Merge remote-tracking branch 'origin/main' into gatekeeper/fix-2429-1

# Conflicts:
#	rust/lancedb/src/table/query.rs

nodejs/__test__/arrow.test.ts

@@ -6,7 +6,9 @@ import * as arrow17 from "apache-arrow-17";
 import * as arrow18 from "apache-arrow-18";
 
 import {
+  Vector as CurrentVector,
   convertToTable,
+  tableFromIPC as currentTableFromIPC,
   fromBufferToRecordBatch,
   fromDataToBuffer,
   fromRecordBatchToBuffer,
@@ -19,6 +21,7 @@ import {
   FunctionOptions,
 } from "../lancedb/embedding/embedding_function";
 import { EmbeddingFunctionConfig } from "../lancedb/embedding/registry";
+import { sanitizeTable } from "../lancedb/sanitize";
 
 // biome-ignore lint/suspicious/noExplicitAny: skip
 function sampleRecords(): Array<Record<string, any>> {
@@ -64,7 +67,11 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       tableFromIPC,
       DataType,
       Dictionary,
+      RecordBatch: ArrowRecordBatch,
+      Table: ArrowTable,
       Uint8: ArrowUint8,
+      makeData: arrowMakeData,
+      vectorFromArray,
       // biome-ignore lint/suspicious/noExplicitAny: <explanation>
     } = <any>arrow;
     type Schema = ApacheArrow["Schema"];
@@ -166,6 +173,36 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
     }
 
     describe("The function makeArrowTable", function () {
+      it("accepts snake_case embedding metadata like camelCase", function () {
+        const spellings = [
+          // biome-ignore lint/style/useNamingConvention: the Python wire spelling
+          { source_column: "text", vector_column: "vector" },
+          { sourceColumn: "text", vectorColumn: "vector" },
+        ];
+        for (const columns of spellings) {
+          const schema = new Schema(
+            [
+              new Field("text", new Utf8(), false),
+              new Field(
+                "vector",
+                new FixedSizeList(3, new Field("item", new Float32(), true)),
+                false,
+              ),
+            ],
+            new Map([
+              [
+                "embedding_functions",
+                JSON.stringify([{ name: "mock", model: {}, ...columns }]),
+              ],
+            ]),
+          );
+          // The vector field is non-nullable and absent from the data; only a
+          // recognized embedding config makes that acceptable.
+          const table = makeArrowTable([{ text: "hello" }], { schema });
+          expect(table.numRows).toBe(1);
+        }
+      });
+
       it("will use data types from a provided schema instead of inference", async function () {
         const schema = new Schema([
           new Field("a", new Int32(), false),
@@ -197,6 +234,35 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
         expect(table.getChild("d")?.toJSON()).toEqual([9n, 10n, null]);
       });
 
+      it("will use a provided FixedSizeList schema with typed array values", function () {
+        const schema = new Schema([
+          new Field("text", new Utf8(), false),
+          new Field(
+            "vector",
+            new FixedSizeList(3, new Field("item", new Float32(), false)),
+            false,
+          ),
+        ]);
+
+        const table = makeArrowTable(
+          [
+            {
+              text: "foo",
+              vector: new Float32Array([1, 2, 3]),
+            },
+          ],
+          { schema },
+        );
+
+        expect(table.getChild("text")?.toJSON()).toEqual(["foo"]);
+        expect(
+          table
+            .getChild("vector")
+            ?.toJSON()
+            .map((value) => value.toJSON()),
+        ).toEqual([[1, 2, 3]]);
+      });
+
       it("will assume the column `vector` is FixedSizeList<Float32> by default", async function () {
         const schema = new Schema([
           new Field("a", new Float(Precision.DOUBLE), true),
@@ -449,6 +515,137 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
         );
       });
 
+      it("will allow matching inferred types across records", function () {
+        expect(() =>
+          makeArrowTable([{ value: 1 }, { value: 2 }]),
+        ).not.toThrow();
+      });
+
+      it("will reject mismatched inferred types across records", function () {
+        expect(() => makeArrowTable([{ value: 1 }, { value: "two" }])).toThrow(
+          "Failed to infer schema for data. Previously inferred type Float64 but found Utf8 for field value at row 1. Consider providing an explicit schema.",
+        );
+      });
+
+      it("will ignore generated dictionary IDs when comparing inferred types", function () {
+        const table = makeArrowTable([{ str: "a" }, { str: "b" }], {
+          dictionaryEncodeStrings: true,
+        });
+
+        expect(table.getChild("str")?.toJSON()).toEqual(["a", "b"]);
+      });
+
+      it("will preserve null values without treating them as type mismatches", function () {
+        for (const records of [
+          [{ vector: [1, 2, 3] }, { vector: null }],
+          [{ vector: null }, { vector: [1, 2, 3] }],
+        ]) {
+          const table = makeArrowTable(records);
+
+          expect(table.numRows).toBe(2);
+          expect(table.getChild("vector")?.nullCount).toBe(1);
+        }
+      });
+
+      it("will preserve empty variable-size lists", function () {
+        for (const records of [
+          [{ items: [1] }, { items: [] }],
+          [{ items: [] }, { items: [1] }],
+        ]) {
+          const table = makeArrowTable(records);
+          expect(
+            table
+              .getChild("items")
+              ?.toJSON()
+              .map((value) => value.toJSON()),
+          ).toEqual(records.map((record) => record.items));
+        }
+      });
+
+      it("will propagate deferred evidence through nested lists", function () {
+        for (const records of [
+          [{ items: [1] }, { items: [null] }],
+          [{ items: [null] }, { items: [1] }],
+          [{ items: [null, 1] }, { items: [2, null] }],
+        ]) {
+          const table = makeArrowTable(records);
+          expect(
+            table
+              .getChild("items")
+              ?.toJSON()
+              .map((value) => value.toJSON()),
+          ).toEqual(records.map((record) => record.items));
+        }
+
+        const nestedRecords = [{ items: [[1]] }, { items: [[null]] }];
+        const nestedTable = makeArrowTable(nestedRecords);
+        expect(
+          nestedTable
+            .getChild("items")
+            ?.toJSON()
+            .map((value) =>
+              value
+                .toJSON()
+                .map((nestedValue: { toJSON: () => unknown[] }) =>
+                  nestedValue.toJSON(),
+                ),
+            ),
+        ).toEqual(nestedRecords.map((record) => record.items));
+      });
+
+      it("will reject incompatible deferred evidence within a list", function () {
+        for (const items of [
+          [[], 1],
+          [1, []],
+          [[null], 1],
+          [1, [null]],
+        ]) {
+          expect(() => makeArrowTable([{ items }])).toThrow(
+            "Failed to infer data type for field items at row 0.",
+          );
+        }
+      });
+
+      it("will reject empty fixed-size lists", function () {
+        expect(() =>
+          makeArrowTable([{ vector: [1, 2, 3] }, { vector: [] }]),
+        ).toThrow(
+          "Failed to infer schema for data. Previously inferred type FixedSizeList[3]<Float32> but found List[0] for field vector at row 1.",
+        );
+      });
+
+      it("will reject inferred leaf and branch shape changes", function () {
+        expect(() =>
+          makeArrowTable([{ value: 1 }, { value: { nested: 2 } }]),
+        ).toThrow(
+          "Failed to infer schema for data. Previously inferred type Float64 but found Struct for field value at row 1.",
+        );
+        expect(() =>
+          makeArrowTable([{ value: { nested: 1 } }, { value: 2 }]),
+        ).toThrow(
+          "Failed to infer schema for data. Previously inferred type Struct but found Float64 for field value at row 1.",
+        );
+      });
+
+      it("will allow null values around inferred struct values", function () {
+        for (const { records, nullIndex } of [
+          {
+            records: [{ value: null }, { value: { nested: 2 } }],
+            nullIndex: 0,
+          },
+          {
+            records: [{ value: { nested: 1 } }, { value: null }],
+            nullIndex: 1,
+          },
+        ]) {
+          const table = makeArrowTable(records);
+          const values = table.getChild("value");
+
+          expect(values?.nullCount).toBe(1);
+          expect(values?.get(nullIndex)).toBeNull();
+        }
+      });
+
       it("will allow a schema to be provided", async function () {
         await checkTableCreation(
           async (records, _, schema) =>
@@ -1025,6 +1222,114 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
     });
 
     describe("when using two versions of arrow", function () {
+      it("preserves a dictionary shared by multiple fields", async function () {
+        const values = ["alpha", "beta", "alpha"];
+        const dictionaryVector = vectorFromArray(values);
+        const batch = new ArrowRecordBatch({
+          first: dictionaryVector.data[0],
+          second: dictionaryVector.data[0],
+        });
+        const table = new ArrowTable([batch]);
+
+        const sanitized = sanitizeTable(table);
+        expect([...sanitized.getChild("first")!]).toEqual(values);
+        expect([...sanitized.getChild("second")!]).toEqual(values);
+        const firstType = sanitized.schema.fields[0].type as {
+          dictionary: unknown;
+        };
+        const secondType = sanitized.schema.fields[1].type as {
+          dictionary: unknown;
+        };
+        expect(secondType.dictionary).toBe(firstType.dictionary);
+        expect(sanitized.batches[0].data.children[1].dictionary).toBe(
+          sanitized.batches[0].data.children[0].dictionary,
+        );
+
+        const buf = await fromDataToBuffer(table);
+        const actual = currentTableFromIPC(buf);
+        expect([...actual.getChild("first")!]).toEqual(values);
+        expect([...actual.getChild("second")!]).toEqual(values);
+      });
+
+      it("preserves shared dictionary data from another Arrow version", async function () {
+        const values = ["alpha", "beta", "alpha"];
+        const dictionaryVector = vectorFromArray(values);
+        const firstBatch = new ArrowRecordBatch({
+          label: dictionaryVector.slice(0, 2).data[0],
+        });
+        const secondBatch = new ArrowRecordBatch({
+          label: dictionaryVector.slice(2).data[0],
+        });
+        const table = new ArrowTable([firstBatch, secondBatch]);
+
+        const sanitized = sanitizeTable(table);
+        expect([...sanitized.getChild("label")!]).toEqual(values);
+
+        const dictionaries = sanitized.batches.map(
+          (batch) => batch.data.children[0].dictionary,
+        );
+        expect(dictionaries[0]).toBeInstanceOf(CurrentVector);
+        expect(dictionaries[1]).toBe(dictionaries[0]);
+
+        const buf = await fromDataToBuffer(table);
+        const actual = currentTableFromIPC(buf);
+        expect([...actual.getChild("label")!]).toEqual(values);
+      });
+
+      it("preserves shared chunks in growing dictionaries", async function () {
+        const type = new Dictionary(new Utf8(), new Int32(), 42, false);
+        const firstDictionary = vectorFromArray(["alpha", "beta"], new Utf8());
+        const secondDictionary = firstDictionary.concat(
+          vectorFromArray(["gamma"], new Utf8()),
+        );
+        const firstData = arrowMakeData({
+          type,
+          data: Int32Array.from([0, 1]),
+          dictionary: firstDictionary,
+        });
+        const secondData = arrowMakeData({
+          type,
+          data: Int32Array.from([2]),
+          dictionary: secondDictionary,
+        });
+        const table = new ArrowTable([
+          new ArrowRecordBatch({ label: firstData }),
+          new ArrowRecordBatch({ label: secondData }),
+        ]);
+
+        const sanitized = sanitizeTable(table);
+        const expected = ["alpha", "beta", "gamma"];
+        expect([...sanitized.getChild("label")!]).toEqual(expected);
+        const firstLocalDictionary =
+          sanitized.batches[0].data.children[0].dictionary!;
+        const secondLocalDictionary =
+          sanitized.batches[1].data.children[0].dictionary!;
+        expect(secondLocalDictionary.data[0]).toBe(
+          firstLocalDictionary.data[0],
+        );
+
+        const buf = await fromTableToBuffer(sanitized);
+        const actual = currentTableFromIPC(buf);
+        expect([...actual.getChild("label")!]).toEqual(expected);
+      });
+
+      it("can serialize list data from another Arrow version", async function () {
+        const values = [["anime", "action"], [], null];
+        const vector = vectorFromArray(
+          values,
+          new List(new Field("item", new Utf8(), true)),
+        );
+        const table = new ArrowTable({ tags: vector });
+
+        const buf = await fromDataToBuffer(table);
+        const actual = currentTableFromIPC(buf);
+        const actualTags = actual.getChild("tags");
+
+        expect(actualTags?.get(0)?.toJSON()).toEqual(values[0]);
+        expect(actualTags?.get(1)?.toJSON()).toEqual(values[1]);
+        expect(actualTags?.get(2)).toBeNull();
+      });
+
       it("can still import data", async function () {
         const schema = new arrow15.Schema([
           new arrow15.Field("id", new arrow15.Int32()),

nodejs/__test__/connection.test.ts

@@ -4,7 +4,13 @@
 import { readdirSync } from "fs";
 import { Field, Float64, Schema } from "apache-arrow";
 import * as tmp from "tmp";
-import { Connection, Table, connect, connectNamespace } from "../lancedb";
+import {
+  Connection,
+  ListTablesResponse,
+  Table,
+  connect,
+  connectNamespace,
+} from "../lancedb";
 import { LocalTable } from "../lancedb/table";
 
 describe("when connecting", () => {
@@ -47,6 +53,7 @@ describe("given a connection", () => {
     await db.close();
     expect(db.isOpen()).toBe(false);
     await expect(db.tableNames()).rejects.toThrow("Connection is closed");
+    await expect(db.listTables()).rejects.toThrow("Connection is closed");
     await expect(db.renameTable("a", "b")).rejects.toThrow(
       "Connection is closed",
     );
@@ -89,6 +96,16 @@ 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);
@@ -119,6 +136,66 @@ describe("given a connection", () => {
     expect(tables).toEqual(["b", "c"]);
   });
 
+  it("should respect limit and page token when listing tables", async () => {
+    const db = await connect(tmpDir.name);
+
+    await db.createTable("b", [{ id: 1 }]);
+    await db.createTable("a", [{ id: 1 }]);
+    await db.createTable("c", [{ id: 1 }]);
+
+    const all = await db.listTables();
+    expect(all.tables).toEqual(["a", "b", "c"]);
+    expect(all.pageToken).toBeUndefined();
+
+    const first = await db.listTables({ limit: 1 });
+    expect(first.tables).toEqual(["a"]);
+    expect(first.pageToken).toBeDefined();
+
+    const second = await db.listTables({
+      limit: 1,
+      pageToken: first.pageToken,
+    });
+    expect(second.tables).toEqual(["b"]);
+  });
+
+  it("should visit every table exactly once when walking pages", async () => {
+    const db = await connect(tmpDir.name);
+
+    const created = ["a", "b", "c", "d", "e"];
+    for (const name of created) {
+      await db.createTable(name, [{ id: 1 }]);
+    }
+
+    const seen: string[] = [];
+    let pageToken: string | undefined = undefined;
+    do {
+      const page: ListTablesResponse = await db.listTables({
+        limit: 2,
+        pageToken,
+      });
+      seen.push(...page.tables);
+      pageToken = page.pageToken;
+    } while (pageToken);
+
+    expect(seen).toEqual(created);
+  });
+
+  it("should list tables in a namespace", async () => {
+    const db = await connect(tmpDir.name, {
+      // biome-ignore lint/style/useNamingConvention: opaque backend property key, must match Rust
+      namespaceClientProperties: { manifest_enabled: "true" },
+    });
+    await db.createNamespace(["child"]);
+    await db.createTable("nested", [{ id: 1 }], ["child"]);
+
+    await expect(db.listTables(["child"])).resolves.toEqual(
+      expect.objectContaining({ tables: ["nested"] }),
+    );
+    await expect(db.listTables()).resolves.toEqual(
+      expect.objectContaining({ tables: [] }),
+    );
+  });
+
   it("should create tables in v2 mode", async () => {
     const db = await connect(tmpDir.name);
     const data = [...Array(10000).keys()].map((i) => ({ id: i }));

nodejs/__test__/embedding.test.ts

@@ -11,8 +11,11 @@ import {
   Float16,
   Float32,
   Float64,
+  Int32,
   Schema,
   Utf8,
+  fromDataToBuffer,
+  tableFromIPC,
 } from "../lancedb/arrow";
 import { EmbeddingFunction, LanceSchema } from "../lancedb/embedding";
 import { getRegistry, register } from "../lancedb/embedding/registry";
@@ -184,6 +187,63 @@ describe("embedding functions", () => {
     const vector0 = JSON.parse(JSON.stringify(arr[0].vector));
     expect(vector0).toEqual([1, 2, 3]);
   });
+
+  it("should append generated vectors to a non-nullable schema", async () => {
+    @register("non_nullable_schema_test")
+    class MockEmbeddingFunction extends EmbeddingFunction<string> {
+      ndims() {
+        return 3;
+      }
+      embeddingDataType(): Float {
+        return new Float64();
+      }
+      async computeSourceEmbeddings(data: string[]) {
+        return data.map(() => [1, 2, 3]);
+      }
+    }
+
+    const schema = new Schema([
+      new Field("id", new Int32()),
+      new Field("text", new Utf8()),
+      new Field("type", new Utf8()),
+      new Field(
+        "vector",
+        new FixedSizeList(3, new Field("item", new Float64())),
+      ),
+    ]);
+    const func = new MockEmbeddingFunction();
+    const db = await connect(tmpDir.name);
+    const table = await db.createEmptyTable("test_non_nullable", schema, {
+      embeddingFunction: {
+        function: func,
+        sourceColumn: "text",
+      },
+    });
+
+    const data = [
+      { id: 1, text: "Carrot", type: "vegetable" },
+      { id: 2, text: "Apple", type: "fruit" },
+    ];
+    const buffer = await fromDataToBuffer(
+      data,
+      undefined,
+      await table.schema(),
+    );
+    const generatedTable = tableFromIPC(buffer);
+    const vectorField = generatedTable.schema.fields.find(
+      (field) => field.name === "vector",
+    );
+    expect(vectorField?.nullable).toBe(false);
+
+    await table.add(data);
+
+    const rows = await table.query().toArray();
+    expect(rows).toHaveLength(2);
+    for (const row of rows) {
+      expect([...row.vector]).toEqual([1, 2, 3]);
+    }
+  });
+
   it("should error when appending to a table with an unregistered embedding function", async () => {
     @register("mock")
     class MockEmbeddingFunction extends EmbeddingFunction<string> {
@@ -427,4 +487,52 @@ describe("embedding functions", () => {
       expect(stringSchema3).toEqual(stringExpectedSchema);
     },
   );
+  test("parses one function writing several vector columns", async () => {
+    class MockEmbeddingFunction extends EmbeddingFunction<string> {
+      ndims() {
+        return 3;
+      }
+      embeddingDataType(): Float {
+        return new Float32();
+      }
+      async computeQueryEmbeddings(_data: string) {
+        return [1, 2, 3];
+      }
+      async computeSourceEmbeddings(data: string[]) {
+        return Array.from({ length: data.length }).fill([
+          1, 2, 3,
+        ]) as number[][];
+      }
+    }
+    const registry = getRegistry();
+    registry.register("multi_output_mock")(MockEmbeddingFunction);
+
+    // A materialized view can project one source vector column under two
+    // names, so a table's configuration names the same function twice.
+    const parsed = await registry.parseFunctions(
+      new Map([
+        [
+          "embedding_functions",
+          JSON.stringify([
+            {
+              name: "multi_output_mock",
+              sourceColumn: "text",
+              vectorColumn: "vector_a",
+              model: {},
+            },
+            {
+              name: "multi_output_mock",
+              sourceColumn: "text",
+              vectorColumn: "vector_b",
+              model: {},
+            },
+          ]),
+        ],
+      ]),
+    );
+
+    expect(
+      [...parsed.values()].map(({ vectorColumn }) => vectorColumn).sort(),
+    ).toEqual(["vector_a", "vector_b"]);
+  });
 });

nodejs/__test__/materialized_view.test.ts

@@ -0,0 +1,147 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+import * as tmp from "tmp";
+
+import { Connection, connect } from "../lancedb";
+import {
+  DEFINITION_META_KEY,
+  definitionFromMetadata,
+} from "../lancedb/materialized_view";
+
+describe("materialized views", () => {
+  let tmpDir: tmp.DirResult;
+  let db: Connection;
+
+  beforeEach(async () => {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+    db = await connect(tmpDir.name);
+    await db.createTable(
+      "people",
+      [
+        { name: "ada", age: 36 },
+        { name: "kid", age: 7 },
+        { name: "grace", age: 85 },
+      ],
+      { storageOptions: { newTableEnableStableRowIds: "true" } },
+    );
+  });
+  afterEach(() => tmpDir.removeCallback());
+
+  it("rejects a stored limit a number cannot carry", () => {
+    const big = new Map([
+      [
+        DEFINITION_META_KEY,
+        '{"kind":"select","source_table":"people","limit":9007199254740993}',
+      ],
+    ]);
+    expect(() => definitionFromMetadata(big, "v")).toThrow(
+      /too large to represent exactly/,
+    );
+
+    const safe = new Map([
+      [
+        DEFINITION_META_KEY,
+        '{"kind":"select","source_table":"people","limit":42}',
+      ],
+    ]);
+    expect(definitionFromMetadata(safe, "v").limit).toBe(42);
+  });
+
+  it("creates, refreshes and queries a view", async () => {
+    const view = await db.createMaterializedView("adults", "people", {
+      select: ["name", ["shout", "upper(name)"]],
+      where: "age >= 18",
+    });
+    expect(view.name).toBe("adults");
+    expect(await view.table().countRows()).toBe(0);
+
+    const result = await view.refresh();
+    expect(result.mode).toBe("rebuild");
+    expect(Number(result.rowsWritten)).toBe(2);
+
+    const rows = await view.table().query().toArray();
+    expect(rows.map((r) => r.shout).sort()).toEqual(["ADA", "GRACE"]);
+  });
+
+  it("round-trips the definition", async () => {
+    await db.createMaterializedView("adults", "people", {
+      where: "age >= 18",
+    });
+    const view = await db.openMaterializedView("adults");
+    const definition = await view.definition();
+    expect(definition.sourceTable).toBe("people");
+    expect(definition.filter).toBe("age >= 18");
+    expect(definition.projections).toEqual([
+      ["name", "`name`"],
+      ["age", "`age`"],
+    ]);
+    expect(definition.inputs).toEqual(["age", "name"]);
+  });
+
+  it("refreshes incrementally after an append", async () => {
+    const view = await db.createMaterializedView("copy", "people");
+    await view.refresh();
+
+    const people = await db.openTable("people");
+    await people.add([{ name: "alan", age: 41 }]);
+    const result = await view.refresh();
+    expect(result.mode).toBe("incremental");
+    expect(Number(result.rowsWritten)).toBe(1);
+    expect(await view.table().countRows()).toBe(4);
+
+    expect((await view.refresh()).mode).toBe("no_op");
+  });
+
+  it("lists views and rejects non-views", async () => {
+    await db.createMaterializedView("adults", "people", {
+      where: "age >= 18",
+    });
+    expect(await db.listMaterializedViews()).toEqual(["adults"]);
+    await expect(db.openMaterializedView("people")).rejects.toThrow(
+      "not a materialized view",
+    );
+  });
+
+  it("rejects an invalid expression at create time", async () => {
+    await expect(
+      db.createMaterializedView("bad", "people", {
+        select: [["x", "missing + 1"]],
+      }),
+    ).rejects.toThrow("missing");
+  });
+
+  it("rejects invalid numeric options before creating anything", async () => {
+    for (const limit of [-5, 1.5, Infinity, NaN]) {
+      await expect(
+        db.createMaterializedView("bad", "people", { limit }),
+      ).rejects.toThrow("non-negative integer");
+    }
+    expect(await db.listMaterializedViews()).toEqual([]);
+
+    const view = await db.createMaterializedView("copy", "people");
+    for (const sourceVersion of [-1, 1.5, Infinity, NaN]) {
+      await expect(view.refresh({ sourceVersion })).rejects.toThrow(
+        "non-negative integer",
+      );
+    }
+  });
+
+  it("quotes bare select names", async () => {
+    await db.createTable("odd_names", [{ "order item": "widget" }], {
+      storageOptions: { newTableEnableStableRowIds: "true" },
+    });
+    const view = await db.createMaterializedView("quoted", "odd_names", {
+      select: ["order item"],
+    });
+    const result = await view.refresh();
+    expect(Number(result.rowsWritten)).toBe(1);
+  });
+
+  it("requires stable row ids on the source", async () => {
+    await db.createTable("plain", [{ x: 1 }]);
+    await expect(db.createMaterializedView("v", "plain")).rejects.toThrow(
+      "stable row ids",
+    );
+  });
+});

nodejs/__test__/package.test.ts

@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+import packageJson = require("../package.json");
+
+describe("package metadata", () => {
+  it("requires Node.js type declarations compatible with the runtime", () => {
+    expect(packageJson.engines.node).toBe(">= 18");
+    expect(packageJson.peerDependencies["@types/node"]).toBe(">=18");
+    expect(packageJson.peerDependenciesMeta["@types/node"]).toEqual({
+      optional: true,
+    });
+  });
+});

nodejs/__test__/query.test.ts

@@ -110,6 +110,81 @@ describe("Query outputSchema", () => {
   });
 });
 
+describe("Search pagination", () => {
+  let tmpDir: tmp.DirResult;
+  let table: Table;
+
+  beforeEach(async () => {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+    const db = await connect(tmpDir.name);
+    const schema = new Schema([
+      new Field("id", new Int64(), false),
+      new Field("text", new Utf8(), false),
+      new Field(
+        "vector",
+        new FixedSizeList(2, new Field("item", new Float32())),
+        false,
+      ),
+    ]);
+    const data = makeArrowTable(
+      [
+        { id: 1n, text: "common", vector: [0, 0] },
+        { id: 2n, text: "common common", vector: [1, 1] },
+        { id: 3n, text: "common common common", vector: [2, 2] },
+        { id: 4n, text: "common common common common", vector: [3, 3] },
+      ],
+      { schema },
+    );
+    table = await db.createTable("test", data);
+  });
+
+  afterEach(() => {
+    tmpDir.removeCallback();
+  });
+
+  it("applies offset after the vector search limit", async () => {
+    const allResults = await table
+      .vectorSearch([0, 0])
+      .select(["id"])
+      .limit(4)
+      .toArray();
+    const secondPage = await table
+      .vectorSearch([0, 0])
+      .select(["id"])
+      .limit(2)
+      .offset(2)
+      .toArray();
+
+    expect(allResults).toHaveLength(4);
+    expect(secondPage).toHaveLength(2);
+    expect(secondPage.map((row) => row.id)).toEqual(
+      allResults.slice(2, 4).map((row) => row.id),
+    );
+  });
+
+  it("applies offset after the full-text search limit", async () => {
+    await table.createIndex("text", { config: Index.fts() });
+
+    const allResults = await table
+      .search("common", "fts")
+      .select(["id"])
+      .limit(4)
+      .toArray();
+    const secondPage = await table
+      .search("common", "fts")
+      .select(["id"])
+      .limit(2)
+      .offset(2)
+      .toArray();
+
+    expect(allResults).toHaveLength(4);
+    expect(secondPage).toHaveLength(2);
+    expect(secondPage.map((row) => row.id)).toEqual(
+      allResults.slice(2, 4).map((row) => row.id),
+    );
+  });
+});
+
 describe("Query orderBy", () => {
   let tmpDir: tmp.DirResult;
   let table: Table;

nodejs/__test__/registry.test.ts

@@ -106,6 +106,77 @@ describe.each([arrow15, arrow16, arrow17, arrow18])("Registry", (arrow) => {
       'Embedding function with alias "mock-embedding" already exists',
     );
   });
+  test("parseFunctions keeps entries sharing a function name", async () => {
+    class MockEmbeddingFunction extends EmbeddingFunction<string> {
+      ndims() {
+        return 3;
+      }
+      embeddingDataType() {
+        return new arrow.Float32() as apiArrow.Float;
+      }
+      async computeSourceEmbeddings(data: string[]) {
+        return data.map(() => [1, 2, 3]);
+      }
+    }
+    register("mock-embedding")(MockEmbeddingFunction);
+    const parsed = await getRegistry().parseFunctions(
+      new Map([
+        [
+          "embedding_functions",
+          JSON.stringify([
+            {
+              name: "mock-embedding",
+              sourceColumn: "text",
+              vectorColumn: "vector_a",
+              model: {},
+            },
+            {
+              name: "mock-embedding",
+              sourceColumn: "text",
+              vectorColumn: "vector_b",
+              model: {},
+            },
+          ]),
+        ],
+      ]),
+    );
+    expect([...parsed.values()].map((f) => f.vectorColumn)).toEqual([
+      "vector_a",
+      "vector_b",
+    ]);
+
+    // The Python bindings write snake_case keys.
+    const snake = await getRegistry().parseFunctions(
+      new Map([
+        [
+          "embedding_functions",
+          JSON.stringify([
+            {
+              name: "mock-embedding",
+              // biome-ignore lint/style/useNamingConvention: the Python wire spelling
+              source_column: "text",
+              // biome-ignore lint/style/useNamingConvention: the Python wire spelling
+              vector_column: "vector_a",
+              model: {},
+            },
+            {
+              name: "mock-embedding",
+              // biome-ignore lint/style/useNamingConvention: the Python wire spelling
+              source_column: "text",
+              // biome-ignore lint/style/useNamingConvention: the Python wire spelling
+              vector_column: "vector_b",
+              model: {},
+            },
+          ]),
+        ],
+      ]),
+    );
+    expect([...snake.keys()]).toEqual(["vector_a", "vector_b"]);
+    expect([...snake.values()].map((f) => f.sourceColumn)).toEqual([
+      "text",
+      "text",
+    ]);
+  });
   test("schema should contain correct metadata", async () => {
     class MockEmbeddingFunction extends EmbeddingFunction<string> {
       constructor(args: FunctionOptions = {}) {

nodejs/__test__/remote.test.ts

@@ -75,6 +75,25 @@ async function withMockDatabase(
 }
 
 describe("remote connection", () => {
+  it("refuses materialized views before issuing any request", async () => {
+    const paths: string[] = [];
+    await withMockDatabase(
+      (req, res) => {
+        paths.push(req.url ?? "");
+        res.writeHead(404).end();
+      },
+      async (db) => {
+        await expect(db.openMaterializedView("secret_table")).rejects.toThrow(
+          /only on local databases/,
+        );
+        await expect(db.listMaterializedViews()).rejects.toThrow(
+          /only on local databases/,
+        );
+        expect(paths).toEqual([]);
+      },
+    );
+  });
+
   it("should accept partial connection options", async () => {
     await connect("db://test", {
       apiKey: "fake",
@@ -170,6 +189,38 @@ describe("remote connection", () => {
     );
   });
 
+  it("surfaces JSON server errors from remote table operations", async () => {
+    await withMockDatabase(
+      (req, res) => {
+        const path = req.url ?? "";
+        if (path.endsWith("/describe/")) {
+          res.writeHead(200, { "Content-Type": "application/json" }).end(
+            JSON.stringify({
+              name: "broken_table",
+              version: 1,
+              schema: { fields: [] },
+            }),
+          );
+          return;
+        }
+
+        if (path.endsWith("/count_rows/")) {
+          res
+            .writeHead(400, { "Content-Type": "application/json" })
+            .end(JSON.stringify({ error: "count rows failed" }));
+          return;
+        }
+
+        res.writeHead(404).end();
+      },
+      async (db) => {
+        const table = await db.openTable("broken_table");
+
+        await expect(table.countRows()).rejects.toThrow("count rows failed");
+      },
+    );
+  });
+
   it("should pass on requested extra headers", async () => {
     await withMockDatabase(
       (req, res) => {
@@ -279,7 +330,7 @@ describe("remote connection", () => {
     expect(createIndexBody?.["custom_stop_words"]).toEqual(["the"]);
   });
 
-  it("diffs and merges remote branches", async () => {
+  it("diffs and cherry-picks remote branches", async () => {
     const sampleDiff = {
       fromBranch: "exp",
       parentVersion: 1,
@@ -301,10 +352,9 @@ describe("remote connection", () => {
       changedColumns: [],
       addedIndexes: [],
       removedIndexes: [],
-      mergeable: true,
-      mergeBlockers: [],
+      errors: [],
     };
-    const mergeBodies: Record<string, unknown>[] = [];
+    const cherryPickBodies: Record<string, unknown>[] = [];
 
     await withMockDatabase(
       (req, res) => {
@@ -334,17 +384,16 @@ describe("remote connection", () => {
               .end(JSON.stringify(sampleDiff));
             return;
           }
-          if (path.endsWith("/branches/merge/")) {
-            mergeBodies.push(body);
+          if (path.endsWith("/branches/cherry_pick/")) {
+            cherryPickBodies.push(body);
             const dryRun = body["dry_run"] === true;
             const response = {
-              status: dryRun ? "ready" : "rejected",
+              status: dryRun ? "ready" : "failed",
               diff: dryRun
                 ? sampleDiff
                 : {
                     ...sampleDiff,
-                    mergeable: false,
-                    mergeBlockers: [
+                    errors: [
                       { code: "baseMoved", message: "main has advanced" },
                     ],
                   },
@@ -366,19 +415,19 @@ describe("remote connection", () => {
 
         await expect(branches.diff("exp")).resolves.toEqual(sampleDiff);
 
-        const rejected = await branches.merge("exp");
-        expect(rejected.status).toBe("rejected");
-        expect(rejected.diff.mergeBlockers).toEqual([
+        const failed = await branches.cherryPick("exp");
+        expect(failed.status).toBe("failed");
+        expect(failed.diff.errors).toEqual([
           { code: "baseMoved", message: "main has advanced" },
         ]);
 
-        const preview = await branches.merge("exp", true);
+        const preview = await branches.cherryPick("exp", true);
         expect(preview.status).toBe("ready");
         expect(preview.preview.promotedColumns).toEqual(["tag"]);
       },
     );
 
-    expect(mergeBodies).toEqual([
+    expect(cherryPickBodies).toEqual([
       // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
       { from_branch: "exp", dry_run: false },
       // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format

nodejs/__test__/table.test.ts

@@ -89,6 +89,44 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       await expect(table.countRows()).resolves.toBe(3);
     });
 
+    it("should support a foreign Float64 vector schema end to end", async () => {
+      const conn = await connect(tmpDir.name);
+      const schema = new arrow.Schema([
+        new arrow.Field("resource_id", new arrow.Int32(), false),
+        new arrow.Field(
+          "vector",
+          new arrow.FixedSizeList(
+            3,
+            new arrow.Field("value", new arrow.Float64(), true),
+          ),
+          false,
+        ),
+      ]);
+      const data = [
+        {
+          // biome-ignore lint/style/useNamingConvention: matches the reported schema
+          resource_id: 0,
+          vector: [0.1, 0.1, 0.1],
+        },
+      ];
+
+      const resources = await conn.createTable("resources", data, { schema });
+
+      const existing = await resources
+        .query()
+        .where("resource_id = 0")
+        .limit(1)
+        .toArray();
+      expect(existing).toHaveLength(1);
+
+      const matched = await resources
+        .search(Float64Array.from(data[0].vector))
+        .limit(1)
+        .toArray();
+      expect(matched).toHaveLength(1);
+      expect(matched[0]["resource_id"]).toBe(0);
+    });
+
     it("should support branches", async () => {
       await table.add([{ id: 1 }]);
       expect(await table.countRows()).toBe(1);
@@ -242,8 +280,16 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
         },
         numIndices: 0,
         numRows: 3,
-        totalBytes: 44,
+        // Full on-disk size of the two data files, footers and metadata included.
+        totalBytes: 684,
       });
+
+      // Index files count toward totalBytes too (only deletion files and
+      // manifests are excluded).
+      await table.createIndex("id", { config: Index.btree() });
+      const statsWithIndex = await table.stats();
+      expect(statsWithIndex.numIndices).toBe(1);
+      expect(statsWithIndex.totalBytes).toBeGreaterThan(684);
     });
 
     it("should overwrite data if asked", async () => {
@@ -3098,7 +3144,7 @@ describe("column name options", () => {
       .limit(10)
       .toArray();
     expect(results2.length).toBe(10);
-  });
+  }, 30_000);
 });
 
 describe("when creating an empty table", () => {
@@ -3485,3 +3531,120 @@ describe("LSM merge insert", () => {
     await expect(table.query().useLsm(true).toArray()).rejects.toThrow();
   });
 });
+
+describe("LSM convergence and stats", () => {
+  let tmpDir: tmp.DirResult;
+
+  beforeEach(() => {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+  });
+  afterEach(() => tmpDir.removeCallback());
+
+  async function lsmTable(conn: Connection): Promise<Table> {
+    const table = await conn.createEmptyTable(
+      "t",
+      new arrow.Schema([new arrow.Field("id", new arrow.Utf8(), false)]),
+    );
+    await table.setUnenforcedPrimaryKey("id");
+    await table.setLsmWriteSpec({ specType: "unsharded" });
+    return table;
+  }
+
+  // These four route through the server that owns the MemWAL, so a local table
+  // rejects them rather than answering. What is asserted here is that the
+  // bindings reach the core at all; the behavior against a real endpoint is
+  // covered by the mocked endpoint tests in rust/lancedb/src/remote/table.rs.
+  it("rejects flushLsm on a local table", async () => {
+    const conn = await connect(tmpDir.name);
+    const table = await lsmTable(conn);
+
+    await expect(table.flushLsm()).rejects.toThrow(/not supported/i);
+  });
+
+  it("rejects compactLsm on a local table", async () => {
+    const conn = await connect(tmpDir.name);
+    const table = await lsmTable(conn);
+
+    await expect(table.compactLsm()).rejects.toThrow(/not supported/i);
+  });
+
+  it("rejects getLsmStats on a local table", async () => {
+    const conn = await connect(tmpDir.name);
+    const table = await lsmTable(conn);
+
+    await expect(table.getLsmStats()).rejects.toThrow(/not supported/i);
+    await expect(table.getLsmStats(true)).rejects.toThrow(/not supported/i);
+  });
+
+  it("rejects checkpointLsm on a local table", async () => {
+    const conn = await connect(tmpDir.name);
+    const table = await lsmTable(conn);
+
+    // checkpointLsm seals first, so it surfaces flushLsm's rejection.
+    await expect(table.checkpointLsm()).rejects.toThrow(/not supported/i);
+  });
+});
+
+describe("computed columns", () => {
+  let tmpDir: tmp.DirResult;
+  beforeEach(() => {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+  });
+  afterEach(() => tmpDir.removeCallback());
+
+  it("declares a column and fills it on refresh", async () => {
+    const db = await connect(tmpDir.name);
+    const table = await db.createTable("computed", [{ x: 1 }, { x: 2 }]);
+
+    await table.addColumns({
+      computed: [{ name: "doubled", valueSql: "x * 2" }],
+    });
+    let rows = await table.query().toArray();
+    expect(rows.map((r) => r.doubled)).toEqual([null, null]);
+
+    const result = await table.refreshColumn("doubled");
+    expect(result.rowsFilled).toBe(2);
+
+    rows = await table.query().toArray();
+    expect(rows.map((r) => r.doubled).sort()).toEqual([2, 4]);
+  });
+
+  it("returns a job handle from refreshColumnAsync", async () => {
+    const db = await connect(tmpDir.name);
+    const table = await db.createTable("computed_job", [{ x: 1 }, { x: 2 }]);
+
+    await table.addColumns({
+      computed: [{ name: "doubled", valueSql: "x * 2" }],
+    });
+
+    const job = await table.refreshColumnAsync("doubled");
+    expect(job.id).toBeNull();
+    await job.wait();
+    expect(await job.status()).toBe("finished");
+
+    const rows = await table.query().toArray();
+    expect(rows.map((r) => r.doubled).sort()).toEqual([2, 4]);
+
+    // Bad input rejects at the call, not through the job.
+    await expect(table.refreshColumnAsync("x")).rejects.toThrow(
+      "not a computed column",
+    );
+  });
+
+  it("fills rows added since the last refresh", async () => {
+    const db = await connect(tmpDir.name);
+    const table = await db.createTable("computed_append", [{ x: 1 }]);
+
+    await table.addColumns({
+      computed: [{ name: "doubled", valueSql: "x * 2" }],
+    });
+    await table.refreshColumn("doubled");
+    await table.add([{ x: 5 }]);
+
+    const result = await table.refreshColumn("doubled");
+    expect(result.rowsFilled).toBe(1);
+
+    const rows = await table.query().toArray();
+    expect(rows.map((r) => r.doubled).sort()).toEqual([10, 2]);
+  });
+});