support for gemini thinking model

[narengogi]

Description: (optional)

• Two cases:

1. x-portkey-strict-open-ai-complaince: false the Chain of Thought message is included in the response and separated with \r\n\r\n
   example:

{
    "id": "portkey-2b003c25-7379-4620-a6f0-0b0ba3bc5d51",
    "object": "chat_completion",
    "created": 1736168989,
    "model": "Unknown",
    "provider": "vertex-ai",
    "choices": [
        {
            "message": {
                "role": "assistant",
                "content": "The user is continuing the pattern of simple arithmetic questions, building upon the previous answer.  They are asking for the product of 4 multiplied by itself. I need to perform this multiplication.\r\n\r\nFollowing that same line of thought, 4 * 4 = 16\n"
            },
            "index": 0,
            "finish_reason": "STOP"
        }
    ],
    "usage": {
        "prompt_tokens": 57,
        "completion_tokens": 55,
        "total_tokens": 112
    }
}

2. x-portkey-strict-open-ai-complaince: true only the response is sent, not the CoT message

{
    "id": "portkey-099083cc-2ced-4d5d-8e87-a133d1ac51c2",
    "object": "chat_completion",
    "created": 1736168868,
    "model": "Unknown",
    "provider": "vertex-ai",
    "choices": [
        {
            "message": {
                "role": "assistant",
                "content": "Following that line of thought, 4 * 4 = 16\n"
            },
            "index": 0,
            "finish_reason": "STOP"
        }
    ],
    "usage": {
        "prompt_tokens": 57,
        "completion_tokens": 69,
        "total_tokens": 126
    }
}

Motivation: (optional)

• Why this change is necessary or beneficial

Related Issues: (optional)

• [Feature] Support gemini thinking experimental model #857

[pedroallenrevez]

any news on this?

[narengogi]

Added support for streaming response transforms as well