feat(bridge): gate Whisper behind Silero VAD; harden broadcast auto-start

Address review of the noise/broadcast fixes:

- STT now refuses to run Whisper on non-speech. transcribe() runs the Silero
  VAD (bundled with faster-whisper, no new dep) BEFORE the model, so noise or a
  brief loud blip with no real speech never reaches STT and can't be
  hallucinated into a transcript. The no_speech_prob/avg_logprob post-filter
  stays as a second line of defence (a clap the VAD lets through is still killed
  by Whisper's own no_speech_prob). VAD is env-tunable (VAD_THRESHOLD,
  VAD_MIN_SPEECH_MS, VAD_ENABLED) and fail-open so a VAD error never swallows a
  real utterance. Validated on real audio: synthesised Korean speech passes;
  silence, a 50ms blip and white noise are rejected.

- Broadcast auto-start no longer blocks the voice join and no longer silently
  swallows failures: wiring is synchronous, the Go-Live start runs in the
  background with a bounded retry and a loud final-failure log.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
javis-bot
2026-06-13 14:53:54 +09:00
parent 39c7a22a12
commit 6d72e10f9c
5 changed files with 194 additions and 48 deletions

View File

@@ -3,7 +3,7 @@ import { test, expect } from "bun:test";
// broadcast.ts pulls in the runtime `config`, which requires DISCORD_GUILD_ID.
// Set it before the dynamic import so the module loads without a real .env.
process.env.DISCORD_GUILD_ID ||= "test-guild";
const { coupleBroadcast } = await import("./broadcast.ts");
const { wireBroadcast, autoStartBroadcast } = await import("./broadcast.ts");
/** Minimal in-memory ScreenStreamer that records start/stop calls. */
function fakeStreamer(active = false) {
@@ -27,44 +27,67 @@ function fakeStreamer(active = false) {
const ctx = { guildId: "g", voiceChannelId: "c" };
test("auto-starts the broadcast when joining with the stream idle", async () => {
test("wireBroadcast reports live state to the brain", () => {
const s = fakeStreamer(false);
const session: any = {};
await coupleBroadcast(session, s as any, ctx);
expect(s.calls).toEqual(["start"]);
expect(session.getBroadcasting()).toBe(true);
});
test("does not restart a broadcast that is already live", async () => {
const s = fakeStreamer(true);
const session: any = {};
await coupleBroadcast(session, s as any, ctx);
expect(s.calls).toEqual([]);
expect(session.getBroadcasting()).toBe(true);
});
test("the brain can toggle the stream by voice via onBroadcastAction", async () => {
const s = fakeStreamer(false);
const session: any = {};
await coupleBroadcast(session, s as any, ctx); // auto-start fires
await session.onBroadcastAction("start"); // already live -> no-op
await session.onBroadcastAction("stop"); // stops
wireBroadcast(session, s as any, ctx);
expect(session.getBroadcasting()).toBe(false);
await session.onBroadcastAction("start"); // restarts
expect(session.getBroadcasting()).toBe(true);
expect(s.calls).toEqual(["start", "stop", "start"]);
});
test("an auto-start failure is swallowed but the toggle hooks are still wired", async () => {
test("wireBroadcast lets the brain toggle the stream by voice", async () => {
const s = fakeStreamer(false);
const session: any = {};
wireBroadcast(session, s as any, ctx);
await session.onBroadcastAction("start"); // idle -> start
expect(session.getBroadcasting()).toBe(true);
await session.onBroadcastAction("start"); // already live -> no-op
await session.onBroadcastAction("stop"); // stop
expect(session.getBroadcasting()).toBe(false);
expect(s.calls).toEqual(["start", "stop"]);
});
test("autoStartBroadcast starts the broadcast when idle", async () => {
const s = fakeStreamer(false);
const ok = await autoStartBroadcast(s as any, ctx, 2, 0);
expect(ok).toBe(true);
expect(s.calls).toEqual(["start"]);
});
test("autoStartBroadcast does not restart an already-live broadcast", async () => {
const s = fakeStreamer(true);
const ok = await autoStartBroadcast(s as any, ctx, 2, 0);
expect(ok).toBe(true);
expect(s.calls).toEqual([]);
});
test("autoStartBroadcast retries a transient failure and then succeeds", async () => {
let on = false;
const calls: string[] = [];
const s: any = {
isActive: () => on,
async start() {
calls.push("start");
if (calls.length === 1) throw new Error("transient: voice not ready");
on = true;
},
async stop() {},
};
const ok = await autoStartBroadcast(s, ctx, 2, 0);
expect(ok).toBe(true);
expect(calls).toEqual(["start", "start"]);
});
test("autoStartBroadcast returns false after exhausting retries (no throw)", async () => {
let attempts = 0;
const s: any = {
isActive: () => false,
async start() {
attempts++;
throw new Error("boom");
},
async stop() {},
};
const session: any = {};
await coupleBroadcast(session, s, ctx);
expect(typeof session.getBroadcasting).toBe("function");
expect(typeof session.onBroadcastAction).toBe("function");
const ok = await autoStartBroadcast(s, ctx, 2, 0);
expect(ok).toBe(false);
expect(attempts).toBe(2); // retried, then gave up without throwing
});