Class: TouringTest::Agent

Inherits:
Object
  • Object
show all
Defined in:
lib/touring_test/agent.rb

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(driver, instruction, max_steps: 15) ⇒ Agent

Returns a new instance of Agent.



12
13
14
15
16
17
18
19
 
# File 'lib/touring_test/agent.rb', line 12

def initialize(driver, instruction, max_steps: 15)
  @driver = driver
  @instruction = instruction
  @api_key = ENV.fetch("GEMINI_API_KEY")
  @max_steps = max_steps
  @conversation_history = []
  @log_file = setup_log_file
end

Instance Attribute Details

#driver ⇒ Object (readonly)

Returns the value of attribute driver.



10
11
12
 
# File 'lib/touring_test/agent.rb', line 10

def driver
  @driver
end

#instruction ⇒ Object (readonly)

Returns the value of attribute instruction.



10
11
12
 
# File 'lib/touring_test/agent.rb', line 10

def instruction
  @instruction
end

Instance Method Details

#run ⇒ Object 



21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
 
# File 'lib/touring_test/agent.rb', line 21

def run
  # Initial turn
  puts "[User] #{instruction}"
  screenshot_path, url = driver.capture_screenshot_and_url
  user_turn = build_user_turn(instruction, screenshot_path, url)
  @conversation_history << user_turn

  step_count = 0
  loop do
    if step_count >= @max_steps
      raise "Agent exceeded maximum steps (#{@max_steps}). Halting execution to prevent infinite loop."
    end
    step_count += 1
    puts "[Debug] === API Request Loop Iteration #{step_count}/#{@max_steps} ===" if debug?

    response = make_api_request(@conversation_history)
    model_turn = response.dig("candidates", 0, "content")
    @conversation_history << model_turn

    parts = model_turn["parts"]
    function_calls = parts.select { |part| part["functionCall"] }

    puts "[Debug] Found #{function_calls.size} function calls in response" if debug?
    break if function_calls.empty?

    function_responses = []
    function_calls.each_with_index do |part, idx|
      function_call = part["functionCall"]
      next if function_call.nil?

      puts "[Debug] Processing function call #{idx + 1}/#{function_calls.size}: #{function_call['name']}" if debug?
      driver.execute_action(function_call)
      screenshot_path, url = driver.capture_screenshot_and_url
      puts "[Debug] Screenshot saved to: #{screenshot_path}" if debug?

      # Each function response includes its own screenshot
      function_responses << {
        "functionResponse" => {
          "name" => function_call["name"],
          "response" => { "url" => url }
        }
      }
      function_responses << {
        "inline_data" => {
          "mime_type" => "image/png",
          "data" => encode_image(screenshot_path)
        }
      }
    end

    user_turn = { "role" => "user", "parts" => function_responses }
    @conversation_history << user_turn
  end
end