cua-agent 0.4.31__py3-none-any.whl → 0.4.32__py3-none-any.whl

agent/callbacks/trajectory_saver.py

@@ -188,6 +188,8 @@ class TrajectorySaverCallback(AsyncCallbackHandler):
             model_name_short = model.split("+")[-1].split("/")[-1].lower()[:16]
             if "+" in model:
                 model_name_short = model.split("+")[0].lower()[:4] + "_" + model_name_short
+            # strip non-alphanumeric characters from model_name_short
+            model_name_short = ''.join(c for c in model_name_short if c.isalnum() or c == '_')
 
             # id format: yyyy-mm-dd_model_hhmmss_uuid[:4]
             now = datetime.now()

agent/cli.py

@@ -18,6 +18,15 @@ try:
     import json
     from typing import List, Dict, Any
     import dotenv
+    import base64
+    import time
+    import platform
+    from pathlib import Path
+    try:
+        from PIL import Image, ImageDraw
+        PIL_AVAILABLE = True
+    except Exception:
+        PIL_AVAILABLE = False
     from yaspin import yaspin
 except ImportError:
     if __name__ == "__main__":
@@ -248,6 +257,13 @@ Examples:
         help="Initial prompt to send to the agent. Leave blank for interactive mode."
     )
 
+    parser.add_argument(
+        "--predict-click",
+        dest="predict_click",
+        type=str,
+        help="Instruction for click prediction. If set, runs predict_click, draws crosshair on a fresh screenshot, saves and opens it."
+    )
+
     parser.add_argument(
         "-c", "--cache",
         action="store_true",
@@ -331,6 +347,7 @@ Examples:
         agent_kwargs = {
             "model": args.model,
             "tools": [computer],
+            "trust_remote_code": True, # needed for some local models (e.g., InternVL, OpenCUA)
             "verbosity": 20 if args.verbose else 30,  # DEBUG vs WARNING
             "max_retries": args.max_retries
         }
@@ -353,7 +370,79 @@ Examples:
         
         agent = ComputerAgent(**agent_kwargs)
         
-        # Start chat loop
+        # If predict-click mode is requested, run once and exit
+        if args.predict_click:
+            if not PIL_AVAILABLE:
+                print_colored("❌ Pillow (PIL) is required for --predict-click visualization. Install with: pip install pillow", Colors.RED, bold=True)
+                sys.exit(1)
+
+            instruction = args.predict_click
+            print_colored(f"Predicting click for: '{instruction}'", Colors.CYAN)
+
+            # Take a fresh screenshot FIRST
+            try:
+                img_bytes = await computer.interface.screenshot()
+            except Exception as e:
+                print_colored(f"❌ Failed to take screenshot: {e}", Colors.RED, bold=True)
+                sys.exit(1)
+
+            # Encode screenshot to base64 for predict_click
+            try:
+                image_b64 = base64.b64encode(img_bytes).decode("utf-8")
+            except Exception as e:
+                print_colored(f"❌ Failed to encode screenshot: {e}", Colors.RED, bold=True)
+                sys.exit(1)
+
+            try:
+                coords = await agent.predict_click(instruction, image_b64=image_b64)
+            except Exception as e:
+                print_colored(f"❌ predict_click failed: {e}", Colors.RED, bold=True)
+                sys.exit(1)
+
+            if not coords:
+                print_colored("⚠️  No coordinates returned.", Colors.YELLOW)
+                sys.exit(2)
+
+            x, y = coords
+            print_colored(f"✅ Predicted coordinates: ({x}, {y})", Colors.GREEN)
+
+            try:
+                from io import BytesIO
+                with Image.open(BytesIO(img_bytes)) as img:
+                    img = img.convert("RGB")
+                    draw = ImageDraw.Draw(img)
+                    # Draw crosshair
+                    size = 12
+                    color = (255, 0, 0)
+                    draw.line([(x - size, y), (x + size, y)], fill=color, width=3)
+                    draw.line([(x, y - size), (x, y + size)], fill=color, width=3)
+                    # Optional small circle
+                    r = 6
+                    draw.ellipse([(x - r, y - r), (x + r, y + r)], outline=color, width=2)
+
+                    out_path = Path.cwd() / f"predict_click_{int(time.time())}.png"
+                    img.save(out_path)
+                    print_colored(f"🖼️  Saved to {out_path}")
+
+                    # Open the image with default viewer
+                    try:
+                        system = platform.system().lower()
+                        if system == "windows":
+                            os.startfile(str(out_path))  # type: ignore[attr-defined]
+                        elif system == "darwin":
+                            os.system(f"open \"{out_path}\"")
+                        else:
+                            os.system(f"xdg-open \"{out_path}\"")
+                    except Exception:
+                        pass
+            except Exception as e:
+                print_colored(f"❌ Failed to render/save screenshot: {e}", Colors.RED, bold=True)
+                sys.exit(1)
+
+            # Done
+            sys.exit(0)
+
+        # Start chat loop (default interactive mode)
         await chat_loop(agent, args.model, container_name, args.prompt, args.usage)
 
 

agent/loops/__init__.py

@@ -10,5 +10,19 @@ from . import omniparser
 from . import gta1
 from . import composed_grounded
 from . import glm45v
+from . import opencua
+from . import internvl
+from . import holo
 
-__all__ = ["anthropic", "openai", "uitars", "omniparser", "gta1", "composed_grounded", "glm45v"]
+__all__ = [
+    "anthropic", 
+    "openai", 
+    "uitars", 
+    "omniparser", 
+    "gta1", 
+    "composed_grounded", 
+    "glm45v", 
+    "opencua",
+    "internvl",
+    "holo",
+]

agent/loops/anthropic.py

@@ -1577,11 +1577,10 @@ Task: Click {instruction}. Output ONLY a click action on the target element."""
                 isinstance(item.get("action"), dict)):
                 
                 action = item["action"]
-                if action.get("type") == "click":
+                if action.get("x") and action.get("y"):
                     x = action.get("x")
                     y = action.get("y")
-                    if x is not None and y is not None:
-                        return (int(x), int(y))
+                    return (int(x), int(y))
         
         return None
     

agent/loops/composed_grounded.py

@@ -126,7 +126,7 @@ def get_last_computer_call_image(messages: List[Dict[str, Any]]) -> Optional[str
 
 
 @register_agent(r".*\+.*", priority=1)
-class ComposedGroundedConfig:
+class ComposedGroundedConfig(AsyncAgentConfig):
     """
     Composed-grounded agent configuration that uses both grounding and thinking models.
     

agent/loops/glm45v.py

@@ -844,7 +844,7 @@ Where x,y are coordinates normalized to 0-999 range."""
             api_kwargs = {
                 "model": model,
                 "messages": litellm_messages,
-                "max_tokens": 100,
+                "max_tokens": 2056,
                 "temperature": 0.001,
                 "extra_body": {
                     "skip_special_tokens": False,
@@ -856,6 +856,7 @@ Where x,y are coordinates normalized to 0-999 range."""
             
             # Extract response content
             response_content = response.choices[0].message.content.strip()
+            print(response)
             
             # Parse response for click coordinates
             # Look for coordinates in the response, handling special tokens
@@ -866,7 +867,7 @@ Where x,y are coordinates normalized to 0-999 range."""
                 # Fallback: look for coordinates without special tokens
                 coord_pattern = r"left_click\(start_box='?\[(\d+),(\d+)\]'?\)"
                 match = re.search(coord_pattern, response_content)
-            
+
             if match:
                 x, y = int(match.group(1)), int(match.group(2))
                 

agent/loops/gta1.py

@@ -155,7 +155,7 @@ class GTA1Config(AsyncAgentConfig):
         api_kwargs = {
             "model": model,
             "messages": [system_message, user_message],
-            "max_tokens": 32,
+            "max_tokens": 2056,
             "temperature": 0.0,
             **kwargs
         }

agent/loops/holo.py

@@ -0,0 +1,216 @@
+"""
+Holo 1.5 agent loop implementation for click prediction using litellm.acompletion.
+
+Implements the Holo1.5 grounding behavior:
+- Prompt asks for absolute pixel coordinates in JSON: {"action":"click_absolute","x":int,"y":int}
+- Optionally resizes the image using Qwen2-VL smart_resize parameters (via transformers AutoProcessor)
+- If resized, maps predicted coordinates back to the original screenshot resolution
+
+Note: We do NOT manually load the model; acompletions (via HuggingFaceLocalAdapter)
+will handle loading based on the provided model name.
+"""
+
+from __future__ import annotations
+
+import base64
+import json
+from io import BytesIO
+from typing import Any, Dict, List, Optional, Tuple
+
+import litellm
+from PIL import Image
+
+from ..decorators import register_agent
+from .base import AsyncAgentConfig
+from ..types import AgentCapability
+
+
+def _strip_hf_prefix(model: str) -> str:
+    """Strip provider prefixes like 'huggingface-local/' from model names for HF processor load."""
+    if "/" in model and model.lower().startswith("huggingface-local/"):
+        return model.split("/", 1)[1]
+    return model
+
+
+def _maybe_smart_resize(image: Image.Image, model: str) -> Tuple[Image.Image, Tuple[int, int]]:
+    """
+    Try to compute Qwen2-VL smart_resize output size using transformers AutoProcessor.
+
+    Returns (processed_image, (orig_w, orig_h)). If transformers or processor unavailable,
+    returns the original image and size without resizing.
+    """
+    orig_w, orig_h = image.size
+    try:
+        # Import lazily to avoid hard dependency if not installed
+        from transformers import AutoProcessor  # type: ignore
+        from transformers.models.qwen2_vl.image_processing_qwen2_vl import (  # type: ignore
+            smart_resize,
+        )
+
+        processor_name = _strip_hf_prefix(model)
+        processor = AutoProcessor.from_pretrained(processor_name)
+        image_processor = getattr(processor, "image_processor", None)
+        if image_processor is None:
+            return image, (orig_w, orig_h)
+
+        factor = getattr(image_processor, "patch_size", 14) * getattr(image_processor, "merge_size", 1)
+        min_pixels = getattr(image_processor, "min_pixels", 256 * 256)
+        max_pixels = getattr(image_processor, "max_pixels", 1536 * 1536)
+
+        resized_h, resized_w = smart_resize(
+            orig_h,
+            orig_w,
+            factor=factor,
+            min_pixels=min_pixels,
+            max_pixels=max_pixels,
+        )
+
+        if (resized_w, resized_h) == (orig_w, orig_h):
+            return image, (orig_w, orig_h)
+
+        processed = image.resize((resized_w, resized_h), resample=Image.Resampling.LANCZOS)
+        return processed, (orig_w, orig_h)
+    except Exception:
+        # If any failure (no transformers, processor load error), fall back to original
+        return image, (orig_w, orig_h)
+
+
+def _build_holo_prompt(instruction: str) -> str:
+    """Construct the Holo1.5 grounding prompt."""
+    # Keep it close to the cookbook while avoiding heavy schema generation
+    schema_hint = '{"action": "click_absolute", "x": <int>, "y": <int>}'
+    return (
+        "Localize an element on the GUI image according to the provided target and output a click position. "
+        f"You must output a valid JSON following the format: {schema_hint} "
+        f"Your target is: {instruction}"
+    )
+
+
+def _parse_click_json(output_text: str) -> Optional[Tuple[int, int]]:
+    """
+    Parse JSON from model output and extract x, y ints.
+    Tries to find the first JSON object substring if extra text is present.
+    """
+    try:
+        # Fast path: direct JSON
+        data = json.loads(output_text)
+    except Exception:
+        # Try to locate a JSON object within the text
+        start = output_text.find("{")
+        end = output_text.rfind("}")
+        if start == -1 or end == -1 or end <= start:
+            return None
+        try:
+            data = json.loads(output_text[start : end + 1])
+        except Exception:
+            return None
+
+    try:
+        x = int(data.get("x"))
+        y = int(data.get("y"))
+        return x, y
+    except Exception:
+        return None
+
+
+@register_agent(models=r"(?i).*(Holo1\.5|Hcompany/Holo1\.5).*")
+class HoloConfig(AsyncAgentConfig):
+    """Holo is a family of UI grounding models from H Company"""
+
+    async def predict_step(
+        self,
+        messages: List[Dict[str, Any]],
+        model: str,
+        tools: Optional[List[Dict[str, Any]]] = None,
+        max_retries: Optional[int] = None,
+        stream: bool = False,
+        computer_handler=None,
+        _on_api_start=None,
+        _on_api_end=None,
+        _on_usage=None,
+        _on_screenshot=None,
+        **kwargs,
+    ) -> Dict[str, Any]:
+        # Holo models are only trained on UI localization tasks, not all-in-one agent
+        raise NotImplementedError()
+
+    async def predict_click(
+        self,
+        model: str,
+        image_b64: str,
+        instruction: str,
+        **kwargs,
+    ) -> Optional[Tuple[int, int]]:
+        """
+        Predict click coordinates using Holo1.5 via litellm.acompletion.
+
+        - Optionally smart-resizes the image using Qwen2-VL rules if transformers are available
+        - Prompts for JSON with absolute pixel coordinates
+        - Parses x,y and maps back to original screenshot size if resized
+        """
+        try:
+            img_bytes = base64.b64decode(image_b64)
+            original_img = Image.open(BytesIO(img_bytes))
+        except Exception:
+            return None
+
+        # Optional preprocessing
+        processed_img, (orig_w, orig_h) = _maybe_smart_resize(original_img, model)
+
+        # If we resized, send the resized image; otherwise send original
+        img_to_send = processed_img
+        buf = BytesIO()
+        img_to_send.save(buf, format="PNG")
+        processed_b64 = base64.b64encode(buf.getvalue()).decode("utf-8")
+
+        prompt = _build_holo_prompt(instruction)
+
+        messages = [
+            {
+                "role": "user",
+                "content": [
+                    {
+                        "type": "image_url",
+                        "image_url": {"url": f"data:image/png;base64,{processed_b64}"},
+                    },
+                    {"type": "text", "text": prompt},
+                ],
+            }
+        ]
+
+        api_kwargs = {
+            "model": model,
+            "messages": messages,
+            # Deterministic, small output
+            "max_tokens": kwargs.get("max_tokens", 256),
+            "temperature": kwargs.get("temperature", 0.0),
+        }
+
+        response = await litellm.acompletion(**api_kwargs)
+        output_text = (response.choices[0].message.content or "").strip()  # type: ignore
+
+        coords = _parse_click_json(output_text)
+        if coords is None:
+            return None
+
+        x, y = coords
+
+        # Map back to original size if we resized
+        proc_w, proc_h = img_to_send.size
+        if (proc_w, proc_h) != (orig_w, orig_h):
+            try:
+                sx = orig_w / float(proc_w)
+                sy = orig_h / float(proc_h)
+                x = int(round(x * sx))
+                y = int(round(y * sy))
+            except Exception:
+                # Fallback: clamp within original bounds
+                pass
+
+        # Clamp to original image bounds
+        x = max(0, min(orig_w - 1, x))
+        y = max(0, min(orig_h - 1, y))
+        return x, y
+
+    def get_capabilities(self) -> List[AgentCapability]:
+        return ["click"]

agent/loops/internvl.py

@@ -0,0 +1,185 @@
+"""
+InternVL agent loop implementation for click prediction using litellm.acompletion.
+
+Implements the ScreenSpot InternVL grounding baseline behavior:
+- Uses the exact grounding prompt format with <image> and <ref> tags
+- Expects coordinates in 0-1000 normalized range in formats [[x1,y1,x2,y2]] or [[x,y]]
+- Converts to pixel coordinates relative to the original screenshot size
+
+Note: We do NOT manually load the InternVL model; acompletions (via HuggingFaceLocalAdapter)
+will handle loading based on the provided model name.
+"""
+
+from __future__ import annotations
+
+import base64
+import math
+import re
+from io import BytesIO
+from typing import Any, Dict, List, Optional, Tuple
+
+from PIL import Image
+import litellm
+
+from ..decorators import register_agent
+from .composed_grounded import ComposedGroundedConfig
+from ..types import AgentCapability
+
+
+# Regex patterns for extracting coordinates
+# Accept optional whitespace and optional decimal fractions
+_NUM = r"(\d+(?:\.\d+)?)"
+_POINT_PATTERN = re.compile(r"\[\[\s*" + _NUM + r"\s*,\s*" + _NUM + r"\s*\]\]")
+_BBOX_PATTERN = re.compile(
+    r"\[\[\s*" + _NUM + r"\s*,\s*" + _NUM + r"\s*,\s*" + _NUM + r"\s*,\s*" + _NUM + r"\s*\]\]"
+)
+
+
+def _extract_first_point(text: str) -> Optional[Tuple[float, float]]:
+    """Extract the first [[x,y]] as normalized (0-1000) floats."""
+    m = _POINT_PATTERN.search(text)
+    if not m:
+        return None
+    try:
+        x = float(m.group(1))
+        y = float(m.group(2))
+        return x, y
+    except Exception:
+        return None
+
+
+def _extract_last_bbox(text: str) -> Optional[Tuple[float, float, float, float]]:
+    """Extract the last [[x1,y1,x2,y2]] as normalized (0-1000) floats."""
+    matches = list(_BBOX_PATTERN.finditer(text))
+    if not matches:
+        return None
+    m = matches[-1]
+    try:
+        x1 = float(m.group(1))
+        y1 = float(m.group(2))
+        x2 = float(m.group(3))
+        y2 = float(m.group(4))
+        return x1, y1, x2, y2
+    except Exception:
+        return None
+
+
+def _scale_norm_to_pixels(x_norm: float, y_norm: float, width: int, height: int) -> Tuple[int, int]:
+    """Scale 0-1000 normalized coordinates to pixel coordinates for given image size."""
+    x_px = int(math.floor((x_norm / 1000.0) * width))
+    y_px = int(math.floor((y_norm / 1000.0) * height))
+    # Clamp to image bounds just in case
+    x_px = max(0, min(width - 1, x_px))
+    y_px = max(0, min(height - 1, y_px))
+    return x_px, y_px
+
+
+@register_agent(models=r"(?i).*InternVL.*")
+class InternVLConfig(ComposedGroundedConfig):
+    """InternVL agent configuration reusing ComposedGroundedConfig for steps and
+    overriding predict_click to implement ScreenSpot InternVL grounding baseline."""
+
+    async def predict_step(
+        self,
+        messages: List[Dict[str, Any]],
+        model: str,
+        tools: Optional[List[Dict[str, Any]]] = None,
+        max_retries: Optional[int] = None,
+        stream: bool = False,
+        computer_handler=None,
+        _on_api_start=None,
+        _on_api_end=None,
+        _on_usage=None,
+        _on_screenshot=None,
+        **kwargs
+    ) -> Dict[str, Any]:
+        """Fallback to a self-composed model"""
+        return await super().predict_step(
+            messages=messages,
+            model=f"{model}+{model}",
+            tools=tools,
+            max_retries=max_retries,
+            stream=stream,
+            computer_handler=computer_handler,
+            _on_api_start=_on_api_start,
+            _on_api_end=_on_api_end,
+            _on_usage=_on_usage,
+            _on_screenshot=_on_screenshot,
+            **kwargs
+        )
+    
+    async def predict_click(
+        self,
+        model: str,
+        image_b64: str,
+        instruction: str,
+        **kwargs
+    ) -> Optional[Tuple[int, int]]:
+        """
+        Predict click coordinates using InternVL via litellm.acompletion.
+
+        Behavior mirrors the ScreenSpot InternVL baseline:
+        - Prompt: "<image>\nPlease provide the bounding box coordinate of the UI element this user instruction describes: <ref>{instruction}</ref>. Answer in the format of [[x1, y1, x2, y2]]"
+        - Parse either [[x,y]] point or [[x1,y1,x2,y2]] bbox, using bbox center if point missing
+        - Coordinates are 0-1000 normalized; convert to pixel coordinates for the original screenshot
+        """
+        try:
+            # Decode image dimensions to scale the normalized outputs
+            img_bytes = base64.b64decode(image_b64)
+            image = Image.open(BytesIO(img_bytes))
+            width, height = image.size
+        except Exception:
+            # If decoding fails, proceed with a safe default size to avoid crash
+            width, height = 1920, 1080
+
+        # Build grounding prompt exactly like the baseline
+        grounding_prompt = (
+            f"Please provide the bounding box coordinate of the UI element this user instruction describes: <ref>{instruction}</ref>. "
+            f"Answer in the format of [[x1, y1, x2, y2]]"
+        )
+
+        # Prepare messages for LiteLLM
+        messages = [
+            {
+                "role": "user",
+                "content": [
+                    {
+                        "type": "image_url",
+                        "image_url": {"url": f"data:image/png;base64,{image_b64}"},
+                    },
+                    {"type": "text", "text": grounding_prompt},
+                ],
+            }
+        ]
+
+        # Call acompletion; HuggingFaceLocalAdapter/model handler will handle InternVL loading
+        api_kwargs = {
+            "model": model,
+            "messages": messages,
+            # Conservative generation params akin to baseline (deterministic)
+            "max_tokens": kwargs.get("max_tokens", 256),
+            "temperature": kwargs.get("temperature", 0.0),
+        }
+
+        response = await litellm.acompletion(**api_kwargs)
+        output_text = (response.choices[0].message.content or "").strip()  # type: ignore
+
+        # print(f"InternVL output: {output_text}")
+
+        # Try to parse a point first; if absent, parse bbox and take center
+        point = _extract_first_point(output_text)
+        if point is None:
+            bbox = _extract_last_bbox(output_text)
+            if bbox is None:
+                return None
+            x1, y1, x2, y2 = bbox
+            cx = (x1 + x2) / 2.0
+            cy = (y1 + y2) / 2.0
+            point = (cx, cy)
+
+        x_norm, y_norm = point
+        x_px, y_px = _scale_norm_to_pixels(x_norm, y_norm, width, height)
+        return (x_px, y_px)
+
+    def get_capabilities(self) -> List[AgentCapability]:
+        return ["click", "step"]