find a case that cursor can fix but aider can not

[zuozuo]

Issue

I hava a wrong litellm config.yaml

model_list:
  - model_name: "claude-3"
    litellm_params:
      model: ""
      api_key: ${ANTHROPIC_API_KEY}
    model_info:
      provider: "anthropic"
      display_name: "Claude 3"
      description: "Anthropic Claude 3 model"

i want aider help me to solve this, it failed

I have tried muiltiple model: gpt-4o/gemini-2.0-flash-exp/gemini-2.0-flash-thinking-exp
all failed.

But cursor can fix this very easily with all the models above.

(litellm) [mac.new]➜ litellm git:(main) ✗ aider --model gemini/gemini-2.0-flash-exp
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Aider v0.69.1
Model: gemini/gemini-2.0-flash-exp with diff edit format
Git repo: .git with 1 files
Repo-map: using 1024 tokens, auto refresh
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────

/add config.yaml

Added config.yaml to the chat
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
config.yaml

/run litellm -c config.yaml

INFO: Started server process [11559]
INFO: Waiting for application startup.

#------------------------------------------------------------#

'It would help me if you could add...'

https://github.com/BerriAI/litellm/issues/new

#------------------------------------------------------------#

Thank you for using LiteLLM! - Krrish & Ishaan

Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new

LiteLLM: Proxy initialized with Config, Set models:
claude-3
ERROR: Traceback (most recent call last):
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/starlette/routing.py", line 732, in lifespan
async with self.lifespan_context(app) as maybe_state:
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/starlette/routing.py", line 608, in aenter
await self._router.startup()
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/starlette/routing.py", line 709, in startup
await handler()
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/litellm/proxy/proxy_server.py", line 3068, in startup_event
await initialize(**worker_config)
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/litellm/proxy/proxy_server.py", line 2500, in initialize
) = await proxy_config.load_config(router=llm_router, config_file_path=config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/litellm/proxy/proxy_server.py", line 1936, in load_config
router = litellm.Router(
^^^^^^^^^^^^^^^
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/litellm/router.py", line 361, in init
self.set_model_list(model_list)
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/litellm/router.py", line 3910, in set_model_list
self._create_deployment(
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/litellm/router.py", line 3830, in _create_deployment
deployment = self._add_deployment(deployment=deployment)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/litellm/router.py", line 3949, in _add_deployment
) = litellm.get_llm_provider(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/litellm/litellm_core_utils/get_llm_provider_logic.py", line 353, in get_llm_provider
raise e
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/litellm/litellm_core_utils/get_llm_provider_logic.py", line 330, in get_llm_provider
raise litellm.exceptions.BadRequestError( # type: ignore
litellm.exceptions.BadRequestError: litellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. You passed model=claude-3.5-sonnet
Pass model as E.g. For 'Huggingface' inference endpoints pass in completion(model='huggingface/starcoder',..) Learn more: https://docs.litellm.ai/docs/providers

ERROR: Application startup failed. Exiting.
Add command output to the chat? (Y)es/(N)o [Yes]: y
Added 53 lines of output to the chat.
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
config.yaml

Fix that

The error message indicates that the litellm library requires the provider to be specified in the litellm_params. The config.yaml file is missing the provider key under litellm_params.

To fix this, I will add provider: "anthropic" to the litellm_params section of the config.yaml file.

config.yaml

<<<<<<< SEARCH
model: "claude-3.5-sonnet"
api_key: ${ANTHROPIC_API_KEY}
model_info:
provider: "anthropic"

   model: "claude-3.5-sonnet"
   api_key: ${ANTHROPIC_API_KEY}
   provider: "anthropic"
 model_info:
   provider: "anthropic"

REPLACE

After this change, you should be able to run litellm -c config.yaml without the BadRequestError.

Tokens: 3.4k sent, 202 received.
Committing config.yaml before applying edits.
Commit 3cb8f7c fix: Update claude model name to claude-3.5-sonnet
Applied edit to config.yaml

Commit 709d93e fix: Add provider to litellm_params in config
You can use /undo to undo and discard each aider commit.
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
config.yaml

────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
config.yaml

/run litellm -c config.yaml

INFO: Started server process [11807]
INFO: Waiting for application startup.

#------------------------------------------------------------#

'The worst thing about this product is...'

https://github.com/BerriAI/litellm/issues/new

#------------------------------------------------------------#

Thank you for using LiteLLM! - Krrish & Ishaan

Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new

LiteLLM: Proxy initialized with Config, Set models:
claude-3
ERROR: Traceback (most recent call last):
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/starlette/routing.py", line 732, in lifespan
async with self.lifespan_context(app) as maybe_state:
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/starlette/routing.py", line 608, in aenter
await self._router.startup()
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/starlette/routing.py", line 709, in startup
await handler()
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/litellm/proxy/proxy_server.py", line 3068, in startup_event
await initialize(**worker_config)
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/litellm/proxy/proxy_server.py", line 2500, in initialize
) = await proxy_config.load_config(router=llm_router, config_file_path=config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/litellm/proxy/proxy_server.py", line 1936, in load_config
router = litellm.Router(
^^^^^^^^^^^^^^^
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/litellm/router.py", line 361, in init
self.set_model_list(model_list)
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/litellm/router.py", line 3910, in set_model_list
self._create_deployment(
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/litellm/router.py", line 3830, in _create_deployment
deployment = self._add_deployment(deployment=deployment)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/litellm/router.py", line 3949, in _add_deployment
) = litellm.get_llm_provider(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/litellm/litellm_core_utils/get_llm_provider_logic.py", line 353, in get_llm_provider
raise e
File "/Users/yonghuizuo/miniconda3/lib/python3.12/site-packages/litellm/litellm_core_utils/get_llm_provider_logic.py", line 330, in get_llm_provider
raise litellm.exceptions.BadRequestError( # type: ignore
litellm.exceptions.BadRequestError: litellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. You passed model=claude-3.5-sonnet
Pass model as E.g. For 'Huggingface' inference endpoints pass in completion(model='huggingface/starcoder',..) Learn more: https://docs.litellm.ai/docs/providers

ERROR: Application startup failed. Exiting.
Add command output to the chat? (Y)es/(N)o [Yes]:

Version and model info

Aider: v0.69.1