smartai/test/test.vision.anthropic.ts

import { expect, tap } from '@push.rocks/tapbundle';
import * as qenv from '@push.rocks/qenv';
import * as smartfile from '@push.rocks/smartfile';

const testQenv = new qenv.Qenv('./', './.nogit/');

import * as smartai from '../ts/index.js';

let anthropicProvider: smartai.AnthropicProvider;

tap.test('Anthropic Vision: should create and start Anthropic provider', async () => {
  anthropicProvider = new smartai.AnthropicProvider({
    anthropicToken: await testQenv.getEnvVarOnDemand('ANTHROPIC_TOKEN'),
  });
  await anthropicProvider.start();
  expect(anthropicProvider).toBeInstanceOf(smartai.AnthropicProvider);
});

tap.test('Anthropic Vision: should analyze coffee image with latte art', async () => {
  // Test 1: Coffee image from Unsplash by Dani
  const imagePath = './test/testimages/coffee-dani/coffee.jpg';
  console.log(`Loading coffee image from: ${imagePath}`);

  const imageBuffer = await smartfile.fs.toBuffer(imagePath);
  console.log(`Image loaded, size: ${imageBuffer.length} bytes`);

  const result = await anthropicProvider.vision({
    image: imageBuffer,
    prompt: 'Describe this coffee image. What do you see in terms of the cup, foam pattern, and overall composition?'
  });

  console.log(`Anthropic Vision (Coffee) - Result: ${result}`);
  expect(result).toBeTruthy();
  expect(typeof result).toEqual('string');
  expect(result.toLowerCase()).toInclude('coffee');
  // The image has a heart pattern in the latte art
  const mentionsLatte = result.toLowerCase().includes('heart') ||
                        result.toLowerCase().includes('latte') ||
                        result.toLowerCase().includes('foam');
  expect(mentionsLatte).toBeTrue();
});

tap.test('Anthropic Vision: should analyze laptop/workspace image', async () => {
  // Test 2: Laptop image from Unsplash by Nicolas Bichon
  const imagePath = './test/testimages/laptop-nicolas/laptop.jpg';
  console.log(`Loading laptop image from: ${imagePath}`);

  const imageBuffer = await smartfile.fs.toBuffer(imagePath);
  console.log(`Image loaded, size: ${imageBuffer.length} bytes`);

  const result = await anthropicProvider.vision({
    image: imageBuffer,
    prompt: 'Describe the technology and workspace setup in this image. What devices and equipment can you see?'
  });

  console.log(`Anthropic Vision (Laptop) - Result: ${result}`);
  expect(result).toBeTruthy();
  expect(typeof result).toEqual('string');
  // Should mention laptop, computer, keyboard, or desk
  const mentionsTech = result.toLowerCase().includes('laptop') ||
                       result.toLowerCase().includes('computer') ||
                       result.toLowerCase().includes('keyboard') ||
                       result.toLowerCase().includes('desk');
  expect(mentionsTech).toBeTrue();
});

tap.test('Anthropic Vision: should analyze receipt/document image', async () => {
  // Test 3: Receipt image from Unsplash by Annie Spratt
  const imagePath = './test/testimages/receipt-annie/receipt.jpg';
  console.log(`Loading receipt image from: ${imagePath}`);

  const imageBuffer = await smartfile.fs.toBuffer(imagePath);
  console.log(`Image loaded, size: ${imageBuffer.length} bytes`);

  const result = await anthropicProvider.vision({
    image: imageBuffer,
    prompt: 'What type of document is this? Can you identify any text or numbers visible in the image?'
  });

  console.log(`Anthropic Vision (Receipt) - Result: ${result}`);
  expect(result).toBeTruthy();
  expect(typeof result).toEqual('string');
  // Should mention receipt, document, text, or paper
  const mentionsDocument = result.toLowerCase().includes('receipt') ||
                          result.toLowerCase().includes('document') ||
                          result.toLowerCase().includes('text') ||
                          result.toLowerCase().includes('paper');
  expect(mentionsDocument).toBeTrue();
});

tap.test('Anthropic Vision: should stop the provider', async () => {
  await anthropicProvider.stop();
});

export default tap.start();