Documentation

npm install @alldaytech/multiverse-sdk zod @langchain/core @langchain/anthropic

import { multiverse } from '@alldaytech/multiverse-sdk';

multiverse.configure({
  baseUrl: process.env.MULTIVERSE_URL,
  apiKey: process.env.MULTIVERSE_API_KEY,
});

import { multiverse, wrap } from '@alldaytech/multiverse-sdk';
import { z } from 'zod';

// 1. Wrap your LangChain tools
const bookFlight = wrap(yourBookFlightTool, {
  output: z.object({ id: z.string(), from: z.string(), to: z.string() }),
});

// 2. Define your test, generate scenarios, and run
const test = multiverse.describe({
  name: 'flight-booking-agent',
  task: 'Help the user book a flight',
  agent: async (ctx) => await yourAgent.invoke({ input: ctx.userMessage }),
  conversational: true,
});

const scenarios = await test.generateScenarios({ count: 10 });
const results = await test.run({
  scenarios,
  success: (world) => world.getCollection('bookings').size > 0,
});

console.log(results.passRate);  // e.g. 87
console.log(results.url);       // dashboard link

import { wrap } from '@alldaytech/multiverse-sdk';

const bookFlight = wrap(bookFlightTool, {
  output: BookingSchema,
  effects: (output, world) => [{
    operation: 'create',
    collection: 'bookings',
    id: output.id,
    data: output,
  }],
});

const bookFlight = multiverse.tool({
  // ...
  effects: (output, world) => [{
    operation: 'create',
    collection: 'bookings',
    id: output.bookingId,
    data: output,
  }],
});

// Advanced: read existing state from world before writing
const addPassenger = multiverse.tool({
  // ...
  effects: (output, world) => {
    const booking = world.getCollection('bookings').get(output.bookingId);
    const currentCount = booking?.passengerCount ?? 0;
    return [{
      operation: 'update',
      collection: 'bookings',
      id: output.bookingId,
      data: { passengerCount: currentCount + output.addedCount },
    }];
  },
});

// success() reads from world state
success: (world) => {
  const bookings = world.getCollection('bookings');
  return bookings.size > 0;
}

success: (world, trace, scenario) => {
  // Check world state
  const bookings = world.getCollection('bookings');
  if (bookings.size === 0) return false;

  // Use scenario variables for precise assertions
  if (scenario.variables?.expectedBookings) {
    return bookings.size === scenario.variables.expectedBookings;
  }

  return true;
}

passed = success() === true && qualityScore >= qualityThreshold

const test = multiverse.describe({
  name: 'flight-booking-agent',
  task: 'Book round trip flights for groups of passengers',
  agent: runAgent,
  conversational: true,
  variables: z.object({
    passengerCount: z.number().describe('Total number of passengers to book for'),
  }),
});

const scenarios = await test.generateScenarios({ count: 5 });
const results = await test.run({
  scenarios,
  success: (world, trace, scenario) =>
    world.getCollection('bookings').size === scenario.variables.passengerCount,
});

// Generate scenarios upfront for inspection
const scenarios = await test.generateScenarios({ count: 5 });

// Save for reuse across runs
await test.saveScenarios(scenarios);

// Load saved scenarios (null if none saved yet)
const { scenarios: saved } = await test.getScenarios();

// Run with saved scenarios
await test.run({ scenarios: saved ?? [], success: ... });

// Clear saved scenarios
await test.clearScenarios();

# .github/workflows/eval.yml
- run: npx tsx evals/booking.test.ts
  env:
    MULTIVERSE_API_KEY: ${{ secrets.MULTIVERSE_API_KEY }}
    ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}

await test.run({
  scenarios,
  success: (world) => world.getCollection('bookings').size > 0,
  ci: {
    postToPR: true,    // Post report as PR comment (requires GitHub App)
    printReport: true, // Print report to stdout
  },
});

await test.run({ scenarios, success: ..., skipReport: true });

claude mcp add --transport http multiverse https://multiverse.allday.com/mcp \
  --header "Authorization: Bearer mv_live_..."