Enabled CI editor Assistant to use Claude 3 behind feature flag

What does this MR do and why?

The following MR moves the CIEditorAssistant to match the Claude 3 API prompt messaging API. More specifically, we are trying to match the AI gateway's API to show the following prompt format:

[
  {"role": "user", "content": "Hello there."},
  {"role": "assistant", "content": "Hi, I'm Claude. How can I help you?"},
  {"role": "user", "content": "Can you explain LLMs in plain English?"},
]

Why:

We are migrating Duo features towards relying on Claude 3. This is a large push by the org to accomplish this work.

MR acceptance checklist

Please evaluate this MR against the MR acceptance checklist. It helps you analyze changes to reduce risks in quality, performance, reliability, security, and maintainability.

• Tested the new feature locally to see if it handles correctly the prompt messaging with the claude-3 model.
• Test to make sure we don't have regression issues with the existing models.

Screenshots or screen recordings

Screenshots are required for UI changes, and strongly recommended for all other merge requests.

Before	After	Prompt Format
Feature.enabled?(:ai_claude_3_sonnet)=> true
Feature.enabled?(:ai_claude_3_sonnet) => false

How to set up and validate locally

Numbered steps to set up and validate the change are strongly suggested.

1. In rails console enable the experiment fully

   Feature.enable(:ai_claude_3_sonnet)

2. Visit any group or project member pages such as http://gdk.test:3000. Run the following example message prompt in the Duo Chat UI Please create a deployment configuration for a node.js application.

3. Verify message created is in line with expectations. Here's an example LangSmith trace for the following run of Duo.