thinking/ Reasoning not working for openai models with litellm proxy

[jainl03]

When passing thinking or reasoning_effort parameter to o1, o3 and gpt models. Either it's not working and throwing error or it doesn't give Thinking and Reasoning response in Response payload with litellm proxy.

We are getting reasoning_token but there is no reasoning response in response payload.
Payload without error but with no Thinking and reasoning response:

**reasoning_effort:**
Request Payload:
{
    "model": "o3-mini",
    "messages": [
        {
            "role": "user",
            "content": "tell me about pfizer"
        }
    ],
    "reasoning_effort":"high"
}
Respones Payload:
{
    "id": "chatcmpl-Cbout8ovhe0k6hk6FUPgGXeOmnbTC",
    "created": 1763129895,
    "model": "azure/o3-mini-2025-01-31",
    "object": "chat.completion",
    "system_fingerprint": "fp_52e4403cb8",
    "choices": [
        {
            "finish_reason": "stop",
            "index": 0,
            "message": {
                "content": "****",
                "role": "assistant",
                "annotations": []
            },
            "provider_specific_fields": {
                "content_filter_results": {
                    "hate": {
                        "filtered": false,
                        "severity": "safe"
                    },
                    "protected_material_code": {
                        "filtered": false,
                        "detected": false
                    },
                    "protected_material_text": {
                        "filtered": false,
                        "detected": false
                    },
                    "self_harm": {
                        "filtered": false,
                        "severity": "safe"
                    },
                    "sexual": {
                        "filtered": false,
                        "severity": "safe"
                    },
                    "violence": {
                        "filtered": false,
                        "severity": "safe"
                    }
                }
            }
        }
    ],
    "usage": {
        "completion_tokens": 1732,
        "prompt_tokens": 11,
        "total_tokens": 1743,
        "completion_tokens_details": {
            "accepted_prediction_tokens": 0,
            "audio_tokens": 0,
            **"reasoning_tokens": 1344,**
            "rejected_prediction_tokens": 0
        },
        "prompt_tokens_details": {
            "audio_tokens": 0,
            "cached_tokens": 0
        }
    },
    "prompt_filter_results": [
        {
            "prompt_index": 0,
            "content_filter_results": {
                "hate": {
                    "filtered": false,
                    "severity": "safe"
                },
                "jailbreak": {
                    "filtered": false,
                    "detected": false
                },
                "self_harm": {
                    "filtered": false,
                    "severity": "safe"
                },
                "sexual": {
                    "filtered": false,
                    "severity": "safe"
                },
                "violence": {
                    "filtered": false,
                    "severity": "safe"
                }
            }
        }
    ]
}