cua-agent 0.4.23__py3-none-any.whl → 0.4.25__py3-none-any.whl

agent/callbacks/image_retention.py

@@ -50,90 +50,41 @@ class ImageRetentionCallback(AsyncCallbackHandler):
         """
         if self.only_n_most_recent_images is None:
             return messages
-        
-        # First pass: Assign call_id to reasoning items based on the next computer_call
-        messages_with_call_ids = []
-        for i, msg in enumerate(messages):
-            msg_copy = msg.copy() if isinstance(msg, dict) else msg
-            
-            # If this is a reasoning item without a call_id, find the next computer_call
-            if (msg_copy.get("type") == "reasoning" and 
-                not msg_copy.get("call_id")):
-                # Look ahead for the next computer_call
-                for j in range(i + 1, len(messages)):
-                    next_msg = messages[j]
-                    if (next_msg.get("type") == "computer_call" and 
-                        next_msg.get("call_id")):
-                        msg_copy["call_id"] = next_msg.get("call_id")
-                        break
-            
-            messages_with_call_ids.append(msg_copy)
-        
-        # Find all computer_call_output items with images and their call_ids
-        image_call_ids = []
-        for msg in reversed(messages_with_call_ids):  # Process in reverse to get most recent first
-            if (msg.get("type") == "computer_call_output" and 
-                isinstance(msg.get("output"), dict) and 
-                "image_url" in msg.get("output", {})):
-                call_id = msg.get("call_id")
-                if call_id and call_id not in image_call_ids:
-                    image_call_ids.append(call_id)
-                    if len(image_call_ids) >= self.only_n_most_recent_images:
-                        break
-        
-        # Keep the most recent N image call_ids (reverse to get chronological order)
-        keep_call_ids = set(image_call_ids[:self.only_n_most_recent_images])
-        
-        # Filter messages: remove computer_call, computer_call_output, and reasoning for old images
-        filtered_messages = []
-        for msg in messages_with_call_ids:
-            msg_type = msg.get("type")
-            call_id = msg.get("call_id")
-            
-            # Remove old computer_call items
-            if msg_type == "computer_call" and call_id not in keep_call_ids:
-                # Check if this call_id corresponds to an image call
-                has_image_output = any(
-                    m.get("type") == "computer_call_output" and 
-                    m.get("call_id") == call_id and
-                    isinstance(m.get("output"), dict) and
-                    "image_url" in m.get("output", {})
-                    for m in messages_with_call_ids
-                )
-                if has_image_output:
-                    continue  # Skip this computer_call
-            
-            # Remove old computer_call_output items with images
-            if (msg_type == "computer_call_output" and 
-                call_id not in keep_call_ids and
-                isinstance(msg.get("output"), dict) and 
-                "image_url" in msg.get("output", {})):
-                continue  # Skip this computer_call_output
-            
-            # Remove old reasoning items that are paired with removed computer calls
-            if (msg_type == "reasoning" and 
-                call_id and call_id not in keep_call_ids):
-                # Check if this call_id corresponds to an image call that's being removed
-                has_image_output = any(
-                    m.get("type") == "computer_call_output" and 
-                    m.get("call_id") == call_id and
-                    isinstance(m.get("output"), dict) and
-                    "image_url" in m.get("output", {})
-                    for m in messages_with_call_ids
-                )
-                if has_image_output:
-                    continue  # Skip this reasoning item
-            
-            filtered_messages.append(msg)
-        
-        # Clean up: Remove call_id from reasoning items before returning
-        final_messages = []
-        for msg in filtered_messages:
-            if msg.get("type") == "reasoning" and "call_id" in msg:
-                # Create a copy without call_id for reasoning items
-                cleaned_msg = {k: v for k, v in msg.items() if k != "call_id"}
-                final_messages.append(cleaned_msg)
-            else:
-                final_messages.append(msg)
-        
-        return final_messages
+
+        # Gather indices of all computer_call_output messages that contain an image_url
+        output_indices: List[int] = []
+        for idx, msg in enumerate(messages):
+            if msg.get("type") == "computer_call_output":
+                out = msg.get("output")
+                if isinstance(out, dict) and ("image_url" in out):
+                    output_indices.append(idx)
+
+        # Nothing to trim
+        if len(output_indices) <= self.only_n_most_recent_images:
+            return messages
+
+        # Determine which outputs to keep (most recent N)
+        keep_output_indices = set(output_indices[-self.only_n_most_recent_images :])
+
+        # Build set of indices to remove in one pass
+        to_remove: set[int] = set()
+
+        for idx in output_indices:
+            if idx in keep_output_indices:
+                continue  # keep this screenshot and its context
+
+            to_remove.add(idx)  # remove the computer_call_output itself
+
+            # Remove the immediately preceding computer_call with matching call_id (if present)
+            call_id = messages[idx].get("call_id")
+            prev_idx = idx - 1
+            if prev_idx >= 0 and messages[prev_idx].get("type") == "computer_call" and messages[prev_idx].get("call_id") == call_id:
+                to_remove.add(prev_idx)
+                # Check a single reasoning immediately before that computer_call
+                r_idx = prev_idx - 1
+                if r_idx >= 0 and messages[r_idx].get("type") == "reasoning":
+                    to_remove.add(r_idx)
+
+        # Construct filtered list
+        filtered = [m for i, m in enumerate(messages) if i not in to_remove]
+        return filtered

agent/callbacks/operator_validator.py

@@ -102,37 +102,37 @@ class OperatorNormalizerCallback(AsyncCallbackHandler):
                 _keep_keys(action, keep)
             
 
-        # Second pass: if an assistant message is immediately followed by a computer_call,
-        # replace the assistant message itself with a reasoning message with summary text.
-        if isinstance(output, list):
-            for i, item in enumerate(output):
-                # AssistantMessage shape: { type: 'message', role: 'assistant', content: OutputContent[] }
-                if item.get("type") == "message" and item.get("role") == "assistant":
-                    next_idx = i + 1
-                    if next_idx >= len(output):
-                        continue
-                    next_item = output[next_idx]
-                    if not isinstance(next_item, dict):
-                        continue
-                    if next_item.get("type") != "computer_call":
-                        continue
-                    contents = item.get("content") or []
-                    # Extract text from OutputContent[]
-                    text_parts: List[str] = []
-                    if isinstance(contents, list):
-                        for c in contents:
-                            if isinstance(c, dict) and c.get("type") == "output_text" and isinstance(c.get("text"), str):
-                                text_parts.append(c["text"])
-                    text_content = "\n".join(text_parts).strip()
-                    # Replace assistant message with reasoning message
-                    output[i] = {
-                        "type": "reasoning",
-                        "summary": [
-                            {
-                                "type": "summary_text",
-                                "text": text_content,
-                            }
-                        ],
-                    }
+        # # Second pass: if an assistant message is immediately followed by a computer_call,
+        # # replace the assistant message itself with a reasoning message with summary text.
+        # if isinstance(output, list):
+        #     for i, item in enumerate(output):
+        #         # AssistantMessage shape: { type: 'message', role: 'assistant', content: OutputContent[] }
+        #         if item.get("type") == "message" and item.get("role") == "assistant":
+        #             next_idx = i + 1
+        #             if next_idx >= len(output):
+        #                 continue
+        #             next_item = output[next_idx]
+        #             if not isinstance(next_item, dict):
+        #                 continue
+        #             if next_item.get("type") != "computer_call":
+        #                 continue
+        #             contents = item.get("content") or []
+        #             # Extract text from OutputContent[]
+        #             text_parts: List[str] = []
+        #             if isinstance(contents, list):
+        #                 for c in contents:
+        #                     if isinstance(c, dict) and c.get("type") == "output_text" and isinstance(c.get("text"), str):
+        #                         text_parts.append(c["text"])
+        #             text_content = "\n".join(text_parts).strip()
+        #             # Replace assistant message with reasoning message
+        #             output[i] = {
+        #                 "type": "reasoning",
+        #                 "summary": [
+        #                     {
+        #                         "type": "summary_text",
+        #                         "text": text_content,
+        #                     }
+        #                 ],
+        #             }
 
         return output

agent/human_tool/ui.py

@@ -15,6 +15,11 @@ class HumanCompletionUI:
         self.current_call_id: Optional[str] = None
         self.refresh_interval = 2.0  # seconds
         self.last_image = None  # Store the last image for display
+        # Track current interactive action controls
+        self.current_action_type: str = "click"
+        self.current_button: str = "left"
+        self.current_scroll_x: int = 0
+        self.current_scroll_y: int = -120
     
     def format_messages_for_chatbot(self, messages: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
         """Format messages for display in gr.Chatbot with type='messages'."""
@@ -440,8 +445,8 @@ def create_ui():
                     with gr.Group(visible=False) as click_actions_group:
                         with gr.Row():
                             action_type_radio = gr.Dropdown(
-                                label="Action",
-                                choices=["click", "double_click", "move", "left_mouse_up", "left_mouse_down"],
+                                label="Interactive Action",
+                                choices=["click", "double_click", "move", "left_mouse_up", "left_mouse_down", "scroll"],
                                 value="click",
                                 scale=2
                             )
@@ -452,6 +457,18 @@ def create_ui():
                                 visible=True,
                                 scale=1
                             )
+                            scroll_x_input = gr.Number(
+                                label="scroll_x",
+                                value=0,
+                                visible=False,
+                                scale=1
+                            )
+                            scroll_y_input = gr.Number(
+                                label="scroll_y",
+                                value=-120,
+                                visible=False,
+                                scale=1
+                            )
                     
                     conversation_chatbot = gr.Chatbot(
                         label="Conversation",
@@ -545,9 +562,15 @@ def create_ui():
         def handle_image_click(evt: gr.SelectData):
             if evt.index is not None:
                 x, y = evt.index
-                action_type = action_type_radio.value or "click"
-                button = action_button_radio.value or "left"
-                result = ui_handler.submit_click_action(x, y, action_type, button)
+                action_type = ui_handler.current_action_type or "click"
+                button = ui_handler.current_button or "left"
+                if action_type == "scroll":
+                    sx_i = int(ui_handler.current_scroll_x or 0)
+                    sy_i = int(ui_handler.current_scroll_y or 0)
+                    # Submit a scroll action with x,y position and scroll deltas
+                    result = ui_handler.submit_action("scroll", x=x, y=y, scroll_x=sx_i, scroll_y=sy_i)
+                else:
+                    result = ui_handler.submit_click_action(x, y, action_type, button)
                 ui_handler.wait_for_pending_calls()
                 return result
             return "No coordinates selected"
@@ -570,14 +593,49 @@ def create_ui():
             outputs=[call_dropdown, screenshot_image, conversation_chatbot, submit_btn, click_actions_group, actions_group]
         )
         
-        # Toggle button radio visibility based on action type
-        def toggle_button_visibility(action_type):
-            return gr.update(visible=(action_type == "click"))
+        # Toggle visibility of controls based on action type
+        def toggle_action_controls(action_type):
+            # Button visible only for click
+            button_vis = gr.update(visible=(action_type == "click"))
+            # Scroll inputs visible only for scroll
+            scroll_x_vis = gr.update(visible=(action_type == "scroll"))
+            scroll_y_vis = gr.update(visible=(action_type == "scroll"))
+            # Update state
+            ui_handler.current_action_type = action_type or "click"
+            return button_vis, scroll_x_vis, scroll_y_vis
         
         action_type_radio.change(
-            fn=toggle_button_visibility,
+            fn=toggle_action_controls,
             inputs=[action_type_radio],
-            outputs=[action_button_radio]
+            outputs=[action_button_radio, scroll_x_input, scroll_y_input]
+        )
+
+        # Keep other control values in ui_handler state
+        def on_button_change(val):
+            ui_handler.current_button = (val or "left")
+        action_button_radio.change(
+            fn=on_button_change,
+            inputs=[action_button_radio]
+        )
+
+        def on_scroll_x_change(val):
+            try:
+                ui_handler.current_scroll_x = int(val) if val is not None else 0
+            except Exception:
+                ui_handler.current_scroll_x = 0
+        scroll_x_input.change(
+            fn=on_scroll_x_change,
+            inputs=[scroll_x_input]
+        )
+
+        def on_scroll_y_change(val):
+            try:
+                ui_handler.current_scroll_y = int(val) if val is not None else 0
+            except Exception:
+                ui_handler.current_scroll_y = 0
+        scroll_y_input.change(
+            fn=on_scroll_y_change,
+            inputs=[scroll_y_input]
         )
         
         type_submit_btn.click(

agent/loops/anthropic.py

@@ -132,23 +132,22 @@ def _convert_responses_items_to_completion_messages(messages: Messages) -> List[
                 converted_content = []
                 for item in content:
                     if isinstance(item, dict) and item.get("type") == "input_image":
-                        # Convert input_image to Anthropic image format
+                        # Convert input_image to OpenAI image format
                         image_url = item.get("image_url", "")
                         if image_url and image_url != "[omitted]":
-                            # Extract base64 data from data URL
-                            if "," in image_url:
-                                base64_data = image_url.split(",")[-1]
-                            else:
-                                base64_data = image_url
-                            
                             converted_content.append({
-                                "type": "image",
-                                "source": {
-                                    "type": "base64",
-                                    "media_type": "image/png",
-                                    "data": base64_data
+                                "type": "image_url",
+                                "image_url": {
+                                    "url": image_url
                                 }
                             })
+                    elif isinstance(item, dict) and item.get("type") == "input_text":
+                        # Convert input_text to OpenAI text format
+                        text = item.get("text", "")
+                        converted_content.append({
+                            "type": "text",
+                            "text": text
+                        })
                     else:
                         # Keep other content types as-is
                         converted_content.append(item)

cua_agent-0.4.25.dist-info/METADATA

@@ -0,0 +1,138 @@
+Metadata-Version: 2.1
+Name: cua-agent
+Version: 0.4.25
+Summary: CUA (Computer Use) Agent for AI-driven computer interaction
+Author-Email: TryCua <gh@trycua.com>
+Requires-Python: >=3.12
+Requires-Dist: httpx>=0.27.0
+Requires-Dist: aiohttp>=3.9.3
+Requires-Dist: asyncio
+Requires-Dist: anyio>=4.4.1
+Requires-Dist: typing-extensions>=4.12.2
+Requires-Dist: pydantic>=2.6.4
+Requires-Dist: rich>=13.7.1
+Requires-Dist: python-dotenv>=1.0.1
+Requires-Dist: cua-computer<0.5.0,>=0.4.0
+Requires-Dist: cua-core<0.2.0,>=0.1.8
+Requires-Dist: certifi>=2024.2.2
+Requires-Dist: litellm>=1.74.12
+Provides-Extra: openai
+Provides-Extra: anthropic
+Provides-Extra: omni
+Requires-Dist: cua-som<0.2.0,>=0.1.0; extra == "omni"
+Provides-Extra: uitars
+Provides-Extra: uitars-mlx
+Requires-Dist: mlx-vlm>=0.1.27; sys_platform == "darwin" and extra == "uitars-mlx"
+Provides-Extra: uitars-hf
+Requires-Dist: accelerate; extra == "uitars-hf"
+Requires-Dist: torch; extra == "uitars-hf"
+Requires-Dist: transformers>=4.54.0; extra == "uitars-hf"
+Provides-Extra: glm45v-hf
+Requires-Dist: accelerate; extra == "glm45v-hf"
+Requires-Dist: torch; extra == "glm45v-hf"
+Requires-Dist: transformers-v4.55.0-GLM-4.5V-preview; extra == "glm45v-hf"
+Provides-Extra: ui
+Requires-Dist: gradio>=5.23.3; extra == "ui"
+Requires-Dist: python-dotenv>=1.0.1; extra == "ui"
+Provides-Extra: cli
+Requires-Dist: yaspin>=3.1.0; extra == "cli"
+Provides-Extra: hud
+Requires-Dist: hud-python<0.5.0,>=0.4.12; extra == "hud"
+Provides-Extra: all
+Requires-Dist: mlx-vlm>=0.1.27; sys_platform == "darwin" and extra == "all"
+Requires-Dist: accelerate; extra == "all"
+Requires-Dist: torch; extra == "all"
+Requires-Dist: transformers>=4.54.0; extra == "all"
+Requires-Dist: gradio>=5.23.3; extra == "all"
+Requires-Dist: python-dotenv>=1.0.1; extra == "all"
+Requires-Dist: yaspin>=3.1.0; extra == "all"
+Requires-Dist: hud-python<0.5.0,>=0.4.12; extra == "all"
+Description-Content-Type: text/markdown
+
+<div align="center">
+<h1>
+  <div class="image-wrapper" style="display: inline-block;">
+    <picture>
+      <source media="(prefers-color-scheme: dark)" alt="logo" height="150" srcset="https://raw.githubusercontent.com/trycua/cua/main/img/logo_white.png" style="display: block; margin: auto;">
+      <source media="(prefers-color-scheme: light)" alt="logo" height="150" srcset="https://raw.githubusercontent.com/trycua/cua/main/img/logo_black.png" style="display: block; margin: auto;">
+      <img alt="Shows my svg">
+    </picture>
+  </div>
+
+  [![Python](https://img.shields.io/badge/Python-333333?logo=python&logoColor=white&labelColor=333333)](#)
+  [![macOS](https://img.shields.io/badge/macOS-000000?logo=apple&logoColor=F0F0F0)](#)
+  [![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?&logo=discord&logoColor=white)](https://discord.com/invite/mVnXXpdE85)
+  [![PyPI](https://img.shields.io/pypi/v/cua-computer?color=333333)](https://pypi.org/project/cua-computer/)
+</h1>
+</div>
+
+**cua-agent** is a general Computer-Use framework with liteLLM integration for running agentic workflows on macOS, Windows, and Linux sandboxes. It provides a unified interface for computer-use agents across multiple LLM providers with advanced callback system for extensibility.
+
+## Features
+
+- **Safe Computer-Use/Tool-Use**: Using Computer SDK for sandboxed desktops
+- **Multi-Agent Support**: Anthropic Claude, OpenAI computer-use-preview, UI-TARS, Omniparser + any LLM
+- **Multi-API Support**: Take advantage of liteLLM supporting 100+ LLMs / model APIs, including local models (`huggingface-local/`, `ollama_chat/`, `mlx/`)
+- **Cross-Platform**: Works on Windows, macOS, and Linux with cloud and local computer instances
+- **Extensible Callbacks**: Built-in support for image retention, cache control, PII anonymization, budget limits, and trajectory tracking
+
+## Install
+
+```bash
+pip install "cua-agent[all]"
+```
+
+## Quick Start
+
+```python
+import asyncio
+import os
+from agent import ComputerAgent
+from computer import Computer
+
+async def main():
+    # Set up computer instance
+    async with Computer(
+        os_type="linux",
+        provider_type="cloud",
+        name=os.getenv("CUA_CONTAINER_NAME"),
+        api_key=os.getenv("CUA_API_KEY")
+    ) as computer:
+        
+        # Create agent
+        agent = ComputerAgent(
+            model="anthropic/claude-3-5-sonnet-20241022",
+            tools=[computer],
+            only_n_most_recent_images=3,
+            trajectory_dir="trajectories",
+            max_trajectory_budget=5.0  # $5 budget limit
+        )
+        
+        # Run agent
+        messages = [{"role": "user", "content": "Take a screenshot and tell me what you see"}]
+        
+        async for result in agent.run(messages):
+            for item in result["output"]:
+                if item["type"] == "message":
+                    print(item["content"][0]["text"])
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+## Docs
+
+- [Agent Loops](https://trycua.com/docs/agent-sdk/agent-loops)
+- [Supported Agents](https://trycua.com/docs/agent-sdk/supported-agents)
+- [Supported Models](https://trycua.com/docs/agent-sdk/supported-models)
+- [Chat History](https://trycua.com/docs/agent-sdk/chat-history)
+- [Callbacks](https://trycua.com/docs/agent-sdk/callbacks)
+- [Custom Tools](https://trycua.com/docs/agent-sdk/custom-tools)
+- [Custom Computer Handlers](https://trycua.com/docs/agent-sdk/custom-computer-handlers)
+- [Prompt Caching](https://trycua.com/docs/agent-sdk/prompt-caching)
+- [Usage Tracking](https://trycua.com/docs/agent-sdk/usage-tracking)
+- [Benchmarks](https://trycua.com/docs/agent-sdk/benchmarks)
+
+## License
+
+MIT License - see LICENSE file for details.

{cua_agent-0.4.23.dist-info → cua_agent-0.4.25.dist-info}/RECORD

@@ -8,9 +8,9 @@ agent/agent.py,sha256=ao3SKnZoX5_P6mTzEg0hgOUam6bNRwpbitzlyvwI3bg,29826
 agent/callbacks/__init__.py,sha256=et6pNfX_AiJqhVzUfCvcjzFbDhfLoHazKCXN5sqwxaM,631
 agent/callbacks/base.py,sha256=UnnnYlh6XCm6HKZZsAPaT_Eyo9LUYLyjyNwF-QRm6Ns,4691
 agent/callbacks/budget_manager.py,sha256=RyKM-7iXQcDotYvrw3eURzeEHEXvQjID-NobtvQWE7k,1832
-agent/callbacks/image_retention.py,sha256=tiuRT5ke9xXTb2eP8Gz-2ITyAMY29LURUH6AbjX3RP8,6165
+agent/callbacks/image_retention.py,sha256=8MeLo5-Y7cACpsNk2p_bvnZIYKpW6XgyukmdYGX23rE,3588
 agent/callbacks/logging.py,sha256=OOxU97EzrxlnUAtiEnvy9FB7SwCUK90-rdpDFA2Ae4E,10921
-agent/callbacks/operator_validator.py,sha256=dLvR749glMPiGt8UP-XMLm_LcaTUUhWvRZJN_qkHV7Y,6430
+agent/callbacks/operator_validator.py,sha256=T5tp62pkShkcdHu2rgREUGdk8fryL_ziJsItXsfgYUQ,6494
 agent/callbacks/pii_anonymization.py,sha256=NEkUTUjQBi82nqus7kT-1E4RaeQ2hQrY7YCnKndLhP8,3272
 agent/callbacks/telemetry.py,sha256=RbUDhE41mTi8g9hNre0EpltK_NUZkLj8buJLWBzs0Ek,7363
 agent/callbacks/trajectory_saver.py,sha256=rslgg4Ak7JHSNmmJgANRQ5TsUYWGuUJDZ6amureaz_o,15963
@@ -23,11 +23,11 @@ agent/decorators.py,sha256=n8VvMsififWkmuk75Q7HIpo0xAA2yAeQ6J-OOiwbAKc,1836
 agent/human_tool/__init__.py,sha256=3m5_g-Fo_0yX5vi7eg-A92oTqO0N3aY929Ajp78HKsE,771
 agent/human_tool/__main__.py,sha256=VsW2BAghlonOuqZbP_xuCsaec9bemA1I_ibnDcED9D4,1068
 agent/human_tool/server.py,sha256=ceuL5kw_RjgAi8fueLU3nTjyzOLE25Shv1oTJnSHsoQ,7964
-agent/human_tool/ui.py,sha256=c5IbzVbj6dTtrswK3KKo6svjatQhQHHwzFA848U2Cw0,28130
+agent/human_tool/ui.py,sha256=wu9eZorhxCkyPTlBSZjYaVzutoHMlucAz8UGNpAT4bM,30644
 agent/integrations/hud/__init__.py,sha256=q0QEyJZSrcjiN2sRi_hoX-ePmLyYm9CpAIvA0xMxGJI,8360
 agent/integrations/hud/proxy.py,sha256=yA7C2jeXnrpI5HS0VgCvn0BflVbAORZynIfyE27rvBg,7782
 agent/loops/__init__.py,sha256=Ef8aj07l3osibwDk-DTo80PrpL4_GdKRTP1ikl_b-BQ,328
-agent/loops/anthropic.py,sha256=Th3dNv8FULvyDXx7aPVGSzbrqBiDNFXRso3DSa88d_w,70301
+agent/loops/anthropic.py,sha256=q7lr1PjI6VPtlozoweluY2c3hCGqa_2s-whzxa37iKE,70250
 agent/loops/base.py,sha256=LK7kSTnc2CB88LI7qr2VP7LMq0eS5r2bSEnrxO6IN5U,2345
 agent/loops/composed_grounded.py,sha256=8oJoqaRzKWbI9I4VoFuAoUzQ11_CFnYT-EdPOy-NVEQ,12349
 agent/loops/glm45v.py,sha256=V1f-5vAifbYcY-qTc7fW2KXVRkAfApQI_EjavH3X2ak,35110
@@ -45,7 +45,7 @@ agent/ui/__main__.py,sha256=vudWXYvGM0aNT5aZ94HPtGW8YXOZ4cLXepHyhUM_k1g,73
 agent/ui/gradio/__init__.py,sha256=yv4Mrfo-Sj2U5sVn_UJHAuwYCezo-5O4ItR2C9jzNko,145
 agent/ui/gradio/app.py,sha256=Ol97YEbwREZZQ9_PMjVHlfOcu9BGsawxgAGAm79hT80,9117
 agent/ui/gradio/ui_components.py,sha256=dJUvKDmc1oSejtoR_gU_oWWYwxaOOQyPloSYRGMrUCQ,36068
-cua_agent-0.4.23.dist-info/METADATA,sha256=pBBwUDqUNHDWsNyueuDPr3N3OMHWvfTD8uPncS7rWVg,12712
-cua_agent-0.4.23.dist-info/WHEEL,sha256=9P2ygRxDrTJz3gsagc0Z96ukrxjr-LFBGOgv3AuKlCA,90
-cua_agent-0.4.23.dist-info/entry_points.txt,sha256=6OYgBcLyFCUgeqLgnvMyOJxPCWzgy7se4rLPKtNonMs,34
-cua_agent-0.4.23.dist-info/RECORD,,
+cua_agent-0.4.25.dist-info/METADATA,sha256=RddHOGfOJVdXhPQMXCj1c7RLBJcmH2yZMwS36dbnB5Q,5624
+cua_agent-0.4.25.dist-info/WHEEL,sha256=9P2ygRxDrTJz3gsagc0Z96ukrxjr-LFBGOgv3AuKlCA,90
+cua_agent-0.4.25.dist-info/entry_points.txt,sha256=6OYgBcLyFCUgeqLgnvMyOJxPCWzgy7se4rLPKtNonMs,34
+cua_agent-0.4.25.dist-info/RECORD,,

cua_agent-0.4.23.dist-info/METADATA

@@ -1,436 +0,0 @@
-Metadata-Version: 2.1
-Name: cua-agent
-Version: 0.4.23
-Summary: CUA (Computer Use) Agent for AI-driven computer interaction
-Author-Email: TryCua <gh@trycua.com>
-Requires-Python: >=3.12
-Requires-Dist: httpx>=0.27.0
-Requires-Dist: aiohttp>=3.9.3
-Requires-Dist: asyncio
-Requires-Dist: anyio>=4.4.1
-Requires-Dist: typing-extensions>=4.12.2
-Requires-Dist: pydantic>=2.6.4
-Requires-Dist: rich>=13.7.1
-Requires-Dist: python-dotenv>=1.0.1
-Requires-Dist: cua-computer<0.5.0,>=0.4.0
-Requires-Dist: cua-core<0.2.0,>=0.1.8
-Requires-Dist: certifi>=2024.2.2
-Requires-Dist: litellm>=1.74.12
-Provides-Extra: openai
-Provides-Extra: anthropic
-Provides-Extra: omni
-Requires-Dist: ultralytics>=8.0.0; extra == "omni"
-Requires-Dist: cua-som<0.2.0,>=0.1.0; extra == "omni"
-Provides-Extra: uitars
-Provides-Extra: uitars-mlx
-Requires-Dist: mlx-vlm>=0.1.27; sys_platform == "darwin" and extra == "uitars-mlx"
-Provides-Extra: uitars-hf
-Requires-Dist: accelerate; extra == "uitars-hf"
-Requires-Dist: torch; extra == "uitars-hf"
-Requires-Dist: transformers>=4.54.0; extra == "uitars-hf"
-Provides-Extra: glm45v-hf
-Requires-Dist: accelerate; extra == "glm45v-hf"
-Requires-Dist: torch; extra == "glm45v-hf"
-Requires-Dist: transformers-v4.55.0-GLM-4.5V-preview; extra == "glm45v-hf"
-Provides-Extra: ui
-Requires-Dist: gradio>=5.23.3; extra == "ui"
-Requires-Dist: python-dotenv>=1.0.1; extra == "ui"
-Provides-Extra: cli
-Requires-Dist: yaspin>=3.1.0; extra == "cli"
-Provides-Extra: hud
-Requires-Dist: hud-python<0.5.0,>=0.4.12; extra == "hud"
-Provides-Extra: all
-Requires-Dist: ultralytics>=8.0.0; extra == "all"
-Requires-Dist: cua-som<0.2.0,>=0.1.0; extra == "all"
-Requires-Dist: mlx-vlm>=0.1.27; sys_platform == "darwin" and extra == "all"
-Requires-Dist: accelerate; extra == "all"
-Requires-Dist: torch; extra == "all"
-Requires-Dist: transformers>=4.54.0; extra == "all"
-Requires-Dist: gradio>=5.23.3; extra == "all"
-Requires-Dist: python-dotenv>=1.0.1; extra == "all"
-Requires-Dist: yaspin>=3.1.0; extra == "all"
-Requires-Dist: hud-python<0.5.0,>=0.4.12; extra == "all"
-Description-Content-Type: text/markdown
-
-<div align="center">
-<h1>
-  <div class="image-wrapper" style="display: inline-block;">
-    <picture>
-      <source media="(prefers-color-scheme: dark)" alt="logo" height="150" srcset="https://raw.githubusercontent.com/trycua/cua/main/img/logo_white.png" style="display: block; margin: auto;">
-      <source media="(prefers-color-scheme: light)" alt="logo" height="150" srcset="https://raw.githubusercontent.com/trycua/cua/main/img/logo_black.png" style="display: block; margin: auto;">
-      <img alt="Shows my svg">
-    </picture>
-  </div>
-
-  [![Python](https://img.shields.io/badge/Python-333333?logo=python&logoColor=white&labelColor=333333)](#)
-  [![macOS](https://img.shields.io/badge/macOS-000000?logo=apple&logoColor=F0F0F0)](#)
-  [![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?&logo=discord&logoColor=white)](https://discord.com/invite/mVnXXpdE85)
-  [![PyPI](https://img.shields.io/pypi/v/cua-computer?color=333333)](https://pypi.org/project/cua-computer/)
-</h1>
-</div>
-
-**cua-agent** is a general Computer-Use framework with liteLLM integration for running agentic workflows on macOS, Windows, and Linux sandboxes. It provides a unified interface for computer-use agents across multiple LLM providers with advanced callback system for extensibility.
-
-## Features
-
-- **Safe Computer-Use/Tool-Use**: Using Computer SDK for sandboxed desktops
-- **Multi-Agent Support**: Anthropic Claude, OpenAI computer-use-preview, UI-TARS, Omniparser + any LLM
-- **Multi-API Support**: Take advantage of liteLLM supporting 100+ LLMs / model APIs, including local models (`huggingface-local/`, `ollama_chat/`, `mlx/`)
-- **Cross-Platform**: Works on Windows, macOS, and Linux with cloud and local computer instances
-- **Extensible Callbacks**: Built-in support for image retention, cache control, PII anonymization, budget limits, and trajectory tracking
-
-## Install
-
-```bash
-pip install "cua-agent[all]"
-
-# or install specific providers
-pip install "cua-agent[openai]"        # OpenAI computer-use-preview support
-pip install "cua-agent[anthropic]"     # Anthropic Claude support
-pip install "cua-agent[omni]"          # Omniparser + any LLM support
-pip install "cua-agent[uitars]"        # UI-TARS
-pip install "cua-agent[uitars-mlx]"    # UI-TARS + MLX support
-pip install "cua-agent[uitars-hf]"     # UI-TARS + Huggingface support
-pip install "cua-agent[glm45v-hf]"     # GLM-4.5V + Huggingface support
-pip install "cua-agent[ui]"            # Gradio UI support
-```
-
-## Quick Start
-
-```python
-import asyncio
-import os
-from agent import ComputerAgent
-from computer import Computer
-
-async def main():
-    # Set up computer instance
-    async with Computer(
-        os_type="linux",
-        provider_type="cloud",
-        name=os.getenv("CUA_CONTAINER_NAME"),
-        api_key=os.getenv("CUA_API_KEY")
-    ) as computer:
-        
-        # Create agent
-        agent = ComputerAgent(
-            model="anthropic/claude-3-5-sonnet-20241022",
-            tools=[computer],
-            only_n_most_recent_images=3,
-            trajectory_dir="trajectories",
-            max_trajectory_budget=5.0  # $5 budget limit
-        )
-        
-        # Run agent
-        messages = [{"role": "user", "content": "Take a screenshot and tell me what you see"}]
-        
-        async for result in agent.run(messages):
-            for item in result["output"]:
-                if item["type"] == "message":
-                    print(item["content"][0]["text"])
-
-if __name__ == "__main__":
-    asyncio.run(main())
-```
-
-## Supported Models
-
-### Anthropic Claude (Computer Use API)
-```python
-model="anthropic/claude-3-5-sonnet-20241022"
-model="anthropic/claude-3-7-sonnet-20250219"
-model="anthropic/claude-opus-4-20250514"
-model="anthropic/claude-sonnet-4-20250514"
-```
-
-### OpenAI Computer Use Preview
-```python
-model="openai/computer-use-preview"
-```
-
-### UI-TARS (Local or Huggingface Inference)
-```python
-model="huggingface-local/ByteDance-Seed/UI-TARS-1.5-7B"
-model="ollama_chat/0000/ui-tars-1.5-7b"
-```
-
-### Omniparser + Any LLM
-```python
-model="omniparser+ollama_chat/mistral-small3.2"
-model="omniparser+vertex_ai/gemini-pro"
-model="omniparser+anthropic/claude-3-5-sonnet-20241022"
-model="omniparser+openai/gpt-4o"
-```
-
-## Custom Tools
-
-Define custom tools using decorated functions:
-
-```python
-from computer.helpers import sandboxed
-
-@sandboxed()
-def read_file(location: str) -> str:
-    """Read contents of a file
-    
-    Parameters
-    ----------
-    location : str
-        Path to the file to read
-        
-    Returns
-    -------
-    str
-        Contents of the file or error message
-    """
-    try:
-        with open(location, 'r') as f:
-            return f.read()
-    except Exception as e:
-        return f"Error reading file: {str(e)}"
-
-def calculate(a: int, b: int) -> int:
-    """Calculate the sum of two integers"""
-    return a + b
-
-# Use with agent
-agent = ComputerAgent(
-    model="anthropic/claude-3-5-sonnet-20241022",
-    tools=[computer, read_file, calculate]
-)
-```
-
-## Callbacks System
-
-agent provides a comprehensive callback system for extending functionality:
-
-### Built-in Callbacks
-
-```python
-from agent.callbacks import (
-    ImageRetentionCallback,
-    TrajectorySaverCallback, 
-    BudgetManagerCallback,
-    LoggingCallback
-)
-
-agent = ComputerAgent(
-    model="anthropic/claude-3-5-sonnet-20241022",
-    tools=[computer],
-    callbacks=[
-        ImageRetentionCallback(only_n_most_recent_images=3),
-        TrajectorySaverCallback(trajectory_dir="trajectories"),
-        BudgetManagerCallback(max_budget=10.0, raise_error=True),
-        LoggingCallback(level=logging.INFO)
-    ]
-)
-```
-
-### Custom Callbacks
-
-```python
-from agent.callbacks.base import AsyncCallbackHandler
-
-class CustomCallback(AsyncCallbackHandler):
-    async def on_llm_start(self, messages):
-        """Preprocess messages before LLM call"""
-        # Add custom preprocessing logic
-        return messages
-    
-    async def on_llm_end(self, messages):
-        """Postprocess messages after LLM call"""
-        # Add custom postprocessing logic
-        return messages
-    
-    async def on_usage(self, usage):
-        """Track usage information"""
-        print(f"Tokens used: {usage.total_tokens}")
-```
-
-## Budget Management
-
-Control costs with built-in budget management:
-
-```python
-# Simple budget limit
-agent = ComputerAgent(
-    model="anthropic/claude-3-5-sonnet-20241022",
-    max_trajectory_budget=5.0  # $5 limit
-)
-
-# Advanced budget configuration
-agent = ComputerAgent(
-    model="anthropic/claude-3-5-sonnet-20241022",
-    max_trajectory_budget={
-        "max_budget": 10.0,
-        "raise_error": True,  # Raise error when exceeded
-        "reset_after_each_run": False  # Persistent across runs
-    }
-)
-```
-
-## Trajectory Management
-
-Save and replay agent conversations:
-
-```python
-agent = ComputerAgent(
-    model="anthropic/claude-3-5-sonnet-20241022",
-    trajectory_dir="trajectories",  # Auto-save trajectories
-    tools=[computer]
-)
-
-# Trajectories are saved with:
-# - Complete conversation history
-# - Usage statistics and costs
-# - Timestamps and metadata
-# - Screenshots and computer actions
-```
-
-## Configuration Options
-
-### ComputerAgent Parameters
-
-- `model`: Model identifier (required)
-- `tools`: List of computer objects and decorated functions
-- `callbacks`: List of callback handlers for extensibility
-- `only_n_most_recent_images`: Limit recent images to prevent context overflow
-- `verbosity`: Logging level (logging.INFO, logging.DEBUG, etc.)
-- `trajectory_dir`: Directory to save conversation trajectories
-- `max_retries`: Maximum API call retries (default: 3)
-- `screenshot_delay`: Delay between actions and screenshots (default: 0.5s)
-- `use_prompt_caching`: Enable prompt caching for supported models
-- `max_trajectory_budget`: Budget limit configuration
-
-### Environment Variables
-
-```bash
-# Computer instance (cloud)
-export CUA_CONTAINER_NAME="your-container-name"
-export CUA_API_KEY="your-cua-api-key"
-
-# LLM API keys
-export ANTHROPIC_API_KEY="your-anthropic-key"
-export OPENAI_API_KEY="your-openai-key"
-```
-
-## Advanced Usage
-
-### Streaming Responses
-
-```python
-async for result in agent.run(messages, stream=True):
-    # Process streaming chunks
-    for item in result["output"]:
-        if item["type"] == "message":
-            print(item["content"][0]["text"], end="", flush=True)
-        elif item["type"] == "computer_call":
-            action = item["action"]
-            print(f"\n[Action: {action['type']}]")
-```
-
-### Interactive Chat Loop
-
-```python
-history = []
-while True:
-    user_input = input("> ")
-    if user_input.lower() in ['quit', 'exit']:
-        break
-        
-    history.append({"role": "user", "content": user_input})
-    
-    async for result in agent.run(history):
-        history += result["output"]
-        
-        # Display assistant responses
-        for item in result["output"]:
-            if item["type"] == "message":
-                print(item["content"][0]["text"])
-```
-
-### Error Handling
-
-```python
-try:
-    async for result in agent.run(messages):
-        # Process results
-        pass
-except BudgetExceededException:
-    print("Budget limit exceeded")
-except Exception as e:
-    print(f"Agent error: {e}")
-```
-
-## API Reference
-
-### ComputerAgent.run()
-
-```python
-async def run(
-    self,
-    messages: Messages,
-    stream: bool = False,
-    **kwargs
-) -> AsyncGenerator[Dict[str, Any], None]:
-    """
-    Run the agent with the given messages.
-    
-    Args:
-        messages: List of message dictionaries
-        stream: Whether to stream the response
-        **kwargs: Additional arguments
-        
-    Returns:
-        AsyncGenerator that yields response chunks
-    """
-```
-
-### Message Format
-
-```python
-messages = [
-    {
-        "role": "user",
-        "content": "Take a screenshot and describe what you see"
-    },
-    {
-        "role": "assistant", 
-        "content": "I'll take a screenshot for you."
-    }
-]
-```
-
-### Response Format
-
-```python
-{
-    "output": [
-        {
-            "type": "message",
-            "role": "assistant",
-            "content": [{"type": "output_text", "text": "I can see..."}]
-        },
-        {
-            "type": "computer_call",
-            "action": {"type": "screenshot"},
-            "call_id": "call_123"
-        },
-        {
-            "type": "computer_call_output",
-            "call_id": "call_123",
-            "output": {"image_url": "data:image/png;base64,..."}
-        }
-    ],
-    "usage": {
-        "prompt_tokens": 150,
-        "completion_tokens": 75,
-        "total_tokens": 225,
-        "response_cost": 0.01,
-    }
-}
-```
-
-## License
-
-MIT License - see LICENSE file for details.