feat(lotus): report the local mic level to the host (cinny #146)

The host had only a boolean `speaking` for yourself, throttled to 500 ms, so
nothing on the call bar showed that the mic was actually picking you up.

- lotusMicLevel.ts: one shared local mic sampler (a clone of the published
  track, ~10 Hz RMS, while a mic is published, muted or not), shared per
  call view model so there is one AudioContext.
- MicLevelQuantizer: 0–3 bars (≈ −46/−36/−26 dBFS), rising at once and
  falling one bar per sample so it doesn't flicker between words.
- fromWidget io.lotus.mic_level { bars } only when the value changes; 0 while
  muted or with no mic. Opt-in with the host state stream (lotusCallState=1).
- "Talking while muted" (#37) now reads the same sampler instead of running
  its own; same gate and behaviour.

Verified in a local call with a fake-tone mic: the host receives 0–3 as the
tone rises/falls (about 4 messages/s while it changes), 0 on mute and levels
again on unmute; muted + tone still raises speakingWhileMuted and the host's
"You're muted" notice. Lotus/room suites pass on Node 22 (148 tests).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPmy3tPq869XDW4njjVaKA
This commit is contained in:
Lotus CI
2026-09-25 12:08:57 -04:00
co-authored by Claude Opus 5.5
parent 44023a4c84
commit cee6bab9a6
6 changed files with 257 additions and 89 deletions
+19 -89
View File
@@ -6,14 +6,15 @@ Please see LICENSE in the repository root for full details.
*/
import {
type LocalTrackPublication,
type Room as LivekitRoom,
RoomEvent,
Track,
} from "livekit-client";
import { Observable, distinctUntilChanged, switchMap } from "rxjs";
type Observable,
distinctUntilChanged,
map,
scan,
startWith,
} from "rxjs";
import { type CallViewModel } from "../state/CallViewModel/CallViewModel";
import { type LocalMicSample, observeLocalMicSample$ } from "./lotusMicLevel";
/**
* [lotus #37] "Talking while muted" detection for the LOCAL participant.
@@ -23,13 +24,12 @@ import { type CallViewModel } from "../state/CallViewModel/CallViewModel";
* tells the user they are talking into a muted mic. This taps a CLONE of the
* published track (the post-processor track when the in-source denoiser is
* active, so keyboard noise doesn't count), samples RMS at ~10 Hz and emits a
* debounced boolean. Zero cost when unmuted (tap torn down), local-only —
* debounced boolean. Local-only —
* the flag rides `io.lotus.call_state` to the host and never reaches other
* participants.
*/
export const MUTED_SPEECH_RMS = 0.015; // ≈ −36 dBFS; normal speech into a headset is 0.05–0.3
const SAMPLE_MS = 100;
const ON_SAMPLES = 3; // 300 ms of voice before we say "talking"
const OFF_SAMPLES = 8; // 800 ms of quiet before we drop it
@@ -61,94 +61,24 @@ export class MutedSpeechGate {
}
}
const mutedMicTrack = (room: LivekitRoom): MediaStreamTrack | null => {
const pub: LocalTrackPublication | undefined =
room.localParticipant.getTrackPublication(Track.Source.Microphone);
const track = pub?.track?.mediaStreamTrack;
return pub?.isMuted && track && track.readyState === "live" ? track : null;
};
/**
* Emits while the local mic is muted and voice is detected on it. Emits
* `false` whenever the mic is unmuted, unpublished or the connection changes.
* [lotus #146] Fed by the shared local mic sampler (lotusMicLevel.ts), which
* also drives the host's mic level meter while unmuted.
*/
export function observeSpeakingWhileMuted$(
vm: CallViewModel,
): Observable<boolean> {
return vm.allConnections$.pipe(
switchMap(
(data) =>
new Observable<boolean>((subscriber) => {
const rooms = data.getConnections().map((c) => c.livekitRoom);
let ctx: AudioContext | null = null;
let clone: MediaStreamTrack | null = null;
let timer: ReturnType<typeof setInterval> | undefined;
let tapped: MediaStreamTrack | null = null;
const stopTap = (): void => {
if (timer !== undefined) clearInterval(timer);
timer = undefined;
clone?.stop();
clone = null;
void ctx?.close().catch(() => undefined);
ctx = null;
tapped = null;
subscriber.next(false);
};
const startTap = (source: MediaStreamTrack): void => {
try {
clone = source.clone();
clone.enabled = true; // the source is disabled by the mute — the clone must not be
ctx = new AudioContext();
const analyser = ctx.createAnalyser();
analyser.fftSize = 1024;
ctx
.createMediaStreamSource(new MediaStream([clone]))
.connect(analyser);
const buf = new Float32Array(analyser.fftSize);
const gate = new MutedSpeechGate();
tapped = source;
timer = setInterval(() => {
analyser.getFloatTimeDomainData(buf);
let sum = 0;
for (let i = 0; i < buf.length; i += 1) sum += buf[i] * buf[i];
subscriber.next(gate.push(Math.sqrt(sum / buf.length)));
}, SAMPLE_MS);
} catch {
stopTap();
}
};
const reconcile = (): void => {
const track =
rooms.map(mutedMicTrack).find((t) => t !== null) ?? null;
if (track === tapped) return;
if (tapped) stopTap();
if (track) startTap(track);
};
const events = [
RoomEvent.TrackMuted,
RoomEvent.TrackUnmuted,
RoomEvent.LocalTrackPublished,
RoomEvent.LocalTrackUnpublished,
RoomEvent.Reconnected,
RoomEvent.Disconnected,
] as const;
rooms.forEach((room) =>
events.forEach((ev) => room.on(ev, reconcile)),
);
subscriber.next(false);
reconcile();
return () => {
rooms.forEach((room) =>
events.forEach((ev) => room.off(ev, reconcile)),
);
if (tapped) stopTap();
};
}),
),
return observeLocalMicSample$(vm).pipe(
scan((gate: MutedSpeechGate | null, sample: LocalMicSample | null) => {
if (!sample?.muted) return null;
const g = gate ?? new MutedSpeechGate();
g.push(sample.rms);
return g;
}, null),
map((gate) => gate?.value ?? false),
startWith(false),
distinctUntilChanged(),
);
}