use github copilot in local litellm

[735547951]

1. I have a litellm proxy running locally
   litellm --config config.yaml

2. GitHub Copilot Chat Completion is can get response
   from litellm import completion

model_name = "github_copilot/gpt-4"

messages = [{"role": "user", "content": "Write a Python function to calculate fibonacci numbers"}]

extra_headers = {"editor-version": "vscode/1.85.1", "Copilot-Integration-Id": "vscode-chat"}

try:
response = completion(model=model_name, messages=messages, extra_headers=extra_headers)
print("Copilot output:\n", response)
except Exception as e:
print("Error:", e)

3. https://docs.all-hands.dev/openhands/usage/llms/litellm-proxy
   To use LiteLLM proxy with OpenHands, but error.
   so where should I configure this extra_headers?

Please visit https://github.com/login/device and enter code D7E2-FD37 to authenticate.
06:10:54 - openhands:ERROR: conversation_summary.py:63 - Error generating conversation title: litellm.BadRequestError: Error code: 400 - {'error': {'message': 'litellm.BadRequestError: Github_copilotException - bad request: missing Editor-Version header for IDE auth. Received Model Group=github_copilot/gpt-4\nAvailable Model Group Fallbacks=None', 'type': None, 'param': None, 'code': '400'}}
06:10:54 - openhands:INFO: conversation_summary.py:138 - Generated title using truncation: ？
INFO: 127.0.0.1:52968 - "GET /api/conversations/3046b22a9ebf47d08e0f94b281037c8f HTTP/1.1" 200 OK
06:11:04 - openhands:INFO: standalone_conversation_manager.py:144 - ServerConversation 3046b22a9ebf47d08e0f94b281037c8f connected in 0.0002601146697998047 seconds
06:11:04 - openhands:INFO: standalone_conversation_manager.py:112 - Reusing detached conversation 3046b22a9ebf47d08e0f94b281037c8f
INFO: 127.0.0.1:41822 - "GET /api/conversations/3046b22a9ebf47d08e0f94b281037c8f/vscode-url HTTP/1.1" 200 OK
INFO: 127.0.0.1:41810 - "GET /api/conversations/3046b22a9ebf47d08e0f94b281037c8f/web-hosts HTTP/1.1" 200 OK
Please visit https://github.com/login/device and enter code 1DDE-7254 to authenticate.
06:11:58 - openhands:ERROR: agent_controller.py:365 - [Agent Controller 3046b22a9ebf47d08e0f94b281037c8f] Error while running the agent (session ID: 3046b22a9ebf47d08e0f94b281037c8f): litellm.BadRequestError: Error code: 400 - {'error': {'message': 'litellm.BadRequestError: Github_copilotException - bad request: missing Editor-Version header for IDE auth. Received Model Group=github_copilot/gpt-4\nAvailable Model Group Fallbacks=None', 'type': None, 'param': None, 'code': '400'}}. Traceback: Traceback (most recent call last):
File "/app/.venv/lib/python3.12/site-packages/litellm/llms/openai/openai.py", line 725, in completion
raise e
File "/app/.venv/lib/python3.12/site-packages/litellm/llms/openai/openai.py", line 653, in completion
) = self.make_sync_openai_chat_completion_request(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/litellm/litellm_core_utils/logging_utils.py", line 149, in sync_wrapper
result = func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/litellm/llms/openai/openai.py", line 471, in make_sync_openai_chat_completion_request
raise e
File "/app/.venv/lib/python3.12/site-packages/litellm/llms/openai/openai.py", line 453, in make_sync_openai_chat_completion_request
raw_response = openai_client.chat.completions.with_raw_response.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/openai/_legacy_response.py", line 364, in wrapped
return cast(LegacyAPIResponse[R], func(*args, **kwargs))
^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/openai/_utils/_utils.py", line 287, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/openai/resources/chat/completions/completions.py", line 1150, in create
return self._post(
^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1259, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1047, in request
raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': 'litellm.BadRequestError: Github_copilotException - bad request: missing Editor-Version header for IDE auth. Received Model Group=github_copilot/gpt-4\nAvailable Model Group Fallbacks=None', 'type': None, 'param': None, 'code': '400'}}

[mamoodi]

@enyst in this issue, you mentioned a litellm bug which has now merged. Does that mean this in theory should work?