Files
lancedb/nodejs/__test__/remote.test.ts
T
Xuanwo 4d22c0ce2b feat: expose Function refresh resource budgets in SDKs (#4951)
## Summary

- Add the canonical Rust `FunctionWorkerResourceBudget` and
`RefreshColumnOptions::resource_budget()` for explicit Enterprise
Function refreshes.
- Forward the nested budget through Python sync/async, PyO3, Rust remote
requests, Node NAPI, and TypeScript.
- Require positive CPU and memory values; normalize an omitted nested
GPU count to numeric zero; reject the nested budget when combined with
the top-level `gpu_count` shorthand.
- Reject `resource_budget` on LanceDB Embedded refresh paths instead of
silently ignoring it.
- Document the Rust, Python, and TypeScript APIs, including that SQL
servers currently require all three budget fields.

The Rust, Python, and TypeScript additions use `cpu_millis` /
`cpuMillis`, `memory_bytes` / `memoryBytes`, and `gpu_count` /
`gpuCount`. The top-level GPU shorthand keeps its existing behavior and
remains mutually exclusive with the complete nested budget.

## Scope and compatibility

This change configures only the explicit refresh call. It does not
configure `add_columns` automatic refresh and does not introduce a
fleet-wide call-cap interface.

A LanceDB Enterprise server must expose the nested `resource_budget`
backfill contract. LanceDB Embedded continues to support its existing
expression refresh defaults and rejects the new complete budget
explicitly.

## Validation

Validated against the final signed product source:

- Rust: resource-budget remote serialization test `2 passed`; validation
test `1 passed`.
- Python: actual PyO3 build; remote-request matrix `22 passed`;
invalid-option matrix `20 passed`; local rejection `22 passed`; Ruff
check and format clean.
- Repository-standard Pyright entry point: `0 errors`, within the
repository's configured include set.
- Node: native build and Biome lint passed; the existing remote-request
test `1 passed`, including fractional, negative, overflow, NaN, and
infinity nested GPU cases; the existing local-rejection test `1 passed`.
- TypeDoc generation and generated-document cleanliness passed.
- The native-tested product source differs from this head only in two
semantically equivalent Node range checks required by Clippy. Current CI
compiles and lints the final blobs. No dependency or lockfile changes
are included.
2026-11-11 10:05:52 +08:00

2142 lines
72 KiB
TypeScript

// SPDX-License-Identifier: Apache-2.0
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
import * as http from "http";
import { RequestListener } from "http";
import packageJson = require("../package.json");
import {
ClientAuthMethod,
ClientConfig,
Connection,
ConnectionOptions,
OAuthConfig,
OAuthFlowType,
TlsConfig,
blob,
connect,
} from "../lancedb";
import {
Table as ArrowTable,
Field,
Int64,
RecordBatch,
RecordBatchReader,
Schema,
Struct,
makeArrowTable,
tableToIPC,
} from "../lancedb/arrow";
import {
HeaderProvider,
OAuthHeaderProvider,
StaticHeaderProvider,
} from "../lancedb/header";
import { Index } from "../lancedb/indices";
import type { JobProgress } from "../lancedb/job";
import { LocalTable } from "../lancedb/table";
// Test-only header providers
class CustomProvider extends HeaderProvider {
getHeaders(): Record<string, string> {
return { "X-Custom": "custom-value" };
}
}
class ErrorProvider extends HeaderProvider {
private errorMessage: string;
public callCount: number = 0;
constructor(errorMessage: string = "Test error") {
super();
this.errorMessage = errorMessage;
}
getHeaders(): Record<string, string> {
this.callCount++;
throw new Error(this.errorMessage);
}
}
class ConcurrentProvider extends HeaderProvider {
private counter: number = 0;
getHeaders(): Record<string, string> {
this.counter++;
return { "X-Request-Id": String(this.counter) };
}
}
async function withMockDatabase(
listener: RequestListener,
callback: (db: Connection) => void,
connectionOptions?: ConnectionOptions,
) {
const server = http.createServer(listener);
server.listen(8000);
const db = await connect(
"db://dev",
Object.assign(
{
apiKey: "fake",
hostOverride: "http://localhost:8000",
},
connectionOptions,
),
);
try {
await callback(db);
} finally {
// `close()` alone leaves the port bound until keep-alive sockets drain, so
// a single failing test would cascade into EADDRINUSE for every test after
// it. Destroy the connections and wait for the port to actually be free.
await new Promise<void>((resolve) => {
server.closeAllConnections();
server.close(() => resolve());
});
}
}
describe("remote connection", () => {
it.each([
{ dataStorageVersion: "2.0" },
{ enableV2ManifestPaths: false },
{ storageOptions: { bogusOptionXyz: "1" } },
])("rejects local create options %j before sending data", async (options) => {
const requests: string[] = [];
await withMockDatabase(
(req, res) => {
requests.push(req.url ?? "");
res.writeHead(200).end();
},
async (db) => {
await expect(
db.createTable("test", [{ value: 1 }], {
...options,
mode: "overwrite",
}),
).rejects.toThrow(/write_options.*LanceDB Enterprise/);
await expect(
db.createEmptyTable(
"test",
new Schema([new Field("value", new Int64(), true)]),
options,
),
).rejects.toThrow(/write_options.*LanceDB Enterprise/);
},
);
expect(requests).toEqual([]);
});
it.each([{ indexCacheSize: 5 }, { storageOptions: { x: "y" } }])(
"rejects local open options %j before sending a request",
async (options) => {
const requests: string[] = [];
await withMockDatabase(
(req, res) => {
requests.push(req.url ?? "");
res.writeHead(200).end();
},
async (db) => {
await expect(
db.openTable("test", undefined, options),
).rejects.toThrow(
/not supported for table access in LanceDB Enterprise/,
);
},
);
expect(requests).toEqual([]);
},
);
it.each([false, true])(
"normalizes remote blob writes (range target: %s)",
async (wide) => {
const field = (full: boolean) => {
const f = blob("image");
return full
? f
: new Field(
f.name,
new Struct((f.type as Struct).children.slice(0, 2)),
f.nullable,
f.metadata,
);
};
const schema = (full: boolean) =>
new Schema([new Field("id", new Int64(), true), field(full)]);
const writes: { path: string; schema: Schema }[] = [];
let storedWide = wide;
const describe = () => ({
version: writes.length + 1,
schema: {
fields: [
{ name: "id", type: { type: "int64" }, nullable: true },
{
name: "image",
nullable: true,
metadata: { "ARROW:extension:name": "lance.blob.v2" },
type: {
type: "struct",
fields: [
{
name: "data",
nullable: true,
type: { type: "large_binary" },
},
{ name: "uri", nullable: true, type: { type: "string" } },
...(storedWide
? ["position", "size"].map((name) => ({
name,
nullable: true,
type: { type: "uint64" },
}))
: []),
],
},
},
],
},
});
await withMockDatabase(
(req, res) => {
if (req.url?.includes("/describe/")) {
res
.writeHead(200, { "content-type": "application/json" })
.end(JSON.stringify(describe()));
return;
}
const chunks: Buffer[] = [];
// Failed streaming input aborts before end; only complete bodies commit.
req.on("error", () => {
/* Aborted inputs must not commit. */
});
req.on("data", (chunk) => chunks.push(chunk));
req.on("end", () => {
const reader = RecordBatchReader.from(Buffer.concat(chunks)).open();
// Only read the schema: Rust separately checks compressed wire values.
writes.push({ path: req.url ?? "", schema: reader.schema });
storedWide =
(reader.schema.fields[1].type as Struct).children.length === 4;
res.writeHead(200, { "content-type": "application/json" }).end(
JSON.stringify({
version: writes.length + 1,
// biome-ignore lint/style/useNamingConvention: server wire format
num_inserted_rows: 1,
}),
);
});
},
async (db) => {
const table = await db.openTable("test");
const input = makeArrowTable(
[{ id: 1n, image: Buffer.from("payload") }],
{ schema: schema(!wide) },
);
await table.add(input);
await table
.mergeInsert("id")
.whenMatchedUpdateAll()
.whenNotMatchedInsertAll()
.execute(input);
expect(writes).toHaveLength(2);
for (const write of writes)
expect(write.schema).toEqual(schema(wide));
expect(writes[0].path).toContain("/insert/");
expect(writes[1].path).toContain("/merge_insert/");
if (!wide) {
const invalid = makeArrowTable(
[
{
id: 1n,
image: {
uri: "s3://registered/payload",
position: 4,
size: 6,
},
},
],
{ schema: schema(true) },
);
await expect(table.add(invalid)).rejects.toThrow(
/cannot store byte ranges/,
);
await expect(
table
.mergeInsert("id")
.whenMatchedUpdateAll()
.whenNotMatchedInsertAll()
.execute(invalid),
).rejects.toThrow(/cannot store byte ranges/);
expect(writes).toHaveLength(2);
}
await table.add(input, { mode: "overwrite" });
expect(writes).toHaveLength(3);
expect(writes[2].path).toContain("mode=overwrite");
expect(writes[2].schema).toEqual(schema(!wide));
expect(await table.schema()).toEqual(schema(!wide));
},
);
},
);
it("reports unsupported operations with backend-neutral errors", async () => {
await withMockDatabase(
(req, res) => {
expect(req.url).toBe("/v1/table/test/describe/");
res.writeHead(200, { "Content-Type": "application/json" }).end(
JSON.stringify({
version: 1,
schema: {
fields: [
{ name: "id", type: { type: "int64" }, nullable: false },
{
name: "vector",
type: {
type: "fixed_size_list",
fields: [
{ name: "item", type: { type: "float" }, nullable: true },
],
length: 2,
},
nullable: false,
},
],
},
}),
);
},
async (db) => {
const table = (await db.openTable("test")) as LocalTable;
const cases: [() => Promise<unknown>, string][] = [
[() => table.usesV2ManifestPaths(), "uses_v2_manifest_paths"],
[() => table.migrateManifestPathsV2(), "migrate_manifest_paths_v2"],
[
() => table.createIndex("vector", { config: Index.hnswPq() }),
"IVF_HNSW_PQ",
],
];
for (const [run, operation] of cases) {
let message = `LanceDBError: not supported: ${operation} is not supported in LanceDB Enterprise.`;
if (operation === "IVF_HNSW_PQ") {
message += " Please use IVF_HNSW_SQ instead.";
}
await expect(run()).rejects.toThrow(new Error(message));
}
},
);
});
it("rejects nprobes(0) before sending a query", async () => {
const requests: string[] = [];
await withMockDatabase(
(req, res) => {
requests.push(req.url ?? "");
if (req.url === "/v1/table/test/describe/") {
res
.writeHead(200, { "Content-Type": "application/json" })
.end(JSON.stringify({ version: 1, schema: { fields: [] } }));
} else {
res.writeHead(404).end();
}
},
async (db) => {
const table = await db.openTable("test");
expect(() => table.vectorSearch([0, 0]).nprobes(0)).toThrow(
"Invalid input, nprobes must be greater than 0",
);
expect(() =>
table.query().nearestTo([0, 0]).fullTextSearch("dog").nprobes(0),
).toThrow("Invalid input, nprobes must be greater than 0");
await expect(
table
.vectorSearch(Promise.resolve([0, 0]))
.nprobes(0)
.toArrow(),
).rejects.toThrow("Invalid input, nprobes must be greater than 0");
},
);
expect(requests).toEqual(["/v1/table/test/describe/"]);
});
it.each([false, true])(
"preserves an empty query's schema with an empty batch: %s",
async (withEmptyBatch) => {
const schema = new Schema(
[new Field("doubled", new Int64(), false)],
new Map([["source", "query-output"]]),
);
const result = new ArrowTable(
schema,
withEmptyBatch ? [new RecordBatch(schema, undefined)] : [],
);
const response = Buffer.from(tableToIPC(result, "stream"));
let queryRequests = 0;
await withMockDatabase(
(req, res) => {
if (req.url?.endsWith("/describe/")) {
res.writeHead(200, { "Content-Type": "application/json" }).end(
JSON.stringify({
name: "items",
version: 1,
schema: {
fields: [
{ name: "id", type: { type: "int64" }, nullable: false },
],
},
}),
);
} else if (req.url?.endsWith("/query/")) {
queryRequests++;
req.resume();
req.on("end", () => {
res
.writeHead(200, {
"Content-Type": "application/vnd.apache.arrow.stream",
})
.end(response);
});
} else {
res.writeHead(404).end();
}
},
async (db) => {
const table = await db.openTable("items");
const result = await table
.query()
.where("id < 0")
.select({ doubled: "id * 2" })
.toArrow();
expect(result.numRows).toBe(0);
expect(result.schema).toEqual(schema);
expect(result.getChild("doubled")?.length).toBe(0);
},
);
expect(queryRequests).toBe(1);
},
);
it("rejects the external blob opt-in without blocking regular adds", async () => {
let insertRequests = 0;
const describeRequests: string[] = [];
await withMockDatabase(
(req, res) => {
const requestPath = req.url ?? "";
if (requestPath.endsWith("/describe/")) {
describeRequests.push(requestPath);
res.writeHead(200, { "Content-Type": "application/json" }).end(
JSON.stringify({
name: "items",
version: 1,
schema: {
fields: [
{
name: "id",
type: { type: "int64" },
nullable: true,
},
],
},
}),
);
return;
}
if (requestPath.endsWith("/insert/")) {
insertRequests++;
req.resume();
req.on("end", () => {
res
.writeHead(200, { "Content-Type": "application/json" })
.end(JSON.stringify({ version: insertRequests + 1 }));
});
return;
}
res.writeHead(404).end();
},
async (db) => {
const table = await db.openTable("items");
await expect(
table.add([{ id: 1n }], {
allowExternalBlobOutsideBases: true,
}),
).rejects.toThrow("only supported in LanceDB Embedded");
expect(insertRequests).toBe(0);
await expect(table.add([{ id: 2n }])).resolves.toMatchObject({
version: 2,
});
await expect(
table.add([{ id: 3n }], {
allowExternalBlobOutsideBases: false,
}),
).resolves.toMatchObject({ version: 3 });
},
);
expect(describeRequests.length).toBeGreaterThan(0);
expect(insertRequests).toBe(2);
});
it("should accept partial connection options", async () => {
await connect("db://test", {
apiKey: "fake",
clientConfig: {
timeoutConfig: { readTimeout: 5 },
retryConfig: { retries: 2 },
},
});
});
it("should accept overall timeout configuration", async () => {
await connect("db://test", {
apiKey: "fake",
clientConfig: {
timeoutConfig: { timeout: 30 },
},
});
// Test with all timeout parameters
await connect("db://test", {
apiKey: "fake",
clientConfig: {
timeoutConfig: {
timeout: 60,
connectTimeout: 10,
readTimeout: 20,
poolIdleTimeout: 300,
},
},
});
});
it("should pass down apiKey and userAgent", async () => {
await withMockDatabase(
(req, res) => {
expect(req.headers["x-api-key"]).toEqual("fake");
expect(req.headers["user-agent"]).toEqual(
`LanceDB-Node-Client/${packageJson.version}`,
);
const body = JSON.stringify({ tables: [] });
res.writeHead(200, { "Content-Type": "application/json" }).end(body);
},
async (db) => {
const tableNames = await db.tableNames();
expect(tableNames).toEqual([]);
},
);
});
it("allows customizing user agent", async () => {
await withMockDatabase(
(req, res) => {
expect(req.headers["user-agent"]).toEqual("MyApp/1.0");
const body = JSON.stringify({ tables: [] });
res.writeHead(200, { "Content-Type": "application/json" }).end(body);
},
async (db) => {
const tableNames = await db.tableNames();
expect(tableNames).toEqual([]);
},
{
clientConfig: {
userAgent: "MyApp/1.0",
},
},
);
});
it("rejects a zero blob request concurrency limit", async () => {
await expect(
connect("db://dev", {
apiKey: "fake",
clientConfig: { blobRequestConcurrency: 0 },
}),
).rejects.toThrow("blob_request_concurrency");
});
it("shows the full error messages on retry errors", async () => {
await withMockDatabase(
(_req, res) => {
// We retry on 500 errors, so we return 500s until the client gives up.
res.writeHead(500).end("Internal Server Error");
},
async (db) => {
try {
await db.tableNames();
fail("expected an error");
// biome-ignore lint/suspicious/noExplicitAny: skip
} catch (e: any) {
expect(e.message).toContain("Hit retry limit for request_id=");
expect(e.message).toContain("Caused by: Http error");
expect(e.message).toContain("500 Internal Server Error");
}
},
{
clientConfig: {
retryConfig: { retries: 2 },
},
},
);
});
it("lists the rows a Function refresh skipped", async () => {
const bodies: unknown[] = [];
await withMockDatabase(
(req, res) => {
const path = req.url ?? "";
if (path.endsWith("/describe/")) {
res.writeHead(200, { "Content-Type": "application/json" }).end(
JSON.stringify({
name: "docs",
version: 1,
schema: { fields: [] },
}),
);
return;
}
if (path === "/v1/table/docs/errors") {
let body = "";
req.on("data", (chunk) => {
body += chunk;
});
req.on("end", () => {
bodies.push(JSON.parse(body));
res.writeHead(200, { "Content-Type": "application/json" }).end(
`{"records": [{"job_id": "j-7", "fragment_id": 3, "row_offset": 9,
"column": "embedding", "function": "embed", "function_version": "2",
"table_version": 11, "error_type": "ValueError",
"error_message": "bad input 'x'", "created_at_millis": 1700000000000}],
"fragments": [{"job_id": "j-7", "fragment_id": 4, "rows_skipped": 500,
"rows_recorded": 100}], "truncated": true}`,
);
});
return;
}
res.writeHead(404).end();
},
async (db) => {
const table = await db.openTable("docs");
const errors = await table.functionErrors({
jobId: "j-7",
column: "embedding",
limit: 2,
});
expect(errors.truncated).toBe(true);
expect(errors.records.map((r) => r.errorMessage)).toEqual([
"bad input 'x'",
]);
expect(errors.records[0].rowOffset).toBe(9);
expect(errors.fragments[0].rowsSkipped).toBe(500);
await table.functionErrors();
await expect(table.functionErrors({ limit: -1 })).rejects.toThrow(
"limit must be a non-negative integer",
);
},
);
expect(bodies).toEqual([
JSON.parse('{"job_id": "j-7", "column": "embedding", "limit": 2}'),
{},
]);
});
it("forwards refresh options to the backfill request", async () => {
const bodies: unknown[] = [];
await withMockDatabase(
(req, res) => {
const path = req.url ?? "";
if (path.endsWith("/describe/")) {
res.writeHead(200, { "Content-Type": "application/json" }).end(
JSON.stringify({
name: "docs",
version: 1,
schema: { fields: [] },
}),
);
return;
}
if (path === "/v1/table/docs/backfill_column") {
let body = "";
req.on("data", (chunk) => {
body += chunk;
});
req.on("end", () => {
bodies.push(JSON.parse(body));
res
.writeHead(202, { "Content-Type": "application/json" })
.end('{"job_id": "j-9"}');
});
return;
}
res.writeHead(404).end();
},
async (db) => {
const table = await db.openTable("docs");
const job = await table.refreshColumnAsync("embedding", {
where: "id % 2 = 0",
batchSize: 16,
gpuClass: "a10g",
gpuCount: 2,
errorPolicy: "skip",
maxFailedFraction: 0.01,
maxFailedRows: 50,
rowTimeoutSeconds: 30,
initTimeoutSeconds: 120,
maxExecutorProcessesPerWorker: 2,
});
expect(job.id).toBe("j-9");
await table.refreshColumnAsync("embedding");
await table.refreshColumnAsync("embedding", {
resourceBudget: {
cpuMillis: 8_000,
memoryBytes: 16 * 1024 ** 3,
},
});
// Invalid options reject before any request is sent.
for (const [options, message] of [
[{ maxFailedRows: -1 }, "maxFailedRows"],
[{ errorPolicy: "retry" }, "errorPolicy"],
[{ where: " " }, "where"],
[{ maxFailedFraction: 2 }, "max_failed_fraction"],
[{ rowTimeoutSeconds: 0 }, "row_timeout_seconds"],
[{ numWorkers: 0 }, "num_workers"],
[{ gpuCount: 0 }, "gpu_count"],
[
{
resourceBudget: {
cpuMillis: 1_000,
memoryBytes: 1_024,
},
gpuCount: 1,
},
"gpu_count cannot be combined with resource_budget",
],
[
{
resourceBudget: {
cpuMillis: 0,
memoryBytes: 1_024,
},
},
"resourceBudget.cpuMillis",
],
[
{
resourceBudget: {
cpuMillis: 1_000,
memoryBytes: 1_024,
gpuCount: 1.5,
},
},
"resourceBudget.gpuCount",
],
[
{
resourceBudget: {
cpuMillis: 1_000,
memoryBytes: 1_024,
gpuCount: -1,
},
},
"resourceBudget.gpuCount",
],
[
{
resourceBudget: {
cpuMillis: 1_000,
memoryBytes: 1_024,
gpuCount: 2 ** 32,
},
},
"resourceBudget.gpuCount",
],
[
{
resourceBudget: {
cpuMillis: 1_000,
memoryBytes: 1_024,
gpuCount: Number.NaN,
},
},
"resourceBudget.gpuCount",
],
[
{
resourceBudget: {
cpuMillis: 1_000,
memoryBytes: 1_024,
gpuCount: Number.POSITIVE_INFINITY,
},
},
"resourceBudget.gpuCount",
],
] as const) {
await expect(
table.refreshColumnAsync("embedding", options),
).rejects.toThrow(message);
}
},
);
expect(bodies).toEqual([
JSON.parse(
`{"column": "embedding", "where": "id % 2 = 0", "batch_size": 16,
"gpu_class": "a10g", "gpu_count": 2, "error_policy": "skip",
"max_failed_fraction": 0.01, "max_failed_rows": 50,
"row_timeout_seconds": 30, "init_timeout_seconds": 120,
"max_executor_processes_per_worker": 2}`,
),
{ column: "embedding" },
JSON.parse(
`{"column": "embedding",
"resource_budget": {
"cpu_millis": 8000,
"memory_bytes": 17179869184,
"gpu_count": 0
}}`,
),
]);
});
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) => {
expect(req.headers["x-my-header"]).toEqual("my-value");
const body = JSON.stringify({ tables: [] });
res.writeHead(200, { "Content-Type": "application/json" }).end(body);
},
async (db) => {
const tableNames = await db.tableNames();
expect(tableNames).toEqual([]);
},
{
clientConfig: {
extraHeaders: {
"x-my-header": "my-value",
},
},
},
);
});
it("supports version time-travel and branches on remote", async () => {
await withMockDatabase(
(req, res) => {
const body = req.url?.includes("/branches/list")
? JSON.stringify({
branches: {
exp: { parentVersion: 1, createAt: 1, manifestSize: 1 },
},
})
: JSON.stringify({ name: "t", version: 2, schema: { fields: [] } });
res.writeHead(200, { "Content-Type": "application/json" }).end(body);
},
async (db) => {
// version-only (and "main" + version) time-travel the main chain
const v2 = await db.openTable("t", undefined, { version: 2 });
expect(v2.currentBranch()).toBeNull();
const mainV2 = await db.openTable("t", undefined, {
branch: "main",
version: 2,
});
expect(mainV2.currentBranch()).toBeNull();
// a non-main branch opens a handle scoped to that branch
const exp = await db.openTable("t", undefined, { branch: "exp" });
expect(exp.currentBranch()).toBe("exp");
const expV2 = await db.openTable("t", undefined, {
branch: "exp",
version: 2,
});
expect(expV2.currentBranch()).toBe("exp");
},
);
});
it("sends FTS options to remote tables", async () => {
let createIndexBody: Record<string, unknown> | undefined;
await withMockDatabase(
(req, res) => {
const path = req.url ?? "";
if (path.endsWith("/describe/")) {
res.writeHead(200, { "Content-Type": "application/json" }).end(
JSON.stringify({
name: "t",
version: 1,
schema: {
fields: [
{ name: "text", type: { type: "string" }, nullable: false },
],
},
}),
);
return;
}
if (path.endsWith("/create_index/")) {
let raw = "";
req.on("data", (chunk) => {
raw += chunk;
});
req.on("end", () => {
createIndexBody = JSON.parse(raw);
res.writeHead(200).end();
});
return;
}
res.writeHead(404).end();
},
async (db) => {
const table = await db.openTable("t");
await table.createIndex("text", {
config: Index.fts({
blockSize: 256,
removeStopWords: true,
customStopWords: ["the"],
}),
});
},
);
expect(createIndexBody?.["column"]).toBe("text");
expect(createIndexBody?.["index_type"]).toBe("FTS");
expect(createIndexBody?.["block_size"]).toBe(256);
expect(createIndexBody?.["custom_stop_words"]).toEqual(["the"]);
});
it("diffs and cherry-picks remote branches", async () => {
const sampleDiff = {
fromBranch: "exp",
parentVersion: 1,
mainVersion: 2,
branchVersion: 3,
baseMoved: false,
rowCountMain: 3,
rowCountBranch: 3,
rowSummary: {
unchanged: 3,
newOnBase: 0,
newOnBranch: 0,
staleRecompute: 0,
inputsChanged: 0,
deltaAvailable: false,
},
addedColumns: [{ name: "tag", dataType: "utf8", nullable: true }],
removedColumns: [],
changedColumns: [],
addedIndexes: [],
removedIndexes: [],
errors: [],
};
const cherryPickBodies: Record<string, unknown>[] = [];
await withMockDatabase(
(req, res) => {
const path = req.url ?? "";
if (path.endsWith("/describe/")) {
res.writeHead(200, { "Content-Type": "application/json" }).end(
JSON.stringify({
name: "t",
version: 2,
schema: { fields: [] },
}),
);
return;
}
let raw = "";
req.on("data", (chunk) => {
raw += chunk;
});
req.on("end", () => {
const body = raw ? JSON.parse(raw) : {};
if (path.endsWith("/branches/diff/")) {
// biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
expect(body).toEqual({ from_branch: "exp" });
res
.writeHead(200, { "Content-Type": "application/json" })
.end(JSON.stringify(sampleDiff));
return;
}
if (path.endsWith("/branches/cherry_pick/")) {
cherryPickBodies.push(body);
const dryRun = body["dry_run"] === true;
const response = {
status: dryRun ? "ready" : "failed",
diff: dryRun
? sampleDiff
: {
...sampleDiff,
errors: [
{ code: "baseMoved", message: "main has advanced" },
],
},
preview: { promotedColumns: dryRun ? ["tag"] : [] },
};
res
.writeHead(dryRun ? 200 : 409, {
"Content-Type": "application/json",
})
.end(JSON.stringify(response));
return;
}
res.writeHead(404).end();
});
},
async (db) => {
const table = await db.openTable("t");
const branches = await table.branches();
await expect(branches.diff("exp")).resolves.toEqual(sampleDiff);
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.cherryPick("exp", true);
expect(preview.status).toBe("ready");
expect(preview.preview.promotedColumns).toEqual(["tag"]);
},
);
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
{ from_branch: "exp", dry_run: true },
]);
});
describe("OAuthConfig", () => {
it("should expose client auth method values", () => {
expect(ClientAuthMethod.None).toBe("none");
expect(ClientAuthMethod.ClientSecretBasic).toBe("client_secret_basic");
expect(ClientAuthMethod.ClientSecretPost).toBe("client_secret_post");
});
it("should accept a confidential client with basic auth", () => {
const config: OAuthConfig = {
issuerUrl: "https://issuer.example.com",
clientId: "client-id",
clientSecret: "secret",
scopes: ["openid"],
flow: OAuthFlowType.AuthorizationCode,
clientAuthMethod: ClientAuthMethod.ClientSecretBasic,
};
expect(config.clientAuthMethod).toBe(ClientAuthMethod.ClientSecretBasic);
});
it("should accept a public PKCE client without auth method or secret", () => {
const config: OAuthConfig = {
issuerUrl: "https://issuer.example.com",
clientId: "client-id",
scopes: ["openid"],
flow: OAuthFlowType.AuthorizationCode,
usePkce: true,
};
expect(config.clientSecret).toBeUndefined();
expect(config.clientAuthMethod).toBeUndefined();
});
});
describe("TlsConfig", () => {
it("should create TlsConfig with all fields", () => {
const tlsConfig: TlsConfig = {
certFile: "/path/to/cert.pem",
keyFile: "/path/to/key.pem",
sslCaCert: "/path/to/ca.pem",
assertHostname: false,
};
expect(tlsConfig.certFile).toBe("/path/to/cert.pem");
expect(tlsConfig.keyFile).toBe("/path/to/key.pem");
expect(tlsConfig.sslCaCert).toBe("/path/to/ca.pem");
expect(tlsConfig.assertHostname).toBe(false);
});
it("should create TlsConfig with partial fields", () => {
const tlsConfig: TlsConfig = {
certFile: "/path/to/cert.pem",
keyFile: "/path/to/key.pem",
};
expect(tlsConfig.certFile).toBe("/path/to/cert.pem");
expect(tlsConfig.keyFile).toBe("/path/to/key.pem");
expect(tlsConfig.sslCaCert).toBeUndefined();
expect(tlsConfig.assertHostname).toBeUndefined();
});
it("should create ClientConfig with TlsConfig", () => {
const tlsConfig: TlsConfig = {
certFile: "/path/to/cert.pem",
keyFile: "/path/to/key.pem",
sslCaCert: "/path/to/ca.pem",
assertHostname: true,
};
const clientConfig: ClientConfig = {
userAgent: "test-agent",
tlsConfig: tlsConfig,
};
expect(clientConfig.userAgent).toBe("test-agent");
expect(clientConfig.tlsConfig).toBeDefined();
expect(clientConfig.tlsConfig?.certFile).toBe("/path/to/cert.pem");
expect(clientConfig.tlsConfig?.keyFile).toBe("/path/to/key.pem");
expect(clientConfig.tlsConfig?.sslCaCert).toBe("/path/to/ca.pem");
expect(clientConfig.tlsConfig?.assertHostname).toBe(true);
});
it("should handle empty TlsConfig", () => {
const tlsConfig: TlsConfig = {};
expect(tlsConfig.certFile).toBeUndefined();
expect(tlsConfig.keyFile).toBeUndefined();
expect(tlsConfig.sslCaCert).toBeUndefined();
expect(tlsConfig.assertHostname).toBeUndefined();
});
it("should accept TlsConfig in connection options", () => {
const tlsConfig: TlsConfig = {
certFile: "/path/to/cert.pem",
keyFile: "/path/to/key.pem",
sslCaCert: "/path/to/ca.pem",
assertHostname: false,
};
// Just verify that the ClientConfig accepts the TlsConfig
const clientConfig: ClientConfig = {
tlsConfig: tlsConfig,
};
const connectionOptions: ConnectionOptions = {
apiKey: "fake",
clientConfig: clientConfig,
};
// Verify the configuration structure is correct
expect(connectionOptions.clientConfig).toBeDefined();
expect(connectionOptions.clientConfig?.tlsConfig).toBeDefined();
expect(connectionOptions.clientConfig?.tlsConfig?.certFile).toBe(
"/path/to/cert.pem",
);
});
});
describe("header providers", () => {
it("should work with StaticHeaderProvider", async () => {
const provider = new StaticHeaderProvider({
authorization: "Bearer test-token",
"X-Custom": "value",
});
const headers = provider.getHeaders();
expect(headers).toEqual({
authorization: "Bearer test-token",
"X-Custom": "value",
});
// Test that it returns a copy
headers["X-Modified"] = "modified";
const headers2 = provider.getHeaders();
expect(headers2).not.toHaveProperty("X-Modified");
});
it("should pass headers from StaticHeaderProvider to requests", async () => {
const provider = new StaticHeaderProvider({
"X-Custom-Auth": "secret-token",
"X-Request-Source": "test-suite",
});
await withMockDatabase(
(req, res) => {
expect(req.headers["x-custom-auth"]).toEqual("secret-token");
expect(req.headers["x-request-source"]).toEqual("test-suite");
const body = JSON.stringify({ tables: [] });
res.writeHead(200, { "Content-Type": "application/json" }).end(body);
},
async () => {
// Use actual header provider mechanism instead of extraHeaders
const conn = await connect(
"db://dev",
{
apiKey: "fake",
hostOverride: "http://localhost:8000",
},
undefined, // session
provider, // headerProvider
);
const tableNames = await conn.tableNames();
expect(tableNames).toEqual([]);
},
);
});
it("should work with CustomProvider", () => {
const provider = new CustomProvider();
const headers = provider.getHeaders();
expect(headers).toEqual({ "X-Custom": "custom-value" });
});
it("should handle ErrorProvider errors", () => {
const provider = new ErrorProvider("Authentication failed");
expect(() => provider.getHeaders()).toThrow("Authentication failed");
expect(provider.callCount).toBe(1);
// Test that error is thrown each time
expect(() => provider.getHeaders()).toThrow("Authentication failed");
expect(provider.callCount).toBe(2);
});
it("should work with ConcurrentProvider", () => {
const provider = new ConcurrentProvider();
const headers1 = provider.getHeaders();
const headers2 = provider.getHeaders();
const headers3 = provider.getHeaders();
expect(headers1).toEqual({ "X-Request-Id": "1" });
expect(headers2).toEqual({ "X-Request-Id": "2" });
expect(headers3).toEqual({ "X-Request-Id": "3" });
});
describe("OAuthHeaderProvider", () => {
it("should initialize correctly", () => {
const fetcher = () => ({
accessToken: "token123",
expiresIn: 3600,
});
const provider = new OAuthHeaderProvider(fetcher);
expect(provider).toBeInstanceOf(HeaderProvider);
});
it("should fetch token on first use", async () => {
let callCount = 0;
const fetcher = () => {
callCount++;
return {
accessToken: "token123",
expiresIn: 3600,
};
};
const provider = new OAuthHeaderProvider(fetcher);
// Need to manually refresh first due to sync limitation
await provider.refreshToken();
const headers = provider.getHeaders();
expect(headers).toEqual({ authorization: "Bearer token123" });
expect(callCount).toBe(1);
// Second call should not fetch again
const headers2 = provider.getHeaders();
expect(headers2).toEqual({ authorization: "Bearer token123" });
expect(callCount).toBe(1);
});
it("should handle tokens without expiry", async () => {
const fetcher = () => ({
accessToken: "permanent_token",
});
const provider = new OAuthHeaderProvider(fetcher);
await provider.refreshToken();
const headers = provider.getHeaders();
expect(headers).toEqual({ authorization: "Bearer permanent_token" });
});
it("should throw error when access_token is missing", async () => {
const fetcher = () =>
({
expiresIn: 3600,
}) as { accessToken?: string; expiresIn?: number };
const provider = new OAuthHeaderProvider(
fetcher as () => {
accessToken: string;
expiresIn?: number;
},
);
await expect(provider.refreshToken()).rejects.toThrow(
"Token fetcher did not return 'accessToken'",
);
});
it("should handle async token fetchers", async () => {
const fetcher = async () => {
// Simulate async operation
await new Promise((resolve) => setTimeout(resolve, 10));
return {
accessToken: "async_token",
expiresIn: 3600,
};
};
const provider = new OAuthHeaderProvider(fetcher);
await provider.refreshToken();
const headers = provider.getHeaders();
expect(headers).toEqual({ authorization: "Bearer async_token" });
});
});
it("should merge header provider headers with extra headers", async () => {
const provider = new StaticHeaderProvider({
"X-From-Provider": "provider-value",
});
await withMockDatabase(
(req, res) => {
expect(req.headers["x-from-provider"]).toEqual("provider-value");
expect(req.headers["x-extra-header"]).toEqual("extra-value");
const body = JSON.stringify({ tables: [] });
res.writeHead(200, { "Content-Type": "application/json" }).end(body);
},
async () => {
// Use header provider with additional extraHeaders
const conn = await connect(
"db://dev",
{
apiKey: "fake",
hostOverride: "http://localhost:8000",
clientConfig: {
extraHeaders: {
"X-Extra-Header": "extra-value",
},
},
},
undefined, // session
provider, // headerProvider
);
const tableNames = await conn.tableNames();
expect(tableNames).toEqual([]);
},
);
});
});
describe("header provider integration", () => {
it("should work with TypeScript StaticHeaderProvider", async () => {
let requestCount = 0;
await withMockDatabase(
(req, res) => {
requestCount++;
// Check headers are present on each request
expect(req.headers["authorization"]).toEqual("Bearer test-token-123");
expect(req.headers["x-custom"]).toEqual("custom-value");
// Return different responses based on the endpoint
if (req.url === "/v1/table/test_table/describe/") {
const body = JSON.stringify({
name: "test_table",
schema: { fields: [] },
});
res
.writeHead(200, { "Content-Type": "application/json" })
.end(body);
} else {
const body = JSON.stringify({ tables: ["test_table"] });
res
.writeHead(200, { "Content-Type": "application/json" })
.end(body);
}
},
async () => {
// Create provider with static headers
const provider = new StaticHeaderProvider({
authorization: "Bearer test-token-123",
"X-Custom": "custom-value",
});
// Connect with the provider
const conn = await connect(
"db://dev",
{
apiKey: "fake",
hostOverride: "http://localhost:8000",
},
undefined, // session
provider, // headerProvider
);
// Make multiple requests to verify headers are sent each time
const tables1 = await conn.tableNames();
expect(tables1).toEqual(["test_table"]);
const tables2 = await conn.tableNames();
expect(tables2).toEqual(["test_table"]);
// Verify headers were sent with each request
expect(requestCount).toBeGreaterThanOrEqual(2);
},
);
});
it("should work with JavaScript function provider", async () => {
let requestId = 0;
await withMockDatabase(
(req, res) => {
// Check dynamic header is present
expect(req.headers["x-request-id"]).toBeDefined();
expect(req.headers["x-request-id"]).toMatch(/^req-\d+$/);
const body = JSON.stringify({ tables: [] });
res.writeHead(200, { "Content-Type": "application/json" }).end(body);
},
async () => {
// Create a JavaScript function that returns dynamic headers
const getHeaders = async () => {
requestId++;
return {
"X-Request-Id": `req-${requestId}`,
"X-Timestamp": new Date().toISOString(),
};
};
// Connect with the function directly
const conn = await connect(
"db://dev",
{
apiKey: "fake",
hostOverride: "http://localhost:8000",
},
undefined, // session
getHeaders, // headerProvider
);
// Make requests - each should have different headers
const tables = await conn.tableNames();
expect(tables).toEqual([]);
},
);
});
it("should support OAuth-like token refresh pattern", async () => {
let tokenVersion = 0;
await withMockDatabase(
(req, res) => {
// Verify authorization header
const authHeader = req.headers["authorization"];
expect(authHeader).toBeDefined();
expect(authHeader).toMatch(/^Bearer token-v\d+$/);
const body = JSON.stringify({ tables: [] });
res.writeHead(200, { "Content-Type": "application/json" }).end(body);
},
async () => {
// Simulate OAuth token fetcher
const fetchToken = async () => {
tokenVersion++;
return {
authorization: `Bearer token-v${tokenVersion}`,
};
};
// Connect with the function directly
const conn = await connect(
"db://dev",
{
apiKey: "fake",
hostOverride: "http://localhost:8000",
},
undefined, // session
fetchToken, // headerProvider
);
// Each request will fetch a new token
await conn.tableNames();
// Token should be different on next request
await conn.tableNames();
},
);
});
});
describe("renameTable", () => {
async function captureRenameRequest(
call: (db: Connection) => Promise<void>,
): Promise<{ url: string; body: Record<string, unknown> }> {
let captured: { url: string; body: Record<string, unknown> } | undefined;
await withMockDatabase((req, res) => {
let raw = "";
req.on("data", (chunk) => {
raw += chunk;
});
req.on("end", () => {
captured = {
url: req.url ?? "",
body: raw ? JSON.parse(raw) : {},
};
res.writeHead(200, { "Content-Type": "application/json" }).end("");
});
}, call);
if (!captured) {
throw new Error("mock server never saw a request");
}
return captured;
}
it("sends rename request for a table in the root namespace", async () => {
const { url, body } = await captureRenameRequest(async (db) => {
await db.renameTable("table1", "table2");
});
expect(url).toBe("/v1/table/table1/rename/");
// biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
expect(body).toEqual({ new_table_name: "table2" });
});
it("omits new_namespace when only the current namespace is supplied", async () => {
// Safe-default check: passing namespacePath alone must not send
// `new_namespace`, so the server keeps the table in its current
// namespace instead of silently moving it to root.
const { url, body } = await captureRenameRequest(async (db) => {
await db.renameTable("table1", "table2", {
namespacePath: ["ns1"],
});
});
expect(url).toBe("/v1/table/ns1$table1/rename/");
// biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
expect(body).toEqual({ new_table_name: "table2" });
});
it("includes new_namespace in the body for a cross-namespace rename", async () => {
const { url, body } = await captureRenameRequest(async (db) => {
await db.renameTable("table1", "table2", {
namespacePath: ["ns1"],
newNamespacePath: ["ns2"],
});
});
expect(url).toBe("/v1/table/ns1$table1/rename/");
expect(body).toEqual({
// biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
new_table_name: "table2",
// biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
new_namespace: ["ns2"],
});
});
});
});
describe("remote connection jobs surface", () => {
it("lists, describes, cancels, and reads history", async () => {
const { tableFromArrays, tableToIPC } = await import("apache-arrow");
const eventsTable = tableFromArrays({ state: ["created", "succeeded"] });
const eventsBody = Buffer.from(tableToIPC(eventsTable, "stream"));
const queryEventsPayloads: Record<string, unknown>[] = [];
await withMockDatabase(
(req, res) => {
let body = "";
req.on("data", (chunk) => {
body += chunk;
});
req.on("end", () => {
const payload = body.length > 0 ? JSON.parse(body) : {};
if (req.url === "/v1/jobs/list") {
if (payload["page_token"] === undefined) {
res
.writeHead(200, { "Content-Type": "application/json" })
.end(
'{"jobs": [{"job_id": "job-1", "table": "t1", ' +
'"job_type": "create_index", "state": "in_progress", ' +
'"created_at_millis": 1000, ' +
'"progress": {"rows_planned": 4, "rows_computed": 2}, ' +
'"phase": "running", "paused": false}], "page_token": "next"}',
);
} else {
res
.writeHead(200, { "Content-Type": "application/json" })
.end(
'{"jobs": [{"job_id": "job-2", "table": "t2", ' +
'"job_type": "create_index", "state": "succeeded", ' +
'"created_at_millis": 2000}]}',
);
}
} else if (req.url === "/v1/jobs/describe") {
if (payload["job_id"] === "job-2") {
res
.writeHead(200, { "Content-Type": "application/json" })
.end(
'{"job_id": "job-2", "job_type": "refresh_column", ' +
'"job_state": "DONE", "creation_ms": 2000, ' +
'"result": {"rows_assigned": 1000000}}',
);
return;
}
if (payload["job_id"] !== "job-1") {
res.writeHead(404).end("no such job");
return;
}
res
.writeHead(200, { "Content-Type": "application/json" })
.end(
'{"job_id": "job-1", "job_type": "create_index", ' +
'"job_state": "FAILED", "creation_ms": 1000, ' +
'"progress": {"rows_planned": 4, "rows_computed": 2, ' +
'"vendor_extension": "kept"}, ' +
'"phase": "running", ' +
'"spec": {"column": "vec"}, "failure": {"phase": "execute", ' +
'"message": "worker died", "retryable": true}}',
);
} else if (req.url === "/v1/jobs/cancel") {
if (payload["job_id"] !== "job-1") {
res.writeHead(404).end("no such job");
return;
}
res
.writeHead(200, { "Content-Type": "application/json" })
.end('{"job_id": "job-1"}');
} else if (req.url === "/v1/jobs/pause") {
if (payload["job_id"] !== "job-1") {
res.writeHead(404).end("no such job");
return;
}
res
.writeHead(200, { "Content-Type": "application/json" })
.end('{"job_id": "job-1", "paused": true}');
} else if (req.url === "/v1/jobs/resume") {
if (payload["job_id"] !== "job-1") {
res.writeHead(404).end("no such job");
return;
}
res
.writeHead(200, { "Content-Type": "application/json" })
.end(
'{"job_id": "job-1", "resumed": false, "still_pausing": true}',
);
} else if (req.url === "/v1/jobs/query_events") {
queryEventsPayloads.push(payload);
res
.writeHead(200, {
"Content-Type": "application/vnd.apache.arrow.stream",
})
.end(eventsBody);
} else {
res.writeHead(404).end();
}
});
},
async (db) => {
const jobs = await collect(db.listJobs());
expect(jobs.map((job) => job.jobId)).toEqual(["job-1", "job-2"]);
expect(jobs[0].state).toEqual("running");
expect(jobs[1].state).toEqual("finished");
expect(jobs[0].progress).toEqual({
// biome-ignore lint/style/useNamingConvention: server wire format
job_type: "create_index",
state: "running",
// biome-ignore lint/style/useNamingConvention: server wire format
creation_ms: 1000,
paused: false,
phase: "running",
// biome-ignore lint/style/useNamingConvention: server wire format
rows_planned: 4,
// biome-ignore lint/style/useNamingConvention: server wire format
rows_computed: 2,
});
expect(await db.cancelJob("job-1")).toBe(true);
expect(await db.cancelJob("missing")).toBe(false);
expect(await db.pauseJob("job-1")).toEqual("pausing");
expect(await db.resumeJob("job-1")).toEqual("still_pausing");
// Opening a job hands back a populated handle; a missing one rejects.
await expect(db.openJob("missing")).rejects.toThrow("not found");
const finished = await db.openJob("job-2");
expect(finished.state).toEqual("finished");
expect(finished.result).toEqual({
// biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
rows_assigned: 1000000,
});
const job = await db.openJob("job-1");
expect(job.id).toEqual("job-1");
// openJob already populated the handle; refresh() re-reads it.
expect(job.state).toEqual("failed");
await job.refresh();
expect(job.state).toEqual("failed");
expect(job.jobType).toEqual("create_index");
expect(job.creationMs).toEqual(1000);
expect(job.spec).toEqual({ column: "vec" });
expect(job.result).toBeNull();
expect(job.failure?.message).toEqual("worker died");
expect(await job.progress()).toEqual({
// biome-ignore lint/style/useNamingConvention: server wire format
job_type: "create_index",
state: "failed",
// biome-ignore lint/style/useNamingConvention: server wire format
creation_ms: 1000,
paused: false,
phase: "running",
// biome-ignore lint/style/useNamingConvention: server wire format
rows_planned: 4,
// biome-ignore lint/style/useNamingConvention: server wire format
rows_computed: 2,
// biome-ignore lint/style/useNamingConvention: server wire format
vendor_extension: "kept",
});
// The handle reaches its own events, supplying its job id.
const jobEvents = await job.events({
limit: 500,
filter: "state = 'claim_complete'",
});
expect(jobEvents.numRows).toEqual(2);
expect(queryEventsPayloads.pop()).toEqual({
// biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
job_id: "job-1",
limit: 500,
filter: "state = 'claim_complete'",
});
// Printing lays every known field out on its own line, with the JSON
// payloads indented rather than crammed onto one line.
expect(`${job}`).toEqual(
[
"Job(",
' id="job-1",',
' state="failed",',
' jobType="create_index",',
" creationMs=1000,",
" spec={",
' "column": "vec"',
" },",
" failure={",
' "phase": "execute",',
' "message": "worker died",',
' "retryable": true',
" },",
")",
].join("\n"),
);
expect(await job.status()).toEqual("failed");
await expect(job.wait()).rejects.toThrow("worker died");
},
);
});
it("observes structured progress through the existing wait poller", async () => {
const now = Date.now();
const unknownFleet = {
desired: 2,
launched: 1,
// biome-ignore lint/style/useNamingConvention: server wire format
pending_workers: 1,
ready: 0,
// biome-ignore lint/style/useNamingConvention: server wire format
requested_gpus: 1,
// biome-ignore lint/style/useNamingConvention: server wire format
ready_gpus: 0,
// biome-ignore lint/style/useNamingConvention: server wire format
resource_classes: ["a10g"],
// biome-ignore lint/style/useNamingConvention: server wire format
first_launched_at_millis: now - 4000,
};
const knownFleet = {
...unknownFleet,
// biome-ignore lint/style/useNamingConvention: server wire format
warm_reused: true,
// biome-ignore lint/style/useNamingConvention: server wire format
wait_reason: "Job queued, waiting for GPU capacity in class 'a10g'",
};
const progress = (
rowsComputed: number,
rowsRemaining: number,
sampleOffset: number,
workerFleet: typeof knownFleet | typeof unknownFleet,
) =>
JSON.stringify({
// biome-ignore lint/style/useNamingConvention: server wire format
rows_planned: 100,
// biome-ignore lint/style/useNamingConvention: server wire format
rows_computed: rowsComputed,
// biome-ignore lint/style/useNamingConvention: server wire format
rows_skipped: 0,
// biome-ignore lint/style/useNamingConvention: server wire format
rows_remaining: rowsRemaining,
// biome-ignore lint/style/useNamingConvention: server wire format
fragments_planned: 4,
// biome-ignore lint/style/useNamingConvention: server wire format
execution_epoch: 7,
// biome-ignore lint/style/useNamingConvention: server wire format
sample_at_millis: now - sampleOffset,
// biome-ignore lint/style/useNamingConvention: server wire format
worker_fleet: workerFleet,
// biome-ignore lint/style/useNamingConvention: server wire format
queue_reason: "Waiting for Function worker capacity",
});
const descriptions = [
`{"job_id":"job-wait","job_type":"refresh_column","job_state":"IN_PROGRESS","creation_ms":1000,"queue_reason":"Waiting for Function worker capacity","progress":${progress(20, 80, 3000, unknownFleet)}}`,
`{"job_id":"job-wait","job_type":"refresh_column","job_state":"IN_PROGRESS","creation_ms":1000,"queue_reason":"Waiting for Function worker capacity","progress":${progress(20, 80, 2000, knownFleet)}}`,
`{"job_id":"job-wait","job_type":"refresh_column","job_state":"IN_PROGRESS","creation_ms":1000,"queue_reason":"Waiting for Function worker capacity","progress":${progress(40, 60, 1000, unknownFleet)}}`,
`{"job_id":"job-wait","job_type":"refresh_column","job_state":"DONE","creation_ms":1000,"result":{},"progress":${progress(60, 0, 0, unknownFleet)}}`,
];
let describeCount = 0;
await withMockDatabase(
(req, res) => {
if (req.url === "/v1/jobs/describe") {
describeCount++;
const description = descriptions.shift();
if (description === undefined) {
res.writeHead(500).end("unexpected describe");
return;
}
res
.writeHead(200, { "Content-Type": "application/json" })
.end(description);
return;
}
res.writeHead(404).end();
},
async (db) => {
const job = await db.openJob("job-wait");
const first = await job.progress();
expect(first).toMatchObject({
state: "running",
// biome-ignore lint/style/useNamingConvention: server wire format
rows_computed: 20,
// biome-ignore lint/style/useNamingConvention: server wire format
rows_remaining: 80,
});
expect(first?.worker_fleet).toMatchObject(knownFleet);
expect(
(first?.worker_fleet as Record<string, unknown> | null | undefined)
?.warm_reused,
).toBe(true);
expect(first?.queue_reason).toBe(
"Waiting for Function worker capacity",
);
expect(first).not.toHaveProperty("estimated_remaining_time_millis");
const observed: JobProgress[] = [];
await job.wait((progress) => observed.push(progress));
expect(observed).toHaveLength(2);
expect(observed[0]).toMatchObject({
state: "running",
// biome-ignore lint/style/useNamingConvention: server wire format
rows_computed: 40,
// biome-ignore lint/style/useNamingConvention: server wire format
estimated_remaining_time_millis: 3000,
});
expect(observed[0].worker_fleet).toEqual(unknownFleet);
expect(observed[0].worker_fleet).not.toHaveProperty("warm_reused");
expect(observed[0].queue_reason).toBe(
"Waiting for Function worker capacity",
);
expect(observed[1]).toMatchObject({
state: "finished",
// biome-ignore lint/style/useNamingConvention: server wire format
rows_remaining: 0,
// biome-ignore lint/style/useNamingConvention: server wire format
estimated_remaining_time_millis: 0,
});
},
);
expect(describeCount).toBe(4);
});
it("does not derive ETA across a zero-rate, epoch, or pause boundary", async () => {
const now = Date.now();
const descriptions = [
`{"job_id":"job-eta","job_type":"refresh_column","job_state":"IN_PROGRESS","creation_ms":1000,"progress":{"rows_planned":100,"rows_computed":20,"rows_skipped":0,"rows_remaining":80,"fragments_planned":4,"execution_epoch":1,"sample_at_millis":${now - 5000}}}`,
`{"job_id":"job-eta","job_type":"refresh_column","job_state":"IN_PROGRESS","creation_ms":1000,"progress":{"rows_planned":100,"rows_computed":20,"rows_skipped":0,"rows_remaining":80,"fragments_planned":4,"execution_epoch":1,"sample_at_millis":${now - 4000}}}`,
`{"job_id":"job-eta","job_type":"refresh_column","job_state":"IN_PROGRESS","creation_ms":1000,"progress":{"rows_planned":100,"rows_computed":40,"rows_skipped":0,"rows_remaining":60,"fragments_planned":4,"execution_epoch":2,"sample_at_millis":${now - 3000}}}`,
`{"job_id":"job-eta","job_type":"refresh_column","job_state":"IN_PROGRESS","creation_ms":1000,"phase":"initializing","progress":{"rows_planned":100,"rows_computed":60,"rows_skipped":0,"rows_remaining":40,"fragments_planned":4,"execution_epoch":2,"sample_at_millis":${now - 2000}}}`,
`{"job_id":"job-eta","job_type":"refresh_column","job_state":"IN_PROGRESS","creation_ms":1000,"paused_at_millis":5000,"progress":{"rows_planned":100,"rows_computed":60,"rows_skipped":0,"rows_remaining":40,"fragments_planned":4,"execution_epoch":2,"sample_at_millis":${now - 1500}}}`,
`{"job_id":"job-eta","job_type":"refresh_column","job_state":"IN_PROGRESS","creation_ms":1000,"progress":{"rows_planned":100,"rows_computed":80,"rows_skipped":0,"rows_remaining":20,"fragments_planned":4,"execution_epoch":2,"sample_at_millis":${now - 1000}}}`,
];
await withMockDatabase(
(req, res) => {
if (req.url === "/v1/jobs/describe") {
const description = descriptions.shift();
if (description === undefined) {
res.writeHead(500).end("unexpected describe");
return;
}
res
.writeHead(200, { "Content-Type": "application/json" })
.end(description);
return;
}
res.writeHead(404).end();
},
async (db) => {
const job = await db.openJob("job-eta");
for (let i = 0; i < 5; i++) {
const progress = await job.progress();
expect(progress).not.toHaveProperty(
"estimated_remaining_time_millis",
);
}
},
);
});
it("keeps a thrown progress observer from escaping wait", async () => {
const descriptions = [
'{"job_id":"job-throw","job_type":"refresh_column","job_state":"IN_PROGRESS","creation_ms":1000,"progress":{"rows_planned":4,"rows_computed":2}}',
'{"job_id":"job-throw","job_type":"refresh_column","job_state":"DONE","creation_ms":1000,"result":{}}',
];
await withMockDatabase(
(req, res) => {
if (req.url === "/v1/jobs/describe") {
const description = descriptions.shift();
if (description === undefined) {
res.writeHead(500).end("unexpected describe");
return;
}
res
.writeHead(200, { "Content-Type": "application/json" })
.end(description);
return;
}
res.writeHead(404).end();
},
async (db) => {
const job = await db.openJob("job-throw");
const warn = jest
.spyOn(console, "warn")
.mockImplementation(() => undefined);
try {
await expect(
job.wait(() => {
throw new Error("observer failed");
}),
).resolves.toBeUndefined();
expect(warn).toHaveBeenCalled();
} finally {
warn.mockRestore();
}
},
);
});
it("leaves numDeletedRows absent when the server omits it", async () => {
// A server that predates num_deleted_rows says nothing about deleted rows
const statsReply =
'{"total_bytes":1,"num_rows":3,"num_indices":0,"fragment_stats":' +
'{"num_fragments":1,"num_small_fragments":0,' +
'"lengths":{"min":3,"max":3,"mean":3,"p25":3,"p50":3,"p75":3,"p99":3}}}';
await withMockDatabase(
(req, res) => {
const path = req.url ?? "";
const body = path.endsWith("/describe/")
? JSON.stringify({ name: "t", version: 1, schema: { fields: [] } })
: statsReply;
res.writeHead(200, { "Content-Type": "application/json" }).end(body);
},
async (db) => {
const stats = await (await db.openTable("t")).stats();
expect("numDeletedRows" in stats).toBe(false);
expect(stats.numDeletedRows).toBeUndefined();
},
);
});
});
async function collect<T>(items: AsyncIterable<T>): Promise<T[]> {
const result: T[] = [];
for await (const item of items) result.push(item);
return result;
}
describe("lazy resource listings", () => {
for (const kind of ["jobs"] as const) {
const listing = (
db: Connection,
options: { pageToken?: string; pageLimit?: number } = {},
) => {
return db.listJobs(options);
};
const page = (names: string[], token?: string) => {
const items =
kind === "jobs"
? names.map((name) => ({
// biome-ignore lint/style/useNamingConvention: server wire format
job_id: name,
table: "t",
// biome-ignore lint/style/useNamingConvention: server wire format
job_type: "create_index",
state: "in_progress",
// biome-ignore lint/style/useNamingConvention: server wire format
created_at_millis: 1,
}))
: names;
return {
[kind === "jobs" ? "jobs" : "views"]: items,
// biome-ignore lint/style/useNamingConvention: server wire format
page_token: token,
};
};
it(`${kind} fetches lazily, skips empty pages, and resumes`, async () => {
const requests: { url: string; body: Record<string, unknown> }[] = [];
const responses = [
page(["a", "b"], "empty"),
page([], "last"),
page(["c", "d"], ""),
];
await withMockDatabase(
async (req, res) => {
const chunks: Buffer[] = [];
for await (const chunk of req) chunks.push(Buffer.from(chunk));
const body = Buffer.concat(chunks).toString();
requests.push({
url: req.url ?? "",
body: body ? JSON.parse(body) : {},
});
res
.writeHead(200, { "content-type": "application/json" })
.end(JSON.stringify(responses.shift()));
},
async (db) => {
const items = listing(db, { pageToken: "start/token", pageLimit: 2 });
expect(requests).toHaveLength(0);
expect(items.pageToken()).toBe("start/token");
expect(items.numPageResults()).toBe(0);
expect((await items.next()).done).toBe(false);
expect(items.numPageResults()).toBe(1);
expect(items.pageToken()).toBe("empty");
await items.next();
expect(requests).toHaveLength(1);
const resumed = listing(db, {
pageToken: items.pageToken(),
pageLimit: 2,
});
await resumed.next();
expect(resumed.numPageResults()).toBe(1);
expect(resumed.pageToken()).toBeUndefined();
expect(requests).toHaveLength(3);
await resumed.next();
expect((await resumed.next()).done).toBe(true);
expect((await resumed.next()).done).toBe(true);
for (const [i, request] of requests.entries()) {
const token = ["start/token", "empty", "last"][i];
const url = new URL(request.url, "http://localhost");
if (kind === "jobs") {
expect(url.pathname).toBe("/v1/jobs/list");
expect(request.body).toEqual({
// biome-ignore lint/style/useNamingConvention: server wire format
page_token: token,
limit: 2,
});
} else {
expect(url.pathname).toBe("/v1/namespace/team/view/list");
expect(url.searchParams.get("page_token")).toBe(token);
expect(url.searchParams.get("limit")).toBe("2");
}
}
},
);
});
it(`${kind} retains failed tokens and serializes concurrent advances`, async () => {
let requests = 0;
await withMockDatabase(
(_req, res) => {
requests += 1;
res
.writeHead(requests === 1 ? 401 : 200, {
"content-type": "application/json",
})
.end(JSON.stringify(requests === 1 ? {} : page(["a", "b"])));
},
async (db) => {
const failed = listing(db, { pageToken: "retry" });
await expect(failed.next()).rejects.toThrow();
expect(failed.pageToken()).toBe("retry");
expect((await failed.next()).done).toBe(true);
expect(requests).toBe(1);
const resumed = listing(db, { pageToken: failed.pageToken() });
const results = await Promise.all([
resumed.next(),
resumed.next(),
resumed.next(),
]);
expect(results.filter((result) => result.done)).toHaveLength(1);
expect(requests).toBe(2);
for (const limit of [
0,
-1,
1.5,
Number.NaN,
Number.POSITIVE_INFINITY,
2147483648,
]) {
expect(() => listing(db, { pageLimit: limit })).toThrow("limit");
}
expect(requests).toBe(2);
},
);
});
}
});