mirror of
https://github.com/openclaw/openclaw.git
synced 2026-08-27 21:07:01 -06:00
Merge pull request #118204 from openclaw/fix-openai-realtime-transcript-bounds-20260802
* commit '15195713985f5b069f53bbb769a9dc621ed4c7e9': test(openai): isolate terminal history bounds test(openai): cover terminal history saturation fix(openai): preserve terminal history precedence test(openai): cover tombstone eviction ordering fix(openai): retain active predecessor satisfaction test(openai): cover rejected terminal failures fix(openai): preserve terminal error precedence test(openai): cover pre-commit terminal events fix(openai): tombstone pre-commit terminal events test(openai): pin first transcript terminal outcome fix(openai): ignore post-terminal transcript events test(openai): cover realtime transcription bounds fix(openai): bound realtime transcription state
This commit is contained in:
Vincent Koc
@@ -0,0 +1,227 @@
|
||||
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
|
||||
import { buildOpenAIRealtimeTranscriptionProvider } from "./realtime-transcription-provider.js";
|
||||
|
||||
const { FakeWebSocket } = vi.hoisted(() => {
|
||||
type Listener = (...args: unknown[]) => void;
|
||||
|
||||
class MockWebSocket {
|
||||
static readonly OPEN = 1;
|
||||
static readonly CLOSED = 3;
|
||||
static instances: MockWebSocket[] = [];
|
||||
|
||||
readonly listeners = new Map<string, Listener[]>();
|
||||
readyState = 0;
|
||||
closed = false;
|
||||
|
||||
constructor() {
|
||||
MockWebSocket.instances.push(this);
|
||||
}
|
||||
|
||||
on(event: string, listener: Listener): this {
|
||||
const listeners = this.listeners.get(event) ?? [];
|
||||
listeners.push(listener);
|
||||
this.listeners.set(event, listeners);
|
||||
return this;
|
||||
}
|
||||
|
||||
emit(event: string, ...args: unknown[]): void {
|
||||
for (const listener of this.listeners.get(event) ?? []) {
|
||||
listener(...args);
|
||||
}
|
||||
}
|
||||
|
||||
send(): void {}
|
||||
|
||||
close(code?: number, reason?: string): void {
|
||||
this.closed = true;
|
||||
this.readyState = MockWebSocket.CLOSED;
|
||||
this.emit("close", code ?? 1000, Buffer.from(reason ?? ""));
|
||||
}
|
||||
|
||||
terminate(): void {
|
||||
this.closed = true;
|
||||
this.readyState = MockWebSocket.CLOSED;
|
||||
}
|
||||
}
|
||||
|
||||
return { FakeWebSocket: MockWebSocket };
|
||||
});
|
||||
|
||||
vi.mock("ws", () => ({
|
||||
default: FakeWebSocket,
|
||||
}));
|
||||
|
||||
type FakeWebSocketInstance = InstanceType<typeof FakeWebSocket>;
|
||||
|
||||
async function waitForFakeSocket(index = 0): Promise<FakeWebSocketInstance> {
|
||||
let socket: FakeWebSocketInstance | undefined;
|
||||
await vi.waitFor(() => {
|
||||
socket = FakeWebSocket.instances[index];
|
||||
if (!socket) {
|
||||
throw new Error("expected session to create a websocket");
|
||||
}
|
||||
});
|
||||
if (!socket) {
|
||||
throw new Error("expected session to create a websocket");
|
||||
}
|
||||
return socket;
|
||||
}
|
||||
|
||||
function emitJson(socket: FakeWebSocketInstance, event: Record<string, unknown>): void {
|
||||
socket.emit("message", Buffer.from(JSON.stringify(event)));
|
||||
}
|
||||
|
||||
async function connectFakeSession(
|
||||
session: { connect(): Promise<void> },
|
||||
socketIndex = 0,
|
||||
): Promise<FakeWebSocketInstance> {
|
||||
const connecting = session.connect();
|
||||
const socket = await waitForFakeSocket(socketIndex);
|
||||
socket.readyState = FakeWebSocket.OPEN;
|
||||
socket.emit("open");
|
||||
emitJson(socket, { type: "session.updated" });
|
||||
await connecting;
|
||||
return socket;
|
||||
}
|
||||
|
||||
describe("OpenAI realtime transcription terminal history bounds", () => {
|
||||
beforeEach(() => {
|
||||
FakeWebSocket.instances = [];
|
||||
vi.stubEnv("OPENAI_API_KEY", "");
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
vi.unstubAllEnvs();
|
||||
});
|
||||
|
||||
it("does not re-admit a terminal item after the settled frontier fills", async () => {
|
||||
const onError = vi.fn();
|
||||
const onPartial = vi.fn();
|
||||
const transcripts: string[] = [];
|
||||
const provider = buildOpenAIRealtimeTranscriptionProvider();
|
||||
const session = provider.createSession({
|
||||
providerConfig: { apiKey: "sk-test" }, // pragma: allowlist secret
|
||||
onError,
|
||||
onPartial,
|
||||
onTranscript: (transcript) => transcripts.push(transcript),
|
||||
});
|
||||
const socket = await connectFakeSession(session);
|
||||
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "oldest",
|
||||
transcript: "first",
|
||||
});
|
||||
for (let index = 0; index < 4095; index += 1) {
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: `settled-${index}`,
|
||||
transcript: "",
|
||||
});
|
||||
}
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "oldest",
|
||||
transcript: "duplicate",
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.delta",
|
||||
item_id: "oldest",
|
||||
delta: "late partial",
|
||||
});
|
||||
|
||||
expect(transcripts).toEqual(["first"]);
|
||||
expect(onPartial).not.toHaveBeenCalled();
|
||||
expect(onError).not.toHaveBeenCalled();
|
||||
expect(session.isConnected()).toBe(true);
|
||||
session.close();
|
||||
});
|
||||
|
||||
it("fails visibly instead of evicting terminal item history", async () => {
|
||||
const onError = vi.fn();
|
||||
const onTranscript = vi.fn();
|
||||
const provider = buildOpenAIRealtimeTranscriptionProvider();
|
||||
const session = provider.createSession({
|
||||
providerConfig: { apiKey: "sk-test" }, // pragma: allowlist secret
|
||||
onError,
|
||||
onTranscript,
|
||||
});
|
||||
const socket = await connectFakeSession(session);
|
||||
|
||||
for (let index = 0; index < 4096; index += 1) {
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: `settled-${index}`,
|
||||
transcript: "",
|
||||
});
|
||||
}
|
||||
emitJson(socket, {
|
||||
type: "input_audio_buffer.committed",
|
||||
item_id: "overflow-item",
|
||||
previous_item_id: null,
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.failed",
|
||||
item_id: "overflow-item",
|
||||
error: { message: "provider failure" },
|
||||
});
|
||||
|
||||
expect(onError).toHaveBeenCalledExactlyOnceWith(
|
||||
expect.objectContaining({
|
||||
message: "OpenAI realtime transcription exceeded the terminal item history limit",
|
||||
}),
|
||||
);
|
||||
expect(onTranscript).not.toHaveBeenCalled();
|
||||
expect(session.isConnected()).toBe(false);
|
||||
|
||||
const reconnecting = session.connect();
|
||||
const replacementSocket = await waitForFakeSocket(1);
|
||||
replacementSocket.readyState = FakeWebSocket.OPEN;
|
||||
replacementSocket.emit("open");
|
||||
emitJson(replacementSocket, { type: "session.updated" });
|
||||
await reconnecting;
|
||||
emitJson(replacementSocket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "replacement-item",
|
||||
transcript: "replacement transcript",
|
||||
});
|
||||
|
||||
expect(onTranscript).toHaveBeenCalledExactlyOnceWith("replacement transcript");
|
||||
expect(onError).toHaveBeenCalledTimes(1);
|
||||
session.close();
|
||||
});
|
||||
|
||||
it("fails visibly when terminal item identities exceed 256 KiB", async () => {
|
||||
const onError = vi.fn();
|
||||
const onTranscript = vi.fn();
|
||||
const provider = buildOpenAIRealtimeTranscriptionProvider();
|
||||
const session = provider.createSession({
|
||||
providerConfig: { apiKey: "sk-test" }, // pragma: allowlist secret
|
||||
onError,
|
||||
onTranscript,
|
||||
});
|
||||
const socket = await connectFakeSession(session);
|
||||
|
||||
for (let index = 0; index < 256; index += 1) {
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: `${index.toString().padStart(4, "0")}${"i".repeat(1020)}`,
|
||||
transcript: "",
|
||||
});
|
||||
}
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "overflow-item",
|
||||
transcript: "must not emit",
|
||||
});
|
||||
|
||||
expect(onError).toHaveBeenCalledExactlyOnceWith(
|
||||
expect.objectContaining({
|
||||
message: "OpenAI realtime transcription exceeded the terminal item history limit",
|
||||
}),
|
||||
);
|
||||
expect(onTranscript).not.toHaveBeenCalled();
|
||||
expect(session.isConnected()).toBe(false);
|
||||
session.close();
|
||||
});
|
||||
});
|
||||
@@ -45,6 +45,11 @@ const { FakeWebSocket, providerAuthMocks, ssrfMocks } = vi.hoisted(() => {
|
||||
this.readyState = MockWebSocket.CLOSED;
|
||||
this.emit("close", code ?? 1000, Buffer.from(reason ?? ""));
|
||||
}
|
||||
|
||||
terminate(): void {
|
||||
this.closed = true;
|
||||
this.readyState = MockWebSocket.CLOSED;
|
||||
}
|
||||
}
|
||||
|
||||
return {
|
||||
@@ -83,10 +88,10 @@ function parseSent(socket: FakeWebSocketInstance): SentRealtimeEvent[] {
|
||||
return socket.sent.map((payload) => JSON.parse(payload) as SentRealtimeEvent);
|
||||
}
|
||||
|
||||
async function waitForFakeSocket(): Promise<FakeWebSocketInstance> {
|
||||
async function waitForFakeSocket(index = 0): Promise<FakeWebSocketInstance> {
|
||||
let socket: FakeWebSocketInstance | undefined;
|
||||
await vi.waitFor(() => {
|
||||
socket = FakeWebSocket.instances[0];
|
||||
socket = FakeWebSocket.instances[index];
|
||||
if (!socket) {
|
||||
throw new Error("expected session to create a websocket");
|
||||
}
|
||||
@@ -97,6 +102,23 @@ async function waitForFakeSocket(): Promise<FakeWebSocketInstance> {
|
||||
return socket;
|
||||
}
|
||||
|
||||
function emitJson(socket: FakeWebSocketInstance, event: Record<string, unknown>): void {
|
||||
socket.emit("message", Buffer.from(JSON.stringify(event)));
|
||||
}
|
||||
|
||||
async function connectFakeSession(
|
||||
session: { connect(): Promise<void> },
|
||||
socketIndex = 0,
|
||||
): Promise<FakeWebSocketInstance> {
|
||||
const connecting = session.connect();
|
||||
const socket = await waitForFakeSocket(socketIndex);
|
||||
socket.readyState = FakeWebSocket.OPEN;
|
||||
socket.emit("open");
|
||||
emitJson(socket, { type: "session.updated" });
|
||||
await connecting;
|
||||
return socket;
|
||||
}
|
||||
|
||||
function mockCallArg(mock: { mock: { calls: unknown[][] } }, index = 0): Record<string, unknown> {
|
||||
const call = mock.mock.calls[index];
|
||||
if (!call) {
|
||||
@@ -565,4 +587,493 @@ describe("buildOpenAIRealtimeTranscriptionProvider", () => {
|
||||
expect(transcripts).toEqual(["second final"]);
|
||||
session.close();
|
||||
});
|
||||
|
||||
it("releases settled turns from the unresolved item budget", async () => {
|
||||
const transcripts: string[] = [];
|
||||
const onError = vi.fn();
|
||||
const provider = buildOpenAIRealtimeTranscriptionProvider();
|
||||
const session = provider.createSession({
|
||||
providerConfig: { apiKey: "sk-test" }, // pragma: allowlist secret
|
||||
onError,
|
||||
onTranscript: (transcript) => transcripts.push(transcript),
|
||||
});
|
||||
const socket = await connectFakeSession(session);
|
||||
|
||||
for (let index = 0; index < 128; index += 1) {
|
||||
const itemId = `item-${index}`;
|
||||
emitJson(socket, {
|
||||
type: "input_audio_buffer.committed",
|
||||
item_id: itemId,
|
||||
previous_item_id: index === 0 ? null : `item-${index - 1}`,
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: itemId,
|
||||
transcript: `turn-${index}`,
|
||||
});
|
||||
}
|
||||
emitJson(socket, {
|
||||
type: "input_audio_buffer.committed",
|
||||
item_id: "item-129",
|
||||
previous_item_id: "item-128",
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "item-129",
|
||||
transcript: "turn-129",
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "input_audio_buffer.committed",
|
||||
item_id: "item-128",
|
||||
previous_item_id: "item-127",
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "item-128",
|
||||
transcript: "turn-128",
|
||||
});
|
||||
|
||||
expect(transcripts).toHaveLength(130);
|
||||
expect(transcripts.slice(-2)).toEqual(["turn-128", "turn-129"]);
|
||||
expect(onError).not.toHaveBeenCalled();
|
||||
expect(session.isConnected()).toBe(true);
|
||||
session.close();
|
||||
});
|
||||
|
||||
it("fails once when unresolved item correlation exceeds its session bound", async () => {
|
||||
const onError = vi.fn();
|
||||
const onTranscript = vi.fn();
|
||||
const provider = buildOpenAIRealtimeTranscriptionProvider();
|
||||
const session = provider.createSession({
|
||||
providerConfig: { apiKey: "sk-test" }, // pragma: allowlist secret
|
||||
onError,
|
||||
onTranscript,
|
||||
});
|
||||
const socket = await connectFakeSession(session);
|
||||
|
||||
for (let index = 0; index < 64; index += 1) {
|
||||
emitJson(socket, {
|
||||
type: "input_audio_buffer.committed",
|
||||
item_id: `item-${index}`,
|
||||
previous_item_id: "missing-predecessor",
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: `item-${index}`,
|
||||
transcript: `turn-${index}`,
|
||||
});
|
||||
}
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.failed",
|
||||
item_id: "overflow-item",
|
||||
error: { message: "provider failure" },
|
||||
});
|
||||
|
||||
expect(onError).toHaveBeenCalledExactlyOnceWith(
|
||||
expect.objectContaining({
|
||||
message: "OpenAI realtime transcription exceeded the 64 unresolved item limit",
|
||||
}),
|
||||
);
|
||||
expect(onTranscript).not.toHaveBeenCalled();
|
||||
expect(session.isConnected()).toBe(false);
|
||||
|
||||
const reconnecting = session.connect();
|
||||
const replacementSocket = await waitForFakeSocket(1);
|
||||
replacementSocket.readyState = FakeWebSocket.OPEN;
|
||||
replacementSocket.emit("open");
|
||||
emitJson(replacementSocket, { type: "session.updated" });
|
||||
await reconnecting;
|
||||
emitJson(replacementSocket, {
|
||||
type: "input_audio_buffer.committed",
|
||||
item_id: "replacement-item",
|
||||
previous_item_id: null,
|
||||
});
|
||||
emitJson(replacementSocket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "replacement-item",
|
||||
transcript: "replacement transcript",
|
||||
});
|
||||
|
||||
expect(onTranscript).toHaveBeenCalledExactlyOnceWith("replacement transcript");
|
||||
expect(onError).toHaveBeenCalledTimes(1);
|
||||
session.close();
|
||||
session.close();
|
||||
});
|
||||
|
||||
it("fails once when aggregate in-progress transcript text exceeds 256 KiB", async () => {
|
||||
const onError = vi.fn();
|
||||
const onPartial = vi.fn();
|
||||
const onTranscript = vi.fn();
|
||||
const provider = buildOpenAIRealtimeTranscriptionProvider();
|
||||
const session = provider.createSession({
|
||||
providerConfig: { apiKey: "sk-test" }, // pragma: allowlist secret
|
||||
onError,
|
||||
onPartial,
|
||||
onTranscript,
|
||||
});
|
||||
const socket = await connectFakeSession(session);
|
||||
const exactLimit = "🙂".repeat((256 * 1024) / 4);
|
||||
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.delta",
|
||||
item_id: "item-1",
|
||||
delta: exactLimit,
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.delta",
|
||||
item_id: "item-1",
|
||||
delta: "x",
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "item-1",
|
||||
transcript: "late transcript",
|
||||
});
|
||||
|
||||
expect(onPartial).toHaveBeenCalledExactlyOnceWith(exactLimit);
|
||||
expect(onError).toHaveBeenCalledExactlyOnceWith(
|
||||
expect.objectContaining({
|
||||
message: "OpenAI realtime transcription exceeded the 256 KiB retained transcript limit",
|
||||
}),
|
||||
);
|
||||
expect(onTranscript).not.toHaveBeenCalled();
|
||||
expect(session.isConnected()).toBe(false);
|
||||
session.close();
|
||||
});
|
||||
|
||||
it("accounts for UTF-8 surrogate pairs split across delta frames", async () => {
|
||||
const onError = vi.fn();
|
||||
const onPartial = vi.fn();
|
||||
const provider = buildOpenAIRealtimeTranscriptionProvider();
|
||||
const session = provider.createSession({
|
||||
providerConfig: { apiKey: "sk-test" }, // pragma: allowlist secret
|
||||
onError,
|
||||
onPartial,
|
||||
});
|
||||
const socket = await connectFakeSession(session);
|
||||
const prefix = "x".repeat(256 * 1024 - 4);
|
||||
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.delta",
|
||||
item_id: "item-1",
|
||||
delta: prefix,
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.delta",
|
||||
item_id: "item-1",
|
||||
delta: "\ud83d",
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.delta",
|
||||
item_id: "item-1",
|
||||
delta: "\ude42",
|
||||
});
|
||||
|
||||
expect(onPartial).toHaveBeenLastCalledWith(`${prefix}🙂`);
|
||||
expect(onError).not.toHaveBeenCalled();
|
||||
expect(session.isConnected()).toBe(true);
|
||||
session.close();
|
||||
});
|
||||
|
||||
it("ignores duplicate completion events without double-charging retained text", async () => {
|
||||
const onError = vi.fn();
|
||||
const onPartial = vi.fn();
|
||||
const transcripts: string[] = [];
|
||||
const provider = buildOpenAIRealtimeTranscriptionProvider();
|
||||
const session = provider.createSession({
|
||||
providerConfig: { apiKey: "sk-test" }, // pragma: allowlist secret
|
||||
onError,
|
||||
onPartial,
|
||||
onTranscript: (transcript) => transcripts.push(transcript),
|
||||
});
|
||||
const socket = await connectFakeSession(session);
|
||||
const secondTranscript = "x".repeat(192 * 1024);
|
||||
|
||||
emitJson(socket, {
|
||||
type: "input_audio_buffer.committed",
|
||||
item_id: "item-2",
|
||||
previous_item_id: "item-1",
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "item-2",
|
||||
transcript: secondTranscript,
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.delta",
|
||||
item_id: "item-2",
|
||||
delta: "late partial",
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.failed",
|
||||
item_id: "item-2",
|
||||
error: { message: "late failure" },
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "item-2",
|
||||
transcript: secondTranscript,
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "input_audio_buffer.committed",
|
||||
item_id: "item-1",
|
||||
previous_item_id: null,
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "item-1",
|
||||
transcript: "first",
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "item-2",
|
||||
transcript: "late duplicate",
|
||||
});
|
||||
|
||||
expect(transcripts).toEqual(["first", secondTranscript]);
|
||||
expect(onPartial).not.toHaveBeenCalled();
|
||||
expect(onError).not.toHaveBeenCalled();
|
||||
expect(session.isConnected()).toBe(true);
|
||||
|
||||
const reconnecting = session.connect();
|
||||
const replacementSocket = await waitForFakeSocket(1);
|
||||
replacementSocket.readyState = FakeWebSocket.OPEN;
|
||||
replacementSocket.emit("open");
|
||||
emitJson(replacementSocket, { type: "session.updated" });
|
||||
await reconnecting;
|
||||
emitJson(replacementSocket, {
|
||||
type: "input_audio_buffer.committed",
|
||||
item_id: "item-2",
|
||||
previous_item_id: null,
|
||||
});
|
||||
emitJson(replacementSocket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "item-2",
|
||||
transcript: "new session",
|
||||
});
|
||||
|
||||
expect(transcripts).toEqual(["first", secondTranscript, "new session"]);
|
||||
session.close();
|
||||
});
|
||||
|
||||
it("tombstones terminal outcomes received before their commit", async () => {
|
||||
const errors: string[] = [];
|
||||
const partials: string[] = [];
|
||||
const transcripts: string[] = [];
|
||||
const provider = buildOpenAIRealtimeTranscriptionProvider();
|
||||
const session = provider.createSession({
|
||||
providerConfig: { apiKey: "sk-test" }, // pragma: allowlist secret
|
||||
onError: (error) => errors.push(error.message),
|
||||
onPartial: (partial) => partials.push(partial),
|
||||
onTranscript: (transcript) => transcripts.push(transcript),
|
||||
});
|
||||
const socket = await connectFakeSession(session);
|
||||
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "item-completed",
|
||||
transcript: "first",
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "item-completed",
|
||||
transcript: "duplicate",
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.delta",
|
||||
item_id: "item-completed",
|
||||
delta: "late partial",
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.failed",
|
||||
item_id: "item-completed",
|
||||
error: { message: "late failure" },
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "input_audio_buffer.committed",
|
||||
item_id: "item-completed",
|
||||
previous_item_id: null,
|
||||
});
|
||||
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.failed",
|
||||
item_id: "item-failed",
|
||||
error: { message: "first failure" },
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "item-failed",
|
||||
transcript: "late completion",
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.delta",
|
||||
item_id: "item-failed",
|
||||
delta: "late partial",
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.failed",
|
||||
item_id: "item-failed",
|
||||
error: { message: "duplicate failure" },
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "input_audio_buffer.committed",
|
||||
item_id: "item-failed",
|
||||
previous_item_id: null,
|
||||
});
|
||||
|
||||
expect(transcripts).toEqual(["first"]);
|
||||
expect(errors).toEqual(["first failure"]);
|
||||
expect(partials).toEqual([]);
|
||||
expect(session.isConnected()).toBe(true);
|
||||
session.close();
|
||||
});
|
||||
|
||||
it("keeps active predecessor satisfaction as terminal history grows", async () => {
|
||||
const transcripts: string[] = [];
|
||||
const provider = buildOpenAIRealtimeTranscriptionProvider();
|
||||
const session = provider.createSession({
|
||||
providerConfig: { apiKey: "sk-test" }, // pragma: allowlist secret
|
||||
onTranscript: (transcript) => transcripts.push(transcript),
|
||||
});
|
||||
const socket = await connectFakeSession(session);
|
||||
|
||||
emitJson(socket, {
|
||||
type: "input_audio_buffer.committed",
|
||||
item_id: "root",
|
||||
previous_item_id: null,
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "root",
|
||||
transcript: "root transcript",
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "input_audio_buffer.committed",
|
||||
item_id: "waiting",
|
||||
previous_item_id: "root",
|
||||
});
|
||||
for (let index = 0; index < 64; index += 1) {
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: `uncommitted-${index}`,
|
||||
transcript: "",
|
||||
});
|
||||
}
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "waiting",
|
||||
transcript: "waiting transcript",
|
||||
});
|
||||
|
||||
expect(transcripts).toEqual(["root transcript", "waiting transcript"]);
|
||||
expect(session.isConnected()).toBe(true);
|
||||
session.close();
|
||||
});
|
||||
|
||||
it("keeps the first failed terminal outcome when completion arrives late", async () => {
|
||||
const errors: string[] = [];
|
||||
const transcripts: string[] = [];
|
||||
const provider = buildOpenAIRealtimeTranscriptionProvider();
|
||||
const session = provider.createSession({
|
||||
providerConfig: { apiKey: "sk-test" }, // pragma: allowlist secret
|
||||
onError: (error) => errors.push(error.message),
|
||||
onTranscript: (transcript) => transcripts.push(transcript),
|
||||
});
|
||||
const socket = await connectFakeSession(session);
|
||||
|
||||
emitJson(socket, {
|
||||
type: "input_audio_buffer.committed",
|
||||
item_id: "item-2",
|
||||
previous_item_id: "item-1",
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.failed",
|
||||
item_id: "item-2",
|
||||
error: { message: "second failed" },
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "item-2",
|
||||
transcript: "late second",
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "input_audio_buffer.committed",
|
||||
item_id: "item-1",
|
||||
previous_item_id: null,
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "item-1",
|
||||
transcript: "first",
|
||||
});
|
||||
|
||||
expect(errors).toEqual(["second failed"]);
|
||||
expect(transcripts).toEqual(["first"]);
|
||||
expect(session.isConnected()).toBe(true);
|
||||
session.close();
|
||||
});
|
||||
|
||||
it("fails before retaining oversized correlation identities", async () => {
|
||||
const onError = vi.fn();
|
||||
const onTranscript = vi.fn();
|
||||
const provider = buildOpenAIRealtimeTranscriptionProvider();
|
||||
const session = provider.createSession({
|
||||
providerConfig: { apiKey: "sk-test" }, // pragma: allowlist secret
|
||||
onError,
|
||||
onTranscript,
|
||||
});
|
||||
const socket = await connectFakeSession(session);
|
||||
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.failed",
|
||||
item_id: "i".repeat(1025),
|
||||
error: { message: "provider failure" },
|
||||
});
|
||||
|
||||
expect(onError).toHaveBeenCalledExactlyOnceWith(
|
||||
expect.objectContaining({
|
||||
message: "OpenAI realtime transcription exceeded the 1024-byte item identity limit",
|
||||
}),
|
||||
);
|
||||
expect(onTranscript).not.toHaveBeenCalled();
|
||||
expect(session.isConnected()).toBe(false);
|
||||
session.close();
|
||||
});
|
||||
|
||||
it("fails before retaining an oversized completed transcript", async () => {
|
||||
const onError = vi.fn();
|
||||
const onTranscript = vi.fn();
|
||||
const provider = buildOpenAIRealtimeTranscriptionProvider();
|
||||
const session = provider.createSession({
|
||||
providerConfig: { apiKey: "sk-test" }, // pragma: allowlist secret
|
||||
onError,
|
||||
onTranscript,
|
||||
});
|
||||
const socket = await connectFakeSession(session);
|
||||
|
||||
emitJson(socket, {
|
||||
type: "input_audio_buffer.committed",
|
||||
item_id: "item-1",
|
||||
previous_item_id: null,
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "item-1",
|
||||
transcript: "x".repeat(256 * 1024 + 1),
|
||||
});
|
||||
emitJson(socket, {
|
||||
type: "conversation.item.input_audio_transcription.completed",
|
||||
item_id: "item-1",
|
||||
transcript: "late transcript",
|
||||
});
|
||||
|
||||
expect(onError).toHaveBeenCalledExactlyOnceWith(
|
||||
expect.objectContaining({
|
||||
message: "OpenAI realtime transcription exceeded the 256 KiB retained transcript limit",
|
||||
}),
|
||||
);
|
||||
expect(onTranscript).not.toHaveBeenCalled();
|
||||
expect(session.isConnected()).toBe(false);
|
||||
session.close();
|
||||
});
|
||||
});
|
||||
|
||||
@@ -75,11 +75,39 @@ const OPENAI_REALTIME_TRANSCRIPTION_CONNECT_TIMEOUT_MS = 10_000;
|
||||
const OPENAI_REALTIME_TRANSCRIPTION_MAX_RECONNECT_ATTEMPTS = 5;
|
||||
const OPENAI_REALTIME_TRANSCRIPTION_RECONNECT_DELAY_MS = 1000;
|
||||
const OPENAI_REALTIME_TRANSCRIPTION_DEFAULT_MODEL = "gpt-4o-transcribe";
|
||||
const OPENAI_REALTIME_TRANSCRIPTION_MAX_UNRESOLVED_ITEMS = 64;
|
||||
const OPENAI_REALTIME_TRANSCRIPTION_MAX_ITEM_ID_BYTES = 1024;
|
||||
const OPENAI_REALTIME_TRANSCRIPTION_MAX_RETAINED_TRANSCRIPT_BYTES = 256 * 1024;
|
||||
const OPENAI_REALTIME_TRANSCRIPTION_MAX_SETTLED_ITEMS = 4096;
|
||||
const OPENAI_REALTIME_TRANSCRIPTION_MAX_SETTLED_ID_BYTES = 256 * 1024;
|
||||
const OPENAI_REALTIME_TRANSCRIPTION_ITEM_OVERFLOW_MESSAGE =
|
||||
"OpenAI realtime transcription exceeded the 64 unresolved item limit";
|
||||
const OPENAI_REALTIME_TRANSCRIPTION_IDENTITY_OVERFLOW_MESSAGE =
|
||||
"OpenAI realtime transcription exceeded the 1024-byte item identity limit";
|
||||
const OPENAI_REALTIME_TRANSCRIPTION_TEXT_OVERFLOW_MESSAGE =
|
||||
"OpenAI realtime transcription exceeded the 256 KiB retained transcript limit";
|
||||
const OPENAI_REALTIME_TRANSCRIPTION_SETTLED_OVERFLOW_MESSAGE =
|
||||
"OpenAI realtime transcription exceeded the terminal item history limit";
|
||||
const OPENAI_REALTIME_TRANSCRIPTION_API_KEY_REQUIRED =
|
||||
"OpenAI Realtime transcription requires an OpenAI Platform API key";
|
||||
const OPENAI_REALTIME_TRANSCRIPTION_API_KEY_REJECTED =
|
||||
"OpenAI Realtime transcription rejected the selected API key. Update or remove the active OpenAI API-key source";
|
||||
|
||||
function appendedUtf8ByteLength(previous: string, appended: string): number {
|
||||
const appendedBytes = Buffer.byteLength(appended, "utf8");
|
||||
if (!previous || !appended) {
|
||||
return appendedBytes;
|
||||
}
|
||||
const previousCodeUnit = previous.charCodeAt(previous.length - 1);
|
||||
const appendedCodeUnit = appended.charCodeAt(0);
|
||||
const joinsSurrogatePair =
|
||||
previousCodeUnit >= 0xd800 &&
|
||||
previousCodeUnit <= 0xdbff &&
|
||||
appendedCodeUnit >= 0xdc00 &&
|
||||
appendedCodeUnit <= 0xdfff;
|
||||
return joinsSurrogatePair ? appendedBytes - 2 : appendedBytes;
|
||||
}
|
||||
|
||||
function normalizeProviderConfig(
|
||||
config: RealtimeTranscriptionProviderConfig,
|
||||
): OpenAIRealtimeTranscriptionProviderConfig {
|
||||
@@ -172,35 +200,112 @@ async function resolveOpenAIRealtimeTranscriptionAuthorization(
|
||||
function createOpenAIRealtimeTranscriptionSession(
|
||||
config: OpenAIRealtimeTranscriptionSessionConfig,
|
||||
): RealtimeTranscriptionSession {
|
||||
const pendingTranscripts = new Map<string, string>();
|
||||
const pendingTranscripts = new Map<string, { bytes: number; text: string }>();
|
||||
const committedItemIds: string[] = [];
|
||||
const committedItems = new Set<string>();
|
||||
const previousItemIds = new Map<string, string | null | undefined>();
|
||||
const settledItemIds = new Set<string>();
|
||||
const committedItems = new Map<string, string | null | undefined>();
|
||||
const completedTranscripts = new Map<string, string | undefined>();
|
||||
const trackedItemIds = new Set<string>();
|
||||
const settledItemIds = new Set<string>();
|
||||
const unkeyedTranscript = "__openclaw_unkeyed_transcript__";
|
||||
let retainedTranscriptBytes = 0;
|
||||
let settledItemIdBytes = 0;
|
||||
|
||||
const resetTranscriptionState = () => {
|
||||
pendingTranscripts.clear();
|
||||
committedItemIds.length = 0;
|
||||
committedItems.clear();
|
||||
previousItemIds.clear();
|
||||
settledItemIds.clear();
|
||||
completedTranscripts.clear();
|
||||
trackedItemIds.clear();
|
||||
settledItemIds.clear();
|
||||
retainedTranscriptBytes = 0;
|
||||
settledItemIdBytes = 0;
|
||||
};
|
||||
|
||||
const commitItem = (itemId: string, previousItemId: string | null | undefined) => {
|
||||
if (committedItems.has(itemId)) {
|
||||
const failTerminal = (error: Error, transport: RealtimeTranscriptionWebSocketTransport) => {
|
||||
resetTranscriptionState();
|
||||
transport.closeNow();
|
||||
try {
|
||||
config.onError?.(error);
|
||||
} catch {
|
||||
// The provider terminal owns this outcome; observer failures must not
|
||||
// re-enter shared error dispatch or duplicate the terminal callback.
|
||||
}
|
||||
};
|
||||
|
||||
const trackItem = (
|
||||
itemId: string,
|
||||
transport: RealtimeTranscriptionWebSocketTransport,
|
||||
): boolean => {
|
||||
if (settledItemIds.has(itemId) || completedTranscripts.has(itemId)) {
|
||||
return false;
|
||||
}
|
||||
if (trackedItemIds.has(itemId)) {
|
||||
return true;
|
||||
}
|
||||
if (trackedItemIds.size >= OPENAI_REALTIME_TRANSCRIPTION_MAX_UNRESOLVED_ITEMS) {
|
||||
failTerminal(new Error(OPENAI_REALTIME_TRANSCRIPTION_ITEM_OVERFLOW_MESSAGE), transport);
|
||||
return false;
|
||||
}
|
||||
if (Buffer.byteLength(itemId, "utf8") > OPENAI_REALTIME_TRANSCRIPTION_MAX_ITEM_ID_BYTES) {
|
||||
failTerminal(new Error(OPENAI_REALTIME_TRANSCRIPTION_IDENTITY_OVERFLOW_MESSAGE), transport);
|
||||
return false;
|
||||
}
|
||||
trackedItemIds.add(itemId);
|
||||
return true;
|
||||
};
|
||||
|
||||
const settleItem = (
|
||||
itemId: string,
|
||||
transport: RealtimeTranscriptionWebSocketTransport,
|
||||
): boolean => {
|
||||
const itemIdBytes = Buffer.byteLength(itemId, "utf8");
|
||||
if (
|
||||
settledItemIds.size >= OPENAI_REALTIME_TRANSCRIPTION_MAX_SETTLED_ITEMS ||
|
||||
itemIdBytes > OPENAI_REALTIME_TRANSCRIPTION_MAX_SETTLED_ID_BYTES - settledItemIdBytes
|
||||
) {
|
||||
failTerminal(new Error(OPENAI_REALTIME_TRANSCRIPTION_SETTLED_OVERFLOW_MESSAGE), transport);
|
||||
return false;
|
||||
}
|
||||
trackedItemIds.delete(itemId);
|
||||
// Predecessor satisfaction belongs to each active item. Recording it here
|
||||
// prevents terminal-history saturation from invalidating admitted state.
|
||||
for (const [candidateId, previousItemId] of committedItems) {
|
||||
if (previousItemId === itemId) {
|
||||
committedItems.set(candidateId, null);
|
||||
}
|
||||
}
|
||||
// Never evict terminal identities within a connection generation. Closing
|
||||
// at the bound preserves first-terminal precedence without unbounded state.
|
||||
settledItemIds.add(itemId);
|
||||
settledItemIdBytes += itemIdBytes;
|
||||
return true;
|
||||
};
|
||||
|
||||
const commitItem = (
|
||||
itemId: string,
|
||||
previousItemId: string | null | undefined,
|
||||
transport: RealtimeTranscriptionWebSocketTransport,
|
||||
) => {
|
||||
if (settledItemIds.has(itemId) || committedItems.has(itemId) || !trackItem(itemId, transport)) {
|
||||
return;
|
||||
}
|
||||
committedItems.add(itemId);
|
||||
previousItemIds.set(itemId, previousItemId);
|
||||
if (
|
||||
previousItemId &&
|
||||
Buffer.byteLength(previousItemId, "utf8") > OPENAI_REALTIME_TRANSCRIPTION_MAX_ITEM_ID_BYTES
|
||||
) {
|
||||
failTerminal(new Error(OPENAI_REALTIME_TRANSCRIPTION_IDENTITY_OVERFLOW_MESSAGE), transport);
|
||||
return;
|
||||
}
|
||||
committedItems.set(
|
||||
itemId,
|
||||
previousItemId && settledItemIds.has(previousItemId) ? null : previousItemId,
|
||||
);
|
||||
committedItemIds.push(itemId);
|
||||
|
||||
const arrivalOrder = committedItemIds.splice(0);
|
||||
const successors = new Map<string, string>();
|
||||
for (const candidateId of arrivalOrder) {
|
||||
const previousId = previousItemIds.get(candidateId);
|
||||
const previousId = committedItems.get(candidateId);
|
||||
if (previousId) {
|
||||
successors.set(previousId, candidateId);
|
||||
}
|
||||
@@ -215,7 +320,7 @@ function createOpenAIRealtimeTranscriptionSession(
|
||||
}
|
||||
};
|
||||
for (const candidateId of arrivalOrder) {
|
||||
const previousId = previousItemIds.get(candidateId);
|
||||
const previousId = committedItems.get(candidateId);
|
||||
if (previousId == null || settledItemIds.has(previousId)) {
|
||||
appendChain(candidateId);
|
||||
}
|
||||
@@ -225,44 +330,75 @@ function createOpenAIRealtimeTranscriptionSession(
|
||||
}
|
||||
};
|
||||
|
||||
const flushCompletedTranscripts = () => {
|
||||
const flushCompletedTranscripts = (
|
||||
transport: RealtimeTranscriptionWebSocketTransport,
|
||||
): boolean => {
|
||||
while (committedItemIds.length > 0) {
|
||||
const itemId = committedItemIds[0];
|
||||
if (!itemId || !completedTranscripts.has(itemId)) {
|
||||
return;
|
||||
return true;
|
||||
}
|
||||
const previousItemId = previousItemIds.get(itemId);
|
||||
const previousItemId = committedItems.get(itemId);
|
||||
if (
|
||||
previousItemId &&
|
||||
!settledItemIds.has(previousItemId) &&
|
||||
!committedItems.has(previousItemId)
|
||||
) {
|
||||
return;
|
||||
return true;
|
||||
}
|
||||
committedItemIds.shift();
|
||||
committedItems.delete(itemId);
|
||||
previousItemIds.delete(itemId);
|
||||
settledItemIds.add(itemId);
|
||||
if (!settleItem(itemId, transport)) {
|
||||
return false;
|
||||
}
|
||||
const transcript = completedTranscripts.get(itemId);
|
||||
completedTranscripts.delete(itemId);
|
||||
pendingTranscripts.delete(itemId);
|
||||
if (transcript) {
|
||||
retainedTranscriptBytes -= Buffer.byteLength(transcript, "utf8");
|
||||
}
|
||||
if (transcript) {
|
||||
config.onTranscript?.(transcript);
|
||||
}
|
||||
}
|
||||
return true;
|
||||
};
|
||||
|
||||
const completeItem = (itemId: string | undefined, transcript: string | undefined) => {
|
||||
const completeItem = (
|
||||
itemId: string | undefined,
|
||||
transcript: string | undefined,
|
||||
transport: RealtimeTranscriptionWebSocketTransport,
|
||||
): boolean => {
|
||||
const key = itemId ?? unkeyedTranscript;
|
||||
if (itemId && !trackItem(itemId, transport)) {
|
||||
return false;
|
||||
}
|
||||
const partialBytes = pendingTranscripts.get(key)?.bytes ?? 0;
|
||||
pendingTranscripts.delete(key);
|
||||
retainedTranscriptBytes -= partialBytes;
|
||||
if (!itemId || !committedItems.has(itemId)) {
|
||||
if (itemId) {
|
||||
if (!settleItem(itemId, transport)) {
|
||||
return false;
|
||||
}
|
||||
} else {
|
||||
trackedItemIds.delete(key);
|
||||
}
|
||||
if (transcript) {
|
||||
config.onTranscript?.(transcript);
|
||||
}
|
||||
return;
|
||||
return true;
|
||||
}
|
||||
const transcriptBytes = transcript ? Buffer.byteLength(transcript, "utf8") : 0;
|
||||
if (
|
||||
transcriptBytes >
|
||||
OPENAI_REALTIME_TRANSCRIPTION_MAX_RETAINED_TRANSCRIPT_BYTES - retainedTranscriptBytes
|
||||
) {
|
||||
failTerminal(new Error(OPENAI_REALTIME_TRANSCRIPTION_TEXT_OVERFLOW_MESSAGE), transport);
|
||||
return false;
|
||||
}
|
||||
completedTranscripts.set(itemId, transcript);
|
||||
flushCompletedTranscripts();
|
||||
retainedTranscriptBytes += transcriptBytes;
|
||||
return flushCompletedTranscripts(transport);
|
||||
};
|
||||
|
||||
const handleEvent = (
|
||||
@@ -277,32 +413,63 @@ function createOpenAIRealtimeTranscriptionSession(
|
||||
|
||||
case "input_audio_buffer.committed":
|
||||
if (event.item_id) {
|
||||
commitItem(event.item_id, event.previous_item_id);
|
||||
commitItem(event.item_id, event.previous_item_id, transport);
|
||||
}
|
||||
return;
|
||||
|
||||
case "conversation.item.input_audio_transcription.delta":
|
||||
if (event.delta) {
|
||||
const key = event.item_id ?? unkeyedTranscript;
|
||||
const pendingTranscript = `${pendingTranscripts.get(key) ?? ""}${event.delta}`;
|
||||
pendingTranscripts.set(key, pendingTranscript);
|
||||
config.onPartial?.(pendingTranscript);
|
||||
if (!trackItem(key, transport)) {
|
||||
return;
|
||||
}
|
||||
const pendingTranscript = pendingTranscripts.get(key);
|
||||
const previousPartial = pendingTranscript?.text ?? "";
|
||||
const deltaBytes = appendedUtf8ByteLength(previousPartial, event.delta);
|
||||
if (
|
||||
deltaBytes >
|
||||
OPENAI_REALTIME_TRANSCRIPTION_MAX_RETAINED_TRANSCRIPT_BYTES - retainedTranscriptBytes
|
||||
) {
|
||||
failTerminal(new Error(OPENAI_REALTIME_TRANSCRIPTION_TEXT_OVERFLOW_MESSAGE), transport);
|
||||
return;
|
||||
}
|
||||
const partial = `${previousPartial}${event.delta}`;
|
||||
pendingTranscripts.set(key, {
|
||||
bytes: (pendingTranscript?.bytes ?? 0) + deltaBytes,
|
||||
text: partial,
|
||||
});
|
||||
retainedTranscriptBytes += deltaBytes;
|
||||
config.onPartial?.(partial);
|
||||
}
|
||||
return;
|
||||
|
||||
case "conversation.item.input_audio_transcription.completed":
|
||||
completeItem(event.item_id, event.transcript);
|
||||
completeItem(event.item_id, event.transcript, transport);
|
||||
return;
|
||||
|
||||
case "conversation.item.input_audio_transcription.failed":
|
||||
completeItem(event.item_id, undefined);
|
||||
config.onError?.(new Error(readRealtimeErrorDetail(event.error)));
|
||||
if (
|
||||
event.item_id &&
|
||||
(settledItemIds.has(event.item_id) || completedTranscripts.has(event.item_id))
|
||||
) {
|
||||
return;
|
||||
}
|
||||
if (completeItem(event.item_id, undefined, transport)) {
|
||||
config.onError?.(new Error(readRealtimeErrorDetail(event.error)));
|
||||
}
|
||||
return;
|
||||
|
||||
case "input_audio_buffer.speech_started":
|
||||
pendingTranscripts.delete(event.item_id ?? unkeyedTranscript);
|
||||
case "input_audio_buffer.speech_started": {
|
||||
const key = event.item_id ?? unkeyedTranscript;
|
||||
const partialBytes = pendingTranscripts.get(key)?.bytes ?? 0;
|
||||
pendingTranscripts.delete(key);
|
||||
retainedTranscriptBytes -= partialBytes;
|
||||
if (!committedItems.has(key)) {
|
||||
trackedItemIds.delete(key);
|
||||
}
|
||||
config.onSpeechStart?.();
|
||||
return;
|
||||
}
|
||||
|
||||
case "error": {
|
||||
const detail = readRealtimeErrorDetail(event.error);
|
||||
|
||||
Reference in New Issue
Block a user