[Bug]: Anthropic Authentication Error

[apeixinho]

Is there an existing issue for the same bug?

• I have checked the existing issues.

Describe the bug and reproduction steps

1 - Follow installations steps ...
2 - Get error msg SANDBOX_USER_ID not found
...
3- On windows the following was used for running the docker image:

winpty docker run -it --rm -e SANDBOX_USER_ID=$(id -u)  -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.11-nikolaik -v //var//run//docker.sock://var//run//docker.sock -p 3000:3000 --add-host host.docker.internal:host-gateway --name openhands-app docker.all-hands.dev/all-hands-ai/openhands:0.11

4 - check Anthropic and create a new API key
5 - test with new API key
6 - :( same result ... authentication error

OpenHands Installation

Docker command in README

OpenHands Version

0.11

Operating System

WSL on Windows

Logs, Errors, Screenshots, and Additional Context

File "/app/.venv/lib/python3.12/site-packages/litellm/main.py", line 1715, in completion
   response = anthropic_chat_completions.completion(
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/app/.venv/lib/python3.12/site-packages/litellm/llms/anthropic/chat/handler.py", line 567, in completion
   raise AnthropicError(
litellm.llms.anthropic.common_utils.AnthropicError: {"type":"error","error":{"type":"authentication_error","message":"invalid x-api-key"}}

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
 File "/app/openhands/controller/agent_controller.py", line 156, in start_step_loop
   await self._step()
 File "/app/openhands/controller/agent_controller.py", line 436, in _step
   action = self.agent.step(self.state)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/app/openhands/agenthub/codeact_agent/codeact_agent.py", line 216, in step
   response = self.llm.completion(**params)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/app/.venv/lib/python3.12/site-packages/tenacity/__init__.py", line 336, in wrapped_f
   return copy(f, *args, **kw)
          ^^^^^^^^^^^^^^^^^^^^
 File "/app/.venv/lib/python3.12/site-packages/tenacity/__init__.py", line 475, in __call__
   do = self.iter(retry_state=retry_state)
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/app/.venv/lib/python3.12/site-packages/tenacity/__init__.py", line 376, in iter
   result = action(retry_state)
            ^^^^^^^^^^^^^^^^^^^
 File "/app/.venv/lib/python3.12/site-packages/tenacity/__init__.py", line 398, in <lambda>
   self._add_action_func(lambda rs: rs.outcome.result())
                                    ^^^^^^^^^^^^^^^^^^^
 File "/usr/local/lib/python3.12/concurrent/futures/_base.py", line 449, in result
   return self.__get_result()
          ^^^^^^^^^^^^^^^^^^^
 File "/usr/local/lib/python3.12/concurrent/futures/_base.py", line 401, in __get_result
   raise self._exception
 File "/app/.venv/lib/python3.12/site-packages/tenacity/__init__.py", line 478, in __call__
   result = fn(*args, **kwargs)
            ^^^^^^^^^^^^^^^^^^^
 File "/app/openhands/llm/llm.py", line 195, in wrapper
   resp: ModelResponse = completion_unwrapped(*args, **kwargs)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/app/.venv/lib/python3.12/site-packages/litellm/utils.py", line 1006, in wrapper
   raise e
 File "/app/.venv/lib/python3.12/site-packages/litellm/utils.py", line 896, in wrapper
   result = original_function(*args, **kwargs)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/app/.venv/lib/python3.12/site-packages/litellm/main.py", line 2959, in completion
   raise exception_type(
         ^^^^^^^^^^^^^^^
 File "/app/.venv/lib/python3.12/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 2116, in exception_type
   raise e
 File "/app/.venv/lib/python3.12/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 459, in exception_type
   raise AuthenticationError(
litellm.exceptions.AuthenticationError: litellm.AuthenticationError: AnthropicException - {"type":"error","error":{"type":"authentication_error","message":"invalid x-api-key"}}
2024-10-31 02:15:54,762 - ERROR - Error while running the agent: litellm.AuthenticationError: AnthropicException - {"type":"error","error":{"type":"authentication_error","message":"invalid x-api-key"}}
2024-10-31 02:15:54,770 - ERROR - Traceback (most recent call last):
 File "/app/.venv/lib/python3.12/site-packages/litellm/llms/anthropic/chat/handler.py", line 552, in completion
   response = client.post(
              ^^^^^^^^^^^^
 File "/app/.venv/lib/python3.12/site-packages/litellm/llms/custom_httpx/http_handler.py", line 371, in post
   raise e
 File "/app/.venv/lib/python3.12/site-packages/litellm/llms/custom_httpx/http_handler.py", line 357, in post
   response.raise_for_status()
 File "/app/.venv/lib/python3.12/site-packages/httpx/_models.py", line 763, in raise_for_status
   raise HTTPStatusError(message, request=request, response=self)
httpx.HTTPStatusError: Client error '401 Unauthorized' for url 'https://api.anthropic.com/v1/messages'
For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/401

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
 File "/app/.venv/lib/python3.12/site-packages/litellm/main.py", line 1715, in completion
   response = anthropic_chat_completions.completion(
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/app/.venv/lib/python3.12/site-packages/litellm/llms/anthropic/chat/handler.py", line 567, in completion
   raise AnthropicError(
litellm.llms.anthropic.common_utils.AnthropicError: {"type":"error","error":{"type":"authentication_error","message":"invalid x-api-key"}}

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
 File "/app/openhands/controller/agent_controller.py", line 156, in start_step_loop
   await self._step()
 File "/app/openhands/controller/agent_controller.py", line 436, in _step
   action = self.agent.step(self.state)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/app/openhands/agenthub/codeact_agent/codeact_agent.py", line 216, in step
   response = self.llm.completion(**params)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/app/.venv/lib/python3.12/site-packages/tenacity/__init__.py", line 336, in wrapped_f
   return copy(f, *args, **kw)
          ^^^^^^^^^^^^^^^^^^^^
 File "/app/.venv/lib/python3.12/site-packages/tenacity/__init__.py", line 475, in __call__
   do = self.iter(retry_state=retry_state)
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/app/.venv/lib/python3.12/site-packages/tenacity/__init__.py", line 376, in iter
   result = action(retry_state)
            ^^^^^^^^^^^^^^^^^^^
 File "/app/.venv/lib/python3.12/site-packages/tenacity/__init__.py", line 398, in <lambda>
   self._add_action_func(lambda rs: rs.outcome.result())
                                    ^^^^^^^^^^^^^^^^^^^
 File "/usr/local/lib/python3.12/concurrent/futures/_base.py", line 449, in result
   return self.__get_result()
          ^^^^^^^^^^^^^^^^^^^
 File "/usr/local/lib/python3.12/concurrent/futures/_base.py", line 401, in __get_result
   raise self._exception
 File "/app/.venv/lib/python3.12/site-packages/tenacity/__init__.py", line 478, in __call__
   result = fn(*args, **kwargs)
            ^^^^^^^^^^^^^^^^^^^
 File "/app/openhands/llm/llm.py", line 195, in wrapper
   resp: ModelResponse = completion_unwrapped(*args, **kwargs)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/app/.venv/lib/python3.12/site-packages/litellm/utils.py", line 1006, in wrapper
   raise e
 File "/app/.venv/lib/python3.12/site-packages/litellm/utils.py", line 896, in wrapper
   result = original_function(*args, **kwargs)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/app/.venv/lib/python3.12/site-packages/litellm/main.py", line 2959, in completion
   raise exception_type(
         ^^^^^^^^^^^^^^^
 File "/app/.venv/lib/python3.12/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 2116, in exception_type
   raise e
 File "/app/.venv/lib/python3.12/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 459, in exception_type
   raise AuthenticationError(
litellm.exceptions.AuthenticationError: litellm.AuthenticationError: AnthropicException - {"type":"error","error":{"type":"authentication_error","message":"invalid x-api-key"}}

[apeixinho]

tested with claude-3-5-sonnet since I don't have access to other Anthropic LLMs.

import os
from litellm import completion

# set env
os.environ["ANTHROPIC_API_KEY"] = "sgp_fd1b4edb60bf82b8_583b05eac759334bed1a12be31ff329d91dec2b5"

messages = [{"role": "user", "content": "Hey! how's it going?"}]
response = completion(model="claude-3-5-sonnet-20240620", messages=messages, stream=True)
for chunk in response:
    print(chunk["choices"][0]["delta"]["content"])  # same as openai format

with the following output:

Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.

Traceback (most recent call last):
  File "C:\Python311\Lib\site-packages\litellm\main.py", line 1327, in completion
    response = anthropic_chat_completions.completion(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\litellm\llms\anthropic.py", line 609, in completion
    raise AnthropicError(
litellm.llms.anthropic.AnthropicError: {"type":"error","error":{"type":"authentication_error","message":"invalid x-api-key"}}

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "c:\Users\Student\Documents\testapi.py", line 8, in <module>
    response = completion(model="claude-3-5-sonnet-20240620", messages=messages, stream=True)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\litellm\utils.py", line 3421, in wrapper
    raise e
  File "C:\Python311\Lib\site-packages\litellm\utils.py", line 3314, in wrapper
    result = original_function(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\litellm\main.py", line 2434, in completion
    raise exception_type(
          ^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\litellm\utils.py", line 9972, in exception_type
    raise e
  File "C:\Python311\Lib\site-packages\litellm\utils.py", line 8757, in exception_type
    raise AuthenticationError(
litellm.exceptions.AuthenticationError: AnthropicException - {"type":"error","error":{"type":"authentication_error","message":"invalid x-api-key"}}

[SmartManoj]

Don't share your keys. Could you generate a new key and test it?
If still fails, checkout free Google Gemini models. Click here to get the key.

--

Seems anthropic keys starts with sk-ant-api03. Did you get the key from here?

[neubig]

Yeah, I think the key is invalid for some reason. If it's not working with litellm it also won't work with OpenHands.

[teepean]

I am experiencing the same issue with Claude. I did test Gemini and it worked without problems.

I did a test with openllm and it seems to work as well.

response = completion(model="claude-3-5-sonnet-20241022", messages=messages)
print(response)
ModelResponse(id='chatcmpl-fe784db2-358b-4b02-ad57-ac5d60fa64b4', choices=[Choices(finish_reason='stop', index=0, message=Message(content="I'm doing well, thanks! I'm Claude, an AI assistant. How are you today?", role='assistant', tool_calls=None, function_call=None))], created=1730630182, model='claude-3-5-sonnet-20241022', object='chat.completion', system_fingerprint=None, usage=Usage(completion_tokens=24, prompt_tokens=14, total_tokens=38, completion_tokens_details=None, prompt_tokens_details=PromptTokensDetailsWrapper(audio_tokens=None, cached_tokens=0, text_tokens=None, image_tokens=None), cache_creation_input_tokens=0, cache_read_input_tokens=0))

Last edit: Claude started working after a while so no issues at the moment.