## Bug Description

When using the `/v1/responses` endpoint with streaming enabled, LiteLLM fails with a Pydantic validation error for `ContentPartDoneEvent` because `logprobs` field in `ContentPartDonePartOutputText` lacks a default value.

## Error

``` pydantic_core._pydantic_core.ValidationError: 5 validation errors for ContentPartDoneEvent part.ContentPartDonePartOutputText.logprobs Field required [type=missing, input_value={'type': 'output_text', ...}, input_type=dict] ```

## Root Cause

In `litellm/types/llms/openai.py`, `ContentPartDonePartOutputText` defines:

```python logprobs: Optional[List[OpenAIChatCompletionLogprobsContent]] ```

In Pydantic v2, `Optional[X]` without `= None` means "field is required but accepts None". Since upstream models (Gemini, etc.) do NOT return `logprobs` in their response, Pydantic validation fails.

## Fix

```python logprobs: Optional[List[OpenAIChatCompletionLogprobsContent]] = None ```

## Reproduction

```bash curl -X POST http://localhost:4000/v1/responses \ -H "Authorization: Bearer sk-xxx" \ -H "Content-Type: application/json" \ -d '{"model":"gemini/gemini-2.5-flash","input":"hello","stream":true}' ```

## Environment

- Lit…