Gemini doesn't work well when trying to output json objects. Using it
to output raw json strings with complex, multi-line structures
requires more intense clean-up of raw json string for parsing
GPT-4o-mini is cheaper, smarter and can hold more context than
GPT-3.5-turbo. In production, we also default to gpt-4o-mini, so makes
sense to upgrade defaults and tests to work with it
Previously was assuming the system prompt is being always passed as
the first message. So expected there to be at least 2 messages in logs.
This broke chat actors querying with single long non system message.
A more robust way to extract system prompt is via the message role
instead
