cua-agent 0.4.13__py3-none-any.whl → 0.4.15__py3-none-any.whl

agent/__init__.py

@@ -28,13 +28,9 @@ try:
     # Import from core telemetry for basic functions
     from core.telemetry import (
         is_telemetry_enabled,
-        flush,
         record_event,
     )
 
-    # Import set_dimension from our own telemetry module
-    from .telemetry import set_dimension
-
     # Check if telemetry is enabled
     if is_telemetry_enabled():
         logger.info("Telemetry is enabled")
@@ -49,11 +45,6 @@ try:
             },
         )
 
-        # Set the package version as a dimension
-        set_dimension("agent_version", __version__)
-
-        # Flush events to ensure they're sent
-        flush()
     else:
         logger.info("Telemetry is disabled")
 except ImportError as e:

agent/callbacks/telemetry.py

@@ -7,13 +7,18 @@ import uuid
 from typing import List, Dict, Any, Optional, Union
 
 from .base import AsyncCallbackHandler
-from ..telemetry import (
+from core.telemetry import (
     record_event,
     is_telemetry_enabled,
-    set_dimension,
-    SYSTEM_INFO,
 )
 
+import platform
+
+SYSTEM_INFO = {
+    "os": platform.system().lower(),
+    "os_version": platform.release(),
+    "python_version": platform.python_version(),
+}
 
 class TelemetryCallback(AsyncCallbackHandler):
     """
@@ -65,11 +70,6 @@ class TelemetryCallback(AsyncCallbackHandler):
             **SYSTEM_INFO
         }
         
-        # Set session-level dimensions
-        set_dimension("session_id", self.session_id)
-        set_dimension("agent_type", agent_info["agent_type"])
-        set_dimension("model", agent_info["model"])
-        
         record_event("agent_session_start", agent_info)
     
     async def on_run_start(self, kwargs: Dict[str, Any], old_items: List[Dict[str, Any]]) -> None:
@@ -98,7 +98,6 @@ class TelemetryCallback(AsyncCallbackHandler):
             if trajectory:
                 run_data["uploaded_trajectory"] = trajectory
         
-        set_dimension("run_id", self.run_id)
         record_event("agent_run_start", run_data)
     
     async def on_run_end(self, kwargs: Dict[str, Any], old_items: List[Dict[str, Any]], new_items: List[Dict[str, Any]]) -> None:

agent/loops/uitars.py

@@ -782,11 +782,19 @@ class UITARSConfig:
             # Extract response content
             response_content = response.choices[0].message.content.strip() # type: ignore
             
+            print(response_content)
+
             # Parse the response to extract click coordinates
-            # Look for click action with coordinates
+            # Look for click action with coordinates (with special tokens)
             click_pattern = r"click\(point='<\|box_start\|>\((\d+),(\d+)\)<\|box_end\|>'\)"
             match = re.search(click_pattern, response_content)
             
+            # Fallback: Look for simpler format without special tokens
+            if not match:
+                # Pattern for: click(start_box='(x,y)') or click(point='(x,y)')
+                fallback_pattern = r"click\((?:start_box|point)='\((\d+),(\d+)\)'\)"
+                match = re.search(fallback_pattern, response_content)
+            
             if match:
                 x, y = int(match.group(1)), int(match.group(2))
                 # Scale coordinates back to original image dimensions

agent/ui/gradio/app.py

@@ -114,14 +114,14 @@ MODEL_MAPPINGS = {
         "Anthropic: Claude 4 Opus (20250514)": "anthropic/claude-opus-4-20250514",
         "Anthropic: Claude 4 Sonnet (20250514)": "anthropic/claude-sonnet-4-20250514",
         "Anthropic: Claude 3.7 Sonnet (20250219)": "anthropic/claude-3-7-sonnet-20250219",
-        "Anthropic: Claude 3.5 Sonnet (20240620)": "anthropic/claude-3-5-sonnet-20240620",
+        "Anthropic: Claude 3.5 Sonnet (20241022)": "anthropic/claude-3-5-sonnet-20241022",
     },
     "omni": {
         "default": "omniparser+openai/gpt-4o",
         "OMNI: OpenAI GPT-4o": "omniparser+openai/gpt-4o",
         "OMNI: OpenAI GPT-4o mini": "omniparser+openai/gpt-4o-mini",
         "OMNI: Claude 3.7 Sonnet (20250219)": "omniparser+anthropic/claude-3-7-sonnet-20250219",
-        "OMNI: Claude 3.5 Sonnet (20240620)": "omniparser+anthropic/claude-3-5-sonnet-20240620",
+        "OMNI: Claude 3.5 Sonnet (20241022)": "omniparser+anthropic/claude-3-5-sonnet-20241022",
     },
     "uitars": {
         "default": "huggingface-local/ByteDance-Seed/UI-TARS-1.5-7B" if is_mac else "ui-tars",

agent/ui/gradio/ui_components.py

@@ -38,13 +38,13 @@ def create_gradio_ui() -> gr.Blocks:
         "Anthropic: Claude 4 Opus (20250514)",
         "Anthropic: Claude 4 Sonnet (20250514)",
         "Anthropic: Claude 3.7 Sonnet (20250219)",
-        "Anthropic: Claude 3.5 Sonnet (20240620)",
+        "Anthropic: Claude 3.5 Sonnet (20241022)",
     ]
     omni_models = [
         "OMNI: OpenAI GPT-4o",
         "OMNI: OpenAI GPT-4o mini",
         "OMNI: Claude 3.7 Sonnet (20250219)", 
-        "OMNI: Claude 3.5 Sonnet (20240620)"
+        "OMNI: Claude 3.5 Sonnet (20241022)"
     ]
     
     # Check if API keys are available

{cua_agent-0.4.13.dist-info → cua_agent-0.4.15.dist-info}/METADATA

@@ -1,9 +1,9 @@
 Metadata-Version: 2.1
 Name: cua-agent
-Version: 0.4.13
+Version: 0.4.15
 Summary: CUA (Computer Use) Agent for AI-driven computer interaction
 Author-Email: TryCua <gh@trycua.com>
-Requires-Python: >=3.11
+Requires-Python: >=3.12
 Requires-Dist: httpx>=0.27.0
 Requires-Dist: aiohttp>=3.9.3
 Requires-Dist: asyncio
@@ -138,7 +138,7 @@ if __name__ == "__main__":
 ### Anthropic Claude (Computer Use API)
 ```python
 model="anthropic/claude-3-5-sonnet-20241022"
-model="anthropic/claude-3-5-sonnet-20240620"
+model="anthropic/claude-3-7-sonnet-20250219"
 model="anthropic/claude-opus-4-20250514"
 model="anthropic/claude-sonnet-4-20250514"
 ```

{cua_agent-0.4.13.dist-info → cua_agent-0.4.15.dist-info}/RECORD

@@ -1,4 +1,4 @@
-agent/__init__.py,sha256=vWbQYgjkzIso7zILSm4OAbNU_vrmN4HyYkfX8vC-Yi0,1547
+agent/__init__.py,sha256=MaW-BczJ-lCACPYH39DvFhE7ZWiSo7sBO6pBfyO7Nxc,1269
 agent/__main__.py,sha256=lBUe8Niqa5XoCjwFfXyX7GtnUwjjZXC1-j4V9mvUYSc,538
 agent/adapters/__init__.py,sha256=lNH6srgIMmZOI7dgicJs3LCk_1MeqLF0lou9n7b23Ts,238
 agent/adapters/huggingfacelocal_adapter.py,sha256=Uqjtcohhzd33VFh38Ra2y4Uv_lTghMswoqS1t-KKFkw,8480
@@ -10,7 +10,7 @@ agent/callbacks/budget_manager.py,sha256=RyKM-7iXQcDotYvrw3eURzeEHEXvQjID-NobtvQ
 agent/callbacks/image_retention.py,sha256=tiuRT5ke9xXTb2eP8Gz-2ITyAMY29LURUH6AbjX3RP8,6165
 agent/callbacks/logging.py,sha256=OOxU97EzrxlnUAtiEnvy9FB7SwCUK90-rdpDFA2Ae4E,10921
 agent/callbacks/pii_anonymization.py,sha256=NEkUTUjQBi82nqus7kT-1E4RaeQ2hQrY7YCnKndLhP8,3272
-agent/callbacks/telemetry.py,sha256=PU7pkK7W1v1xjDN-9gA30lGvn4-WhqK3BPHGW3HpTOc,7497
+agent/callbacks/telemetry.py,sha256=RbUDhE41mTi8g9hNre0EpltK_NUZkLj8buJLWBzs0Ek,7363
 agent/callbacks/trajectory_saver.py,sha256=VHbiDQzI_XludkWhZIVqIMrsxgwKfFWwVtqaRot_D4U,12231
 agent/cli.py,sha256=AgaXwywHd3nGQWuqMRj6SbPyFaCPjfo5980Y1ApQOTQ,12413
 agent/computers/__init__.py,sha256=39ISJsaREaQIZckpzxSuLhuR763wUU3TxUux78EKjAg,1477
@@ -35,16 +35,15 @@ agent/loops/gta1.py,sha256=ha5TaUWqUzTffx_ow1WiBU8i3VNP-6FL5XC66ajPFjg,5829
 agent/loops/model_types.csv,sha256=GmFn4x80yoUpQZuQ-GXtJkPVlOLYWZ5u_5A73HRyeNE,112
 agent/loops/omniparser.py,sha256=-db8JUL2Orn47ERIaLbuNShAXn4LeIgYzRWphn_9Dg4,15071
 agent/loops/openai.py,sha256=8Ad_XufpENmLq1nEnhzF3oswPrPK1EPz-C5NU8UOEs0,8035
-agent/loops/uitars.py,sha256=EDq8AO20lrnwB013uJoWSkkz3TVRU9oG8DQ1VviXltc,31445
+agent/loops/uitars.py,sha256=PVNOdwcn2K6RgaxoU-9I4HjBTsEH073M11LTqTrN7C4,31849
 agent/responses.py,sha256=TTJ3wXN_eb0J26GKhO3cVQngOiZ1AgUPIUadozLUQyE,28991
-agent/telemetry.py,sha256=87ZTyBaT0wEPQn4v76II3g0V3GERuIVbypoX-Ug6FKQ,4786
 agent/types.py,sha256=ZoWY8a3GZtB8V0SnOzoI7DQy4nP_GRubxJKbuLPOc8c,840
 agent/ui/__init__.py,sha256=DTZpK85QXscXK2nM9HtpAhVBF13yAamUrtwrQSuV-kM,126
 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=m2yDd6Tua_lMMZT1zCzOty2meYEy756d8OlFF7lpdeU,9117
-agent/ui/gradio/ui_components.py,sha256=vfsqVo_COsFfw11ouMHClib9fdBf3q52G-qbuo0RyOY,36068
-cua_agent-0.4.13.dist-info/METADATA,sha256=Xr2mN1uCE8Mu5TiYskFjb6DpN-FgmihPTyNyPa665yo,12616
-cua_agent-0.4.13.dist-info/WHEEL,sha256=9P2ygRxDrTJz3gsagc0Z96ukrxjr-LFBGOgv3AuKlCA,90
-cua_agent-0.4.13.dist-info/entry_points.txt,sha256=6OYgBcLyFCUgeqLgnvMyOJxPCWzgy7se4rLPKtNonMs,34
-cua_agent-0.4.13.dist-info/RECORD,,
+agent/ui/gradio/app.py,sha256=Ol97YEbwREZZQ9_PMjVHlfOcu9BGsawxgAGAm79hT80,9117
+agent/ui/gradio/ui_components.py,sha256=dJUvKDmc1oSejtoR_gU_oWWYwxaOOQyPloSYRGMrUCQ,36068
+cua_agent-0.4.15.dist-info/METADATA,sha256=NZ_ccvhA-BeLMnCajZAfVhzXvttSRHYfTdJlezFCks8,12616
+cua_agent-0.4.15.dist-info/WHEEL,sha256=9P2ygRxDrTJz3gsagc0Z96ukrxjr-LFBGOgv3AuKlCA,90
+cua_agent-0.4.15.dist-info/entry_points.txt,sha256=6OYgBcLyFCUgeqLgnvMyOJxPCWzgy7se4rLPKtNonMs,34
+cua_agent-0.4.15.dist-info/RECORD,,

agent/telemetry.py

@@ -1,142 +0,0 @@
-"""Agent telemetry for tracking anonymous usage and feature usage."""
-
-import logging
-import os
-import platform
-import sys
-from typing import Dict, Any, Callable
-
-# Import the core telemetry module
-TELEMETRY_AVAILABLE = False
-
-
-# Local fallbacks in case core telemetry isn't available
-def _noop(*args: Any, **kwargs: Any) -> None:
-    """No-op function for when telemetry is not available."""
-    pass
-
-
-# Define default functions with unique names to avoid shadowing
-_default_record_event = _noop
-_default_increment_counter = _noop
-_default_set_dimension = _noop
-_default_get_telemetry_client = lambda: None
-_default_flush = _noop
-_default_is_telemetry_enabled = lambda: False
-_default_is_telemetry_globally_disabled = lambda: True
-
-# Set the actual functions to the defaults initially
-record_event = _default_record_event
-increment_counter = _default_increment_counter
-set_dimension = _default_set_dimension
-get_telemetry_client = _default_get_telemetry_client
-flush = _default_flush
-is_telemetry_enabled = _default_is_telemetry_enabled
-is_telemetry_globally_disabled = _default_is_telemetry_globally_disabled
-
-logger = logging.getLogger("agent.telemetry")
-
-try:
-    # Import from core telemetry
-    from core.telemetry import (
-        record_event as core_record_event,
-        increment as core_increment,
-        get_telemetry_client as core_get_telemetry_client,
-        flush as core_flush,
-        is_telemetry_enabled as core_is_telemetry_enabled,
-        is_telemetry_globally_disabled as core_is_telemetry_globally_disabled,
-    )
-
-    # Override the default functions with actual implementations
-    record_event = core_record_event
-    get_telemetry_client = core_get_telemetry_client
-    flush = core_flush
-    is_telemetry_enabled = core_is_telemetry_enabled
-    is_telemetry_globally_disabled = core_is_telemetry_globally_disabled
-
-    def increment_counter(counter_name: str, value: int = 1) -> None:
-        """Wrapper for increment to maintain backward compatibility."""
-        if is_telemetry_enabled():
-            core_increment(counter_name, value)
-
-    def set_dimension(name: str, value: Any) -> None:
-        """Set a dimension that will be attached to all events."""
-        logger.debug(f"Setting dimension {name}={value}")
-
-    TELEMETRY_AVAILABLE = True
-    logger.info("Successfully imported telemetry")
-except ImportError as e:
-    logger.warning(f"Could not import telemetry: {e}")
-    logger.debug("Telemetry not available, using no-op functions")
-
-# Get system info once to use in telemetry
-SYSTEM_INFO = {
-    "os": platform.system().lower(),
-    "os_version": platform.release(),
-    "python_version": platform.python_version(),
-}
-
-
-def enable_telemetry() -> bool:
-    """Enable telemetry if available.
-
-    Returns:
-        bool: True if telemetry was successfully enabled, False otherwise
-    """
-    global TELEMETRY_AVAILABLE, record_event, increment_counter, get_telemetry_client, flush, is_telemetry_enabled, is_telemetry_globally_disabled
-
-    # Check if globally disabled using core function
-    if TELEMETRY_AVAILABLE and is_telemetry_globally_disabled():
-        logger.info("Telemetry is globally disabled via environment variable - cannot enable")
-        return False
-
-    # Already enabled
-    if TELEMETRY_AVAILABLE:
-        return True
-
-    # Try to import and enable
-    try:
-        from core.telemetry import (
-            record_event,
-            increment,
-            get_telemetry_client,
-            flush,
-            is_telemetry_globally_disabled,
-        )
-
-        # Check again after import
-        if is_telemetry_globally_disabled():
-            logger.info("Telemetry is globally disabled via environment variable - cannot enable")
-            return False
-
-        TELEMETRY_AVAILABLE = True
-        logger.info("Telemetry successfully enabled")
-        return True
-    except ImportError as e:
-        logger.warning(f"Could not enable telemetry: {e}")
-        return False
-
-
-def is_telemetry_enabled() -> bool:
-    """Check if telemetry is enabled.
-
-    Returns:
-        bool: True if telemetry is enabled, False otherwise
-    """
-    # Use the core function if available, otherwise use our local flag
-    if TELEMETRY_AVAILABLE:
-        from core.telemetry import is_telemetry_enabled as core_is_enabled
-
-        return core_is_enabled()
-    return False
-
-
-def record_agent_initialization() -> None:
-    """Record when an agent instance is initialized."""
-    if TELEMETRY_AVAILABLE and is_telemetry_enabled():
-        record_event("agent_initialized", SYSTEM_INFO)
-
-        # Set dimensions that will be attached to all events
-        set_dimension("os", SYSTEM_INFO["os"])
-        set_dimension("os_version", SYSTEM_INFO["os_version"])
-        set_dimension("python_version", SYSTEM_INFO["python_version"])