Support verbosity

Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    ai-chat (0.5.1)
+    ai-chat (0.5.4)
       amazing_print (~> 2.0)
       base64 (~> 0.1, > 0.1.1)
       json (~> 2.0)

README.md

@@ -671,6 +671,15 @@ The `reasoning_effort` parameter guides the model on how many reasoning tokens t
 
 By default, `reasoning_effort` is `nil`, which means no reasoning parameter is sent to the API. For `gpt-5.2` (the default model), this is equivalent to `"none"` reasoning.
 
+## Verbosity
+
+Verbosity determines how many output tokens are generated. Lowering the number of tokens reduces overall latency. While the model's reasoning approach stays mostly the same, the model finds ways to answer more concisely—which can either improve or diminish answer quality, depending on your use case. Here are some scenarios for both ends of the verbosity spectrum:
+
+- High verbosity: Use when you need the model to provide thorough explanations of documents or perform extensive code refactoring.
+- Low verbosity: Best for situations where you want concise answers or simple code generation, such as SQL queries.
+
+The supported values are `:high`, `:medium`, or `:low`. The default value is `:medium` for `gpt-5.2`. **Older models (like `gpt-4.1-nano`) only support `:medium`**.
+
 ## Advanced: Response Details
 
 When you call `generate!` (or later call `get_response` in background mode), the gem stores additional information about the API response:

examples/17_verbosity.rb

@@ -0,0 +1,102 @@
+#!/usr/bin/env ruby
+
+require_relative "../lib/ai-chat"
+require "dotenv"
+Dotenv.load(File.expand_path("../.env", __dir__))
+require "amazing_print"
+
+puts "\n=== AI::Chat Verbosity Tests ==="
+puts
+
+puts "1. Supports verbosity = :low"
+puts "-" * 30
+chat1 = AI::Chat.new
+chat1.verbosity = :low
+chat1.user("How high do planes typically fly?")
+response = chat1.generate![:content]
+puts response
+puts
+puts "Total characters: #{response.length}"
+puts
+
+puts "2. Supports verbosity = :medium"
+puts "-" * 30
+chat2 = AI::Chat.new
+chat2.verbosity = :medium
+chat2.user("How high do planes typically fly?")
+response = chat2.generate![:content]
+puts response
+puts
+puts "Total characters: #{response.length}"
+puts
+
+puts "3. Supports verbosity = :high"
+puts "-" * 30
+chat3 = AI::Chat.new
+chat3.verbosity = :medium
+chat3.user("How high do planes typically fly?")
+response = chat3.generate![:content]
+puts response
+puts
+puts "Total characters: #{response.length}"
+puts
+
+puts "4. Raises error for unsupported verbosity values"
+puts "-" * 30
+chat4 = AI::Chat.new
+chat4.user("How high do planes typically fly?")
+  begin
+    chat4.verbosity = :extreme
+  puts "✗ Failed to raise ArgumentError for invalid verbosity: #{chat4.verbosity}"
+rescue ArgumentError => e
+  puts "✓ Raises Argument error correctly: #{e.message}"
+end
+puts
+
+puts
+puts "5. Supports verbosity with Structured Outputs"
+puts "-" * 30
+path = "my_schemas/test.json"
+File.delete(path) if File.exist?(path)
+AI::Chat.generate_schema!("A user with full name (required), first_name (required), last_name (required), coolness_level (score between 0-10 representing how cool the user sounds), coolness_reasoning (the explanation of the coolness_leve)", location: path, api_key: ENV["OPENAI_API_KEY"])
+
+chat5 = AI::Chat.new
+chat5.verbosity = :low
+chat5.schema_file = path
+chat5.system("Extract the profile information from the user message. Describe it like a 90's robot.")
+chat5.user("My name is Bryan. I like to skateboard and be cool. I'm seventeen and a quarter. You can reach me at bryan@example.com.")
+puts chat5.last[:content]
+puts 
+begin
+  response = chat5.generate![:content]
+  puts "✓ Generates structured output response with verbosity"
+rescue => e
+  puts "✗ Failed to generate structured output response with verbosity: #{e.message}"
+end
+puts
+
+puts "6. Supports verbosity = :medium for gpt-4.1-nano"
+puts "-" * 30
+chat6 = AI::Chat.new
+chat6.model = "gpt-4.1-nano"
+chat6.verbosity = :medium
+chat6.user("How high do planes typically fly?")
+response = chat6.generate![:content]
+puts response
+puts
+puts "Total characters: #{response.length}"
+puts
+
+puts "7. Fails verbosity = :low for gpt-4.1-nano"
+puts "-" * 30
+chat7 = AI::Chat.new
+chat7.model = "gpt-4.1-nano"
+chat7.verbosity = :low
+chat7.user("How high do planes typically fly?")
+begin
+  response = chat7.generate![:content]
+  puts "✗ Failed to raise error when setting :low verbosity on unsupported model."
+rescue OpenAI::Errors::BadRequestError => e
+  puts "✓ Successfully raises error on for unsupported verbosity for older model: #{e.message}"
+end
+puts

examples/all.rb

@@ -53,3 +53,9 @@
 
 # Proxy
 require_relative "15_proxy"
+
+# Get items
+require_relative "16_get_items"
+
+# Verbosity
+require_relative "17_verbosity"

lib/ai/chat.rb

@@ -19,7 +19,7 @@ module AI
   class Chat
     # :reek:Attribute
     attr_accessor :background, :code_interpreter, :conversation_id, :image_generation, :image_folder, :messages, :model, :reasoning_effort, :web_search
-    attr_reader :client, :last_response_id, :proxy, :schema, :schema_file
+    attr_reader :client, :last_response_id, :proxy, :schema, :schema_file, :verbosity
 
     BASE_PROXY_URL = "https://prepend.me/api.openai.com/v1"
 
@@ -34,6 +34,7 @@ def initialize(api_key: nil, api_key_env_var: "OPENAI_API_KEY")
       @image_generation = false
       @image_folder = "./images"
       @api_key_validated = false
+      @verbosity = :medium
     end
 
     def self.generate_schema!(description, location: "schema.json", api_key: nil, api_key_env_var: "OPENAI_API_KEY", proxy: false)
@@ -183,6 +184,14 @@ def schema_file=(path)
       self.schema = content
     end
 
+    def verbosity=(value)
+      if ["low", "medium", "high"].include?(value.to_s)
+        @verbosity = value.to_sym
+      else
+        raise ArgumentError, "Invalid verbosity value:'#{value}'. Must be one of :low, :medium, :high."
+      end
+    end
+
     def last
       messages.last
     end
@@ -221,6 +230,7 @@ def inspectable_attributes
       attrs << [:@web_search, @web_search] if @web_search
       attrs << [:@schema, @schema] if @schema
       attrs << [:@schema_file, @schema_file] if @schema_file
+      attrs << [:@verbosity, verbosity] if verbosity
 
       attrs
     end
@@ -274,6 +284,7 @@ def create_response
 
       create_conversation unless conversation_id
       parameters[:conversation] = conversation_id
+      parameters[:text] = (parameters[:text] || {}).merge(verbosity: verbosity) if verbosity
 
       messages_to_send = prepare_messages_for_api
       parameters[:input] = strip_responses(messages_to_send) unless messages_to_send.empty?