Bump version: 0.37.1-beta.1 → 0.38.0-beta.0

feat: add asynchronous drop table API (#3936 )
## Summary - add `drop_table_async` and return a job handle while preserving `drop_table` - consume remote 202 responses with cleanup job IDs and retain older-server compatibility - expose the API through Python and TypeScript connection wrappers
2026-09-01 19:18:38 +00:00 · 2026-08-14 01:09:15 +00:00 · 2026-08-13 18:05:44 -07:00 · 2026-08-13 11:26:58 -07:00 · 2026-08-13 13:23:37 -04:00 · 2026-08-14 00:00:18 +08:00
34 changed files with 528 additions and 159 deletions
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.37.1-beta.1"
+current_version = "0.38.0-beta.0"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
@@ -4,14 +4,14 @@ on:
  workflow_call:
    inputs:
      tag:
-        description: "Tag name from Lance. If omitted, the skill will use the latest Lance release that needs an update."
+        description: "Tag name from Lance (e.g. `v7.2.0-beta.1`). If omitted, the newest release is resolved automatically — stable releases are preferred over pre-releases — and the run is skipped if it is not newer than the version currently pinned in Cargo.toml."
        required: false
        default: ""
        type: string
  workflow_dispatch:
    inputs:
      tag:
-        description: "Tag name from Lance. Leave empty to use the latest Lance release that needs an update."
+        description: "Tag name from Lance (e.g. `v7.2.0-beta.1`). Leave empty to resolve the newest release automatically — stable releases are preferred over pre-releases — and skip the run if it is not newer than the version currently pinned in Cargo.toml."
        required: false
        default: ""
        type: string
@@ -3455,8 +3455,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"

 [[package]]
 name = "fsst"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arrow-array",
 "rand 0.9.5",
@@ -4815,8 +4815,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a"

 [[package]]
 name = "lance"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arc-swap",
 "arrow",
@@ -4832,7 +4832,6 @@ dependencies = [
 "async-recursion",
 "async-trait",
 "async_cell",
- "aws-credential-types",
 "aws-sdk-dynamodb",
 "byteorder",
 "bytes",
@@ -4848,7 +4847,6 @@ dependencies = [
 "either",
 "fst",
 "futures",
- "half",
 "humantime",
 "itertools 0.14.0",
 "lance-arrow",
@@ -4890,8 +4888,8 @@ dependencies = [

 [[package]]
 name = "lance-arrow"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4913,7 +4911,7 @@ dependencies = [
 [[package]]
 name = "lance-arrow-scalar"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4927,7 +4925,7 @@ dependencies = [
 [[package]]
 name = "lance-arrow-stats"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -4936,8 +4934,8 @@ dependencies = [

 [[package]]
 name = "lance-bitpacking"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arrayref",
 "crunchy",
@@ -4947,8 +4945,8 @@ dependencies = [

 [[package]]
 name = "lance-core"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4956,12 +4954,10 @@ dependencies = [
 "arrow-schema",
 "async-trait",
 "blake3",
- "byteorder",
 "bytes",
 "datafusion-common",
 "datafusion-sql",
 "futures",
- "itertools 0.14.0",
 "lance-arrow",
 "lance-derive",
 "libc",
@@ -4979,7 +4975,6 @@ dependencies = [
 "snafu 0.9.0",
 "tempfile",
 "tokio",
- "tokio-stream",
 "tokio-util",
 "tracing",
 "twox-hash",
@@ -4988,8 +4983,8 @@ dependencies = [

 [[package]]
 name = "lance-datafusion"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5019,8 +5014,8 @@ dependencies = [

 [[package]]
 name = "lance-datagen"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5037,8 +5032,8 @@ dependencies = [

 [[package]]
 name = "lance-derive"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "proc-macro2",
 "quote",
@@ -5047,8 +5042,8 @@ dependencies = [

 [[package]]
 name = "lance-encoding"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -5073,7 +5068,6 @@ dependencies = [
 "num-traits",
 "prost",
 "prost-build",
- "rand 0.9.5",
 "tokio",
 "tracing",
 "xxhash-rust",
@@ -5082,8 +5076,8 @@ dependencies = [

 [[package]]
 name = "lance-file"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -5114,8 +5108,8 @@ dependencies = [

 [[package]]
 name = "lance-index"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arc-swap",
 "arrow",
@@ -5130,7 +5124,6 @@ dependencies = [
 "async-trait",
 "bitvec",
 "bytes",
- "chrono",
 "crossbeam-queue",
 "datafusion",
 "datafusion-common",
@@ -5148,7 +5141,6 @@ dependencies = [
 "lance-bitpacking",
 "lance-core",
 "lance-datafusion",
- "lance-datagen",
 "lance-encoding",
 "lance-file",
 "lance-index-core",
@@ -5177,13 +5169,12 @@ dependencies = [
 "tempfile",
 "tokio",
 "tracing",
- "uuid",
 ]

 [[package]]
 name = "lance-index-core"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -5205,8 +5196,8 @@ dependencies = [

 [[package]]
 name = "lance-io"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5220,7 +5211,6 @@ dependencies = [
 "futures",
 "http 1.5.0",
 "io-uring",
- "lance-arrow",
 "lance-core",
 "lance-namespace",
 "log",
@@ -5238,29 +5228,28 @@ dependencies = [
 "tokio",
 "tracing",
 "url",
+ "uuid",
 ]

 [[package]]
 name = "lance-linalg"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arrow-array",
- "arrow-buffer",
 "arrow-schema",
 "cc",
 "half",
 "lance-arrow",
 "lance-core",
 "num-traits",
- "rand 0.9.5",
 "rayon",
 ]

 [[package]]
 name = "lance-namespace"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arrow",
 "async-trait",
@@ -5272,8 +5261,8 @@ dependencies = [

 [[package]]
 name = "lance-namespace-impls"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arrow",
 "arrow-ipc",
@@ -5326,14 +5315,13 @@ dependencies = [

 [[package]]
 name = "lance-select"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
 "arrow-schema",
 "byteorder",
- "bytes",
 "itertools 0.14.0",
 "lance-core",
 "roaring",
@@ -5342,8 +5330,8 @@ dependencies = [

 [[package]]
 name = "lance-table"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5383,8 +5371,8 @@ dependencies = [

 [[package]]
 name = "lance-testing"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -5397,8 +5385,8 @@ dependencies = [

 [[package]]
 name = "lance-tokenizer"
-version = "11.0.0-beta.7"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea"
+version = "11.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
 dependencies = [
 "frostem",
 "icu_segmenter",
@@ -13,20 +13,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"

 [workspace.dependencies]
-lance = { "version" = "=11.0.0-beta.7", default-features = false, "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=11.0.0-beta.7", default-features = false, "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=11.0.0-beta.7", default-features = false, "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=11.0.0-beta.8", default-features = false, "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=11.0.0-beta.8", default-features = false, "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=11.0.0-beta.8", default-features = false, "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "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 }
@@ -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.1</version>
+    <version>0.38.0-beta.0</version>
 </dependency>
 ```

@@ -386,6 +386,29 @@ Drop an existing table.

 ***

+### dropTableAsync()
+
+```ts
+abstract dropTableAsync(name, namespacePath?): Promise<Job>
+```
+
+Start dropping a table and return its cleanup job.
+
+The table may become unavailable before its data files are removed. Wait
+on the returned job to know when cleanup has finished.
+
+#### Parameters
+
+* **name**: `string`
+
+* **namespacePath?**: `string`[]
+
+#### Returns
+
+`Promise`&lt;[`Job`](Job.md)&gt;
+
+***
+
 ### getJob()

 ```ts
@@ -8,7 +8,7 @@
    <parent>
      <groupId>com.lancedb</groupId>
      <artifactId>lancedb-parent</artifactId>
-      <version>0.37.1-beta.1</version>
+      <version>0.38.0-beta.0</version>
      <relativePath>../pom.xml</relativePath>
    </parent>

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

    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-parent</artifactId>
-    <version>0.37.1-beta.1</version>
+    <version>0.38.0-beta.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.7</lance-core.version>
+        <lance-core.version>11.0.0-beta.8</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.1"
+version = "0.38.0-beta.0"
 publish = false
 license.workspace = true
 description.workspace = true
@@ -89,6 +89,16 @@ describe("given a connection", () => {
    await db.createTable("test4", [{ id: 1 }, { id: 2 }]);
  });

+  it("should return a completed job when dropping a local table", async () => {
+    await db.createTable("async-drop", [{ id: 1 }]);
+
+    const job = await db.dropTableAsync("async-drop");
+    expect(job.id).toBeNull();
+    await expect(job.status()).resolves.toBe("finished");
+    await job.wait();
+    await expect(db.tableNames()).resolves.toEqual([]);
+  });
+
  it("should fail if creating table twice, unless overwrite is true", async () => {
    let tbl = await db.createTable("test", [{ id: 1 }, { id: 2 }]);
    await expect(tbl.countRows()).resolves.toBe(2);
@@ -327,6 +327,14 @@ export abstract class Connection {
   */
  abstract dropTable(name: string, namespacePath?: string[]): Promise<void>;

+  /**
+   * Start dropping a table and return its cleanup job.
+   *
+   * The table may become unavailable before its data files are removed. Wait
+   * on the returned job to know when cleanup has finished.
+   */
+  abstract dropTableAsync(name: string, namespacePath?: string[]): Promise<Job>;
+
  /**
   * Drop all tables in the database.
   * @param {string[]} namespacePath The namespace path to drop tables from (defaults to root namespace).
@@ -705,6 +713,10 @@ export class LocalConnection extends Connection {
    return this.inner.dropTable(name, namespacePath ?? []);
  }

+  async dropTableAsync(name: string, namespacePath?: string[]): Promise<Job> {
+    return this.inner.dropTableAsync(name, namespacePath ?? []);
+  }
+
  async dropAllTables(namespacePath?: string[]): Promise<void> {
    return this.inner.dropAllTables(namespacePath ?? []);
  }
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.37.1-beta.1",
+	"version": "0.38.0-beta.0",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.37.1-beta.1",
+	"version": "0.38.0-beta.0",
 	"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.1",
+	"version": "0.38.0-beta.0",
 	"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.1",
+	"version": "0.38.0-beta.0",
 	"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.1",
+	"version": "0.38.0-beta.0",
 	"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.1",
+  "version": "0.38.0-beta.0",
  "os": [
    "win32"
  ],
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.37.1-beta.1",
+	"version": "0.38.0-beta.0",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",
@@ -11,7 +11,7 @@
    "ann"
  ],
  "private": false,
-  "version": "0.37.1-beta.1",
+  "version": "0.38.0-beta.0",
  "main": "dist/index.js",
  "exports": {
    ".": "./dist/index.js",
@@ -334,6 +334,22 @@ impl Connection {
            .default_error()
    }

+    /// Start dropping a table and return its cleanup job.
+    #[napi(catch_unwind)]
+    pub async fn drop_table_async(
+        &self,
+        name: String,
+        namespace_path: Option<Vec<String>>,
+    ) -> napi::Result<crate::job::Job> {
+        let ns = namespace_path.unwrap_or_default();
+        let job = self
+            .get_inner()?
+            .drop_table_async(&name, &ns)
+            .await
+            .default_error()?;
+        Ok(crate::job::Job::new(job))
+    }
+
    #[napi(catch_unwind)]
    pub async fn drop_all_tables(&self, namespace_path: Option<Vec<String>>) -> napi::Result<()> {
        let ns = namespace_path.unwrap_or_default();
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.37.1-beta.1"
+version = "0.38.0-beta.0"
 publish = false
 edition.workspace = true
 description = "Python bindings for LanceDB"
@@ -198,6 +198,9 @@ class Connection(object):
    async def drop_table(
        self, name: str, namespace_path: Optional[List[str]] = None
    ) -> None: ...
+    async def drop_table_async(
+        self, name: str, namespace_path: Optional[List[str]] = None
+    ) -> Job: ...
    async def drop_all_tables(
        self, namespace_path: Optional[List[str]] = None
    ) -> None: ...
@@ -524,6 +524,12 @@ class DBConnection(EnforceOverrides):
            namespace_path = []
        raise NotImplementedError

+    def drop_table_async(
+        self, name: str, namespace_path: Optional[List[str]] = None
+    ) -> Job:
+        """Start dropping a table and return its cleanup job."""
+        raise NotImplementedError
+
    def rename_table(
        self,
        cur_name: str,
@@ -1186,6 +1192,20 @@ class LanceDBConnection(DBConnection):
            )
        )

+    @override
+    def drop_table_async(
+        self, name: str, namespace_path: Optional[List[str]] = None
+    ) -> Job:
+        """Start dropping a table and return its cleanup job.
+
+        The table may become unavailable before its data files are removed.
+        Call :meth:`Job.wait` to wait for cleanup to finish.
+        """
+        if namespace_path is None:
+            namespace_path = []
+        job = LOOP.run(self._conn.drop_table_async(name, namespace_path=namespace_path))
+        return Job(job if isinstance(job, AsyncJob) else AsyncJob(job))
+
    @override
    def drop_all_tables(self, namespace_path: Optional[List[str]] = None):
        if namespace_path is None:
@@ -1963,6 +1983,23 @@ class AsyncConnection(object):
            if f"Table '{name}' was not found" not in str(e):
                raise e

+    async def drop_table_async(
+        self,
+        name: str,
+        *,
+        namespace_path: Optional[List[str]] = None,
+    ) -> AsyncJob:
+        """Start dropping a table and return its cleanup job.
+
+        The table may become unavailable before its data files are removed.
+        Await :meth:`AsyncJob.wait` to wait for cleanup to finish.
+        """
+        if namespace_path is None:
+            namespace_path = []
+        return AsyncJob(
+            await self._inner.drop_table_async(name, namespace_path=namespace_path)
+        )
+
    async def drop_all_tables(self, namespace_path: Optional[List[str]] = None):
        """Drop all tables from the database.

@@ -49,6 +49,7 @@ from lancedb._lancedb import (
 )
 from lancedb.background_loop import LOOP
 from lancedb.db import AsyncConnection, DBConnection
+from lancedb.job import AsyncJob, Job
 from lance_namespace import (
    LanceNamespace,
    connect as namespace_connect,
@@ -624,6 +625,18 @@ class LanceNamespaceDBConnection(DBConnection):
            namespace_path = []
        LOOP.run(self._inner.drop_table(name, namespace_path=namespace_path))

+    @override
+    def drop_table_async(
+        self, name: str, namespace_path: Optional[List[str]] = None
+    ) -> Job:
+        """Start dropping a table and return its cleanup job."""
+        if namespace_path is None:
+            namespace_path = []
+        job = LOOP.run(
+            self._inner.drop_table_async(name, namespace_path=namespace_path)
+        )
+        return Job(job if isinstance(job, AsyncJob) else AsyncJob(job))
+
    @override
    def rename_table(
        self,
@@ -1134,6 +1147,14 @@ class AsyncLanceNamespaceDBConnection:
            namespace_path = []
        await self._inner.drop_table(name, namespace_path=namespace_path)

+    async def drop_table_async(
+        self, name: str, namespace_path: Optional[List[str]] = None
+    ) -> AsyncJob:
+        """Start dropping a table and return its cleanup job."""
+        if namespace_path is None:
+            namespace_path = []
+        return await self._inner.drop_table_async(name, namespace_path=namespace_path)
+
    async def rename_table(
        self,
        cur_name: str,
@@ -23,7 +23,7 @@ import pyarrow as pa

 from ..common import DATA
 from ..db import DBConnection, LOOP
-from ..job import Job
+from ..job import AsyncJob, Job

 if TYPE_CHECKING:
    from .._lancedb import JobDescription, JobInfo
@@ -663,6 +663,16 @@ class RemoteDBConnection(DBConnection):
            namespace_path = []
        LOOP.run(self._conn.drop_table(name, namespace_path=namespace_path))

+    @override
+    def drop_table_async(
+        self, name: str, namespace_path: Optional[List[str]] = None
+    ) -> Job:
+        """Start dropping a table and return its cleanup job."""
+        if namespace_path is None:
+            namespace_path = []
+        job = LOOP.run(self._conn.drop_table_async(name, namespace_path=namespace_path))
+        return Job(job if isinstance(job, AsyncJob) else AsyncJob(job))
+
    @override
    def rename_table(
        self,
@@ -755,8 +755,7 @@ def test_delete_table(tmp_db: lancedb.DBConnection):
    assert tmp_db.table_names() == []


-@pytest.mark.asyncio
-async def test_delete_table_async(tmp_db: lancedb.DBConnection):
+def test_drop_table_async(tmp_db: lancedb.DBConnection):
    data = pd.DataFrame(
        {
            "vector": [[3.1, 4.1], [5.9, 26.5]],
@@ -772,7 +771,10 @@ async def test_delete_table_async(tmp_db: lancedb.DBConnection):

    assert tmp_db.table_names() == ["test"]

-    tmp_db.drop_table("test")
+    job = tmp_db.drop_table_async("test")
+    assert job.id is None
+    assert job.status() == "finished"
+    job.wait()
    assert tmp_db.table_names() == []

    tmp_db.create_table("test", data=data)
@@ -781,6 +783,17 @@ async def test_delete_table_async(tmp_db: lancedb.DBConnection):
    tmp_db.drop_table("does_not_exist", ignore_missing=True)


+@pytest.mark.asyncio
+async def test_drop_table_async_connection(tmp_db_async: lancedb.AsyncConnection):
+    await tmp_db_async.create_table("test", data=pa.table({"id": [1, 2]}))
+
+    job = await tmp_db_async.drop_table_async("test")
+    assert job.id is None
+    assert await job.status() == "finished"
+    await job.wait()
+    assert await tmp_db_async.table_names() == []
+
+
 def test_drop_database(tmp_db: lancedb.DBConnection):
    data = pd.DataFrame(
        {
@@ -346,6 +346,23 @@ impl Connection {
        })
    }

+    #[pyo3(signature = (name, namespace_path=None))]
+    pub fn drop_table_async(
+        self_: PyRef<'_, Self>,
+        name: String,
+        namespace_path: Option<Vec<String>>,
+    ) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.get_inner()?.clone();
+        let ns_path = namespace_path.unwrap_or_default();
+        future_into_py(self_.py(), async move {
+            inner
+                .drop_table_async(name, &ns_path)
+                .await
+                .infer_error()
+                .map(crate::job::Job::new)
+        })
+    }
+
    #[pyo3(signature = (namespace_path=None,))]
    pub fn drop_all_tables(
        self_: PyRef<'_, Self>,
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.37.1-beta.1"
+version = "0.38.0-beta.0"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
@@ -565,6 +565,21 @@ impl Connection {
            .await
    }

+    /// Start dropping a table and return a handle to the cleanup job.
+    ///
+    /// The table may become unavailable before its physical data is removed.
+    /// Call [`crate::job::Job::wait`] to wait for cleanup to finish. Local
+    /// backends may complete the drop before returning the handle.
+    pub async fn drop_table_async(
+        &self,
+        name: impl AsRef<str>,
+        namespace_path: &[String],
+    ) -> Result<crate::job::Job> {
+        self.internal
+            .drop_table_async(name.as_ref(), namespace_path)
+            .await
+    }
+
    /// Drop the database
    ///
    /// This is the same as dropping all of the tables
@@ -323,6 +323,18 @@ pub trait Database:
    ) -> Result<()>;
    /// Drop a table in the database
    async fn drop_table(&self, name: &str, namespace_path: &[String]) -> Result<()>;
+    /// Start dropping a table and return a handle to the cleanup job.
+    ///
+    /// Backends without asynchronous cleanup complete the drop before
+    /// returning an already-finished job.
+    async fn drop_table_async(
+        &self,
+        name: &str,
+        namespace_path: &[String],
+    ) -> Result<crate::job::Job> {
+        self.drop_table(name, namespace_path).await?;
+        Ok(crate::job::Job::new_done())
+    }
    /// Drop all tables in the database
    async fn drop_all_tables(&self, namespace_path: &[String]) -> Result<()>;
    fn as_any(&self) -> &dyn std::any::Any;
@@ -19,6 +19,15 @@ const ARROW_FILE_CONTENT_TYPE: &str = "application/vnd.apache.arrow.file";
 #[cfg(test)]
 const JSON_CONTENT_TYPE: &str = "application/json";

+fn extract_job_id(body: &str) -> Option<String> {
+    serde_json::from_str::<serde_json::Value>(body)
+        .ok()?
+        .get("job_id")?
+        .as_str()
+        .filter(|job_id| !job_id.is_empty())
+        .map(str::to_string)
+}
+
 pub use client::{ClientConfig, HeaderProvider, RetryConfig, TimeoutConfig, TlsConfig};
 pub use db::{RemoteDatabaseOptions, RemoteDatabaseOptionsBuilder};
 pub use oauth::{OAuthConfig, OAuthFlow, OAuthHeaderProvider};
@@ -9,6 +9,7 @@ use http::StatusCode;
 use lance_io::object_store::StorageOptions;
 use lance_namespace_impls::{DynamicContextProvider, OperationInfo};
 use moka::future::Cache;
+use reqwest::Response;
 use reqwest::header::CONTENT_TYPE;

 use lance_namespace::models::{
@@ -23,15 +24,17 @@ use crate::database::{
    JobDescription, JobInfo, OpenTableRequest, ReadConsistency, TableNamesRequest,
 };
 use crate::error::Result;
+use crate::job::Job;
+use crate::remote::job::RemoteJob;
 use crate::remote::util::stream_as_body;
 use crate::table::BaseTable;

-use super::ARROW_STREAM_CONTENT_TYPE;
 use super::client::{
    ClientConfig, HeaderProvider, HttpSend, RequestResultExt, RestfulLanceDbClient, Sender,
 };
 use super::table::RemoteTable;
 use super::util::parse_server_version;
+use super::{ARROW_STREAM_CONTENT_TYPE, extract_job_id};

 // Request structure for the remote clone table API
 #[derive(serde::Serialize)]
@@ -326,6 +329,22 @@ impl RemoteDatabase {
    }
 }

+impl<S: HttpSend> RemoteDatabase<S> {
+    async fn submit_drop_table(
+        &self,
+        name: &str,
+        namespace_path: &[String],
+    ) -> Result<(String, Response)> {
+        let identifier = build_table_identifier(name, namespace_path, &self.client.id_delimiter);
+        let cache_key = build_cache_key(name, namespace_path);
+        let req = self.client.post(&format!("/v1/table/{}/drop/", identifier));
+        let (request_id, resp) = self.client.send(req).await?;
+        let resp = self.client.check_response(&request_id, resp).await?;
+        self.table_cache.remove(&cache_key).await;
+        Ok((request_id, resp))
+    }
+}
+
 #[cfg(all(test, feature = "remote"))]
 mod test_utils {
    use super::*;
@@ -894,13 +913,28 @@ impl<S: HttpSend> Database for RemoteDatabase<S> {
    }

    async fn drop_table(&self, name: &str, namespace_path: &[String]) -> Result<()> {
-        let identifier = build_table_identifier(name, namespace_path, &self.client.id_delimiter);
-        let cache_key = build_cache_key(name, namespace_path);
-        let req = self.client.post(&format!("/v1/table/{}/drop/", identifier));
-        let (request_id, resp) = self.client.send(req).await?;
-        self.client.check_response(&request_id, resp).await?;
-        self.table_cache.remove(&cache_key).await;
-        Ok(())
+        self.submit_drop_table(name, namespace_path)
+            .await
+            .map(|_| ())
+    }
+
+    async fn drop_table_async(&self, name: &str, namespace_path: &[String]) -> Result<Job> {
+        let (request_id, response) = self.submit_drop_table(name, namespace_path).await?;
+        let status = response.status();
+        let body = response.text().await.err_to_http(request_id.clone())?;
+        let job_id = extract_job_id(&body);
+        Ok(match job_id {
+            Some(job_id) => Job::new(Box::new(RemoteJob::new(self.client.clone(), job_id))),
+            None if status == StatusCode::ACCEPTED => {
+                return Err(Error::Http {
+                    source: "asynchronous drop-table response did not contain a valid job_id"
+                        .into(),
+                    request_id,
+                    status_code: Some(status),
+                });
+            }
+            None => Job::new_done(),
+        })
    }

    async fn drop_all_tables(&self, namespace_path: &[String]) -> Result<()> {
@@ -1492,6 +1526,67 @@ mod tests {
        // NOTE: the API will return 200 even if the table does not exist. So we shouldn't expect 404.
    }

+    #[tokio::test]
+    async fn test_drop_table_does_not_read_response_body() {
+        let conn = Connection::new_with_handler(|_| {
+            http::Response::builder()
+                .status(200)
+                .body(vec![0xff])
+                .unwrap()
+        });
+
+        conn.drop_table("table1", &[]).await.unwrap();
+    }
+
+    #[tokio::test]
+    async fn test_drop_table_async_returns_job() {
+        let conn = Connection::new_with_handler(|request| {
+            assert_eq!(request.method(), &reqwest::Method::POST);
+            assert_eq!(request.url().path(), "/v1/table/table1/drop/");
+            http::Response::builder()
+                .status(202)
+                .body(r#"{"job_id":"drop-job-123"}"#)
+                .unwrap()
+        });
+
+        let job = conn.drop_table_async("table1", &[]).await.unwrap();
+        assert_eq!(job.id(), Some("drop-job-123"));
+    }
+
+    #[tokio::test]
+    async fn test_drop_table_async_old_server_returns_done_job() {
+        let conn = Connection::new_with_handler(|_| {
+            http::Response::builder().status(200).body("").unwrap()
+        });
+
+        let job = conn.drop_table_async("table1", &[]).await.unwrap();
+        assert_eq!(job.id(), None);
+        assert_eq!(job.status().await.unwrap(), "finished");
+    }
+
+    #[tokio::test]
+    async fn test_drop_table_async_rejects_accepted_response_without_job_id() {
+        let conn = Connection::new_with_handler(|_| {
+            http::Response::builder().status(202).body("{}").unwrap()
+        });
+
+        let error = conn.drop_table_async("table1", &[]).await.err().unwrap();
+        assert!(error.to_string().contains("valid job_id"));
+    }
+
+    #[tokio::test]
+    async fn test_drop_table_async_rejects_empty_job_id() {
+        let conn = Connection::new_with_handler(|_| {
+            http::Response::builder()
+                .status(202)
+                .body(r#"{"job_id":""}"#)
+                .unwrap()
+        });
+
+        let error = conn.drop_table_async("table1", &[]).await.err().unwrap();
+        assert!(error.to_string().contains("valid job_id"));
+    }
+
    #[tokio::test]
    async fn test_rename_table() {
        let conn = Connection::new_with_handler(|request| {
@@ -8,7 +8,7 @@ use self::insert::{RemoteWriteExec, WriteOp};
 use super::client::RequestResultExt;
 use super::client::{HttpSend, RestfulLanceDbClient, Sender};
 use super::db::ServerVersion;
-use super::{ARROW_FILE_CONTENT_TYPE, ARROW_STREAM_CONTENT_TYPE};
+use super::{ARROW_FILE_CONTENT_TYPE, ARROW_STREAM_CONTENT_TYPE, extract_job_id};
 use crate::blob::BlobFile;
 use crate::data::scannable::{PeekedScannable, Scannable, estimate_write_partitions};
 use crate::expr::expr_to_sql_string;
@@ -392,13 +392,7 @@ impl<S: HttpSend> RemoteTable<S> {
            .text()
            .await
            .ok()
-            .and_then(|body| serde_json::from_str::<serde_json::Value>(&body).ok())
-            .and_then(|value| {
-                value
-                    .get("job_id")
-                    .and_then(|id| id.as_str())
-                    .map(str::to_string)
-            });
+            .and_then(|body| extract_job_id(&body));

        if let Some(wait_timeout) = index.wait_timeout {
            let index_name = index.name.unwrap_or_else(|| format!("{}_idx", column));
@@ -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 +231,36 @@ 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 {
+            if let Some(caught_up) = details
                .index_catchup
                .iter()
-                .find(|icp| icp.index_name == name)
+                .find(|icp| icp.index_name == *name)
                .and_then(|icp| icp.caught_up_generation_for_shard(&entry.shard_id))
-        {
-            watermark = watermark.min(caught_up);
+            {
+                watermark = watermark.min(caught_up);
+            }
        }
        exclude.entry(entry.shard_id).or_insert(watermark);
    }
@@ -271,9 +278,9 @@ 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 +494,33 @@ 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 +529,43 @@ 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 +767,85 @@ 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.
        assert_eq!(
-            exclusion_watermarks(&details, Some("caught_up_idx")).get(&shard),
+            exclusion_watermarks(&details, &["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 contributes no cap today, so a lagging
+    /// sibling must still govern rather than being widened by the untracked one.
+    #[test]
+    fn an_untracked_index_does_not_widen_a_lagging_sibling() {
+        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(&4));
+    }
+
    #[test]
    fn resolve_single_index_dedupes_segments() {
        let maintained = vec!["fts_idx".to_string()];
Author	SHA1	Message	Date
Lance Release	2f57dd053e	Bump version: 0.37.1-beta.1 → 0.38.0-beta.0	2026-08-14 01:09:15 +00:00
Jack Ye	ffd35c1a8f	feat: add asynchronous drop table API (#3936 ) ## Summary - add `drop_table_async` and return a job handle while preserving `drop_table` - consume remote 202 responses with cleanup job IDs and retain older-server compatibility - expose the API through Python and TypeScript connection wrappers	2026-08-13 18:05:44 -07:00
Wyatt Alt	790d0c684c	docs(ci): clarify tag input on codex-update-lance-dependency (#3924 ) Say what resolving "latest" actually does: pick the newest release, preferring stable over pre-release, and skip the run if it is not newer than the version pinned in Cargo.toml. Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>	2026-08-13 11:26:58 -07:00
XY Zhan	251f194696	refactor(lsm): gate SSTable exclusion on every index a query relies on (#3780 ) `exclusion_watermarks` resolved a single index and capped SSTable exclusion at that index's catch-up watermark. It now takes every index the query relies on and retains to the lowest of them, and the resolver collects arms together rather than returning at the first match. This is groundwork, not a fix for a reachable bug: `reject_unsupported` refuses hybrid search, so the vector and full-text arms are mutually exclusive and the list never holds more than one entry today. The generalisation is what the remaining work below plugs into. Unchanged: a plain scan uses the compaction watermark alone, an index with no catch-up entry contributes no cap, and a caught-up index falls back to the compaction watermark. Taking a minimum over more indexes can only lower a watermark, so the failure direction is "read an SSTable unnecessarily", never "miss rows". ## Tests Three in `lsm`: the existing lagging-index test updated for the new signature; `exclusion_watermark_takes_the_minimum_across_every_index_used` (two indexes at 7 and 4 against compaction at 9 — each alone stops at its own watermark, together the lower governs, order-independent); and `an_untracked_index_does_not_widen_a_lagging_sibling`. `cargo test -p lancedb --lib` — 45 lsm tests, 484 in the crate. `cargo fmt --check` clean. ## Follow-ups This crate pins lance to a released tag, so anything needing unreleased Lance symbols waits for a bump. 1. Select legacy versus strict semantics from the feature bit. On a table with `FLAG_MEM_WAL_INDEX_CATCHUP` set, a missing entry must mean "not caught up" and retain the SSTables, instead of leaving the compaction watermark unchanged. Needs the bit from lance-format/lance#8263. This must land before any table is activated — otherwise the bit is set while queries still read permissively. 2. Collect scalar and bitmap-family prefilter indexes. The genuinely multi-index query is a vector search with a scalar prefilter, and it is gated on the vector index alone today. Identifying the others needs the planner's chosen indexes, not the columns the filter names, so it needs a Lance-side helper. 3. Verify a retained SSTable can actually answer. Both base and SSTable arms use `fast_search`; a source without a compatible index contributes nothing, so retention alone does not guarantee its rows are returned. Needs a flat-search fallback or an explicit error in Lance's `LsmScanner`. 4. Planner-level integration tests. Current tests exercise the watermark arithmetic directly. End-to-end coverage over real queries — prefilter forms, legacy versus activated, missing index and missing shard entries — depends on 1–3.	2026-08-13 13:23:37 -04:00
LanceDB Robot	4b7325bd74	chore: update lance dependency to v11.0.0-beta.8 (#3928 ) Updates the Rust workspace and Java lance-core dependency to Lance v11.0.0-beta.8, with refreshed Cargo lockfile metadata. No compatibility fixes were required. Lance tag: https://github.com/lance-format/lance/releases/tag/v11.0.0-beta.8	2026-08-14 00:00:18 +08:00