cua-agent 0.4.30__py3-none-any.whl → 0.4.32__py3-none-any.whl

agent/adapters/huggingfacelocal_adapter.py

@@ -15,54 +15,31 @@ try:
 except ImportError:
     HF_AVAILABLE = False
 
+from .models import load_model as load_model_handler
 
 class HuggingFaceLocalAdapter(CustomLLM):
     """HuggingFace Local Adapter for running vision-language models locally."""
     
-    def __init__(self, device: str = "auto", **kwargs):
+    def __init__(self, device: str = "auto", trust_remote_code: bool = False, **kwargs):
         """Initialize the adapter.
         
         Args:
             device: Device to load model on ("auto", "cuda", "cpu", etc.)
+            trust_remote_code: Whether to trust remote code
             **kwargs: Additional arguments
         """
         super().__init__()
         self.device = device
-        self.models = {}  # Cache for loaded models
-        self.processors = {}  # Cache for loaded processors
+        self.trust_remote_code = trust_remote_code
+        # Cache for model handlers keyed by model_name
+        self._handlers: Dict[str, Any] = {}
         self._executor = ThreadPoolExecutor(max_workers=1)  # Single thread pool
         
-    def _load_model_and_processor(self, model_name: str):
-        """Load model and processor if not already cached.
-        
-        Args:
-            model_name: Name of the model to load
-            
-        Returns:
-            Tuple of (model, processor)
-        """
-        if model_name not in self.models:
-            # Load model
-            model = AutoModelForImageTextToText.from_pretrained(
-                model_name,
-                torch_dtype=torch.float16,
-                device_map=self.device,
-                attn_implementation="sdpa"
-            )
-            
-            # Load processor
-            processor = AutoProcessor.from_pretrained(
-                model_name,
-                min_pixels=3136,
-                max_pixels=4096 * 2160,
-                device_map=self.device
-            )
-            
-            # Cache them
-            self.models[model_name] = model
-            self.processors[model_name] = processor
-            
-        return self.models[model_name], self.processors[model_name]
+    def _get_handler(self, model_name: str):
+        """Get or create a model handler for the given model name."""
+        if model_name not in self._handlers:
+            self._handlers[model_name] = load_model_handler(model_name=model_name, device=self.device, trust_remote_code=self.trust_remote_code)
+        return self._handlers[model_name]
     
     def _convert_messages(self, messages: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
         """Convert OpenAI format messages to HuggingFace format.
@@ -133,41 +110,13 @@ class HuggingFaceLocalAdapter(CustomLLM):
         if ignored_kwargs:
             warnings.warn(f"Ignoring unsupported kwargs: {ignored_kwargs}")
         
-        # Load model and processor
-        model, processor = self._load_model_and_processor(model_name)
-        
         # Convert messages to HuggingFace format
         hf_messages = self._convert_messages(messages)
         
-        # Apply chat template and tokenize
-        inputs = processor.apply_chat_template(
-            hf_messages,
-            add_generation_prompt=True,
-            tokenize=True,
-            return_dict=True,
-            return_tensors="pt"
-        )
-        
-        # Move inputs to the same device as model
-        inputs = inputs.to(model.device)
-        
-        # Generate response
-        with torch.no_grad():
-            generated_ids = model.generate(**inputs, max_new_tokens=max_new_tokens)
-            
-        # Trim input tokens from output
-        generated_ids_trimmed = [
-            out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
-        ]
-        
-        # Decode output
-        output_text = processor.batch_decode(
-            generated_ids_trimmed, 
-            skip_special_tokens=True, 
-            clean_up_tokenization_spaces=False
-        )
-        
-        return output_text[0] if output_text else ""
+        # Delegate to model handler
+        handler = self._get_handler(model_name)
+        generated_text = handler.generate(hf_messages, max_new_tokens=max_new_tokens)
+        return generated_text
     
     def completion(self, *args, **kwargs) -> ModelResponse:
         """Synchronous completion method.

agent/adapters/models/__init__.py

@@ -0,0 +1,33 @@
+from typing import Optional
+
+try:
+    from transformers import AutoConfig
+    HF_AVAILABLE = True
+except ImportError:
+    HF_AVAILABLE = False
+
+from .generic import GenericHFModel
+from .opencua import OpenCUAModel
+from .qwen2_5_vl import Qwen2_5_VLModel
+from .internvl import InternVLModel
+
+def load_model(model_name: str, device: str = "auto", trust_remote_code: bool = False):
+    """Factory function to load and return the right model handler instance.
+    
+    - If the underlying transformers config class matches OpenCUA, return OpenCUAModel
+    - Otherwise, return GenericHFModel
+    """
+    if not HF_AVAILABLE:
+        raise ImportError(
+            "HuggingFace transformers dependencies not found. Install with: pip install \"cua-agent[uitars-hf]\""
+        )
+    cfg = AutoConfig.from_pretrained(model_name, trust_remote_code=trust_remote_code)
+    cls = cfg.__class__.__name__
+    print(f"cls: {cls}")
+    if "OpenCUA" in cls:
+        return OpenCUAModel(model_name=model_name, device=device, trust_remote_code=trust_remote_code)
+    elif "Qwen2_5_VL" in cls:
+        return Qwen2_5_VLModel(model_name=model_name, device=device, trust_remote_code=trust_remote_code)
+    elif "InternVL" in cls:
+        return InternVLModel(model_name=model_name, device=device, trust_remote_code=trust_remote_code)
+    return GenericHFModel(model_name=model_name, device=device, trust_remote_code=trust_remote_code)

agent/adapters/models/generic.py

@@ -0,0 +1,75 @@
+from typing import List, Dict, Any, Optional
+
+# Hugging Face imports are local to avoid hard dependency at module import
+try:
+    import torch  # type: ignore
+    from transformers import AutoModel, AutoProcessor  # type: ignore
+    HF_AVAILABLE = True
+except Exception:
+    HF_AVAILABLE = False
+
+
+class GenericHFModel:
+    """Generic Hugging Face vision-language model handler.
+    Loads an AutoModelForImageTextToText and AutoProcessor and generates text.
+    """
+
+    def __init__(self, model_name: str, device: str = "auto", trust_remote_code: bool = False) -> None:
+        if not HF_AVAILABLE:
+            raise ImportError(
+                "HuggingFace transformers dependencies not found. Install with: pip install \"cua-agent[uitars-hf]\""
+            )
+        self.model_name = model_name
+        self.device = device
+        self.model = None
+        self.processor = None
+        self.trust_remote_code = trust_remote_code
+        self._load()
+
+    def _load(self) -> None:
+        # Load model
+        self.model = AutoModel.from_pretrained(
+            self.model_name,
+            torch_dtype=torch.float16,
+            device_map=self.device,
+            attn_implementation="sdpa",
+            trust_remote_code=self.trust_remote_code,
+        )
+        # Load processor
+        self.processor = AutoProcessor.from_pretrained(
+            self.model_name,
+            min_pixels=3136,
+            max_pixels=4096 * 2160,
+            device_map=self.device,
+            trust_remote_code=self.trust_remote_code,
+        )
+
+    def generate(self, messages: List[Dict[str, Any]], max_new_tokens: int = 128) -> str:
+        """Generate text for the given HF-format messages.
+        messages: [{ role, content: [{type:'text'|'image', text|image}] }]
+        """
+        assert self.model is not None and self.processor is not None
+        # Apply chat template and tokenize
+        inputs = self.processor.apply_chat_template(
+            messages,
+            add_generation_prompt=True,
+            tokenize=True,
+            return_dict=True,
+            return_tensors="pt",
+        )
+        # Move inputs to the same device as model
+        inputs = inputs.to(self.model.device)
+        # Generate
+        with torch.no_grad():
+            generated_ids = self.model.generate(**inputs, max_new_tokens=max_new_tokens)
+        # Trim prompt tokens from output
+        generated_ids_trimmed = [
+            out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+        ]
+        # Decode
+        output_text = self.processor.batch_decode(
+            generated_ids_trimmed,
+            skip_special_tokens=True,
+            clean_up_tokenization_spaces=False,
+        )
+        return output_text[0] if output_text else ""

agent/adapters/models/internvl.py

@@ -0,0 +1,254 @@
+from __future__ import annotations
+from typing import List, Dict, Any, Optional
+
+# Hugging Face imports are local to avoid hard dependency at module import
+try:
+    import torch  # type: ignore
+    from transformers import AutoModel, AutoTokenizer  # type: ignore
+    # Attempt to import InternVL's model dependencies
+    import einops as _  # type: ignore
+    import timm as _  # type: ignore
+    from PIL import Image  # type: ignore
+    import torchvision.transforms as T  # type: ignore
+    from torchvision.transforms.functional import InterpolationMode  # type: ignore
+    import base64  # type: ignore
+    from io import BytesIO  # type: ignore
+    import requests  # type: ignore
+    HF_AVAILABLE = True
+except Exception:
+    HF_AVAILABLE = False
+
+
+class InternVLModel:
+    """Generic Hugging Face vision-language model handler.
+    Uses InternVL's native `model.chat()` interface with `AutoTokenizer`.
+    Provides preprocessing to support multi-turn conversations with multiple images.
+    """
+
+    def __init__(self, model_name: str, device: str = "auto", trust_remote_code: bool = False) -> None:
+        if not HF_AVAILABLE:
+            raise ImportError(
+                "InternVL dependencies not found. Install with: pip install \"cua-agent[internvl-hf]\""
+            )
+        self.model_name = model_name
+        self.device = device
+        self.model = None
+        self.tokenizer = None
+        self.trust_remote_code = trust_remote_code
+        self._load()
+
+    def _load(self) -> None:
+        # Load model
+        self.model = AutoModel.from_pretrained(
+            self.model_name,
+            torch_dtype=torch.bfloat16,
+            low_cpu_mem_usage=True,
+            use_flash_attn=True,
+            device_map=self.device,
+            trust_remote_code=self.trust_remote_code,
+        ).eval()
+        # Load tokenizer (InternVL requires trust_remote_code=True and often use_fast=False)
+        self.tokenizer = AutoTokenizer.from_pretrained(
+            self.model_name,
+            trust_remote_code=self.trust_remote_code,
+            use_fast=False,
+        )
+
+    # ---- Image preprocessing utilities adapted from InternVL docs ----
+    IMAGENET_MEAN = (0.485, 0.456, 0.406)
+    IMAGENET_STD = (0.229, 0.224, 0.225)
+
+    def _build_transform(self, input_size: int) -> T.Compose:
+        MEAN, STD = self.IMAGENET_MEAN, self.IMAGENET_STD
+        transform = T.Compose([
+            T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
+            T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),
+            T.ToTensor(),
+            T.Normalize(mean=MEAN, std=STD)
+        ])
+        return transform
+
+    def _find_closest_aspect_ratio(self, aspect_ratio: float, target_ratios: List[tuple], width: int, height: int, image_size: int):
+        best_ratio_diff = float('inf')
+        best_ratio = (1, 1)
+        area = width * height
+        for ratio in target_ratios:
+            target_aspect_ratio = ratio[0] / ratio[1]
+            ratio_diff = abs(aspect_ratio - target_aspect_ratio)
+            if ratio_diff < best_ratio_diff:
+                best_ratio_diff = ratio_diff
+                best_ratio = ratio
+            elif ratio_diff == best_ratio_diff:
+                if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]:
+                    best_ratio = ratio
+        return best_ratio
+
+    def _dynamic_preprocess(self, image: Image.Image, min_num: int = 1, max_num: int = 12, image_size: int = 448, use_thumbnail: bool = True) -> List[Image.Image]:
+        orig_width, orig_height = image.size
+        aspect_ratio = orig_width / orig_height
+
+        target_ratios = set(
+            (i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) if
+            i * j <= max_num and i * j >= min_num)
+        target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1])
+
+        target_aspect_ratio = self._find_closest_aspect_ratio(
+            aspect_ratio, target_ratios, orig_width, orig_height, image_size)
+
+        target_width = image_size * target_aspect_ratio[0]
+        target_height = image_size * target_aspect_ratio[1]
+        blocks = target_aspect_ratio[0] * target_aspect_ratio[1]
+
+        resized_img = image.resize((target_width, target_height))
+        processed_images: List[Image.Image] = []
+        for i in range(blocks):
+            box = (
+                (i % (target_width // image_size)) * image_size,
+                (i // (target_width // image_size)) * image_size,
+                ((i % (target_width // image_size)) + 1) * image_size,
+                ((i // (target_width // image_size)) + 1) * image_size
+            )
+            split_img = resized_img.crop(box)
+            processed_images.append(split_img)
+        assert len(processed_images) == blocks
+        if use_thumbnail and len(processed_images) != 1:
+            thumbnail_img = image.resize((image_size, image_size))
+            processed_images.append(thumbnail_img)
+        return processed_images
+
+    def _load_image_from_source(self, src: str) -> Image.Image:
+        """Load PIL image from various sources: data URL, http(s), or local path."""
+        if src.startswith("data:image/"):
+            # data URL base64
+            header, b64data = src.split(",", 1)
+            img_bytes = base64.b64decode(b64data)
+            return Image.open(BytesIO(img_bytes)).convert('RGB')
+        if src.startswith("http://") or src.startswith("https://"):
+            resp = requests.get(src, timeout=10)
+            resp.raise_for_status()
+            return Image.open(BytesIO(resp.content)).convert('RGB')
+        # Assume local file path
+        return Image.open(src).convert('RGB')
+
+    def _images_to_pixel_values(self, images: List[Image.Image], input_size: int = 448, max_num: int = 12):
+        transform = self._build_transform(input_size=input_size)
+        pixel_values_list = []
+        num_patches_list: List[int] = []
+        for img in images:
+            tiles = self._dynamic_preprocess(img, image_size=input_size, use_thumbnail=True, max_num=max_num)
+            pv = [transform(tile) for tile in tiles]
+            pv = torch.stack(pv)
+            num_patches_list.append(pv.shape[0])
+            pixel_values_list.append(pv)
+        if not pixel_values_list:
+            return None, []
+        pixel_values = torch.cat(pixel_values_list)
+        return pixel_values, num_patches_list
+
+    def generate(self, messages: List[Dict[str, Any]], max_new_tokens: int = 128) -> str:
+        """Generate text for the given HF-format messages.
+        messages: [{ role, content: [{type:'text'|'image', text|image}] }]
+
+        This implementation constructs InternVL-compatible inputs and uses
+        `model.chat(tokenizer, pixel_values, question, history=...)` to avoid
+        relying on AutoProcessor (which fails for some tokenizers).
+        """
+        assert self.model is not None and self.tokenizer is not None
+
+        # Build textual context and collect images and the final question
+        context_lines: List[str] = []
+        all_images: List[Image.Image] = []
+        last_user_text_parts: List[str] = []
+
+        for msg in messages:
+            role = msg.get("role", "user")
+            content = msg.get("content", [])
+            if isinstance(content, str):
+                content_items = [{"type": "text", "text": content}]
+            else:
+                content_items = content
+
+            if role == "user":
+                # Collect text and images
+                parts_text: List[str] = []
+                for item in content_items:
+                    if item.get("type") == "text":
+                        t = item.get("text", "")
+                        if t:
+                            parts_text.append(t)
+                    elif item.get("type") == "image":
+                        url = item.get("image", "")
+                        if url:
+                            try:
+                                all_images.append(self._load_image_from_source(url))
+                            except Exception:
+                                # Ignore failed image loads but keep going
+                                pass
+                text = "\n".join(parts_text).strip()
+                if text:
+                    context_lines.append(f"User: {text}")
+                # Track last user text separately for question
+                last_user_text_parts = parts_text or last_user_text_parts
+            elif role == "assistant":
+                # Only keep text content for history
+                parts_text = [item.get("text", "") for item in content_items if item.get("type") == "text"]
+                text = "\n".join(parts_text).strip()
+                if text:
+                    context_lines.append(f"Assistant: {text}")
+
+        # Prepare pixel values for all collected images (across turns)
+        pixel_values = None
+        num_patches_list: List[int] = []
+        if all_images:
+            pixel_values, num_patches_list = self._images_to_pixel_values(all_images, input_size=448, max_num=12)
+            if pixel_values is not None:
+                # Convert dtype/device as in docs
+                pixel_values = pixel_values.to(torch.bfloat16)
+                # Chat API expects tensors on CUDA when model is on CUDA
+                try:
+                    pixel_values = pixel_values.to(self.model.device)
+                except Exception:
+                    pass
+
+        # Build question with any prior context and numbered image placeholders
+        if all_images:
+            # Separate images layout: Image-1: <image> ... then question text
+            prefix_lines = [f"Image-{i+1}: <image>" for i in range(len(all_images))]
+            prefix = "\n".join(prefix_lines) + "\n"
+        else:
+            prefix = ""
+
+        last_user_text = "\n".join(last_user_text_parts).strip()
+        # Combine prior text-only turns as context to emulate multi-turn
+        context_text = "\n".join(context_lines[:-1]) if len(context_lines) > 1 else ""
+        base_question = last_user_text if last_user_text else "Describe the image(s) in detail."
+        if context_text:
+            question = (context_text + "\n" + prefix + base_question).strip()
+        else:
+            question = (prefix + base_question).strip()
+
+        # Generation config
+        generation_config = dict(max_new_tokens=max_new_tokens, do_sample=False)
+
+        # Call InternVL chat
+        try:
+            if pixel_values is None:
+                # Pure-text conversation (embed prior turns in question)
+                response = self.model.chat(self.tokenizer, None, question, generation_config)
+            else:
+                # Multi-image: pass num_patches_list if >1 image
+                if len(num_patches_list) > 1:
+                    response = self.model.chat(
+                        self.tokenizer,
+                        pixel_values,
+                        question,
+                        generation_config,
+                        num_patches_list=num_patches_list,
+                    )
+                else:
+                    response = self.model.chat(self.tokenizer, pixel_values, question, generation_config)
+        except Exception as e:
+            # Fallback: return empty string to avoid crashing the adapter
+            return ""
+
+        return response or ""

agent/adapters/models/opencua.py

@@ -0,0 +1,100 @@
+from typing import List, Dict, Any
+import re
+import base64
+from io import BytesIO
+
+try:
+    import torch  # type: ignore
+    from transformers import AutoTokenizer, AutoModel, AutoImageProcessor  # type: ignore
+    from PIL import Image  # type: ignore
+    import blobfile as _ # assert blobfile is installed
+    OPENCUA_AVAILABLE = True
+except Exception:
+    OPENCUA_AVAILABLE = False
+
+
+class OpenCUAModel:
+    """OpenCUA model handler using AutoTokenizer, AutoModel and AutoImageProcessor."""
+
+    def __init__(self, model_name: str, device: str = "auto", trust_remote_code: bool = False) -> None:
+        if not OPENCUA_AVAILABLE:
+            raise ImportError(
+                "OpenCUA requirements not found. Install with: pip install \"cua-agent[opencua-hf]\""
+            )
+        self.model_name = model_name
+        self.device = device
+        self.model = None
+        self.tokenizer = None
+        self.image_processor = None
+        self.trust_remote_code = trust_remote_code
+        self._load()
+
+    def _load(self) -> None:
+        self.tokenizer = AutoTokenizer.from_pretrained(
+            self.model_name, trust_remote_code=self.trust_remote_code
+        )
+        self.model = AutoModel.from_pretrained(
+            self.model_name,
+            torch_dtype="auto",
+            device_map=self.device,
+            trust_remote_code=self.trust_remote_code,
+            attn_implementation="sdpa",
+        )
+        self.image_processor = AutoImageProcessor.from_pretrained(
+            self.model_name, trust_remote_code=self.trust_remote_code
+        )
+
+    @staticmethod
+    def _extract_last_image_b64(messages: List[Dict[str, Any]]) -> str:
+        # Expect HF-format messages with content items type: "image" with data URL
+        for msg in reversed(messages):
+            for item in reversed(msg.get("content", [])):
+                if isinstance(item, dict) and item.get("type") == "image":
+                    url = item.get("image", "")
+                    if isinstance(url, str) and url.startswith("data:image/"):
+                        return url.split(",", 1)[1]
+        return ""
+
+    def generate(self, messages: List[Dict[str, Any]], max_new_tokens: int = 512) -> str:
+        assert self.model is not None and self.tokenizer is not None and self.image_processor is not None
+
+        # Tokenize text side using chat template
+        input_ids = self.tokenizer.apply_chat_template(
+            messages, tokenize=True, add_generation_prompt=True
+        )
+        input_ids = torch.tensor([input_ids]).to(self.model.device)
+
+        # Prepare image inputs from last data URL image
+        image_b64 = self._extract_last_image_b64(messages)
+        pixel_values = None
+        grid_thws = None
+        if image_b64:
+            image = Image.open(BytesIO(base64.b64decode(image_b64))).convert("RGB")
+            image_info = self.image_processor.preprocess(images=[image])
+            pixel_values = torch.tensor(image_info["pixel_values"]).to(
+                dtype=torch.bfloat16, device=self.model.device
+            )
+            grid_thws = torch.tensor(image_info["image_grid_thw"]) if "image_grid_thw" in image_info else None
+
+        gen_kwargs: Dict[str, Any] = {
+            "max_new_tokens": max_new_tokens,
+            "temperature": 0,
+        }
+        if pixel_values is not None:
+            gen_kwargs["pixel_values"] = pixel_values
+        if grid_thws is not None:
+            gen_kwargs["grid_thws"] = grid_thws
+
+        with torch.no_grad():
+            generated_ids = self.model.generate(
+                input_ids,
+                **gen_kwargs,
+            )
+
+        # Remove prompt tokens
+        prompt_len = input_ids.shape[1]
+        generated_ids = generated_ids[:, prompt_len:]
+        output_text = self.tokenizer.batch_decode(
+            generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
+        )[0]
+        return output_text

agent/adapters/models/qwen2_5_vl.py

@@ -0,0 +1,75 @@
+from typing import List, Dict, Any, Optional
+
+# Hugging Face imports are local to avoid hard dependency at module import
+try:
+    import torch  # type: ignore
+    from transformers import AutoModelForImageTextToText, AutoProcessor  # type: ignore
+    HF_AVAILABLE = True
+except Exception:
+    HF_AVAILABLE = False
+
+
+class Qwen2_5_VLModel:
+    """Qwen2.5-VL Hugging Face vision-language model handler.
+    Loads an AutoModelForImageTextToText and AutoProcessor and generates text.
+    """
+
+    def __init__(self, model_name: str, device: str = "auto", trust_remote_code: bool = False) -> None:
+        if not HF_AVAILABLE:
+            raise ImportError(
+                "HuggingFace transformers dependencies not found. Install with: pip install \"cua-agent[uitars-hf]\""
+            )
+        self.model_name = model_name
+        self.device = device
+        self.model = None
+        self.processor = None
+        self.trust_remote_code = trust_remote_code
+        self._load()
+
+    def _load(self) -> None:
+        # Load model
+        self.model = AutoModelForImageTextToText.from_pretrained(
+            self.model_name,
+            torch_dtype=torch.bfloat16,
+            device_map=self.device,
+            attn_implementation="sdpa",
+            trust_remote_code=self.trust_remote_code,
+        )
+        # Load processor
+        self.processor = AutoProcessor.from_pretrained(
+            self.model_name,
+            min_pixels=3136,
+            max_pixels=4096 * 2160,
+            device_map=self.device,
+            trust_remote_code=self.trust_remote_code,
+        )
+
+    def generate(self, messages: List[Dict[str, Any]], max_new_tokens: int = 128) -> str:
+        """Generate text for the given HF-format messages.
+        messages: [{ role, content: [{type:'text'|'image', text|image}] }]
+        """
+        assert self.model is not None and self.processor is not None
+        # Apply chat template and tokenize
+        inputs = self.processor.apply_chat_template(
+            messages,
+            add_generation_prompt=True,
+            tokenize=True,
+            return_dict=True,
+            return_tensors="pt",
+        )
+        # Move inputs to the same device as model
+        inputs = inputs.to(self.model.device)
+        # Generate
+        with torch.no_grad():
+            generated_ids = self.model.generate(**inputs, max_new_tokens=max_new_tokens)
+        # Trim prompt tokens from output
+        generated_ids_trimmed = [
+            out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+        ]
+        # Decode
+        output_text = self.processor.batch_decode(
+            generated_ids_trimmed,
+            skip_special_tokens=True,
+            clean_up_tokenization_spaces=False,
+        )
+        return output_text[0] if output_text else ""

agent/agent.py

@@ -171,6 +171,7 @@ class ComputerAgent:
         use_prompt_caching: Optional[bool] = False,
         max_trajectory_budget: Optional[float | dict] = None,
         telemetry_enabled: Optional[bool] = True,
+        trust_remote_code: Optional[bool] = False,
         **kwargs
     ):
         """
@@ -190,6 +191,7 @@ class ComputerAgent:
             use_prompt_caching: If set, use prompt caching to avoid reprocessing the same prompt. Intended for use with anthropic providers.
             max_trajectory_budget: If set, adds BudgetManagerCallback to track usage costs and stop when budget is exceeded
             telemetry_enabled: If set, adds TelemetryCallback to track anonymized usage data. Enabled by default.
+            trust_remote_code: If set, trust remote code when loading local models. Disabled by default.
             **kwargs: Additional arguments passed to the agent loop
         """        
         # If the loop is "human/human", we need to prefix a grounding model fallback
@@ -209,6 +211,7 @@ class ComputerAgent:
         self.use_prompt_caching = use_prompt_caching
         self.telemetry_enabled = telemetry_enabled
         self.kwargs = kwargs
+        self.trust_remote_code = trust_remote_code
 
         # == Add built-in callbacks ==
 
@@ -252,7 +255,8 @@ class ComputerAgent:
 
         # Register local model providers
         hf_adapter = HuggingFaceLocalAdapter(
-            device="auto"
+            device="auto",
+            trust_remote_code=self.trust_remote_code or False
         )
         human_adapter = HumanAdapter()
         mlx_adapter = MLXVLMAdapter()