cua-agent 0.2.5__py3-none-any.whl → 0.2.7__py3-none-any.whl

agent/core/tools.py

@@ -1,10 +1,10 @@
 """Tool-related type definitions."""
 
-from enum import Enum
+from enum import StrEnum
 from typing import Dict, Any, Optional
 from pydantic import BaseModel, ConfigDict
 
-class ToolInvocationState(str, Enum):
+class ToolInvocationState(StrEnum):
     """States for tool invocation."""
     CALL = 'call'
     PARTIAL_CALL = 'partial-call'

agent/core/types.py

@@ -1,18 +1,18 @@
 """Core type definitions."""
 
 from typing import Any, Dict, List, Optional, TypedDict, Union
-from enum import Enum, StrEnum, auto
+from enum import StrEnum
 from dataclasses import dataclass
 
 
-class AgentLoop(Enum):
+class AgentLoop(StrEnum):
     """Enumeration of available loop types."""
 
-    ANTHROPIC = auto()  # Anthropic implementation
-    OMNI = auto()  # OmniLoop implementation
-    OPENAI = auto()  # OpenAI implementation
-    OLLAMA = auto()  # OLLAMA implementation
-    UITARS = auto()  # UI-TARS implementation
+    ANTHROPIC = "anthropic"  # Anthropic implementation
+    OMNI = "omni"  # OmniLoop implementation
+    OPENAI = "openai"  # OpenAI implementation
+    OLLAMA = "ollama"  # OLLAMA implementation
+    UITARS = "uitars"  # UI-TARS implementation
     # Add more loop types as needed
 
 

agent/providers/anthropic/prompts.py

@@ -3,6 +3,9 @@
 from datetime import datetime
 import platform
 
+today = datetime.today()
+today = f"{today.strftime('%A, %B')} {today.day}, {today.year}"
+
 SYSTEM_PROMPT = f"""<SYSTEM_CAPABILITY>
 * You are utilising a macOS virtual machine using ARM architecture with internet access and Safari as default browser.
 * You can feel free to install macOS applications with your bash tool. Use curl instead of wget.
@@ -10,7 +13,7 @@ SYSTEM_PROMPT = f"""<SYSTEM_CAPABILITY>
 * When using your bash tool with commands that are expected to output very large quantities of text, redirect into a tmp file and use str_replace_editor or `grep -n -B <lines before> -A <lines after> <query> <filename>` to confirm output.
 * When viewing a page it can be helpful to zoom out so that you can see everything on the page.  Either that, or make sure you scroll down to see everything before deciding something isn't available.
 * When using your computer function calls, they take a while to run and send back to you.  Where possible/feasible, try to chain multiple of these calls all into one function calls request.
-* The current date is {datetime.today().strftime('%A, %B %-d, %Y')}.
+* The current date is {today}.
 </SYSTEM_CAPABILITY>
 
 <IMPORTANT>

agent/providers/anthropic/tools/computer.py

@@ -478,17 +478,11 @@ class ComputerTool(BaseComputerTool, BaseAnthropicTool):
                 if direction == "down":
                     # Scroll down (Page Down on macOS)
                     self.logger.info(f"Scrolling down, amount: {amount}")
-                    # Use fn+down for page down on macOS
-                    for _ in range(amount):
-                        await self.computer.interface.hotkey("fn", "down")
-                        await asyncio.sleep(0.1)
+                    await self.computer.interface.scroll_down(amount)
                 else:
                     # Scroll up (Page Up on macOS)
                     self.logger.info(f"Scrolling up, amount: {amount}")
-                    # Use fn+up for page up on macOS
-                    for _ in range(amount):
-                        await self.computer.interface.hotkey("fn", "up")
-                        await asyncio.sleep(0.1)
+                    await self.computer.interface.scroll_up(amount)
 
                 # Wait briefly for UI changes
                 await asyncio.sleep(0.5)

agent/ui/gradio/app.py

@@ -22,7 +22,7 @@ Supported Agent Loops and Models:
 Requirements:
     - Mac with Apple Silicon (M1/M2/M3/M4)
     - macOS 14 (Sonoma) or newer
-    - Python 3.10+
+    - Python 3.11+
     - Lume CLI installed (https://github.com/trycua/cua)
     - OpenAI or Anthropic API key
 """
@@ -31,6 +31,7 @@ import os
 import asyncio
 import logging
 import json
+import platform
 from pathlib import Path
 from typing import Dict, List, Optional, AsyncGenerator, Any, Tuple, Union
 import gradio as gr
@@ -129,6 +130,9 @@ class GradioChatScreenshotHandler(DefaultCallbackHandler):
             )
 
 
+# Detect if current device is MacOS
+is_mac = platform.system().lower() == "darwin"
+
 # Map model names to specific provider model names
 MODEL_MAPPINGS = {
     "openai": {
@@ -165,7 +169,7 @@ MODEL_MAPPINGS = {
     },
     "uitars": {
         # UI-TARS models using MLXVLM provider
-        "default": "mlx-community/UI-TARS-1.5-7B-4bit",
+        "default": "mlx-community/UI-TARS-1.5-7B-4bit" if is_mac else "tgi",
         "mlx-community/UI-TARS-1.5-7B-4bit": "mlx-community/UI-TARS-1.5-7B-4bit",
         "mlx-community/UI-TARS-1.5-7B-6bit": "mlx-community/UI-TARS-1.5-7B-6bit"
     },
@@ -475,16 +479,18 @@ def create_gradio_ui(
     if ollama_models:
         omni_models += ollama_models
 
+    # Detect if current device is MacOS
+    is_mac = platform.system().lower() == "darwin"
+    
     # Format model choices
     provider_to_models = {
         "OPENAI": openai_models,
         "ANTHROPIC": anthropic_models,
         "OMNI": omni_models + ["Custom model (OpenAI compatible API)", "Custom model (ollama)"],  # Add custom model options
-        "UITARS": [
+        "UITARS": ([
             "mlx-community/UI-TARS-1.5-7B-4bit",
             "mlx-community/UI-TARS-1.5-7B-6bit",
-            "Custom model (OpenAI compatible API)"
-        ],  # UI-TARS options with MLX models
+        ] if is_mac else []) + ["Custom model (OpenAI compatible API)"],  # UI-TARS options with MLX models
     }
 
     # --- Apply Saved Settings (override defaults if available) ---
@@ -730,10 +736,14 @@ if __name__ == "__main__":
                         info="Select the operating system for the computer",
                     )
                     
+                    # Detect if current device is MacOS
+                    is_mac = platform.system().lower() == "darwin"
+                    
                     computer_provider = gr.Radio(
                         choices=["cloud", "lume"],
                         label="Provider",
-                        value="lume",
+                        value="lume" if is_mac else "cloud",
+                        visible=is_mac,
                         info="Select the computer provider",
                     )
                     
@@ -1445,7 +1455,7 @@ if __name__ == "__main__":
 def test_cua():
     """Standalone function to launch the Gradio app."""
     demo = create_gradio_ui()
-    demo.launch(share=False)  # Don't create a public link
+    demo.launch(share=False, inbrowser=True)  # Don't create a public link
 
 
 if __name__ == "__main__":

{cua_agent-0.2.5.dist-info → cua_agent-0.2.7.dist-info}/METADATA

@@ -1,9 +1,9 @@
 Metadata-Version: 2.1
 Name: cua-agent
-Version: 0.2.5
+Version: 0.2.7
 Summary: CUA (Computer Use) Agent for AI-driven computer interaction
 Author-Email: TryCua <gh@trycua.com>
-Requires-Python: >=3.10
+Requires-Python: >=3.11
 Requires-Dist: httpx<0.29.0,>=0.27.0
 Requires-Dist: aiohttp<4.0.0,>=3.9.3
 Requires-Dist: asyncio

{cua_agent-0.2.5.dist-info → cua_agent-0.2.7.dist-info}/RECORD

@@ -8,7 +8,7 @@ agent/core/factory.py,sha256=zzlCdibctqhf8Uta-SrvE-G7h59wAw-7SGhHiGvS9GY,4608
 agent/core/messages.py,sha256=-OVMDqcxK5MUHPEkHliK29XFJYMRAc1keFvzrUyrOmM,16231
 agent/core/provider_config.py,sha256=jB3fLsEsf806HQZ8jtzfSq4bCYGYONBeuCOoog_Nv_Y,768
 agent/core/telemetry.py,sha256=HElPd32k_w2SJ6t-Cc3j_2-AKdLbFwh2YlM8QViDgRw,4790
-agent/core/tools.py,sha256=Jes2CFCFqC727WWHbO-sG7V03rBHnQe5X7Oi9ZkuScI,877
+agent/core/tools.py,sha256=53aPme3O8U91n122Smu3TGbyGjQQe2zDimaZgKkFNi0,878
 agent/core/tools/__init__.py,sha256=xZen-PqUp2dUaMEHJowXCQm33_5Sxhsx9PSoD0rq6tI,489
 agent/core/tools/base.py,sha256=CdzRFNuOjNfzgyTUN4ZoCGkUDR5HI0ECQVpvrUdEij8,2295
 agent/core/tools/bash.py,sha256=jnJKVlHn8np8e0gWd8EO0_qqjMkfQzutSugA_Iol4jE,1585
@@ -16,7 +16,7 @@ agent/core/tools/collection.py,sha256=NuwTn6dXSyznxWodfmFDQwUlxxaGb4oBPym4AEJABS
 agent/core/tools/computer.py,sha256=lT_aW3huoYpcM8kffuokELupSz_WZG_qkaW1gITRC58,3892
 agent/core/tools/edit.py,sha256=kv4jTKCM0VXrnoNErf7mT-xlr81-7T8v49_VA9y_L4Y,2005
 agent/core/tools/manager.py,sha256=IRsCXjGc076nncQuyIjODoafnHTDhrf9sP5B4q5Pcdo,1742
-agent/core/types.py,sha256=tkT-PqjgjL0oWVBRFkHAGWVwYx2Byp7PlUWSpvw_-h8,2442
+agent/core/types.py,sha256=8DBbj2v9EYZ7e4NKbYHnZuWRsGV6tuij7FRSLRrg89I,2444
 agent/core/visualization.py,sha256=1DuFF5sSeSf5BRSevBMDxml9-ajl7BQLFm5KBUwMbI8,6573
 agent/providers/__init__.py,sha256=b4tIBAaIB1V7p8V0BWipHVnMhfHH_OuVgP4OWGSHdD8,194
 agent/providers/anthropic/__init__.py,sha256=Mj11IZnVshZ2iHkvg4Z5-jrQIaD1WvzDz2Zk_pMwqIA,149
@@ -26,13 +26,13 @@ agent/providers/anthropic/api_handler.py,sha256=pWXcqDs0ruviDhRNRrz5Ac9ZH4yDv6Zl
 agent/providers/anthropic/callbacks/__init__.py,sha256=PciBb6Z6MKSwfXqDjU3pV_0FS4MOn_Np_A7_skD-6dA,104
 agent/providers/anthropic/callbacks/manager.py,sha256=euIah5yiM8nhisN-RWXewo6v0WQr0c-FbMBO04r6dJk,1865
 agent/providers/anthropic/loop.py,sha256=Sepfo0b0oQT98xd3Sv2S7Xc81bfU7L4_Zv3VTiapKkg,21661
-agent/providers/anthropic/prompts.py,sha256=nHFfgPrfvnWrEdVP7EUBGUHAI85D2X9HeZirk9EwncU,1941
+agent/providers/anthropic/prompts.py,sha256=EaqyvUb90yybv75VsBYzu4sroga7eMACys0uH9mIVWM,1993
 agent/providers/anthropic/response_handler.py,sha256=ZTprV4NTP9Eb9jQ7QgEKZBX0L6rMj5nqBRiE3Zfws8I,8008
 agent/providers/anthropic/tools/__init__.py,sha256=JyZwuVtPUnZwRSZBSCdQv9yxbLCsygm3l8Ywjjt9qTQ,661
 agent/providers/anthropic/tools/base.py,sha256=WnRDbqO25tQzLpS2RU2ZXTLF5wd5IqU7SiyRAglQat4,2752
 agent/providers/anthropic/tools/bash.py,sha256=QODuFjWuHM4GgGTqK2HizSyYqGqQwX70AdwrFiGSp2Q,2218
 agent/providers/anthropic/tools/collection.py,sha256=RBK_6hxfHExR-EOxadiLl0OznmFj07nyIUjFgaYZ6Eo,960
-agent/providers/anthropic/tools/computer.py,sha256=HWirLMkG_29X7wYSysQlKt2Zliq6ifsHaY8-bKrp4Fw,25933
+agent/providers/anthropic/tools/computer.py,sha256=3MWMGOy_xDXOg5B7CvQDVNts2WQ9NcAyfzsLEMxt5ME,25627
 agent/providers/anthropic/tools/edit.py,sha256=EGRP61MDA4Oue1D7Q-_vLpd6LdGbdBA1Z4HSZ66DbmI,13465
 agent/providers/anthropic/tools/manager.py,sha256=yNvgTkfEqnOz5isDF0RxvmBMZB0uh2PipFEH-PUXpoY,2020
 agent/providers/anthropic/tools/run.py,sha256=xhXdnBK1di9muaO44CEirL9hpGy3NmKbjfMpyeVmn8Y,1595
@@ -79,8 +79,8 @@ agent/providers/uitars/utils.py,sha256=493STTEEJcVhVbQgR0e8rNTI1DjkxUx8IgIv3wkJ1
 agent/telemetry.py,sha256=pVGxbj0ewnvq4EGj28CydN4a1iOfvZR_XKL3vIOqhOM,390
 agent/ui/__init__.py,sha256=ohhxJLBin6k1hl5sKcmBST8mgh23WXgAXz3pN4f470E,45
 agent/ui/gradio/__init__.py,sha256=ANKZhv1HqsLheWbLVBlyRQ7Q5qGeXuPi5jDs8vu-ZMo,579
-agent/ui/gradio/app.py,sha256=zwc-boCJshWRE3vwV95NjqVv3mSMzRLjFeiMlfmyPbQ,70223
-cua_agent-0.2.5.dist-info/METADATA,sha256=WAh_WUblNwCBX0qNkEB3hoAQB3OH9c1JMs_pBL9DmXo,12688
-cua_agent-0.2.5.dist-info/WHEEL,sha256=tSfRZzRHthuv7vxpI4aehrdN9scLjk-dCJkPLzkHxGg,90
-cua_agent-0.2.5.dist-info/entry_points.txt,sha256=6OYgBcLyFCUgeqLgnvMyOJxPCWzgy7se4rLPKtNonMs,34
-cua_agent-0.2.5.dist-info/RECORD,,
+agent/ui/gradio/app.py,sha256=StBehGfPJhE6ywnxU3CHDPkZrOm_2XMT1Npepf89G5c,70675
+cua_agent-0.2.7.dist-info/METADATA,sha256=Jdz7v8P_JvHbN1vEcIyDzf2a51FUJQ5D4WJqL9cLbyA,12688
+cua_agent-0.2.7.dist-info/WHEEL,sha256=tSfRZzRHthuv7vxpI4aehrdN9scLjk-dCJkPLzkHxGg,90
+cua_agent-0.2.7.dist-info/entry_points.txt,sha256=6OYgBcLyFCUgeqLgnvMyOJxPCWzgy7se4rLPKtNonMs,34
+cua_agent-0.2.7.dist-info/RECORD,,