Extending video is not working while using proxy

#### Environment details

- Programming language: Python
- OS: Windows
- Language runtime version: Python3.12
- Package version: google-genai==1.57.0 and it's dependencies

#### Steps to reproduce
just run the code
``` python
import os
import time

import httpx
import requests
from dotenv import load_dotenv
from google import genai
from google.genai import types
from google.genai.types import Video

if __name__ == '__main__':
load_dotenv()
api_key = os.getenv("GENAI_API_KEY")
proxy = os.getenv("GRPC_PROXY")
genai_client = genai.Client(
api_key=api_key,
http_options=types.HttpOptions(
httpx_client=httpx.Client(proxy=proxy)
)
)

# Generate a video via Veo
source = types.GenerateVideosSource(
prompt="Upbeat and adorable background music throughout the video. A close-up shot focusing on the face of a cute lynx-point Ragdoll cat, with its big, bright blue eyes staring at the camera curiously, then tilting its head adorably toward the lens."
)
config = types.GenerateVideosConfig(
duration_seconds=4,
aspect_ratio="16:9",
resolution="720p",
negative_prompt="nsfw",
)

operation: types.GenerateVideosOperation = genai_client.models.generate_videos(
model="veo-3.1-fast-generate-preview",
source=source,
config=config
)
while not operation.done:
print("Waiting for video generation to complete...")
time.sleep(10)
operation = genai_client.operations.get(operation)

generated_video = operation.response.generated_videos[0] if operation.response.generated_videos else None
# download the video directly via proxy and save
if generated_video:
video = generated_video.video
download_url = video.uri
actual_download_url = f'{download_url}&key={api_key}'
rsp = requests.get(actual_download_url, proxies={
'http': proxy,
'https': proxy
})
video_bytes = rsp.content
video = Video(uri=download_url, video_bytes=video_bytes)
video.save("cat-gen.mp4")

# extend the video
# re-create the config
config = types.GenerateVideosConfig(
duration_seconds=4,
aspect_ratio="16:9",
resolution="720p",
negative_prompt="nsfw",
)

# request for extend (will crash here)
operation: types.GenerateVideosOperation = genai_client.models.generate_videos(
model="veo-3.1-fast-generate-preview",
video=operation.response.generated_videos[0].video,
prompt="Upbeat and adorable background music throughout the video. A close-up shot focusing on the face of a cute lynx-point Ragdoll cat, with its big, bright blue eyes staring at the camera curiously, then tilting its head adorably toward the lens. and eyes blinking.",
config=config
)

while not operation.done:
print("Waiting for video generation to complete...")
time.sleep(10)
operation = genai_client.operations.get(operation)

generated_video = operation.response.generated_videos[0] if operation.response.generated_videos else None

# download the video directly via proxy and save
if generated_video:
video = generated_video.video
download_url = video.uri
actual_download_url = f'{download_url}&key={api_key}'
rsp = requests.get(actual_download_url, proxies={
'http': proxy,
'https': proxy
})
video_bytes = rsp.content
video = Video(uri=download_url, video_bytes=video_bytes)
video.save("cat-gen-extend.mp4")

```

Here is the .env look like:
```python
# this is my proxy location, which work well in video generation
GRPC_PROXY='http://user:password@192.168.24.100:6666'
# gemini api token
GENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxxxxxx
```

the first generation is downloaded successfully, but there is an error while trying to extend the video passing the first object via genai client.
```
Traceback (most recent call last):
File "C:\Program Files\JetBrains\PyCharm Community Edition 2023.3.4\plugins\python-ce\helpers\pydev\pydevd.py", line 1534, in _exec
pydev_imports.execfile(file, globals, locals) # execute the script
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\JetBrains\PyCharm Community Edition 2023.3.4\plugins\python-ce\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "C:\code\repository-python\dify-official-plugins\tools\gemini_video\test\test_gen.py", line 69, in
operation: types.GenerateVideosOperation = genai_client.models.generate_videos(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\code\repository-python\dify-official-plugins\tools\gemini_video\venv\Lib\site-packages\google\genai\models.py", line 5725, in generate_videos
return self._generate_videos(
^^^^^^^^^^^^^^^^^^^^^^
File "C:\code\repository-python\dify-official-plugins\tools\gemini_video\venv\Lib\site-packages\google\genai\models.py", line 5082, in _generate_videos
response = self._api_client.request(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\code\repository-python\dify-official-plugins\tools\gemini_video\venv\Lib\site-packages\google\genai\_api_client.py", line 1375, in request
response = self._request(http_request, http_options, stream=False)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\code\repository-python\dify-official-plugins\tools\gemini_video\venv\Lib\site-packages\google\genai\_api_client.py", line 1211, in _request
return self._retry(self._request_once, http_request, stream) # type: ignore[no-any-return]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\code\repository-python\dify-official-plugins\tools\gemini_video\venv\Lib\site-packages\tenacity\__init__.py", line 477, in __call__
do = self.iter(retry_state=retry_state)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\code\repository-python\dify-official-plugins\tools\gemini_video\venv\Lib\site-packages\tenacity\__init__.py", line 378, in iter
result = action(retry_state)
^^^^^^^^^^^^^^^^^^^
File "C:\code\repository-python\dify-official-plugins\tools\gemini_video\venv\Lib\site-packages\tenacity\__init__.py", line 420, in exc_check
raise retry_exc.reraise()
^^^^^^^^^^^^^^^^^^^
File "C:\code\repository-python\dify-official-plugins\tools\gemini_video\venv\Lib\site-packages\tenacity\__init__.py", line 187, in reraise
raise self.last_attempt.result()
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\william\AppData\Local\Programs\Python\Python312\Lib\concurrent\futures\_base.py", line 449, in result
return self.__get_result()
^^^^^^^^^^^^^^^^^^^
File "C:\Users\william\AppData\Local\Programs\Python\Python312\Lib\concurrent\futures\_base.py", line 401, in __get_result
raise self._exception
File "C:\code\repository-python\dify-official-plugins\tools\gemini_video\venv\Lib\site-packages\tenacity\__init__.py", line 480, in __call__
result = fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "C:\code\repository-python\dify-official-plugins\tools\gemini_video\venv\Lib\site-packages\google\genai\_api_client.py", line 1188, in _request_once
errors.APIError.raise_for_response(response)
File "C:\code\repository-python\dify-official-plugins\tools\gemini_video\venv\Lib\site-packages\google\genai\errors.py", line 121, in raise_for_response
cls.raise_error(response.status_code, response_json, response)
File "C:\code\repository-python\dify-official-plugins\tools\gemini_video\venv\Lib\site-packages\google\genai\errors.py", line 146, in raise_error
raise ClientError(status_code, response_json, response)
google.genai.errors.ClientError: 400 INVALID_ARGUMENT. {'error': {'code': 400, 'message': 'Your use case is currently not supported. Please refer to Gemini API documentation for current model offering.', 'status': 'INVALID_ARGUMENT'}}
```

I’m using direct download via the requests library because of issue #1946, and I haven’t been able to resolve this problem yet.

According to the official documentation, I used the Video instance returned from the first generation as the video parameter (matching the approach in the [official code example](https://ai.google.dev/gemini-api/docs/video?example=dialogue#extending_veo_videos)), but it still doesn’t work.
I also investigated the root cause by checking the google/genai/models.py file and found that the code simply creates a new Video object with uri and mime_type like this:

Unfortunately, the genai tool will not return mime_type in the first generation, and even I put `video/mp4` in it, the error still remains.