeError(w, http.StatusInternalServerError, "InternalFailure", err.Error())
+		vectorErr(w, err)
 		return
 	}
 	writeJSON(w, http.StatusOK, &GetVectorsResponse{
@@ -631,7 +824,7 @@ func (s *Server) handleListVectors(w http.ResponseWriter, r *http.Request) {
 		out, nextToken, err := s.listSegmentVectors(r.Context(), tableID(arns.bucket, arns.index),
 			offset, req.MaxResults, uint64(req.SegmentCount), uint64(req.SegmentIndex), req.ReturnData, req.ReturnMetadata)
 		if err != nil {
-			writeError(w, http.StatusInternalServerError, "InternalFailure", err.Error())
+			vectorErr(w, err)
 			return
 		}
 		writeJSON(w, http.StatusOK, &ListVectorsResponse{
@@ -648,7 +841,7 @@ func (s *Server) handleListVectors(w http.ResponseWriter, r *http.Request) {
 		ReturnMetadata: req.ReturnMetadata,
 	})
 	if err != nil {
-		writeError(w, http.StatusInternalServerError, "InternalFailure", err.Error())
+		vectorErr(w, err)
 		return
 	}
 	writeJSON(w, http.StatusOK, &ListVectorsResponse{
@@ -727,12 +920,16 @@ func (s *Server) handleDeleteVectors(w http.ResponseWriter, r *http.Request) {
 		catalogErr(w, err)
 		return
 	}
+	if err := s.authorizeIndexWrite(r.Context(), r, arns.bucket, arns.index); err != nil {
+		catalogErr(w, err)
+		return
+	}
 	_, err = s.vectors.DeleteVectors(r.Context(), &vector_pb.DeleteVectorsRequest{
 		Table: tableID(arns.bucket, arns.index),
 		Keys:  req.Keys,
 	})
 	if err != nil {
-		writeError(w, http.StatusInternalServerError, "InternalFailure", err.Error())
+		vectorErr(w, err)
 		return
 	}
 	writeJSON(w, http.StatusOK, &DeleteVectorsResponse{})
@@ -787,55 +984,123 @@ func filterExpr(filter map[string]interface{}) (string, error) {
 	return strings.Join(parts, " AND "), nil
 }
 
+// fieldAccess renders the operand's comparison column over the serialized
+// json_extract text. Strings and booleans compare the serialized form
+// directly, which is exact-typed and never errors — booleans serialize as
+// exactly 'true'/'false', and a cast would also accept the '1'/'0' a stored
+// number produces. Numbers go through TRY_CAST, which is NULL on any other
+// stored type. The json_get_* extractors are not used — they convert
+// numeric-looking strings and booleans, and error on mismatched types.
+func fieldAccess(field string, operand interface{}) (string, error) {
+	path := sqlEscape(existsPath(field))
+	switch operand.(type) {
+	case float64:
+		return fmt.Sprintf("TRY_CAST(json_extract(`metadata`, '%s') AS DOUBLE)", path), nil
+	case bool, string:
+		return fmt.Sprintf("json_extract(`metadata`, '%s')", path), nil
+	default:
+		return "", fmt.Errorf("unsupported filter operand %v", operand)
+	}
+}
+
+// fieldMatch renders "field <rhs>".
+func fieldMatch(field string, operand interface{}, rhs string) (string, error) {
+	col, err := fieldAccess(field, operand)
+	if err != nil {
+		return "", err
+	}
+	return col + " " + rhs, nil
+}
+
+// existsPath renders the field as a JSONPath for the json_exists and
+// json_extract parsers: bracket notation keeps dots, spaces, and other
+// specials inside the key literal.
+func existsPath(field string) string {
+	field = strings.ReplaceAll(field, `\`, `\\`)
+	field = strings.ReplaceAll(field, `"`, `\"`)
+	return `$["` + field + `"]`
+}
+
+func sqlEscape(s string) string {
+	return strings.ReplaceAll(s, "'", "''")
+}
+
 func fieldClause(field string, cond interface{}) (string, error) {
-	col := fmt.Sprintf("json_get_string(`metadata`, '%s')", strings.ReplaceAll(field, "'", "''"))
 	switch c := cond.(type) {
 	case map[string]interface{}:
 		parts := []string{}
 		for op, operand := range c {
 			switch op {
 			case "$exists":
-				if operand == true {
-					parts = append(parts, fmt.Sprintf("json_exists(`metadata`, '%s')", strings.ReplaceAll(field, "'", "''")))
+				if b, ok := operand.(bool); ok {
+					expr := fmt.Sprintf("json_exists(`metadata`, '%s')", sqlEscape(existsPath(field)))
+					if !b {
+						expr = "NOT " + expr
+					}
+					parts = append(parts, expr)
 				} else {
-					parts = append(parts, fmt.Sprintf("NOT json_exists(`metadata`, '%s')", strings.ReplaceAll(field, "'", "''")))
+					return "", fmt.Errorf("$exists expects a boolean")
 				}
 			case "$eq", "$ne":
 				lit, err := sqlLiteral(operand)
 				if err != nil {
 					return "", err
 				}
-				sym := "="
-				if op == "$ne" {
-					sym = "<>"
+				match, err := fieldMatch(field, operand, "= "+lit)
+				if err != nil {
+					return "", err
 				}
-				parts = append(parts, fmt.Sprintf("%s %s %s", col, sym, lit))
+				if op == "$ne" {
+					match = "NOT COALESCE(" + match + ", false)"
+				}
+				parts = append(parts, match)
 			case "$in", "$nin":
 				list, ok := operand.([]interface{})
 				if !ok {
 					return "", fmt.Errorf("%s expects a list", op)
 				}
-				vals := make([]string, 0, len(list))
+				if len(list) == 0 {
+					if op == "$in" {
+						parts = append(parts, "false")
+					} else {
+						parts = append(parts, "true")
+					}
+					continue
+				}
+				// Members may mix types; each extractor only sees its own. A
+				// member whose typed extractor returns NULL must not let NOT
+				// invert NULL into NULL under $nin, so every group coalesces.
+				var groups []string
 				for _, item := range list {
 					lit, err := sqlLiteral(item)
 					if err != nil {
 						return "", err
 					}
-					vals = append(vals, lit)
+					g, err := fieldMatch(field, item, "in ("+lit+")")
+					if err != nil {
+						return "", err
+					}
+					groups = append(groups, fmt.Sprintf("COALESCE(%s, false)", g))
 				}
-				sym := "IN"
+				expr := "(" + strings.Join(groups, " OR ") + ")"
 				if op == "$nin" {
-					sym = "NOT IN"
+					expr = "NOT " + expr
 				}
-				parts = append(parts, fmt.Sprintf("%s %s (%s)", col, sym, strings.Join(vals, ", ")))
+				parts = append(parts, expr)
 			case "$lt", "$lte", "$gt", "$gte":
+				if _, ok := operand.(float64); !ok {
+					return "", fmt.Errorf("%s expects a number", op)
+				}
 				lit, err := sqlLiteral(operand)
 				if err != nil {
 					return "", err
 				}
 				sym := map[string]string{"$lt": "<", "$lte": "<=", "$gt": ">", "$gte": ">="}[op]
-				numCol := fmt.Sprintf("json_get_float(`metadata`, '%s')", strings.ReplaceAll(field, "'", "''"))
-				parts = append(parts, fmt.Sprintf("%s %s %s", numCol, sym, lit))
+				col, err := fieldAccess(field, operand)
+				if err != nil {
+					return "", err
+				}
+				parts = append(parts, fmt.Sprintf("%s %s %s", col, sym, lit))
 			default:
 				return "", fmt.Errorf("unsupported operator %s", op)
 			}
@@ -846,19 +1111,50 @@ func fieldClause(field string, cond interface{}) (string, error) {
 		if err != nil {
 			return "", err
 		}
-		return fmt.Sprintf("%s = %s", col, lit), nil
+		return fieldMatch(field, cond, "= "+lit)
 	}
 }
 
+// jsonbString renders s as the JSON text json_extract returns for a stored
+// string: quoted, with the same escapes the jsonb serializer emits.
+func jsonbString(s string) string {
+	var b strings.Builder
+	b.WriteByte('"')
+	for _, r := range s {
+		switch r {
+		case '"':
+			b.WriteString(`\"`)
+		case '\\':
+			b.WriteString(`\\`)
+		case '\n':
+			b.WriteString(`\n`)
+		case '\r':
+			b.WriteString(`\r`)
+		case '\t':
+			b.WriteString(`\t`)
+		case 0:
+			b.WriteString(`\0`)
+		default:
+			if r < 0x20 || (r >= 0x7f && r <= 0x9f) {
+				fmt.Fprintf(&b, `\u{%x}`, r)
+			} else {
+				b.WriteRune(r)
+			}
+		}
+	}
+	b.WriteByte('"')
+	return b.String()
+}
+
 func sqlLiteral(v interface{}) (string, error) {
 	switch t := v.(type) {
 	case string:
-		return "'" + strings.ReplaceAll(t, "'", "''") + "'", nil
+		return "'" + sqlEscape(jsonbString(t)) + "'", nil
 	case bool:
 		if t {
-			return "true", nil
+			return "'true'", nil
 		}
-		return "false", nil
+		return "'false'", nil
 	case float64:
 		return fmt.Sprintf("%v", t), nil
 	}
@@ -895,8 +1191,8 @@ func (s *Server) handleQueryVectors(w http.ResponseWriter, r *http.Request) {
 		writeError(w, http.StatusBadRequest, "ValidationException", err.Error())
 		return
 	}
-	if req.TopK < 0 {
-		writeError(w, http.StatusBadRequest, "ValidationException", "topK must be non-negative")
+	if req.TopK <= 0 {
+		writeError(w, http.StatusBadRequest, "ValidationException", "topK must be positive")
 		return
 	}
 	resp, err := s.vectors.QueryVectors(r.Context(), &vector_pb.QueryVectorsRequest{
@@ -908,7 +1204,7 @@ func (s *Server) handleQueryVectors(w http.ResponseWriter, r *http.Request) {
 		ReturnDistance: req.ReturnDistance,
 	})
 	if err != nil {
-		writeError(w, http.StatusInternalServerError, "InternalFailure", err.Error())
+		vectorErr(w, err)
 		return
 	}
 	out := &QueryVectorsResponse{DistanceMetric: metric}
diff --git a/weed/s3api/s3vectors/handlers_test.go b/weed/s3api/s3vectors/handlers_test.go
index 32563acfb7..d20e48a02a 100644
--- a/weed/s3api/s3vectors/handlers_test.go
+++ b/weed/s3api/s3vectors/handlers_test.go
@@ -155,3 +155,108 @@ func TestListSegmentVectorsPageLimits(t *testing.T) {
 		t.Fatalf("capped page: %d rows token %q", len(out), next)
 	}
 }
+
+func TestArnParts(t *testing.T) {
+	var v vectorBucketARNs
+
+	if err := arnParts(&v, "plain", ""); err != nil || v.bucket != "plain" {
+		t.Fatalf("plain name: bucket=%q err=%v", v.bucket, err)
+	}
+	if err := arnParts(&v, "", "arn:aws:s3vectors:r:a:bucket/mybucket"); err != nil || v.bucket != "mybucket" || v.index != "" {
+		t.Fatalf("bucket ARN: %+v err=%v", v, err)
+	}
+	v = vectorBucketARNs{}
+	if err := arnParts(&v, "", "arn:aws:s3vectors:r:a:bucket/mybucket/index/myindex"); err != nil || v.bucket != "mybucket" || v.index != "myindex" {
+		t.Fatalf("index ARN: %+v err=%v", v, err)
+	}
+	for _, bad := range []string{
+		"arn:aws:s3vectors:r:a:bucket/",
+		"arn:aws:s3vectors:r:a:bucket//index/i",
+		"arn:aws:s3vectors:r:a:bucket",
+	} {
+		v = vectorBucketARNs{}
+		if err := arnParts(&v, "", bad); err == nil {
+			t.Fatalf("ARN %q should be rejected", bad)
+		}
+	}
+}
+
+func TestResolveIndexARNs(t *testing.T) {
+	arns, err := resolveIndexARNs("", "", "", "arn:aws:s3vectors:r:a:bucket/b/index/i")
+	if err != nil || arns.bucket != "b" || arns.index != "i" {
+		t.Fatalf("indexArn only: %+v err=%v", arns, err)
+	}
+	arns, err = resolveIndexARNs("b", "", "i", "")
+	if err != nil || arns.bucket != "b" || arns.index != "i" {
+		t.Fatalf("names only: %+v err=%v", arns, err)
+	}
+	if _, err := resolveIndexARNs("", "not-an-arn", "i", ""); err == nil {
+		t.Fatal("non-ARN vectorBucketArn should be rejected")
+	}
+	if _, err := resolveIndexARNs("", "", "", ""); err == nil {
+		t.Fatal("missing identifiers should be rejected")
+	}
+	if _, err := resolveIndexARNs("b", "", "", ""); err == nil {
+		t.Fatal("missing indexName should be rejected")
+	}
+}
+
+func TestTranslateFilter(t *testing.T) {
+	cases := []struct {
+		name   string
+		filter map[string]interface{}
+		want   string
+	}{
+		{"bare string equality", map[string]interface{}{"k": "v"},
+			"json_extract(`metadata`, '$[\"k\"]') = '\"v\"'"},
+		{"bare number equality", map[string]interface{}{"k": float64(3)},
+			"TRY_CAST(json_extract(`metadata`, '$[\"k\"]') AS DOUBLE) = 3"},
+		{"bare bool equality", map[string]interface{}{"k": true},
+			"json_extract(`metadata`, '$[\"k\"]') = 'true'"},
+		{"ne", map[string]interface{}{"k": map[string]interface{}{"$ne": "v"}},
+			"NOT COALESCE(json_extract(`metadata`, '$[\"k\"]') = '\"v\"', false)"},
+		{"exists true", map[string]interface{}{"k": map[string]interface{}{"$exists": true}},
+			"json_exists(`metadata`, '$[\"k\"]')"},
+		{"exists false", map[string]interface{}{"k": map[string]interface{}{"$exists": false}},
+			"NOT json_exists(`metadata`, '$[\"k\"]')"},
+		{"exists special key", map[string]interface{}{`a.b"c`: map[string]interface{}{"$exists": true}},
+			"json_exists(`metadata`, '$[\"a.b\\\"c\"]')"},
+		{"range", map[string]interface{}{"k": map[string]interface{}{"$gt": float64(1)}},
+			"TRY_CAST(json_extract(`metadata`, '$[\"k\"]') AS DOUBLE) > 1"},
+		{"in strings", map[string]interface{}{"k": map[string]interface{}{"$in": []interface{}{"a", "b"}}},
+			"(COALESCE(json_extract(`metadata`, '$[\"k\"]') in ('\"a\"'), false) OR COALESCE(json_extract(`metadata`, '$[\"k\"]') in ('\"b\"'), false))"},
+		{"nin numbers", map[string]interface{}{"k": map[string]interface{}{"$nin": []interface{}{float64(1)}}},
+			"NOT (COALESCE(TRY_CAST(json_extract(`metadata`, '$[\"k\"]') AS DOUBLE) in (1), false))"},
+		{"and", map[string]interface{}{"$and": []interface{}{
+			map[string]interface{}{"a": "1"}, map[string]interface{}{"b": float64(2)},
+		}},
+			"(json_extract(`metadata`, '$[\"a\"]') = '\"1\"' AND TRY_CAST(json_extract(`metadata`, '$[\"b\"]') AS DOUBLE) = 2)"},
+		{"sql injection", map[string]interface{}{"a'b": "v'1"},
+			"json_extract(`metadata`, '$[\"a''b\"]') = '\"v''1\"'"},
+	}
+	for _, tc := range cases {
+		got, err := translateFilter(tc.filter)
+		if err != nil {
+			t.Fatalf("%s: %v", tc.name, err)
+		}
+		if got != tc.want {
+			t.Fatalf("%s:\n got %s\nwant %s", tc.name, got, tc.want)
+		}
+	}
+
+	for name, filter := range map[string]map[string]interface{}{
+		"unknown operator":  {"k": map[string]interface{}{"$bogus": "v"}},
+		"exists non-bool":   {"k": map[string]interface{}{"$exists": "yes"}},
+		"range non-number":  {"k": map[string]interface{}{"$gt": "v"}},
+		"in non-list":       {"k": map[string]interface{}{"$in": "v"}},
+		"top-level bad op":  {"$bogus": []interface{}{}},
+		"nested bad member": {"$and": []interface{}{"x"}},
+	} {
+		if _, err := translateFilter(filter); err == nil {
+			t.Fatalf("%s should fail", name)
+		}
+	}
+	if got, err := translateFilter(nil); err != nil || got != "" {
+		t.Fatalf("empty filter: %q %v", got, err)
+	}
+}
diff --git a/weed/s3api/s3vectors/server.go b/weed/s3api/s3vectors/server.go
index a30f733f07..bcea9907ef 100644
--- a/weed/s3api/s3vectors/server.go
+++ b/weed/s3api/s3vectors/server.go
@@ -24,10 +24,11 @@ type S3Authenticator interface {
 	DefaultAllow() bool
 }
 
-// Server implements the AWS S3 Vectors JSON API.
+// Server implements the AWS S3 Vectors API.
 type Server struct {
 	filerClient   FilerClient
 	tables        *s3tables.Manager
+	internal      *s3tables.Manager
 	vectors       vector_pb.VectorServiceClient
 	authenticator S3Authenticator
 	region        string
@@ -40,9 +41,15 @@ func NewServer(filerClient FilerClient, authenticator S3Authenticator, vectors v
 	if authenticator != nil {
 		manager.SetDefaultAllow(authenticator.DefaultAllow())
 	}
+	// Bookkeeping calls that ride along an operation the catalog already
+	// authorizes — format lookups, the implicit index namespace — must not
+	// demand read grants the API does not require.
+	internal := s3tables.NewManager()
+	internal.SetTrusted(true)
 	return &Server{
 		filerClient:   filerClient,
 		tables:        manager,
+		internal:      internal,
 		vectors:       vectors,
 		authenticator: authenticator,
 	}
diff --git a/weed/s3api/s3vectors/types.go b/weed/s3api/s3vectors/types.go
index 78592e28f2..f007262fbf 100644
--- a/weed/s3api/s3vectors/types.go
+++ b/weed/s3api/s3vectors/types.go
@@ -57,7 +57,9 @@ type CreateVectorBucketRequest struct {
 	MetadataResourceTags    map[string]string      `json:"-"`
 }
 
-type CreateVectorBucketResponse struct{}
+type CreateVectorBucketResponse struct {
+	VectorBucketArn string `json:"vectorBucketArn"`
+}
 
 type GetVectorBucketRequest struct {
 	VectorBucketName string `json:"vectorBucketName"`
@@ -107,7 +109,9 @@ type MetadataConfiguration struct {
 	NonFilterableMetadataKeys []string `json:"nonFilterableMetadataKeys"`
 }
 
-type CreateIndexResponse struct{}
+type CreateIndexResponse struct {
+	IndexArn string `json:"indexArn"`
+}
 
 type GetIndexRequest struct {
 	IndexArn         string `json:"indexArn"`
@@ -139,9 +143,18 @@ type ListIndexesRequest struct {
 	VectorBucketArn  string `json:"vectorBucketArn"`
 }
 
+// IndexSummary is the listing shape: the catalog knows the name, ARN, and
+// creation time without a per-index metadata read.
+type IndexSummary struct {
+	CreationTime     time.Time `json:"creationTime"`
+	IndexArn         string    `json:"indexArn"`
+	IndexName        string    `json:"indexName"`
+	VectorBucketName string    `json:"vectorBucketName"`
+}
+
 type ListIndexesResponse struct {
-	Indexes   []*Index `json:"indexes"`
-	NextToken string   `json:"nextToken,omitempty"`
+	Indexes   []*IndexSummary `json:"indexes"`
+	NextToken string          `json:"nextToken,omitempty"`
 }
 
 type DeleteIndexRequest struct {
diff --git a/weed/server/filer_grpc_server.go b/weed/server/filer_grpc_server.go
index 1c8b8da560..c6295f7810 100644
--- a/weed/server/filer_grpc_server.go
+++ b/weed/server/filer_grpc_server.go
@@ -1064,14 +1064,60 @@ func (fs *FilerServer) DeleteEntry(ctx context.Context, req *filer_pb.DeleteEntr
 
 	glog.V(4).InfofCtx(ctx, "DeleteEntry %v", req)
 
+	fullpath := util.JoinPath(req.Directory, req.Name)
+
+	// A delete carrying extended-attribute preconditions is a read-then-delete
+	// that the per-path lock below only makes atomic on this filer. Route it
+	// to the entry's ring owner so one filer's lock arbitrates every writer
+	// cluster-wide; is_moved bounds this to one hop.
+	if len(req.ExpectedExtended) > 0 {
+		if !req.IsMoved {
+			var ownerResp *filer_pb.DeleteEntryResponse
+			handled, forwardErr := fs.forwardToWriteOwner(ctx, entryRouteKey(fullpath), func(owner pb.ServerAddress) error {
+				glog.V(2).InfofCtx(ctx, "DeleteEntry %s: forwarding to owner %s", fullpath, owner)
+				req.IsMoved = true
+				return pb.WithFilerClient(false, 0, owner, fs.grpcDialOption, func(client filer_pb.SeaweedFilerClient) error {
+					forwarded, e := client.DeleteEntry(ctx, req)
+					if e != nil {
+						return e
+					}
+					ownerResp = forwarded
+					return nil
+				})
+			})
+			if handled {
+				if forwardErr != nil {
+					return &filer_pb.DeleteEntryResponse{}, forwardErr
+				}
+				return ownerResp, nil
+			}
+		} else {
+			if err := fs.checkMovedMarker(ctx, req.IsMoved, fs.writeOwner(entryRouteKey(fullpath))); err != nil {
+				return &filer_pb.DeleteEntryResponse{}, err
+			}
+		}
+	}
+
 	// A delete queues the entry's chunks for deletion, so it must not
 	// interleave with a conditional update's check-then-write on the same
 	// path: the update would pass its precondition and then resurrect fids
 	// that are already on the deletion queue.
-	fullpath := util.JoinPath(req.Directory, req.Name)
 	pathLock := fs.entryLockTable.AcquireLock("DeleteEntry", fullpath, util.ExclusiveLock)
 	defer fs.entryLockTable.ReleaseLock(fullpath, pathLock)
 
+	// Extended-attribute preconditions run here, under the lock the delete
+	// runs under: an attribute write that keeps Mtime can no longer slip
+	// between the check and the delete.
+	if len(req.ExpectedExtended) > 0 {
+		entry, err := fs.filer.FindEntry(ctx, fullpath)
+		if err != nil {
+			return &filer_pb.DeleteEntryResponse{}, status.Errorf(codes.FailedPrecondition, "extended attribute precondition %s: %v", fullpath, err)
+		}
+		if err := validateUpdateEntryPreconditions(entry, req.ExpectedExtended); err != nil {
+			return &filer_pb.DeleteEntryResponse{}, err
+		}
+	}
+
 	if req.KeepRemoteObject {
 		ctx = filer.WithKeepRemoteObject(ctx)
 	}