fix: captain assistant image comprehension (#13390)

# Pull Request Template

## Description

Fixes # (issue)

When we migrated to RubyLLM, images weren't being sent properly in
RubyLLM format to the model, so it did not understand images.

## Type of change

Please delete options that are not relevant.

- [x] Bug fix (non-breaking change which fixes an issue)

## How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.

specs + local testing

Current behaviour on staging:
<img width="772" height="1012" alt="image"
src="https://github.com/user-attachments/assets/7b7d360f-dea4-48af-b20b-ee4c98a38a85"
/>

local testing with fix:
<img width="792" height="1216" alt="image"
src="https://github.com/user-attachments/assets/5ef82452-015e-4bda-a68f-884d00acb014"
/>


## Checklist:

- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules

---------

Co-authored-by: Sojan Jose <sojan@pepalo.com>

enterprise/app/helpers/captain/chat_helper.rb

@@ -10,7 +10,10 @@ module Captain::ChatHelper
 
     add_messages_to_chat(chat)
     with_agent_session do
-      response = chat.ask(conversation_messages.last[:content])
+      last_content = conversation_messages.last[:content]
+      text, attachments = Captain::OpenAiMessageBuilderService.extract_text_and_attachments(last_content)
+
+      response = attachments.any? ? chat.ask(text, with: attachments) : chat.ask(text)
       build_response(response)
     end
   rescue StandardError => e
@@ -68,7 +71,9 @@ module Captain::ChatHelper
 
   def add_messages_to_chat(chat)
     conversation_messages[0...-1].each do |msg|
-      chat.add_message(role: msg[:role].to_sym, content: msg[:content])
+      text, attachments = Captain::OpenAiMessageBuilderService.extract_text_and_attachments(msg[:content])
+      content = attachments.any? ? RubyLLM::Content.new(text, attachments) : text
+      chat.add_message(role: msg[:role].to_sym, content: content)
     end
   end
 

enterprise/app/services/captain/open_ai_message_builder_service.rb

@@ -1,6 +1,15 @@
 class Captain::OpenAiMessageBuilderService
   pattr_initialize [:message!]
 
+  # Extracts text and image URLs from multimodal content array (reverse of generate_content)
+  def self.extract_text_and_attachments(content)
+    return [content, []] unless content.is_a?(Array)
+
+    text_parts = content.select { |part| part[:type] == 'text' }.pluck(:text)
+    image_urls = content.select { |part| part[:type] == 'image_url' }.filter_map { |part| part.dig(:image_url, :url) }
+    [text_parts.join(' ').presence, image_urls]
+  end
+
   def generate_content
     parts = []
     parts << text_part(@message.content) if @message.content.present?