chore: keep remote write types crate-visible

Merge remote-tracking branch 'upstream/main' into codex/update-lance-10-1-0-beta-1
# Conflicts: # Cargo.lock # Cargo.toml # java/pom.xml
2026-09-04 12:38:38 +00:00 · 2026-07-31 17:45:27 -04:00 · 2026-07-31 17:22:33 -04:00 · 2026-07-31 16:47:25 -04:00
24 changed files with 192 additions and 2208 deletions
@@ -601,7 +601,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "hex",
- "http 1.5.0",
+ "http 1.4.2",
 "sha1 0.10.6",
 "time",
 "tokio",
@@ -664,7 +664,7 @@ dependencies = [
 "bytes-utils",
 "fastrand",
 "http 0.2.12",
- "http 1.5.0",
+ "http 1.4.2",
 "http-body 0.4.6",
 "http-body 1.1.0",
 "percent-encoding",
@@ -694,7 +694,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "http 0.2.12",
- "http 1.5.0",
+ "http 1.4.2",
 "http-body-util",
 "regex-lite",
 "tracing",
@@ -719,7 +719,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "http 0.2.12",
- "http 1.5.0",
+ "http 1.4.2",
 "regex-lite",
 "tracing",
 ]
@@ -743,7 +743,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "http 0.2.12",
- "http 1.5.0",
+ "http 1.4.2",
 "regex-lite",
 "tracing",
 ]
@@ -773,7 +773,7 @@ dependencies = [
 "hex",
 "hmac 0.13.0",
 "http 0.2.12",
- "http 1.5.0",
+ "http 1.4.2",
 "http-body 1.1.0",
 "lru",
 "percent-encoding",
@@ -802,7 +802,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "http 0.2.12",
- "http 1.5.0",
+ "http 1.4.2",
 "regex-lite",
 "tracing",
 ]
@@ -826,7 +826,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "http 0.2.12",
- "http 1.5.0",
+ "http 1.4.2",
 "regex-lite",
 "tracing",
 ]
@@ -851,7 +851,7 @@ dependencies = [
 "aws-types",
 "fastrand",
 "http 0.2.12",
- "http 1.5.0",
+ "http 1.4.2",
 "regex-lite",
 "tracing",
 ]
@@ -873,7 +873,7 @@ dependencies = [
 "hex",
 "hmac 0.13.0",
 "http 0.2.12",
- "http 1.5.0",
+ "http 1.4.2",
 "p256",
 "percent-encoding",
 "ring",
@@ -906,7 +906,7 @@ dependencies = [
 "bytes",
 "crc-fast",
 "hex",
- "http 1.5.0",
+ "http 1.4.2",
 "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 1.5.0",
+ "http 1.4.2",
 "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 1.5.0",
+ "http 1.4.2",
 "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 1.5.0",
+ "http 1.4.2",
 "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 1.5.0",
+ "http 1.4.2",
 "pin-project-lite",
 "tokio",
 "tracing",
@@ -1070,7 +1070,7 @@ checksum = "7442cb268338f0eb8278140a107c046756aa01093d8ef5e99628d34ae09c94f5"
 dependencies = [
 "aws-smithy-runtime-api",
 "aws-smithy-types",
- "http 1.5.0",
+ "http 1.4.2",
 ]

 [[package]]
@@ -1084,7 +1084,7 @@ dependencies = [
 "bytes-utils",
 "futures-core",
 "http 0.2.12",
- "http 1.5.0",
+ "http 1.4.2",
 "http-body 0.4.6",
 "http-body 1.1.0",
 "http-body-util",
@@ -1132,7 +1132,7 @@ dependencies = [
 "axum-core",
 "bytes",
 "futures-util",
- "http 1.5.0",
+ "http 1.4.2",
 "http-body 1.1.0",
 "http-body-util",
 "hyper 1.9.0",
@@ -1165,7 +1165,7 @@ dependencies = [
 "async-trait",
 "bytes",
 "futures-util",
- "http 1.5.0",
+ "http 1.4.2",
 "http-body 1.1.0",
 "http-body-util",
 "mime",
@@ -3842,7 +3842,7 @@ dependencies = [
 "fnv",
 "futures-core",
 "futures-sink",
- "http 1.5.0",
+ "http 1.4.2",
 "indexmap 2.14.0",
 "slab",
 "tokio",
@@ -3953,7 +3953,7 @@ checksum = "629d8f3bbeda9d148036d6b0de0a3ab947abd08ce90626327fc3547a49d59d97"
 dependencies = [
 "dirs",
 "futures",
- "http 1.5.0",
+ "http 1.4.2",
 "indicatif",
 "libc",
 "log",
@@ -3976,7 +3976,7 @@ checksum = "430b33fa84f92796d4d263070b6c0d3ca219df7b9a0e1853ee431029b1612bcd"
 dependencies = [
 "async-trait",
 "bytes",
- "http 1.5.0",
+ "http 1.4.2",
 "more-asserts",
 "serde",
 "thiserror 2.0.18",
@@ -4041,9 +4041,9 @@ dependencies = [

 [[package]]
 name = "http"
-version = "1.5.0"
+version = "1.4.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "918d3568bebf352712bc2ef3d46a8bcf1a75b373be6539de198e9105cbbf9ce0"
+checksum = "6970f50e31d6fc17d3fa27329444bfa74e196cf62e95052a3f6fee181dba6425"
 dependencies = [
 "bytes",
 "itoa",
@@ -4067,7 +4067,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ca2a8f2913ee65f60facd6a5905613afaa448497a0230cc41ce022d93290bc2c"
 dependencies = [
 "bytes",
- "http 1.5.0",
+ "http 1.4.2",
 ]

 [[package]]
@@ -4078,7 +4078,7 @@ checksum = "b021d93e26becf5dc7e1b75b1bed1fd93124b374ceb73f43d4d4eafec896a64a"
 dependencies = [
 "bytes",
 "futures-core",
- "http 1.5.0",
+ "http 1.4.2",
 "http-body 1.1.0",
 "pin-project-lite",
 ]
@@ -4145,7 +4145,7 @@ dependencies = [
 "futures-channel",
 "futures-core",
 "h2 0.4.14",
- "http 1.5.0",
+ "http 1.4.2",
 "http-body 1.1.0",
 "httparse",
 "httpdate",
@@ -4177,7 +4177,7 @@ version = "0.27.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "33ca68d021ef39cf6463ab54c1d0f5daf03377b70561305bb89a8f83aab66e0f"
 dependencies = [
- "http 1.5.0",
+ "http 1.4.2",
 "hyper 1.9.0",
 "hyper-util",
 "rustls 0.23.40",
@@ -4211,7 +4211,7 @@ dependencies = [
 "bytes",
 "futures-channel",
 "futures-util",
- "http 1.5.0",
+ "http 1.4.2",
 "http-body 1.1.0",
 "hyper 1.9.0",
 "ipnet",
@@ -5182,7 +5182,7 @@ dependencies = [
 "chrono",
 "futures",
 "goosefs-sdk",
- "http 1.5.0",
+ "http 1.4.2",
 "io-uring",
 "lance-arrow",
 "lance-core",
@@ -5414,7 +5414,7 @@ dependencies = [
 "goosefs-sdk",
 "half",
 "hf-hub",
- "http 1.5.0",
+ "http 1.4.2",
 "http-body 1.1.0",
 "lance",
 "lance-arrow",
@@ -6080,15 +6080,15 @@ dependencies = [

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

 [[package]]
 name = "napi-derive"
-version = "3.6.1"
+version = "3.6.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4d5c9c02556ea6dc99dffd36c1ce60141411657438501a125b675776d011ce92"
+checksum = "a49c513341a61a16a10af6efcce46b30d0822ba2d4fb197d24d33dfc199c78d5"
 dependencies = [
 "convert_case",
 "ctor 1.0.5",
@@ -6100,9 +6100,9 @@ dependencies = [

 [[package]]
 name = "napi-derive-backend"
-version = "6.1.1"
+version = "6.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d60b5d773ad46c698c8cc2cd9fde0b283d39cbb7f71c04bee633c7bdba4423bd"
+checksum = "4747005fa3e2c9989ac45a723a514c5db2411238b72981a3cda4c701a9dfea17"
 dependencies = [
 "convert_case",
 "proc-macro2",
@@ -6356,7 +6356,7 @@ dependencies = [
 "futures-channel",
 "futures-core",
 "futures-util",
- "http 1.5.0",
+ "http 1.4.2",
 "http-body-util",
 "httparse",
 "humantime",
@@ -6477,7 +6477,7 @@ dependencies = [
 "base64 0.22.1",
 "bytes",
 "futures",
- "http 1.5.0",
+ "http 1.4.2",
 "http-body 1.1.0",
 "jiff",
 "log",
@@ -6502,7 +6502,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0d6f81ba6960e3fae1882f253b114b21d7e444e1534f209c7737a79f6243eb6f"
 dependencies = [
 "futures",
- "http 1.5.0",
+ "http 1.4.2",
 "mea",
 "opendal-core",
 ]
@@ -6546,7 +6546,7 @@ checksum = "0030644366ef5d8cbe3a4a5822bf99a4aafddc1666e9d24b44d158d9062fc76a"
 dependencies = [
 "base64 0.22.1",
 "bytes",
- "http 1.5.0",
+ "http 1.4.2",
 "log",
 "opendal-core",
 "opendal-service-azure-common",
@@ -6567,7 +6567,7 @@ checksum = "6dea4908d490143a9b0b7f7a790e139ff829b06a023f670455ed3d44f664b361"
 dependencies = [
 "base64 0.22.1",
 "bytes",
- "http 1.5.0",
+ "http 1.4.2",
 "log",
 "opendal-core",
 "opendal-service-azure-common",
@@ -6585,7 +6585,7 @@ version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9b489f13c42e69d69bdd72952b634356ec43a7881a20259b38b540fcecdf4051"
 dependencies = [
- "http 1.5.0",
+ "http 1.4.2",
 "opendal-core",
 ]

@@ -6596,7 +6596,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "aa8cafe9729213375c7331019b0cb756ad3e1aff7f45cd32c45eae91ebde8901"
 dependencies = [
 "bytes",
- "http 1.5.0",
+ "http 1.4.2",
 "log",
 "opendal-core",
 "quick-xml 0.39.4",
@@ -6614,7 +6614,7 @@ checksum = "48de101aac565ed06af4b47903c24eafd249075553ec1fb18256751c45148d47"
 dependencies = [
 "async-trait",
 "bytes",
- "http 1.5.0",
+ "http 1.4.2",
 "log",
 "opendal-core",
 "percent-encoding",
@@ -6649,7 +6649,7 @@ checksum = "c4922661976a1d40794a2adfbdb888cc3c23097690f825a92f773af38908a848"
 dependencies = [
 "bytes",
 "hf-xet",
- "http 1.5.0",
+ "http 1.4.2",
 "log",
 "opendal-core",
 "percent-encoding",
@@ -6665,7 +6665,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "328fa55e8888cbdfe00826bfea2a79042422b720e8369e9e021e46121dea5ace"
 dependencies = [
 "bytes",
- "http 1.5.0",
+ "http 1.4.2",
 "log",
 "opendal-core",
 "quick-xml 0.39.4",
@@ -6684,7 +6684,7 @@ dependencies = [
 "base64 0.22.1",
 "bytes",
 "crc32c",
- "http 1.5.0",
+ "http 1.4.2",
 "log",
 "md-5 0.11.0",
 "opendal-core",
@@ -7583,7 +7583,7 @@ version = "0.14.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "343d3bd7056eda839b03204e68deff7d1b13aba7af2b2fd16890697274262ee7"
 dependencies = [
- "heck 0.4.1",
+ "heck 0.5.0",
 "itertools 0.14.0",
 "log",
 "multimap",
@@ -8226,7 +8226,7 @@ checksum = "57ac2757f3140aa2e213b554148ae0b52733e624fc6723f0cc6bb3d440176c95"
 dependencies = [
 "anyhow",
 "form_urlencoded",
- "http 1.5.0",
+ "http 1.4.2",
 "log",
 "percent-encoding",
 "reqsign-core",
@@ -8244,7 +8244,7 @@ dependencies = [
 "anyhow",
 "bytes",
 "form_urlencoded",
- "http 1.5.0",
+ "http 1.4.2",
 "log",
 "percent-encoding",
 "quick-xml 0.39.4",
@@ -8266,7 +8266,7 @@ dependencies = [
 "base64 0.22.1",
 "bytes",
 "form_urlencoded",
- "http 1.5.0",
+ "http 1.4.2",
 "jsonwebtoken",
 "log",
 "pem",
@@ -8291,7 +8291,7 @@ dependencies = [
 "futures",
 "hex",
 "hmac 0.12.1",
- "http 1.5.0",
+ "http 1.4.2",
 "jiff",
 "log",
 "percent-encoding",
@@ -8318,7 +8318,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "35cc609b49c69e76ecaceb775a03f792d1ed3e7755ab3548d4534fd801e3242e"
 dependencies = [
 "form_urlencoded",
- "http 1.5.0",
+ "http 1.4.2",
 "jsonwebtoken",
 "log",
 "percent-encoding",
@@ -8338,7 +8338,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e128f19525861dbded59e1e7c17653a8ed63d573ca04aed708d552dbef5bb32a"
 dependencies = [
 "anyhow",
- "http 1.5.0",
+ "http 1.4.2",
 "log",
 "percent-encoding",
 "reqsign-core",
@@ -8358,7 +8358,7 @@ dependencies = [
 "futures-core",
 "futures-util",
 "h2 0.4.14",
- "http 1.5.0",
+ "http 1.4.2",
 "http-body 1.1.0",
 "http-body-util",
 "hyper 1.9.0",
@@ -8402,7 +8402,7 @@ dependencies = [
 "bytes",
 "futures-core",
 "futures-util",
- "http 1.5.0",
+ "http 1.4.2",
 "http-body 1.1.0",
 "http-body-util",
 "hyper 1.9.0",
@@ -8456,7 +8456,7 @@ checksum = "199dda04a536b532d0cc04d7979e39b1c763ea749bf91507017069c00b96056f"
 dependencies = [
 "anyhow",
 "async-trait",
- "http 1.5.0",
+ "http 1.4.2",
 "reqwest 0.13.3",
 "thiserror 2.0.18",
 "tower-service",
@@ -8498,9 +8498,9 @@ dependencies = [

 [[package]]
 name = "rkyv"
-version = "0.8.17"
+version = "0.8.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "815cc8a37159a463064825246cadb07961e25cd9885908606f6d08a98d8f8874"
+checksum = "73389e0c99e664f919275ab5b5b0471391fe9a8de61e1dff9b1eaf56a90f16e3"
 dependencies = [
 "bytecheck",
 "bytes",
@@ -8517,9 +8517,9 @@ dependencies = [

 [[package]]
 name = "rkyv_derive"
-version = "0.8.17"
+version = "0.8.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c0ed1a78a1b19d184b0daa629dd9a024573173ec7d485b287cb369fb3607cc1c"
+checksum = "5d2ed0b54125315fb36bd021e82d314d1c126548f871634b483f46b31d13cac6"
 dependencies = [
 "proc-macro2",
 "quote",
@@ -9277,7 +9277,7 @@ version = "0.8.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c1c97747dbf44bb1ca44a561ece23508e99cb592e862f22222dcf42f51d1e451"
 dependencies = [
- "heck 0.4.1",
+ "heck 0.5.0",
 "proc-macro2",
 "quote",
 "syn 2.0.117",
@@ -9289,7 +9289,7 @@ version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "54254b8531cafa275c5e096f62d48c81435d1015405a91198ddb11e967301d40"
 dependencies = [
- "heck 0.4.1",
+ "heck 0.5.0",
 "proc-macro2",
 "quote",
 "syn 2.0.117",
@@ -9730,7 +9730,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "32497e9a4c7b38532efcdebeef879707aa9f794296a4f0244f6f69e9bc8574bd"
 dependencies = [
 "fastrand",
- "getrandom 0.3.4",
+ "getrandom 0.4.2",
 "once_cell",
 "rustix",
 "windows-sys 0.61.2",
@@ -10058,7 +10058,7 @@ dependencies = [
 "base64 0.22.1",
 "bytes",
 "h2 0.4.14",
- "http 1.5.0",
+ "http 1.4.2",
 "http-body 1.1.0",
 "http-body-util",
 "hyper 1.9.0",
@@ -10114,7 +10114,7 @@ checksum = "1e9cd434a998747dd2c4276bc96ee2e0c7a2eadf3cae88e52be55a05fa9053f5"
 dependencies = [
 "bitflags 2.11.1",
 "bytes",
- "http 1.5.0",
+ "http 1.4.2",
 "http-body 1.1.0",
 "http-body-util",
 "pin-project-lite",
@@ -10134,7 +10134,7 @@ dependencies = [
 "bytes",
 "futures-core",
 "futures-util",
- "http 1.5.0",
+ "http 1.4.2",
 "http-body 1.1.0",
 "http-body-util",
 "pin-project-lite",
@@ -11155,7 +11155,7 @@ dependencies = [
 "clap",
 "crc32fast",
 "futures",
- "http 1.5.0",
+ "http 1.4.2",
 "hyper 1.9.0",
 "lazy_static",
 "more-asserts",
@@ -11229,7 +11229,7 @@ dependencies = [
 "chrono",
 "clap",
 "gearhash",
- "http 1.5.0",
+ "http 1.4.2",
 "itertools 0.14.0",
 "lazy_static",
 "more-asserts",
@@ -15,7 +15,6 @@ renovate.json
 src
 lancedb
 examples
-scripts
 nodejs-artifacts
 Cargo.toml
 biome.json
@@ -1,47 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-const {
-  checkNativeBinary,
-  findForbiddenUndefinedSymbols,
-} = require("../scripts/check-native-symbols.js");
-
-test("detects the unresolved AVX-512 symbol from broken musl binaries", () => {
-  const output = [
-    "                 U napi_create_function",
-    "                 U sum_4bit_dist_table_32bytes_batch_avx512",
-    "                 U strlen",
-  ].join("\n");
-
-  expect(findForbiddenUndefinedSymbols(output)).toEqual([
-    "sum_4bit_dist_table_32bytes_batch_avx512",
-  ]);
-});
-
-test("accepts native binaries without unresolved internal Lance symbols", () => {
-  const runNm = jest.fn(() => ({
-    status: 0,
-    stdout:
-      "                 U napi_create_function\n                 U strlen\n",
-    stderr: "",
-  }));
-
-  expect(() => checkNativeBinary("lancedb.node", runNm)).not.toThrow();
-  expect(runNm).toHaveBeenCalledWith(
-    "nm",
-    ["-D", "--undefined-only", "lancedb.node"],
-    { encoding: "utf8" },
-  );
-});
-
-test("rejects native binaries with the unresolved AVX-512 symbol", () => {
-  const runNm = jest.fn(() => ({
-    status: 0,
-    stdout: "                 U sum_4bit_dist_table_32bytes_batch_avx512\n",
-    stderr: "",
-  }));
-
-  expect(() => checkNativeBinary("lancedb.node", runNm)).toThrow(
-    "lancedb.node contains unresolved internal Lance symbols: sum_4bit_dist_table_32bytes_batch_avx512",
-  );
-});
@@ -86,8 +86,7 @@
    "postdocs": "node typedoc_post_process.js",
    "lint": "biome check . && biome format .",
    "lint-fix": "biome check --write . && biome format --write .",
-    "check:native-symbols": "node scripts/check-native-symbols.js",
-    "prepublishOnly": "pnpm check:native-symbols && napi prepublish -t npm",
+    "prepublishOnly": "napi prepublish -t npm",
    "test": "jest --verbose",
    "integration": "S3_TEST=1 pnpm test",
    "universal": "napi universalize",
@@ -1,77 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-const { spawnSync } = require("node:child_process");
-const { existsSync } = require("node:fs");
-const path = require("node:path");
-
-const FORBIDDEN_UNDEFINED_SYMBOLS = new Set([
-  "sum_4bit_dist_table_32bytes_batch_avx512",
-]);
-
-function findForbiddenUndefinedSymbols(output) {
-  const found = new Set();
-
-  for (const line of output.split(/\r?\n/)) {
-    const columns = line.trim().split(/\s+/);
-    const symbol = columns.at(-1)?.split("@")[0];
-    if (symbol && FORBIDDEN_UNDEFINED_SYMBOLS.has(symbol)) {
-      found.add(symbol);
-    }
-  }
-
-  return [...found].sort();
-}
-
-function checkNativeBinary(binaryPath, runNm = spawnSync) {
-  const result = runNm("nm", ["-D", "--undefined-only", binaryPath], {
-    encoding: "utf8",
-  });
-
-  if (result.error) {
-    throw new Error(`Unable to inspect ${binaryPath}: ${result.error.message}`);
-  }
-  if (result.status !== 0) {
-    throw new Error(
-      `Unable to inspect ${binaryPath}: nm exited with status ${result.status}\n${result.stderr}`,
-    );
-  }
-
-  const forbidden = findForbiddenUndefinedSymbols(result.stdout);
-  if (forbidden.length > 0) {
-    throw new Error(
-      `${binaryPath} contains unresolved internal Lance symbols: ${forbidden.join(
-        ", ",
-      )}`,
-    );
-  }
-}
-
-function main() {
-  const binaryPath = path.resolve(
-    __dirname,
-    "..",
-    "npm",
-    "linux-x64-musl",
-    "lancedb.linux-x64-musl.node",
-  );
-
-  if (!existsSync(binaryPath)) {
-    throw new Error(
-      `Missing ${binaryPath}; assemble the native artifacts before publishing`,
-    );
-  }
-
-  checkNativeBinary(binaryPath);
-}
-
-if (require.main === module) {
-  try {
-    main();
-  } catch (error) {
-    console.error(error instanceof Error ? error.message : error);
-    process.exitCode = 1;
-  }
-}
-
-module.exports = { checkNativeBinary, findForbiddenUndefinedSymbols };
@@ -339,9 +339,7 @@ impl Table {
        let transforms = NewColumnTransform::SqlExpressions(transforms);
        let res = self
            .inner_ref()?
-            .add_columns()
-            .transform(transforms)
-            .execute()
+            .add_columns(transforms, None)
            .await
            .default_error()?;
        Ok(res.into())
@@ -358,9 +356,7 @@ impl Table {
        let transforms = NewColumnTransform::AllNulls(schema);
        let res = self
            .inner_ref()?
-            .add_columns()
-            .transform(transforms)
-            .execute()
+            .add_columns(transforms, None)
            .await
            .default_error()?;
        Ok(res.into())
@@ -92,10 +92,8 @@ 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
-            self._when_not_matched_by_source_condition = None
-        else:
+        elif condition is not None:
            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 is not None:
+        if self._minimum_nprobes:
            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``. Remote tables require LanceDB Cloud server 0.5.0 or
-        newer.
+        rows are ``None``. Unsupported on LanceDB Cloud, where
+        :meth:`fetch_blobs` returns full bytes instead.
        """

    @abstractmethod
@@ -123,19 +123,6 @@ 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 = (
@@ -2055,24 +2055,6 @@ 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))
@@ -2110,21 +2092,8 @@ 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"]
-
-
-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"
+        with pytest.raises(NotImplementedError, match="Use fetch_blobs for full bytes"):
+            table.fetch_blob_files("image", [10, 20, 30])


 def test_remote_blob_fetch_accepts_query_table():
@@ -2364,29 +2364,6 @@ 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,
@@ -426,11 +426,9 @@ pub struct PyBlobFile {
 impl PyBlobFile {
    fn read_bytes(self_: PyRef<'_, Self>) -> PyResult<Py<PyBytes>> {
        let inner = self_.inner.clone();
-        let py = self_.py();
-        let bytes = py
-            .detach(move || block_on(async move { inner.read().await }))
+        let bytes = block_on(async move { inner.read().await })
            .map_err(|e| PyRuntimeError::new_err(format!("blob read failed: {e}")))?;
-        Ok(PyBytes::new(py, bytes.as_ref()).unbind())
+        Ok(PyBytes::new(self_.py(), bytes.as_ref()).unbind())
    }

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

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

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

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

    fn read_up_to(self_: PyRef<'_, Self>, length: usize) -> PyResult<Py<PyBytes>> {
        let inner = self_.inner.clone();
-        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())
+        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())
    }
 }

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

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

        let inner = self_.inner_ref()?.clone();
        future_into_py(self_.py(), async move {
-            let result = inner
-                .add_columns()
-                .transform(transform)
-                .execute()
-                .await
-                .infer_error()?;
+            let result = inner.add_columns(transform, None).await.infer_error()?;
            Ok(AddColumnsResult::from(result))
        })
    }
@@ -1,2 +1,2 @@
 [toolchain]
-channel = "1.97.0"
+channel = "1.95.0"
@@ -9,7 +9,6 @@
 //!
 //! 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;
@@ -18,202 +17,10 @@ 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_io::object_store::ObjectStore;
-use object_store::path::Path;

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

-/// 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,
-        }
-    }
-}
+pub use lance::dataset::BlobFile;

 /// One row-specific blob range read request.
 ///
@@ -457,10 +264,7 @@ 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
-        .into_iter()
-        .map(|handle| handle.map(Into::into))
-        .collect())
+    Ok(handles)
 }

 #[cfg(test)]
@@ -264,7 +264,7 @@ pub fn compute_output_schema(
        let field_name = ed
            .dest_column
            .clone()
-            .unwrap_or_else(|| format!("{}_embedding", ed.source_column));
+            .unwrap_or_else(|| format!("{}_embedding", &ed.source_column));

        sb.push(Field::new(
            field_name,
@@ -291,7 +291,7 @@ pub fn compute_embeddings_for_batch(
        let dst_field_name = fld
            .dest_column
            .clone()
-            .unwrap_or_else(|| format!("{}_embedding", fld.source_column));
+            .unwrap_or_else(|| format!("{}_embedding", &fld.source_column));

        let dst_field = Field::new(
            dst_field_name,
@@ -315,7 +315,7 @@ impl<R: RecordBatchReader> WithEmbeddings<R> {
                let field_name = ed
                    .dest_column
                    .clone()
-                    .unwrap_or_else(|| format!("{}_embedding", ed.source_column));
+                    .unwrap_or_else(|| format!("{}_embedding", &ed.source_column));
                Ok(Field::new(
                    field_name,
                    func.dest_type()?.into_owned(),
@@ -706,7 +706,7 @@ impl<S: HttpSend> RestfulLanceDbClient<S> {
            .err_to_http(request_id.clone())?;
        debug!(
            "Received response for request_id={}: {:?}",
-            request_id, response
+            request_id, &response
        );
        Ok((request_id, response))
    }
@@ -768,7 +768,7 @@ impl<S: HttpSend> RestfulLanceDbClient<S> {
                Ok((status, response)) if status.is_success() => {
                    debug!(
                        "Received response for request_id={}: {:?}",
-                        retry_counter.request_id, response
+                        retry_counter.request_id, &response
                    );
                    return Ok((retry_counter.request_id, response));
                }
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors

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

 use self::insert::{RemoteWriteExec, WriteOp};
@@ -3089,12 +3089,10 @@ mod tests {
            Box::pin(table.delete("false").map_ok(|_| ())),
            Box::pin(
                table
-                    .add_columns()
-                    .transform(NewColumnTransform::SqlExpressions(vec![(
-                        "x".into(),
-                        "y".into(),
-                    )]))
-                    .execute()
+                    .add_columns(
+                        NewColumnTransform::SqlExpressions(vec![("x".into(), "y".into())]),
+                        None,
+                    )
                    .map_ok(|_| ()),
            ),
            Box::pin(async {
@@ -4302,9 +4300,32 @@ 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(),
-            "requires LanceDB Cloud server 0.5.0 or newer",
+            "Use fetch_blobs for full bytes",
        );
    }

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

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

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

 //! LanceDB Table APIs

-use crate::blob::BlobFile;
 use arrow_array::{LargeBinaryArray, RecordBatch, RecordBatchReader};
 use arrow_schema::{Schema, SchemaRef};
 use async_trait::async_trait;
@@ -13,6 +12,7 @@ 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;
@@ -65,7 +65,6 @@ 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;
@@ -80,7 +79,6 @@ 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};
@@ -1622,8 +1620,12 @@ impl Table {
    }

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

    /// Change a column's name or nullability.
@@ -1,161 +0,0 @@
-// 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());
-    }
-}
@@ -576,12 +576,10 @@ mod tests {

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

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

@@ -193,12 +193,10 @@ mod tests {

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

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

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

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

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

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

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

@@ -1078,252 +1075,3 @@ 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(())
-}
Author	SHA1	Message	Date
Lu Qiu	86d3f23f53	chore: keep remote write types crate-visible	2026-07-31 17:45:27 -04:00
Lu Qiu	1c130f61da	Merge remote-tracking branch 'upstream/main' into codex/update-lance-10-1-0-beta-1 # Conflicts: # Cargo.lock # Cargo.toml # java/pom.xml	2026-07-31 17:22:33 -04:00
Lu Qiu	b36cdc72d9	chore: update lance dependency to v10.1.0-beta.1	2026-07-31 16:47:25 -04:00