refactor(lsm): remove the index-catchup activation surface

Follows the lance change that removes the feature bit. With one set of semantics there is no mode to switch into, so `require_mem_wal_index_catchup` goes from the trait, `NativeTable`, and the LSM merge module. `exclusion_watermarks` loses its `catchup_required` argument and keeps the conservative branch: an index with no `index_catchup` entry is not known to hold the compacted rows, so its generations stay readable from their SSTables. That is what makes an existing table safe to read the moment the new binary starts -- nothing is excluded until an index records that it covers it. Two tests changed because they encoded the branch that is gone, and they had conflated two different things: an index that is *caught up* and an index that is *untracked* both fell back to the compaction watermark. Untracked now retains everything, so the tests assert that and cover the genuinely-caught-up case separately. 484 lancedb lib tests pass.
feat(lsm): move catch-up activation to an explicit API
2026-08-27 16:38:31 +00:00 · 2026-08-20 18:29:56 -04:00 · 2026-08-10 09:10:05 -04:00 · 2026-08-09 23:19:21 -04:00 · 2026-08-02 00:12:47 +00:00
8 changed files with 415 additions and 264 deletions
@@ -775,7 +775,7 @@ dependencies = [
 "http 0.2.12",
 "http 1.4.2",
 "http-body 1.1.0",
- "lru",
+ "lru 0.16.4",
 "percent-encoding",
 "regex-lite",
 "sha2 0.11.0",
@@ -1241,6 +1241,12 @@ version = "0.22.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"

+[[package]]
+name = "base64"
+version = "0.23.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b25655df2c3cdd83c5e5b293b88acd880332b2ddadd7c30ac43144fdc0033da9"
+
 [[package]]
 name = "base64-simd"
 version = "0.8.0"
@@ -1964,15 +1970,6 @@ 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"
@@ -2174,9 +2171,9 @@ dependencies = [

 [[package]]
 name = "ctor"
-version = "1.0.5"
+version = "1.0.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "378f0974ae2468eaf63aa036dbe9c926b0dc7ea64c156f2ea618bc2f75b934f0"
+checksum = "2d83cb7e7a873830708d6b02a78cd36a592c6fa14bf267b68725103b85c0d77f"
 dependencies = [
 "link-section",
 "linktime-proc-macro",
@@ -2902,6 +2899,37 @@ dependencies = [
 "uuid",
 ]

+[[package]]
+name = "defmt"
+version = "1.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e2953bfe4f93bbd20cc71198842756f77d161884c99ebbabc41d80231ded88d1"
+dependencies = [
+ "bitflags 1.3.2",
+ "defmt-macros",
+]
+
+[[package]]
+name = "defmt-macros"
+version = "1.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bad9c72e7ca2137e0dc3813245a0d282fd6daad32fd800af018306a9169b5fe8"
+dependencies = [
+ "defmt-parser",
+ "proc-macro2",
+ "quote",
+ "syn 2.0.117",
+]
+
+[[package]]
+name = "defmt-parser"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "10d60334b3b2e7c9d91ef8150abfb6fa4c1c39ebbcf4a81c2e346aad939fee3e"
+dependencies = [
+ "thiserror 2.0.18",
+]
+
 [[package]]
 name = "der"
 version = "0.6.1"
@@ -3421,8 +3449,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"

 [[package]]
 name = "fsst"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arrow-array",
 "rand 0.9.5",
@@ -3779,14 +3807,22 @@ dependencies = [

 [[package]]
 name = "goosefs-sdk"
-version = "0.1.5"
+version = "0.1.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9ae079b88ffe7772d12cfc5c40a5a324babb357893d95b5e3a22ae857f236c5f"
+checksum = "4a9bc9414e3b2cb0bd08dfe0eb315b177e86b119c7fa5e16179c92fc7b184860"
 dependencies = [
+ "arc-swap",
 "async-trait",
 "bytes",
 "dashmap",
+ "futures",
 "hostname",
+ "io-uring",
+ "itoa",
+ "libc",
+ "lru 0.12.5",
+ "memmap2 0.9.10",
+ "moka",
 "prost",
 "prost-types",
 "rand 0.9.5",
@@ -3799,6 +3835,7 @@ dependencies = [
 "tonic-prost",
 "tracing",
 "uuid",
+ "xxhash-rust",
 ]

 [[package]]
@@ -3888,6 +3925,8 @@ version = "0.15.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9229cfe53dfd69f0609a49f65461bd93001ea1ef889cd5529dd176593f5338a1"
 dependencies = [
+ "allocator-api2",
+ "equivalent",
 "foldhash 0.1.5",
 ]

@@ -4599,10 +4638,12 @@ dependencies = [

 [[package]]
 name = "jiff"
-version = "0.2.24"
+version = "0.2.35"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f00b5dbd620d61dfdcb6007c9c1f6054ebd75319f163d886a9055cec1155073d"
+checksum = "668b7183bd07af9a4885f5c35b0cc5c83c4607a913c16b7e17291832910d2dcc"
 dependencies = [
+ "defmt",
+ "jiff-core",
 "jiff-static",
 "jiff-tzdb-platform",
 "js-sys",
@@ -4611,15 +4652,25 @@ dependencies = [
 "portable-atomic-util",
 "serde_core",
 "wasm-bindgen",
- "windows-sys 0.61.2",
+ "windows-link",
+]
+
+[[package]]
+name = "jiff-core"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7feca88439efe53da3754500c1851dedf3cb36c524dd5cf8225cc0794de95d09"
+dependencies = [
+ "defmt",
 ]

 [[package]]
 name = "jiff-static"
-version = "0.2.24"
+version = "0.2.35"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e000de030ff8022ea1da3f466fbb0f3a809f5e51ed31f6dd931c35181ad8e6d7"
+checksum = "3a69dcb3a21cfb32ce1cd056169337ca284af0766dd766e7878819b251a49204"
 dependencies = [
+ "jiff-core",
 "proc-macro2",
 "quote",
 "syn 2.0.117",
@@ -4731,24 +4782,6 @@ dependencies = [
 "zmij",
 ]

-[[package]]
-name = "jsonwebtoken"
-version = "10.4.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "eba32bfb4ffdeaca3e34431072faf01745c9b26d25504aa7a6cf5684334fc4fc"
-dependencies = [
- "aws-lc-rs",
- "base64 0.22.1",
- "getrandom 0.2.17",
- "js-sys",
- "pem",
- "serde",
- "serde_json",
- "signature 2.2.0",
- "simple_asn1",
- "zeroize",
-]
-
 [[package]]
 name = "kanaria"
 version = "0.2.0"
@@ -4777,8 +4810,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a"

 [[package]]
 name = "lance"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arc-swap",
 "arrow",
@@ -4852,8 +4885,8 @@ dependencies = [

 [[package]]
 name = "lance-arrow"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4875,7 +4908,7 @@ dependencies = [
 [[package]]
 name = "lance-arrow-scalar"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4889,7 +4922,7 @@ dependencies = [
 [[package]]
 name = "lance-arrow-stats"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -4898,8 +4931,8 @@ dependencies = [

 [[package]]
 name = "lance-bitpacking"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arrayref",
 "crunchy",
@@ -4909,8 +4942,8 @@ dependencies = [

 [[package]]
 name = "lance-core"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4950,8 +4983,8 @@ dependencies = [

 [[package]]
 name = "lance-datafusion"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -4981,8 +5014,8 @@ dependencies = [

 [[package]]
 name = "lance-datagen"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -4999,8 +5032,8 @@ dependencies = [

 [[package]]
 name = "lance-derive"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "proc-macro2",
 "quote",
@@ -5009,8 +5042,8 @@ dependencies = [

 [[package]]
 name = "lance-encoding"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -5045,8 +5078,8 @@ dependencies = [

 [[package]]
 name = "lance-file"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -5077,8 +5110,8 @@ dependencies = [

 [[package]]
 name = "lance-index"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arc-swap",
 "arrow",
@@ -5145,8 +5178,8 @@ dependencies = [

 [[package]]
 name = "lance-index-core"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -5168,8 +5201,8 @@ dependencies = [

 [[package]]
 name = "lance-io"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5181,7 +5214,6 @@ dependencies = [
 "bytes",
 "chrono",
 "futures",
- "goosefs-sdk",
 "http 1.4.2",
 "io-uring",
 "lance-arrow",
@@ -5206,8 +5238,8 @@ dependencies = [

 [[package]]
 name = "lance-linalg"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -5223,8 +5255,8 @@ dependencies = [

 [[package]]
 name = "lance-namespace"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arrow",
 "async-trait",
@@ -5236,8 +5268,8 @@ dependencies = [

 [[package]]
 name = "lance-namespace-impls"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arrow",
 "arrow-ipc",
@@ -5291,8 +5323,8 @@ dependencies = [

 [[package]]
 name = "lance-select"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -5307,8 +5339,8 @@ dependencies = [

 [[package]]
 name = "lance-table"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5347,8 +5379,8 @@ dependencies = [

 [[package]]
 name = "lance-testing"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -5361,8 +5393,8 @@ dependencies = [

 [[package]]
 name = "lance-tokenizer"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "10.1.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.2#94cca93d13b1c731afd6660d46ad2f8d4b4345c4"
 dependencies = [
 "icu_segmenter",
 "jieba-rs",
@@ -5682,15 +5714,15 @@ dependencies = [

 [[package]]
 name = "link-section"
-version = "0.16.1"
+version = "0.19.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5c8600ca3dbe044f07955b443ff606c50f45295b863289bbe7d0844d50cf11e4"
+checksum = "5ee1a0d6e252afe82e7bc2db42fba60e02ddf3b1accaf8cb21d96e34ba61f3d4"

 [[package]]
 name = "linktime-proc-macro"
-version = "0.1.0"
+version = "0.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a44cd706ff0d503ee32b2071166510ca27e281228de10cd3aa8d35ff94560f81"
+checksum = "348d0075b1fc163b26d72a7f75fc5141daf2fd1bdf128d873cbaf6785d495bdf"

 [[package]]
 name = "linux-raw-sys"
@@ -5738,6 +5770,15 @@ dependencies = [
 "tracing-subscriber",
 ]

+[[package]]
+name = "lru"
+version = "0.12.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "234cf4f4a04dc1f57e24b96cc0cd600cf2af460d4161ac5ecdd0af8e1f3b2a38"
+dependencies = [
+ "hashbrown 0.15.5",
+]
+
 [[package]]
 name = "lru"
 version = "0.16.4"
@@ -6067,7 +6108,7 @@ checksum = "de33522036981030a75c231829566bc63414e08101a6f5ff4ac6cef19c8e0941"
 dependencies = [
 "bitflags 2.11.1",
 "chrono",
- "ctor 1.0.5",
+ "ctor 1.0.12",
 "futures",
 "napi-build",
 "napi-sys",
@@ -6091,7 +6132,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a49c513341a61a16a10af6efcce46b30d0822ba2d4fb197d24d33dfc199c78d5"
 dependencies = [
 "convert_case",
- "ctor 1.0.5",
+ "ctor 1.0.12",
 "napi-derive-backend",
 "proc-macro2",
 "quote",
@@ -6384,9 +6425,9 @@ dependencies = [

 [[package]]
 name = "object_store_opendal"
-version = "0.57.0"
+version = "0.58.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0eb12a624a41fce745838d0ef3701ff6c47797c13cd18ad3612fd2a3134fdbd8"
+checksum = "88f165780495c17aa3ce86846600504198c3fffd99073521552751c2430fa6ac"
 dependencies = [
 "async-trait",
 "bytes",
@@ -6447,12 +6488,13 @@ checksum = "d6790f58c7ff633d8771f42965289203411a5e5c68388703c06e14f24770b41e"

 [[package]]
 name = "opendal"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "96c9c85ce253ff87225e7669979d877a20c98a06604ec9d6dd5f4473e08f1ae1"
+checksum = "4f20562cc7447fcc915fc5c23df305a412ea80a733c9f2fd9e2d267e2815be6d"
 dependencies = [
- "ctor 1.0.5",
+ "ctor 1.0.12",
 "opendal-core",
+ "opendal-http-transport-reqwest",
 "opendal-layer-concurrent-limit",
 "opendal-layer-logging",
 "opendal-layer-retry",
@@ -6469,24 +6511,22 @@ dependencies = [

 [[package]]
 name = "opendal-core"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c4f8607c90e2c963a91467f50fb49fbc7fb3d573f88cea219ca59ccd3740b309"
+checksum = "ec75551ff4cf3e57da98979f6a937aaa9ddb3915bf68cc17d03df733be6646ed"
 dependencies = [
 "anyhow",
- "base64 0.22.1",
+ "base64 0.23.0",
 "bytes",
 "futures",
 "http 1.4.2",
- "http-body 1.1.0",
 "jiff",
 "log",
 "md-5 0.11.0",
 "mea",
 "percent-encoding",
- "quick-xml 0.39.4",
+ "quick-xml 0.41.0",
 "reqsign-core",
- "reqwest 0.13.3",
 "serde",
 "serde_json",
 "tokio",
@@ -6496,10 +6536,24 @@ dependencies = [
 ]

 [[package]]
-name = "opendal-layer-concurrent-limit"
-version = "0.57.0"
+name = "opendal-http-transport-reqwest"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0d6f81ba6960e3fae1882f253b114b21d7e444e1534f209c7737a79f6243eb6f"
+checksum = "ad4d4f19c3ce01126a30611f8e544eaa217104a278c889ac17c9374fe4f9e4ef"
+dependencies = [
+ "bytes",
+ "futures",
+ "http 1.4.2",
+ "http-body 1.1.0",
+ "opendal-core",
+ "reqwest 0.13.4",
+]
+
+[[package]]
+name = "opendal-layer-concurrent-limit"
+version = "0.58.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "249ac5b0aa5a7a6c3737342d10456067937f9c9a6f3f02544271f7908ab91081"
 dependencies = [
 "futures",
 "http 1.4.2",
@@ -6509,9 +6563,9 @@ dependencies = [

 [[package]]
 name = "opendal-layer-logging"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "58ada45c6d81d1aa4c9305d0c7d4bc317c59c85866a0908a2d75a7a978aa5ee2"
+checksum = "5c75411ab00f77851ff086b686c1e9ca8175ac18c15afa2cb75b9036436cb06c"
 dependencies = [
 "log",
 "opendal-core",
@@ -6519,9 +6573,9 @@ dependencies = [

 [[package]]
 name = "opendal-layer-retry"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7b2a25a718afb81fad81cb9a0580a1cb989221fa2317f888c6a37f8dad408eb7"
+checksum = "80b7738bd5f233ad8da39af9b9316b9b7a4eaddd91e8e32a1e19b7030688121d"
 dependencies = [
 "backon",
 "log",
@@ -6530,9 +6584,9 @@ dependencies = [

 [[package]]
 name = "opendal-layer-timeout"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1e91f731724c213af81e9d03517859c8fc47b4578e64ad61ae4f099f10fe36e3"
+checksum = "a704141924500f3803c05ed871b53305d2a2f11cb5ef20160c3ee688a1857f66"
 dependencies = [
 "opendal-core",
 "tokio",
@@ -6540,17 +6594,17 @@ dependencies = [

 [[package]]
 name = "opendal-service-azblob"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0030644366ef5d8cbe3a4a5822bf99a4aafddc1666e9d24b44d158d9062fc76a"
+checksum = "b3310fbbb48f111c6f590473c2cd15e1b7f8e384444b0d4e328f0464c864d767"
 dependencies = [
- "base64 0.22.1",
+ "base64 0.23.0",
 "bytes",
 "http 1.4.2",
 "log",
 "opendal-core",
 "opendal-service-azure-common",
- "quick-xml 0.39.4",
+ "quick-xml 0.41.0",
 "reqsign-azure-storage",
 "reqsign-core",
 "reqsign-file-read-tokio",
@@ -6561,17 +6615,18 @@ dependencies = [

 [[package]]
 name = "opendal-service-azdls"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6dea4908d490143a9b0b7f7a790e139ff829b06a023f670455ed3d44f664b361"
+checksum = "2e3c406729935fe214ce574d68681a1ff7e0b322548f14094912bdbfe50e5c53"
 dependencies = [
- "base64 0.22.1",
+ "base64 0.23.0",
 "bytes",
 "http 1.4.2",
 "log",
+ "mea",
 "opendal-core",
 "opendal-service-azure-common",
- "quick-xml 0.39.4",
+ "quick-xml 0.41.0",
 "reqsign-azure-storage",
 "reqsign-core",
 "reqsign-file-read-tokio",
@@ -6581,9 +6636,9 @@ dependencies = [

 [[package]]
 name = "opendal-service-azure-common"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9b489f13c42e69d69bdd72952b634356ec43a7881a20259b38b540fcecdf4051"
+checksum = "7348c88edf15af435b7be930077746b569fac5e738c1bf6a363b675e7317c9df"
 dependencies = [
 "http 1.4.2",
 "opendal-core",
@@ -6591,15 +6646,15 @@ dependencies = [

 [[package]]
 name = "opendal-service-cos"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "aa8cafe9729213375c7331019b0cb756ad3e1aff7f45cd32c45eae91ebde8901"
+checksum = "d533d4582105d269c8aebeee5f0e8bcf960f41b8aab6197df7012254d9f39bf0"
 dependencies = [
 "bytes",
 "http 1.4.2",
 "log",
 "opendal-core",
- "quick-xml 0.39.4",
+ "quick-xml 0.41.0",
 "reqsign-core",
 "reqsign-file-read-tokio",
 "reqsign-tencent-cos",
@@ -6608,9 +6663,9 @@ dependencies = [

 [[package]]
 name = "opendal-service-gcs"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "48de101aac565ed06af4b47903c24eafd249075553ec1fb18256751c45148d47"
+checksum = "007f3fba63c21e516c956b891e96ff9892d8175662bfb781cdada9d3766a11e6"
 dependencies = [
 "async-trait",
 "bytes",
@@ -6618,7 +6673,7 @@ dependencies = [
 "log",
 "opendal-core",
 "percent-encoding",
- "quick-xml 0.39.4",
+ "quick-xml 0.41.0",
 "reqsign-core",
 "reqsign-file-read-tokio",
 "reqsign-google",
@@ -6629,9 +6684,9 @@ dependencies = [

 [[package]]
 name = "opendal-service-goosefs"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "69e43048bde419947ba826fbdc2f134d6c03f44ebf48bd33a03b72f9fc45fcb4"
+checksum = "60871e6386f04d831e6a5bdbc032af4a91aeba49963252d0ef456a2cf36a9b78"
 dependencies = [
 "bytes",
 "goosefs-sdk",
@@ -6643,9 +6698,9 @@ dependencies = [

 [[package]]
 name = "opendal-service-hf"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c4922661976a1d40794a2adfbdb888cc3c23097690f825a92f773af38908a848"
+checksum = "b41fd41eb7ed03c5e66cefda61e8e117808ffd2908f2916737cb020a6beb02c7"
 dependencies = [
 "bytes",
 "hf-xet",
@@ -6653,22 +6708,21 @@ dependencies = [
 "log",
 "opendal-core",
 "percent-encoding",
- "reqwest 0.13.3",
 "serde",
 "serde_json",
 ]

 [[package]]
 name = "opendal-service-oss"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "328fa55e8888cbdfe00826bfea2a79042422b720e8369e9e021e46121dea5ace"
+checksum = "cd528ec2d49c5ca69e674ffed7b3e0686fb9cfcfea0596870de381467fda4f1b"
 dependencies = [
 "bytes",
 "http 1.4.2",
 "log",
 "opendal-core",
- "quick-xml 0.39.4",
+ "quick-xml 0.41.0",
 "reqsign-aliyun-oss",
 "reqsign-core",
 "reqsign-file-read-tokio",
@@ -6677,18 +6731,18 @@ dependencies = [

 [[package]]
 name = "opendal-service-s3"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "313d46c9f5ae70bca26b7c3e3fbb9b639292625f28af73aa016f47e788af9deb"
+checksum = "58e80cdf192d7eff05feed747894d64f81905ac4eaf132edf7ea270abdd2d663"
 dependencies = [
- "base64 0.22.1",
+ "base64 0.23.0",
 "bytes",
- "crc32c",
+ "crc-fast",
 "http 1.4.2",
 "log",
 "md-5 0.11.0",
 "opendal-core",
- "quick-xml 0.39.4",
+ "quick-xml 0.41.0",
 "reqsign-aws-v4",
 "reqsign-core",
 "reqsign-file-read-tokio",
@@ -7799,6 +7853,16 @@ dependencies = [
 "memchr",
 ]

+[[package]]
+name = "quick-xml"
+version = "0.41.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e660451e55124f798a69a5af3f49ccfbefbd41910eefd25caf2393e1f3473ec1"
+dependencies = [
+ "memchr",
+ "serde",
+]
+
 [[package]]
 name = "quick_cache"
 version = "0.6.24"
@@ -8220,9 +8284,9 @@ dependencies = [

 [[package]]
 name = "reqsign-aliyun-oss"
-version = "3.0.0"
+version = "3.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "57ac2757f3140aa2e213b554148ae0b52733e624fc6723f0cc6bb3d440176c95"
+checksum = "9c0f9f69a519dd6958c4b43606bb8e1278cdc76d611fc8fed4b796eee548dc0f"
 dependencies = [
 "anyhow",
 "form_urlencoded",
@@ -8237,37 +8301,37 @@ dependencies = [

 [[package]]
 name = "reqsign-aws-v4"
-version = "3.0.0"
+version = "3.0.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "44eaca382e94505a49f1a4849658d153aebf79d9c1a58e5dd3b10361511e9f43"
+checksum = "cc883bc56889f3e4a419265c87facea222a921debc5c6f15c7fd8b68ec4b36b2"
 dependencies = [
 "anyhow",
 "bytes",
 "form_urlencoded",
+ "hex",
 "http 1.4.2",
 "log",
 "percent-encoding",
- "quick-xml 0.39.4",
+ "quick-xml 0.41.0",
 "reqsign-core",
 "rust-ini",
 "serde",
 "serde_json",
 "serde_urlencoded",
- "sha1 0.10.6",
+ "sha1 0.11.0",
 ]

 [[package]]
 name = "reqsign-azure-storage"
-version = "3.0.0"
+version = "3.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7a321980405d596bd34aaf95c4722a3de4128a67fd19e74a81a83aa3fdf082e6"
+checksum = "a6ebd8524185ce9c64063e3095f83968acfa90922f00c601a4a0f3aca15b077e"
 dependencies = [
 "anyhow",
 "base64 0.22.1",
 "bytes",
 "form_urlencoded",
 "http 1.4.2",
- "jsonwebtoken",
 "log",
 "pem",
 "percent-encoding",
@@ -8275,36 +8339,38 @@ dependencies = [
 "rsa",
 "serde",
 "serde_json",
- "sha1 0.10.6",
+ "sha1 0.11.0",
 ]

 [[package]]
 name = "reqsign-core"
-version = "3.0.0"
+version = "3.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b10302cf0a7d7e7352ba211fc92c3c5bebf1286153e49cc5aa87348078a8e102"
+checksum = "7e38b44697c60a823705ccef85cb04d8e0527c9d16ed7c58bf1c6395bdd24ceb"
 dependencies = [
 "anyhow",
 "base64 0.22.1",
 "bytes",
- "form_urlencoded",
 "futures",
 "hex",
- "hmac 0.12.1",
+ "hmac 0.13.0",
 "http 1.4.2",
 "jiff",
 "log",
 "percent-encoding",
- "sha1 0.10.6",
- "sha2 0.10.9",
+ "rsa",
+ "serde",
+ "serde_json",
+ "sha1 0.11.0",
+ "sha2 0.11.0",
 "windows-sys 0.61.2",
 ]

 [[package]]
 name = "reqsign-file-read-tokio"
-version = "3.0.0"
+version = "3.0.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e2d89295b3d17abea31851cc8de55d843d89c52132c864963c38d41920613dc5"
+checksum = "688ff0ae421b8d4b92b53fdafaf53df2de28f428a9962edcf21702990b26f74b"
 dependencies = [
 "anyhow",
 "reqsign-core",
@@ -8313,13 +8379,12 @@ dependencies = [

 [[package]]
 name = "reqsign-google"
-version = "3.0.0"
+version = "3.0.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "35cc609b49c69e76ecaceb775a03f792d1ed3e7755ab3548d4534fd801e3242e"
+checksum = "a96da0b579b846d358090cb06b9e3c2ad1375529efbe3e0c45f96bd7bcf043ea"
 dependencies = [
 "form_urlencoded",
 "http 1.4.2",
- "jsonwebtoken",
 "log",
 "percent-encoding",
 "reqsign-aws-v4",
@@ -8327,15 +8392,14 @@ dependencies = [
 "rsa",
 "serde",
 "serde_json",
- "sha2 0.10.9",
 "tokio",
 ]

 [[package]]
 name = "reqsign-tencent-cos"
-version = "3.0.0"
+version = "3.0.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e128f19525861dbded59e1e7c17653a8ed63d573ca04aed708d552dbef5bb32a"
+checksum = "f6497dd9f6e3d1349b420521484099b284f95e8d3a65f088fccef42493a7b644"
 dependencies = [
 "anyhow",
 "http 1.4.2",
@@ -8394,9 +8458,9 @@ dependencies = [

 [[package]]
 name = "reqwest"
-version = "0.13.3"
+version = "0.13.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "62e0021ea2c22aed41653bc7e1419abb2c97e038ff2c33d0e1309e49a97deec0"
+checksum = "219c5811de6525e5416c7d5d53bb656d3afdbc6c5af816e0802bcfa42dbdc1c3"
 dependencies = [
 "base64 0.22.1",
 "bytes",
@@ -8457,7 +8521,7 @@ dependencies = [
 "anyhow",
 "async-trait",
 "http 1.4.2",
- "reqwest 0.13.3",
+ "reqwest 0.13.4",
 "thiserror 2.0.18",
 "tower-service",
 ]
@@ -9206,18 +9270,6 @@ version = "0.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e3a9fe34e3e7a50316060351f37187a3f546bce95496156754b601a5fa71b76e"

-[[package]]
-name = "simple_asn1"
-version = "0.6.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0d585997b0ac10be3c5ee635f1bab02d512760d14b7c468801ac8a01d9ae5f1d"
-dependencies = [
- "num-bigint",
- "num-traits",
- "thiserror 2.0.18",
- "time",
-]
-
 [[package]]
 name = "siphasher"
 version = "1.0.3"
@@ -11161,7 +11213,7 @@ dependencies = [
 "more-asserts",
 "rand 0.10.1",
 "redb",
- "reqwest 0.13.3",
+ "reqwest 0.13.4",
 "reqwest-middleware",
 "serde",
 "serde_json",
@@ -11274,7 +11326,7 @@ dependencies = [
 "oneshot",
 "pin-project",
 "rand 0.10.1",
- "reqwest 0.13.3",
+ "reqwest 0.13.4",
 "serde",
 "serde_json",
 "shellexpand",
@@ -11370,20 +11422,6 @@ name = "zeroize"
 version = "1.8.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b97154e67e32c85465826e8bcc1c59429aaaf107c1e4a9e53c8d8ccd5eff88d0"
-dependencies = [
- "zeroize_derive",
-]
-
-[[package]]
-name = "zeroize_derive"
-version = "1.4.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "85a5b4158499876c763cb03bc4e49185d3cccbabb15b33c627f7884f43db852e"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn 2.0.117",
-]

 [[package]]
 name = "zerotrie"
@@ -13,20 +13,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"

 [workspace.dependencies]
-lance = { "version" = "=10.1.0-beta.1", default-features = false, "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=10.1.0-beta.1", default-features = false, "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=10.1.0-beta.1", default-features = false, "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=10.1.0-beta.2", default-features = false, "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=10.1.0-beta.2", default-features = false, "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=10.1.0-beta.2", default-features = false, "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "58.0.0", optional = false }
@@ -28,7 +28,7 @@
    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>10.1.0-beta.1</lance-core.version>
+        <lance-core.version>10.1.0-beta.2</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>
@@ -49,8 +49,8 @@ lance-namespace = { workspace = true }
 lance-namespace-impls = { workspace = true }
 metrics = { workspace = true, optional = true }
 metrics-util = { workspace = true, optional = true }
-# Pin the transitive GooseFS SDK until the 0.1.6 compile break is fixed upstream.
-goosefs-sdk = { version = "=0.1.5", optional = true }
+# Keep the direct dependency aligned with the version required by OpenDAL.
+goosefs-sdk = { version = "=0.1.8", optional = true }
 moka = { workspace = true }
 pin-project = { workspace = true }
 tokio = { version = "1.23", features = ["rt-multi-thread", "sync"] }
@@ -2939,7 +2939,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
 }

 #[derive(Serialize, Clone, Debug)]
-pub(crate) struct MergeInsertRequest {
+pub struct MergeInsertRequest {
    on: String,
    when_matched_update_all: bool,
    when_matched_update_all_filt: Option<String>,
@@ -33,7 +33,7 @@ use crate::table::{AddResult, MergeResult};
 /// same Arrow-IPC streaming body and error side-channel; only the target
 /// endpoint, query parameters, and parsed result type differ.
 #[derive(Debug, Clone)]
-pub(crate) enum WriteOp {
+pub enum WriteOp {
    /// `add`: stream to `/v1/table/{id}/insert/`, optionally overwriting.
    Insert { overwrite: bool },
    /// `merge_insert`: stream to `/v1/table/{id}/merge_insert/` with the merge
@@ -49,7 +49,7 @@ pub(crate) enum WriteOp {
 /// The parsed server response for a completed write, discriminated by the
 /// operation that produced it.
 #[derive(Debug, Clone)]
-pub(crate) enum WriteResult {
+pub enum WriteResult {
    Add(AddResult),
    Merge(MergeResult),
 }
@@ -18,6 +18,7 @@

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

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

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

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

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

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

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

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

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

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

+    /// A hybrid search reads a vector and a full-text index, and either may lag.
+    /// Retaining to the lower of the two is what keeps both arms complete;
+    /// gating on one alone would drop SSTables the other has not indexed.
+    #[test]
+    fn exclusion_watermark_takes_the_minimum_across_every_index_used() {
+        let shard = Uuid::from_u128(1);
+        let details = MemWalIndexDetails {
+            compacted_sstables: vec![CompactedSsTable::new(shard, 9)],
+            index_catchup: vec![
+                IndexCatchupProgress::new(
+                    "vec_idx".to_string(),
+                    vec![CompactedSsTable::new(shard, 7)],
+                ),
+                IndexCatchupProgress::new(
+                    "fts_idx".to_string(),
+                    vec![CompactedSsTable::new(shard, 4)],
+                ),
+            ],
+            maintained_indexes: vec!["vec_idx".to_string(), "fts_idx".to_string()],
+            ..Default::default()
+        };
+
+        // Each index alone stops at its own catch-up.
+        assert_eq!(
+            exclusion_watermarks(&details, &["vec_idx".to_string()]).get(&shard),
+            Some(&7)
+        );
+        assert_eq!(
+            exclusion_watermarks(&details, &["fts_idx".to_string()]).get(&shard),
+            Some(&4)
+        );
+
+        // Used together, the lower one governs regardless of order.
+        let both = ["vec_idx".to_string(), "fts_idx".to_string()];
+        assert_eq!(exclusion_watermarks(&details, &both).get(&shard), Some(&4));
+        let reversed = ["fts_idx".to_string(), "vec_idx".to_string()];
+        assert_eq!(
+            exclusion_watermarks(&details, &reversed).get(&shard),
+            Some(&4)
+        );
+    }
+
+    /// An index with no catch-up entry is not known to hold anything, so it
+    /// governs over a lagging sibling rather than the other way round.
+    #[test]
+    fn an_untracked_index_retains_everything() {
+        let shard = Uuid::from_u128(1);
+        let details = MemWalIndexDetails {
+            compacted_sstables: vec![CompactedSsTable::new(shard, 9)],
+            index_catchup: vec![IndexCatchupProgress::new(
+                "fts_idx".to_string(),
+                vec![CompactedSsTable::new(shard, 4)],
+            )],
+            maintained_indexes: vec!["fts_idx".to_string(), "untracked_idx".to_string()],
+            ..Default::default()
+        };
+
+        let both = ["fts_idx".to_string(), "untracked_idx".to_string()];
+        assert_eq!(exclusion_watermarks(&details, &both).get(&shard), Some(&0));
+    }
+
    #[test]
    fn resolve_single_index_dedupes_segments() {
        let maintained = vec!["fts_idx".to_string()];
Author	SHA1	Message	Date
XYZhan	6c4269bbb0	refactor(lsm): remove the index-catchup activation surface Follows the lance change that removes the feature bit. With one set of semantics there is no mode to switch into, so `require_mem_wal_index_catchup` goes from the trait, `NativeTable`, and the LSM merge module. `exclusion_watermarks` loses its `catchup_required` argument and keeps the conservative branch: an index with no `index_catchup` entry is not known to hold the compacted rows, so its generations stay readable from their SSTables. That is what makes an existing table safe to read the moment the new binary starts -- nothing is excluded until an index records that it covers it. Two tests changed because they encoded the branch that is gone, and they had conflated two different things: an index that is caught up and an index that is untracked both fell back to the compaction watermark. Untracked now retains everything, so the tests assert that and cover the genuinely-caught-up case separately. 484 lancedb lib tests pass.	2026-08-20 18:29:56 -04:00
XYZhan	41e0161067	feat(lsm): move catch-up activation to an explicit API	2026-08-10 09:10:05 -04:00
XYZhan	f75279b69f	feat(lsm): strict catch-up semantics and activation, on the 10.1 line lancedb#3780 plus the two pieces it deferred: a missing index_catchup entry means not-caught-up once the feature bit is set, and turning WAL on requires catch-up while the table is provably clean. Local only, for end-to-end work before the lance bump.	2026-08-09 23:19:21 -04:00
lancedb automation	667cf32e78	chore: update lance dependency to v10.1.0-beta.2	2026-08-02 00:12:47 +00:00