class LittleGhost::Usage

Usage makes token accounting consistent across model providers. It keeps input, output, cache, and reasoning counts separate so applications can aggregate them without double-counting.

Providers report uncached input, visible output, cache reads, cache writes, and reasoning separately. Invalid or negative values normalize to zero.

Public Class Methods

new (input_tokens: 0, output_tokens: 0, cache_read_tokens: 0, cache_write_tokens: 0, reasoning_tokens: 0)

Source

# File lib/little_ghost/usage.rb, line 16
def initialize(input_tokens: 0, output_tokens: 0, cache_read_tokens: 0, cache_write_tokens: 0, reasoning_tokens: 0)
  @input_tokens = integer(input_tokens)
  @output_tokens = integer(output_tokens)
  @cache_read_tokens = integer(cache_read_tokens)
  @cache_write_tokens = integer(cache_write_tokens)
  @reasoning_tokens = integer(reasoning_tokens)
end

Normalizes provider token counts; invalid or negative values become zero.

Public Instance Methods

+ (other)

Source

# File lib/little_ghost/usage.rb, line 30
def +(other)
  self.class.new(**FIELDS.to_h { |field| [field, public_send(field) + other.public_send(field)] })
end

Adds two usage values field by field.

to_h ()

Source

# File lib/little_ghost/usage.rb, line 35
def to_h
  FIELDS.to_h { |field| [field, public_send(field)] }.merge(total_tokens: total_tokens)
end

Exposes every field and total_tokens as a hash.

total_tokens ()

Source

# File lib/little_ghost/usage.rb, line 25
def total_tokens
  FIELDS.sum { |field| public_send(field) }
end

Sums every normalized token field.