webavatar-core/src/lib/client/humanoid/avatar-state.spec.ts

import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
import type { ServerEvent } from '../../core/protocol.js';
import { deriveAvatarState, type AvatarStateSource } from './avatar-state.js';

/** Minimal stand-in for RealtimeClient/ResilientRealtimeClient — only .on() is used. */
class FakeSource implements AvatarStateSource {
	private handler: ((event: ServerEvent) => void) | null = null;

	on(handler: (event: ServerEvent) => void): () => void {
		this.handler = handler;
		return () => {
			this.handler = null;
		};
	}

	emit(event: ServerEvent): void {
		this.handler?.(event);
	}
}

describe('deriveAvatarState', () => {
	beforeEach(() => {
		vi.useFakeTimers();
	});

	afterEach(() => {
		vi.useRealTimers();
	});

	it('subscribe() emits the current state immediately', () => {
		const store = deriveAvatarState(new FakeSource());
		const run = vi.fn();
		store.subscribe(run);
		expect(run).toHaveBeenCalledTimes(1);
		expect(run).toHaveBeenCalledWith('idleActive');
	});

	it('walks listening -> thinking -> talking -> idleActive across a full voice turn', () => {
		const source = new FakeSource();
		const store = deriveAvatarState(source);
		const seen: string[] = [];
		store.subscribe((s) => seen.push(s));

		store.setListening(true);
		store.setListening(false);
		source.emit({ type: 'output_audio.chunk', audio: '' });
		source.emit({ type: 'output_audio.done' });

		expect(seen).toEqual(['idleActive', 'listening', 'thinking', 'talking', 'idleActive']);
	});

	it('notifyResponseRequested() drives thinking for the typed-text path', () => {
		const source = new FakeSource();
		const store = deriveAvatarState(source);
		const seen: string[] = [];
		store.subscribe((s) => seen.push(s));

		store.notifyResponseRequested();
		source.emit({ type: 'transcript.delta', role: 'assistant', text: 'hi' });
		source.emit({ type: 'transcript.done', role: 'assistant' });

		expect(seen).toEqual(['idleActive', 'thinking', 'talking', 'idleActive']);
	});

	it('ignores user transcript events (no signal either way)', () => {
		const source = new FakeSource();
		const store = deriveAvatarState(source);
		const seen: string[] = [];
		store.subscribe((s) => seen.push(s));

		source.emit({ type: 'transcript.delta', role: 'user', text: 'hello' });

		expect(seen).toEqual(['idleActive']);
	});

	it('session.ready and session.closed reset to idleActive from any state', () => {
		const source = new FakeSource();
		const store = deriveAvatarState(source);
		const seen: string[] = [];
		store.subscribe((s) => seen.push(s));

		source.emit({ type: 'output_audio.chunk', audio: '' }); // -> talking
		source.emit({ type: 'session.closed', reason: 'client_requested' });

		expect(seen).toEqual(['idleActive', 'talking', 'idleActive']);
	});

	it('response.done is a fallback that stops talking even without output_audio.done', () => {
		const source = new FakeSource();
		const store = deriveAvatarState(source);
		const seen: string[] = [];
		store.subscribe((s) => seen.push(s));

		source.emit({ type: 'output_audio.chunk', audio: '' });
		source.emit({ type: 'response.done' });

		expect(seen).toEqual(['idleActive', 'talking', 'idleActive']);
	});

	it('destroy() stops reacting to further events', () => {
		const source = new FakeSource();
		const store = deriveAvatarState(source);
		const seen: string[] = [];
		store.subscribe((s) => seen.push(s));

		store.destroy();
		source.emit({ type: 'output_audio.chunk', audio: '' });

		expect(seen).toEqual(['idleActive']);
	});

	it('settles idleActive into idlePassive after the configured timeout with no other signal', () => {
		const source = new FakeSource();
		const store = deriveAvatarState(source, { idlePassiveTimeoutMs: 5_000 });
		const seen: string[] = [];
		store.subscribe((s) => seen.push(s));

		vi.advanceTimersByTime(5_000);

		expect(seen).toEqual(['idleActive', 'idlePassive']);
	});

	it('does not fire idle_timeout while something else is happening', () => {
		const source = new FakeSource();
		const store = deriveAvatarState(source, { idlePassiveTimeoutMs: 5_000 });
		const seen: string[] = [];
		store.subscribe((s) => seen.push(s));

		vi.advanceTimersByTime(4_000);
		store.setListening(true); // -> listening, cancels/re-arms the idle timer
		vi.advanceTimersByTime(4_000); // < 5s since re-arm — still listening
		store.setListening(false); // -> thinking

		expect(seen).toEqual(['idleActive', 'listening', 'thinking']);
	});

	it('re-arms the idle timer once back in idleActive, and destroy() cancels it', () => {
		const source = new FakeSource();
		const store = deriveAvatarState(source, { idlePassiveTimeoutMs: 5_000 });
		const seen: string[] = [];
		store.subscribe((s) => seen.push(s));

		source.emit({ type: 'output_audio.chunk', audio: '' }); // -> talking
		source.emit({ type: 'output_audio.done' }); // -> idleActive, re-arms timer

		store.destroy();
		vi.advanceTimersByTime(5_000);

		expect(seen).toEqual(['idleActive', 'talking', 'idleActive']);
	});
});