Own the microphone level in the state layer

- The capture, the analyser loop and the loudness maths were in a component
  hook. Call logic belongs in the state layer; components render.
- observeMicrophoneState$ opens the device when something subscribes and
  releases it when nothing does. The hook is left as a bridge, no domain logic.
- Fixes a leak. A permission prompt outlives the menu that opened it, so the
  browser could hand over a microphone after cleanup had already run — with the
  variable that cleanup would have released still unset. The device stayed
  held, indicator lit, no meter on screen.
- Expressed now as the subscriber being closed, which the observable can always
  answer.
- The hook had no tests at all, which is why this survived. Four now, and the
  capture stub they need is in the shared factories rather than hand-rolled.
- One counts emissions across twenty animation frames and expects one: the
  redraw cost AGENTS.md asks continuous drawing to account for.
This commit is contained in:
fkwp
2026-09-17 11:56:25 +02:00
parent 0802649375
commit d8211c0c61
5 changed files with 327 additions and 88 deletions
@@ -0,0 +1,42 @@
/*
Copyright 2026 Element Creations Ltd.
SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-Element-Commercial
Please see LICENSE in the repository root for full details.
*/
import { afterEach, describe, expect, test } from "vitest";
import { renderHook } from "@testing-library/react";
import { useMicrophoneLevel } from "./useMicrophoneLevel";
import { restoreAudioCapture, stubAudioCapture } from "../utils/test";
// The capture itself, and releasing it, belong to observeMicrophoneState$ and
// are covered in src/state/MicrophoneLevel.test.ts. What is left here is the
// bridging: when the hook watches, and what it reports before it has an answer.
describe("useMicrophoneLevel", () => {
afterEach(restoreAudioCapture);
test("holds no capture while the meter is not shown", () => {
const capture = stubAudioCapture();
renderHook(() => useMicrophoneLevel("mic1", false));
expect(capture.getUserMedia).not.toHaveBeenCalled();
});
test("starts from nothing rather than the previous device's level", () => {
const capture = stubAudioCapture();
const { result, rerender } = renderHook(
({ id }: { id: string }) => useMicrophoneLevel(id, true),
{ initialProps: { id: "mic1" } },
);
capture.grant();
rerender({ id: "mic2" });
// No level carried over: the meter reads the new device or nothing at all.
expect(result.current).toEqual({ type: "level", level: 0 });
});
});
+13 -87
View File
@@ -6,109 +6,35 @@ Please see LICENSE in the repository root for full details.
*/
import { useEffect, useState } from "react";
import { logger } from "matrix-js-sdk/lib/logger";
import {
type MicrophoneState,
segmentsForVolume,
smoothVolume,
observeMicrophoneState$,
} from "../state/MicrophoneLevel";
const IDLE: MicrophoneState = { type: "level", level: 0 };
/**
* Reads the live input level of a microphone, while `active`.
*
* Capture is scoped to the caller being on screen: the meter only exists while
* the menu that shows it is open, so nothing holds a second capture of the
* device for the length of a call.
*
* The level says whether the microphone is picking anything up, which is not
* the same as whether the user is being heard. It keeps moving while muted, and
* the mute control is what says nothing is transmitted.
* A bridge and nothing else: the capture, its lifetime and the maths belong to
* {@link observeMicrophoneState$}. Scoped to `active` so the device is held
* only while whatever shows the meter is on screen, rather than for the length
* of a call.
*/
export function useMicrophoneLevel(
deviceId: string | undefined,
active: boolean,
): MicrophoneState {
const [state, setState] = useState<MicrophoneState>({
type: "level",
level: 0,
});
const [state, setState] = useState<MicrophoneState>(IDLE);
useEffect(() => {
if (!active) return;
let stopped = false;
let stream: MediaStream | undefined;
let context: AudioContext | undefined;
let frame: number | undefined;
const stop = (): void => {
stopped = true;
if (frame !== undefined) cancelAnimationFrame(frame);
stream?.getTracks().forEach((track) => track.stop());
void context?.close();
};
const start = async (): Promise<void> => {
stream = await navigator.mediaDevices.getUserMedia({
audio:
deviceId === undefined ? true : { deviceId: { exact: deviceId } },
});
if (stopped) return;
context = new AudioContext();
// Chrome starts the context suspended unless it was created during a
// gesture; opening the menu is one, but resume explicitly so the meter
// cannot silently sit at zero.
if (context.state === "suspended") await context.resume();
if (stopped) return;
const analyser = context.createAnalyser();
analyser.fftSize = 1024;
context.createMediaStreamSource(stream).connect(analyser);
const samples = new Uint8Array(analyser.fftSize);
let displayed = 0;
let previousFrame = performance.now();
const read = (): void => {
analyser.getByteTimeDomainData(samples);
// Root mean square of the waveform around its centre, which is the
// loudness a listener perceives rather than the tallest spike.
let sum = 0;
for (const sample of samples) {
const centred = (sample - 128) / 128;
sum += centred * centred;
}
const now = performance.now();
displayed = smoothVolume(
displayed,
Math.sqrt(sum / samples.length),
now - previousFrame,
);
previousFrame = now;
const level = segmentsForVolume(displayed);
setState((current) =>
current.type === "level" && current.level === level
? current
: { type: "level", level },
);
frame = requestAnimationFrame(read);
};
read();
};
start().catch((e: unknown) => {
const name = e instanceof Error ? e.name : "";
if (name === "NotAllowedError" || name === "SecurityError") {
setState({ type: "permission-denied" });
} else if (name === "NotFoundError" || name === "OverconstrainedError") {
setState({ type: "no-device" });
} else {
logger.error("Could not read the microphone level", e);
setState({ type: "no-device" });
}
});
return stop;
// Idle first, so a new device starts from nothing rather than from the
// level the previous one was reading.
setState(IDLE);
const subscription = observeMicrophoneState$(deviceId).subscribe(setState);
return (): void => subscription.unsubscribe();
}, [deviceId, active]);
return state;
+73 -1
View File
@@ -5,15 +5,17 @@ SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-Element-Commercial
Please see LICENSE in the repository root for full details.
*/
import { describe, expect, test } from "vitest";
import { afterEach, describe, expect, test, vi } from "vitest";
import {
ATTACK_MS,
METER_SEGMENTS,
observeMicrophoneState$,
RELEASE_MS,
segmentsForVolume,
smoothVolume,
} from "./MicrophoneLevel";
import { restoreAudioCapture, stubAudioCapture } from "../utils/test";
describe("segmentsForVolume", () => {
test("shows nothing for silence", () => {
@@ -88,3 +90,73 @@ describe("smoothVolume", () => {
expect(smoothVolume(0.5, 1, 0)).toBe(0.5);
});
});
describe("observeMicrophoneState$", () => {
afterEach(restoreAudioCapture);
test("releases a capture the browser grants after nobody is watching", async () => {
const capture = stubAudioCapture();
const subscription = observeMicrophoneState$("mic1").subscribe();
// The user gives up on the permission prompt and closes the menu, and only
// then does the browser hand the microphone over.
subscription.unsubscribe();
capture.grant();
await vi.waitFor(() => expect(capture.track.stop).toHaveBeenCalled());
});
test("releases the capture and the audio context when the subscription ends", async () => {
const capture = stubAudioCapture();
const subscription = observeMicrophoneState$("mic1").subscribe();
capture.grant();
await vi.waitFor(() => expect(capture.contexts).toHaveLength(1));
subscription.unsubscribe();
expect(capture.track.stop).toHaveBeenCalled();
expect(capture.contexts[0].close).toHaveBeenCalled();
});
test("tells denied permission and a missing device apart", async () => {
for (const [name, expected] of [
["NotAllowedError", "permission-denied"],
["NotFoundError", "no-device"],
] as const) {
const capture = stubAudioCapture();
capture.getUserMedia.mockRejectedValue(named(new Error(name), name));
const seen: string[] = [];
const subscription = observeMicrophoneState$("mic1").subscribe((state) =>
seen.push(state.type),
);
await vi.waitFor(() => expect(seen).toContain(expected));
subscription.unsubscribe();
restoreAudioCapture();
}
});
test("says nothing on a frame that did not change the level", async () => {
const capture = stubAudioCapture();
let emissions = 0;
const subscription = observeMicrophoneState$("mic1").subscribe(
() => emissions++,
);
capture.grant();
await vi.waitFor(() => expect(emissions).toBe(1));
// The analyser is read every animation frame, but the meter has only
// METER_SEGMENTS steps: a steady signal must not redraw the meter.
capture.drawFrames(20);
expect(emissions).toBe(1);
subscription.unsubscribe();
});
});
/** An error with the `name` the browser would give it, not just a message. */
function named(error: Error, name: string): Error {
error.name = name;
return error;
}
+109
View File
@@ -5,6 +5,9 @@ SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-Element-Commercial
Please see LICENSE in the repository root for full details.
*/
import { distinctUntilChanged, Observable } from "rxjs";
import { logger } from "matrix-js-sdk/lib/logger";
/**
* What the microphone selector can say about the input, beyond its level.
*
@@ -24,6 +27,112 @@ export type MicrophoneState =
*/
export const METER_SEGMENTS = 24;
/**
* Observes what a microphone is picking up, as the meter should show it.
*
* Subscribing opens the device and unsubscribing releases it, so it is held for
* exactly as long as something is watching — the menu, and not the call.
*
* Opens a capture of its own rather than reading the track the call already
* holds. That is a shortcut, recorded as S1 in the feature spec: the pre-join
* screen freezes its audio track to the device selected when it mounted, so a
* meter fed from that track could not follow the picker.
*
* The level says whether the microphone is picking anything up, which is not
* the same as whether the user is being heard: it keeps reading while muted,
* and the mute control is what says nothing is transmitted.
*/
export function observeMicrophoneState$(
deviceId: string | undefined,
): Observable<MicrophoneState> {
return new Observable<MicrophoneState>((subscriber) => {
let stream: MediaStream | undefined;
let context: AudioContext | undefined;
let frame: number | undefined;
// Safe to call more than once: unsubscribing runs it, and `start` runs it
// again for anything the browser handed over after that.
const release = (): void => {
if (frame !== undefined) cancelAnimationFrame(frame);
stream?.getTracks().forEach((track) => track.stop());
void context?.close();
frame = undefined;
stream = undefined;
context = undefined;
};
const start = async (): Promise<void> => {
stream = await navigator.mediaDevices.getUserMedia({
audio:
deviceId === undefined ? true : { deviceId: { exact: deviceId } },
});
// A permission prompt outlives the subscription that asked for it, so by
// now nobody may be watching — and `release` ran while `stream` was still
// undefined. Nothing will call it again, so release here or the device
// stays held, with the indicator lit and no meter on screen.
if (subscriber.closed) return release();
context = new AudioContext();
// Chrome starts the context suspended unless it was created during a
// gesture; opening the menu is one, but resume explicitly so the meter
// cannot silently sit at zero.
if (context.state === "suspended") await context.resume();
if (subscriber.closed) return release();
const analyser = context.createAnalyser();
analyser.fftSize = 1024;
context.createMediaStreamSource(stream).connect(analyser);
const samples = new Uint8Array(analyser.fftSize);
let displayed = 0;
let previousFrame = performance.now();
const read = (): void => {
analyser.getByteTimeDomainData(samples);
// Root mean square of the waveform around its centre, which is the
// loudness a listener perceives rather than the tallest spike.
let sum = 0;
for (const sample of samples) {
const centred = (sample - 128) / 128;
sum += centred * centred;
}
const now = performance.now();
displayed = smoothVolume(
displayed,
Math.sqrt(sum / samples.length),
now - previousFrame,
);
previousFrame = now;
subscriber.next({ type: "level", level: segmentsForVolume(displayed) });
frame = requestAnimationFrame(read);
};
read();
};
start().catch((e: unknown) => subscriber.next(stateForFailure(e)));
return release;
}).pipe(
// Read every animation frame, but quantised to a whole number of segments,
// so most frames say nothing new and should not reach React.
distinctUntilChanged(
(a, b) =>
a.type === b.type &&
(a.type !== "level" || b.type !== "level" || a.level === b.level),
),
);
}
/** What a failure to open the microphone means for the person using it. */
function stateForFailure(e: unknown): MicrophoneState {
const name = e instanceof Error ? e.name : "";
if (name === "NotAllowedError" || name === "SecurityError")
return { type: "permission-denied" };
if (name === "NotFoundError" || name === "OverconstrainedError")
return { type: "no-device" };
logger.error("Could not read the microphone level", e);
return { type: "no-device" };
}
/**
* Loudness below which the microphone is treated as picking up nothing.
*
+90
View File
@@ -8,6 +8,7 @@ import { map, type Observable, of, type SchedulerLike } from "rxjs";
import { type RunHelpers, TestScheduler } from "rxjs/testing";
import {
expect,
type Mock,
type MockedObject,
type MockInstance,
onTestFinished,
@@ -590,3 +591,92 @@ export class MockConnection extends Connection {
public async start(): Promise<void> {}
public async stop(): Promise<void> {}
}
export interface StubbedCapture {
getUserMedia: Mock;
/** Hands the microphone over, as the browser does once permission is given. */
grant: () => void;
track: { stop: Mock };
contexts: { close: Mock }[];
/** Runs the animation frames the level meter reads on, in order. */
drawFrames: (count: number) => void;
}
/**
* Stubs just enough of the capture and Web Audio APIs for a microphone level to
* be read, with the grant held back so a test decides when — or whether — it
* lands, and with animation frames driven by hand rather than by a clock.
*
* Call {@link restoreAudioCapture} afterwards, or every later test in the run
* inherits the stub.
*/
export function stubAudioCapture(): StubbedCapture {
const track = { stop: vi.fn() };
const contexts: { close: Mock }[] = [];
let grant = (): void => {};
const granted = new Promise<MediaStream>((resolve) => {
grant = (): void =>
resolve({ getTracks: () => [track] } as unknown as MediaStream);
});
const frames: FrameRequestCallback[] = [];
vi.stubGlobal("requestAnimationFrame", (callback: FrameRequestCallback) => {
frames.push(callback);
return frames.length;
});
vi.stubGlobal("cancelAnimationFrame", vi.fn());
vi.stubGlobal(
"AudioContext",
class {
public readonly state = "running";
public readonly close = vi.fn();
public constructor() {
contexts.push(this);
}
public createAnalyser(): object {
return {
fftSize: 1024,
// Digital silence, which is the midpoint of the range and not zero:
// a buffer left at zero reads as a full-scale waveform.
getByteTimeDomainData: (samples: Uint8Array): void => {
samples.fill(128);
},
};
}
public createMediaStreamSource(): object {
return { connect: (): void => {} };
}
},
);
// Only this property: replacing navigator wholesale drops the getters on its
// prototype, such as userAgent.
Object.defineProperty(navigator, "mediaDevices", {
configurable: true,
value: { getUserMedia: vi.fn().mockReturnValue(granted) },
});
return {
getUserMedia: navigator.mediaDevices.getUserMedia as unknown as Mock,
grant: () => grant(),
track,
contexts,
drawFrames: (count): void => {
for (let i = 0; i < count; i++) frames.shift()?.(i);
},
};
}
const realMediaDevices = Object.getOwnPropertyDescriptor(
navigator,
"mediaDevices",
);
/** Undoes {@link stubAudioCapture}. */
export function restoreAudioCapture(): void {
vi.unstubAllGlobals();
if (realMediaDevices === undefined) {
Reflect.deleteProperty(navigator, "mediaDevices");
} else {
Object.defineProperty(navigator, "mediaDevices", realMediaDevices);
}
}