Add an exception for GoogleGemini and GoogleVertexAI when using the OutputFixingParser

[carlows]

Connected to #1015

As described in the README, the google APIs have a different format for their LLMs:

messages = [
  { role: "system", content: "You are a helpful assistant." },
  { role: "user", content: "What's the weather like today?" }
  # Google Gemini and Google VertexAI expect messages in a different format:
  # { role: "user", parts: [{ text: "why is the sky blue?" }]}
]
response = llm.chat(messages: messages)
chat_completion = response.chat_completion

And the OutputFixingParser class doesn't work with Gemini 2.5-flash, as it throws the following error:

{"error"=>{"code"=>400, "message"=>"Invalid JSON payload received. Unknown name "content" at 'contents[0]': Cannot find field.", "status"=>"INVALID_ARGUMENT", "details"=>[{"@type"=>"type.googleapis.com/google.rpc.BadRequest", "fieldViolations"=>[{"field"=>"contents[0]", "description"=>"Invalid JSON payload received. Unknown name "content" at 'contents[0]': Cannot find field."}]}]}}

The goal of this PR is to use the correct format instead.