Bump version: 0.37.1-beta.3 → 0.37.1

Bump version: 0.37.1-beta.2 → 0.37.1-beta.3
Bump version: 0.37.1-beta.1 → 0.37.1-beta.2
2026-08-28 00:48:40 +00:00 · 2026-08-10 07:54:42 +00:00 · 2026-08-10 07:53:53 +00:00 · 2026-08-10 06:30:45 +00:00 · 2026-08-10 14:23:41 +08:00 · 2026-08-10 14:23:33 +08:00
44 changed files with 2395 additions and 423 deletions
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.37.1-beta.0"
+current_version = "0.37.1"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
@@ -1,7 +1,8 @@
 name: Create release commit

-# This workflow increments the version, tags it, and pushes it. All SDKs share
-# a single version, so one tag releases all of them.
+# This workflow increments the version, updates lockfiles, tags the final
+# commit, and pushes it. All SDKs share a single version, so one tag releases
+# all of them.
 # When a tag is pushed, another workflow is triggered that creates a GH release
 # and uploads the binaries. This workflow is only for creating the tag.

@@ -63,6 +64,7 @@ jobs:
          pip install bump-my-version PyGithub packaging
          bash ci/bump_version.sh ${{ inputs.type }} ${{ inputs.bump-minor }}
          bash ci/update_lockfiles.sh --amend
+          bash ci/create_release_tag.sh
      - name: Push new version tag
        if: ${{ !inputs.dry_run }}
        uses: ad-m/github-push-action@881a6320fdb16eb5318c5054f31c218aec2b324c # v1.3.0
@@ -775,7 +775,7 @@ dependencies = [
 "http 0.2.12",
 "http 1.5.0",
 "http-body 1.1.0",
- "lru 0.16.4",
+ "lru",
 "percent-encoding",
 "regex-lite",
 "sha2 0.11.0",
@@ -1970,6 +1970,15 @@ dependencies = [
 "spin 0.10.1",
 ]

+[[package]]
+name = "crc32c"
+version = "0.6.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3a47af21622d091a8f0fb295b88bc886ac74efcc613efc19f5d0b21de5c89e47"
+dependencies = [
+ "rustc_version",
+]
+
 [[package]]
 name = "crc32fast"
 version = "1.5.0"
@@ -3441,12 +3450,6 @@ 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"
@@ -3455,8 +3458,9 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"

 [[package]]
 name = "fsst"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d0981ce90521824089f3cd68a48b1c4c89e9ad96d0eb74f58d6e550a3d604545"
 dependencies = [
 "arrow-array",
 "rand 0.9.5",
@@ -3813,23 +3817,14 @@ dependencies = [

 [[package]]
 name = "goosefs-sdk"
-version = "0.1.9"
+version = "0.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e1ea4eee6dcbc31b25ab4fd577adc55b677d2bed3aa3016c44c58fbe1b2298a5"
+checksum = "9ae079b88ffe7772d12cfc5c40a5a324babb357893d95b5e3a22ae857f236c5f"
 dependencies = [
- "arc-swap",
 "async-trait",
 "bytes",
 "dashmap",
- "fastrand",
- "futures",
 "hostname",
- "io-uring",
- "itoa",
- "libc",
- "lru 0.18.2",
- "memmap2 0.9.10",
- "moka",
 "prost",
 "prost-types",
 "rand 0.9.5",
@@ -3842,7 +3837,6 @@ dependencies = [
 "tonic-prost",
 "tracing",
 "uuid",
- "xxhash-rust",
 ]

 [[package]]
@@ -4815,8 +4809,9 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a"

 [[package]]
 name = "lance"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "830548f9fc92ae74b848a504282d4da06f016f2ee94b663773c2738b9cb61c42"
 dependencies = [
 "arc-swap",
 "arrow",
@@ -4890,8 +4885,9 @@ dependencies = [

 [[package]]
 name = "lance-arrow"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "24187f972374567bb3573cffd8728f2f4f7f06d644c3c5d4430b79d6b0b67300"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4913,7 +4909,8 @@ dependencies = [
 [[package]]
 name = "lance-arrow-scalar"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "771f68b04b47f3addf781116f65061808de94b05e1e9411c23c18f32d14ebe79"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4927,17 +4924,20 @@ dependencies = [
 [[package]]
 name = "lance-arrow-stats"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dd47ec33c90bf29f688fd02118e37d3a5ad5c339caa3163f89e417dc0867001f"
 dependencies = [
 "arrow-array",
 "arrow-schema",
+ "half",
 "lance-arrow-scalar",
 ]

 [[package]]
 name = "lance-bitpacking"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "55fa50ad941e25298afb54eec107c3584f80c16db4adf7a6e4e9c4b6066f4281"
 dependencies = [
 "arrayref",
 "crunchy",
@@ -4947,8 +4947,9 @@ dependencies = [

 [[package]]
 name = "lance-core"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "21f4fd872bfe948150a6878d983327c4f150dc1b629e94ae7677310fa6a3f35f"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4988,8 +4989,9 @@ dependencies = [

 [[package]]
 name = "lance-datafusion"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "230770734cd5f6fe1f1cb4a66750acad5c5a862c23c7f587d7def57c9f2c5f6b"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5019,8 +5021,9 @@ dependencies = [

 [[package]]
 name = "lance-datagen"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c0c9edcea9dbf154a3baf470595bdcdb7ef6b44dcf2b5a0c28e8815c2d4837c5"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5037,8 +5040,9 @@ dependencies = [

 [[package]]
 name = "lance-derive"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "03ac280ef94d66c2e7a4b0104e60d548f45156f114f02cd0ac57423721ec96ec"
 dependencies = [
 "proc-macro2",
 "quote",
@@ -5047,8 +5051,9 @@ dependencies = [

 [[package]]
 name = "lance-encoding"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "65b345fecf1792d4147982e9ded1cf211992a442bcf73dd17a598b1c8c9b53a5"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -5074,6 +5079,7 @@ dependencies = [
 "prost",
 "prost-build",
 "rand 0.9.5",
+ "strum 0.26.3",
 "tokio",
 "tracing",
 "xxhash-rust",
@@ -5082,8 +5088,9 @@ dependencies = [

 [[package]]
 name = "lance-file"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "203400160ecd4ac6f67f6bfdb3c186f94758ff70a6ca76d4f300c327f5c14a11"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -5114,8 +5121,9 @@ dependencies = [

 [[package]]
 name = "lance-index"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "db67792e22332a7be08d35e60ce9e4c6fb7f75f70ab1566b67b462d1aac21b13"
 dependencies = [
 "arc-swap",
 "arrow",
@@ -5182,8 +5190,9 @@ dependencies = [

 [[package]]
 name = "lance-index-core"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "49b5700d71f43e5da2057908f3243a6bc01247b5dd12247313f789c280155aae"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -5205,8 +5214,9 @@ dependencies = [

 [[package]]
 name = "lance-io"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4b8a6872b9bff95e75e223e04011feebd990d8784878eaf5df73c86d6acebb47"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5218,6 +5228,7 @@ dependencies = [
 "bytes",
 "chrono",
 "futures",
+ "goosefs-sdk",
 "http 1.5.0",
 "io-uring",
 "lance-arrow",
@@ -5242,8 +5253,9 @@ dependencies = [

 [[package]]
 name = "lance-linalg"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5a1dd49fdf61da86650dc335fbe1f239803f9d73bc2bc5ffbc0c905dd8809892"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -5259,8 +5271,9 @@ dependencies = [

 [[package]]
 name = "lance-namespace"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1449221f599147e570bec6e09eaea6ce6b9286f632e00a27f945dd0c6b70ccd8"
 dependencies = [
 "arrow",
 "async-trait",
@@ -5272,8 +5285,9 @@ dependencies = [

 [[package]]
 name = "lance-namespace-impls"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c30bff40ab9a9a58313818ab97241cff7bab2b90b8d65039908425a065a797de"
 dependencies = [
 "arrow",
 "arrow-ipc",
@@ -5327,8 +5341,9 @@ dependencies = [

 [[package]]
 name = "lance-select"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c66c5cb12ed194c7c8e427a0e90e990cdbc7159edba2bfc7b7e8db2c90c747af"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -5343,8 +5358,9 @@ dependencies = [

 [[package]]
 name = "lance-table"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6cd2a39f2e288d1acecf887cb9cc655711fb67bcf3b24a2034158dbac7a6f60e"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5383,8 +5399,9 @@ dependencies = [

 [[package]]
 name = "lance-testing"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0847352699e869a465b49bd49ecbc467bc5a3dcb168757bf39368362aad05f99"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -5397,13 +5414,14 @@ dependencies = [

 [[package]]
 name = "lance-tokenizer"
-version = "11.0.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "254c1e9287789c8d744f93f2010a8389a5ea3fcedc0dddf7649c4117ec830c57"
 dependencies = [
- "frostem",
 "icu_segmenter",
 "jieba-rs",
 "lindera",
+ "rust-stemmers",
 "serde",
 "stop-words",
 "unicode-normalization",
@@ -5411,7 +5429,7 @@ dependencies = [

 [[package]]
 name = "lancedb"
-version = "0.37.1-beta.0"
+version = "0.37.1"
 dependencies = [
 "ahash",
 "anyhow",
@@ -5447,7 +5465,6 @@ dependencies = [
 "datafusion-physical-plan",
 "datafusion-sql",
 "futures",
- "goosefs-sdk",
 "half",
 "hf-hub",
 "http 1.5.0",
@@ -5480,6 +5497,7 @@ dependencies = [
 "random_word",
 "regex",
 "reqwest 0.12.28",
+ "roaring",
 "rstest",
 "semver",
 "serde",
@@ -5499,7 +5517,7 @@ dependencies = [

 [[package]]
 name = "lancedb-nodejs"
-version = "0.37.1-beta.0"
+version = "0.37.1"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -5524,7 +5542,7 @@ dependencies = [

 [[package]]
 name = "lancedb-python"
-version = "0.37.1-beta.0"
+version = "0.37.1"
 dependencies = [
 "arrow",
 "async-trait",
@@ -5681,7 +5699,7 @@ dependencies = [
 "serde",
 "serde_json",
 "serde_yaml_ng",
- "strum",
+ "strum 0.28.0",
 "strum_macros 0.28.0",
 "unicode-blocks",
 "unicode-normalization",
@@ -5711,7 +5729,7 @@ dependencies = [
 "rkyv",
 "serde",
 "serde_json",
- "strum",
+ "strum 0.28.0",
 "strum_macros 0.28.0",
 "thiserror 2.0.18",
 ]
@@ -5783,15 +5801,6 @@ 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"
@@ -6429,9 +6438,9 @@ dependencies = [

 [[package]]
 name = "object_store_opendal"
-version = "0.58.0"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "88f165780495c17aa3ce86846600504198c3fffd99073521552751c2430fa6ac"
+checksum = "0eb12a624a41fce745838d0ef3701ff6c47797c13cd18ad3612fd2a3134fdbd8"
 dependencies = [
 "async-trait",
 "bytes",
@@ -6492,13 +6501,12 @@ checksum = "d6790f58c7ff633d8771f42965289203411a5e5c68388703c06e14f24770b41e"

 [[package]]
 name = "opendal"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4f20562cc7447fcc915fc5c23df305a412ea80a733c9f2fd9e2d267e2815be6d"
+checksum = "96c9c85ce253ff87225e7669979d877a20c98a06604ec9d6dd5f4473e08f1ae1"
 dependencies = [
 "ctor 1.0.12",
 "opendal-core",
- "opendal-http-transport-reqwest",
 "opendal-layer-concurrent-limit",
 "opendal-layer-logging",
 "opendal-layer-retry",
@@ -6515,22 +6523,24 @@ dependencies = [

 [[package]]
 name = "opendal-core"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ec75551ff4cf3e57da98979f6a937aaa9ddb3915bf68cc17d03df733be6646ed"
+checksum = "c4f8607c90e2c963a91467f50fb49fbc7fb3d573f88cea219ca59ccd3740b309"
 dependencies = [
 "anyhow",
- "base64 0.23.1",
+ "base64 0.22.1",
 "bytes",
 "futures",
 "http 1.5.0",
+ "http-body 1.1.0",
 "jiff",
 "log",
 "md-5 0.11.0",
 "mea",
 "percent-encoding",
- "quick-xml 0.41.0",
+ "quick-xml 0.39.4",
 "reqsign-core",
+ "reqwest 0.13.4",
 "serde",
 "serde_json",
 "tokio",
@@ -6539,25 +6549,11 @@ dependencies = [
 "web-time",
 ]

-[[package]]
-name = "opendal-http-transport-reqwest"
-version = "0.58.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ad4d4f19c3ce01126a30611f8e544eaa217104a278c889ac17c9374fe4f9e4ef"
-dependencies = [
- "bytes",
- "futures",
- "http 1.5.0",
- "http-body 1.1.0",
- "opendal-core",
- "reqwest 0.13.4",
-]
-
 [[package]]
 name = "opendal-layer-concurrent-limit"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "249ac5b0aa5a7a6c3737342d10456067937f9c9a6f3f02544271f7908ab91081"
+checksum = "0d6f81ba6960e3fae1882f253b114b21d7e444e1534f209c7737a79f6243eb6f"
 dependencies = [
 "futures",
 "http 1.5.0",
@@ -6567,9 +6563,9 @@ dependencies = [

 [[package]]
 name = "opendal-layer-logging"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5c75411ab00f77851ff086b686c1e9ca8175ac18c15afa2cb75b9036436cb06c"
+checksum = "58ada45c6d81d1aa4c9305d0c7d4bc317c59c85866a0908a2d75a7a978aa5ee2"
 dependencies = [
 "log",
 "opendal-core",
@@ -6577,9 +6573,9 @@ dependencies = [

 [[package]]
 name = "opendal-layer-retry"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "80b7738bd5f233ad8da39af9b9316b9b7a4eaddd91e8e32a1e19b7030688121d"
+checksum = "7b2a25a718afb81fad81cb9a0580a1cb989221fa2317f888c6a37f8dad408eb7"
 dependencies = [
 "backon",
 "log",
@@ -6588,9 +6584,9 @@ dependencies = [

 [[package]]
 name = "opendal-layer-timeout"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a704141924500f3803c05ed871b53305d2a2f11cb5ef20160c3ee688a1857f66"
+checksum = "1e91f731724c213af81e9d03517859c8fc47b4578e64ad61ae4f099f10fe36e3"
 dependencies = [
 "opendal-core",
 "tokio",
@@ -6598,17 +6594,17 @@ dependencies = [

 [[package]]
 name = "opendal-service-azblob"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b3310fbbb48f111c6f590473c2cd15e1b7f8e384444b0d4e328f0464c864d767"
+checksum = "0030644366ef5d8cbe3a4a5822bf99a4aafddc1666e9d24b44d158d9062fc76a"
 dependencies = [
- "base64 0.23.1",
+ "base64 0.22.1",
 "bytes",
 "http 1.5.0",
 "log",
 "opendal-core",
 "opendal-service-azure-common",
- "quick-xml 0.41.0",
+ "quick-xml 0.39.4",
 "reqsign-azure-storage",
 "reqsign-core",
 "reqsign-file-read-tokio",
@@ -6619,18 +6615,17 @@ dependencies = [

 [[package]]
 name = "opendal-service-azdls"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2e3c406729935fe214ce574d68681a1ff7e0b322548f14094912bdbfe50e5c53"
+checksum = "6dea4908d490143a9b0b7f7a790e139ff829b06a023f670455ed3d44f664b361"
 dependencies = [
- "base64 0.23.1",
+ "base64 0.22.1",
 "bytes",
 "http 1.5.0",
 "log",
- "mea",
 "opendal-core",
 "opendal-service-azure-common",
- "quick-xml 0.41.0",
+ "quick-xml 0.39.4",
 "reqsign-azure-storage",
 "reqsign-core",
 "reqsign-file-read-tokio",
@@ -6640,9 +6635,9 @@ dependencies = [

 [[package]]
 name = "opendal-service-azure-common"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7348c88edf15af435b7be930077746b569fac5e738c1bf6a363b675e7317c9df"
+checksum = "9b489f13c42e69d69bdd72952b634356ec43a7881a20259b38b540fcecdf4051"
 dependencies = [
 "http 1.5.0",
 "opendal-core",
@@ -6650,15 +6645,15 @@ dependencies = [

 [[package]]
 name = "opendal-service-cos"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d533d4582105d269c8aebeee5f0e8bcf960f41b8aab6197df7012254d9f39bf0"
+checksum = "aa8cafe9729213375c7331019b0cb756ad3e1aff7f45cd32c45eae91ebde8901"
 dependencies = [
 "bytes",
 "http 1.5.0",
 "log",
 "opendal-core",
- "quick-xml 0.41.0",
+ "quick-xml 0.39.4",
 "reqsign-core",
 "reqsign-file-read-tokio",
 "reqsign-tencent-cos",
@@ -6667,9 +6662,9 @@ dependencies = [

 [[package]]
 name = "opendal-service-gcs"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "007f3fba63c21e516c956b891e96ff9892d8175662bfb781cdada9d3766a11e6"
+checksum = "48de101aac565ed06af4b47903c24eafd249075553ec1fb18256751c45148d47"
 dependencies = [
 "async-trait",
 "bytes",
@@ -6677,7 +6672,7 @@ dependencies = [
 "log",
 "opendal-core",
 "percent-encoding",
- "quick-xml 0.41.0",
+ "quick-xml 0.39.4",
 "reqsign-core",
 "reqsign-file-read-tokio",
 "reqsign-google",
@@ -6688,9 +6683,9 @@ dependencies = [

 [[package]]
 name = "opendal-service-goosefs"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "60871e6386f04d831e6a5bdbc032af4a91aeba49963252d0ef456a2cf36a9b78"
+checksum = "69e43048bde419947ba826fbdc2f134d6c03f44ebf48bd33a03b72f9fc45fcb4"
 dependencies = [
 "bytes",
 "goosefs-sdk",
@@ -6702,9 +6697,9 @@ dependencies = [

 [[package]]
 name = "opendal-service-hf"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b41fd41eb7ed03c5e66cefda61e8e117808ffd2908f2916737cb020a6beb02c7"
+checksum = "c4922661976a1d40794a2adfbdb888cc3c23097690f825a92f773af38908a848"
 dependencies = [
 "bytes",
 "hf-xet",
@@ -6712,21 +6707,22 @@ dependencies = [
 "log",
 "opendal-core",
 "percent-encoding",
+ "reqwest 0.13.4",
 "serde",
 "serde_json",
 ]

 [[package]]
 name = "opendal-service-oss"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cd528ec2d49c5ca69e674ffed7b3e0686fb9cfcfea0596870de381467fda4f1b"
+checksum = "328fa55e8888cbdfe00826bfea2a79042422b720e8369e9e021e46121dea5ace"
 dependencies = [
 "bytes",
 "http 1.5.0",
 "log",
 "opendal-core",
- "quick-xml 0.41.0",
+ "quick-xml 0.39.4",
 "reqsign-aliyun-oss",
 "reqsign-core",
 "reqsign-file-read-tokio",
@@ -6735,18 +6731,18 @@ dependencies = [

 [[package]]
 name = "opendal-service-s3"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "58e80cdf192d7eff05feed747894d64f81905ac4eaf132edf7ea270abdd2d663"
+checksum = "313d46c9f5ae70bca26b7c3e3fbb9b639292625f28af73aa016f47e788af9deb"
 dependencies = [
- "base64 0.23.1",
+ "base64 0.22.1",
 "bytes",
- "crc-fast",
+ "crc32c",
 "http 1.5.0",
 "log",
 "md-5 0.11.0",
 "opendal-core",
- "quick-xml 0.41.0",
+ "quick-xml 0.39.4",
 "reqsign-aws-v4",
 "reqsign-core",
 "reqsign-file-read-tokio",
@@ -8679,6 +8675,16 @@ 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"
@@ -9552,6 +9558,15 @@ 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"
@@ -9574,6 +9589,19 @@ 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"
@@ -13,20 +13,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"

 [workspace.dependencies]
-lance = { "version" = "=11.0.0-beta.2", default-features = false, "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=11.0.0-beta.2", default-features = false, "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=11.0.0-beta.2", default-features = false, "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=10.0.0", default-features = false }
+lance-core = "=10.0.0"
+lance-datagen = "=10.0.0"
+lance-file = "=10.0.0"
+lance-io = { "version" = "=10.0.0", default-features = false }
+lance-index = "=10.0.0"
+lance-linalg = "=10.0.0"
+lance-namespace = "=10.0.0"
+lance-namespace-impls = { "version" = "=10.0.0", default-features = false }
+lance-table = "=10.0.0"
+lance-testing = "=10.0.0"
+lance-datafusion = "=10.0.0"
+lance-encoding = "=10.0.0"
+lance-arrow = "=10.0.0"
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "58.0.0", optional = false }
@@ -6,16 +6,11 @@ HEAD_SHA=$(git rev-parse HEAD)

 readonly TAG_PREFIX="v"
 readonly SELF_DIR=$(cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )
+readonly BUMP_ARGS="--no-tag"

 PREV_TAG=$(git tag --sort='version:refname' | grep ^$TAG_PREFIX | python $SELF_DIR/semver_sort.py $TAG_PREFIX | tail -n 1)
 echo "Found previous tag $PREV_TAG"

-# Initially, we don't want to tag if we are doing stable, because we will bump
-# again later. See comment at end for why.
-if [[ "$RELEASE_TYPE" == 'stable' ]]; then
-  BUMP_ARGS="--no-tag"
-fi
-
 # If last is stable and not bumping minor
 if [[ $PREV_TAG != *beta* ]]; then
    if [[ "$BUMP_MINOR" != "false" ]]; then
@@ -39,12 +34,12 @@ fi
 # a stable version, bump the pre-release level ("pre_l") to make it stable.
 if [[ $RELEASE_TYPE == 'stable' ]]; then
  # X.Y.Z-beta.N -> X.Y.Z
-  bump-my-version bump -vv pre_l
+  bump-my-version bump -vv $BUMP_ARGS pre_l
 fi

 # Validate that we have incremented version appropriately for breaking changes
-NEW_TAG=$(git describe --tags --exact-match HEAD)
-NEW_VERSION=$(echo $NEW_TAG | sed "s/^$TAG_PREFIX//")
+NEW_VERSION=$(python -c 'import tomllib; print(tomllib.load(open(".bumpversion.toml", "rb"))["tool"]["bumpversion"]["current_version"])')
+NEW_TAG="$TAG_PREFIX$NEW_VERSION"
 LAST_STABLE_RELEASE=$(git tag --sort='version:refname' | grep ^$TAG_PREFIX | grep -v beta | grep -vF "$NEW_TAG" | python $SELF_DIR/semver_sort.py $TAG_PREFIX | tail -n 1)
 LAST_STABLE_VERSION=$(echo $LAST_STABLE_RELEASE | sed "s/^$TAG_PREFIX//")

@@ -0,0 +1,21 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+RELEASE_VERSION=$(python -c 'import tomllib; print(tomllib.load(open(".bumpversion.toml", "rb"))["tool"]["bumpversion"]["current_version"])')
+RELEASE_TAG="v${RELEASE_VERSION}"
+
+if git rev-parse --quiet --verify "refs/tags/${RELEASE_TAG}" >/dev/null; then
+  echo "Release tag ${RELEASE_TAG} already exists" >&2
+  exit 1
+fi
+
+git tag --annotate "$RELEASE_TAG" --message "Release ${RELEASE_TAG}"
+
+HEAD_SHA=$(git rev-parse HEAD)
+TAG_SHA=$(git rev-parse "refs/tags/${RELEASE_TAG}^{}")
+if [[ "$TAG_SHA" != "$HEAD_SHA" ]]; then
+  echo "Release tag ${RELEASE_TAG} points to ${TAG_SHA}, expected ${HEAD_SHA}" >&2
+  exit 1
+fi
+
+echo "Created ${RELEASE_TAG} at ${HEAD_SHA}"
@@ -0,0 +1,72 @@
+import tempfile
+import unittest
+from pathlib import Path
+
+from validate_stable_lance import validate
+
+
+class ValidateStableLanceTest(unittest.TestCase):
+    def write_fixture(
+        self,
+        root: Path,
+        *,
+        rust: str = "=10.0.0",
+        python: str = "10.0.0",
+        java: str = "10.0.0",
+    ) -> None:
+        (root / "python").mkdir()
+        (root / "java").mkdir()
+        (root / "Cargo.toml").write_text(
+            f'[workspace.dependencies]\nlance = "{rust}"\nlance-core = "{rust}"\n'
+        )
+        (root / "python" / "pyproject.toml").write_text(
+            '[project.optional-dependencies]\ntests = ["pylance==' + python + '"]\n'
+        )
+        (root / "java" / "pom.xml").write_text(
+            "<project><properties><lance-core.version>"
+            + java
+            + "</lance-core.version></properties></project>"
+        )
+
+    def test_accepts_matching_stable_versions(self) -> None:
+        with tempfile.TemporaryDirectory() as temp_dir:
+            root = Path(temp_dir)
+            self.write_fixture(root)
+            self.assertEqual(validate(root), "10.0.0")
+
+    def test_rejects_prerelease(self) -> None:
+        with tempfile.TemporaryDirectory() as temp_dir:
+            root = Path(temp_dir)
+            self.write_fixture(root, python="10.0.0rc1")
+            with self.assertRaisesRegex(ValueError, "not stable"):
+                validate(root)
+
+    def test_rejects_sdk_mismatch(self) -> None:
+        with tempfile.TemporaryDirectory() as temp_dir:
+            root = Path(temp_dir)
+            self.write_fixture(root, java="9.0.0")
+            with self.assertRaisesRegex(ValueError, "do not match across SDKs"):
+                validate(root)
+
+    def test_rejects_non_exact_rust_dependency(self) -> None:
+        with tempfile.TemporaryDirectory() as temp_dir:
+            root = Path(temp_dir)
+            self.write_fixture(root, rust="10.0.0")
+            with self.assertRaisesRegex(ValueError, "not exact"):
+                validate(root)
+
+    def test_rejects_unpublished_rust_source(self) -> None:
+        with tempfile.TemporaryDirectory() as temp_dir:
+            root = Path(temp_dir)
+            self.write_fixture(root)
+            (root / "Cargo.toml").write_text(
+                "[workspace.dependencies]\n"
+                'lance = { version = "=10.0.0", git = "https://example.com/lance", '
+                'tag = "v10.0.0" }\n'
+            )
+            with self.assertRaisesRegex(ValueError, "unpublished source fields"):
+                validate(root)
+
+
+if __name__ == "__main__":
+    unittest.main()
@@ -1,34 +1,112 @@
+#!/usr/bin/env python3
+"""Validate that every SDK uses the same published stable Lance release."""
+
+from __future__ import annotations
+
+import re
+import xml.etree.ElementTree as ET
+from pathlib import Path
+
 import tomllib

-found_preview_lance = False
+STABLE_VERSION = re.compile(r"[0-9]+\.[0-9]+\.[0-9]+")

-with open("Cargo.toml", "rb") as f:
-    cargo_data = tomllib.load(f)

-    for name, dep in cargo_data["workspace"]["dependencies"].items():
-        if name == "lance" or name.startswith("lance-"):
-            if isinstance(dep, str):
-                version = dep
-            elif isinstance(dep, dict):
-                # Version doesn't have the beta tag in it, so we instead look
-                # at the git tag.
-                version = dep.get('tag', dep.get('version'))
-            else:
-                raise ValueError("Unexpected type for dependency: " + str(dep))
+def _stable_version(raw: str, *, dependency: str, exact: bool = False) -> str:
+    value = raw.strip()
+    if exact and not value.startswith("="):
+        raise ValueError(f"Dependency '{dependency}' is not exact: {raw}")
+    value = value.removeprefix("=").removeprefix("v")
+    if STABLE_VERSION.fullmatch(value) is None:
+        raise ValueError(f"Dependency '{dependency}' is not stable: {raw}")
+    return value

-            if "beta" in version:
-                found_preview_lance = True
-                print(f"Dependency '{name}' is a preview version: {version}")

-with open("python/pyproject.toml", "rb") as f:
-    py_proj_data = tomllib.load(f)
+def rust_lance_version(repo_root: Path) -> str:
+    with (repo_root / "Cargo.toml").open("rb") as cargo_file:
+        dependencies = tomllib.load(cargo_file)["workspace"]["dependencies"]

-    for dep in py_proj_data["project"]["dependencies"]:
-        if dep.startswith("pylance"):
-            if "b" in dep:
-                found_preview_lance = True
-                print(f"Dependency '{dep}' is a preview version")
-            break  # Only one pylance dependency
+    versions: dict[str, str] = {}
+    for name, dependency in dependencies.items():
+        if name != "lance" and not name.startswith("lance-"):
+            continue

-if found_preview_lance:
-    raise ValueError("Found preview version of Lance in dependencies")
+        if isinstance(dependency, str):
+            raw_version = dependency
+        elif isinstance(dependency, dict):
+            forbidden_sources = [
+                source
+                for source in ("git", "path", "branch", "rev", "tag")
+                if source in dependency
+            ]
+            if forbidden_sources:
+                joined = ", ".join(forbidden_sources)
+                raise ValueError(
+                    f"Dependency '{name}' uses unpublished source fields: {joined}"
+                )
+            raw_version = dependency.get("version")
+            if raw_version is None:
+                raise ValueError(f"Dependency '{name}' has no version")
+        else:
+            raise TypeError(f"Dependency '{name}' has an unexpected definition")
+
+        versions[name] = _stable_version(raw_version, dependency=name, exact=True)
+
+    if not versions:
+        raise ValueError("No Rust Lance dependencies found")
+    unique_versions = set(versions.values())
+    if len(unique_versions) != 1:
+        details = ", ".join(f"{name}={version}" for name, version in versions.items())
+        raise ValueError(f"Rust Lance dependency versions do not match: {details}")
+    return unique_versions.pop()
+
+
+def python_lance_version(repo_root: Path) -> str:
+    with (repo_root / "python" / "pyproject.toml").open("rb") as pyproject_file:
+        pyproject = tomllib.load(pyproject_file)
+
+    requirements = pyproject["project"]["optional-dependencies"]["tests"]
+    pylance_requirements = [
+        requirement for requirement in requirements if requirement.startswith("pylance")
+    ]
+    if len(pylance_requirements) != 1:
+        raise ValueError(
+            "Expected exactly one pylance requirement in the Python test dependencies"
+        )
+
+    requirement = pylance_requirements[0]
+    prefix = "pylance=="
+    if not requirement.startswith(prefix):
+        raise ValueError(f"Python test dependency is not exact: {requirement}")
+    return _stable_version(requirement[len(prefix) :], dependency="pylance")
+
+
+def java_lance_version(repo_root: Path) -> str:
+    pom_root = ET.parse(repo_root / "java" / "pom.xml").getroot()
+    versions = [
+        element.text
+        for element in pom_root.iter()
+        if element.tag.rsplit("}", 1)[-1] == "lance-core.version"
+    ]
+    if len(versions) != 1 or versions[0] is None:
+        raise ValueError("Expected exactly one Java lance-core.version property")
+    return _stable_version(versions[0], dependency="Java lance-core")
+
+
+def validate(repo_root: Path) -> str:
+    versions = {
+        "Rust": rust_lance_version(repo_root),
+        "Python": python_lance_version(repo_root),
+        "Java": java_lance_version(repo_root),
+    }
+    if len(set(versions.values())) != 1:
+        details = ", ".join(f"{sdk}={version}" for sdk, version in versions.items())
+        raise ValueError(
+            f"Lance dependency versions do not match across SDKs: {details}"
+        )
+    return versions["Rust"]
+
+
+if __name__ == "__main__":
+    version = validate(Path(__file__).resolve().parents[1])
+    print(f"Validated published stable Lance v{version} across Rust, Python, and Java")
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
 <dependency>
    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-core</artifactId>
-    <version>0.37.1-beta.0</version>
+    <version>0.37.1</version>
 </dependency>
 ```

@@ -44,4 +44,7 @@ The number of rows in the table
 totalBytes: number;
 ```

-The total number of bytes in the table
+The total size, in bytes, of the table's data files, index files, and
+overlay files
+
+Read from the manifest, so this excludes deletion files and manifests.
@@ -8,7 +8,7 @@
    <parent>
      <groupId>com.lancedb</groupId>
      <artifactId>lancedb-parent</artifactId>
-      <version>0.37.1-beta.0</version>
+      <version>0.37.1-final.0</version>
      <relativePath>../pom.xml</relativePath>
    </parent>

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

    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-parent</artifactId>
-    <version>0.37.1-beta.0</version>
+    <version>0.37.1-final.0</version>
    <packaging>pom</packaging>
    <name>${project.artifactId}</name>
    <description>LanceDB Java SDK Parent POM</description>
@@ -28,7 +28,7 @@
    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>11.0.0-beta.2</lance-core.version>
+        <lance-core.version>10.0.0</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>
@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.37.1-beta.0"
+version = "0.37.1"
 publish = false
 license.workspace = true
 description.workspace = true
@@ -6,7 +6,9 @@ import * as arrow17 from "apache-arrow-17";
 import * as arrow18 from "apache-arrow-18";

 import {
+  Vector as CurrentVector,
  convertToTable,
+  tableFromIPC as currentTableFromIPC,
  fromBufferToRecordBatch,
  fromDataToBuffer,
  fromRecordBatchToBuffer,
@@ -19,6 +21,7 @@ import {
  FunctionOptions,
 } from "../lancedb/embedding/embedding_function";
 import { EmbeddingFunctionConfig } from "../lancedb/embedding/registry";
+import { sanitizeTable } from "../lancedb/sanitize";

 // biome-ignore lint/suspicious/noExplicitAny: skip
 function sampleRecords(): Array<Record<string, any>> {
@@ -64,7 +67,11 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
      tableFromIPC,
      DataType,
      Dictionary,
+      RecordBatch: ArrowRecordBatch,
+      Table: ArrowTable,
      Uint8: ArrowUint8,
+      makeData: arrowMakeData,
+      vectorFromArray,
      // biome-ignore lint/suspicious/noExplicitAny: <explanation>
    } = <any>arrow;
    type Schema = ApacheArrow["Schema"];
@@ -1054,6 +1061,114 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
    });

    describe("when using two versions of arrow", function () {
+      it("preserves a dictionary shared by multiple fields", async function () {
+        const values = ["alpha", "beta", "alpha"];
+        const dictionaryVector = vectorFromArray(values);
+        const batch = new ArrowRecordBatch({
+          first: dictionaryVector.data[0],
+          second: dictionaryVector.data[0],
+        });
+        const table = new ArrowTable([batch]);
+
+        const sanitized = sanitizeTable(table);
+        expect([...sanitized.getChild("first")!]).toEqual(values);
+        expect([...sanitized.getChild("second")!]).toEqual(values);
+        const firstType = sanitized.schema.fields[0].type as {
+          dictionary: unknown;
+        };
+        const secondType = sanitized.schema.fields[1].type as {
+          dictionary: unknown;
+        };
+        expect(secondType.dictionary).toBe(firstType.dictionary);
+        expect(sanitized.batches[0].data.children[1].dictionary).toBe(
+          sanitized.batches[0].data.children[0].dictionary,
+        );
+
+        const buf = await fromDataToBuffer(table);
+        const actual = currentTableFromIPC(buf);
+        expect([...actual.getChild("first")!]).toEqual(values);
+        expect([...actual.getChild("second")!]).toEqual(values);
+      });
+
+      it("preserves shared dictionary data from another Arrow version", async function () {
+        const values = ["alpha", "beta", "alpha"];
+        const dictionaryVector = vectorFromArray(values);
+        const firstBatch = new ArrowRecordBatch({
+          label: dictionaryVector.slice(0, 2).data[0],
+        });
+        const secondBatch = new ArrowRecordBatch({
+          label: dictionaryVector.slice(2).data[0],
+        });
+        const table = new ArrowTable([firstBatch, secondBatch]);
+
+        const sanitized = sanitizeTable(table);
+        expect([...sanitized.getChild("label")!]).toEqual(values);
+
+        const dictionaries = sanitized.batches.map(
+          (batch) => batch.data.children[0].dictionary,
+        );
+        expect(dictionaries[0]).toBeInstanceOf(CurrentVector);
+        expect(dictionaries[1]).toBe(dictionaries[0]);
+
+        const buf = await fromDataToBuffer(table);
+        const actual = currentTableFromIPC(buf);
+        expect([...actual.getChild("label")!]).toEqual(values);
+      });
+
+      it("preserves shared chunks in growing dictionaries", async function () {
+        const type = new Dictionary(new Utf8(), new Int32(), 42, false);
+        const firstDictionary = vectorFromArray(["alpha", "beta"], new Utf8());
+        const secondDictionary = firstDictionary.concat(
+          vectorFromArray(["gamma"], new Utf8()),
+        );
+        const firstData = arrowMakeData({
+          type,
+          data: Int32Array.from([0, 1]),
+          dictionary: firstDictionary,
+        });
+        const secondData = arrowMakeData({
+          type,
+          data: Int32Array.from([2]),
+          dictionary: secondDictionary,
+        });
+        const table = new ArrowTable([
+          new ArrowRecordBatch({ label: firstData }),
+          new ArrowRecordBatch({ label: secondData }),
+        ]);
+
+        const sanitized = sanitizeTable(table);
+        const expected = ["alpha", "beta", "gamma"];
+        expect([...sanitized.getChild("label")!]).toEqual(expected);
+        const firstLocalDictionary =
+          sanitized.batches[0].data.children[0].dictionary!;
+        const secondLocalDictionary =
+          sanitized.batches[1].data.children[0].dictionary!;
+        expect(secondLocalDictionary.data[0]).toBe(
+          firstLocalDictionary.data[0],
+        );
+
+        const buf = await fromTableToBuffer(sanitized);
+        const actual = currentTableFromIPC(buf);
+        expect([...actual.getChild("label")!]).toEqual(expected);
+      });
+
+      it("can serialize list data from another Arrow version", async function () {
+        const values = [["anime", "action"], [], null];
+        const vector = vectorFromArray(
+          values,
+          new List(new Field("item", new Utf8(), true)),
+        );
+        const table = new ArrowTable({ tags: vector });
+
+        const buf = await fromDataToBuffer(table);
+        const actual = currentTableFromIPC(buf);
+        const actualTags = actual.getChild("tags");
+
+        expect(actualTags?.get(0)?.toJSON()).toEqual(values[0]);
+        expect(actualTags?.get(1)?.toJSON()).toEqual(values[1]);
+        expect(actualTags?.get(2)).toBeNull();
+      });
+
      it("can still import data", async function () {
        const schema = new arrow15.Schema([
          new arrow15.Field("id", new arrow15.Int32()),
@@ -277,8 +277,16 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
        },
        numIndices: 0,
        numRows: 3,
-        totalBytes: 44,
+        // Full on-disk size of the two data files, footers and metadata included.
+        totalBytes: 684,
      });
+
+      // Index files count toward totalBytes too (only deletion files and
+      // manifests are excluded).
+      await table.createIndex("id", { config: Index.btree() });
+      const statsWithIndex = await table.stats();
+      expect(statsWithIndex.numIndices).toBe(1);
+      expect(statsWithIndex.totalBytes).toBeGreaterThan(684);
    });

    it("should overwrite data if asked", async () => {
@@ -9,7 +9,7 @@
 // comes from the exact same library instance.  This is not always the case
 // and so we must sanitize the input to ensure that it is compatible.

-import { BufferType, Data } from "apache-arrow";
+import { BufferType, Data, Vector } from "apache-arrow";
 import type { IntBitWidth, TKeys, TimeBitWidth } from "apache-arrow/type";
 import {
  Binary,
@@ -74,6 +74,20 @@ import {
  Utf8,
 } from "./arrow";

+type SanitizationContext = {
+  types: WeakMap<object, DataType>;
+  vectors: WeakMap<object, Vector>;
+  data: WeakMap<object, Data<DataType>>;
+};
+
+function createSanitizationContext(): SanitizationContext {
+  return {
+    types: new WeakMap(),
+    vectors: new WeakMap(),
+    data: new WeakMap(),
+  };
+}
+
 export function sanitizeMetadata(
  metadataLike?: unknown,
 ): Map<string, string> | undefined {
@@ -186,6 +200,13 @@ export function sanitizeInterval(typeLike: object) {
 }

 export function sanitizeList(typeLike: object) {
+  return sanitizeListWithContext(typeLike, createSanitizationContext());
+}
+
+function sanitizeListWithContext(
+  typeLike: object,
+  context: SanitizationContext,
+) {
  if (!("children" in typeLike) || !Array.isArray(typeLike.children)) {
    throw Error(
      "Expected a List type to have an array-like `children` property",
@@ -194,19 +215,35 @@ export function sanitizeList(typeLike: object) {
  if (typeLike.children.length !== 1) {
    throw Error("Expected a List type to have exactly one child");
  }
-  return new List(sanitizeField(typeLike.children[0]));
+  return new List(sanitizeFieldWithContext(typeLike.children[0], context));
 }

 export function sanitizeStruct(typeLike: object) {
+  return sanitizeStructWithContext(typeLike, createSanitizationContext());
+}
+
+function sanitizeStructWithContext(
+  typeLike: object,
+  context: SanitizationContext,
+) {
  if (!("children" in typeLike) || !Array.isArray(typeLike.children)) {
    throw Error(
      "Expected a Struct type to have an array-like `children` property",
    );
  }
-  return new Struct(typeLike.children.map((child) => sanitizeField(child)));
+  return new Struct(
+    typeLike.children.map((child) => sanitizeFieldWithContext(child, context)),
+  );
 }

 export function sanitizeUnion(typeLike: object) {
+  return sanitizeUnionWithContext(typeLike, createSanitizationContext());
+}
+
+function sanitizeUnionWithContext(
+  typeLike: object,
+  context: SanitizationContext,
+) {
  if (
    !("typeIds" in typeLike) ||
    !("mode" in typeLike) ||
@@ -226,7 +263,7 @@ export function sanitizeUnion(typeLike: object) {
    typeLike.mode,
    // biome-ignore lint/suspicious/noExplicitAny: skip
    typeLike.typeIds as any,
-    typeLike.children.map((child) => sanitizeField(child)),
+    typeLike.children.map((child) => sanitizeFieldWithContext(child, context)),
  );
 }

@@ -234,6 +271,19 @@ export function sanitizeTypedUnion(
  typeLike: object,
  // eslint-disable-next-line @typescript-eslint/naming-convention
  UnionType: typeof DenseUnion | typeof SparseUnion,
+) {
+  return sanitizeTypedUnionWithContext(
+    typeLike,
+    UnionType,
+    createSanitizationContext(),
+  );
+}
+
+function sanitizeTypedUnionWithContext(
+  typeLike: object,
+  // eslint-disable-next-line @typescript-eslint/naming-convention
+  UnionType: typeof DenseUnion | typeof SparseUnion,
+  context: SanitizationContext,
 ) {
  if (!("typeIds" in typeLike)) {
    throw Error(
@@ -248,7 +298,7 @@ export function sanitizeTypedUnion(

  return new UnionType(
    typeLike.typeIds as Int32Array | number[],
-    typeLike.children.map((child) => sanitizeField(child)),
+    typeLike.children.map((child) => sanitizeFieldWithContext(child, context)),
  );
 }

@@ -262,6 +312,16 @@ export function sanitizeFixedSizeBinary(typeLike: object) {
 }

 export function sanitizeFixedSizeList(typeLike: object) {
+  return sanitizeFixedSizeListWithContext(
+    typeLike,
+    createSanitizationContext(),
+  );
+}
+
+function sanitizeFixedSizeListWithContext(
+  typeLike: object,
+  context: SanitizationContext,
+) {
  if (!("listSize" in typeLike) || typeof typeLike.listSize !== "number") {
    throw Error("Expected a FixedSizeList type to have a `listSize` property");
  }
@@ -275,11 +335,18 @@ export function sanitizeFixedSizeList(typeLike: object) {
  }
  return new FixedSizeList(
    typeLike.listSize,
-    sanitizeField(typeLike.children[0]),
+    sanitizeFieldWithContext(typeLike.children[0], context),
  );
 }

 export function sanitizeMap(typeLike: object) {
+  return sanitizeMapWithContext(typeLike, createSanitizationContext());
+}
+
+function sanitizeMapWithContext(
+  typeLike: object,
+  context: SanitizationContext,
+) {
  if (!("children" in typeLike) || !Array.isArray(typeLike.children)) {
    throw Error(
      "Expected a Map type to have an array-like `children` property",
@@ -292,7 +359,10 @@ export function sanitizeMap(typeLike: object) {
    throw Error("Expected a Map type to have exactly one child");
  }

-  return new Map_(sanitizeField(typeLike.children[0]), typeLike.keysSorted);
+  return new Map_(
+    sanitizeFieldWithContext(typeLike.children[0], context),
+    typeLike.keysSorted,
+  );
 }

 export function sanitizeDuration(typeLike: object) {
@@ -303,6 +373,13 @@ export function sanitizeDuration(typeLike: object) {
 }

 export function sanitizeDictionary(typeLike: object) {
+  return sanitizeDictionaryWithContext(typeLike, createSanitizationContext());
+}
+
+function sanitizeDictionaryWithContext(
+  typeLike: object,
+  context: SanitizationContext,
+) {
  if (!("id" in typeLike) || typeof typeLike.id !== "number") {
    throw Error("Expected a Dictionary type to have an `id` property");
  }
@@ -316,8 +393,8 @@ export function sanitizeDictionary(typeLike: object) {
    throw Error("Expected a Dictionary type to have an `isOrdered` property");
  }
  return new Dictionary(
-    sanitizeType(typeLike.dictionary),
-    sanitizeType(typeLike.indices) as TKeys,
+    sanitizeTypeWithContext(typeLike.dictionary, context),
+    sanitizeTypeWithContext(typeLike.indices, context) as TKeys,
    typeLike.id,
    typeLike.isOrdered,
  );
@@ -325,12 +402,23 @@ export function sanitizeDictionary(typeLike: object) {

 // biome-ignore lint/suspicious/noExplicitAny: skip
 export function sanitizeType(typeLike: unknown): DataType<any> {
+  return sanitizeTypeWithContext(typeLike, createSanitizationContext());
+}
+
+function sanitizeTypeWithContext(
+  typeLike: unknown,
+  context: SanitizationContext,
+): DataType {
  if (typeof typeLike === "string") {
    return dataTypeFromName(typeLike);
  }
  if (typeof typeLike !== "object" || typeLike === null) {
    throw Error("Expected a Type but object was null/undefined");
  }
+  const cached = context.types.get(typeLike);
+  if (cached !== undefined) {
+    return cached;
+  }
  if (
    !("typeId" in typeLike) ||
    !(
@@ -349,6 +437,16 @@ export function sanitizeType(typeLike: unknown): DataType<any> {
    throw Error("Type's typeId property was not a function or number");
  }

+  const type = sanitizeTypeById(typeLike, typeId, context);
+  context.types.set(typeLike, type);
+  return type;
+}
+
+function sanitizeTypeById(
+  typeLike: object,
+  typeId: Type,
+  context: SanitizationContext,
+): DataType {
  switch (typeId) {
    case Type.NONE:
      throw Error("Received a Type with a typeId of NONE");
@@ -375,21 +473,21 @@ export function sanitizeType(typeLike: unknown): DataType<any> {
    case Type.Interval:
      return sanitizeInterval(typeLike);
    case Type.List:
-      return sanitizeList(typeLike);
+      return sanitizeListWithContext(typeLike, context);
    case Type.Struct:
-      return sanitizeStruct(typeLike);
+      return sanitizeStructWithContext(typeLike, context);
    case Type.Union:
-      return sanitizeUnion(typeLike);
+      return sanitizeUnionWithContext(typeLike, context);
    case Type.FixedSizeBinary:
      return sanitizeFixedSizeBinary(typeLike);
    case Type.FixedSizeList:
-      return sanitizeFixedSizeList(typeLike);
+      return sanitizeFixedSizeListWithContext(typeLike, context);
    case Type.Map:
-      return sanitizeMap(typeLike);
+      return sanitizeMapWithContext(typeLike, context);
    case Type.Duration:
      return sanitizeDuration(typeLike);
    case Type.Dictionary:
-      return sanitizeDictionary(typeLike);
+      return sanitizeDictionaryWithContext(typeLike, context);
    case Type.Int8:
      return new Int8();
    case Type.Int16:
@@ -433,9 +531,9 @@ export function sanitizeType(typeLike: unknown): DataType<any> {
    case Type.TimestampSecond:
      return sanitizeTypedTimestamp(typeLike, TimestampSecond);
    case Type.DenseUnion:
-      return sanitizeTypedUnion(typeLike, DenseUnion);
+      return sanitizeTypedUnionWithContext(typeLike, DenseUnion, context);
    case Type.SparseUnion:
-      return sanitizeTypedUnion(typeLike, SparseUnion);
+      return sanitizeTypedUnionWithContext(typeLike, SparseUnion, context);
    case Type.IntervalDayTime:
      return new IntervalDayTime();
    case Type.IntervalYearMonth:
@@ -454,6 +552,13 @@ export function sanitizeType(typeLike: unknown): DataType<any> {
 }

 export function sanitizeField(fieldLike: unknown): Field {
+  return sanitizeFieldWithContext(fieldLike, createSanitizationContext());
+}
+
+function sanitizeFieldWithContext(
+  fieldLike: unknown,
+  context: SanitizationContext,
+): Field {
  if (fieldLike instanceof Field) {
    return fieldLike;
  }
@@ -471,7 +576,7 @@ export function sanitizeField(fieldLike: unknown): Field {
  }
  let type: DataType;
  try {
-    type = sanitizeType(fieldLike.type);
+    type = sanitizeTypeWithContext(fieldLike.type, context);
  } catch (error: unknown) {
    throw Error(
      `Unable to sanitize type for field: ${fieldLike.name} due to error: ${error}`,
@@ -501,6 +606,13 @@ export function sanitizeField(fieldLike: unknown): Field {
 * than lancedb is using.
 */
 export function sanitizeSchema(schemaLike: SchemaLike): Schema {
+  return sanitizeSchemaWithContext(schemaLike, createSanitizationContext());
+}
+
+function sanitizeSchemaWithContext(
+  schemaLike: SchemaLike,
+  context: SanitizationContext,
+): Schema {
  if (schemaLike instanceof Schema) {
    return schemaLike;
  }
@@ -522,7 +634,7 @@ export function sanitizeSchema(schemaLike: SchemaLike): Schema {
    );
  }
  const sanitizedFields = schemaLike.fields.map((field) =>
-    sanitizeField(field),
+    sanitizeFieldWithContext(field, context),
  );
  return new Schema(sanitizedFields, metadata);
 }
@@ -544,13 +656,18 @@ export function sanitizeTable(tableLike: TableLike): Table {
      "The table passed in does not appear to be a table (no 'columns' property)",
    );
  }
-  const schema = sanitizeSchema(tableLike.schema);
-
-  const batches = tableLike.batches.map(sanitizeRecordBatch);
+  const context = createSanitizationContext();
+  const schema = sanitizeSchemaWithContext(tableLike.schema, context);
+  const batches = tableLike.batches.map((batch) =>
+    sanitizeRecordBatch(batch, context),
+  );
  return new Table(schema, batches);
 }

-function sanitizeRecordBatch(batchLike: RecordBatchLike): RecordBatch {
+function sanitizeRecordBatch(
+  batchLike: RecordBatchLike,
+  context: SanitizationContext,
+): RecordBatch {
  if (batchLike instanceof RecordBatch) {
    return batchLike;
  }
@@ -567,19 +684,43 @@ function sanitizeRecordBatch(batchLike: RecordBatchLike): RecordBatch {
      "The record batch passed in does not appear to be a record batch (no 'data' property)",
    );
  }
-  const schema = sanitizeSchema(batchLike.schema);
-  const data = sanitizeData(batchLike.data);
+  const schema = sanitizeSchemaWithContext(batchLike.schema, context);
+  const data = sanitizeData(batchLike.data, context) as Data<Struct>;
  return new RecordBatch(schema, data);
 }
+
+type DictionaryVectorLike = {
+  data: readonly DataLike[];
+};
+
+type DictionaryDataLike = DataLike & {
+  dictionary?: DictionaryVectorLike;
+};
+
 function sanitizeData(
  dataLike: DataLike,
-  // biome-ignore lint/suspicious/noExplicitAny: <explanation>
-): import("apache-arrow").Data<Struct<any>> {
+  context: SanitizationContext,
+): Data<DataType> {
  if (dataLike instanceof Data) {
    return dataLike;
  }
-  return new Data(
-    dataLike.type,
+  const cachedData = context.data.get(dataLike);
+  if (cachedData !== undefined) {
+    return cachedData;
+  }
+  const dictionaryLike = (dataLike as DictionaryDataLike).dictionary;
+  let dictionary: Vector | undefined;
+  if (dictionaryLike !== undefined) {
+    dictionary = context.vectors.get(dictionaryLike);
+    if (dictionary === undefined) {
+      dictionary = new Vector(
+        dictionaryLike.data.map((data) => sanitizeData(data, context)),
+      );
+      context.vectors.set(dictionaryLike, dictionary);
+    }
+  }
+  const data = new Data(
+    sanitizeTypeWithContext(dataLike.type, context),
    dataLike.offset,
    dataLike.length,
    dataLike.nullCount,
@@ -589,7 +730,11 @@ function sanitizeData(
      [BufferType.VALIDITY]: dataLike.nullBitmap,
      [BufferType.TYPE]: dataLike.typeIds,
    },
+    dataLike.children.map((child) => sanitizeData(child, context)),
+    dictionary,
  );
+  context.data.set(dataLike, data);
+  return data;
 }

 const constructorsByTypeName = {
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.37.1-beta.0",
+	"version": "0.37.1",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.37.1-beta.0",
+	"version": "0.37.1",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.37.1-beta.0",
+	"version": "0.37.1",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.37.1-beta.0",
+	"version": "0.37.1",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.37.1-beta.0",
+	"version": "0.37.1",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",
@@ -1,6 +1,6 @@
 {
  "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.37.1-beta.0",
+  "version": "0.37.1",
  "os": [
    "win32"
  ],
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.37.1-beta.0",
+	"version": "0.37.1",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",
@@ -1,12 +1,12 @@
 {
  "name": "@lancedb/lancedb",
-  "version": "0.37.1-beta.0",
+  "version": "0.37.1",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "@lancedb/lancedb",
-      "version": "0.37.1-beta.0",
+      "version": "0.37.1",
      "cpu": [
        "x64",
        "arm64"
@@ -11,7 +11,7 @@
    "ann"
  ],
  "private": false,
-  "version": "0.37.1-beta.0",
+  "version": "0.37.1",
  "main": "dist/index.js",
  "exports": {
    ".": "./dist/index.js",
@@ -1043,7 +1043,10 @@ impl From<lancedb::index::IndexStatistics> for IndexStatistics {

 #[napi(object)]
 pub struct TableStatistics {
-    /// The total number of bytes in the table
+    /// The total size, in bytes, of the table's data files, index files, and
+    /// overlay files
+    ///
+    /// Read from the manifest, so this excludes deletion files and manifests.
    pub total_bytes: i64,

    /// The number of rows in the table
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.37.1-beta.0"
+version = "0.37.1"
 publish = false
 edition.workspace = true
 description = "Python bindings for LanceDB"
@@ -63,7 +63,7 @@ tests = [
    "polars>=0.19, <=1.32.3",
    "pyarrow<25",
    "pyarrow-stubs>=16.0",
-    "pylance==9.0.0rc1",
+    "pylance==10.0.0",
    "requests>=2.31.0",
    "datafusion>=54,<55",
    "opentelemetry-sdk>=1.30.0",
@@ -355,6 +355,10 @@ class Table:
    async def set_lsm_write_spec(self, spec: LsmWriteSpec) -> None: ...
    async def unset_lsm_write_spec(self) -> None: ...
    async def get_lsm_write_spec(self) -> Optional[LsmWriteSpec]: ...
+    async def checkpoint_lsm(self) -> None: ...
+    async def flush_lsm(self) -> None: ...
+    async def compact_lsm(self) -> None: ...
+    async def get_lsm_stats(self, include_generation_rows: bool) -> Optional[dict]: ...
    async def close_lsm_writers(self) -> None: ...
    @property
    def tags(self) -> Tags: ...
@@ -183,11 +183,7 @@ class EmbeddingFunction(BaseModel, ABC):
    def VectorField(self, **kwargs):
        """
        Creates a pydantic Field that can automatically annotate
-        the target vector column for this embedding function.
-
-        The field can be annotated as ``list[float]`` for compatibility with
-        static type checkers. LanceDB will infer the fixed vector dimension from
-        this embedding function.
+        the target vector column for this embedding function
        """
        return Field(json_schema_extra={"vector_column_for": self}, **kwargs)

@@ -87,12 +87,13 @@ class JinaEmbeddings(EmbeddingFunction):
        if isinstance(image, bytes):
            image_dict = {"image": base64.b64encode(image).decode("utf-8")}
        elif isinstance(image, (str, Path)):
-            parsed = urlparse.urlparse(image)
-            # TODO handle drive letter on windows.
+            parsed = urlparse(str(image))
            PIL_Image = attempt_import_or_raise("PIL.Image", "pillow")
            if parsed.scheme == "file":
                pil_image = PIL_Image.open(parsed.path)
-            elif parsed.scheme == "":
+            elif parsed.scheme == "" or (os.name == "nt" and len(parsed.scheme) == 1):
+                # A Windows drive letter parses as a one-character scheme
+                # ("C:\\img.png" -> scheme="c"), so treat it as a local path.
                pil_image = PIL_Image.open(image if os.name == "nt" else parsed.path)
            elif parsed.scheme.startswith("http"):
                pil_image = PIL_Image.open(io.BytesIO(url_retrieve(image)))
@@ -99,17 +99,6 @@ def Vector(
    ...     pa.field("url", pa.utf8(), False),
    ...     pa.field("embeddings", pa.list_(pa.float32(), 768))
    ... ])
-
-    Notes
-    -----
-    ``Vector`` creates a type dynamically, so calls such as ``Vector(768)`` are
-    not valid static type annotations. For an embedding field, use the standard
-    ``list[float]`` annotation when running mypy; ``VectorField`` supplies the
-    fixed dimension to LanceDB::
-
-        class MyModel(LanceModel):
-            text: str = embeddings.SourceField()
-            vector: list[float] = embeddings.VectorField()
    """

    # TODO: make a public parameterized type.
@@ -390,10 +379,6 @@ def _unwrap_optional_annotation(annotation: Any) -> Any | None:

 def _pydantic_to_arrow_type(field: FieldInfo) -> pa.DataType:
    """Convert a Pydantic FieldInfo to Arrow DataType"""
-    embedding_vector_type = _embedding_vector_to_arrow_type(field)
-    if embedding_vector_type is not None:
-        return embedding_vector_type
-
    unwrapped = _unwrap_optional_annotation(field.annotation)
    if unwrapped is not None:
        return _pydantic_type_to_arrow_type(unwrapped, field)
@@ -407,32 +392,8 @@ def _pydantic_to_arrow_type(field: FieldInfo) -> pa.DataType:
    return _pydantic_type_to_arrow_type(field.annotation, field)


-def _embedding_vector_to_arrow_type(field: FieldInfo) -> pa.DataType | None:
-    """Infer a fixed-size vector type from ``VectorField`` metadata."""
-    if not _is_embedding_vector_annotation(field):
-        return None
-
-    function = get_extras(field, "vector_column_for")
-    return pa.list_(pa.float32(), function.ndims())
-
-
-def _is_embedding_vector_annotation(field: FieldInfo) -> bool:
-    if get_extras(field, "vector_column_for") is None:
-        return False
-
-    annotation = _unwrap_optional_annotation(field.annotation)
-    if annotation is None:
-        annotation = field.annotation
-
-    origin = getattr(annotation, "__origin__", None)
-    args = getattr(annotation, "__args__", ())
-    return origin is list and args == (float,)
-
-
 def is_nullable(field: FieldInfo) -> bool:
    """Check if a Pydantic FieldInfo is nullable."""
-    if _is_embedding_vector_annotation(field):
-        return True
    if _unwrap_optional_annotation(field.annotation) is not None:
        return True
    if isinstance(field.annotation, (_GenericAlias, GenericAlias)):
@@ -3976,6 +3976,28 @@ class LanceTable(Table):
        [`AsyncTable.get_lsm_write_spec`][lancedb.AsyncTable.get_lsm_write_spec]."""
        return LOOP.run(self._table.get_lsm_write_spec())

+    def checkpoint_lsm(self) -> None:
+        """Synchronous version of
+        [`AsyncTable.checkpoint_lsm`][lancedb.AsyncTable.checkpoint_lsm]."""
+        return LOOP.run(self._table.checkpoint_lsm())
+
+    def flush_lsm(self) -> None:
+        """Synchronous version of
+        [`AsyncTable.flush_lsm`][lancedb.AsyncTable.flush_lsm]."""
+        return LOOP.run(self._table.flush_lsm())
+
+    def compact_lsm(self) -> None:
+        """Synchronous version of
+        [`AsyncTable.compact_lsm`][lancedb.AsyncTable.compact_lsm]."""
+        return LOOP.run(self._table.compact_lsm())
+
+    def get_lsm_stats(self, *, include_generation_rows: bool = False) -> Optional[dict]:
+        """Synchronous version of
+        [`AsyncTable.get_lsm_stats`][lancedb.AsyncTable.get_lsm_stats]."""
+        return LOOP.run(
+            self._table.get_lsm_stats(include_generation_rows=include_generation_rows)
+        )
+
    def close_lsm_writers(self) -> None:
        """Close cached MemWAL shard writers. See
        [`AsyncTable.close_lsm_writers`][lancedb.AsyncTable.close_lsm_writers]."""
@@ -4686,6 +4708,67 @@ class AsyncTable:
        """
        return await self._inner.get_lsm_write_spec()

+    async def checkpoint_lsm(self) -> None:
+        """Converge this table's LSM write path into its base table.
+
+        One flush, sealing every memtable into L0, then compaction triggers
+        until every generation that existed at that moment has reached base.
+        The loop runs client-side, reading progress from ``get_lsm_stats``.
+
+        Best-effort: generations created *while* it runs are deliberately not
+        waited on, which is what lets it terminate on a table taking writes.
+        Idempotent and safe on a cadence.
+
+        There is no deadline, and the caller owns that. It returns when the
+        target generations are gone, raises on a terminal server fault, and
+        otherwise waits however long the server takes. A slow table and a
+        stuck one are the same picture from the client: the compactor pool is
+        shared across every table on the node, so a checkpoint queued behind
+        unrelated work looks exactly like one that is merging. Wrap this in
+        ``asyncio.wait_for`` for a wall-clock bound; abandoning it partway
+        costs nothing.
+        """
+        return await self._inner.checkpoint_lsm()
+
+    async def flush_lsm(self) -> None:
+        """Seal every bucket's active memtable into L0.
+
+        Does not touch the base table — moving L0 into base is
+        `compact_lsm`. On a node that has not claimed this table, this claims
+        it and replays its WAL log first.
+        """
+        return await self._inner.flush_lsm()
+
+    async def compact_lsm(self) -> None:
+        """Trigger a background L0 to base compaction pass per bucket.
+
+        Returns once the passes are dispatched, not once they finish: watch
+        ``get_lsm_stats`` for progress, or use ``checkpoint_lsm`` to loop
+        until the current L0 has reached base.
+        """
+        return await self._inner.compact_lsm()
+
+    async def get_lsm_stats(
+        self, *, include_generation_rows: bool = False
+    ) -> Optional[dict]:
+        """Read live per-bucket LSM state.
+
+        Answers "how far behind is my fresh tier", "which bucket is hot", and
+        "why is my fresh-tier vector search brute-force". Mutates no table
+        state, though on a node that has not claimed this table it claims it,
+        exactly as a read would.
+
+        Returns ``None`` only when the LSM write path is not enabled.
+
+        Parameters
+        ----------
+        include_generation_rows
+            Report a row count per L0 generation. Off by default: each count
+            opens an uncached Lance dataset, and ``checkpoint_lsm`` polls this
+            needing only generation numbers.
+        """
+        return await self._inner.get_lsm_stats(include_generation_rows)
+
    async def close_lsm_writers(self) -> None:
        """Drain and close any cached MemWAL shard writers for this table.

@@ -6251,7 +6334,9 @@ class TableStatistics:
    Attributes
    ----------
    total_bytes: int
-        The total number of bytes in the table.
+        The total size, in bytes, of the table's data files, index files, and
+        overlay files. Read from the manifest, so this excludes deletion files
+        and manifests.
    num_rows: int
        The total number of rows in the table.
    num_indices: int
@@ -631,3 +631,23 @@ def test_url_retrieve_downloads_image():
    image_bytes = url_retrieve(image_url)
    img = Image.open(io.BytesIO(image_bytes))
    assert img.size[0] > 0 and img.size[1] > 0
+
+
+def test_jina_generate_image_input_dict_local_path(tmp_path):
+    """
+    JinaEmbeddings._generate_image_input_dict must accept a local image path
+    (str or Path), not just bytes. Previously it crashed with
+    `AttributeError: 'function' object has no attribute 'urlparse'` on any
+    str/Path input because it called `urlparse.urlparse(image)` instead of
+    `urlparse(image)` (urlparse was imported as a function, not a module).
+    """
+    Image = pytest.importorskip("PIL.Image")
+    from lancedb.embeddings.jinaai import JinaEmbeddings
+
+    image_path = tmp_path / "test.png"
+    Image.new("RGB", (4, 4), color="red").save(image_path, format="PNG")
+
+    for image in (str(image_path), image_path):
+        image_dict = JinaEmbeddings._generate_image_input_dict(image)
+        assert "image" in image_dict
+        assert isinstance(image_dict["image"], str) and len(image_dict["image"]) > 0
@@ -9,7 +9,6 @@ from typing import List, Optional, Tuple
 import pyarrow as pa
 import pydantic
 import pytest
-from lancedb.conftest import MockTextEmbeddingFunction
 from lancedb.pydantic import (
    PYDANTIC_VERSION,
    LanceModel,
@@ -427,25 +426,6 @@ def test_bare_vector_raises_clear_error():
        exec("class TestModel(LanceModel):\n    vector: Vector", namespace)


-def test_embedding_vector_list_annotation():
-    embedding = MockTextEmbeddingFunction.create()
-
-    class StaticTypingModel(LanceModel):
-        text: str = embedding.SourceField()
-        vector: list[float] = embedding.VectorField()
-
-    schema = pydantic_to_schema(StaticTypingModel)
-    assert schema == pa.schema(
-        [
-            pa.field("text", pa.utf8(), False),
-            pa.field("vector", pa.list_(pa.float32(), embedding.ndims()), True),
-        ]
-    )
-
-    model = StaticTypingModel(text="hello", vector=[0.0] * embedding.ndims())
-    assert model.vector == [0.0] * embedding.ndims()
-
-
 def test_fixed_size_list_field():
    class TestModel(pydantic.BaseModel):
        vec: Vector(16)
@@ -3713,7 +3713,8 @@ def test_stats(mem_db: DBConnection):
    stats = table.stats()
    print(f"{stats=}")
    assert stats == {
-        "total_bytes": 60,
+        # Full on-disk size of the data file, footer and metadata included.
+        "total_bytes": 633,
        "num_rows": 2,
        "num_indices": 0,
        "fragment_stats": {
@@ -3731,6 +3732,13 @@ def test_stats(mem_db: DBConnection):
        },
    }

+    # Index files count toward total_bytes too (only deletion files and
+    # manifests are excluded).
+    table.create_index("id", config=BTree())
+    stats_with_index = table.stats()
+    assert stats_with_index["num_indices"] == 1
+    assert stats_with_index["total_bytes"] > stats["total_bytes"]
+

 def test_create_table_empty_list_with_schema(mem_db: DBConnection):
    """Test creating table with empty list data and schema
@@ -28,11 +28,72 @@ use pyo3::{
    Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python,
    exceptions::{PyRuntimeError, PyValueError},
    pyclass, pyfunction, pymethods,
-    types::{IntoPyDict, PyAnyMethods, PyBytes, PyDict, PyDictMethods},
+    types::{IntoPyDict, PyAnyMethods, PyBytes, PyDict, PyDictMethods, PyList, PyListMethods},
 };

 mod scannable;

+/// Convert `LsmStats` to a Python dict, preserving the per-bucket list.
+///
+/// Deliberately not flattened to a table-level summary: a table is N
+/// buckets on one node, and the per-bucket detail is the reason the
+/// endpoint exists — flattening hides the single hot bucket someone opened
+/// it to find.
+fn lsm_stats_to_py(py: Python<'_>, stats: &lancedb::table::LsmStats) -> PyResult<Py<PyDict>> {
+    let out = PyDict::new(py);
+    let buckets = PyList::empty(py);
+    for b in &stats.buckets {
+        let e = PyDict::new(py);
+        e.set_item("shard_id", &b.shard_id)?;
+        e.set_item("status", &b.status)?;
+        e.set_item("writer_epoch", b.writer_epoch)?;
+        e.set_item("manifest_version", b.manifest_version)?;
+        e.set_item("current_generation", b.current_generation)?;
+        e.set_item(
+            "replay_after_wal_entry_position",
+            b.replay_after_wal_entry_position,
+        )?;
+        e.set_item(
+            "wal_entry_position_last_seen",
+            b.wal_entry_position_last_seen,
+        )?;
+
+        let generations = PyList::empty(py);
+        for g in &b.generations {
+            let ge = PyDict::new(py);
+            ge.set_item("generation", g.generation)?;
+            ge.set_item("bytes", g.bytes)?;
+            ge.set_item("rows", g.rows)?;
+            generations.append(ge)?;
+        }
+        e.set_item("generations", generations)?;
+        e.set_item("compacting", b.compacting)?;
+
+        e.set_item(
+            "memtables",
+            b.memtables
+                .as_ref()
+                .map(|ms| {
+                    let l = PyList::empty(py);
+                    for m in ms {
+                        let d = PyDict::new(py);
+                        d.set_item("generation", m.generation)?;
+                        d.set_item("rows", m.rows)?;
+                        d.set_item("bytes", m.bytes)?;
+                        d.set_item("batches", m.batches)?;
+                        d.set_item("indexes", m.indexes.clone())?;
+                        l.append(d)?;
+                    }
+                    PyResult::Ok(l.unbind())
+                })
+                .transpose()?,
+        )?;
+        buckets.append(e)?;
+    }
+    out.set_item("buckets", buckets)?;
+    Ok(out.unbind())
+}
+
 #[derive(FromPyObject)]
 enum PredicateArg {
    Expr(PyExpr),
@@ -1339,6 +1400,51 @@ impl Table {
        })
    }

+    /// Converge the table's LSM write path into its base table.
+    ///
+    /// Best-effort: with writes flowing, new rows may land after the last
+    /// pass. Errors if the table stops making progress.
+    pub fn checkpoint_lsm(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.inner_ref()?.clone();
+        future_into_py(self_.py(), async move {
+            inner.checkpoint_lsm().await.infer_error()
+        })
+    }
+
+    /// Seal every bucket's active memtable into L0.
+    pub fn flush_lsm(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.inner_ref()?.clone();
+        future_into_py(
+            self_.py(),
+            async move { inner.flush_lsm().await.infer_error() },
+        )
+    }
+
+    /// Trigger a background L0 → base pass per bucket. Returns once the
+    /// passes are dispatched, not once they finish — watch `get_lsm_stats`.
+    pub fn compact_lsm(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.inner_ref()?.clone();
+        future_into_py(self_.py(), async move {
+            inner.compact_lsm().await.infer_error()
+        })
+    }
+
+    /// Live LSM state, or `None` when the LSM write path is not enabled.
+    #[pyo3(signature = (include_generation_rows=false))]
+    pub fn get_lsm_stats(
+        self_: PyRef<'_, Self>,
+        include_generation_rows: bool,
+    ) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.inner_ref()?.clone();
+        future_into_py(self_.py(), async move {
+            let stats = inner
+                .get_lsm_stats(include_generation_rows)
+                .await
+                .infer_error()?;
+            Python::attach(|py| stats.map(|s| lsm_stats_to_py(py, &s)).transpose())
+        })
+    }
+
    pub fn close_lsm_writers(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
        let inner = self_.inner_ref()?.clone();
        future_into_py(self_.py(), async move {
@@ -799,7 +799,7 @@ name = "cuda-bindings"
 version = "13.3.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "cuda-pathfinder", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
+    { name = "cuda-pathfinder" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/a9/21/8464d133752951c154feafb3b65c297e7d80f301183d220bec4c830f1441/cuda_bindings-13.3.1-cp310-cp310-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:120fcc53d57903df529c3486962c56528cba5b7d6c57c99537320ed9922c8b86", size = 6073403, upload-time = "2026-05-29T23:11:36.22Z" },
@@ -834,37 +834,37 @@ wheels = [

 [package.optional-dependencies]
 cublas = [
-    { name = "nvidia-cublas", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-cublas" },
 ]
 cudart = [
-    { name = "nvidia-cuda-runtime", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-cuda-runtime" },
 ]
 cufft = [
-    { name = "nvidia-cufft", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-cufft" },
 ]
 cufile = [
-    { name = "nvidia-cufile", marker = "sys_platform == 'linux'" },
+    { name = "nvidia-cufile" },
 ]
 cupti = [
-    { name = "nvidia-cuda-cupti", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-cuda-cupti" },
 ]
 curand = [
-    { name = "nvidia-curand", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-curand" },
 ]
 cusolver = [
-    { name = "nvidia-cusolver", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-cusolver" },
 ]
 cusparse = [
-    { name = "nvidia-cusparse", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-cusparse" },
 ]
 nvjitlink = [
-    { name = "nvidia-nvjitlink", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-nvjitlink" },
 ]
 nvrtc = [
-    { name = "nvidia-cuda-nvrtc", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-cuda-nvrtc" },
 ]
 nvtx = [
-    { name = "nvidia-nvtx", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-nvtx" },
 ]

 [[package]]
@@ -1023,7 +1023,7 @@ name = "exceptiongroup"
 version = "1.3.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "typing-extensions", marker = "python_full_version < '3.11'" },
+    { name = "typing-extensions" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/50/79/66800aadf48771f6b62f7eb014e352e5d06856655206165d775e675a02c9/exceptiongroup-1.3.1.tar.gz", hash = "sha256:8b412432c6055b0b7d14c310000ae93352ed6754f70fa8f7c34141f91c4e3219", size = 30371, upload-time = "2025-11-21T23:01:54.787Z" }
 wheels = [
@@ -1440,16 +1440,16 @@ resolution-markers = [
    "python_full_version < '3.11'",
 ]
 dependencies = [
-    { name = "cachetools", marker = "python_full_version < '3.11'" },
-    { name = "certifi", marker = "python_full_version < '3.11'" },
-    { name = "httpx", marker = "python_full_version < '3.11'" },
-    { name = "ibm-cos-sdk", marker = "python_full_version < '3.11'" },
-    { name = "lomond", marker = "python_full_version < '3.11'" },
-    { name = "packaging", marker = "python_full_version < '3.11'" },
-    { name = "pandas", version = "2.2.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
-    { name = "requests", marker = "python_full_version < '3.11'" },
-    { name = "tabulate", marker = "python_full_version < '3.11'" },
-    { name = "urllib3", marker = "python_full_version < '3.11'" },
+    { name = "cachetools" },
+    { name = "certifi" },
+    { name = "httpx" },
+    { name = "ibm-cos-sdk" },
+    { name = "lomond" },
+    { name = "packaging" },
+    { name = "pandas", version = "2.2.3", source = { registry = "https://pypi.org/simple" } },
+    { name = "requests" },
+    { name = "tabulate" },
+    { name = "urllib3" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/c7/56/2e3df38a1f13062095d7bde23c87a92f3898982993a15186b1bfecbd206f/ibm_watsonx_ai-1.3.42.tar.gz", hash = "sha256:ee5be59009004245d957ce97d1227355516df95a2640189749487614fef674ff", size = 688651, upload-time = "2025-10-01T13:35:41.527Z" }
 wheels = [
@@ -1468,17 +1468,17 @@ resolution-markers = [
    "python_full_version == '3.11.*'",
 ]
 dependencies = [
-    { name = "cachetools", marker = "python_full_version >= '3.11'" },
-    { name = "certifi", marker = "python_full_version >= '3.11'" },
-    { name = "httpx", marker = "python_full_version >= '3.11'" },
-    { name = "ibm-cos-sdk", marker = "python_full_version >= '3.11'" },
-    { name = "lomond", marker = "python_full_version >= '3.11'" },
-    { name = "packaging", marker = "python_full_version >= '3.11'" },
-    { name = "pandas", version = "2.3.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.11' and python_full_version < '3.14'" },
+    { name = "cachetools" },
+    { name = "certifi" },
+    { name = "httpx" },
+    { name = "ibm-cos-sdk" },
+    { name = "lomond" },
+    { name = "packaging" },
+    { name = "pandas", version = "2.3.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.14'" },
    { name = "pandas", version = "3.0.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.14'" },
-    { name = "requests", marker = "python_full_version >= '3.11'" },
-    { name = "tabulate", marker = "python_full_version >= '3.11'" },
-    { name = "urllib3", marker = "python_full_version >= '3.11'" },
+    { name = "requests" },
+    { name = "tabulate" },
+    { name = "urllib3" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/29/a3/c756b534696ab2f3f29882fdb7ca7198b7a5c94e10c0a3a327853d6d6b79/ibm_watsonx_ai-1.5.14.tar.gz", hash = "sha256:a756488bd57e87c0fc51be42dcba871143cfe0ac1e805c497c5047e1e4f13e9d", size = 735804, upload-time = "2026-06-22T12:32:43.85Z" }
 wheels = [
@@ -1554,17 +1554,17 @@ resolution-markers = [
    "python_full_version < '3.11'",
 ]
 dependencies = [
-    { name = "colorama", marker = "python_full_version < '3.11' and sys_platform == 'win32'" },
-    { name = "decorator", marker = "python_full_version < '3.11'" },
-    { name = "exceptiongroup", marker = "python_full_version < '3.11'" },
-    { name = "jedi", marker = "python_full_version < '3.11'" },
-    { name = "matplotlib-inline", marker = "python_full_version < '3.11'" },
-    { name = "pexpect", marker = "python_full_version < '3.11' and sys_platform != 'emscripten' and sys_platform != 'win32'" },
-    { name = "prompt-toolkit", marker = "python_full_version < '3.11'" },
-    { name = "pygments", marker = "python_full_version < '3.11'" },
-    { name = "stack-data", marker = "python_full_version < '3.11'" },
-    { name = "traitlets", marker = "python_full_version < '3.11'" },
-    { name = "typing-extensions", marker = "python_full_version < '3.11'" },
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "decorator" },
+    { name = "exceptiongroup" },
+    { name = "jedi" },
+    { name = "matplotlib-inline" },
+    { name = "pexpect", marker = "sys_platform != 'emscripten' and sys_platform != 'win32'" },
+    { name = "prompt-toolkit" },
+    { name = "pygments" },
+    { name = "stack-data" },
+    { name = "traitlets" },
+    { name = "typing-extensions" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/40/18/f8598d287006885e7136451fdea0755af4ebcbfe342836f24deefaed1164/ipython-8.39.0.tar.gz", hash = "sha256:4110ae96012c379b8b6db898a07e186c40a2a1ef5d57a7fa83166047d9da7624", size = 5513971, upload-time = "2026-03-27T10:02:13.94Z" }
 wheels = [
@@ -1583,18 +1583,18 @@ resolution-markers = [
    "python_full_version == '3.11.*'",
 ]
 dependencies = [
-    { name = "colorama", marker = "python_full_version >= '3.11' and sys_platform == 'win32'" },
-    { name = "decorator", marker = "python_full_version >= '3.11'" },
-    { name = "ipython-pygments-lexers", marker = "python_full_version >= '3.11'" },
-    { name = "jedi", marker = "python_full_version >= '3.11'" },
-    { name = "matplotlib-inline", marker = "python_full_version >= '3.11'" },
-    { name = "pexpect", marker = "python_full_version >= '3.11' and sys_platform != 'emscripten' and sys_platform != 'win32'" },
-    { name = "prompt-toolkit", marker = "python_full_version >= '3.11'" },
-    { name = "psutil", marker = "python_full_version >= '3.11' and sys_platform != 'cygwin' and sys_platform != 'emscripten'" },
-    { name = "pygments", marker = "python_full_version >= '3.11'" },
-    { name = "stack-data", marker = "python_full_version >= '3.11'" },
-    { name = "traitlets", marker = "python_full_version >= '3.11'" },
-    { name = "typing-extensions", marker = "python_full_version == '3.11.*'" },
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "decorator" },
+    { name = "ipython-pygments-lexers" },
+    { name = "jedi" },
+    { name = "matplotlib-inline" },
+    { name = "pexpect", marker = "sys_platform != 'emscripten' and sys_platform != 'win32'" },
+    { name = "prompt-toolkit" },
+    { name = "psutil", marker = "sys_platform != 'cygwin' and sys_platform != 'emscripten'" },
+    { name = "pygments" },
+    { name = "stack-data" },
+    { name = "traitlets" },
+    { name = "typing-extensions", marker = "python_full_version < '3.12'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/53/59/165d3b4d75cc34add3122c4417ecb229085140ac573103c223cd01dde96f/ipython-9.15.0.tar.gz", hash = "sha256:da2819ce2aa83135257df830660b1176d986c3d2876db24df01974fa955b2756", size = 4442580, upload-time = "2026-06-26T11:03:35.913Z" }
 wheels = [
@@ -1606,7 +1606,7 @@ name = "ipython-pygments-lexers"
 version = "1.1.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "pygments", marker = "python_full_version >= '3.11'" },
+    { name = "pygments" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/ef/4c/5dd1d8af08107f88c7f741ead7a40854b8ac24ddf9ae850afbcf698aa552/ipython_pygments_lexers-1.1.1.tar.gz", hash = "sha256:09c0138009e56b6854f9535736f4171d855c8c08a563a0dcd8022f78355c7e81", size = 8393, upload-time = "2025-01-17T11:24:34.505Z" }
 wheels = [
@@ -2005,7 +2005,7 @@ requires-dist = [
    { name = "pyarrow-stubs", marker = "extra == 'tests'", specifier = ">=16.0" },
    { name = "pydantic", specifier = ">=1.10" },
    { name = "pylance", marker = "extra == 'pylance'", specifier = ">=5.0.0b5" },
-    { name = "pylance", marker = "extra == 'tests'", specifier = "==9.0.0rc1" },
+    { name = "pylance", marker = "extra == 'tests'", specifier = "==10.0.0" },
    { name = "pyright", marker = "extra == 'dev'", specifier = ">=1.1.350" },
    { name = "pytest", marker = "extra == 'tests'", specifier = ">=7.0" },
    { name = "pytest-asyncio", marker = "extra == 'tests'", specifier = ">=0.21" },
@@ -2858,7 +2858,7 @@ name = "nvidia-cudnn-cu13"
 version = "9.19.0.56"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
+    { name = "nvidia-cublas" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/f1/84/26025437c1e6b61a707442184fa0c03d083b661adf3a3eecfd6d21677740/nvidia_cudnn_cu13-9.19.0.56-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:6ed29ffaee1176c612daf442e4dd6cfeb6a0caa43ddcbeb59da94953030b1be4", size = 433781201, upload-time = "2026-02-03T20:40:53.805Z" },
@@ -2870,7 +2870,7 @@ name = "nvidia-cufft"
 version = "12.0.0.61"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-nvjitlink", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
+    { name = "nvidia-nvjitlink" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/8b/ae/f417a75c0259e85c1d2f83ca4e960289a5f814ed0cea74d18c353d3e989d/nvidia_cufft-12.0.0.61-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:2708c852ef8cd89d1d2068bdbece0aa188813a0c934db3779b9b1faa8442e5f5", size = 214053554, upload-time = "2025-09-04T08:31:38.196Z" },
@@ -2900,9 +2900,9 @@ name = "nvidia-cusolver"
 version = "12.0.4.66"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
-    { name = "nvidia-cusparse", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
-    { name = "nvidia-nvjitlink", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
+    { name = "nvidia-cublas" },
+    { name = "nvidia-cusparse" },
+    { name = "nvidia-nvjitlink" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/c8/c3/b30c9e935fc01e3da443ec0116ed1b2a009bb867f5324d3f2d7e533e776b/nvidia_cusolver-12.0.4.66-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:02c2457eaa9e39de20f880f4bd8820e6a1cfb9f9a34f820eb12a155aa5bc92d2", size = 223467760, upload-time = "2025-09-04T08:33:04.222Z" },
@@ -2914,7 +2914,7 @@ name = "nvidia-cusparse"
 version = "12.6.3.3"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-nvjitlink", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
+    { name = "nvidia-nvjitlink" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/f8/94/5c26f33738ae35276672f12615a64bd008ed5be6d1ebcb23579285d960a9/nvidia_cusparse-12.6.3.3-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:80bcc4662f23f1054ee334a15c72b8940402975e0eab63178fc7e670aa59472c", size = 162155568, upload-time = "2025-09-04T08:33:42.864Z" },
@@ -3091,10 +3091,10 @@ resolution-markers = [
    "python_full_version < '3.11'",
 ]
 dependencies = [
-    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
-    { name = "python-dateutil", marker = "python_full_version < '3.11'" },
-    { name = "pytz", marker = "python_full_version < '3.11'" },
-    { name = "tzdata", marker = "python_full_version < '3.11'" },
+    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" } },
+    { name = "python-dateutil" },
+    { name = "pytz" },
+    { name = "tzdata" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/9c/d6/9f8431bacc2e19dca897724cd097b1bb224a6ad5433784a44b587c7c13af/pandas-2.2.3.tar.gz", hash = "sha256:4f18ba62b61d7e192368b84517265a99b4d7ee8912f8708660fb4a366cc82667", size = 4399213, upload-time = "2024-09-20T13:10:04.827Z" }
 wheels = [
@@ -3143,11 +3143,11 @@ resolution-markers = [
    "python_full_version == '3.11.*'",
 ]
 dependencies = [
-    { name = "numpy", version = "2.4.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version == '3.11.*'" },
+    { name = "numpy", version = "2.4.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.12' or python_full_version >= '3.14'" },
    { name = "numpy", version = "2.5.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.12' and python_full_version < '3.14'" },
-    { name = "python-dateutil", marker = "python_full_version >= '3.11' and python_full_version < '3.14'" },
-    { name = "pytz", marker = "python_full_version >= '3.11' and python_full_version < '3.14'" },
-    { name = "tzdata", marker = "python_full_version >= '3.11' and python_full_version < '3.14'" },
+    { name = "python-dateutil" },
+    { name = "pytz" },
+    { name = "tzdata" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/33/01/d40b85317f86cf08d853a4f495195c73815fdf205eef3993821720274518/pandas-2.3.3.tar.gz", hash = "sha256:e05e1af93b977f7eafa636d043f9f94c7ee3ac81af99c13508215942e64c993b", size = 4495223, upload-time = "2025-09-29T23:34:51.853Z" }
 wheels = [
@@ -3210,9 +3210,9 @@ resolution-markers = [
    "python_full_version >= '3.14' and sys_platform != 'emscripten' and sys_platform != 'win32'",
 ]
 dependencies = [
-    { name = "numpy", version = "2.5.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.14'" },
-    { name = "python-dateutil", marker = "python_full_version >= '3.14'" },
-    { name = "tzdata", marker = "(python_full_version >= '3.14' and sys_platform == 'emscripten') or (python_full_version >= '3.14' and sys_platform == 'win32')" },
+    { name = "numpy", version = "2.5.1", source = { registry = "https://pypi.org/simple" } },
+    { name = "python-dateutil" },
+    { name = "tzdata", marker = "sys_platform == 'emscripten' or sys_platform == 'win32'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/f8/87/4341c6252d1c47b08768c3d25ac487362bf403f0313ddae4a2a26c9b1b4c/pandas-3.0.3.tar.gz", hash = "sha256:696a4a00a2a2a35d4e5deb3fc946641b96c944f02230e4f76137fe35d806c4fc", size = 4651414, upload-time = "2026-05-11T18:54:29.21Z" }
 wheels = [
@@ -3320,7 +3320,7 @@ name = "pexpect"
 version = "4.9.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "ptyprocess", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
+    { name = "ptyprocess" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/42/92/cc564bf6381ff43ce1f4d06852fc19a2f11d180f23dc32d9588bee2f149d/pexpect-4.9.0.tar.gz", hash = "sha256:ee7d41123f3c9911050ea2c2dac107568dc43b2d3b0c7557a33212c398ead30f", size = 166450, upload-time = "2023-11-25T09:07:26.339Z" }
 wheels = [
@@ -3912,7 +3912,7 @@ crypto = [

 [[package]]
 name = "pylance"
-version = "7.0.0"
+version = "10.0.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
    { name = "lance-namespace" },
@@ -3922,12 +3922,12 @@ dependencies = [
    { name = "pyarrow" },
 ]
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ac/ad/2f64921bf346e7075aef24a72595db44821724a3d89a9a92dd24e79632aa/pylance-7.0.0-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:98422021975be76e72b1572f41b8c9abb3bee5bdc9bfa5e9ce731110a65ed4d1", size = 62134146, upload-time = "2026-05-27T21:59:37.459Z" },
-    { url = "https://files.pythonhosted.org/packages/73/1c/c5a01bee0160b55d9a98895cbd33091d038f0a0995b121ab72e629008d02/pylance-7.0.0-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4bec86ee5b6fbd8bfc493e653f0a1fba0303cfe5492b9b46fc25ab908edc7183", size = 65373684, upload-time = "2026-05-27T22:04:01.584Z" },
-    { url = "https://files.pythonhosted.org/packages/eb/da/1fe8b8f7dbfe734d76af76acc994fc360a0d0c79a4874ef69f5a72a58fe3/pylance-7.0.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:881491432c53184e52f8d1db8d5f872f39a03f36fb104bec77b33d379519d8b5", size = 69458555, upload-time = "2026-05-27T22:16:50.567Z" },
-    { url = "https://files.pythonhosted.org/packages/76/f0/dd505cf3fd0226ab9d94759acd713125af1d3bfacfd80bbd52e3b9f89509/pylance-7.0.0-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:18453999e7fff4f76b16d6b7882c9df0628bd142ff95e2461bd7dd5ee3fe0af3", size = 65394430, upload-time = "2026-05-27T22:05:30.923Z" },
-    { url = "https://files.pythonhosted.org/packages/17/ba/2357b81034f28eb00790e258ed140289a6a887a7468ca9df6349fd186b27/pylance-7.0.0-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:04a58051d408c60fe76d41a220dcaf8fea8fb6d1aa0ca78a709b60bc3cc8d19a", size = 69473470, upload-time = "2026-05-27T22:17:18.935Z" },
-    { url = "https://files.pythonhosted.org/packages/1f/ec/5c00b6303a67d787f9475141832cbdc513d674ac3dcaeef8a7b169905e65/pylance-7.0.0-cp39-abi3-win_amd64.whl", hash = "sha256:467d4864af047eaab4e1370e2f1e88e2c6f507c079874421116cb41d78bc3629", size = 74792863, upload-time = "2026-05-27T22:19:23.875Z" },
+    { url = "https://files.pythonhosted.org/packages/82/b2/c81de196076c4c8d768f485324a0043e113ce0950a339977d83fee9783ef/pylance-10.0.0-cp310-abi3-macosx_11_0_arm64.whl", hash = "sha256:d4bba56ae829202b7e9cdc82c92c00a4b52f03e679dc3edfad1db09d1285be2e", size = 69279797, upload-time = "2026-08-07T18:25:24.812Z" },
+    { url = "https://files.pythonhosted.org/packages/d2/e9/af671a6225740bd70c1e70bd83fa08091d628b960397cbecc477f16aaaf1/pylance-10.0.0-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:489b944827c0271e16a62b4006f8c75acc3bd7fbc381f35388a2afaaae38d438", size = 72775384, upload-time = "2026-08-07T18:31:29.686Z" },
+    { url = "https://files.pythonhosted.org/packages/5d/22/e07194195bb3bbdf062b0c31690fc92fccb2686d5e768efa1dc379a93350/pylance-10.0.0-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:018efe7d437d326b9049c1223458bd955e85e48509b4b0bbf8b2d3d94075dbff", size = 76632194, upload-time = "2026-08-07T18:44:29.001Z" },
+    { url = "https://files.pythonhosted.org/packages/f2/71/ed9956cf657e86a5fee5d5ddcfa7bfed0d7c2968bee39ed85d12629d8c93/pylance-10.0.0-cp310-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:254bad5d765c14db6c4eddd5323133dee3c76ff6d40c4777afe0b0e91d4c04d2", size = 72804222, upload-time = "2026-08-07T18:31:24.264Z" },
+    { url = "https://files.pythonhosted.org/packages/94/96/de449c246b2892df9d5a0af775b79a061e9897e6942bcee5c4ab6d6071f8/pylance-10.0.0-cp310-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:9f0c089e30389d9b7765a4c16f3d9325b05ed4fbf6cc2bbc9418292983472e54", size = 76602015, upload-time = "2026-08-07T18:46:27.724Z" },
+    { url = "https://files.pythonhosted.org/packages/53/81/4a5a9072b6d68c4dbb8c7b5530a381c7a6bea4ba92f9eca58ac885142722/pylance-10.0.0-cp310-abi3-win_amd64.whl", hash = "sha256:9fecf46e6835dc64b2d71767d5eab4f73787543a852432e9ba8ecf8527b3cdab", size = 82799247, upload-time = "2026-08-07T18:47:46.855Z" },
 ]

 [[package]]
@@ -4683,10 +4683,10 @@ resolution-markers = [
    "python_full_version < '3.11'",
 ]
 dependencies = [
-    { name = "joblib", marker = "python_full_version < '3.11'" },
-    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
-    { name = "scipy", version = "1.15.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
-    { name = "threadpoolctl", marker = "python_full_version < '3.11'" },
+    { name = "joblib" },
+    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" } },
+    { name = "scipy", version = "1.15.3", source = { registry = "https://pypi.org/simple" } },
+    { name = "threadpoolctl" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/98/c2/a7855e41c9d285dfe86dc50b250978105dce513d6e459ea66a6aeb0e1e0c/scikit_learn-1.7.2.tar.gz", hash = "sha256:20e9e49ecd130598f1ca38a1d85090e1a600147b9c02fa6f15d69cb53d968fda", size = 7193136, upload-time = "2025-09-09T08:21:29.075Z" }
 wheels = [
@@ -4734,13 +4734,13 @@ resolution-markers = [
    "python_full_version == '3.11.*'",
 ]
 dependencies = [
-    { name = "joblib", marker = "python_full_version >= '3.11'" },
-    { name = "narwhals", marker = "python_full_version >= '3.11'" },
-    { name = "numpy", version = "2.4.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version == '3.11.*'" },
+    { name = "joblib" },
+    { name = "narwhals" },
+    { name = "numpy", version = "2.4.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.12'" },
    { name = "numpy", version = "2.5.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.12'" },
-    { name = "scipy", version = "1.17.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version == '3.11.*'" },
+    { name = "scipy", version = "1.17.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.12'" },
    { name = "scipy", version = "1.18.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.12'" },
-    { name = "threadpoolctl", marker = "python_full_version >= '3.11'" },
+    { name = "threadpoolctl" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/fa/6f/37092bdb25f712817231799fc5674d8e704066a8a70c1d2d40517e18b4ab/scikit_learn-1.9.0.tar.gz", hash = "sha256:8833266989d3a5110178a9fae30783675460724d0e1efb13b14901d2c660c557", size = 7750767, upload-time = "2026-06-02T11:54:32.706Z" }
 wheels = [
@@ -4784,7 +4784,7 @@ resolution-markers = [
    "python_full_version < '3.11'",
 ]
 dependencies = [
-    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
+    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" } },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/0f/37/6964b830433e654ec7485e45a00fc9a27cf868d622838f6b6d9c5ec0d532/scipy-1.15.3.tar.gz", hash = "sha256:eae3cf522bc7df64b42cad3925c876e1b0b6c35c1337c93e12c0f366f55b0eaf", size = 59419214, upload-time = "2025-05-08T16:13:05.955Z" }
 wheels = [
@@ -4843,7 +4843,7 @@ resolution-markers = [
    "python_full_version == '3.11.*'",
 ]
 dependencies = [
-    { name = "numpy", version = "2.4.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version == '3.11.*'" },
+    { name = "numpy", version = "2.4.6", source = { registry = "https://pypi.org/simple" } },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/7a/97/5a3609c4f8d58b039179648e62dd220f89864f56f7357f5d4f45c29eb2cc/scipy-1.17.1.tar.gz", hash = "sha256:95d8e012d8cb8816c226aef832200b1d45109ed4464303e997c5b13122b297c0", size = 30573822, upload-time = "2026-02-23T00:26:24.851Z" }
 wheels = [
@@ -4920,7 +4920,7 @@ resolution-markers = [
    "python_full_version >= '3.12' and python_full_version < '3.14'",
 ]
 dependencies = [
-    { name = "numpy", version = "2.5.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.12'" },
+    { name = "numpy", version = "2.5.1", source = { registry = "https://pypi.org/simple" } },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/a7/25/c2700dfaf6442b4effaa91af24ebce5dc9d31bb4a69706313aae70d72cd0/scipy-1.18.0.tar.gz", hash = "sha256:67b2ad2ad54c72ca6d04975a9b2df8c3638c34ddd5b28738e94fc2b57929d378", size = 30774447, upload-time = "2026-06-19T15:01:43.456Z" }
 wheels = [
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.37.1-beta.0"
+version = "0.37.1"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
@@ -49,8 +49,6 @@ lance-namespace = { workspace = true }
 lance-namespace-impls = { workspace = true }
 metrics = { workspace = true, optional = true }
 metrics-util = { workspace = true, 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"] }
@@ -100,7 +98,8 @@ anyhow = "1"
 lance-testing = { workspace = true }
 tempfile = "3.5.0"
 random_word = { version = "0.4.3", features = ["en"] }
-tokio = { version = "1.23", features = ["io-util", "macros", "net", "rt-multi-thread", "sync"] }
+roaring = "0.11.4"
+tokio = { version = "1.23", features = ["io-util", "macros", "net", "rt-multi-thread", "sync", "test-util"] }
 uuid = { version = "1.7.0", features = ["v4"] }
 walkdir = "2"
 aws-sdk-dynamodb = { version = "1.55.0" }
@@ -135,7 +134,6 @@ azure = [
 ]
 cos = ["lance/tencent", "lance-io/tencent"]
 goosefs = [
-    "dep:goosefs-sdk",
    "lance/goosefs",
    "lance-io/goosefs",
    "lance-namespace-impls/dir-goosefs",
@@ -12,8 +12,7 @@ use lance_encoding::decoder::{DecoderPlugins, FilterExpression};
 use lance_file::{
    reader::{FileReader, FileReaderOptions},
    version::ConcreteFileVersion,
-    versions,
-    writer::FileWriterOptions,
+    writer::{FileWriter, FileWriterOptions},
 };
 use lance_io::{
    ReadBatchParams,
@@ -154,11 +153,13 @@ impl Shuffler {
                    source: None,
                })?;
            let object_writer = object_store.create(&path).await?;
-            let writer = versions::create_writer(
-                ConcreteFileVersion::V2_1,
+            let writer = FileWriter::try_new(
                object_writer,
                schema.clone(),
-                FileWriterOptions::default(),
+                FileWriterOptions {
+                    format_version: Some(ConcreteFileVersion::V2_1.into()),
+                    ..Default::default()
+                },
            )?;
            file_writers.push(writer);
        }
@@ -23,11 +23,13 @@ use crate::table::AddResult;
 use crate::table::BranchDiff;
 use crate::table::DeleteResult;
 use crate::table::DropColumnsResult;
+use crate::table::LsmStats;
 use crate::table::LsmWriteSpec;
 use crate::table::MergeBranchResult;
 use crate::table::MergeResult;
 use crate::table::Tags;
 use crate::table::UpdateResult;
+use crate::table::lsm_stats::GetLsmStatsResponse;
 use crate::table::merge::MergeFilter;
 use crate::table::query::create_multi_vector_plan;
 use crate::table::write_progress::FinishOnDrop;
@@ -991,6 +993,18 @@ impl<S: HttpSend> RemoteTable<S> {
        }
    }

+    /// Send an LSM operator request with the transport retry layer **off**.
+    ///
+    /// Retry policy on these routes belongs to the checkpoint loop, which
+    /// reads the status and can tell contention from a lost claim. Leaving the
+    /// transport layer on would re-ask on its own schedule first, and surface
+    /// an `Error::Retry` whose status the loop would then have to unwrap.
+    async fn send_lsm_route(&self, request: RequestBuilder) -> Result<(String, reqwest::Response)> {
+        let (request_id, response) = self.send(request, false).await?;
+        let response = self.check_table_response(&request_id, response).await?;
+        Ok((request_id, response))
+    }
+
    /// Build a POST request and attach the read-freshness headers
    /// (`x-lancedb-min-version`, `x-lancedb-min-timestamp`).
    fn post_read(&self, uri: &str) -> RequestBuilder {
@@ -2468,6 +2482,40 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
        })
    }

+    async fn flush_lsm(&self) -> Result<()> {
+        let request = self
+            .client
+            .post(&format!("/v1/table/{}/flush_lsm/", self.identifier));
+        self.send_lsm_route(request).await?;
+        Ok(())
+    }
+
+    async fn compact_lsm(&self) -> Result<()> {
+        let request = self
+            .client
+            .post(&format!("/v1/table/{}/compact_lsm/", self.identifier));
+        self.send_lsm_route(request).await?;
+        Ok(())
+    }
+
+    async fn get_lsm_stats(&self, include_generation_rows: bool) -> Result<Option<LsmStats>> {
+        // Read-semantics POST, like `get_lsm_write_spec`.
+        let request = self
+            .post_read(&format!("/v1/table/{}/get_lsm_stats/", self.identifier))
+            .json(&serde_json::json!({
+                "include_generation_rows": include_generation_rows,
+            }));
+        let (request_id, response) = self.send_lsm_route(request).await?;
+        let body = response.text().await.err_to_http(request_id.clone())?;
+        let parsed: GetLsmStatsResponse = serde_json::from_str(&body).map_err(|e| Error::Http {
+            source: format!("Failed to parse get_lsm_stats response: {e}").into(),
+            request_id,
+            status_code: None,
+        })?;
+        // `null` — and only — when the table has no LSM write path.
+        Ok(parsed.lsm_stats)
+    }
+
    async fn set_lsm_write_spec(&self, spec: LsmWriteSpec) -> Result<()> {
        self.check_mutable().await?;

@@ -5907,18 +5955,17 @@ mod tests {
            .await
            .unwrap();

-        // Positions are relative to the first retained token, so dropping the
-        // leading "hello" stop word does not shift the remaining tokens.
+        // Lance 10 retains original token positions after stop-word removal.
        assert_eq!(
            tokens,
            vec![
                FtsToken {
                    text: "こんにちは".to_string(),
-                    position: 0,
+                    position: 1,
                },
                FtsToken {
                    text: "世界".to_string(),
-                    position: 1,
+                    position: 2,
                },
            ]
        );
@@ -6682,6 +6729,499 @@ mod tests {
        assert!(table.get_lsm_write_spec().await.unwrap().is_none());
    }

+    /// Build a `get_lsm_stats` body for one bucket holding `generations`.
+    fn stats_body(generations: &[u64], compacting: bool) -> String {
+        serde_json::json!({
+            "lsm_stats": {
+                "buckets": [{
+                    "shard_id": "b0",
+                    "status": "Active",
+                    "writer_epoch": 1,
+                    "manifest_version": 1,
+                    "current_generation": generations.iter().max().copied().unwrap_or(0) + 1,
+                    "replay_after_wal_entry_position": 0,
+                    "wal_entry_position_last_seen": 0,
+                    "generations": generations.iter()
+                        .map(|g| serde_json::json!({ "generation": g, "bytes": 1 }))
+                        .collect::<Vec<_>>(),
+                    "compacting": compacting,
+                    "memtables": [],
+                }],
+            }
+        })
+        .to_string()
+    }
+
+    /// `flush_lsm` / `compact_lsm` answer 202 with no body at all.
+    fn accepted() -> http::Response<String> {
+        http::Response::builder()
+            .status(202)
+            .body(String::new())
+            .unwrap()
+    }
+
+    fn ok_json(body: String) -> http::Response<String> {
+        http::Response::builder().status(200).body(body).unwrap()
+    }
+
+    /// A flush landing in an empty L0 finishes on the opening stats read
+    /// alone. Asserting zero compacts is the point: "it returned Ok" is also
+    /// true of a loop that ran a pointless pass.
+    #[tokio::test(start_paused = true)]
+    async fn test_checkpoint_short_circuits_on_empty_l0() {
+        let compacts = Arc::new(std::sync::atomic::AtomicUsize::new(0));
+        let seen = compacts.clone();
+        let table = Table::new_with_handler("my_table", move |request| {
+            let path = request.url().path().to_string();
+            if path.contains("compact_lsm") {
+                seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst);
+                panic!("an already-converged table must issue no compact calls");
+            }
+            if path.contains("flush_lsm") {
+                return accepted();
+            }
+            assert_eq!(path, "/v1/table/my_table/get_lsm_stats/");
+            ok_json(stats_body(&[], false))
+        });
+
+        table.checkpoint_lsm().await.unwrap();
+        assert_eq!(compacts.load(std::sync::atomic::Ordering::SeqCst), 0);
+    }
+
+    /// The loop triggers compaction until every generation that existed at
+    /// the start is gone, one bounded prefix per pass.
+    #[tokio::test(start_paused = true)]
+    async fn test_checkpoint_triggers_until_targets_are_drained() {
+        let compacts = Arc::new(std::sync::atomic::AtomicUsize::new(0));
+        let seen = compacts.clone();
+        let table = Table::new_with_handler("my_table", move |request| {
+            let path = request.url().path().to_string();
+            if path.contains("flush_lsm") {
+                return accepted();
+            }
+            if path.contains("compact_lsm") {
+                seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst);
+                return accepted();
+            }
+            // Each pass drains the oldest generation.
+            let drained = seen.load(std::sync::atomic::Ordering::SeqCst);
+            let left: Vec<u64> = [1u64, 2, 3].into_iter().skip(drained).collect();
+            ok_json(stats_body(&left, false))
+        });
+
+        table.checkpoint_lsm().await.unwrap();
+        assert_eq!(
+            compacts.load(std::sync::atomic::Ordering::SeqCst),
+            3,
+            "one trigger per generation prefix, then stop"
+        );
+    }
+
+    /// Generations created *during* the checkpoint are not waited on, which
+    /// is what lets the loop terminate on a table taking writes where "L0 is
+    /// empty" never becomes true.
+    #[tokio::test(start_paused = true)]
+    async fn test_checkpoint_ignores_generations_created_while_it_runs() {
+        let compacts = Arc::new(std::sync::atomic::AtomicUsize::new(0));
+        let seen = compacts.clone();
+        let table = Table::new_with_handler("my_table", move |request| {
+            let path = request.url().path().to_string();
+            if path.contains("flush_lsm") {
+                return accepted();
+            }
+            if path.contains("compact_lsm") {
+                seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst);
+                return accepted();
+            }
+            // Target is 5. One pass drains it; a writer keeps adding above.
+            let n = seen.load(std::sync::atomic::Ordering::SeqCst);
+            let body = if n == 0 {
+                stats_body(&[5], false)
+            } else {
+                stats_body(&[6, 7], false)
+            };
+            ok_json(body)
+        });
+
+        table.checkpoint_lsm().await.unwrap();
+        assert_eq!(
+            compacts.load(std::sync::atomic::Ordering::SeqCst),
+            1,
+            "the loop must not chase generations written after it started"
+        );
+    }
+
+    /// Contention is a 429 and must be retried. The server keeps it off 503
+    /// precisely so the client can act on the status alone — reading it as
+    /// terminal stops the checkpoint early on a healthy node.
+    #[tokio::test(start_paused = true)]
+    async fn test_checkpoint_retries_contention() {
+        let compacts = Arc::new(std::sync::atomic::AtomicUsize::new(0));
+        let seen = compacts.clone();
+        let table = Table::new_with_handler("my_table", move |request| {
+            let path = request.url().path().to_string();
+            if path.contains("flush_lsm") {
+                return accepted();
+            }
+            if path.contains("compact_lsm") {
+                // First two triggers: every bucket already latched.
+                if seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst) < 2 {
+                    return http::Response::builder()
+                        .status(429)
+                        .body(r#"{"code":21,"error":"Too many concurrent writes"}"#.to_string())
+                        .unwrap();
+                }
+                return accepted();
+            }
+            let accepted_triggers = seen
+                .load(std::sync::atomic::Ordering::SeqCst)
+                .saturating_sub(2);
+            let left: Vec<u64> = if accepted_triggers == 0 {
+                vec![1]
+            } else {
+                vec![]
+            };
+            ok_json(stats_body(&left, false))
+        });
+
+        table
+            .checkpoint_lsm()
+            .await
+            .expect("contention must not abort the checkpoint");
+        assert_eq!(
+            compacts.load(std::sync::atomic::Ordering::SeqCst),
+            3,
+            "assert the retry count, not just the outcome"
+        );
+    }
+
+    /// A transient fault on the poll must not abort the checkpoint. This route
+    /// meets the most contention — it runs every `POLL_INTERVAL` for the
+    /// checkpoint's whole life, with the transport retry layer disabled — yet
+    /// was the one call reached with a bare `?`.
+    #[tokio::test(start_paused = true)]
+    async fn test_checkpoint_retries_a_contended_stats_poll() {
+        let polls = Arc::new(std::sync::atomic::AtomicUsize::new(0));
+        let seen = polls.clone();
+        let table = Table::new_with_handler("my_table", move |request| {
+            let path = request.url().path().to_string();
+            if path.contains("flush_lsm") || path.contains("compact_lsm") {
+                return accepted();
+            }
+            // The opening read lands; the next two polls are latched out.
+            let n = seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst);
+            if (1..3).contains(&n) {
+                return http::Response::builder()
+                    .status(429)
+                    .body(r#"{"code":21,"error":"Too many concurrent writes"}"#.to_string())
+                    .unwrap();
+            }
+            ok_json(stats_body(if n < 4 { &[1] } else { &[] }, false))
+        });
+
+        table
+            .checkpoint_lsm()
+            .await
+            .expect("a contended poll must be retried, not surfaced");
+        assert_eq!(
+            polls.load(std::sync::atomic::Ordering::SeqCst),
+            5,
+            "the two rejected polls must be re-issued, not skipped"
+        );
+    }
+
+    /// Contention and a lost claim draw on separate budgets: five straight
+    /// 429s on `flush`, more than `MAX_REISSUES`, must still converge. On one
+    /// shared counter this spent the re-issue cap and then reported a lost
+    /// claim nothing had ever reported.
+    #[tokio::test(start_paused = true)]
+    async fn test_contention_does_not_exhaust_the_reissue_budget() {
+        let flushes = Arc::new(std::sync::atomic::AtomicUsize::new(0));
+        let seen = flushes.clone();
+        let table = Table::new_with_handler("my_table", move |request| {
+            let path = request.url().path().to_string();
+            if path.contains("flush_lsm") {
+                if seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst) < 5 {
+                    return http::Response::builder()
+                        .status(429)
+                        .body(r#"{"code":21,"error":"Too many concurrent writes"}"#.to_string())
+                        .unwrap();
+                }
+                return accepted();
+            }
+            if path.contains("compact_lsm") {
+                return accepted();
+            }
+            ok_json(stats_body(&[], false))
+        });
+
+        table
+            .checkpoint_lsm()
+            .await
+            .expect("contention must not be reported as a lost claim");
+        assert_eq!(
+            flushes.load(std::sync::atomic::Ordering::SeqCst),
+            6,
+            "five retries against one seal, then it lands"
+        );
+    }
+
+    /// An exhausted retry budget surfaces the fault that consumed it, not a
+    /// message the loop invented: "429, nine times" points an operator at a
+    /// saturated pool, a generic runtime error points them nowhere.
+    #[tokio::test(start_paused = true)]
+    async fn test_exhausted_retries_surface_the_underlying_fault() {
+        let calls = Arc::new(std::sync::atomic::AtomicUsize::new(0));
+        let seen = calls.clone();
+        let table = Table::new_with_handler("my_table", move |_request| {
+            seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst);
+            http::Response::builder()
+                .status(429)
+                .body(r#"{"code":21,"error":"Too many concurrent writes"}"#.to_string())
+                .unwrap()
+        });
+
+        let err = table.checkpoint_lsm().await.unwrap_err();
+        assert!(
+            matches!(&err, Error::Http { status_code: Some(s), .. } if s.as_u16() == 429),
+            "the fault that spent the budget must be the one reported: {err:?}"
+        );
+        assert_eq!(
+            calls.load(std::sync::atomic::Ordering::SeqCst),
+            9,
+            "one call plus MAX_RETRIES — the re-issue budget is not spent on top"
+        );
+    }
+
+    /// A draining node is terminal, but the client does not know that from the
+    /// status: draining and a proxy blip are both 503, and telling them apart
+    /// takes parsing the body for a namespace code. So it spends the retry
+    /// budget and then reports what the server said — the drain gate never
+    /// releases, so the answer does not change, and the operator still reads
+    /// "WAL node draining" in the error.
+    #[tokio::test(start_paused = true)]
+    async fn test_draining_surfaces_after_the_retry_budget() {
+        let calls = Arc::new(std::sync::atomic::AtomicUsize::new(0));
+        let seen = calls.clone();
+        let table = Table::new_with_handler("my_table", move |_request| {
+            seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst);
+            http::Response::builder()
+                .status(503)
+                .body(r#"{"code":19,"error":"WAL node draining"}"#.to_string())
+                .unwrap()
+        });
+
+        let err = table.checkpoint_lsm().await.unwrap_err();
+        let message = err.to_string();
+        assert!(
+            matches!(&err, Error::Http { status_code: Some(s), .. } if s.as_u16() == 503),
+            "the 503 must surface as itself: {err:?}"
+        );
+        assert!(
+            message.contains("WAL node draining"),
+            "the server's own diagnosis must survive to the caller: {message}"
+        );
+        assert_eq!(
+            calls.load(std::sync::atomic::Ordering::SeqCst),
+            9,
+            "one call plus MAX_RETRIES, then it reports rather than spinning"
+        );
+    }
+
+    /// A long stall with nothing compacting must keep waiting, not fail. The
+    /// client cannot judge this: a checkpoint queued behind unrelated tables
+    /// on the pod-wide compactor pool reports exactly these numbers — flat
+    /// generations, an idle latch — as one whose merges are failing. The
+    /// deadline is the caller's.
+    #[tokio::test(start_paused = true)]
+    async fn test_checkpoint_waits_out_a_long_stall_rather_than_failing() {
+        let polls = Arc::new(std::sync::atomic::AtomicUsize::new(0));
+        let seen = polls.clone();
+        let table = Table::new_with_handler("my_table", move |request| {
+            let path = request.url().path().to_string();
+            if path.contains("flush_lsm") || path.contains("compact_lsm") {
+                return accepted();
+            }
+            // Flat for far longer than any bound this loop ever had, with
+            // `compacting: false` throughout — then it drains.
+            let n = seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst);
+            ok_json(stats_body(if n < 40 { &[1, 2] } else { &[] }, false))
+        });
+
+        table
+            .checkpoint_lsm()
+            .await
+            .expect("a stall is the server being slow, not the client's call to make");
+        assert!(
+            polls.load(std::sync::atomic::Ordering::SeqCst) > 40,
+            "the loop must have kept polling well past the old ten-poll bound"
+        );
+    }
+
+    /// A pass already owns the latch on every outstanding bucket, so the loop
+    /// waits rather than piling on triggers it would only refuse. This is the
+    /// sole thing `compacting` is read for.
+    #[tokio::test(start_paused = true)]
+    async fn test_checkpoint_waits_while_a_pass_is_running() {
+        let polls = Arc::new(std::sync::atomic::AtomicUsize::new(0));
+        let compacts = Arc::new(std::sync::atomic::AtomicUsize::new(0));
+        let seen_polls = polls.clone();
+        let seen_compacts = compacts.clone();
+        let table = Table::new_with_handler("my_table", move |request| {
+            let path = request.url().path().to_string();
+            if path.contains("flush_lsm") {
+                return accepted();
+            }
+            if path.contains("compact_lsm") {
+                seen_compacts.fetch_add(1, std::sync::atomic::Ordering::SeqCst);
+                return accepted();
+            }
+            // Latched for many polls, then done.
+            let n = seen_polls.fetch_add(1, std::sync::atomic::Ordering::SeqCst);
+            ok_json(if n > 15 {
+                stats_body(&[], false)
+            } else {
+                stats_body(&[1], true)
+            })
+        });
+
+        table
+            .checkpoint_lsm()
+            .await
+            .expect("a running pass is progress, not a stall");
+        assert_eq!(
+            compacts.load(std::sync::atomic::Ordering::SeqCst),
+            0,
+            "never trigger against a bucket already compacting"
+        );
+    }
+
+    /// WAL off ⇒ `None`; WAL on ⇒ a fully populated `Some` with no field
+    /// defaulting to a zero it did not measure. `include_generation_rows`
+    /// rides in the body and is off unless asked for.
+    #[tokio::test]
+    async fn test_get_lsm_stats_round_trip() {
+        let table = Table::new_with_handler("my_table", |request| {
+            assert_eq!(request.url().path(), "/v1/table/my_table/get_lsm_stats/");
+            let body = request.body().unwrap().as_bytes().unwrap();
+            let body: serde_json::Value = serde_json::from_slice(body).unwrap();
+            assert_eq!(
+                body["include_generation_rows"], true,
+                "the flag must reach the server, not be silently dropped"
+            );
+            let response = serde_json::json!({
+                "lsm_stats": {
+                    "buckets": [{
+                        "shard_id": "b0",
+                        "status": "Active",
+                        "writer_epoch": 3,
+                        "manifest_version": 11,
+                        "current_generation": 9,
+                        "replay_after_wal_entry_position": 100,
+                        "wal_entry_position_last_seen": 140,
+                        "generations": [{ "generation": 8, "bytes": 4096, "rows": 30 }],
+                        "compacting": false,
+                        "memtables": [
+                            { "generation": 9, "rows": 12, "bytes": 900, "batches": 2,
+                              "indexes": ["vec_idx"] }
+                        ],
+                    }],
+                }
+            });
+            http::Response::builder()
+                .status(200)
+                .body(response.to_string())
+                .unwrap()
+        });
+
+        let stats = table
+            .get_lsm_stats(true)
+            .await
+            .unwrap()
+            .expect("a WAL-backed table reports Some");
+        let bucket = &stats.buckets[0];
+        assert_eq!(bucket.replay_after_wal_entry_position, 100);
+        assert_eq!(bucket.wal_entry_position_last_seen, 140);
+        assert!(!bucket.compacting);
+        assert_eq!(bucket.generations[0].generation, 8);
+        assert_eq!(bucket.generations[0].rows, Some(30));
+        // The line that answers "why is my fresh-tier vector search
+        // brute-force" — an absent index name is the whole explanation.
+        let memtables = bucket.memtables.as_ref().unwrap();
+        assert_eq!(memtables[0].indexes, vec!["vec_idx".to_string()]);
+    }
+
+    /// A 404 arrives as `TableNotFound`, not as a lost claim the loop
+    /// re-issues from flush until its cap. The two are distinguished by
+    /// status: 404 is "no such table", 421 is "this node holds no claim".
+    /// They shared 404 once, and the loop chased a name that never existed.
+    #[tokio::test(start_paused = true)]
+    async fn test_missing_table_is_not_read_as_a_lost_claim() {
+        let calls = Arc::new(std::sync::atomic::AtomicUsize::new(0));
+        let seen = calls.clone();
+        let table = Table::new_with_handler("my_table", move |_request| {
+            seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst);
+            http::Response::builder()
+                .status(404)
+                .body(r#"{"code":4,"error":"Not found: Table not found: my_table"}"#.to_string())
+                .unwrap()
+        });
+
+        let err = table.checkpoint_lsm().await.unwrap_err();
+        assert!(
+            matches!(err, Error::TableNotFound { .. }),
+            "a missing table must say so: {err:?}"
+        );
+        assert_eq!(
+            calls.load(std::sync::atomic::Ordering::SeqCst),
+            1,
+            "no point re-claiming a table that does not exist"
+        );
+    }
+
+    /// A lost claim — 421, not 404 — does re-issue from flush, the call that
+    /// re-claims and replays.
+    #[tokio::test(start_paused = true)]
+    async fn test_registry_miss_reissues_from_flush() {
+        let calls = Arc::new(std::sync::atomic::AtomicUsize::new(0));
+        let seen = calls.clone();
+        let table = Table::new_with_handler("my_table", move |request| {
+            let path = request.url().path().to_string();
+            let n = seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst);
+            if path.contains("flush_lsm") {
+                // First flush lands; the claim is then lost, and the
+                // re-issued flush succeeds.
+                return accepted();
+            }
+            if path.contains("compact_lsm") {
+                if n < 4 {
+                    return http::Response::builder()
+                        .status(421)
+                        .body(r#"{"code":19,"error":"table not claimed"}"#.to_string())
+                        .unwrap();
+                }
+                return accepted();
+            }
+            ok_json(stats_body(if n < 6 { &[1] } else { &[] }, false))
+        });
+
+        table
+            .checkpoint_lsm()
+            .await
+            .expect("a lost claim must be recovered by re-flushing, not surfaced");
+    }
+
+    #[tokio::test]
+    async fn test_get_lsm_stats_absent_when_wal_off() {
+        let table = Table::new_with_handler("my_table", |_request| {
+            http::Response::builder()
+                .status(200)
+                .body(serde_json::json!({ "lsm_stats": null }).to_string())
+                .unwrap()
+        });
+        assert!(table.get_lsm_stats(false).await.unwrap().is_none());
+    }
+
    #[tokio::test]
    async fn test_wait_for_index() {
        let table = _make_table_with_indices(0);
@@ -68,10 +68,12 @@ use self::merge::MergeInsertBuilder;
 pub mod add_columns;
 mod add_data;
 pub mod branch_merge;
+pub mod checkpoint;
 mod create_index;
 pub mod datafusion;
 pub(crate) mod dataset;
 pub mod delete;
+pub mod lsm_stats;
 pub mod merge;
 pub mod optimize;
 mod primary_key;
@@ -93,8 +95,8 @@ pub use delete::DeleteResult;
 use futures::future::join_all;
 pub use lance::dataset::refs::{BranchContents, Ref, TagContents, Tags as LanceTags};
 pub use lance::dataset::scanner::DatasetRecordBatchStream;
-use lance::dataset::statistics::DatasetStatisticsExt;
 pub use lance_index::optimize::OptimizeOptions;
+pub use lsm_stats::{BucketStats, GenerationStats, LsmStats, MemtableStats};
 pub use optimize::{CompactionOptions, OptimizeAction, OptimizeStats};
 pub use schema_evolution::{
    AddColumnsResult, AlterColumnsResult, DropColumnsResult, FieldMetadataUpdate,
@@ -685,6 +687,31 @@ pub trait BaseTable: std::fmt::Display + std::fmt::Debug + Send + Sync {
            message: "get_lsm_write_spec is not supported on this table type".into(),
        })
    }
+    /// Seal every bucket's active memtable into L0.
+    ///
+    /// The default implementation returns `NotSupported`.
+    async fn flush_lsm(&self) -> Result<()> {
+        Err(Error::NotSupported {
+            message: "flush_lsm is not supported on this table type".into(),
+        })
+    }
+    /// Trigger a background L0 → base compaction pass per bucket.
+    ///
+    /// The default implementation returns `NotSupported`.
+    async fn compact_lsm(&self) -> Result<()> {
+        Err(Error::NotSupported {
+            message: "compact_lsm is not supported on this table type".into(),
+        })
+    }
+    /// Read live LSM state, or `None` when the LSM write path is not
+    /// enabled for this table.
+    ///
+    /// The default implementation returns `NotSupported`.
+    async fn get_lsm_stats(&self, _include_generation_rows: bool) -> Result<Option<LsmStats>> {
+        Err(Error::NotSupported {
+            message: "get_lsm_stats is not supported on this table type".into(),
+        })
+    }
    /// Drain and close any cached MemWAL shard writers for this table.
    ///
    /// The default implementation is a no-op; table types that maintain
@@ -1726,6 +1753,85 @@ impl Table {
        self.inner.get_lsm_write_spec().await
    }

+    /// Converge this table's LSM write path into its base table.
+    ///
+    /// One `flush` to seal every memtable into L0, then compaction triggers
+    /// until every generation that existed at that moment has reached base.
+    /// The loop runs client-side, reading progress from `get_lsm_stats`, so
+    /// there is no held socket and nothing to reconcile if you drop this
+    /// future partway through.
+    ///
+    /// **Best-effort.** Generations created *after* the opening flush are
+    /// deliberately not waited on — that is what lets this terminate on a
+    /// table taking writes. Idempotent and safe on a cadence: an
+    /// already-converged table costs two round trips and triggers nothing.
+    ///
+    /// **No deadline, and the caller owns that.** It returns when the target
+    /// generations are gone, propagates a terminal server fault, and
+    /// otherwise waits however long the server takes. A slow table and a
+    /// stuck one are the same picture from here: the compactor pool is shared
+    /// across every table on the node, so a checkpoint queued behind
+    /// unrelated work is indistinguishable from one that is merging. Wrap
+    /// this in `tokio::time::timeout` for a wall-clock bound; abandoning it
+    /// partway costs nothing.
+    ///
+    /// # Example
+    ///
+    /// ```no_run
+    /// # use lancedb::Table;
+    /// # async fn example(table: &Table) -> Result<(), Box<dyn std::error::Error>> {
+    /// let before = table.get_lsm_stats(false).await?;
+    /// table.checkpoint_lsm().await?;
+    /// let after = table.get_lsm_stats(false).await?;
+    /// # Ok(())
+    /// # }
+    /// ```
+    pub async fn checkpoint_lsm(&self) -> Result<()> {
+        checkpoint::checkpoint_lsm(self).await
+    }
+
+    /// Seal every bucket's active memtable into L0 without touching the
+    /// base table.
+    ///
+    /// Independently useful: flushing makes memtable rows readable from L0 at
+    /// a lower per-query cost. On a node that has not claimed this table it
+    /// claims it and replays the WAL log first — reporting "nothing to flush"
+    /// without replaying would lie about durable data.
+    pub async fn flush_lsm(&self) -> Result<()> {
+        self.inner.flush_lsm().await
+    }
+
+    /// Run one bounded L0 → base compaction pass per bucket, reporting what
+    /// it merged and what is left.
+    ///
+    /// One pass, not convergence: that bounds each request's cost and gives a
+    /// caller driving its own cadence a progress signal per round trip.
+    pub async fn compact_lsm(&self) -> Result<()> {
+        self.inner.compact_lsm().await
+    }
+
+    /// Read live per-bucket LSM state.
+    ///
+    /// Answers "how far behind is my fresh tier", "which bucket is hot", and
+    /// "why is my fresh-tier vector search brute-force". Mutates no table
+    /// state, though on a node that has not claimed this table it claims it,
+    /// exactly as a read would.
+    ///
+    /// `include_generation_rows` reports a row count per L0 generation. Off by
+    /// default: each count opens an uncached Lance dataset, and
+    /// `checkpoint_lsm` polls this needing only generation numbers.
+    ///
+    /// `Ok(None)` only when the LSM write path is not enabled, matching
+    /// [`Table::get_lsm_write_spec`]. Stats is fresh-tier only, so with the
+    /// WAL off there is no manifest to report and a struct of zeros would
+    /// read as measurements.
+    ///
+    /// Do not build a checkpoint's termination on this: the completion
+    /// predicate lives in the `flush` and `compact` responses.
+    pub async fn get_lsm_stats(&self, include_generation_rows: bool) -> Result<Option<LsmStats>> {
+        self.inner.get_lsm_stats(include_generation_rows).await
+    }
+
    /// Drain and close any cached MemWAL shard writers held for this table.
    ///
    /// When an [`LsmWriteSpec`] is installed, `merge_insert` opens MemWAL shard
@@ -3441,9 +3547,24 @@ impl BaseTable for NativeTable {
        let num_rows = self.count_rows(None).await?;
        let num_indices = self.list_indices().await?.len();
        let ds = self.dataset.get().await?;
-        let ds_clone = (*ds).clone();
-        let ds_stats = Arc::new(ds_clone).calculate_data_stats().await?;
-        let total_bytes = ds_stats.fields.iter().map(|f| f.bytes_on_disk).sum::<u64>() as usize;
+        // Sizes come from the manifest. Summing per-field `bytes_on_disk` instead
+        // would open every data file to read its column metadata, which costs one
+        // IO per fragment and reports 0 for legacy v1 storage.
+        //
+        // The manifest summary covers only the fragments' base data files, so
+        // overlay files (recorded on each fragment) and index files (recorded in
+        // the manifest's index section) are added separately.
+        let mut total_bytes = ds.manifest().summary().total_files_size as usize;
+        for frag in ds.manifest().fragments.iter() {
+            for overlay in &frag.overlays {
+                if let Some(size) = overlay.data_file.file_size_bytes.get() {
+                    total_bytes += size.get() as usize;
+                }
+            }
+        }
+        for index in ds.load_indices().await?.iter() {
+            total_bytes += index.total_size_bytes().unwrap_or(0) as usize;
+        }

        let frags = ds.get_fragments();
        let mut sorted_sizes = join_all(
@@ -3515,7 +3636,12 @@ impl BaseTable for NativeTable {
 #[skip_serializing_none]
 #[derive(Debug, Deserialize, PartialEq)]
 pub struct TableStatistics {
-    /// The total number of bytes in the table
+    /// The total size, in bytes, of the table's data files, index files, and
+    /// overlay files
+    ///
+    /// Read from the manifest, so this excludes deletion files and manifests,
+    /// and it excludes any file whose size the manifest does not record
+    /// (tables and indices written before writers persisted file sizes).
    pub total_bytes: usize,

    /// The number of rows in the table
@@ -3576,6 +3702,7 @@ mod tests {
    use super::*;
    use crate::connect;
    use crate::connection::ConnectBuilder;
+    use crate::io::object_store::io_tracking::IoTrackingStore;
    use crate::query::Select;
    use crate::query::{ExecutableQuery, QueryBase};
    use crate::test_utils::connection::new_test_connection;
@@ -5024,12 +5151,16 @@ mod tests {

        let res = table.stats().await.unwrap();
        println!("{:#?}", res);
+        // `total_bytes` is the full on-disk size of the 11 data files (this table
+        // has no index or overlay files), so it is well above the 2000 bytes of
+        // column data these 250 int32 pairs hold: each file carries its own footer
+        // and metadata.
        assert_eq!(
            res,
            TableStatistics {
                num_rows: 250,
                num_indices: 0,
-                total_bytes: 2300,
+                total_bytes: 8925,
                fragment_stats: FragmentStatistics {
                    num_fragments: 11,
                    num_small_fragments: 11,
@@ -5069,4 +5200,198 @@ mod tests {
            }
        )
    }
+
+    /// `total_bytes` counts more than the base data files: index files and
+    /// overlay files recorded in the manifest are included too.
+    #[tokio::test]
+    pub async fn test_stats_includes_index_and_overlay_files() {
+        use lance::dataset::WriteDestination;
+        use lance::dataset::transaction::{DataOverlayGroup, Operation};
+        use lance_file::version::{ConcreteFileVersion, LanceFileVersion};
+        use lance_file::writer::{FileWriter, FileWriterOptions};
+        use lance_io::utils::CachedFileSize;
+        use lance_table::format::DataFile;
+        use lance_table::format::overlay::{DataOverlayFile, OverlayCoverage};
+        use roaring::RoaringBitmap;
+
+        let tmp_dir = tempdir().unwrap();
+        let uri = tmp_dir.path().to_str().unwrap();
+        let conn = ConnectBuilder::new(uri)
+            .read_consistency_interval(Duration::from_secs(0))
+            .execute()
+            .await
+            .unwrap();
+
+        let schema = Arc::new(Schema::new(vec![
+            Field::new("id", DataType::Int32, false),
+            Field::new("foo", DataType::Int32, true),
+        ]));
+        let batch = RecordBatch::try_new(
+            schema.clone(),
+            vec![
+                Arc::new(Int32Array::from_iter_values(0..100)),
+                Arc::new(Int32Array::from_iter_values(0..100)),
+            ],
+        )
+        .unwrap();
+        let table = conn
+            .create_table("test_stats_extra_files", batch)
+            .execute()
+            .await
+            .unwrap();
+
+        let data_only = table.stats().await.unwrap().total_bytes;
+        assert!(data_only > 0);
+
+        // A scalar index adds index files whose sizes are recorded in the
+        // manifest's index section.
+        table
+            .create_index(&["id"], Index::Auto)
+            .execute()
+            .await
+            .unwrap();
+        let with_index = table.stats().await.unwrap().total_bytes;
+        let dataset = {
+            let native = table.as_native().unwrap();
+            (*native.dataset.get().await.unwrap()).clone()
+        };
+        let index_bytes: usize = dataset
+            .load_indices()
+            .await
+            .unwrap()
+            .iter()
+            .map(|idx| idx.total_size_bytes().unwrap_or(0) as usize)
+            .sum();
+        assert!(index_bytes > 0);
+        assert_eq!(with_index, data_only + index_bytes);
+
+        // Commit an overlay file supplying new `foo` values for the first three
+        // rows of fragment 0. There is no high-level API that writes overlays
+        // yet, so write the overlay's data file and commit the `DataOverlay`
+        // operation by hand.
+        let read_version = dataset.version().version;
+        let fragment_id = dataset.get_fragments()[0].id() as u64;
+        let foo_field_id = dataset.schema().field("foo").unwrap().id;
+        let overlay_schema = dataset.schema().project_by_ids(&[foo_field_id], true);
+        let file_version = ConcreteFileVersion::from(LanceFileVersion::Stable);
+
+        let filename = "overlay.lance".to_string();
+        let store = dataset.object_store(None).await.unwrap();
+        let path = dataset.data_dir().child(filename.clone());
+        let obj_writer = store.create(&path).await.unwrap();
+        let mut writer = FileWriter::try_new(
+            obj_writer,
+            overlay_schema,
+            FileWriterOptions {
+                format_version: Some(file_version.into()),
+                ..Default::default()
+            },
+        )
+        .unwrap();
+        writer
+            .write_column(0, Arc::new(Int32Array::from(vec![1000, 1001, 1002])) as _)
+            .await
+            .unwrap();
+        let summary = writer.finish().await.unwrap();
+        let overlay_bytes = summary.size_bytes as usize;
+        assert!(overlay_bytes > 0);
+
+        let mut data_file = DataFile::new_unstarted(filename, file_version);
+        data_file.fields = writer
+            .field_id_to_column_indices()
+            .iter()
+            .map(|(field_id, _)| *field_id as i32)
+            .collect::<Vec<_>>()
+            .into();
+        data_file.column_indices = writer
+            .field_id_to_column_indices()
+            .iter()
+            .map(|(_, column_index)| *column_index as i32)
+            .collect::<Vec<_>>()
+            .into();
+        data_file.file_size_bytes = CachedFileSize::new(summary.size_bytes);
+
+        let overlay = DataOverlayFile {
+            data_file,
+            coverage: OverlayCoverage::dense(RoaringBitmap::from_iter(0..3)),
+            committed_version: 0,
+        };
+        Dataset::commit(
+            WriteDestination::Dataset(Arc::new(dataset)),
+            Operation::DataOverlay {
+                groups: vec![DataOverlayGroup {
+                    fragment_id,
+                    overlays: vec![overlay],
+                }],
+            },
+            Some(read_version),
+            None,
+            None,
+            Arc::new(Default::default()),
+            false,
+        )
+        .await
+        .unwrap();
+
+        table.checkout_latest().await.unwrap();
+        let with_overlay = table.stats().await.unwrap().total_bytes;
+        assert_eq!(with_overlay, with_index + overlay_bytes);
+    }
+
+    /// `stats()` must stay manifest-only. Summing per-field `bytes_on_disk`
+    /// instead opens every data file, so cost would grow with fragment count.
+    #[tokio::test]
+    pub async fn test_stats_does_not_read_data_files() {
+        let tmp_dir = tempdir().unwrap();
+        let uri = tmp_dir.path().to_str().unwrap();
+
+        let conn = ConnectBuilder::new(uri).execute().await.unwrap();
+
+        let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int32, false)]));
+        let batch = RecordBatch::try_new(
+            schema.clone(),
+            vec![Arc::new(Int32Array::from_iter_values(0..10))],
+        )
+        .unwrap();
+
+        conn.create_table("test_stats_io", batch.clone())
+            .execute()
+            .await
+            .unwrap();
+        let table = conn.open_table("test_stats_io").execute().await.unwrap();
+        const NUM_APPENDS: usize = 20;
+        for _ in 0..NUM_APPENDS {
+            table.add(batch.clone()).execute().await.unwrap();
+        }
+
+        // Reopen through a tracking store so the counters cover `stats()` alone and
+        // not the writes above.
+        let (wrapper, io_stats) = IoTrackingStore::new_wrapper();
+        let table = conn
+            .open_table("test_stats_io")
+            .lance_read_params(ReadParams {
+                store_options: Some(ObjectStoreParams {
+                    object_store_wrapper: Some(wrapper),
+                    ..Default::default()
+                }),
+                ..Default::default()
+            })
+            .execute()
+            .await
+            .unwrap();
+        io_stats.lock().unwrap().read_iops = 0;
+
+        let stats = table.stats().await.unwrap();
+        let read_iops = io_stats.lock().unwrap().read_iops;
+
+        assert_eq!(stats.fragment_stats.num_fragments, NUM_APPENDS + 1);
+        assert!(stats.total_bytes > 0);
+        // Reading the fragments' data files would take at least one IOP each.
+        assert!(
+            read_iops < stats.fragment_stats.num_fragments as u64,
+            "stats() issued {} read IOPs across {} fragments",
+            read_iops,
+            stats.fragment_stats.num_fragments
+        );
+    }
 }
@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+//! Converging a table's LSM write path into its base table.
+//!
+//! `checkpoint_lsm` seals once, then triggers compaction and watches
+//! generation numbers until the L0 that existed at the start is gone.
+//!
+//! The loop runs in the client, not the server: `compact_lsm` dispatches a
+//! pass and returns, so nothing holds a socket and a client can vanish
+//! mid-operation with nothing to reconcile. Completion is read from
+//! generation numbers in the shard manifest — durable state, unlike a count
+//! in a compact response, which a concurrent write invalidates.
+//!
+//! The target set is fixed at the start, so generations created *during* the
+//! checkpoint are ignored. That is what lets it terminate under write load,
+//! and what makes it best-effort: it converges the fresh tier as of some
+//! instant. Idempotent, abandonable at any point, safe on a cadence.
+//!
+//! No liveness bound — the caller owns the deadline. The compactor pool is
+//! shared pod-wide, so a checkpoint queued behind unrelated tables looks
+//! exactly like one that is merging.
+
+use std::collections::HashMap;
+use std::future::Future;
+use std::time::Duration;
+
+use crate::{Error, Result, Table};
+
+/// The HTTP status a failed request carried, if it carried one.
+///
+/// `None` for anything with no retry story: a `TableNotFound` that
+/// `check_table_response` already translated, or a connection failure that
+/// never reached the server. Both are terminal.
+fn status_of(e: &Error) -> Option<u16> {
+    #[cfg(feature = "remote")]
+    {
+        match e {
+            Error::Http {
+                status_code: Some(status),
+                ..
+            } => Some(status.as_u16()),
+            _ => None,
+        }
+    }
+    #[cfg(not(feature = "remote"))]
+    {
+        let _ = e;
+        None
+    }
+}
+
+/// 429 (latch held, pool saturated, or the pod replaying its WAL) and 503 (a
+/// draining node, or a proxy between here and it).
+///
+/// The status is the whole signal: the server deliberately keeps contention
+/// off 503, so a latch collision is a 429. A draining node *is* terminal, but
+/// it is also a 503 that stays a 503, so retrying spends one budget and then
+/// reports the server's own message — cheaper than parsing the body for the
+/// namespace code it would take to tell the two apart.
+fn is_retryable(e: &Error) -> bool {
+    matches!(status_of(e), Some(429 | 503))
+}
+
+/// 421: the owning node holds no claim. Only `flush` re-claims and replays,
+/// so this cannot be retried in place — the caller has to start over.
+fn is_lost_claim(e: &Error) -> bool {
+    status_of(e) == Some(421)
+}
+
+/// Interval between `get_lsm_stats` polls. One interval is roughly one
+/// compaction pass, the granularity at which the answer can change.
+///
+/// Fixed rather than configurable, matching `wait_for_index`. It costs
+/// nothing on an already-converged table and at most one interval of tail
+/// latency after the final pass lands.
+const POLL_INTERVAL: Duration = Duration::from_secs(5);
+
+/// Cap on re-issues from `flush` after a 421, so a crash-looping node cannot
+/// turn flush → compact → 421 → flush into a spin.
+///
+/// Deliberately not shared with [`MAX_RETRIES`]: a claim that keeps
+/// evaporating is a broken node, while contention is routine and wants a real
+/// budget. One shared counter let a merely contended table exhaust this cap
+/// and then blame a claim it never lost.
+const MAX_REISSUES: usize = 3;
+
+/// Retryable faults tolerated on a *single* request, reset on every success —
+/// scattered contention across a long checkpoint must not accumulate toward a
+/// cap. Roughly 16s of retrying against the backoff below.
+const MAX_RETRIES: usize = 8;
+
+/// Backoff between retries, doubling up to [`RETRY_BACKOFF_MAX`]. Latch
+/// contention clears in about the time one pass takes, so start small; a
+/// saturated pool wants the ceiling.
+const RETRY_BACKOFF_BASE: Duration = Duration::from_millis(100);
+const RETRY_BACKOFF_MAX: Duration = Duration::from_secs(5);
+
+/// Sleep before re-issuing a retryable request.
+async fn backoff(attempt: usize) {
+    let delay = RETRY_BACKOFF_BASE
+        .saturating_mul(1u32 << attempt.min(8) as u32)
+        .min(RETRY_BACKOFF_MAX);
+    tokio::time::sleep(delay).await;
+}
+
+/// Whether the drain loop finished or needs the table re-claimed first.
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+enum CheckpointOutcome {
+    Done,
+    ReissueFromFlush,
+}
+
+/// What one LSM request produced: its value, or word that the owning node
+/// holds no claim and only `flush` can get it back.
+enum Attempt<T> {
+    Ok(T),
+    ReissueFromFlush,
+}
+
+/// Issue one LSM request, retrying in place while the fault is retryable.
+///
+/// The two recoverable faults have separate budgets: contention clears on its
+/// own and retries here against [`MAX_RETRIES`], while a 421 needs `flush` to
+/// re-claim, which only the caller can drive.
+///
+/// An exhausted budget propagates the last error *as itself* rather than a
+/// synthesized one — "429 after nine tries" beats "checkpoint failed", and a
+/// draining node arrives carrying the server's own message.
+async fn issue<T, F, Fut>(mut call: F) -> Result<Attempt<T>>
+where
+    F: FnMut() -> Fut,
+    Fut: Future<Output = Result<T>>,
+{
+    let mut retries = 0;
+    loop {
+        let e = match call().await {
+            Ok(value) => return Ok(Attempt::Ok(value)),
+            Err(e) => e,
+        };
+        if is_lost_claim(&e) {
+            return Ok(Attempt::ReissueFromFlush);
+        }
+        if !is_retryable(&e) || retries >= MAX_RETRIES {
+            return Err(e);
+        }
+        backoff(retries).await;
+        retries += 1;
+    }
+}
+
+/// Drive [`Table::checkpoint_lsm`]: seal once, fix the target watermark
+/// from the resulting L0, then trigger and poll until it drains.
+pub(crate) async fn checkpoint_lsm(table: &Table) -> Result<()> {
+    for reissue in 0..=MAX_REISSUES {
+        // The seal turns everything written before this call into a
+        // generation, so the watermark has to be read after it. Idempotent:
+        // sealing an empty memtable is a no-op, so a re-issue does not churn
+        // empty generations.
+        match issue(|| table.flush_lsm()).await? {
+            Attempt::Ok(()) => {}
+            Attempt::ReissueFromFlush => {
+                backoff(reissue).await;
+                continue;
+            }
+        }
+
+        let stats = match issue(|| table.get_lsm_stats(false)).await? {
+            Attempt::Ok(stats) => stats,
+            Attempt::ReissueFromFlush => {
+                backoff(reissue).await;
+                continue;
+            }
+        };
+        let Some(stats) = stats else {
+            // Not WAL-backed; `flush_lsm` would have errored first but for a race.
+            return Ok(());
+        };
+        let targets: HashMap<String, u64> = stats
+            .buckets
+            .iter()
+            .filter_map(|b| Some((b.shard_id.clone(), b.newest_generation()?)))
+            .collect();
+        if targets.is_empty() {
+            return Ok(());
+        }
+
+        match drain_to_targets(table, &targets).await? {
+            CheckpointOutcome::Done => return Ok(()),
+            CheckpointOutcome::ReissueFromFlush => {
+                backoff(reissue).await;
+                continue;
+            }
+        }
+    }
+    Err(Error::Runtime {
+        message: "checkpoint_lsm: the owning node kept losing its claim; \
+                  re-issued from flush the maximum number of times"
+            .into(),
+    })
+}
+
+/// Trigger and poll until no bucket holds a generation at or below its
+/// target.
+///
+/// No liveness bound, deliberately. The pod-wide compactor pool (a semaphore
+/// of 2 by default, shared across every table on the node) is taken *inside*
+/// the pass, after the bucket latch, so a checkpoint queued behind unrelated
+/// tables is indistinguishable from one that is merging. An idle-poll counter
+/// here could only ever have fired on a table that would have finished.
+async fn drain_to_targets(
+    table: &Table,
+    targets: &HashMap<String, u64>,
+) -> Result<CheckpointOutcome> {
+    loop {
+        let stats = match issue(|| table.get_lsm_stats(false)).await? {
+            Attempt::Ok(stats) => stats,
+            Attempt::ReissueFromFlush => return Ok(CheckpointOutcome::ReissueFromFlush),
+        };
+        let Some(stats) = stats else {
+            return Ok(CheckpointOutcome::Done);
+        };
+        // `compacting` is the bucket's compaction latch, held from dispatch
+        // until the pass ends — including while it waits on the pod-wide
+        // permit. So it answers one question only: do not pile on. Buckets
+        // with nothing outstanding are skipped, not counted as idle.
+        let mut outstanding = 0;
+        let mut all_compacting = true;
+        for b in &stats.buckets {
+            let Some(target) = targets.get(&b.shard_id) else {
+                continue;
+            };
+            let n = b.outstanding_generations(*target);
+            if n > 0 {
+                outstanding += n;
+                all_compacting &= b.compacting;
+            }
+        }
+        if outstanding == 0 {
+            return Ok(CheckpointOutcome::Done);
+        }
+
+        if !all_compacting {
+            match table.compact_lsm().await {
+                Ok(()) => {}
+                Err(e) if is_lost_claim(&e) => return Ok(CheckpointOutcome::ReissueFromFlush),
+                Err(e) if !is_retryable(&e) => return Err(e),
+                // A 429 here means the server could latch no bucket at all,
+                // which the poll above already handles. Not retried in place:
+                // the latch it would contend for is the one doing the work, so
+                // fall through and re-read — `POLL_INTERVAL` is the backoff.
+                Err(_) => {}
+            }
+        }
+        tokio::time::sleep(POLL_INTERVAL).await;
+    }
+}
+
+#[cfg(all(test, feature = "remote"))]
+mod tests {
+    use super::*;
+
+    fn http(status: u16) -> Error {
+        Error::Http {
+            source: "server said no".into(),
+            request_id: "rid".into(),
+            status_code: reqwest::StatusCode::from_u16(status).ok(),
+        }
+    }
+
+    /// Every status the loop acts on. The two predicates are checked together
+    /// because their overlap is what would be wrong: a status must never be
+    /// both, and 421 in particular must not read as retryable — retrying it in
+    /// place re-issues the call that just said the node holds no claim.
+    #[test]
+    fn taxonomy_round_trips() {
+        for status in [429, 503] {
+            assert!(is_retryable(&http(status)), "{status} must retry");
+            assert!(
+                !is_lost_claim(&http(status)),
+                "{status} is not a lost claim"
+            );
+        }
+        assert!(is_lost_claim(&http(421)), "a lost claim must re-claim");
+        assert!(
+            !is_retryable(&http(421)),
+            "retrying a lost claim in place only asks the same node again"
+        );
+        for status in [400, 404, 409, 500] {
+            assert!(!is_retryable(&http(status)), "{status} is terminal");
+            assert!(!is_lost_claim(&http(status)), "{status} is terminal");
+        }
+    }
+
+    /// An error carrying no status has no retry story and must be terminal —
+    /// a connection that never reached the server, or a `TableNotFound` that
+    /// `check_table_response` translated before the loop saw it.
+    #[test]
+    fn errors_without_a_status_are_terminal() {
+        let no_status = Error::Http {
+            source: "connection reset".into(),
+            request_id: "rid".into(),
+            status_code: None,
+        };
+        assert!(!is_retryable(&no_status));
+        assert!(!is_lost_claim(&no_status));
+
+        let translated = Error::TableNotFound {
+            name: "t".into(),
+            source: "gone".into(),
+        };
+        assert!(!is_retryable(&translated));
+        assert!(!is_lost_claim(&translated));
+    }
+}
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+//! Live per-bucket LSM state — the shape [`crate::Table::get_lsm_stats`]
+//! returns and [`super::checkpoint`] polls.
+//!
+//! Nothing here is derived: sums and differences (total L0 bytes, WAL lag)
+//! are the caller's to compute. There is no "WAL is off" shape — that case is
+//! `None`, because a struct of zeros would read as measurements.
+
+use serde::Deserialize;
+
+/// One flushed L0 generation.
+#[derive(Debug, Clone, Deserialize)]
+pub struct GenerationStats {
+    pub generation: u64,
+    pub bytes: u64,
+    /// Present only when `include_generation_rows` was requested. Off by
+    /// default because each count opens an uncached Lance dataset, and the
+    /// checkpoint loop polls this route needing only generation numbers.
+    #[serde(default)]
+    pub rows: Option<u64>,
+}
+
+/// One in-memory memtable.
+#[derive(Debug, Clone, Deserialize)]
+pub struct MemtableStats {
+    pub generation: u64,
+    pub rows: u64,
+    pub bytes: u64,
+    pub batches: u64,
+    /// Names of the indexes this memtable carries. An absent name is the whole
+    /// answer to "why is my fresh-tier search on that column brute-force".
+    pub indexes: Vec<String>,
+}
+
+/// Live state of one bucket. A table is N buckets on one node; flattening to
+/// a single number hides the one hot bucket that is usually why someone
+/// opened this endpoint.
+#[derive(Debug, Clone, Deserialize)]
+pub struct BucketStats {
+    pub shard_id: String,
+    /// `Active` | `Sealed` (drop-table 2PC in flight).
+    pub status: String,
+    pub writer_epoch: u64,
+    pub manifest_version: u64,
+    pub current_generation: u64,
+    pub replay_after_wal_entry_position: u64,
+    pub wal_entry_position_last_seen: u64,
+    pub generations: Vec<GenerationStats>,
+    /// Whether a pass owns this bucket's compaction latch right now. Says *a*
+    /// driver is running, not *whose*, and the latch is held from dispatch —
+    /// including while the pass queues for a pod-wide compactor permit. Read
+    /// it as "do not pile on", never as "mine is progressing".
+    pub compacting: bool,
+    /// Oldest first, active last. Absent for a `Sealed` bucket, whose
+    /// in-memory state is torn down.
+    #[serde(default)]
+    pub memtables: Option<Vec<MemtableStats>>,
+}
+
+impl BucketStats {
+    /// The newest flushed generation, or `None` when L0 is empty.
+    pub(crate) fn newest_generation(&self) -> Option<u64> {
+        self.generations.iter().map(|g| g.generation).max()
+    }
+
+    /// How many generations at or below `target` are still in L0.
+    ///
+    /// A count, not a boolean: one pass drains a bounded prefix rather than
+    /// the whole target set, so a boolean would read as "no progress" for
+    /// every pass but the last. Compaction drains oldest-first, so this
+    /// decreases monotonically.
+    pub(crate) fn outstanding_generations(&self, target: u64) -> usize {
+        self.generations
+            .iter()
+            .filter(|g| g.generation <= target)
+            .count()
+    }
+}
+
+/// Live LSM state, one entry per bucket.
+#[derive(Debug, Clone, Deserialize)]
+pub struct LsmStats {
+    pub buckets: Vec<BucketStats>,
+}
+
+/// Server-side JSON envelope for `get_lsm_stats`. `lsm_stats` is null when
+/// the table has no LSM write path.
+#[derive(Debug, Deserialize)]
+pub(crate) struct GetLsmStatsResponse {
+    #[serde(default)]
+    pub lsm_stats: Option<LsmStats>,
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn bucket(shard: &str, generations: &[u64], compacting: bool) -> BucketStats {
+        BucketStats {
+            shard_id: shard.into(),
+            status: "Active".into(),
+            writer_epoch: 1,
+            manifest_version: 1,
+            current_generation: generations.iter().max().copied().unwrap_or(0) + 1,
+            replay_after_wal_entry_position: 0,
+            wal_entry_position_last_seen: 0,
+            generations: generations
+                .iter()
+                .map(|g| GenerationStats {
+                    generation: *g,
+                    bytes: 1,
+                    rows: None,
+                })
+                .collect(),
+            compacting,
+            memtables: None,
+        }
+    }
+
+    /// The target watermark is the newest generation at the start, and a
+    /// generation created after it must not hold the loop open — that is why
+    /// the predicate terminates under write load.
+    #[test]
+    fn newer_generations_do_not_extend_the_target() {
+        let start = bucket("b0", &[7, 8], false);
+        let target = start.newest_generation().expect("L0 is non-empty");
+        assert_eq!(target, 8);
+
+        // Compaction drained 7 and 8; 9 and 10 arrived while it ran.
+        let later = bucket("b0", &[9, 10], false);
+        assert_eq!(
+            later.outstanding_generations(target),
+            0,
+            "generations above the target are somebody else's problem"
+        );
+
+        // Still holding 8 means still outstanding.
+        assert_eq!(
+            bucket("b0", &[8, 9], false).outstanding_generations(target),
+            1
+        );
+    }
+
+    /// The metric counts generations, not buckets: a pass drains a bounded
+    /// prefix, so one bucket going 3 → 2 → 1 → 0 is three steps.
+    #[test]
+    fn progress_is_measured_in_generations() {
+        let target = 3;
+        let counts: Vec<usize> = [&[1u64, 2, 3][..], &[2, 3][..], &[3][..], &[][..]]
+            .iter()
+            .map(|gens| bucket("b0", gens, false).outstanding_generations(target))
+            .collect();
+        assert_eq!(counts, vec![3, 2, 1, 0]);
+    }
+
+    #[test]
+    fn empty_l0_has_no_target() {
+        assert!(bucket("b0", &[], false).newest_generation().is_none());
+    }
+}
Author	SHA1	Message	Date
Lance Release	b89f87f206	Bump version: 0.37.1-beta.3 → 0.37.1	2026-08-10 07:54:42 +00:00
Lance Release	a022d3bcb3	Bump version: 0.37.1-beta.2 → 0.37.1-beta.3	2026-08-10 07:53:53 +00:00
Lance Release	8268532d64	Bump version: 0.37.1-beta.1 → 0.37.1-beta.2	2026-08-10 06:30:45 +00:00
Xuanwo	f933ef9b21	fix(ci): tag releases after updating lockfiles	2026-08-10 14:23:41 +08:00
Xuanwo	e885e5dd00	fix(ci): validate stable Lance dependencies	2026-08-10 14:23:33 +08:00
Xuanwo	7c7efa9743	feat: update lance dependency to v10.0.0	2026-08-10 14:23:29 +08:00
ForwardXu	12405a4077	chore: drop explicit goosefs-sdk pin in favor of opendal 0.58.1 transitive dep (#3910 ) ## Summary `opendal 0.58.1` (the version pulled in transitively via Lance) already ships `goosefs-sdk 0.1.9`, which includes the upstream fix for the 0.1.6 compile break. The explicit version pin that lancedb has been carrying since the GooseFS feature was introduced is therefore no longer necessary and is now redundant work to maintain. ## Changes - Remove the direct `goosefs-sdk` dependency from `rust/lancedb/Cargo.toml` (it was pinned to `=0.1.9` with a comment referencing the 0.1.6 compile break). - Remove the `dep:goosefs-sdk` entry from the `goosefs` cargo feature, since no source file in lancedb imports the crate directly. - Refresh `Cargo.lock`; `goosefs-sdk 0.1.9` now resolves transitively through `lance` → `opendal 0.58.1`. ## Verification - `cargo fmt --all` — clean - `cargo check --features remote,goosefs --tests --examples` — passes - `Cargo.lock` confirms `goosefs-sdk 0.1.9` is still resolved (now transitively), so the `goosefs` feature continues to enable the same set of Lance/IOPaths as before. ## Backwards compatibility No public API changes. The `goosefs` cargo feature still activates `lance/goosefs`, `lance-io/goosefs`, and `lance-namespace-impls/dir-goosefs`, and the same `goosefs-sdk 0.1.9` version is selected by the resolver.	2026-08-10 12:16:21 +08:00
lancedb-gatefixer[bot]	36054be576	fix(node): preserve nested Arrow data across versions (#3900 ) <!-- lance-gatekeeper-fix:v1 agent=613a074d606e626c5169d601373a32d8 generation=1 --> ## Root cause When LanceDB accepted an Arrow table created by a different installed Arrow package, its compatibility sanitizer rebuilt each Data node without converting the foreign type or preserving nested children. It also dropped the separate dictionary vector payload and did not preserve identity shared by dictionary schema types, vector wrappers, or growing dictionary chunks. ## Fix Recursively sanitize nested Arrow data types and child data. Use one table-scoped sanitization context to rebuild and memoize source type objects, dictionary vectors, and Data nodes in the local Arrow realm, preserving all identities required by Arrow IPC. Add Arrow 15 through 18 regressions for list serialization, ordinary dictionaries, dictionaries shared across fields and batches, growing dictionaries, and IPC round trips. ## Validation - pnpm test __test__/arrow.test.ts --runInBand (188 passed) - pnpm lint - pnpm build - pnpm test --runInBand (706 passed, 5 skipped) - pnpm run docs Fixes #2256 --------- Co-authored-by: Gatefixer <313497061+lancedb-gatefixer[bot]@users.noreply.github.com>	2026-08-09 03:34:39 +08:00
Dan Tasse	77a93fee76	fix: get table size from metadata, not files (#3790 ) Some issues: - file_size_bytes is optional in the manifest, so if it's not there (old writer I guess) it'll under-report the table size. - it changes results a little bit from the old way by including per-file footers and metadata (probably not a big difference at real scale) --------- Co-authored-by: Will Jones <willjones127@gmail.com>	2026-08-07 17:41:41 -04:00
Lance Release	7bb501839a	Bump version: 0.37.1-beta.0 → 0.37.1-beta.1	2026-08-07 21:16:07 +00:00
Andrew Chen	5b347afd99	fix: avoid AttributeError in JinaEmbeddings image input for str/Path (#3670 ) ## What `JinaEmbeddings._generate_image_input_dict()` crashes with `AttributeError: 'function' object has no attribute 'urlparse'` on any image given as a URL string, local path string, or `pathlib.Path` — i.e. every documented `jina-clip-v1` image-embedding use case except raw `bytes`. ## Why ```python from urllib.parse import urlparse ... parsed = urlparse.urlparse(image) ``` `urlparse` is imported as a function, then called as if it were the `urllib.parse` module (`urlparse.urlparse(...)`). The module-level `is_valid_url()` a few lines above does it correctly (`urlparse(text)`), which is why this reads as a typo rather than intentional. Fixed to `urlparse(str(image))` — `str()` is needed because `urlparse()` only accepts `str`/`bytes` and raises a different `AttributeError` on a raw `Path`. ## Testing Added `test_jina_generate_image_input_dict_local_path`, which fails with the original `AttributeError` before the fix and passes after, covering both a `str` path and a `pathlib.Path`. Verified locally (built the Rust extension, ran red→green, then the full `test_embeddings.py` file: 15 passed / 8 skipped, no regressions) and with `ruff check`/`ruff format`. --- Disclosure: this PR was drafted with AI assistance (Claude); I reviewed, tested, and take responsibility for the change. --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>	2026-08-07 14:05:45 -07:00
Dan Rammer	706a9c327f	feat: infer maintained indexes when an LsmWriteSpec omits them (#3748 ) ## What `LsmWriteSpec::maintained_indexes` becomes `Option<Vec<String>>`: \| value \| meaning \| \|---\|---\| \| `None` (new default) \| every index the MemWAL supports, resolved when the spec is installed \| \| `Some([])` \| maintain nothing — a scan/filter-only WAL table \| \| `Some([..])` \| exactly these, taken verbatim \| `with_maintained_indexes` keeps its signature; `with_no_maintained_indexes()` is new. Surfaced through the remote path (null on the wire), Python, and Node. ## Why Callers had to state the maintained set by hand every time, which is both tedious and easy to get wrong — the common case is "maintain what I already built." Resolution filters on `IndexConfig::is_memwal_maintainable`, delegating to lance's `is_maintainable_index_type`. This is load-bearing rather than cosmetic: lance does not skip an index type its memtable cannot build, it errors when the shard writer opens, so sweeping up a bitmap index would fail every memtable claim and leave the table unwritable. The inferred set excludes those, and an explicit list naming one is now rejected at spec time instead of at claim time. ## Behavior change A freshly constructed spec used to maintain nothing; it now maintains everything supported. This flipped because napi collapses `undefined` and `null` to `None`, so TypeScript cannot express "absent means nothing, null means all" — any other choice makes the bindings disagree with the wire. The error direction also favors it: an unwanted maintained index costs memory, while a silently unmaintained one degrades FTS to an unscored scan. Three existing tests encoded the old default and are updated rather than worked around. ## Caveat The resolved set is a snapshot, not a subscription. An index created after the spec is installed is not maintained until the spec is unset and set again. `get_lsm_write_spec` therefore always reports a concrete list — `None` never round-trips. ## Dependency Needs a lance release carrying `is_maintainable_index_type` (lance-format/lance#8095) before this builds against the pinned tag. Draft until then. ## Testing 38 Rust LSM tests and 10 Python tests pass against a local lance build, including new coverage that a bitmap index is excluded from inference and rejected when named, and that `[]` stays distinguishable from null on the wire. 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>	2026-08-07 14:50:22 -05:00
LanceDB Robot	be290447d9	chore: update lance dependency to v11.0.0-beta.3 (#3896 ) Updates the Rust workspace Lance dependencies and Java lance-core dependency to v11.0.0-beta.3. No compatibility fixes were required; all-features clippy and Rust formatting pass. Triggering tag: https://github.com/lance-format/lance/releases/tag/v11.0.0-beta.3	2026-08-07 13:54:32 -05:00
Dan Rammer	79ba076429	feat(table): checkpoint_lsm, flush_lsm, compact_lsm, get_lsm_stats (#3736 ) Converge a table's LSM write path into its base table, and inspect it. `checkpoint_lsm` is `flush` then `compact`, repeated until the fresh tier is empty — and the loop runs client-side. Putting it on the server would mean a background task, which means a single-flight intent, an intent that leaks on panic, a bounded-iteration policy, an "is it done" observable, and a story for every way a client can vanish mid-operation. None of that exists in this shape: each request does a bounded unit of work and reports what is left, so completion is carried in the responses rather than inferred from a shared counter that cannot distinguish "converged" from "hasn't started yet". Best-effort by construction. Nothing is frozen, so `converged` means L0 was empty as of the last pass. It is idempotent, abandonable at any point with zero consequence, and safe to run on a cadence — an already-converged table costs one round trip and zero compaction passes, because `flush` reports `generations_remaining` and the loop is never entered. ## The failure taxonomy is the load-bearing part Five distinct conditions used to arrive at a client as one 503. `Error::LsmRoute` carries a classification read from the response body's namespace error code at the point of receipt — before any generic helper folds the body into a string and keeps only the status. \| condition \| wire \| client action \| \|---\|---\|---\| \| contention (latch held / pool saturated) \| 429, code 21 \| retry with backoff \| \| owning node draining \| 503, code 19 `InvalidTableState` \| stop \| \| fenced / no slot / transport \| 503, code 17 \| retry with backoff \| \| registry entry vanished \| 404 \| re-issue from `flush` (capped) \| \| table being dropped / not WAL-backed \| 409 / 400 \| stop \| Draining is terminal because the drain gate is a one-way latch — retrying spins until the deadline to report a failure that was knowable on the first response. Transport retry is disabled on these routes for the same reason: it treats every 503 alike and would burn its budget before the classifier ever saw the body. `get_lsm_stats` returns `Option<LsmStats>`, matching `get_lsm_write_spec` — `None` only when the table has no LSM write path, since a struct of zeros would read as measurements. Python bindings mirror all four, preserving per-bucket detail rather than flattening to a table-level summary. ## Testing Six new unit tests against the mocked endpoint, plus the taxonomy round-trip: - flush into an empty L0 issues zero compact calls (asserts the call count — `generations_consumed: 0` is also true of a loop that ran a pointless pass) - the loop drives compact until the server reports zero remaining - contention is not draining: a 429 retries and converges; asserts the retry count - a draining node stops after exactly one request, no retries - stats round-trips fully populated; `include_generation_rows` off by default - every `(status, code)` pair classifies correctly, including unparseable 503 bodies falling back to retryable rather than terminal `cargo test -p lancedb --features remote --lib`: 723 passed. ## Notes for review - Depends on the sibling lance change returning `SealedGeneration` from `force_seal_active` only at the server level — no lance API is used here. - The branch is based on `codex/update-lance-10-0-0-beta-5`, so it carries one extra commit (`chore: update lance dependency to v10.0.0-beta.5`) that is not part of this change. 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: lancedb automation <robot@lancedb.com> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>	2026-08-07 13:44:49 -05:00