feat: ε-greedy v1 as active policy; dwell-time reward inference; offline sim framework

- Promote egreedy-v1 to active serving policy (ADR-0007): /score/egreedy + /reward/egreedy
  replaces linucb-v1 endpoints after offline sim shows +10.7% mean reward (−0.548 vs −0.606)
- Replace explicit helpful/not_helpful feedback with dwell-time inferred reward (inferReward):
  dismiss=−1.0, snooze=+0.1, done<15s=−0.3, done 15s–2min=+1.0, done 2–10min=+0.6, done>10min=+0.3
- Add ml/serving ε-greedy endpoints: /score/egreedy, /reward/egreedy, /stats/egreedy/{user_id}
  with d=7 feature vector (base 5 + sin/cos day-of-week encoding)
- Add offline simulation framework (ml/experiments/sim): rule/LLM/claude-code judges,
  two-phase score+reward, synthetic personas, task generator; results stored in sim_runs/sim_events
- Add /admin/simulations page: start runs, live-poll status, reward curve SVG, action/persona tables
- Fix egreedy day_of_week training skew: reward endpoint now uses actual dow instead of hardcoded 0
- Fix runner.py proxy bypass: httpx.Client(trust_env=False) for localhost ML calls
- Add dwellMs to TipFeedbackEvent contract and bus.test.ts fixture
- Schema: sim_runs, sim_events tables; tip_feedback gains dwell_ms, reward_milli columns
- ADR-0006: admin console framework; ADR-0007: egreedy-v1 policy selection rationale

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-04-16 07:44:37 +00:00
parent c5ea18ec6e
commit faf44c18fc
48 changed files with 6151 additions and 40 deletions

View File

@@ -0,0 +1,131 @@
import { describe, it, expect, vi, beforeEach } from 'vitest';
import { render, screen, waitFor, act, fireEvent } from '@testing-library/react';
import userEvent from '@testing-library/user-event';
// Mock the API module — we test UI behaviour, not network calls
vi.mock('@/lib/api', () => ({
getRecommendation: vi.fn(),
sendFeedback: vi.fn().mockResolvedValue(undefined),
getVapidPublicKey: vi.fn(),
subscribePush: vi.fn(),
}));
import { getRecommendation, sendFeedback } from '@/lib/api';
import TipPage from '@/app/tip/page';
const mockGetRec = getRecommendation as ReturnType<typeof vi.fn>;
const mockSendFeedback = sendFeedback as ReturnType<typeof vi.fn>;
beforeEach(() => {
vi.clearAllMocks();
});
describe('TipPage — empty / error states', () => {
it('shows "All clear." when no tip is returned', async () => {
mockGetRec.mockResolvedValue(null);
render(<TipPage />);
await waitFor(() => expect(screen.getByText('All clear.')).toBeInTheDocument());
});
it('shows "All clear." when getRecommendation throws', async () => {
mockGetRec.mockRejectedValue(Object.assign(new Error('Network error'), { status: 503 }));
render(<TipPage />);
await waitFor(() => expect(screen.getByText('All clear.')).toBeInTheDocument());
});
it('"Check again" button re-calls getRecommendation', async () => {
mockGetRec.mockResolvedValue(null);
render(<TipPage />);
await waitFor(() => screen.getByText('Check again'));
mockGetRec.mockResolvedValue({
tip: { id: 'todoist:2', content: 'New tip', source: 'todoist', createdAt: '' },
});
fireEvent.click(screen.getByText('Check again'));
await waitFor(() => expect(mockGetRec).toHaveBeenCalledTimes(2));
});
});
describe('TipPage — tip display', () => {
it('renders tip content after loading', async () => {
mockGetRec.mockResolvedValue({
tip: { id: 'todoist:1', content: 'Write the test', source: 'todoist', createdAt: '' },
});
render(<TipPage />);
await waitFor(() => expect(screen.getByText('Write the test')).toBeInTheDocument());
});
it('shows "hold to act" hint when tip is displayed', async () => {
mockGetRec.mockResolvedValue({
tip: { id: 'todoist:3', content: 'Do the thing', source: 'todoist', createdAt: '' },
});
render(<TipPage />);
await waitFor(() => expect(screen.getByText(/hold to act/i)).toBeInTheDocument());
});
it('shows "reading you…" while loading', async () => {
// Never resolves during this assertion
mockGetRec.mockReturnValue(new Promise(() => {}));
render(<TipPage />);
expect(screen.getByText(/reading you/i)).toBeInTheDocument();
});
});
describe('TipPage — action sheet', () => {
// Render with real timers, THEN switch to fake for hold simulation
async function renderTipAndHold(id: string, content: string) {
mockGetRec.mockResolvedValue({ tip: { id, content, source: 'todoist', createdAt: '' } });
render(<TipPage />);
// Wait for tip to appear (real timers — no deadlock)
await screen.findByText(content);
const main = screen.getByRole('main');
// Switch to fake timers now that the component is fully loaded
vi.useFakeTimers();
act(() => { main.dispatchEvent(new PointerEvent('pointerdown', { bubbles: true })); });
act(() => { vi.advanceTimersByTime(650); });
vi.useRealTimers();
// Wait for action sheet
await screen.findByText('Done ✓');
return main;
}
it('action sheet appears after a long press (600 ms)', async () => {
await renderTipAndHold('tip:lp', 'Hold me');
expect(screen.getByText('Done ✓')).toBeInTheDocument();
});
it('action sheet does not appear on short press (<600 ms)', async () => {
mockGetRec.mockResolvedValue({ tip: { id: 'tip:sp', content: 'Short press', source: 'todoist', createdAt: '' } });
render(<TipPage />);
await screen.findByText('Short press');
const main = screen.getByRole('main');
vi.useFakeTimers();
act(() => { main.dispatchEvent(new PointerEvent('pointerdown', { bubbles: true })); });
act(() => { vi.advanceTimersByTime(200); });
act(() => { main.dispatchEvent(new PointerEvent('pointerup', { bubbles: true })); });
vi.useRealTimers();
expect(screen.queryByText('Done ✓')).not.toBeInTheDocument();
});
it('clicking "Done ✓" calls sendFeedback with action=done', async () => {
await renderTipAndHold('tip:d', 'Do it');
await act(async () => { fireEvent.click(screen.getByText('Done ✓')); });
expect(mockSendFeedback).toHaveBeenCalledWith('tip:d', { action: 'done' });
});
it('clicking "Dismiss" calls sendFeedback with action=dismiss', async () => {
await renderTipAndHold('tip:dis', 'Dismiss me');
await act(async () => { fireEvent.click(screen.getByText('Dismiss')); });
expect(mockSendFeedback).toHaveBeenCalledWith('tip:dis', { action: 'dismiss' });
});
it('clicking "Helpful" calls sendFeedback with action=helpful (non-navigating)', async () => {
await renderTipAndHold('tip:help', 'Helpful tip');
await act(async () => { fireEvent.click(screen.getByText('Helpful')); });
expect(mockSendFeedback).toHaveBeenCalledWith('tip:help', { action: 'helpful' });
});
});

View File

@@ -0,0 +1 @@
import '@testing-library/jest-dom';