ci: resolve MSRV lockfile against rust-version instead of hand-pinned versions

The MSRV job pinned `aws-smithy-checksums` to 0.63.9, which requires `crc-fast = "~1.3.0"`. Lance v11 pulls in opendal 0.58.1, whose `opendal-service-s3` requires `crc-fast = "^1.9.0"`, so the downgrade step failed to resolve. Replace the hand-maintained pin list with cargo's MSRV-aware resolution, which picks the newest versions whose declared `rust-version` fits the workspace MSRV. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
chore: update lance dependency to v11.0.0-beta.1
2026-09-04 20:48:50 +00:00 · 2026-08-05 15:58:04 -07:00 · 2026-08-05 22:18:14 +00:00 · 2026-08-04 12:23:03 -07:00 · 2026-08-04 11:18:22 -07:00 · 2026-08-03 15:49:52 -07:00
26 changed files with 2261 additions and 522 deletions
@@ -276,38 +276,14 @@ jobs:
          # unreadable outside their own branch anyway, since GitHub scopes
          # caches to the creating ref.
          save-if: ${{ github.ref == 'refs/heads/main' }}
-      - name: Downgrade  dependencies
-        # These packages have newer requirements for MSRV
-        run: |
-          cargo update -p aws-sdk-bedrockruntime --precise 1.77.0
-          cargo update -p aws-sdk-dynamodb --precise 1.68.0
-          cargo update -p aws-config --precise 1.6.0
-          cargo update -p aws-sdk-kms --precise 1.63.0
-          cargo update -p aws-sdk-s3 --precise 1.79.0
-          cargo update -p aws-sdk-sso --precise 1.62.0
-          cargo update -p aws-sdk-ssooidc --precise 1.63.0
-          cargo update -p aws-sdk-sts --precise 1.63.0
-          # aws-runtime/sigv4/credential-types/types and the aws-smithy-*
-          # crates bumped their MSRV to 1.91.1 in late 2026; pin to the last
-          # 1.91.0-compatible versions. The order matters — each downgrade
-          # only succeeds once everything that still pins it at a higher
-          # version has itself been downgraded.
-          cargo update -p aws-runtime --precise 1.5.12
-          cargo update -p aws-types --precise 1.3.9
-          cargo update -p aws-sigv4 --precise 1.3.5
-          cargo update -p aws-credential-types --precise 1.2.8
-          cargo update -p aws-smithy-checksums --precise 0.63.9
-          cargo update -p aws-smithy-runtime --precise 1.9.3
-          cargo update -p aws-smithy-http --precise 0.62.4
-          cargo update -p aws-smithy-eventstream --precise 0.60.12
-          cargo update -p aws-smithy-http-client --precise 1.1.3
-          cargo update -p aws-smithy-observability --precise 0.1.4
-          cargo update -p aws-smithy-query --precise 0.60.8
-          cargo update -p aws-smithy-runtime-api --precise 1.9.1
-          cargo update -p aws-smithy-async --precise 1.2.6
-          cargo update -p aws-smithy-types --precise 1.3.5
-          cargo update -p aws-smithy-xml --precise 0.60.11
-          cargo update -p home --precise 0.5.9
+      - name: Downgrade dependencies that exceed our MSRV
+        # Re-resolve the lockfile against `rust-version` instead of hand-pinning
+        # every crate that raises its MSRV. Hand-pinning drifts: the pins keep
+        # ratcheting further back than needed and eventually contradict a real
+        # requirement elsewhere in the graph.
+        env:
+          CARGO_RESOLVER_INCOMPATIBLE_RUST_VERSIONS: fallback
+        run: cargo update
      - name: cargo +${{ matrix.msrv }} check
        env:
          RUSTUP_TOOLCHAIN: ${{ matrix.msrv }}
@@ -601,7 +601,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "hex",
- "http 1.4.2",
+ "http 1.5.0",
 "sha1 0.10.6",
 "time",
 "tokio",
@@ -664,7 +664,7 @@ dependencies = [
 "bytes-utils",
 "fastrand",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 0.4.6",
 "http-body 1.1.0",
 "percent-encoding",
@@ -694,7 +694,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body-util",
 "regex-lite",
 "tracing",
@@ -719,7 +719,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "regex-lite",
 "tracing",
 ]
@@ -743,7 +743,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "regex-lite",
 "tracing",
 ]
@@ -773,7 +773,7 @@ dependencies = [
 "hex",
 "hmac 0.13.0",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "lru 0.16.4",
 "percent-encoding",
@@ -802,7 +802,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "regex-lite",
 "tracing",
 ]
@@ -826,7 +826,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "regex-lite",
 "tracing",
 ]
@@ -851,7 +851,7 @@ dependencies = [
 "aws-types",
 "fastrand",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "regex-lite",
 "tracing",
 ]
@@ -873,7 +873,7 @@ dependencies = [
 "hex",
 "hmac 0.13.0",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "p256",
 "percent-encoding",
 "ring",
@@ -906,7 +906,7 @@ dependencies = [
 "bytes",
 "crc-fast",
 "hex",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "http-body-util",
 "md-5 0.11.0",
@@ -940,7 +940,7 @@ dependencies = [
 "bytes-utils",
 "futures-core",
 "futures-util",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "http-body-util",
 "percent-encoding",
@@ -961,7 +961,7 @@ dependencies = [
 "h2 0.3.27",
 "h2 0.4.14",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 0.4.6",
 "hyper 0.14.32",
 "hyper 1.9.0",
@@ -1023,7 +1023,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 0.4.6",
 "http-body 1.1.0",
 "http-body-util",
@@ -1044,7 +1044,7 @@ dependencies = [
 "aws-smithy-types",
 "bytes",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "pin-project-lite",
 "tokio",
 "tracing",
@@ -1070,7 +1070,7 @@ checksum = "7442cb268338f0eb8278140a107c046756aa01093d8ef5e99628d34ae09c94f5"
 dependencies = [
 "aws-smithy-runtime-api",
 "aws-smithy-types",
- "http 1.4.2",
+ "http 1.5.0",
 ]

 [[package]]
@@ -1084,7 +1084,7 @@ dependencies = [
 "bytes-utils",
 "futures-core",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 0.4.6",
 "http-body 1.1.0",
 "http-body-util",
@@ -1132,7 +1132,7 @@ dependencies = [
 "axum-core",
 "bytes",
 "futures-util",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "http-body-util",
 "hyper 1.9.0",
@@ -1165,7 +1165,7 @@ dependencies = [
 "async-trait",
 "bytes",
 "futures-util",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "http-body-util",
 "mime",
@@ -1243,9 +1243,9 @@ checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"

 [[package]]
 name = "base64"
-version = "0.23.0"
+version = "0.23.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b25655df2c3cdd83c5e5b293b88acd880332b2ddadd7c30ac43144fdc0033da9"
+checksum = "ac07cdecf99051d9a5238b80f35af32cdeba5b336e55d957b318b50137e18da5"

 [[package]]
 name = "base64-simd"
@@ -3441,6 +3441,12 @@ dependencies = [
 "percent-encoding",
 ]

+[[package]]
+name = "frostem"
+version = "1.20260804.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "82eb03a32a1d50555353c85a7b9d3279a6f1e91af9890b789acdf544ed57c8d7"
+
 [[package]]
 name = "fs_extra"
 version = "1.3.0"
@@ -3449,8 +3455,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"

 [[package]]
 name = "fsst"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arrow-array",
 "rand 0.9.5",
@@ -3807,20 +3813,21 @@ dependencies = [

 [[package]]
 name = "goosefs-sdk"
-version = "0.1.8"
+version = "0.1.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4a9bc9414e3b2cb0bd08dfe0eb315b177e86b119c7fa5e16179c92fc7b184860"
+checksum = "e1ea4eee6dcbc31b25ab4fd577adc55b677d2bed3aa3016c44c58fbe1b2298a5"
 dependencies = [
 "arc-swap",
 "async-trait",
 "bytes",
 "dashmap",
+ "fastrand",
 "futures",
 "hostname",
 "io-uring",
 "itoa",
 "libc",
- "lru 0.12.5",
+ "lru 0.18.2",
 "memmap2 0.9.10",
 "moka",
 "prost",
@@ -3879,7 +3886,7 @@ dependencies = [
 "fnv",
 "futures-core",
 "futures-sink",
- "http 1.4.2",
+ "http 1.5.0",
 "indexmap 2.14.0",
 "slab",
 "tokio",
@@ -3925,8 +3932,6 @@ version = "0.15.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9229cfe53dfd69f0609a49f65461bd93001ea1ef889cd5529dd176593f5338a1"
 dependencies = [
- "allocator-api2",
- "equivalent",
 "foldhash 0.1.5",
 ]

@@ -3992,7 +3997,7 @@ checksum = "629d8f3bbeda9d148036d6b0de0a3ab947abd08ce90626327fc3547a49d59d97"
 dependencies = [
 "dirs",
 "futures",
- "http 1.4.2",
+ "http 1.5.0",
 "indicatif",
 "libc",
 "log",
@@ -4015,7 +4020,7 @@ checksum = "430b33fa84f92796d4d263070b6c0d3ca219df7b9a0e1853ee431029b1612bcd"
 dependencies = [
 "async-trait",
 "bytes",
- "http 1.4.2",
+ "http 1.5.0",
 "more-asserts",
 "serde",
 "thiserror 2.0.18",
@@ -4080,9 +4085,9 @@ dependencies = [

 [[package]]
 name = "http"
-version = "1.4.2"
+version = "1.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6970f50e31d6fc17d3fa27329444bfa74e196cf62e95052a3f6fee181dba6425"
+checksum = "918d3568bebf352712bc2ef3d46a8bcf1a75b373be6539de198e9105cbbf9ce0"
 dependencies = [
 "bytes",
 "itoa",
@@ -4106,7 +4111,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ca2a8f2913ee65f60facd6a5905613afaa448497a0230cc41ce022d93290bc2c"
 dependencies = [
 "bytes",
- "http 1.4.2",
+ "http 1.5.0",
 ]

 [[package]]
@@ -4117,7 +4122,7 @@ checksum = "b021d93e26becf5dc7e1b75b1bed1fd93124b374ceb73f43d4d4eafec896a64a"
 dependencies = [
 "bytes",
 "futures-core",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "pin-project-lite",
 ]
@@ -4184,7 +4189,7 @@ dependencies = [
 "futures-channel",
 "futures-core",
 "h2 0.4.14",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "httparse",
 "httpdate",
@@ -4216,7 +4221,7 @@ version = "0.27.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "33ca68d021ef39cf6463ab54c1d0f5daf03377b70561305bb89a8f83aab66e0f"
 dependencies = [
- "http 1.4.2",
+ "http 1.5.0",
 "hyper 1.9.0",
 "hyper-util",
 "rustls 0.23.40",
@@ -4250,7 +4255,7 @@ dependencies = [
 "bytes",
 "futures-channel",
 "futures-util",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "hyper 1.9.0",
 "ipnet",
@@ -4810,8 +4815,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a"

 [[package]]
 name = "lance"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arc-swap",
 "arrow",
@@ -4885,8 +4890,8 @@ dependencies = [

 [[package]]
 name = "lance-arrow"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4908,7 +4913,7 @@ dependencies = [
 [[package]]
 name = "lance-arrow-scalar"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4922,7 +4927,7 @@ dependencies = [
 [[package]]
 name = "lance-arrow-stats"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -4931,8 +4936,8 @@ dependencies = [

 [[package]]
 name = "lance-bitpacking"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arrayref",
 "crunchy",
@@ -4942,8 +4947,8 @@ dependencies = [

 [[package]]
 name = "lance-core"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4983,8 +4988,8 @@ dependencies = [

 [[package]]
 name = "lance-datafusion"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5014,8 +5019,8 @@ dependencies = [

 [[package]]
 name = "lance-datagen"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5032,8 +5037,8 @@ dependencies = [

 [[package]]
 name = "lance-derive"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "proc-macro2",
 "quote",
@@ -5042,8 +5047,8 @@ dependencies = [

 [[package]]
 name = "lance-encoding"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -5069,7 +5074,6 @@ dependencies = [
 "prost",
 "prost-build",
 "rand 0.9.5",
- "strum 0.26.3",
 "tokio",
 "tracing",
 "xxhash-rust",
@@ -5078,8 +5082,8 @@ dependencies = [

 [[package]]
 name = "lance-file"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -5110,8 +5114,8 @@ dependencies = [

 [[package]]
 name = "lance-index"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arc-swap",
 "arrow",
@@ -5178,8 +5182,8 @@ dependencies = [

 [[package]]
 name = "lance-index-core"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -5201,8 +5205,8 @@ dependencies = [

 [[package]]
 name = "lance-io"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5214,7 +5218,7 @@ dependencies = [
 "bytes",
 "chrono",
 "futures",
- "http 1.4.2",
+ "http 1.5.0",
 "io-uring",
 "lance-arrow",
 "lance-core",
@@ -5238,8 +5242,8 @@ dependencies = [

 [[package]]
 name = "lance-linalg"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -5255,8 +5259,8 @@ dependencies = [

 [[package]]
 name = "lance-namespace"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arrow",
 "async-trait",
@@ -5268,8 +5272,8 @@ dependencies = [

 [[package]]
 name = "lance-namespace-impls"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arrow",
 "arrow-ipc",
@@ -5323,8 +5327,8 @@ dependencies = [

 [[package]]
 name = "lance-select"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -5339,8 +5343,8 @@ dependencies = [

 [[package]]
 name = "lance-table"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5379,8 +5383,8 @@ dependencies = [

 [[package]]
 name = "lance-testing"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -5393,13 +5397,13 @@ dependencies = [

 [[package]]
 name = "lance-tokenizer"
-version = "10.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
+version = "11.0.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.1#649076df12749ac6747b923bafb178626681cdbd"
 dependencies = [
+ "frostem",
 "icu_segmenter",
 "jieba-rs",
 "lindera",
- "rust-stemmers",
 "serde",
 "stop-words",
 "unicode-normalization",
@@ -5446,7 +5450,7 @@ dependencies = [
 "goosefs-sdk",
 "half",
 "hf-hub",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "lance",
 "lance-arrow",
@@ -5677,7 +5681,7 @@ dependencies = [
 "serde",
 "serde_json",
 "serde_yaml_ng",
- "strum 0.28.0",
+ "strum",
 "strum_macros 0.28.0",
 "unicode-blocks",
 "unicode-normalization",
@@ -5707,7 +5711,7 @@ dependencies = [
 "rkyv",
 "serde",
 "serde_json",
- "strum 0.28.0",
+ "strum",
 "strum_macros 0.28.0",
 "thiserror 2.0.18",
 ]
@@ -5770,15 +5774,6 @@ dependencies = [
 "tracing-subscriber",
 ]

-[[package]]
-name = "lru"
-version = "0.12.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "234cf4f4a04dc1f57e24b96cc0cd600cf2af460d4161ac5ecdd0af8e1f3b2a38"
-dependencies = [
- "hashbrown 0.15.5",
-]
-
 [[package]]
 name = "lru"
 version = "0.16.4"
@@ -5788,6 +5783,15 @@ dependencies = [
 "hashbrown 0.16.1",
 ]

+[[package]]
+name = "lru"
+version = "0.18.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5d2f2f9b4ba7e6b24d95e7e899329d35be83bcded72c8540cdd5368932d1d90a"
+dependencies = [
+ "hashbrown 0.17.1",
+]
+
 [[package]]
 name = "lru-slab"
 version = "0.1.2"
@@ -6121,15 +6125,15 @@ dependencies = [

 [[package]]
 name = "napi-build"
-version = "2.3.2"
+version = "2.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c9c366d2c8c60b86fa632df75f745509b52f9128f91a6bad4c796e44abb505e1"
+checksum = "5282704fbe8d49b0cf8b08e3f33233416a528658f205c7e5ace63b582de0b11c"

 [[package]]
 name = "napi-derive"
-version = "3.6.0"
+version = "3.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a49c513341a61a16a10af6efcce46b30d0822ba2d4fb197d24d33dfc199c78d5"
+checksum = "4d5c9c02556ea6dc99dffd36c1ce60141411657438501a125b675776d011ce92"
 dependencies = [
 "convert_case",
 "ctor 1.0.12",
@@ -6141,9 +6145,9 @@ dependencies = [

 [[package]]
 name = "napi-derive-backend"
-version = "6.0.0"
+version = "6.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4747005fa3e2c9989ac45a723a514c5db2411238b72981a3cda4c701a9dfea17"
+checksum = "d60b5d773ad46c698c8cc2cd9fde0b283d39cbb7f71c04bee633c7bdba4423bd"
 dependencies = [
 "convert_case",
 "proc-macro2",
@@ -6397,7 +6401,7 @@ dependencies = [
 "futures-channel",
 "futures-core",
 "futures-util",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body-util",
 "httparse",
 "humantime",
@@ -6516,10 +6520,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ec75551ff4cf3e57da98979f6a937aaa9ddb3915bf68cc17d03df733be6646ed"
 dependencies = [
 "anyhow",
- "base64 0.23.0",
+ "base64 0.23.1",
 "bytes",
 "futures",
- "http 1.4.2",
+ "http 1.5.0",
 "jiff",
 "log",
 "md-5 0.11.0",
@@ -6543,7 +6547,7 @@ checksum = "ad4d4f19c3ce01126a30611f8e544eaa217104a278c889ac17c9374fe4f9e4ef"
 dependencies = [
 "bytes",
 "futures",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "opendal-core",
 "reqwest 0.13.4",
@@ -6556,7 +6560,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "249ac5b0aa5a7a6c3737342d10456067937f9c9a6f3f02544271f7908ab91081"
 dependencies = [
 "futures",
- "http 1.4.2",
+ "http 1.5.0",
 "mea",
 "opendal-core",
 ]
@@ -6598,9 +6602,9 @@ version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b3310fbbb48f111c6f590473c2cd15e1b7f8e384444b0d4e328f0464c864d767"
 dependencies = [
- "base64 0.23.0",
+ "base64 0.23.1",
 "bytes",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "opendal-core",
 "opendal-service-azure-common",
@@ -6619,9 +6623,9 @@ version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2e3c406729935fe214ce574d68681a1ff7e0b322548f14094912bdbfe50e5c53"
 dependencies = [
- "base64 0.23.0",
+ "base64 0.23.1",
 "bytes",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "mea",
 "opendal-core",
@@ -6640,7 +6644,7 @@ version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7348c88edf15af435b7be930077746b569fac5e738c1bf6a363b675e7317c9df"
 dependencies = [
- "http 1.4.2",
+ "http 1.5.0",
 "opendal-core",
 ]

@@ -6651,7 +6655,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d533d4582105d269c8aebeee5f0e8bcf960f41b8aab6197df7012254d9f39bf0"
 dependencies = [
 "bytes",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "opendal-core",
 "quick-xml 0.41.0",
@@ -6669,7 +6673,7 @@ checksum = "007f3fba63c21e516c956b891e96ff9892d8175662bfb781cdada9d3766a11e6"
 dependencies = [
 "async-trait",
 "bytes",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "opendal-core",
 "percent-encoding",
@@ -6704,7 +6708,7 @@ checksum = "b41fd41eb7ed03c5e66cefda61e8e117808ffd2908f2916737cb020a6beb02c7"
 dependencies = [
 "bytes",
 "hf-xet",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "opendal-core",
 "percent-encoding",
@@ -6719,7 +6723,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cd528ec2d49c5ca69e674ffed7b3e0686fb9cfcfea0596870de381467fda4f1b"
 dependencies = [
 "bytes",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "opendal-core",
 "quick-xml 0.41.0",
@@ -6735,10 +6739,10 @@ version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "58e80cdf192d7eff05feed747894d64f81905ac4eaf132edf7ea270abdd2d663"
 dependencies = [
- "base64 0.23.0",
+ "base64 0.23.1",
 "bytes",
 "crc-fast",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "md-5 0.11.0",
 "opendal-core",
@@ -8284,13 +8288,13 @@ dependencies = [

 [[package]]
 name = "reqsign-aliyun-oss"
-version = "3.1.2"
+version = "3.1.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9c0f9f69a519dd6958c4b43606bb8e1278cdc76d611fc8fed4b796eee548dc0f"
+checksum = "a5e6d659fcdbca6fe2d7ef109c2e28499b7be80501f1bb86c10caf5ec8ac1219"
 dependencies = [
 "anyhow",
 "form_urlencoded",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "percent-encoding",
 "reqsign-core",
@@ -8300,16 +8304,15 @@ dependencies = [
 ]

 [[package]]
-name = "reqsign-aws-v4"
+name = "reqsign-aws-core"
 version = "3.0.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cc883bc56889f3e4a419265c87facea222a921debc5c6f15c7fd8b68ec4b36b2"
+checksum = "e4af084e1f3cbf3e67e0c972765399bce54ecec804cceba46b39a8331f3c1bff"
 dependencies = [
- "anyhow",
 "bytes",
 "form_urlencoded",
 "hex",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "percent-encoding",
 "quick-xml 0.41.0",
@@ -8322,16 +8325,31 @@ dependencies = [
 ]

 [[package]]
-name = "reqsign-azure-storage"
-version = "3.1.1"
+name = "reqsign-aws-v4"
+version = "3.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a6ebd8524185ce9c64063e3095f83968acfa90922f00c601a4a0f3aca15b077e"
+checksum = "4ac5b3b7cefa28933792b439186459f77f19f9b6edbeab41b8b187150361a206"
+dependencies = [
+ "bytes",
+ "http 1.5.0",
+ "log",
+ "quick-xml 0.41.0",
+ "reqsign-aws-core",
+ "reqsign-core",
+ "serde",
+]
+
+[[package]]
+name = "reqsign-azure-storage"
+version = "3.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2824e7da3c2cc42ac3406c674eb57c89127fdcd97f3a73c608cfc680505ea134"
 dependencies = [
 "anyhow",
- "base64 0.22.1",
+ "base64 0.23.1",
 "bytes",
 "form_urlencoded",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "pem",
 "percent-encoding",
@@ -8344,17 +8362,17 @@ dependencies = [

 [[package]]
 name = "reqsign-core"
-version = "3.2.0"
+version = "3.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7e38b44697c60a823705ccef85cb04d8e0527c9d16ed7c58bf1c6395bdd24ceb"
+checksum = "c07dd510b1e1b9b241883e483358147fb2ed2d497a7b39b065ba61eb93deceb0"
 dependencies = [
 "anyhow",
- "base64 0.22.1",
+ "base64 0.23.1",
 "bytes",
 "futures",
 "hex",
 "hmac 0.13.0",
- "http 1.4.2",
+ "http 1.5.0",
 "jiff",
 "log",
 "percent-encoding",
@@ -8368,9 +8386,9 @@ dependencies = [

 [[package]]
 name = "reqsign-file-read-tokio"
-version = "3.0.3"
+version = "3.0.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "688ff0ae421b8d4b92b53fdafaf53df2de28f428a9962edcf21702990b26f74b"
+checksum = "663d9d55abd0df0830ef0ae43708297cc1371cf4e8ca91f3ac813c309cca8c98"
 dependencies = [
 "anyhow",
 "reqsign-core",
@@ -8379,12 +8397,12 @@ dependencies = [

 [[package]]
 name = "reqsign-google"
-version = "3.0.3"
+version = "3.0.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a96da0b579b846d358090cb06b9e3c2ad1375529efbe3e0c45f96bd7bcf043ea"
+checksum = "4080a227f82a09f68540ecd028622065d7ac4c0bcb8727a25bdcfc0526235792"
 dependencies = [
 "form_urlencoded",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "percent-encoding",
 "reqsign-aws-v4",
@@ -8397,12 +8415,12 @@ dependencies = [

 [[package]]
 name = "reqsign-tencent-cos"
-version = "3.0.3"
+version = "3.0.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f6497dd9f6e3d1349b420521484099b284f95e8d3a65f088fccef42493a7b644"
+checksum = "764629c90f7c3566a6d4e4641ebab9acd604ce02e16eda4d37c7d7e79e16ed90"
 dependencies = [
 "anyhow",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "percent-encoding",
 "reqsign-core",
@@ -8422,7 +8440,7 @@ dependencies = [
 "futures-core",
 "futures-util",
 "h2 0.4.14",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "http-body-util",
 "hyper 1.9.0",
@@ -8466,7 +8484,7 @@ dependencies = [
 "bytes",
 "futures-core",
 "futures-util",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "http-body-util",
 "hyper 1.9.0",
@@ -8520,7 +8538,7 @@ checksum = "199dda04a536b532d0cc04d7979e39b1c763ea749bf91507017069c00b96056f"
 dependencies = [
 "anyhow",
 "async-trait",
- "http 1.4.2",
+ "http 1.5.0",
 "reqwest 0.13.4",
 "thiserror 2.0.18",
 "tower-service",
@@ -8562,9 +8580,9 @@ dependencies = [

 [[package]]
 name = "rkyv"
-version = "0.8.16"
+version = "0.8.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "73389e0c99e664f919275ab5b5b0471391fe9a8de61e1dff9b1eaf56a90f16e3"
+checksum = "815cc8a37159a463064825246cadb07961e25cd9885908606f6d08a98d8f8874"
 dependencies = [
 "bytecheck",
 "bytes",
@@ -8581,9 +8599,9 @@ dependencies = [

 [[package]]
 name = "rkyv_derive"
-version = "0.8.16"
+version = "0.8.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5d2ed0b54125315fb36bd021e82d314d1c126548f871634b483f46b31d13cac6"
+checksum = "c0ed1a78a1b19d184b0daa629dd9a024573173ec7d485b287cb369fb3607cc1c"
 dependencies = [
 "proc-macro2",
 "quote",
@@ -8661,16 +8679,6 @@ dependencies = [
 "ordered-multimap",
 ]

-[[package]]
-name = "rust-stemmers"
-version = "1.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e46a2036019fdb888131db7a4c847a1063a7493f971ed94ea82c67eada63ca54"
-dependencies = [
- "serde",
- "serde_derive",
-]
-
 [[package]]
 name = "rustc-demangle"
 version = "0.1.27"
@@ -9544,15 +9552,6 @@ version = "0.11.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f"

-[[package]]
-name = "strum"
-version = "0.26.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8fec0f0aef304996cf250b31b5a10dee7980c85da9d759361292b8bca5a18f06"
-dependencies = [
- "strum_macros 0.26.4",
-]
-
 [[package]]
 name = "strum"
 version = "0.28.0"
@@ -9575,19 +9574,6 @@ dependencies = [
 "syn 2.0.117",
 ]

-[[package]]
-name = "strum_macros"
-version = "0.26.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4c6bee85a5a24955dc440386795aa378cd9cf82acd5f764469152d2270e581be"
-dependencies = [
- "heck 0.5.0",
- "proc-macro2",
- "quote",
- "rustversion",
- "syn 2.0.117",
-]
-
 [[package]]
 name = "strum_macros"
 version = "0.28.0"
@@ -10110,7 +10096,7 @@ dependencies = [
 "base64 0.22.1",
 "bytes",
 "h2 0.4.14",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "http-body-util",
 "hyper 1.9.0",
@@ -10166,7 +10152,7 @@ checksum = "1e9cd434a998747dd2c4276bc96ee2e0c7a2eadf3cae88e52be55a05fa9053f5"
 dependencies = [
 "bitflags 2.11.1",
 "bytes",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "http-body-util",
 "pin-project-lite",
@@ -10186,7 +10172,7 @@ dependencies = [
 "bytes",
 "futures-core",
 "futures-util",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "http-body-util",
 "pin-project-lite",
@@ -11207,7 +11193,7 @@ dependencies = [
 "clap",
 "crc32fast",
 "futures",
- "http 1.4.2",
+ "http 1.5.0",
 "hyper 1.9.0",
 "lazy_static",
 "more-asserts",
@@ -11281,7 +11267,7 @@ dependencies = [
 "chrono",
 "clap",
 "gearhash",
- "http 1.4.2",
+ "http 1.5.0",
 "itertools 0.14.0",
 "lazy_static",
 "more-asserts",
@@ -13,20 +13,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"

 [workspace.dependencies]
-lance = { "version" = "=10.1.0-beta.2", default-features = false, "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=10.1.0-beta.2", default-features = false, "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=10.1.0-beta.2", default-features = false, "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=11.0.0-beta.1", default-features = false, "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=11.0.0-beta.1", default-features = false, "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=11.0.0-beta.1", default-features = false, "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "58.0.0", optional = false }
@@ -28,7 +28,7 @@
    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>10.1.0-beta.2</lance-core.version>
+        <lance-core.version>11.0.0-beta.1</lance-core.version>
        <spotless.skip>false</spotless.skip>
        <spotless.version>2.30.0</spotless.version>
        <spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>
@@ -339,7 +339,9 @@ impl Table {
        let transforms = NewColumnTransform::SqlExpressions(transforms);
        let res = self
            .inner_ref()?
-            .add_columns(transforms, None)
+            .add_columns()
+            .transform(transforms)
+            .execute()
            .await
            .default_error()?;
        Ok(res.into())
@@ -356,7 +358,9 @@ impl Table {
        let transforms = NewColumnTransform::AllNulls(schema);
        let res = self
            .inner_ref()?
-            .add_columns(transforms, None)
+            .add_columns()
+            .transform(transforms)
+            .execute()
            .await
            .default_error()?;
        Ok(res.into())
@@ -92,8 +92,10 @@ class LanceMergeInsertBuilder(object):
        self._when_not_matched_by_source_delete = True
        if isinstance(condition, Expr):
            self._when_not_matched_by_source_condition_expr = condition._inner
-        elif condition is not None:
+            self._when_not_matched_by_source_condition = None
+        else:
            self._when_not_matched_by_source_condition = condition
+            self._when_not_matched_by_source_condition_expr = None
        return self

    def use_index(self, use_index: bool) -> LanceMergeInsertBuilder:
@@ -2697,7 +2697,7 @@ class LanceHybridQueryBuilder(LanceQueryBuilder):
            self._fts_query.phrase_query(True)
        if self._distance_type:
            self._vector_query.metric(self._distance_type)
-        if self._minimum_nprobes:
+        if self._minimum_nprobes is not None:
            self._vector_query.minimum_nprobes(self._minimum_nprobes)
        if self._maximum_nprobes is not None:
            self._vector_query.maximum_nprobes(self._maximum_nprobes)
@@ -1595,8 +1595,8 @@ class Table(ABC):
        Prefer this over :meth:`fetch_blobs` for large payloads. ``row_ids`` is
        a ``list[int]`` or a query ``pyarrow.Table`` carrying row identity via
        ``_rowid`` or a ``_lance_row_id`` field on the blob descriptor. Null
-        rows are ``None``. Unsupported on LanceDB Cloud, where
-        :meth:`fetch_blobs` returns full bytes instead.
+        rows are ``None``. Remote tables require LanceDB Cloud server 0.5.0 or
+        newer.
        """

    @abstractmethod
@@ -123,6 +123,19 @@ async def test_async_hybrid_query_default_limit(table: AsyncTable):
    assert texts.count("a") == 1


+def test_hybrid_query_minimum_nprobes_zero_raises(sync_table: Table):
+    # minimum_nprobes(0) must raise the same validation error a plain vector
+    # query raises, not silently no-op because 0 is falsy.
+    with pytest.raises(ValueError, match="minimum_nprobes must be greater than 0"):
+        (
+            sync_table.search(query_type="hybrid")
+            .vector([0.0, 0.4])
+            .text("dog")
+            .minimum_nprobes(0)
+            .to_arrow()
+        )
+
+
 def test_hybrid_query_distance_range(sync_table: Table):
    reranker = RRFReranker(return_score="all")
    result = (
@@ -2055,6 +2055,24 @@ def blob_remote_table(*, server_version=Version("0.5.0")):
            request.send_header("phalanx-version", str(server_version))
            request.end_headers()
            request.wfile.write(json.dumps(BLOB_DESCRIBE_RESPONSE).encode())
+        elif request.path.startswith("/v1/table/test/blob/image/"):
+            path = request.path.partition("?")[0]
+            row_id = int(path.split("/")[-2])
+            payload = {10: b"alpha", 20: None, 30: b"gamma"}[row_id]
+            if payload is None:
+                request.send_response(204)
+                request.end_headers()
+                return
+            byte_range = request.headers["Range"].removeprefix("bytes=")
+            start_text, end_text = byte_range.split("-", maxsplit=1)
+            start = int(start_text)
+            end = int(end_text) if end_text else len(payload) - 1
+            chunk = payload[start : end + 1]
+            request.send_response(206)
+            request.send_header("Content-Range", f"bytes {start}-{end}/{len(payload)}")
+            request.send_header("Content-Length", str(len(chunk)))
+            request.end_headers()
+            request.wfile.write(chunk)
        elif request.path == "/v1/table/test/query/":
            content_len = int(request.headers.get("Content-Length", 0))
            body = json.loads(request.rfile.read(content_len))
@@ -2092,8 +2110,21 @@ def test_remote_blob_columns_and_fetch():
        assert table.blob_columns() == ["image"]
        blobs = table.fetch_blobs("image", [10, 20, 30])
        assert blobs.to_pylist() == [b"alpha", None, b"gamma"]
-        with pytest.raises(NotImplementedError, match="Use fetch_blobs for full bytes"):
-            table.fetch_blob_files("image", [10, 20, 30])
+
+
+def test_remote_blob_files_are_lazy_seekable_handles():
+    with blob_remote_table() as table:
+        files = table.fetch_blob_files("image", [10, 20, 30])
+
+        assert len(files) == 3
+        alpha, null_row, gamma = files
+        assert null_row is None
+        assert alpha is not None
+        assert gamma is not None
+        assert alpha.size() == 5
+        assert alpha.read_range(1, 3) == b"lph"
+        gamma.seek(2)
+        assert gamma.read() == b"mma"


 def test_remote_blob_fetch_accepts_query_table():
@@ -2364,6 +2364,29 @@ def test_merge_insert_by_source_delete_expr(mem_db: DBConnection):
    assert table.to_arrow().sort_by("a") == expected


+def test_merge_insert_by_source_delete_reconfigure(mem_db: DBConnection):
+    # Calling when_not_matched_by_source_delete() again with no condition must
+    # widen the delete to unconditional, not keep the earlier condition around.
+    table = mem_db.create_table(
+        "my_table",
+        data=pa.table({"a": [1, 2, 3], "b": ["a", "b", "c"]}),
+    )
+    new_data = pa.table({"a": [2, 4], "b": ["x", "z"]})
+
+    merge_insert_res = (
+        table.merge_insert("a")
+        .when_matched_update_all()
+        .when_not_matched_insert_all()
+        .when_not_matched_by_source_delete("a > 2")
+        .when_not_matched_by_source_delete()
+        .execute(new_data)
+    )
+    assert merge_insert_res.num_deleted_rows == 2
+
+    expected = pa.table({"a": [2, 4], "b": ["x", "z"]})
+    assert table.to_arrow().sort_by("a") == expected
+
+
@pytest.mark.asyncio
 async def test_merge_insert_by_source_delete_expr_async(
    mem_db_async: AsyncConnection,
@@ -426,9 +426,11 @@ pub struct PyBlobFile {
 impl PyBlobFile {
    fn read_bytes(self_: PyRef<'_, Self>) -> PyResult<Py<PyBytes>> {
        let inner = self_.inner.clone();
-        let bytes = block_on(async move { inner.read().await })
+        let py = self_.py();
+        let bytes = py
+            .detach(move || block_on(async move { inner.read().await }))
            .map_err(|e| PyRuntimeError::new_err(format!("blob read failed: {e}")))?;
-        Ok(PyBytes::new(self_.py(), bytes.as_ref()).unbind())
+        Ok(PyBytes::new(py, bytes.as_ref()).unbind())
    }

    pub fn read(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
@@ -444,24 +446,32 @@ impl PyBlobFile {

    fn close(self_: PyRef<'_, Self>) -> PyResult<()> {
        let inner = self_.inner.clone();
-        block_on(async move { inner.close().await })
+        self_
+            .py()
+            .detach(move || block_on(async move { inner.close().await }))
            .map_err(|e| PyRuntimeError::new_err(format!("blob close failed: {e}")))
    }

    fn is_closed(self_: PyRef<'_, Self>) -> bool {
        let inner = self_.inner.clone();
-        block_on(async move { inner.is_closed().await })
+        self_
+            .py()
+            .detach(move || block_on(async move { inner.is_closed().await }))
    }

    fn seek(self_: PyRef<'_, Self>, position: u64) -> PyResult<()> {
        let inner = self_.inner.clone();
-        block_on(async move { inner.seek(position).await })
+        self_
+            .py()
+            .detach(move || block_on(async move { inner.seek(position).await }))
            .map_err(|e| PyRuntimeError::new_err(format!("blob seek failed: {e}")))
    }

    fn tell(self_: PyRef<'_, Self>) -> PyResult<u64> {
        let inner = self_.inner.clone();
-        block_on(async move { inner.tell().await })
+        self_
+            .py()
+            .detach(move || block_on(async move { inner.tell().await }))
            .map_err(|e| PyRuntimeError::new_err(format!("blob tell failed: {e}")))
    }

@@ -475,16 +485,20 @@ impl PyBlobFile {
            .checked_add(length as u64)
            .ok_or_else(|| PyValueError::new_err("offset + length overflowed"))?;
        let inner = self_.inner.clone();
-        let bytes = block_on(async move { inner.read_range(offset..end).await })
+        let py = self_.py();
+        let bytes = py
+            .detach(move || block_on(async move { inner.read_range(offset..end).await }))
            .map_err(|e| PyRuntimeError::new_err(format!("blob read_range failed: {e}")))?;
-        Ok(PyBytes::new(self_.py(), bytes.as_ref()).unbind())
+        Ok(PyBytes::new(py, bytes.as_ref()).unbind())
    }

    fn read_up_to(self_: PyRef<'_, Self>, length: usize) -> PyResult<Py<PyBytes>> {
        let inner = self_.inner.clone();
-        let bytes = block_on(async move { inner.read_up_to(length).await })
-            .map_err(|e| PyRuntimeError::new_err(format!("blob read failed: {e}")))?;
-        Ok(PyBytes::new(self_.py(), bytes.as_ref()).unbind())
+        let py = self_.py();
+        let bytes = py
+            .detach(move || block_on(async move { inner.read_up_to(length).await }))
+            .map_err(|e| PyRuntimeError::new_err(format!("blob read_up_to failed: {e}")))?;
+        Ok(PyBytes::new(py, bytes.as_ref()).unbind())
    }
 }

@@ -1361,7 +1375,12 @@ impl Table {

        let inner = self_.inner_ref()?.clone();
        future_into_py(self_.py(), async move {
-            let result = inner.add_columns(definitions, None).await.infer_error()?;
+            let result = inner
+                .add_columns()
+                .transform(definitions)
+                .execute()
+                .await
+                .infer_error()?;
            Ok(AddColumnsResult::from(result))
        })
    }
@@ -1375,7 +1394,12 @@ impl Table {

        let inner = self_.inner_ref()?.clone();
        future_into_py(self_.py(), async move {
-            let result = inner.add_columns(transform, None).await.infer_error()?;
+            let result = inner
+                .add_columns()
+                .transform(transform)
+                .execute()
+                .await
+                .infer_error()?;
            Ok(AddColumnsResult::from(result))
        })
    }
@@ -49,8 +49,8 @@ lance-namespace = { workspace = true }
 lance-namespace-impls = { workspace = true }
 metrics = { workspace = true, optional = true }
 metrics-util = { workspace = true, optional = true }
-# Keep the direct dependency aligned with the version required by OpenDAL.
-goosefs-sdk = { version = "=0.1.8", optional = true }
+# Pin the GooseFS SDK to the version required by Lance's OpenDAL dependency.
+goosefs-sdk = { version = "=0.1.9", optional = true }
 moka = { workspace = true }
 pin-project = { workspace = true }
 tokio = { version = "1.23", features = ["rt-multi-thread", "sync"] }
@@ -9,6 +9,7 @@
 //!
 //! Blob tables require Lance file format >= 2.2 and stable row ids at create.

+use std::ops::Range;
 use std::sync::Arc;

 use arrow_array::LargeBinaryArray;
@@ -16,11 +17,203 @@ use arrow_array::builder::LargeBinaryBuilder;
 use arrow_schema::{DataType, Field, Schema};
 use lance::dataset::{BlobRangeRequest as LanceBlobRangeRequest, Dataset, WriteParams};
 use lance_arrow::FieldExt;
-use lance_encoding::version::LanceFileVersion;
+use lance_file::version::LanceFileVersion;
+use lance_io::object_store::ObjectStore;
+use object_store::path::Path;

 use crate::error::{Error, Result};

-pub use lance::dataset::BlobFile;
+/// Seekable handle for one blob value, backed by local storage or a remote
+/// HTTP byte-range endpoint.
+#[derive(Debug)]
+pub struct BlobFile {
+    inner: BlobFileInner,
+}
+
+#[derive(Debug)]
+enum BlobFileInner {
+    Native(lance::dataset::BlobFile),
+    #[cfg(feature = "remote")]
+    Remote(Box<crate::remote::table::blobs::RemoteBlobFile>),
+}
+
+impl From<lance::dataset::BlobFile> for BlobFile {
+    fn from(value: lance::dataset::BlobFile) -> Self {
+        Self {
+            inner: BlobFileInner::Native(value),
+        }
+    }
+}
+
+#[cfg(feature = "remote")]
+impl From<crate::remote::table::blobs::RemoteBlobFile> for BlobFile {
+    fn from(value: crate::remote::table::blobs::RemoteBlobFile) -> Self {
+        Self {
+            inner: BlobFileInner::Remote(Box::new(value)),
+        }
+    }
+}
+
+impl BlobFile {
+    /// Inline reader over a data-file slice.
+    pub fn new_inline(
+        object_store: Arc<ObjectStore>,
+        path: Path,
+        position: u64,
+        size: u64,
+    ) -> Self {
+        lance::dataset::BlobFile::new_inline(object_store, path, position, size).into()
+    }
+
+    /// Dedicated sidecar-file reader.
+    pub fn new_dedicated(object_store: Arc<ObjectStore>, path: Path, size: u64) -> Self {
+        lance::dataset::BlobFile::new_dedicated(object_store, path, size).into()
+    }
+
+    /// Packed reader for a slice in a shared sidecar.
+    pub fn new_packed(
+        object_store: Arc<ObjectStore>,
+        path: Path,
+        position: u64,
+        size: u64,
+    ) -> Self {
+        lance::dataset::BlobFile::new_packed(object_store, path, position, size).into()
+    }
+
+    /// External reader at a resolved object location.
+    pub fn new_external(
+        object_store: Arc<ObjectStore>,
+        path: Path,
+        uri: String,
+        position: u64,
+        size: u64,
+    ) -> Self {
+        lance::dataset::BlobFile::new_external(object_store, path, uri, position, size).into()
+    }
+
+    /// Close the handle.
+    pub async fn close(&self) -> lance_core::Result<()> {
+        match &self.inner {
+            BlobFileInner::Native(file) => file.close().await,
+            #[cfg(feature = "remote")]
+            BlobFileInner::Remote(file) => file.close().await,
+        }
+    }
+
+    /// Whether the handle is closed.
+    pub async fn is_closed(&self) -> bool {
+        match &self.inner {
+            BlobFileInner::Native(file) => file.is_closed().await,
+            #[cfg(feature = "remote")]
+            BlobFileInner::Remote(file) => file.is_closed(),
+        }
+    }
+
+    /// Read a range without moving the cursor.
+    pub async fn read_range(&self, range: Range<u64>) -> lance_core::Result<bytes::Bytes> {
+        match &self.inner {
+            BlobFileInner::Native(file) => file.read_range(range).await,
+            #[cfg(feature = "remote")]
+            BlobFileInner::Remote(file) => file.read_range(range).await,
+        }
+    }
+
+    /// Read ranges without moving the cursor.
+    pub async fn read_ranges(
+        &self,
+        ranges: &[Range<u64>],
+    ) -> lance_core::Result<Vec<bytes::Bytes>> {
+        match &self.inner {
+            BlobFileInner::Native(file) => file.read_ranges(ranges).await,
+            #[cfg(feature = "remote")]
+            BlobFileInner::Remote(file) => file.read_ranges(ranges).await,
+        }
+    }
+
+    /// Read from the cursor to the end.
+    pub async fn read(&self) -> lance_core::Result<bytes::Bytes> {
+        match &self.inner {
+            BlobFileInner::Native(file) => file.read().await,
+            #[cfg(feature = "remote")]
+            BlobFileInner::Remote(file) => file.read().await,
+        }
+    }
+
+    /// Read up to `len` bytes and advance the cursor.
+    pub async fn read_up_to(&self, len: usize) -> lance_core::Result<bytes::Bytes> {
+        match &self.inner {
+            BlobFileInner::Native(file) => file.read_up_to(len).await,
+            #[cfg(feature = "remote")]
+            BlobFileInner::Remote(file) => file.read_up_to(len).await,
+        }
+    }
+
+    /// Move the cursor to `new_cursor`.
+    pub async fn seek(&self, new_cursor: u64) -> lance_core::Result<()> {
+        match &self.inner {
+            BlobFileInner::Native(file) => file.seek(new_cursor).await,
+            #[cfg(feature = "remote")]
+            BlobFileInner::Remote(file) => file.seek(new_cursor).await,
+        }
+    }
+
+    /// Current cursor position.
+    pub async fn tell(&self) -> lance_core::Result<u64> {
+        match &self.inner {
+            BlobFileInner::Native(file) => file.tell().await,
+            #[cfg(feature = "remote")]
+            BlobFileInner::Remote(file) => file.tell().await,
+        }
+    }
+
+    /// Blob length in bytes.
+    pub fn size(&self) -> u64 {
+        match &self.inner {
+            BlobFileInner::Native(file) => file.size(),
+            #[cfg(feature = "remote")]
+            BlobFileInner::Remote(file) => file.size(),
+        }
+    }
+
+    /// Physical byte offset in the data file. `None` on remote handles. The
+    /// Cloud byte-range route does not expose storage layout.
+    pub fn position(&self) -> Option<u64> {
+        match &self.inner {
+            BlobFileInner::Native(file) => Some(file.position()),
+            #[cfg(feature = "remote")]
+            BlobFileInner::Remote(_) => None,
+        }
+    }
+
+    /// Path of the data file holding the blob. `None` on remote handles. The
+    /// Cloud byte-range route does not expose storage layout.
+    pub fn data_path(&self) -> Option<&Path> {
+        match &self.inner {
+            BlobFileInner::Native(file) => Some(file.data_path()),
+            #[cfg(feature = "remote")]
+            BlobFileInner::Remote(_) => None,
+        }
+    }
+
+    /// Native storage layout. `None` on remote handles. The Cloud byte-range
+    /// route does not expose layout.
+    pub fn kind(&self) -> Option<lance_core::datatypes::BlobKind> {
+        match &self.inner {
+            BlobFileInner::Native(file) => Some(file.kind()),
+            #[cfg(feature = "remote")]
+            BlobFileInner::Remote(_) => None,
+        }
+    }
+
+    /// External URI for native handles. Remote handles do not expose storage URIs.
+    pub fn uri(&self) -> Option<&str> {
+        match &self.inner {
+            BlobFileInner::Native(file) => file.uri(),
+            #[cfg(feature = "remote")]
+            BlobFileInner::Remote(_) => None,
+        }
+    }
+}

 /// One row-specific blob range read request.
 ///
@@ -264,7 +457,10 @@ pub(crate) async fn take_blob_files_aligned(

    let handles = dataset.take_blobs(row_ids, column).await?;
    ensure_all_row_ids_resolved(column, row_ids.len(), handles.len())?;
-    Ok(handles)
+    Ok(handles
+        .into_iter()
+        .map(|handle| handle.map(Into::into))
+        .collect())
 }

 #[cfg(test)]
@@ -34,7 +34,7 @@ use crate::remote::{
    db::{OPT_REMOTE_API_KEY, OPT_REMOTE_HOST_OVERRIDE, OPT_REMOTE_REGION},
 };
 use lance::io::ObjectStoreParams;
-pub use lance_encoding::version::LanceFileVersion;
+pub use lance_file::version::LanceFileVersion;
 #[cfg(feature = "remote")]
 use lance_io::object_store::StorageOptions;
 use lance_io::object_store::{StorageOptionsAccessor, StorageOptionsProvider};
@@ -12,7 +12,7 @@ use lance::dataset::refs::Ref;
 use lance::dataset::{ReadParams, WriteMode, builder::DatasetBuilder};
 use lance::io::{ObjectStore, ObjectStoreParams, WrappingObjectStore};
 use lance_datafusion::utils::StreamingWriteSource;
-use lance_encoding::version::LanceFileVersion;
+use lance_file::version::LanceFileVersion;
 use lance_io::object_store::{StorageOptionsAccessor, StorageOptionsProvider};
 use lance_table::io::commit::commit_handler_from_url;
 use object_store::local::LocalFileSystem;
@@ -201,7 +201,7 @@ impl LanceNamespaceDatabase {
        &self,
        request: &DbCreateTableRequest,
    ) -> Result<(
-        Option<lance_encoding::version::LanceFileVersion>,
+        Option<lance_file::version::LanceFileVersion>,
        Option<bool>,
        Option<bool>,
    )> {
@@ -214,7 +214,7 @@ impl LanceNamespaceDatabase {

        let storage_version_override = storage_options
            .and_then(|opts| opts.get(OPT_NEW_TABLE_STORAGE_VERSION))
-            .map(|s| s.parse::<lance_encoding::version::LanceFileVersion>())
+            .map(|s| s.parse::<lance_file::version::LanceFileVersion>())
            .transpose()?;

        let v2_manifest_override = storage_options
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors

-mod blobs;
+pub mod blobs;
 pub mod insert;

 use self::insert::{RemoteWriteExec, WriteOp};
@@ -3089,10 +3089,12 @@ mod tests {
            Box::pin(table.delete("false").map_ok(|_| ())),
            Box::pin(
                table
-                    .add_columns(
-                        NewColumnTransform::SqlExpressions(vec![("x".into(), "y".into())]),
-                        None,
-                    )
+                    .add_columns()
+                    .transform(NewColumnTransform::SqlExpressions(vec![(
+                        "x".into(),
+                        "y".into(),
+                    )]))
+                    .execute()
                    .map_ok(|_| ()),
            ),
            Box::pin(async {
@@ -4300,32 +4302,9 @@ mod tests {
            "fetch_blobs",
        );

-        let message = table
-            .fetch_blob_files("image", &[1])
-            .await
-            .unwrap_err()
-            .to_string();
-        assert!(
-            message.contains("fetch_blob_files is not supported on LanceDB Cloud"),
-            "got: {message}"
-        );
-        assert!(
-            !message.contains("Use fetch_blobs"),
-            "old server must not be told to use fetch_blobs, got: {message}"
-        );
-    }
-
-    #[tokio::test]
-    async fn test_blob_files_point_at_fetch_blobs_on_a_blob_capable_server() {
-        let table = Table::new_with_handler_version(
-            "my_table",
-            semver::Version::new(0, 5, 0),
-            |_| -> http::Response<String> { panic!("fetch_blob_files must not reach the server") },
-        );
-
        assert_not_supported_error(
            table.fetch_blob_files("image", &[1]).await.unwrap_err(),
-            "Use fetch_blobs for full bytes",
+            "requires LanceDB Cloud server 0.5.0 or newer",
        );
    }

@@ -6411,13 +6390,12 @@ mod tests {
        });

        let result = table
-            .add_columns(
-                NewColumnTransform::SqlExpressions(vec![
-                    ("b".into(), "a + 1".into()),
-                    ("x".into(), "cast(NULL as int32)".into()),
-                ]),
-                None,
-            )
+            .add_columns()
+            .transform(NewColumnTransform::SqlExpressions(vec![
+                ("b".into(), "a + 1".into()),
+                ("x".into(), "cast(NULL as int32)".into()),
+            ]))
+            .execute()
            .await
            .unwrap();

@@ -7142,10 +7120,12 @@ mod tests {
            }
            "add_columns" => {
                let _ = table
-                    .add_columns(
-                        NewColumnTransform::SqlExpressions(vec![("c".into(), "a + 1".into())]),
-                        None,
-                    )
+                    .add_columns()
+                    .transform(NewColumnTransform::SqlExpressions(vec![(
+                        "c".into(),
+                        "a + 1".into(),
+                    )]))
+                    .execute()
                    .await;
            }
            "drop_columns" => {
@@ -9903,10 +9883,12 @@ mod tests {
            .await
            .unwrap();
        branch
-            .add_columns(
-                NewColumnTransform::SqlExpressions(vec![("b".into(), "a + 1".into())]),
-                None,
-            )
+            .add_columns()
+            .transform(NewColumnTransform::SqlExpressions(vec![(
+                "b".into(),
+                "a + 1".into(),
+            )]))
+            .execute()
            .await
            .unwrap();
        branch
@@ -3,6 +3,7 @@

 //! LanceDB Table APIs

+use crate::blob::BlobFile;
 use arrow_array::{LargeBinaryArray, RecordBatch, RecordBatchReader};
 use arrow_schema::{Schema, SchemaRef};
 use async_trait::async_trait;
@@ -12,7 +13,6 @@ use datafusion_physical_plan::ExecutionPlan;
 use datafusion_physical_plan::display::DisplayableExecutionPlan;
 use futures::StreamExt;
 use futures::stream::FuturesUnordered;
-use lance::dataset::BlobFile;
 pub use lance::dataset::ColumnAlteration;
 pub use lance::dataset::NewColumnTransform;
 pub use lance::dataset::ReadParams;
@@ -65,6 +65,7 @@ use crate::utils::{PatchReadParam, PatchWriteParam, resolve_arrow_field_path};
 use self::dataset::DatasetConsistencyWrapper;
 use self::merge::MergeInsertBuilder;

+pub mod add_columns;
 mod add_data;
 pub mod branch_merge;
 mod create_index;
@@ -79,6 +80,7 @@ pub mod schema_evolution;
 pub mod update;
 pub mod write_progress;
 use crate::index::waiter::wait_for_index;
+pub use add_columns::AddColumnsBuilder;
 #[cfg(feature = "remote")]
 pub(crate) use add_data::PreprocessingOutput;
 pub use add_data::{AddDataBuilder, AddDataMode, AddResult, NaNVectorBehavior};
@@ -1620,12 +1622,8 @@ impl Table {
    }

    /// Add new columns to the table, providing values to fill in.
-    pub async fn add_columns(
-        &self,
-        transforms: NewColumnTransform,
-        read_columns: Option<Vec<String>>,
-    ) -> Result<AddColumnsResult> {
-        self.inner.add_columns(transforms, read_columns).await
+    pub fn add_columns(&self) -> AddColumnsBuilder {
+        AddColumnsBuilder::new(self.inner.clone())
    }

    /// Change a column's name or nullability.
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+//! Builder for adding columns to a table.
+
+use std::sync::Arc;
+
+use lance::dataset::NewColumnTransform;
+
+use super::BaseTable;
+use super::schema_evolution::AddColumnsResult;
+use crate::{Error, Result};
+
+/// Adds columns to a table. See [`Table::add_columns`](super::Table::add_columns).
+pub struct AddColumnsBuilder {
+    parent: Arc<dyn BaseTable>,
+    transform: Option<NewColumnTransform>,
+    read_columns: Option<Vec<String>>,
+}
+
+impl std::fmt::Debug for AddColumnsBuilder {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.debug_struct("AddColumnsBuilder")
+            .field("parent", &self.parent)
+            .field("has_transform", &self.transform.is_some())
+            .field("read_columns", &self.read_columns)
+            .finish()
+    }
+}
+
+impl AddColumnsBuilder {
+    pub(crate) fn new(parent: Arc<dyn BaseTable>) -> Self {
+        Self {
+            parent,
+            transform: None,
+            read_columns: None,
+        }
+    }
+
+    /// Set how the new columns' values are produced. Required.
+    pub fn transform(mut self, transform: NewColumnTransform) -> Self {
+        self.transform = Some(transform);
+        self
+    }
+
+    /// Limit which existing columns a [`NewColumnTransform::BatchUDF`] mapper
+    /// receives. Every other transform determines what it reads, so setting
+    /// this alongside one is an error rather than a silent no-op.
+    pub fn read_columns(mut self, columns: impl IntoIterator<Item = impl Into<String>>) -> Self {
+        self.read_columns = Some(columns.into_iter().map(Into::into).collect());
+        self
+    }
+
+    /// Add the columns.
+    pub async fn execute(self) -> Result<AddColumnsResult> {
+        let Self {
+            parent,
+            transform,
+            read_columns,
+        } = self;
+
+        let Some(transform) = transform else {
+            return Err(Error::InvalidInput {
+                message: "add_columns requires a transform".into(),
+            });
+        };
+
+        if read_columns.is_some() && !matches!(transform, NewColumnTransform::BatchUDF(_)) {
+            return Err(Error::InvalidInput {
+                message: "read_columns applies only to a BatchUDF transform; \
+                          every other transform determines what it reads"
+                    .into(),
+            });
+        }
+
+        parent.add_columns(transform, read_columns).await
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use std::sync::Arc;
+
+    use arrow_array::{Int32Array, RecordBatch, record_batch};
+    use arrow_schema::{DataType, Field, Schema};
+    use lance::dataset::{BatchUDF, NewColumnTransform};
+
+    use crate::Table;
+    use crate::connect;
+
+    async fn table_with_two_columns(name: &str) -> Table {
+        let conn = connect("memory://").execute().await.unwrap();
+        let batch = record_batch!(("x", Int32, [1, 2, 3]), ("y", Int32, [10, 20, 30])).unwrap();
+        conn.create_table(name, batch).execute().await.unwrap()
+    }
+
+    #[tokio::test]
+    async fn test_requires_a_transform() {
+        let table = table_with_two_columns("no_transform").await;
+        let err = table.add_columns().execute().await.unwrap_err();
+        assert!(
+            err.to_string().contains("requires a transform"),
+            "got: {err}"
+        );
+    }
+
+    #[tokio::test]
+    async fn test_read_columns_with_sql_expressions_is_rejected() {
+        let table = table_with_two_columns("read_cols_sql").await;
+        let err = table
+            .add_columns()
+            .transform(NewColumnTransform::SqlExpressions(vec![(
+                "doubled".into(),
+                "x * 2".into(),
+            )]))
+            .read_columns(["x"])
+            .execute()
+            .await
+            .unwrap_err();
+        assert!(err.to_string().contains("BatchUDF"), "got: {err}");
+
+        let schema = table.schema().await.unwrap();
+        assert!(
+            schema.field_with_name("doubled").is_err(),
+            "a rejected call must not commit"
+        );
+    }
+
+    #[tokio::test]
+    async fn test_read_columns_limits_what_a_batch_udf_sees() {
+        let table = table_with_two_columns("read_cols_udf").await;
+
+        let output_schema = Arc::new(Schema::new(vec![Field::new("sum", DataType::Int32, true)]));
+        let mapper_schema = output_schema.clone();
+        let udf = BatchUDF {
+            mapper: Box::new(move |batch: &RecordBatch| {
+                assert!(batch.column_by_name("x").is_some());
+                assert!(batch.column_by_name("y").is_none(), "y was not requested");
+                let x = batch["x"].as_any().downcast_ref::<Int32Array>().unwrap();
+                let doubled: Int32Array = x.iter().map(|v| v.map(|v| v * 2)).collect();
+                Ok(RecordBatch::try_new(
+                    mapper_schema.clone(),
+                    vec![Arc::new(doubled)],
+                )?)
+            }),
+            output_schema,
+            result_checkpoint: None,
+        };
+
+        table
+            .add_columns()
+            .transform(NewColumnTransform::BatchUDF(udf))
+            .read_columns(["x"])
+            .execute()
+            .await
+            .unwrap();
+
+        let schema = table.schema().await.unwrap();
+        assert!(schema.field_with_name("sum").is_ok());
+    }
+}
@@ -576,10 +576,12 @@ mod tests {

        // Add a new physical column AFTER the embedding column.
        table
-            .add_columns(
-                NewColumnTransform::SqlExpressions(vec![("score".into(), "42.0".into())]),
-                None,
-            )
+            .add_columns()
+            .transform(NewColumnTransform::SqlExpressions(vec![(
+                "score".into(),
+                "42.0".into(),
+            )]))
+            .execute()
            .await
            .unwrap();

@@ -683,7 +685,9 @@ mod tests {
            true,
        )]));
        table
-            .add_columns(NewColumnTransform::AllNulls(nested_schema), None)
+            .add_columns()
+            .transform(NewColumnTransform::AllNulls(nested_schema))
+            .execute()
            .await
            .unwrap();

@@ -18,7 +18,6 @@

 use std::collections::HashMap;
 use std::sync::Arc;
-
 use std::time::Duration;

 use arrow_array::cast::AsArray;
@@ -84,8 +84,9 @@ pub(super) async fn create_lsm_plan(
    let pk_columns = pk_columns(&ds_ref)?;
    // The base index an indexed arm relies on may lag compaction; resolve it so the
    // snapshot retains SSTables the index has not yet caught up to.
-    let arm_indexes = arm_maintained_index_names(&ds_ref, &query, &details).await?;
-    let (snapshots, in_memory) = build_read_context(table, &ds_ref, &details, &arm_indexes).await?;
+    let arm_index = arm_maintained_index_name(&ds_ref, &query, &details).await?;
+    let (snapshots, in_memory) =
+        build_read_context(table, &ds_ref, &details, arm_index.as_deref()).await?;

    let limit = query.base.limit;
    let offset = query.base.offset;
@@ -231,40 +232,28 @@ fn pk_columns(dataset: &Dataset) -> Result<Vec<String>> {
    Ok(pk)
 }

-/// Per-shard SSTable exclusion watermark: the generation at or below which
-/// SSTables are safe to drop for this query.
-///
-/// A generation is droppable only once it is compacted into the base table AND
-/// covered by the catch-up of every index the query relies on, so the watermark
-/// is the minimum across `index_names`. Gating on fewer than all of them would
-/// drop SSTables holding rows an uncounted index has not yet indexed, and that
-/// arm would silently return fewer rows.
-///
-/// See [`arm_maintained_index_names`] for which indexes are collected today: a
-/// vector search with a scalar prefilter is not yet among them.
-///
-/// An empty `index_names` (a plain scan) uses the compaction watermark alone.
-/// First occurrence per shard mirrors Lance's `compacted_generation_for_shard`.
+/// Per-shard SSTable exclusion watermark: the generation at or below which SSTables
+/// are safe to drop for this arm. A generation is droppable only once it is
+/// compacted into the base table AND covered by `index_name`'s catch-up (for an
+/// indexed arm); a plain scan (`index_name == None`) uses the compaction watermark
+/// alone. Capping at the index catch-up keeps rows the base index has not yet
+/// indexed visible through their SSTable. First occurrence per shard mirrors Lance's
+/// `compacted_generation_for_shard`.
 fn exclusion_watermarks(
    details: &MemWalIndexDetails,
-    index_names: &[String],
+    index_name: Option<&str>,
 ) -> HashMap<Uuid, u64> {
    let mut exclude: HashMap<Uuid, u64> = HashMap::new();
    for entry in &details.compacted_sstables {
        let mut watermark = entry.generation;
-        for name in index_names {
-            match details
+        if let Some(name) = index_name
+            && let Some(caught_up) = details
                .index_catchup
                .iter()
-                .find(|icp| icp.index_name == *name)
+                .find(|icp| icp.index_name == name)
                .and_then(|icp| icp.caught_up_generation_for_shard(&entry.shard_id))
-            {
-                Some(caught_up) => watermark = watermark.min(caught_up),
-                // No entry means the index is *not* known to hold these rows,
-                // and the base arm is index-only -- so every generation stays
-                // readable from its SSTable.
-                None => watermark = 0,
-            }
+        {
+            watermark = watermark.min(caught_up);
        }
        exclude.entry(entry.shard_id).or_insert(watermark);
    }
@@ -282,9 +271,9 @@ async fn build_read_context(
    table: &NativeTable,
    dataset: &Dataset,
    details: &MemWalIndexDetails,
-    index_names: &[String],
+    index_name: Option<&str>,
 ) -> Result<(Vec<ShardSnapshot>, HashMap<Uuid, InMemoryMemTables>)> {
-    let exclude = exclusion_watermarks(details, index_names);
+    let exclude = exclusion_watermarks(details, index_name);

    let shard_ids = dataset.list_mem_wal_latest_shard_ids().await?;
    // Use the dataset's own object store (not `ObjectStore::from_uri`, which
@@ -498,33 +487,19 @@ async fn index_maintained(
    }))
 }

-/// Every maintained base index this query relies on, used to gate SSTable
-/// exclusion by index catch-up.
-///
-/// Returns a list because the watermark must be the lowest across every index a
-/// query relies on. Today it never holds more than one: `reject_unsupported`
-/// refuses hybrid search, so the vector and full-text arms are mutually
-/// exclusive.
-///
-/// The case that is genuinely multi-index -- a vector search with a scalar or
-/// bitmap prefilter -- is **not collected yet**. Identifying those needs the
-/// planner's chosen indexes, not the columns the filter names, and no Lance API
-/// exposes them. Until it does, such a query is gated on its vector index alone.
-///
-/// Empty for a plain scan, or when no maintained index covers the searched
-/// column.
-async fn arm_maintained_index_names(
+/// The maintained base index the query's arm relies on (vector index for ANN, FTS
+/// index for full-text), used to gate SSTable compaction exclusion by index catch-up.
+/// `None` for a plain scan or when no maintained index covers the searched column.
+async fn arm_maintained_index_name(
    dataset: &Dataset,
    query: &VectorQueryRequest,
    details: &MemWalIndexDetails,
-) -> Result<Vec<String>> {
+) -> Result<Option<String>> {
    use lance::index::DatasetIndexExt;
-
-    // Each arm's searched column, the index-detail type it relies on, and a
+    // Resolve the arm's searched column, the index-detail type it relies on, and a
    // label for diagnostics — catch-up is taken from the vector/FTS index
    // specifically, not a BTree on the same column.
-    let mut arms: Vec<(String, &str, &str)> = Vec::new();
-    if !query.query_vector.is_empty() {
+    let (column, type_url_suffix, arm) = if !query.query_vector.is_empty() {
        let arrow_schema = ArrowSchema::from(dataset.schema());
        let column = match &query.column {
            Some(column) => column.clone(),
@@ -533,43 +508,31 @@ async fn arm_maintained_index_names(
                default_vector_column(&arrow_schema, dim)?
            }
        };
-        arms.push((column, "VectorIndexDetails", "vector"));
-    }
-    if let Some(fts) = &query.base.full_text_search
-        && let Some(column) = fts.columns().into_iter().next()
-    {
-        arms.push((column, "InvertedIndexDetails", "full-text"));
-    }
-    if arms.is_empty() {
-        return Ok(Vec::new());
-    }
-
-    let indices = dataset.load_indices().await?;
-    let mut names = Vec::with_capacity(arms.len());
-    for (column, type_url_suffix, arm) in arms {
-        let Some(field) = dataset.schema().field(&column) else {
-            continue;
-        };
-        let segment_names: Vec<String> = indices
-            .iter()
-            .filter(|idx| {
-                idx.fields.contains(&field.id)
-                    && idx
-                        .index_details
-                        .as_ref()
-                        .is_some_and(|d| d.type_url.ends_with(type_url_suffix))
-            })
-            .map(|idx| idx.name.clone())
-            .collect();
-        if let Some(name) =
-            resolve_single_index(segment_names, &details.maintained_indexes, arm, &column)?
-        {
-            names.push(name);
+        (column, "VectorIndexDetails", "vector")
+    } else if let Some(fts) = &query.base.full_text_search {
+        match fts.columns().into_iter().next() {
+            Some(column) => (column, "InvertedIndexDetails", "full-text"),
+            None => return Ok(None),
        }
-    }
-    names.sort();
-    names.dedup();
-    Ok(names)
+    } else {
+        return Ok(None);
+    };
+    let Some(field) = dataset.schema().field(&column) else {
+        return Ok(None);
+    };
+    let indices = dataset.load_indices().await?;
+    let segment_names: Vec<String> = indices
+        .iter()
+        .filter(|idx| {
+            idx.fields.contains(&field.id)
+                && idx
+                    .index_details
+                    .as_ref()
+                    .is_some_and(|d| d.type_url.ends_with(type_url_suffix))
+        })
+        .map(|idx| idx.name.clone())
+        .collect();
+    resolve_single_index(segment_names, &details.maintained_indexes, arm, &column)
 }

 /// Resolve the single logical index from the names of its matching physical
@@ -771,99 +734,24 @@ mod tests {
        };

        // Plain scan: drop every compacted generation (through 5).
-        assert_eq!(exclusion_watermarks(&details, &[]).get(&shard), Some(&5));
+        assert_eq!(exclusion_watermarks(&details, None).get(&shard), Some(&5));

        // FTS arm with a lagging index: exclusion is capped at the index catch-up
        // (2), so SSTable generations 3..=5 are retained until the index covers
        // them — otherwise those documents would silently vanish from FTS results.
        assert_eq!(
-            exclusion_watermarks(&details, &["fts_idx".to_string()]).get(&shard),
+            exclusion_watermarks(&details, Some("fts_idx")).get(&shard),
            Some(&2)
        );

-        // An index with no entry has not recorded that it holds these rows, so
-        // nothing is excluded. This is the case a table written before catch-up
-        // was maintained lands in, and it errs toward reading the SSTables.
+        // A caught-up index — or one untracked in index_catchup — falls back to the
+        // compaction watermark.
        assert_eq!(
-            exclusion_watermarks(&details, &["untracked_idx".to_string()]).get(&shard),
-            Some(&0)
-        );
-
-        // An index recorded as covering the compaction watermark excludes up to it.
-        let caught_up = MemWalIndexDetails {
-            index_catchup: vec![IndexCatchupProgress::new(
-                "caught_up_idx".to_string(),
-                vec![CompactedSsTable::new(shard, 5)],
-            )],
-            ..details.clone()
-        };
-        assert_eq!(
-            exclusion_watermarks(&caught_up, &["caught_up_idx".to_string()]).get(&shard),
+            exclusion_watermarks(&details, Some("caught_up_idx")).get(&shard),
            Some(&5)
        );
    }

-    /// A hybrid search reads a vector and a full-text index, and either may lag.
-    /// Retaining to the lower of the two is what keeps both arms complete;
-    /// gating on one alone would drop SSTables the other has not indexed.
-    #[test]
-    fn exclusion_watermark_takes_the_minimum_across_every_index_used() {
-        let shard = Uuid::from_u128(1);
-        let details = MemWalIndexDetails {
-            compacted_sstables: vec![CompactedSsTable::new(shard, 9)],
-            index_catchup: vec![
-                IndexCatchupProgress::new(
-                    "vec_idx".to_string(),
-                    vec![CompactedSsTable::new(shard, 7)],
-                ),
-                IndexCatchupProgress::new(
-                    "fts_idx".to_string(),
-                    vec![CompactedSsTable::new(shard, 4)],
-                ),
-            ],
-            maintained_indexes: vec!["vec_idx".to_string(), "fts_idx".to_string()],
-            ..Default::default()
-        };
-
-        // Each index alone stops at its own catch-up.
-        assert_eq!(
-            exclusion_watermarks(&details, &["vec_idx".to_string()]).get(&shard),
-            Some(&7)
-        );
-        assert_eq!(
-            exclusion_watermarks(&details, &["fts_idx".to_string()]).get(&shard),
-            Some(&4)
-        );
-
-        // Used together, the lower one governs regardless of order.
-        let both = ["vec_idx".to_string(), "fts_idx".to_string()];
-        assert_eq!(exclusion_watermarks(&details, &both).get(&shard), Some(&4));
-        let reversed = ["fts_idx".to_string(), "vec_idx".to_string()];
-        assert_eq!(
-            exclusion_watermarks(&details, &reversed).get(&shard),
-            Some(&4)
-        );
-    }
-
-    /// An index with no catch-up entry is not known to hold anything, so it
-    /// governs over a lagging sibling rather than the other way round.
-    #[test]
-    fn an_untracked_index_retains_everything() {
-        let shard = Uuid::from_u128(1);
-        let details = MemWalIndexDetails {
-            compacted_sstables: vec![CompactedSsTable::new(shard, 9)],
-            index_catchup: vec![IndexCatchupProgress::new(
-                "fts_idx".to_string(),
-                vec![CompactedSsTable::new(shard, 4)],
-            )],
-            maintained_indexes: vec!["fts_idx".to_string(), "untracked_idx".to_string()],
-            ..Default::default()
-        };
-
-        let both = ["fts_idx".to_string(), "untracked_idx".to_string()];
-        assert_eq!(exclusion_watermarks(&details, &both).get(&shard), Some(&0));
-    }
-
    #[test]
    fn resolve_single_index_dedupes_segments() {
        let maintained = vec!["fts_idx".to_string()];
@@ -193,10 +193,12 @@ mod tests {

        // Add a computed column
        let result = table
-            .add_columns(
-                NewColumnTransform::SqlExpressions(vec![("doubled".into(), "id * 2".into())]),
-                None,
-            )
+            .add_columns()
+            .transform(NewColumnTransform::SqlExpressions(vec![(
+                "doubled".into(),
+                "id * 2".into(),
+            )]))
+            .execute()
            .await
            .unwrap();

@@ -251,13 +253,12 @@ mod tests {

        // Add multiple columns at once
        table
-            .add_columns(
-                NewColumnTransform::SqlExpressions(vec![
-                    ("y".into(), "x + 1".into()),
-                    ("z".into(), "x * x".into()),
-                ]),
-                None,
-            )
+            .add_columns()
+            .transform(NewColumnTransform::SqlExpressions(vec![
+                ("y".into(), "x + 1".into()),
+                ("z".into(), "x * x".into()),
+            ]))
+            .execute()
            .await
            .unwrap();

@@ -283,10 +284,12 @@ mod tests {

        // Add a column with a constant value
        table
-            .add_columns(
-                NewColumnTransform::SqlExpressions(vec![("constant".into(), "42".into())]),
-                None,
-            )
+            .add_columns()
+            .transform(NewColumnTransform::SqlExpressions(vec![(
+                "constant".into(),
+                "42".into(),
+            )]))
+            .execute()
            .await
            .unwrap();

@@ -659,10 +662,12 @@ mod tests {

        // Add column increments version
        let add_result = table
-            .add_columns(
-                NewColumnTransform::SqlExpressions(vec![("c".into(), "a + b".into())]),
-                None,
-            )
+            .add_columns()
+            .transform(NewColumnTransform::SqlExpressions(vec![(
+                "c".into(),
+                "a + b".into(),
+            )]))
+            .execute()
            .await
            .unwrap();
        assert!(add_result.version > v1);
@@ -9,14 +9,17 @@ use arrow_array::{
 };
 use arrow_schema::{DataType, Field, Fields, Schema};
 use futures::TryStreamExt;
-use lance_encoding::version::LanceFileVersion;
+use lance::Dataset;
+use lance_file::version::LanceFileVersion;
 use lancedb::{
    Connection, Error, Result, Table,
    blob::{BlobRangeRequest, blob},
    connect, connect_namespace,
-    database::listing::OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS,
+    database::listing::{
+        ListingDatabaseOptions, NewTableConfig, OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS,
+    },
    query::{ExecutableQuery, QueryBase},
-    table::{AddDataMode, CompactionOptions, OptimizeAction},
+    table::{AddDataMode, CompactionOptions, OptimizeAction, OptimizeStats},
 };
 use tempfile::tempdir;

@@ -1075,3 +1078,252 @@ async fn fetch_blob_files_aligns_across_fragments_with_nulls_and_dups() -> Resul
    }
    Ok(())
 }
+
+/// Rows exercising the null/empty interleavings from
+/// <https://github.com/lancedb/lancedb/issues/3744>: a payload, a null, a valid
+/// empty value, then payloads whose descriptors a fragment rewrite used to zero.
+fn null_empty_input_batch() -> RecordBatch {
+    let owned = [
+        Some(dedicated_blob_bytes(1)),
+        None,
+        Some(Vec::new()),
+        Some(dedicated_blob_bytes(4)),
+        Some(dedicated_blob_bytes(5)),
+        Some(dedicated_blob_bytes(6)),
+    ];
+    let payloads: Vec<Option<&[u8]>> = owned.iter().map(|payload| payload.as_deref()).collect();
+    binary_input_batch(&[1, 2, 3, 4, 5, 6], &payloads)
+}
+
+/// One `(id, Some((payload length, first byte)))` per live row, or `(id, None)`
+/// for a null blob.  Comparing lengths and first bytes keeps failure output
+/// readable where comparing whole payloads would not.
+type BlobSummary = Vec<(i64, Option<(usize, Option<u8>)>)>;
+
+/// The rows [`null_empty_input_batch`] leaves behind after `id IN (1, 4)` is
+/// deleted: a null, a valid empty value, and the two payloads that follow them.
+fn expected_null_empty_survivors() -> BlobSummary {
+    vec![
+        (2, None),
+        (3, Some((0, None))),
+        (5, Some((DEDICATED_BLOB_LEN, Some(5)))),
+        (6, Some((DEDICATED_BLOB_LEN, Some(6)))),
+    ]
+}
+
+/// `optimize()` only rewrites a fragment when lance's compaction planner selects
+/// it — here because the delete pushes the fragment past
+/// `materialize_deletions_threshold` (0.1 by default; these tests delete 2 of 6
+/// rows). Without this check, a planner or threshold change upstream would leave
+/// both regression tests green while no rewrite happened at all.
+fn assert_compacted(stats: &OptimizeStats) {
+    let metrics = stats
+        .compaction
+        .as_ref()
+        .expect("OptimizeAction::All runs compaction");
+    assert!(
+        metrics.fragments_removed >= 1,
+        "optimize() rewrote no fragment, so this test proves nothing: {metrics:?}"
+    );
+}
+
+fn summarize(rows: &[(i64, Option<Vec<u8>>)]) -> BlobSummary {
+    rows.iter()
+        .map(|(id, payload)| {
+            (
+                *id,
+                payload
+                    .as_ref()
+                    .map(|bytes| (bytes.len(), bytes.first().copied())),
+            )
+        })
+        .collect()
+}
+
+async fn sorted_id_rowid(table: &Table) -> Result<Vec<(i64, u64)>> {
+    let mut pairs = collect_id_rowid(table).await?;
+    pairs.sort_by_key(|(id, _)| *id);
+    Ok(pairs)
+}
+
+/// `{position, size}` descriptors of a legacy v1 blob column, keyed by `id`.
+async fn v1_blob_descriptors(table: &Table) -> Result<Vec<(i64, Option<(u64, u64)>)>> {
+    let batches = table
+        .query()
+        .execute()
+        .await?
+        .try_collect::<Vec<_>>()
+        .await?;
+    let batch = arrow_select::concat::concat_batches(&batches[0].schema(), &batches).unwrap();
+    let ids = batch
+        .column_by_name("id")
+        .unwrap()
+        .as_any()
+        .downcast_ref::<Int64Array>()
+        .unwrap();
+    let descriptors = batch
+        .column_by_name("image")
+        .unwrap()
+        .as_any()
+        .downcast_ref::<StructArray>()
+        .expect("v1 blob column reads back as a descriptor struct");
+    let position = descriptors
+        .column_by_name("position")
+        .unwrap()
+        .as_any()
+        .downcast_ref::<UInt64Array>()
+        .unwrap();
+    let size = descriptors
+        .column_by_name("size")
+        .unwrap()
+        .as_any()
+        .downcast_ref::<UInt64Array>()
+        .unwrap();
+    let mut rows: Vec<(i64, Option<(u64, u64)>)> = (0..batch.num_rows())
+        .map(|row| {
+            let descriptor =
+                (!descriptors.is_null(row)).then(|| (position.value(row), size.value(row)));
+            (ids.value(row), descriptor)
+        })
+        .collect();
+    rows.sort_by_key(|(id, _)| *id);
+    Ok(rows)
+}
+
+/// Payload bytes of every live row of a legacy v1 blob column, keyed by `id`.
+/// [`Table::fetch_blobs`] rejects v1 columns, so read them through lance.
+async fn v1_blob_payloads(dataset_uri: &str, table: &Table) -> Result<Vec<(i64, Option<Vec<u8>>)>> {
+    let pairs = sorted_id_rowid(table).await?;
+    let row_ids: Vec<u64> = pairs.iter().map(|(_, row_id)| *row_id).collect();
+    let dataset = Arc::new(Dataset::open(dataset_uri).await?);
+    let files = dataset.take_blobs(&row_ids, "image").await?;
+    assert_eq!(
+        files.len(),
+        pairs.len(),
+        "take_blobs returned {} handles for {} live rows",
+        files.len(),
+        pairs.len()
+    );
+    let mut rows = Vec::with_capacity(pairs.len());
+    for ((id, _), file) in pairs.iter().zip(files) {
+        let payload = match file {
+            Some(file) => Some(file.read().await?.to_vec()),
+            None => None,
+        };
+        rows.push((*id, payload));
+    }
+    Ok(rows)
+}
+
+/// Length and first byte of every live blob v2 value, keyed by `id`.
+async fn blob_v2_values(table: &Table) -> Result<BlobSummary> {
+    let pairs = sorted_id_rowid(table).await?;
+    let row_ids: Vec<u64> = pairs.iter().map(|(_, row_id)| *row_id).collect();
+    let bytes = table.fetch_blobs("image", &row_ids).await?;
+    Ok(pairs
+        .iter()
+        .enumerate()
+        .map(|(slot, (id, _))| {
+            let value = (!bytes.is_null(slot))
+                .then(|| (bytes.value(slot).len(), bytes.value(slot).first().copied()));
+            (*id, value)
+        })
+        .collect())
+}
+
+/// Regression test for [#3744]: on storage 2.0 (legacy v1 descriptors),
+/// compaction rewrote every payload following a null or empty value in the same
+/// fragment as `{position: 0, size: 0}`, so the payload bytes read back as `b""`
+/// and the new fragment no longer referenced them at all.
+///
+/// [#3744]: https://github.com/lancedb/lancedb/issues/3744
+#[tokio::test]
+async fn optimize_preserves_v1_blob_payloads_with_null_and_empty() -> Result<()> {
+    let tmp = tempdir().unwrap();
+    let db_uri = tmp.path().to_str().unwrap().to_string();
+    let db = connect(&db_uri)
+        .database_options(&ListingDatabaseOptions {
+            new_table_config: NewTableConfig {
+                data_storage_version: Some(LanceFileVersion::V2_0),
+                ..Default::default()
+            },
+            ..Default::default()
+        })
+        .execute()
+        .await?;
+    let legacy = Field::new("image", DataType::LargeBinary, true).with_metadata(
+        std::collections::HashMap::from([("lance-encoding:blob".to_string(), "true".to_string())]),
+    );
+    let schema = Arc::new(Schema::new(vec![
+        Field::new("id", DataType::Int64, false),
+        legacy,
+    ]));
+    let table = db.create_empty_table("t", schema).execute().await?;
+    table.add(null_empty_input_batch()).execute().await?;
+    assert_eq!(
+        storage_format_version(&table).await,
+        LanceFileVersion::V2_0.resolve(),
+        "v1 blob descriptors only exist below storage 2.2"
+    );
+    let dataset_uri = table.uri().await?;
+
+    // Any rewrite triggers it; deleting rows is the shape from the issue.
+    table.delete("id IN (1, 4)").await?;
+    let descriptors_before = v1_blob_descriptors(&table).await?;
+    let before = v1_blob_payloads(&dataset_uri, &table).await?;
+    assert_eq!(
+        summarize(&before),
+        expected_null_empty_survivors(),
+        "test setup no longer produces the null/empty/payload mix"
+    );
+
+    let stats = table.optimize(OptimizeAction::All).await?;
+    assert_compacted(&stats);
+
+    let descriptors_after = v1_blob_descriptors(&table).await?;
+    let after = v1_blob_payloads(&dataset_uri, &table).await?;
+    assert_eq!(
+        summarize(&after),
+        summarize(&before),
+        "optimize() lost blob payloads; descriptors before={descriptors_before:?} after={descriptors_after:?}"
+    );
+    assert!(after == before, "optimize() changed blob payload bytes");
+    Ok(())
+}
+
+/// Regression test for the blob v2 half of [#3744]: compaction rewrote a valid
+/// empty value as null, destroying the null-vs-empty distinction.
+///
+/// [#3744]: https://github.com/lancedb/lancedb/issues/3744
+#[tokio::test]
+async fn optimize_preserves_blob_v2_null_and_empty_distinction() -> Result<()> {
+    let tmp = tempdir().unwrap();
+    let db = connect(tmp.path().to_str().unwrap()).execute().await?;
+    let table = db
+        .create_empty_table("t", blob_table_schema())
+        .execute()
+        .await?;
+    table.add(null_empty_input_batch()).execute().await?;
+    assert!(
+        storage_format_version(&table).await >= LanceFileVersion::V2_2,
+        "blob v2 columns require storage >= 2.2"
+    );
+
+    table.delete("id IN (1, 4)").await?;
+    let before = blob_v2_values(&table).await?;
+    assert_eq!(
+        before,
+        expected_null_empty_survivors(),
+        "test setup no longer produces the null/empty/payload mix"
+    );
+
+    let stats = table.optimize(OptimizeAction::All).await?;
+    assert_compacted(&stats);
+
+    assert_eq!(
+        blob_v2_values(&table).await?,
+        before,
+        "optimize() changed blob v2 values"
+    );
+    Ok(())
+}