Revert "fix: pass storage_options in LanceNamespaceDatabase::create_table"

This reverts commit 1078983993.
feat: add initial and latest storage options apis
2026-03-29 20:10:39 +00:00 · 2026-01-30 17:28:15 -08:00 · 2026-01-30 17:06:45 -08:00 · 2026-01-30 13:17:40 -08:00 · 2026-01-26 23:39:18 +00:00 · 2026-01-26 23:38:50 +00:00
45 changed files with 802 additions and 504 deletions
--- a/.bumpversion.toml
+++ b/.bumpversion.toml
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.24.0"
+current_version = "0.24.1"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
--- a/.github/workflows/rust.yml
+++ b/.github/workflows/rust.yml
@@ -48,6 +48,8 @@ jobs:
        run: cargo fmt --all -- --check
      - name: Run clippy
        run: cargo clippy --profile ci --workspace --tests --all-features -- -D warnings
+      - name: Run clippy (without remote feature)
+        run: cargo clippy --profile ci --workspace --tests -- -D warnings

  build-no-lock:
    runs-on: ubuntu-24.04
@@ -181,7 +183,7 @@ jobs:
    runs-on: ubuntu-24.04
    strategy:
      matrix:
-        msrv: ["1.78.0"] # This should match up with rust-version in Cargo.toml
+        msrv: ["1.88.0"] # This should match up with rust-version in Cargo.toml
    env:
      # Need up-to-date compilers for kernels
      CC: clang-18
@@ -212,4 +214,6 @@ jobs:
          cargo update -p aws-sdk-sts --precise 1.51.0
          cargo update -p home --precise 0.5.9
      - name: cargo +${{ matrix.msrv }} check
+        env:
+          RUSTUP_TOOLCHAIN: ${{ matrix.msrv }}
        run: cargo check --profile ci --workspace --tests --benches --all-features
--- a/Cargo.lock
+++ b/Cargo.lock
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -12,42 +12,42 @@ repository = "https://github.com/lancedb/lancedb"
 description = "Serverless, low-latency vector database for AI applications"
 keywords = ["lancedb", "lance", "database", "vector", "search"]
 categories = ["database-implementations"]
-rust-version = "1.78.0"
+rust-version = "1.88.0"

 [workspace.dependencies]
-lance = { "version" = "=2.0.0-rc.1", default-features = false, "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=2.0.0-rc.1", default-features = false, "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=2.0.0-rc.1", default-features = false, "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=1.0.4", default-features = false, "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=1.0.4", default-features = false, "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=1.0.4", default-features = false, "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
-arrow = { version = "57.2", optional = false }
-arrow-array = "57.2"
-arrow-data = "57.2"
-arrow-ipc = "57.2"
-arrow-ord = "57.2"
-arrow-schema = "57.2"
-arrow-select = "57.2"
-arrow-cast = "57.2"
+arrow = { version = "56.2", optional = false }
+arrow-array = "56.2"
+arrow-data = "56.2"
+arrow-ipc = "56.2"
+arrow-ord = "56.2"
+arrow-schema = "56.2"
+arrow-select = "56.2"
+arrow-cast = "56.2"
 async-trait = "0"
-datafusion = { version = "51.0", default-features = false }
-datafusion-catalog = "51.0"
-datafusion-common = { version = "51.0", default-features = false }
-datafusion-execution = "51.0"
-datafusion-expr = "51.0"
-datafusion-physical-plan = "51.0"
+datafusion = { version = "50.1", default-features = false }
+datafusion-catalog = "50.1"
+datafusion-common = { version = "50.1", default-features = false }
+datafusion-execution = "50.1"
+datafusion-expr = "50.1"
+datafusion-physical-plan = "50.1"
 env_logger = "0.11"
-half = { "version" = "2.7.1", default-features = false, features = [
+half = { "version" = "2.6.0", default-features = false, features = [
    "num-traits",
 ] }
 futures = "0"
--- a/docs/src/java/java.md
+++ b/docs/src/java/java.md
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
 <dependency>
    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-core</artifactId>
-    <version>0.24.0</version>
+    <version>0.24.1</version>
 </dependency>
 ```

--- a/java/lancedb-core/pom.xml
+++ b/java/lancedb-core/pom.xml
@@ -8,7 +8,7 @@
    <parent>
      <groupId>com.lancedb</groupId>
      <artifactId>lancedb-parent</artifactId>
-      <version>0.24.0-final.0</version>
+      <version>0.24.1-final.0</version>
      <relativePath>../pom.xml</relativePath>
    </parent>

--- a/java/pom.xml
+++ b/java/pom.xml
@@ -6,7 +6,7 @@

    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-parent</artifactId>
-    <version>0.24.0-final.0</version>
+    <version>0.24.1-final.0</version>
    <packaging>pom</packaging>
    <name>${project.artifactId}</name>
    <description>LanceDB Java SDK Parent POM</description>
--- a/nodejs/Cargo.toml
+++ b/nodejs/Cargo.toml
@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.24.0"
+version = "0.24.1"
 license.workspace = true
 description.workspace = true
 repository.workspace = true
--- a/nodejs/test/table.test.ts
+++ b/nodejs/test/table.test.ts
@@ -1520,9 +1520,9 @@ describe("when optimizing a dataset", () => {

  it("delete unverified", async () => {
    const version = await table.version();
-    const versionFile = `${tmpDir.name}/${table.name}.lance/_versions/${String(
-      18446744073709551615n - (BigInt(version) - 1n),
-    ).padStart(20, "0")}.manifest`;
+    const versionFile = `${tmpDir.name}/${table.name}.lance/_versions/${
+      version - 1
+    }.manifest`;
    fs.rmSync(versionFile);

    let stats = await table.optimize({ deleteUnverified: false });
--- a/nodejs/lancedb/table.ts
+++ b/nodejs/lancedb/table.ts
@@ -538,6 +538,35 @@ export abstract class Table {
   *
   */
  abstract stats(): Promise<TableStatistics>;
+
+  /**
+   * Get the initial storage options that were passed in when opening this table.
+   *
+   * For dynamically refreshed options (e.g., credential vending), use
+   * {@link Table.latestStorageOptions}.
+   *
+   * Warning: This is an internal API and the return value is subject to change.
+   *
+   * @returns The storage options, or undefined if no storage options were configured.
+   */
+  abstract initialStorageOptions(): Promise<
+    Record<string, string> | null | undefined
+  >;
+
+  /**
+   * Get the latest storage options, refreshing from provider if configured.
+   *
+   * This method is useful for credential vending scenarios where storage options
+   * may be refreshed dynamically. If no dynamic provider is configured, this
+   * returns the initial static options.
+   *
+   * Warning: This is an internal API and the return value is subject to change.
+   *
+   * @returns The storage options, or undefined if no storage options were configured.
+   */
+  abstract latestStorageOptions(): Promise<
+    Record<string, string> | null | undefined
+  >;
 }

 export class LocalTable extends Table {
@@ -858,6 +887,18 @@ export class LocalTable extends Table {
    return await this.inner.stats();
  }

+  async initialStorageOptions(): Promise<
+    Record<string, string> | null | undefined
+  > {
+    return await this.inner.initialStorageOptions();
+  }
+
+  async latestStorageOptions(): Promise<
+    Record<string, string> | null | undefined
+  > {
+    return await this.inner.latestStorageOptions();
+  }
+
  mergeInsert(on: string | string[]): MergeInsertBuilder {
    on = Array.isArray(on) ? on : [on];
    return new MergeInsertBuilder(this.inner.mergeInsert(on), this.schema());
--- a/nodejs/npm/darwin-arm64/package.json
+++ b/nodejs/npm/darwin-arm64/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.24.0",
+	"version": "0.24.1",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",
--- a/nodejs/npm/darwin-x64/package.json
+++ b/nodejs/npm/darwin-x64/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-x64",
-	"version": "0.24.0",
+	"version": "0.24.1",
 	"os": ["darwin"],
 	"cpu": ["x64"],
 	"main": "lancedb.darwin-x64.node",
--- a/nodejs/npm/linux-arm64-gnu/package.json
+++ b/nodejs/npm/linux-arm64-gnu/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.24.0",
+	"version": "0.24.1",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",
--- a/nodejs/npm/linux-arm64-musl/package.json
+++ b/nodejs/npm/linux-arm64-musl/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.24.0",
+	"version": "0.24.1",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",
--- a/nodejs/npm/linux-x64-gnu/package.json
+++ b/nodejs/npm/linux-x64-gnu/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.24.0",
+	"version": "0.24.1",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",
--- a/nodejs/npm/linux-x64-musl/package.json
+++ b/nodejs/npm/linux-x64-musl/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.24.0",
+	"version": "0.24.1",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",
--- a/nodejs/npm/win32-arm64-msvc/package.json
+++ b/nodejs/npm/win32-arm64-msvc/package.json
@@ -1,6 +1,6 @@
 {
  "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.24.0",
+  "version": "0.24.1",
  "os": [
    "win32"
  ],
--- a/nodejs/npm/win32-x64-msvc/package.json
+++ b/nodejs/npm/win32-x64-msvc/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.24.0",
+	"version": "0.24.1",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",
--- a/nodejs/package-lock.json
+++ b/nodejs/package-lock.json
@@ -1,12 +1,12 @@
 {
  "name": "@lancedb/lancedb",
-  "version": "0.24.0",
+  "version": "0.24.1",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "@lancedb/lancedb",
-      "version": "0.24.0",
+      "version": "0.24.1",
      "cpu": [
        "x64",
        "arm64"
--- a/nodejs/package.json
+++ b/nodejs/package.json
@@ -11,7 +11,7 @@
    "ann"
  ],
  "private": false,
-  "version": "0.24.0",
+  "version": "0.24.1",
  "main": "dist/index.js",
  "exports": {
    ".": "./dist/index.js",
--- a/nodejs/src/table.rs
+++ b/nodejs/src/table.rs
@@ -166,6 +166,19 @@ impl Table {
        Ok(stats.into())
    }

+    #[napi(catch_unwind)]
+    pub async fn initial_storage_options(&self) -> napi::Result<Option<HashMap<String, String>>> {
+        Ok(self.inner_ref()?.initial_storage_options().await)
+    }
+
+    #[napi(catch_unwind)]
+    pub async fn latest_storage_options(&self) -> napi::Result<Option<HashMap<String, String>>> {
+        self.inner_ref()?
+            .latest_storage_options()
+            .await
+            .default_error()
+    }
+
    #[napi(catch_unwind)]
    pub async fn update(
        &self,
--- a/python/.bumpversion.toml
+++ b/python/.bumpversion.toml
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.27.0"
+current_version = "0.27.1"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
--- a/python/Cargo.toml
+++ b/python/Cargo.toml
@@ -1,28 +1,28 @@
 [package]
 name = "lancedb-python"
-version = "0.27.0"
+version = "0.27.1"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true
 repository.workspace = true
 keywords.workspace = true
 categories.workspace = true
-rust-version = "1.75.0"
+rust-version = "1.88.0"

 [lib]
 name = "_lancedb"
 crate-type = ["cdylib"]

 [dependencies]
-arrow = { version = "57.2", features = ["pyarrow"] }
+arrow = { version = "56.2", features = ["pyarrow"] }
 async-trait = "0.1"
 lancedb = { path = "../rust/lancedb", default-features = false }
 lance-core.workspace = true
 lance-namespace.workspace = true
 lance-io.workspace = true
 env_logger.workspace = true
-pyo3 = { version = "0.26", features = ["extension-module", "abi3-py39"] }
-pyo3-async-runtimes = { version = "0.26", features = [
+pyo3 = { version = "0.25", features = ["extension-module", "abi3-py39"] }
+pyo3-async-runtimes = { version = "0.25", features = [
    "attributes",
    "tokio-runtime",
 ] }
@@ -32,7 +32,7 @@ snafu.workspace = true
 tokio = { version = "1.40", features = ["sync"] }

 [build-dependencies]
-pyo3-build-config = { version = "0.26", features = [
+pyo3-build-config = { version = "0.25", features = [
    "extension-module",
    "abi3-py39",
 ] }
--- a/python/python/lancedb/_lancedb.pyi
+++ b/python/python/lancedb/_lancedb.pyi
@@ -180,6 +180,8 @@ class Table:
        delete_unverified: Optional[bool] = None,
    ) -> OptimizeStats: ...
    async def uri(self) -> str: ...
+    async def initial_storage_options(self) -> Optional[Dict[str, str]]: ...
+    async def latest_storage_options(self) -> Optional[Dict[str, str]]: ...
    @property
    def tags(self) -> Tags: ...
    def query(self) -> Query: ...
--- a/python/python/lancedb/query.py
+++ b/python/python/lancedb/query.py
@@ -961,27 +961,22 @@ class LanceQueryBuilder(ABC):
        >>> query = [100, 100]
        >>> plan = table.search(query).analyze_plan()
        >>> print(plan)  # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
-        AnalyzeExec verbose=true, elapsed=..., metrics=...
-          TracedExec, elapsed=..., metrics=...
-            ProjectionExec: elapsed=..., expr=[...],
-            metrics=[output_rows=..., elapsed_compute=..., output_bytes=...]
-              GlobalLimitExec: elapsed=..., skip=0, fetch=10,
-              metrics=[output_rows=..., elapsed_compute=..., output_bytes=...]
-                FilterExec: elapsed=..., _distance@2 IS NOT NULL, metrics=[...]
-                  SortExec: elapsed=..., TopK(fetch=10), expr=[...],
+        AnalyzeExec verbose=true, metrics=[], cumulative_cpu=...
+          TracedExec, metrics=[], cumulative_cpu=...
+            ProjectionExec: expr=[...], metrics=[...], cumulative_cpu=...
+              GlobalLimitExec: skip=0, fetch=10, metrics=[...], cumulative_cpu=...
+                FilterExec: _distance@2 IS NOT NULL,
+                metrics=[output_rows=..., elapsed_compute=...], cumulative_cpu=...
+                  SortExec: TopK(fetch=10), expr=[...],
                  preserve_partitioning=[...],
-                  metrics=[output_rows=..., elapsed_compute=...,
-                  output_bytes=..., row_replacements=...]
-                    KNNVectorDistance: elapsed=..., metric=l2,
-                    metrics=[output_rows=..., elapsed_compute=...,
-                    output_bytes=..., output_batches=...]
-                      LanceRead: elapsed=..., uri=..., projection=[vector],
-                      num_fragments=..., range_before=None, range_after=None,
-                      row_id=true, row_addr=false,
-                      full_filter=--, refine_filter=--,
-                      metrics=[output_rows=..., elapsed_compute=..., output_bytes=...,
-                      fragments_scanned=..., ranges_scanned=1, rows_scanned=1,
-                      bytes_read=..., iops=..., requests=..., task_wait_time=...]
+                  metrics=[output_rows=..., elapsed_compute=..., row_replacements=...],
+                  cumulative_cpu=...
+                    KNNVectorDistance: metric=l2,
+                    metrics=[output_rows=..., elapsed_compute=..., output_batches=...],
+                    cumulative_cpu=...
+                      LanceRead: uri=..., projection=[vector], ...
+                      metrics=[output_rows=..., elapsed_compute=...,
+                      bytes_read=..., iops=..., requests=...], cumulative_cpu=...

        Returns
        -------
--- a/python/python/lancedb/table.py
+++ b/python/python/lancedb/table.py
@@ -2222,6 +2222,37 @@ class LanceTable(Table):
    def uri(self) -> str:
        return LOOP.run(self._table.uri())

+    def initial_storage_options(self) -> Optional[Dict[str, str]]:
+        """Get the initial storage options that were passed in when opening this table.
+
+        For dynamically refreshed options (e.g., credential vending), use
+        :meth:`latest_storage_options`.
+
+        Warning: This is an internal API and the return value is subject to change.
+
+        Returns
+        -------
+        Optional[Dict[str, str]]
+            The storage options, or None if no storage options were configured.
+        """
+        return LOOP.run(self._table.initial_storage_options())
+
+    def latest_storage_options(self) -> Optional[Dict[str, str]]:
+        """Get the latest storage options, refreshing from provider if configured.
+
+        This method is useful for credential vending scenarios where storage options
+        may be refreshed dynamically. If no dynamic provider is configured, this
+        returns the initial static options.
+
+        Warning: This is an internal API and the return value is subject to change.
+
+        Returns
+        -------
+        Optional[Dict[str, str]]
+            The storage options, or None if no storage options were configured.
+        """
+        return LOOP.run(self._table.latest_storage_options())
+
    def create_scalar_index(
        self,
        column: str,
@@ -3624,6 +3655,37 @@ class AsyncTable:
        """
        return await self._inner.uri()

+    async def initial_storage_options(self) -> Optional[Dict[str, str]]:
+        """Get the initial storage options that were passed in when opening this table.
+
+        For dynamically refreshed options (e.g., credential vending), use
+        :meth:`latest_storage_options`.
+
+        Warning: This is an internal API and the return value is subject to change.
+
+        Returns
+        -------
+        Optional[Dict[str, str]]
+            The storage options, or None if no storage options were configured.
+        """
+        return await self._inner.initial_storage_options()
+
+    async def latest_storage_options(self) -> Optional[Dict[str, str]]:
+        """Get the latest storage options, refreshing from provider if configured.
+
+        This method is useful for credential vending scenarios where storage options
+        may be refreshed dynamically. If no dynamic provider is configured, this
+        returns the initial static options.
+
+        Warning: This is an internal API and the return value is subject to change.
+
+        Returns
+        -------
+        Optional[Dict[str, str]]
+            The storage options, or None if no storage options were configured.
+        """
+        return await self._inner.latest_storage_options()
+
    async def add(
        self,
        data: DATA,
--- a/python/python/tests/test_remote_db.py
+++ b/python/python/tests/test_remote_db.py
@@ -601,6 +601,7 @@ def test_head():
 def test_query_sync_minimal():
    def handler(body):
        assert body == {
+            "distance_type": "l2",
            "k": 10,
            "prefilter": True,
            "refine_factor": None,
@@ -684,6 +685,7 @@ def test_query_sync_maximal():
 def test_query_sync_nprobes():
    def handler(body):
        assert body == {
+            "distance_type": "l2",
            "k": 10,
            "prefilter": True,
            "fast_search": True,
@@ -713,6 +715,7 @@ def test_query_sync_nprobes():
 def test_query_sync_no_max_nprobes():
    def handler(body):
        assert body == {
+            "distance_type": "l2",
            "k": 10,
            "prefilter": True,
            "fast_search": True,
@@ -835,6 +838,7 @@ def test_query_sync_hybrid():
        else:
            # Vector query
            assert body == {
+                "distance_type": "l2",
                "k": 42,
                "prefilter": True,
                "refine_factor": None,
--- a/python/python/tests/test_table.py
+++ b/python/python/tests/test_table.py
@@ -1880,13 +1880,8 @@ async def test_optimize_delete_unverified(tmp_db_async: AsyncConnection, tmp_pat
        ],
    )
    version = await table.version()
-    assert version == 2
-
-    # By removing a manifest file, we make the data files we just inserted unverified
-    version_name = 18446744073709551615 - (version - 1)
-    path = tmp_path / "test.lance" / "_versions" / f"{version_name:020}.manifest"
+    path = tmp_path / "test.lance" / "_versions" / f"{version - 1}.manifest"
    os.remove(path)
-
    stats = await table.optimize(delete_unverified=False)
    assert stats.prune.old_versions_removed == 0
    stats = await table.optimize(
--- a/python/src/arrow.rs
+++ b/python/src/arrow.rs
@@ -10,7 +10,8 @@ use arrow::{
 use futures::stream::StreamExt;
 use lancedb::arrow::SendableRecordBatchStream;
 use pyo3::{
-    exceptions::PyStopAsyncIteration, pyclass, pymethods, Bound, Py, PyAny, PyRef, PyResult, Python,
+    exceptions::PyStopAsyncIteration, pyclass, pymethods, Bound, PyAny, PyObject, PyRef, PyResult,
+    Python,
 };
 use pyo3_async_runtimes::tokio::future_into_py;

@@ -35,11 +36,8 @@ impl RecordBatchStream {
 #[pymethods]
 impl RecordBatchStream {
    #[getter]
-    pub fn schema(&self, py: Python) -> PyResult<Py<PyAny>> {
-        (*self.schema)
-            .clone()
-            .into_pyarrow(py)
-            .map(|obj| obj.unbind())
+    pub fn schema(&self, py: Python) -> PyResult<PyObject> {
+        (*self.schema).clone().into_pyarrow(py)
    }

    pub fn __aiter__(self_: PyRef<'_, Self>) -> PyRef<'_, Self> {
@@ -55,12 +53,7 @@ impl RecordBatchStream {
                .next()
                .await
                .ok_or_else(|| PyStopAsyncIteration::new_err(""))?;
-            Python::attach(|py| {
-                inner_next
-                    .infer_error()?
-                    .to_pyarrow(py)
-                    .map(|obj| obj.unbind())
-            })
+            Python::with_gil(|py| inner_next.infer_error()?.to_pyarrow(py))
        })
    }
 }
--- a/python/src/connection.rs
+++ b/python/src/connection.rs
@@ -12,7 +12,7 @@ use pyo3::{
    exceptions::{PyRuntimeError, PyValueError},
    pyclass, pyfunction, pymethods,
    types::{PyDict, PyDictMethods},
-    Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python,
+    Bound, FromPyObject, Py, PyAny, PyObject, PyRef, PyResult, Python,
 };
 use pyo3_async_runtimes::tokio::future_into_py;

@@ -114,7 +114,7 @@ impl Connection {
        data: Bound<'_, PyAny>,
        namespace: Vec<String>,
        storage_options: Option<HashMap<String, String>>,
-        storage_options_provider: Option<Py<PyAny>>,
+        storage_options_provider: Option<PyObject>,
        location: Option<String>,
    ) -> PyResult<Bound<'a, PyAny>> {
        let inner = self_.get_inner()?.clone();
@@ -152,7 +152,7 @@ impl Connection {
        schema: Bound<'_, PyAny>,
        namespace: Vec<String>,
        storage_options: Option<HashMap<String, String>>,
-        storage_options_provider: Option<Py<PyAny>>,
+        storage_options_provider: Option<PyObject>,
        location: Option<String>,
    ) -> PyResult<Bound<'a, PyAny>> {
        let inner = self_.get_inner()?.clone();
@@ -187,7 +187,7 @@ impl Connection {
        name: String,
        namespace: Vec<String>,
        storage_options: Option<HashMap<String, String>>,
-        storage_options_provider: Option<Py<PyAny>>,
+        storage_options_provider: Option<PyObject>,
        index_cache_size: Option<u32>,
        location: Option<String>,
    ) -> PyResult<Bound<'_, PyAny>> {
@@ -307,7 +307,7 @@ impl Connection {
                ..Default::default()
            };
            let response = inner.list_namespaces(request).await.infer_error()?;
-            Python::attach(|py| -> PyResult<Py<PyDict>> {
+            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("namespaces", response.namespaces)?;
                dict.set_item("page_token", response.page_token)?;
@@ -345,7 +345,7 @@ impl Connection {
                ..Default::default()
            };
            let response = inner.create_namespace(request).await.infer_error()?;
-            Python::attach(|py| -> PyResult<Py<PyDict>> {
+            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("properties", response.properties)?;
                Ok(dict.unbind())
@@ -386,7 +386,7 @@ impl Connection {
                ..Default::default()
            };
            let response = inner.drop_namespace(request).await.infer_error()?;
-            Python::attach(|py| -> PyResult<Py<PyDict>> {
+            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("properties", response.properties)?;
                dict.set_item("transaction_id", response.transaction_id)?;
@@ -413,7 +413,7 @@ impl Connection {
                ..Default::default()
            };
            let response = inner.describe_namespace(request).await.infer_error()?;
-            Python::attach(|py| -> PyResult<Py<PyDict>> {
+            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("properties", response.properties)?;
                Ok(dict.unbind())
@@ -443,7 +443,7 @@ impl Connection {
                ..Default::default()
            };
            let response = inner.list_tables(request).await.infer_error()?;
-            Python::attach(|py| -> PyResult<Py<PyDict>> {
+            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("tables", response.tables)?;
                dict.set_item("page_token", response.page_token)?;
--- a/python/src/error.rs
+++ b/python/src/error.rs
@@ -40,7 +40,7 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
                    request_id,
                    source,
                    status_code,
-                } => Python::attach(|py| {
+                } => Python::with_gil(|py| {
                    let message = err.to_string();
                    let http_err_cls = py
                        .import(intern!(py, "lancedb.remote.errors"))?
@@ -75,7 +75,7 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
                    max_read_failures,
                    source,
                    status_code,
-                } => Python::attach(|py| {
+                } => Python::with_gil(|py| {
                    let cause_err = http_from_rust_error(
                        py,
                        source.as_ref(),
--- a/python/src/header.rs
+++ b/python/src/header.rs
@@ -12,7 +12,7 @@ pub struct PyHeaderProvider {

 impl Clone for PyHeaderProvider {
    fn clone(&self) -> Self {
-        Python::attach(|py| Self {
+        Python::with_gil(|py| Self {
            provider: self.provider.clone_ref(py),
        })
    }
@@ -25,7 +25,7 @@ impl PyHeaderProvider {

    /// Get headers from the Python provider (internal implementation)
    fn get_headers_internal(&self) -> Result<HashMap<String, String>, String> {
-        Python::attach(|py| {
+        Python::with_gil(|py| {
            // Call the get_headers method
            let result = self.provider.call_method0(py, "get_headers");

--- a/python/src/permutation.rs
+++ b/python/src/permutation.rs
@@ -281,7 +281,7 @@ impl PyPermutationReader {
        let reader = slf.reader.clone();
        future_into_py(slf.py(), async move {
            let schema = reader.output_schema(selection).await.infer_error()?;
-            Python::attach(|py| schema.to_pyarrow(py).map(|obj| obj.unbind()))
+            Python::with_gil(|py| schema.to_pyarrow(py))
        })
    }

--- a/python/src/query.rs
+++ b/python/src/query.rs
@@ -453,7 +453,7 @@ impl Query {
        let inner = self_.inner.clone();
        future_into_py(self_.py(), async move {
            let schema = inner.output_schema().await.infer_error()?;
-            Python::attach(|py| schema.to_pyarrow(py).map(|obj| obj.unbind()))
+            Python::with_gil(|py| schema.to_pyarrow(py))
        })
    }

@@ -532,7 +532,7 @@ impl TakeQuery {
        let inner = self_.inner.clone();
        future_into_py(self_.py(), async move {
            let schema = inner.output_schema().await.infer_error()?;
-            Python::attach(|py| schema.to_pyarrow(py).map(|obj| obj.unbind()))
+            Python::with_gil(|py| schema.to_pyarrow(py))
        })
    }

@@ -627,7 +627,7 @@ impl FTSQuery {
        let inner = self_.inner.clone();
        future_into_py(self_.py(), async move {
            let schema = inner.output_schema().await.infer_error()?;
-            Python::attach(|py| schema.to_pyarrow(py).map(|obj| obj.unbind()))
+            Python::with_gil(|py| schema.to_pyarrow(py))
        })
    }

@@ -806,7 +806,7 @@ impl VectorQuery {
        let inner = self_.inner.clone();
        future_into_py(self_.py(), async move {
            let schema = inner.output_schema().await.infer_error()?;
-            Python::attach(|py| schema.to_pyarrow(py).map(|obj| obj.unbind()))
+            Python::with_gil(|py| schema.to_pyarrow(py))
        })
    }

--- a/python/src/storage_options.rs
+++ b/python/src/storage_options.rs
@@ -17,20 +17,20 @@ use pyo3::types::PyDict;
 /// Internal wrapper around a Python object implementing StorageOptionsProvider
 pub struct PyStorageOptionsProvider {
    /// The Python object implementing fetch_storage_options()
-    inner: Py<PyAny>,
+    inner: PyObject,
 }

 impl Clone for PyStorageOptionsProvider {
    fn clone(&self) -> Self {
-        Python::attach(|py| Self {
+        Python::with_gil(|py| Self {
            inner: self.inner.clone_ref(py),
        })
    }
 }

 impl PyStorageOptionsProvider {
-    pub fn new(obj: Py<PyAny>) -> PyResult<Self> {
-        Python::attach(|py| {
+    pub fn new(obj: PyObject) -> PyResult<Self> {
+        Python::with_gil(|py| {
            // Verify the object has a fetch_storage_options method
            if !obj.bind(py).hasattr("fetch_storage_options")? {
                return Err(pyo3::exceptions::PyTypeError::new_err(
@@ -60,7 +60,7 @@ impl StorageOptionsProvider for PyStorageOptionsProviderWrapper {
        let py_provider = self.py_provider.clone();

        tokio::task::spawn_blocking(move || {
-            Python::attach(|py| {
+            Python::with_gil(|py| {
                // Call the Python fetch_storage_options method
                let result = py_provider
                    .inner
@@ -119,7 +119,7 @@ impl StorageOptionsProvider for PyStorageOptionsProviderWrapper {
    }

    fn provider_id(&self) -> String {
-        Python::attach(|py| {
+        Python::with_gil(|py| {
            // Call provider_id() method on the Python object
            let obj = self.py_provider.inner.bind(py);
            obj.call_method0("provider_id")
@@ -143,7 +143,7 @@ impl std::fmt::Debug for PyStorageOptionsProviderWrapper {
 /// This is the main entry point for converting Python StorageOptionsProvider objects
 /// to Rust trait objects that can be used by the Lance ecosystem.
 pub fn py_object_to_storage_options_provider(
-    py_obj: Py<PyAny>,
+    py_obj: PyObject,
 ) -> PyResult<Arc<dyn StorageOptionsProvider>> {
    let py_provider = PyStorageOptionsProvider::new(py_obj)?;
    Ok(Arc::new(PyStorageOptionsProviderWrapper::new(py_provider)))
--- a/python/src/table.rs
+++ b/python/src/table.rs
@@ -287,7 +287,7 @@ impl Table {
        let inner = self_.inner_ref()?.clone();
        future_into_py(self_.py(), async move {
            let schema = inner.schema().await.infer_error()?;
-            Python::attach(|py| schema.to_pyarrow(py).map(|obj| obj.unbind()))
+            Python::with_gil(|py| schema.to_pyarrow(py))
        })
    }

@@ -437,7 +437,7 @@ impl Table {
        future_into_py(self_.py(), async move {
            let stats = inner.index_stats(&index_name).await.infer_error()?;
            if let Some(stats) = stats {
-                Python::attach(|py| {
+                Python::with_gil(|py| {
                    let dict = PyDict::new(py);
                    dict.set_item("num_indexed_rows", stats.num_indexed_rows)?;
                    dict.set_item("num_unindexed_rows", stats.num_unindexed_rows)?;
@@ -467,7 +467,7 @@ impl Table {
        let inner = self_.inner_ref()?.clone();
        future_into_py(self_.py(), async move {
            let stats = inner.stats().await.infer_error()?;
-            Python::attach(|py| {
+            Python::with_gil(|py| {
                let dict = PyDict::new(py);
                dict.set_item("total_bytes", stats.total_bytes)?;
                dict.set_item("num_rows", stats.num_rows)?;
@@ -502,6 +502,20 @@ impl Table {
        future_into_py(self_.py(), async move { inner.uri().await.infer_error() })
    }

+    pub fn initial_storage_options(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.inner_ref()?.clone();
+        future_into_py(self_.py(), async move {
+            Ok(inner.initial_storage_options().await)
+        })
+    }
+
+    pub fn latest_storage_options(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.inner_ref()?.clone();
+        future_into_py(self_.py(), async move {
+            inner.latest_storage_options().await.infer_error()
+        })
+    }
+
    pub fn __repr__(&self) -> String {
        match &self.inner {
            None => format!("ClosedTable({})", self.name),
@@ -521,7 +535,7 @@ impl Table {
        let inner = self_.inner_ref()?.clone();
        future_into_py(self_.py(), async move {
            let versions = inner.list_versions().await.infer_error()?;
-            let versions_as_dict = Python::attach(|py| {
+            let versions_as_dict = Python::with_gil(|py| {
                versions
                    .iter()
                    .map(|v| {
@@ -872,7 +886,7 @@ impl Tags {
            let tags = inner.tags().await.infer_error()?;
            let res = tags.list().await.infer_error()?;

-            Python::attach(|py| {
+            Python::with_gil(|py| {
                let py_dict = PyDict::new(py);
                for (key, contents) in res {
                    let value_dict = PyDict::new(py);
--- a/rust/lancedb/Cargo.toml
+++ b/rust/lancedb/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.24.0"
+version = "0.24.1"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
--- a/rust/lancedb/src/connection.rs
+++ b/rust/lancedb/src/connection.rs
@@ -892,6 +892,7 @@ pub struct ConnectBuilder {
    embedding_registry: Option<Arc<dyn EmbeddingRegistry>>,
 }

+#[cfg(feature = "remote")]
 const ENV_VARS_TO_STORAGE_OPTS: [(&str, &str); 1] =
    [("AZURE_STORAGE_ACCOUNT_NAME", "azure_storage_account_name")];

--- a/rust/lancedb/src/dataloader/permutation/shuffle.rs
+++ b/rust/lancedb/src/dataloader/permutation/shuffle.rs
@@ -171,7 +171,7 @@ impl Shuffler {
            // This is kind of an annoying limitation but if we allow runt clumps from batches then
            // clumps will get unaligned and we will mess up the clumps when we do the in-memory
            // shuffle step.  If this is a problem we can probably figure out a better way to do this.
-            if !is_last && batch.num_rows() as u64 % clump_size != 0 {
+            if !is_last && !(batch.num_rows() as u64).is_multiple_of(clump_size) {
                return Err(Error::Runtime {
                    message: format!(
                        "Expected batch size ({}) to be divisible by clump size ({})",
--- a/rust/lancedb/src/dataloader/permutation/split.rs
+++ b/rust/lancedb/src/dataloader/permutation/split.rs
@@ -1,12 +1,9 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors

-use std::{
-    iter,
-    sync::{
-        atomic::{AtomicBool, AtomicU64, AtomicUsize, Ordering},
-        Arc,
-    },
+use std::sync::{
+    atomic::{AtomicBool, AtomicU64, AtomicUsize, Ordering},
+    Arc,
 };

 use arrow_array::{Array, BooleanArray, RecordBatch, UInt64Array};
@@ -158,7 +155,7 @@ impl Splitter {
                remaining_in_split
            };

-            split_ids.extend(iter::repeat(split_id as u64).take(rows_to_add as usize));
+            split_ids.extend(std::iter::repeat_n(split_id as u64, rows_to_add as usize));
            if done {
                // Quit early if we've run out of splits
                break;
@@ -662,7 +659,7 @@ mod tests {
        assert_eq!(split_batch.num_rows(), total_split_sizes as usize);
        let mut expected = Vec::with_capacity(total_split_sizes as usize);
        for (i, size) in expected_split_sizes.iter().enumerate() {
-            expected.extend(iter::repeat(i as u64).take(*size as usize));
+            expected.extend(std::iter::repeat_n(i as u64, *size as usize));
        }
        let expected = Arc::new(UInt64Array::from(expected)) as Arc<dyn Array>;

--- a/rust/lancedb/src/index/vector.rs
+++ b/rust/lancedb/src/index/vector.rs
@@ -297,10 +297,10 @@ impl IvfPqIndexBuilder {
 }

 pub(crate) fn suggested_num_sub_vectors(dim: u32) -> u32 {
-    if dim % 16 == 0 {
+    if dim.is_multiple_of(16) {
        // Should be more aggressive than this default.
        dim / 16
-    } else if dim % 8 == 0 {
+    } else if dim.is_multiple_of(8) {
        dim / 8
    } else {
        log::warn!(
--- a/rust/lancedb/src/remote/table.rs
+++ b/rust/lancedb/src/remote/table.rs
@@ -468,9 +468,7 @@ impl<S: HttpSend> RemoteTable<S> {
        self.apply_query_params(&mut body, &query.base)?;

        // Apply general parameters, before we dispatch based on number of query vectors.
-        if let Some(distance_type) = query.distance_type {
-            body["distance_type"] = serde_json::json!(distance_type);
-        }
+        body["distance_type"] = serde_json::json!(query.distance_type.unwrap_or_default());
        // In 0.23.1 we migrated from `nprobes` to `minimum_nprobes` and `maximum_nprobes`.
        // Old client / new server: since minimum_nprobes is missing, fallback to nprobes
        // New client / old server: old server will only see nprobes, make sure to set both
@@ -1495,6 +1493,14 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
        None
    }

+    async fn initial_storage_options(&self) -> Option<HashMap<String, String>> {
+        None
+    }
+
+    async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>> {
+        Ok(None)
+    }
+
    async fn stats(&self) -> Result<TableStatistics> {
        let request = self
            .client
@@ -2232,6 +2238,7 @@ mod tests {
            let body: serde_json::Value = serde_json::from_slice(body).unwrap();
            let mut expected_body = serde_json::json!({
                "prefilter": true,
+                "distance_type": "l2",
                "nprobes": 20,
                "minimum_nprobes": 20,
                "maximum_nprobes": 20,
--- a/rust/lancedb/src/table.rs
+++ b/rust/lancedb/src/table.rs
@@ -611,7 +611,17 @@ pub trait BaseTable: std::fmt::Display + std::fmt::Debug + Send + Sync {
    /// Get the table URI (storage location)
    async fn uri(&self) -> Result<String>;
    /// Get the storage options used when opening this table, if any.
+    #[deprecated(since = "0.25.0", note = "Use initial_storage_options() instead")]
    async fn storage_options(&self) -> Option<HashMap<String, String>>;
+    /// Get the initial storage options that were passed in when opening this table.
+    ///
+    /// For dynamically refreshed options (e.g., credential vending), use [`Self::latest_storage_options`].
+    async fn initial_storage_options(&self) -> Option<HashMap<String, String>>;
+    /// Get the latest storage options, refreshing from provider if configured.
+    ///
+    /// Returns `Ok(Some(options))` if storage options are available (static or refreshed),
+    /// `Ok(None)` if no storage options were configured, or `Err(...)` if refresh failed.
+    async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>>;
    /// Poll until the columns are fully indexed. Will return Error::Timeout if the columns
    /// are not fully indexed within the timeout.
    async fn wait_for_index(
@@ -1328,10 +1338,32 @@ impl Table {
    /// Get the storage options used when opening this table, if any.
    ///
    /// Warning: This is an internal API and the return value is subject to change.
+    #[deprecated(since = "0.25.0", note = "Use initial_storage_options() instead")]
    pub async fn storage_options(&self) -> Option<HashMap<String, String>> {
+        #[allow(deprecated)]
        self.inner.storage_options().await
    }

+    /// Get the initial storage options that were passed in when opening this table.
+    ///
+    /// For dynamically refreshed options (e.g., credential vending), use [`Self::latest_storage_options`].
+    ///
+    /// Warning: This is an internal API and the return value is subject to change.
+    pub async fn initial_storage_options(&self) -> Option<HashMap<String, String>> {
+        self.inner.initial_storage_options().await
+    }
+
+    /// Get the latest storage options, refreshing from provider if configured.
+    ///
+    /// This method is useful for credential vending scenarios where storage options
+    /// may be refreshed dynamically. If no dynamic provider is configured, this
+    /// returns the initial static options.
+    ///
+    /// Warning: This is an internal API and the return value is subject to change.
+    pub async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>> {
+        self.inner.latest_storage_options().await
+    }
+
    /// Get statistics about an index.
    /// Returns None if the index does not exist.
    pub async fn index_stats(
@@ -1425,9 +1457,7 @@ impl Table {
            })
            .collect::<Vec<_>>();

-        let unioned = UnionExec::try_new(projected_plans).map_err(|err| Error::Runtime {
-            message: err.to_string(),
-        })?;
+        let unioned = Arc::new(UnionExec::new(projected_plans));
        // We require 1 partition in the final output
        let repartitioned = RepartitionExec::try_new(
            unioned,
@@ -2061,7 +2091,7 @@ impl NativeTable {
            return provided;
        }
        let suggested = suggested_num_sub_vectors(dim);
-        if num_bits.is_some_and(|num_bits| num_bits == 4) && suggested % 2 != 0 {
+        if num_bits.is_some_and(|num_bits| num_bits == 4) && !suggested.is_multiple_of(2) {
            // num_sub_vectors must be even when 4 bits are used
            suggested + 1
        } else {
@@ -3233,6 +3263,10 @@ impl BaseTable for NativeTable {
    }

    async fn storage_options(&self) -> Option<HashMap<String, String>> {
+        self.initial_storage_options().await
+    }
+
+    async fn initial_storage_options(&self) -> Option<HashMap<String, String>> {
        self.dataset
            .get()
            .await
@@ -3240,6 +3274,11 @@ impl BaseTable for NativeTable {
            .and_then(|dataset| dataset.initial_storage_options().cloned())
    }

+    async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>> {
+        let dataset = self.dataset.get().await?;
+        Ok(dataset.latest_storage_options().await?.map(|o| o.0))
+    }
+
    async fn index_stats(&self, index_name: &str) -> Result<Option<IndexStatistics>> {
        let stats = match self
            .dataset
@@ -3402,7 +3441,6 @@ pub struct FragmentSummaryStats {
 #[cfg(test)]
 #[allow(deprecated)]
 mod tests {
-    use std::iter;
    use std::sync::atomic::{AtomicBool, Ordering};
    use std::sync::Arc;
    use std::time::Duration;
@@ -4019,7 +4057,7 @@ mod tests {
                schema.clone(),
                vec![
                    Arc::new(Int32Array::from_iter_values(offset..(offset + 10))),
-                    Arc::new(Int32Array::from_iter_values(iter::repeat(age).take(10))),
+                    Arc::new(Int32Array::from_iter_values(std::iter::repeat_n(age, 10))),
                ],
            )],
            schema,
--- a/rust/lancedb/src/table/dataset.rs
+++ b/rust/lancedb/src/table/dataset.rs
@@ -100,8 +100,7 @@ impl DatasetRef {
                let should_checkout = match &target_ref {
                    refs::Ref::Version(_, Some(target_ver)) => version != target_ver,
                    refs::Ref::Version(_, None) => true, // No specific version, always checkout
-                    refs::Ref::VersionNumber(target_ver) => version != target_ver,
-                    refs::Ref::Tag(_) => true, // Always checkout for tags
+                    refs::Ref::Tag(_) => true,           // Always checkout for tags
                };

                if should_checkout {
--- a/rust/lancedb/tests/embedding_registry_test.rs
+++ b/rust/lancedb/tests/embedding_registry_test.rs
@@ -4,7 +4,6 @@
 use std::{
    borrow::Cow,
    collections::{HashMap, HashSet},
-    iter::repeat,
    sync::Arc,
 };

@@ -268,9 +267,10 @@ fn create_some_records() -> Result<impl IntoArrow> {
            schema.clone(),
            vec![
                Arc::new(Int32Array::from_iter_values(0..TOTAL as i32)),
-                Arc::new(StringArray::from_iter(
-                    repeat(Some("hello world".to_string())).take(TOTAL),
-                )),
+                Arc::new(StringArray::from_iter(std::iter::repeat_n(
+                    Some("hello world".to_string()),
+                    TOTAL,
+                ))),
            ],
        )
        .unwrap()]
Author	SHA1	Message	Date
Jack Ye	381e7cb9a6	Revert "fix: pass storage_options in LanceNamespaceDatabase::create_table" This reverts commit `1078983993`.	2026-01-30 17:28:15 -08:00
Jack Ye	a11d28eb33	feat: add initial and latest storage options apis	2026-01-30 17:06:45 -08:00
Jack Ye	1078983993	fix: pass storage_options in LanceNamespaceDatabase::create_table When creating tables via LanceNamespaceDatabase, the storage_options (e.g., S3 endpoint, credentials) stored on the database were not being passed to the underlying NativeTable::create_from_namespace call. This caused issues when using federated namespace databases with custom storage configurations (e.g., minio instead of AWS S3) - the table creation would fail because it tried to use default AWS endpoints. The fix injects self.storage_options into the write params before calling create_from_namespace, ensuring the correct storage configuration is used. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-01-30 13:17:40 -08:00
Lance Release	8500b16eca	Bump version: 0.24.1-beta.0 → 0.24.1	2026-01-26 23:39:18 +00:00
Lance Release	57e7282342	Bump version: 0.24.0 → 0.24.1-beta.0	2026-01-26 23:38:50 +00:00
Lance Release	cc5f8070d7	Bump version: 0.27.1-beta.0 → 0.27.1	2026-01-26 23:38:24 +00:00
Lance Release	dc0fb01f6b	Bump version: 0.27.0 → 0.27.1-beta.0	2026-01-26 23:38:23 +00:00
LanceDB Robot	94b7781551	feat: update lance dependency to v1.0.4 (#2944 ) ## Summary - bump Lance dependencies to v1.0.4 - run `cargo clippy --workspace --tests --all-features -- -D warnings` - run `cargo fmt --all` ## Testing - `cargo clippy --workspace --tests --all-features -- -D warnings` ## Reference - https://github.com/lance-format/lance/releases/tag/v1.0.4	2026-01-26 15:37:28 -08:00
Jack Ye	7bf020b3d5	chore: fix clippy when remote flag is not set (#2943 ) Also add a step in CI to ensure this does not happen in the future	2026-01-26 13:59:31 -08:00
LanceDB Robot	12a98479dc	chore: update lance dependency to v1.0.4-rc.1 (#2942 ) ## Summary - bump Lance dependencies to v1.0.4-rc.1 - verified `cargo clippy --workspace --tests --all-features -- -D warnings` - ran `cargo fmt --all` ## References - https://github.com/lance-format/lance/releases/tag/v1.0.4-rc.1	2026-01-26 12:17:22 -08:00
Jack Ye	e4552e577a	chore(revert): revert update lance dependency to v2.0.0-rc.1 (#2936 ) (#2941 ) This reverts commit `bd84bba14d`, so that we can bump version to 1.0.4-rc.1	2026-01-26 11:13:59 -08:00
Will Jones	f979a902ad	ci(rust): fix MSRV check (#2940 ) Realized our MSRV check was inert because `rust-toolchain.toml` was overriding the Rust version. We set the `RUSTUP_TOOLCHAIN` environment variable, which overrides that. Also needed to update to MSRV 1.88 (due to dependencies like Lance and DataFusion) and fix some clippy warnings.	2026-01-23 15:57:09 -08:00