Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Add "cua/" LLM provider #506

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
f-trycua merged 3 commits into from
Nov 13, 2025
Merged

Add "cua/" LLM provider #506

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4abae2f
Add "cua/" LLM provider
ddupont808 Oct 23, 2025
cfedce2
adjust url
ddupont808 Oct 23, 2025
ac15112
add a more specific env CUA_INFERENCE_API_KEY
ddupont808 Nov 11, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions libs/python/agent/agent/adapters/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
Adapters package for agent - Custom LLM adapters for LiteLLM
"""

from .cua_adapter import CUAAdapter
from .huggingfacelocal_adapter import HuggingFaceLocalAdapter
from .human_adapter import HumanAdapter
from .mlxvlm_adapter import MLXVLMAdapter
Expand All @@ -10,4 +11,5 @@
"HuggingFaceLocalAdapter",
"HumanAdapter",
"MLXVLMAdapter",
"CUAAdapter",
]
73 changes: 73 additions & 0 deletions libs/python/agent/agent/adapters/cua_adapter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,73 @@
import os
from typing import Any, AsyncIterator, Iterator

from litellm import acompletion, completion
from litellm.llms.custom_llm import CustomLLM
from litellm.types.utils import GenericStreamingChunk, ModelResponse


class CUAAdapter(CustomLLM):
def __init__(self, base_url: str | None = None, api_key: str | None = None, **_: Any):
super().__init__()
self.base_url = base_url or os.environ.get("CUA_BASE_URL") or "https://inference.cua.ai/v1"
self.api_key = api_key or os.environ.get("CUA_INFERENCE_API_KEY") or os.environ.get("CUA_API_KEY")

def _normalize_model(self, model: str) -> str:
# Accept either "cua/<model>" or raw "<model>"
return model.split("/", 1)[1] if model and model.startswith("cua/") else model

def completion(self, *args, **kwargs) -> ModelResponse:
params = dict(kwargs)
inner_model = self._normalize_model(params.get("model", ""))
params.update(
{
"model": f"openai/{inner_model}",
"api_base": self.base_url,
"api_key": self.api_key,
"stream": False,
}
)
return completion(**params) # type: ignore

async def acompletion(self, *args, **kwargs) -> ModelResponse:
params = dict(kwargs)
inner_model = self._normalize_model(params.get("model", ""))
params.update(
{
"model": f"openai/{inner_model}",
"api_base": self.base_url,
"api_key": self.api_key,
"stream": False,
}
)
return await acompletion(**params) # type: ignore

def streaming(self, *args, **kwargs) -> Iterator[GenericStreamingChunk]:
params = dict(kwargs)
inner_model = self._normalize_model(params.get("model", ""))
params.update(
{
"model": f"openai/{inner_model}",
"api_base": self.base_url,
"api_key": self.api_key,
"stream": True,
}
)
# Yield chunks directly from LiteLLM's streaming generator
for chunk in completion(**params): # type: ignore
yield chunk # type: ignore

async def astreaming(self, *args, **kwargs) -> AsyncIterator[GenericStreamingChunk]:
params = dict(kwargs)
inner_model = self._normalize_model(params.get("model", ""))
params.update(
{
"model": f"openai/{inner_model}",
"api_base": self.base_url,
"api_key": self.api_key,
"stream": True,
}
)
stream = await acompletion(**params) # type: ignore
async for chunk in stream: # type: ignore
yield chunk # type: ignore
8 changes: 3 additions & 5 deletions libs/python/agent/agent/agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,11 +23,7 @@
import litellm.utils
from litellm.responses.utils import Usage

from .adapters import (
HuggingFaceLocalAdapter,
HumanAdapter,
MLXVLMAdapter,
)
from .adapters import CUAAdapter, HuggingFaceLocalAdapter, HumanAdapter, MLXVLMAdapter
from .callbacks import (
BudgetManagerCallback,
ImageRetentionCallback,
Expand Down Expand Up @@ -272,10 +268,12 @@ def __init__(
)
human_adapter = HumanAdapter()
mlx_adapter = MLXVLMAdapter()
cua_adapter = CUAAdapter()
litellm.custom_provider_map = [
{"provider": "huggingface-local", "custom_handler": hf_adapter},
{"provider": "human", "custom_handler": human_adapter},
{"provider": "mlx", "custom_handler": mlx_adapter},
{"provider": "cua", "custom_handler": cua_adapter},
]
litellm.suppress_debug_info = True

Expand Down
Loading