Fix cohere message param transform

[narengogi]

#563

Verified by making calls to the llm

[b4s36t4]

curl --request POST \
  --url <gateway_url>/v1/chat/completions \
  --header 'authorization: skhXH9Bzk62KcSKmioNF4ueyCRq84O094rv5kN5l' \
  --header 'content-type: application/json' \
  --header 'x-portkey-provider: cohere' \
  --data '{
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    },
    {
      "role": "assistant",
      "content": "Hi there! How can I help you today?\n\nIf you would like, you can skip the small talk and get right to what you need assistance with. I'\''m a chatbot trained to be helpful, polite, and inclusive. \n\nHow can I help you today?"
    },
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Tell me a story"
        },
        {
          "type": "text",
          "text": "about cinderella"
        }
      ]
    }
  ],
  "max_tokens": 10,
  "stream": false
}'

Tested and working as expected.

[b4s36t4]

@narengogi, for the cohere complete response transformer we have a constant finish_reason which is wrong, can you please also fix that to use response.finish_reason? Thanks!