feat: use captain endpoint config in legacy OpenAI base service (#12060)

This PR migrates the legacy OpenAI integration (where users provide
their own API keys) from using hardcoded `https://api.openai.com`
endpoints to use the configurable `CAPTAIN_OPEN_AI_ENDPOINT` from the
captain configuration. This ensures consistency across all OpenAI
integrations in the platform.

## Changes

- Updated `lib/integrations/openai_base_service.rb` to use captain
endpoint config
- Updated `enterprise/app/models/enterprise/concerns/article.rb` to use
captain endpoint config
- Removed unused `enterprise/lib/chat_gpt.rb` class
- Added tests for endpoint configuration behavior

lib/integrations/openai_base_service.rb

@@ -4,7 +4,6 @@ class Integrations::OpenaiBaseService
   # sticking with 120000 to be safe
   # 120000 * 4 = 480,000 characters (rounding off downwards to 400,000 to be safe)
   TOKEN_LIMIT = 400_000
-  API_URL = 'https://api.openai.com/v1/chat/completions'.freeze
   GPT_MODEL = ENV.fetch('OPENAI_GPT_MODEL', 'gpt-4o-mini').freeze
 
   ALLOWED_EVENT_NAMES = %w[rephrase summarize reply_suggestion fix_spelling_grammar shorten expand make_friendly make_formal simplify].freeze
@@ -81,6 +80,12 @@ class Integrations::OpenaiBaseService
     self.class::CACHEABLE_EVENTS.include?(event_name)
   end
 
+  def api_url
+    endpoint = InstallationConfig.find_by(name: 'CAPTAIN_OPEN_AI_ENDPOINT')&.value || 'https://api.openai.com/'
+    endpoint = endpoint.chomp('/')
+    "#{endpoint}/v1/chat/completions"
+  end
+
   def make_api_call(body)
     headers = {
       'Content-Type' => 'application/json',
@@ -88,7 +93,7 @@ class Integrations::OpenaiBaseService
     }
 
     Rails.logger.info("OpenAI API request: #{body}")
-    response = HTTParty.post(API_URL, headers: headers, body: body)
+    response = HTTParty.post(api_url, headers: headers, body: body)
     Rails.logger.info("OpenAI API response: #{response.body}")
 
     return { error: response.parsed_response, error_code: response.code } unless response.success?