schema Customer {
  name: string,
  status: 0.8: "active" | 0.2: "inactive"
}

schema Invoice {
  customer: any of customers,
  amount: decimal in 100..10000,
  status: "draft" | "sent" | "paid",

  assume amount > 0
}

dataset TestData {
  customers: 50 of Customer,
  invoices: 200 of Invoice
}

// Equal probability
status: "draft" | "sent" | "paid"

// Weighted probability
status: 0.6: "paid" | 0.3: "pending" | 0.1: "draft"

// Mixed: unweighted options share remaining probability
status: 0.85: "Active" | "Archived"         // "Archived" gets 15%
category: 0.6: "main" | "side" | "dessert"  // "side" and "dessert" get 20% each

age: int in 18..65
price: decimal in 0.01..999.99
founded: date in 2000..2023

// Decimal with explicit precision
score: decimal(1) in 0..10       // 1 decimal place
amount: decimal(2) in 10..100    // 2 decimal places

line_items: 1..5 of LineItem    // 1-5 items
employees: 100 of Employee       // Exactly 100

schema Invoice {
  issued_date: int in 1..28,
  due_date: int in 1..90,
  status: "draft" | "paid",
  amount: int in 0..10000,

  // Hard constraint
  assume due_date >= issued_date,

  // Conditional constraint
  assume if status == "paid" {
    amount == 0
  }
}

schema Invoice {
  // Reference any customer from the collection
  customer: any of customers,

  // Filtered reference
  active_customer: any of customers where .status == "active"
}

schema LineItem {
  // Inherit currency from parent invoice
  currency: ^base_currency
}

schema Invoice {
  base_currency: "USD" | "GBP" | "EUR",
  line_items: 1..5 of LineItem
}

schema Invoice {
  line_items: 1..10 of LineItem,

  total: sum(line_items.amount),
  item_count: count(line_items),
  avg_price: avg(line_items.unit_price),
  min_price: min(line_items.unit_price),
  max_price: max(line_items.unit_price),
  median_price: median(line_items.unit_price),
  first_item: first(line_items.unit_price),
  last_item: last(line_items.unit_price),
  price_product: product(line_items.unit_price)
}

nickname: string?           // Shorthand: sometimes null
notes: string | null        // Explicit

status: amount_paid >= total ? "paid" : "pending"
grade: score >= 90 ? "A" : score >= 70 ? "B" : "C"

// Pattern matching for multi-way branching
display: match status {
  "pending" => "Awaiting shipment",
  "shipped" => "On the way",
  "delivered" => "Complete"
}

// Returns null if no pattern matches

schema Account {
  type: "personal" | "business",
  companyNumber: string when type == "business"  // Only exists for business accounts
}

schema Order {
  size: "small" | "large",
  items: (size == "large" ? 5..10 : 1..3) of LineItem
}

schema Payment {
  invoice: any of invoices,
  amount: int in 10..500
} then {
  invoice.amount_paid += amount,
  invoice.status = invoice.amount_paid >= invoice.total ? "paid" : "partial"
}

id: unique int in 1000..9999    // No duplicates in collection

schema Person {
  age: private int in 0..105,                    // Generated but excluded from output
  age_bracket: age < 18 ? "minor" : "adult"    // Computed from private field
}
// Output: { "age_bracket": "adult" } -- no "age" field

pitch: [48, 52, 55, 60]   // Cycles in order: 48, 52, 55, 60, 48...
color: ["red", "green", "blue"]

age: gaussian(35, 10, 18, 65)     // mean, stddev, min, max
income: lognormal(10.5, 0.5)      // mu, sigma
wait_time: exponential(0.5)       // rate
daily_orders: poisson(5)          // lambda
conversion: beta(2, 5)            // alpha, beta

created_at: now()                 // Full ISO 8601 timestamp
today_date: today()               // Date only
past: daysAgo(30)                 // 30 days ago
future: daysFromNow(90)           // 90 days from now
random: datetime(2020, 2024)      // Random datetime in range
between: dateBetween("2023-01-01", "2023-12-31")

id: sequence("INV-", 1001)        // "INV-1001", "INV-1002", ...
order_num: sequenceInt("orders")  // 1, 2, 3, ...
prev_value: previous("amount")    // Reference previous record

// Case transformations
upper: uppercase(name)             // "HELLO WORLD"
lower: lowercase(name)             // "hello world"
capitalized: capitalize(name)      // "Hello World"

// Case style conversions
slug: kebabCase(title)             // "hello-world"
snake: snakeCase(title)            // "hello_world"
camel: camelCase(title)            // "helloWorld"

// String manipulation
trimmed: trim("  hello  ")         // "hello"
combined: concat(first, " ", last) // "John Doe"
part: substring(name, 0, 5)        // First 5 characters
replaced: replace(name, "foo", "bar")
len: length(name)                  // String length

// Generate data that violates constraints (for testing error handling)
dataset Invalid violating {
  bad_invoices: 100 of Invoice
}

src/
├── lexer/       # Tokenizer
├── parser/      # Recursive descent parser
├── ast/         # AST node definitions
├── interpreter/ # JSON generator
├── validator/   # Schema validation (Ajv)
├── openapi/     # OpenAPI import support
├── infer/       # Schema inference from data
├── csv/         # CSV input/output formatting
├── ndjson/      # NDJSON (newline-delimited JSON) formatting
├── config/      # Configuration file loading (vague.config.js)
├── logging/     # Debug logging utilities
├── plugins/     # Built-in plugins (faker, issuer, date, regex, http, sql, graphql)
├── spectral/    # OpenAPI linting with Spectral
├── index.ts     # Library exports
└── cli.ts       # CLI entry point