Fix Anthropic client to permit appropriate response handling
What does this MR do and why?
Fix Anthropic client to permit appropriate response handling. The Anthropic documentation mentions to formulate your prompt with \n\nHuman: #{prompt}\n\nAssistant:
. The Anthropic client did not do this currently, which resulted in the API not responding correctly and a Net::Read error being raised.
This MR ensures the formatting is present in the prompt so that the request is handled appropriately. If the appropriate formatting is already present, it won't add it again.
How to set up and validate locally
Assuming you have Anthropic credentials and an environment that can make a request with the Anthropic client, this should allow the request to be completed successfully.
MR acceptance checklist
This checklist encourages us to confirm any changes have been analyzed to reduce risks in quality, performance, reliability, security, and maintainability.
-
I have evaluated the MR acceptance checklist for this MR.