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

Skip to content

Fix cua adapter, add UI-TARS-2 model #592

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
ddupont808 merged 3 commits into from
Nov 18, 2025
Merged

Fix cua adapter, add UI-TARS-2 model #592

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
8284f85
Update params dict
ddupont808 Nov 18, 2025
9ca5083
Add UI-TARS 2
ddupont808 Nov 18, 2025
ebbd5fc
add UI-TARS-2 to docs
ddupont808 Nov 18, 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 README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -216,6 +216,7 @@ The following table shows which capabilities are supported by each model:
| [Gemini CU Preview](https://ai.google.dev/gemini-api/docs/computer-use) | 🖥️ | 🎯 | | 👁️ |
| [InternVL](https://huggingface.co/OpenGVLab/InternVL3_5-1B) | 🖥️ | 🎯 | 🛠️ | 👁️ |
| [UI-TARS](https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B) | 🖥️ | 🎯 | 🛠️ | 👁️ |
| [UI-TARS-2](https://cua.ai/dashboard/vlm-router) | 🖥️ | 🎯 | 🛠️ | 👁️ |
| [OpenCUA](https://huggingface.co/xlangai/OpenCUA-7B) | | 🎯 | | |
| [GTA](https://huggingface.co/HelloKKMe/GTA1-7B) | | 🎯 | | |
| [Holo](https://huggingface.co/Hcompany/Holo1.5-3B) | | 🎯 | | |
Expand Down Expand Up @@ -264,6 +265,7 @@ agent = ComputerAgent(model="moondream3+openai/gpt-4o")
| [Gemini CU Preview](https://ai.google.dev/gemini-api/docs/computer-use) | `gemini-2.5-computer-use-preview` |
| [InternVL](https://huggingface.co/OpenGVLab/InternVL3_5-1B) | `huggingface-local/OpenGVLab/InternVL3_5-{1B,2B,4B,8B,...}` |
| [UI-TARS](https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B) | `huggingface-local/ByteDance-Seed/UI-TARS-1.5-7B` |
| [UI-TARS-2](https://cua.ai/dashboard/vlm-router) | `cua/bytedance/ui-tars-2` |
| [OpenCUA](https://huggingface.co/xlangai/OpenCUA-7B) | `huggingface-local/xlangai/OpenCUA-{7B,32B}` |
| [GTA](https://huggingface.co/HelloKKMe/GTA1-7B) | `huggingface-local/HelloKKMe/GTA1-{7B,32B,72B}` |
| [Holo](https://huggingface.co/Hcompany/Holo1.5-3B) | `huggingface-local/Hcompany/Holo1.5-{3B,7B,72B}` |
Expand Down
12 changes: 12 additions & 0 deletions docs/content/docs/agent-sdk/supported-agents/computer-use-agents.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,6 +99,18 @@ async for _ in agent.run("Open the settings menu and change the theme to dark mo
pass
```

## UI-TARS-2

Next‑generation UI‑TARS via Cua Router:

- `cua/bytedance/ui-tars-2`

```python
agent = ComputerAgent("cua/bytedance/ui-tars-2", tools=[computer])
async for _ in agent.run("Open a browser and search for Python tutorials"):
pass
```

---

CUAs also support direct click prediction. See [Grounding Models](./grounding-models) for details on `predict_click()`.
Expand Down
40 changes: 19 additions & 21 deletions libs/python/agent/agent/adapters/cua_adapter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,30 +19,28 @@ def _normalize_model(self, model: str) -> str:
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,
}
)
params = {
"model": f"openai/{self._normalize_model(kwargs.get("model", ""))}",
"messages": kwargs.get("messages", []),
"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
params = {
"model": f"openai/{self._normalize_model(kwargs.get("model", ""))}",
"messages": kwargs.get("messages", []),
"api_base": self.base_url,
"api_key": self.api_key,
"stream": False,
}

response = await acompletion(**params) # type: ignore

return response

def streaming(self, *args, **kwargs) -> Iterator[GenericStreamingChunk]:
params = dict(kwargs)
Expand Down
2 changes: 2 additions & 0 deletions libs/python/agent/agent/loops/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@
qwen,
uiins,
uitars,
uitars2,
)

__all__ = [
Expand All @@ -37,4 +38,5 @@
"qwen",
"uiins",
"gelato",
"uitars2",
]
2 changes: 1 addition & 1 deletion libs/python/agent/agent/loops/uitars.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -563,7 +563,7 @@ def convert_uitars_messages_to_litellm(messages: Messages) -> List[Dict[str, Any
return litellm_messages


@register_agent(models=r"(?i).*ui-?tars.*")
@register_agent(models=r"(?i).*ui-?tars.*", priority=-1)
class UITARSConfig:
"""
UITARS agent configuration using liteLLM for ByteDance-Seed/UI-TARS-1.5-7B model.
Expand Down
Loading
Loading