cua-agent 0.4.22__py3-none-any.whl → 0.4.24__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

@@ -196,7 +196,9 @@ class HumanCompletionUI:
                 gr.update(choices=["latest"], value="latest"),  # dropdown
                 gr.update(value=None),  # image (no image)
                 gr.update(value=[]),  # chatbot (empty messages)
-                gr.update(interactive=False)  # submit button
+                gr.update(interactive=False),  # submit button
+                gr.update(visible=False),  # click_actions_group hidden
+                gr.update(visible=False),  # actions_group hidden
             )
         
         # Sort pending calls by created_at to get oldest first
@@ -237,7 +239,9 @@ class HumanCompletionUI:
             gr.update(choices=choices, value="latest"),
             gr.update(value=self.last_image),
             gr.update(value=conversation),
-            gr.update(interactive=bool(choices))
+            gr.update(interactive=bool(choices)),
+            gr.update(visible=True),  # click_actions_group visible when there is a call
+            gr.update(visible=True),  # actions_group visible when there is a call
         )
     
     def on_call_selected(self, selected_choice):
@@ -246,7 +250,9 @@ class HumanCompletionUI:
             return (
                 gr.update(value=None),  # no image
                 gr.update(value=[]),  # empty chatbot
-                gr.update(interactive=False)
+                gr.update(interactive=False),
+                gr.update(visible=False),  # click_actions_group hidden
+                gr.update(visible=False),  # actions_group hidden
             )
         
         pending_calls = self.get_pending_calls()
@@ -254,7 +260,9 @@ class HumanCompletionUI:
             return (
                 gr.update(value=None),  # no image
                 gr.update(value=[]),  # empty chatbot
-                gr.update(interactive=False)
+                gr.update(interactive=False),
+                gr.update(visible=False),  # click_actions_group hidden
+                gr.update(visible=False),  # actions_group hidden
             )
         
         # Handle "latest" option
@@ -286,7 +294,9 @@ class HumanCompletionUI:
             return (
                 gr.update(value=None),  # no image
                 gr.update(value=[]),  # empty chatbot
-                gr.update(interactive=False)
+                gr.update(interactive=False),
+                gr.update(visible=False),  # click_actions_group hidden
+                gr.update(visible=False),  # actions_group hidden
             )
         
         conversation = self.format_messages_for_chatbot(selected_call.get("messages", []))
@@ -297,7 +307,9 @@ class HumanCompletionUI:
         return (
             gr.update(value=self.last_image),
             gr.update(value=conversation),
-            gr.update(interactive=True)
+            gr.update(interactive=True),
+            gr.update(visible=True),  # click_actions_group visible
+            gr.update(visible=True),  # actions_group visible
         )
     
     def submit_response(self, response_text: str):
@@ -368,6 +380,10 @@ class HumanCompletionUI:
         """Submit a hotkey action."""
         return self.submit_action("keypress", keys=keys)
     
+    def submit_wait_action(self) -> str:
+        """Submit a wait action with no kwargs."""
+        return self.submit_action("wait")
+    
     def submit_description_click(self, description: str, action_type: str = "click", button: str = "left") -> str:
         """Submit a description-based action."""
         if action_type == "click":
@@ -407,7 +423,7 @@ def create_ui():
     """Create the Gradio interface."""
     ui_handler = HumanCompletionUI()
     
-    with gr.Blocks(title="Human-in-the-Loop Agent Tool") as demo:
+    with gr.Blocks(title="Human-in-the-Loop Agent Tool", fill_width=True) as demo:
         gr.Markdown("# 🤖 Human-in-the-Loop Agent Tool")
         gr.Markdown("Review AI conversation requests and provide human responses.")
         
@@ -415,29 +431,30 @@ def create_ui():
             with gr.Column(scale=2):
                 with gr.Group():
                     screenshot_image = gr.Image(
-                        label="Screenshot",
+                        label="Interactive Screenshot",
                         interactive=False,
                         height=600
                     )
                     
-                    # Action type selection for image clicks
-                    with gr.Row():
-                        action_type_radio = gr.Radio(
-                            label="Action Type",
-                            choices=["click", "double_click", "move", "left_mouse_up", "left_mouse_down"],
-                            value="click",
-                            scale=2
-                        )
-                        action_button_radio = gr.Radio(
-                            label="Button (for click only)",
-                            choices=["left", "right", "wheel", "back", "forward"],
-                            value="left",
-                            visible=True,
-                            scale=1
-                        )
+                    # Action type selection for image clicks (wrapped for visibility control)
+                    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"],
+                                value="click",
+                                scale=2
+                            )
+                            action_button_radio = gr.Dropdown(
+                                label="Button",
+                                choices=["left", "right", "wheel", "back", "forward"],
+                                value="left",
+                                visible=True,
+                                scale=1
+                            )
                     
                     conversation_chatbot = gr.Chatbot(
-                        label="Messages",
+                        label="Conversation",
                         type="messages",
                         height=500,
                         show_copy_button=True
@@ -446,91 +463,83 @@ def create_ui():
             with gr.Column(scale=1):
                 with gr.Group():
                     call_dropdown = gr.Dropdown(
-                        label="Select a pending call",
+                        label="Select a pending conversation request",
                         choices=["latest"],
                         interactive=True,
                         value="latest"
                     )
                     refresh_btn = gr.Button("🔄 Refresh", variant="secondary")
+                    status_display = gr.Textbox(
+                        label="Status",
+                        interactive=False,
+                        value="Ready to receive requests..."
+                    )
 
                 with gr.Group():
                     response_text = gr.Textbox(
-                        label="Response",
+                        label="Message",
                         lines=3,
-                        placeholder="Enter your response here..."
+                        placeholder="Enter your message here..."
                     )
-                    submit_btn = gr.Button("📤 Submit Response", variant="primary", interactive=False)
+                    submit_btn = gr.Button("📤 Submit Message", variant="primary", interactive=False)
                 
-                # Action Accordions
-                with gr.Accordion("🖱️ Click Actions", open=False):
-                    with gr.Group():
-                        with gr.Row():
-                            click_x = gr.Number(label="X", value=0, minimum=0)
-                            click_y = gr.Number(label="Y", value=0, minimum=0)
-                        with gr.Row():
-                            click_action_type = gr.Dropdown(
-                                label="Action Type",
-                                choices=["click", "double_click", "move", "left_mouse_up", "left_mouse_down"],
-                                value="click"
-                            )
-                            click_button = gr.Dropdown(
-                                label="Button (for click only)",
-                                choices=["left", "right", "wheel", "back", "forward"],
-                                value="left"
-                            )
-                        click_submit_btn = gr.Button("Submit Action")
-                
-                with gr.Accordion("📝 Type Action", open=False):
-                    with gr.Group():
-                        type_text = gr.Textbox(
-                            label="Text to Type",
-                            placeholder="Enter text to type..."
-                        )
-                        type_submit_btn = gr.Button("Submit Type")
-                
-                with gr.Accordion("⌨️ Keypress Action", open=False):
-                    with gr.Group():
-                        keypress_text = gr.Textbox(
-                            label="Keys",
-                            placeholder="e.g., ctrl+c, alt+tab"
-                        )
-                        keypress_submit_btn = gr.Button("Submit Keypress")
-                
-                with gr.Accordion("🎯 Description Action", open=False):
-                    with gr.Group():
-                        description_text = gr.Textbox(
-                            label="Element Description",
-                            placeholder="e.g., 'Privacy and security option in left sidebar'"
-                        )
-                        with gr.Row():
-                            description_action_type = gr.Dropdown(
-                                label="Action Type",
-                                choices=["click", "double_click", "move", "left_mouse_up", "left_mouse_down"],
-                                value="click"
-                            )
-                            description_button = gr.Radio(
-                                label="Button (for click only)",
-                                choices=["left", "right", "wheel", "back", "forward"],
-                                value="left"
-                            )
-                        description_submit_btn = gr.Button("Submit Description Action")
-                
-                status_display = gr.Textbox(
-                    label="Status",
-                    interactive=False,
-                    value="Ready to receive calls..."
-                )
+                # Action Accordions (wrapped for visibility control)
+                with gr.Group(visible=False) as actions_group:
+                    with gr.Tabs():
+                        with gr.Tab("🖱️ Click Actions"):
+                            with gr.Group():
+                                description_text = gr.Textbox(
+                                    label="Element Description",
+                                    placeholder="e.g., 'Privacy and security option in left sidebar'"
+                                )
+                                with gr.Row():
+                                    description_action_type = gr.Dropdown(
+                                        label="Action",
+                                        choices=["click", "double_click", "move", "left_mouse_up", "left_mouse_down"],
+                                        value="click"
+                                    )
+                                    description_button = gr.Dropdown(
+                                        label="Button",
+                                        choices=["left", "right", "wheel", "back", "forward"],
+                                        value="left"
+                                    )
+                                description_submit_btn = gr.Button("Submit Click Action")
+                        
+                        with gr.Tab("📝 Type Action"):
+                            with gr.Group():
+                                type_text = gr.Textbox(
+                                    label="Text to Type",
+                                    placeholder="Enter text to type..."
+                                )
+                                type_submit_btn = gr.Button("Submit Type")
+                        
+                        with gr.Tab("⌨️ Keypress Action"):
+                            with gr.Group():
+                                keypress_text = gr.Textbox(
+                                    label="Keys",
+                                    placeholder="e.g., ctrl+c, alt+tab"
+                                )
+                                keypress_submit_btn = gr.Button("Submit Keypress")
+                        
+                        with gr.Tab("🧰 Misc Actions"):
+                            with gr.Group():
+                                misc_action_dropdown = gr.Dropdown(
+                                    label="Action",
+                                    choices=["wait"],
+                                    value="wait"
+                                )
+                                misc_submit_btn = gr.Button("Submit Action")
         
         # Event handlers
         refresh_btn.click(
             fn=ui_handler.refresh_pending_calls,
-            outputs=[call_dropdown, screenshot_image, conversation_chatbot, submit_btn]
+            outputs=[call_dropdown, screenshot_image, conversation_chatbot, submit_btn, click_actions_group, actions_group]
         )
         
         call_dropdown.change(
             fn=ui_handler.on_call_selected,
             inputs=[call_dropdown],
-            outputs=[screenshot_image, conversation_chatbot, submit_btn]
+            outputs=[screenshot_image, conversation_chatbot, submit_btn, click_actions_group, actions_group]
         )
         
         def handle_image_click(evt: gr.SelectData):
@@ -548,7 +557,7 @@ def create_ui():
             outputs=[status_display]
         ).then(
             fn=ui_handler.wait_for_pending_calls,
-            outputs=[call_dropdown, screenshot_image, conversation_chatbot, submit_btn]
+            outputs=[call_dropdown, screenshot_image, conversation_chatbot, submit_btn, click_actions_group, actions_group]
         )
 
         # Response submission
@@ -558,7 +567,7 @@ def create_ui():
             outputs=[response_text, status_display]
         ).then(
             fn=ui_handler.refresh_pending_calls,
-            outputs=[call_dropdown, screenshot_image, conversation_chatbot, submit_btn]
+            outputs=[call_dropdown, screenshot_image, conversation_chatbot, submit_btn, click_actions_group, actions_group]
         )
         
         # Toggle button radio visibility based on action type
@@ -570,16 +579,6 @@ def create_ui():
             inputs=[action_type_radio],
             outputs=[action_button_radio]
         )
-
-        # Action accordion handlers
-        click_submit_btn.click(
-            fn=ui_handler.submit_click_action,
-            inputs=[click_x, click_y, click_action_type, click_button],
-            outputs=[status_display]
-        ).then(
-            fn=ui_handler.wait_for_pending_calls,
-            outputs=[call_dropdown, screenshot_image, conversation_chatbot, submit_btn]
-        )
         
         type_submit_btn.click(
             fn=ui_handler.submit_type_action,
@@ -587,7 +586,7 @@ def create_ui():
             outputs=[status_display]
         ).then(
             fn=ui_handler.wait_for_pending_calls,
-            outputs=[call_dropdown, screenshot_image, conversation_chatbot, submit_btn]
+            outputs=[call_dropdown, screenshot_image, conversation_chatbot, submit_btn, click_actions_group, actions_group]
         )
         
         keypress_submit_btn.click(
@@ -596,7 +595,7 @@ def create_ui():
             outputs=[status_display]
         ).then(
             fn=ui_handler.wait_for_pending_calls,
-            outputs=[call_dropdown, screenshot_image, conversation_chatbot, submit_btn]
+            outputs=[call_dropdown, screenshot_image, conversation_chatbot, submit_btn, click_actions_group, actions_group]
         )
         
         def handle_description_submit(description, action_type, button):
@@ -612,13 +611,30 @@ def create_ui():
             outputs=[status_display]
         ).then(
             fn=ui_handler.wait_for_pending_calls,
-            outputs=[call_dropdown, screenshot_image, conversation_chatbot, submit_btn]
+            outputs=[call_dropdown, screenshot_image, conversation_chatbot, submit_btn, click_actions_group, actions_group]
+        )
+        
+        # Misc action handler
+        def handle_misc_submit(selected_action):
+            if selected_action == "wait":
+                result = ui_handler.submit_wait_action()
+                ui_handler.wait_for_pending_calls()
+                return result
+            return f"Unsupported misc action: {selected_action}"
+
+        misc_submit_btn.click(
+            fn=handle_misc_submit,
+            inputs=[misc_action_dropdown],
+            outputs=[status_display]
+        ).then(
+            fn=ui_handler.wait_for_pending_calls,
+            outputs=[call_dropdown, screenshot_image, conversation_chatbot, submit_btn, click_actions_group, actions_group]
         )
         
         # Load initial data
         demo.load(
             fn=ui_handler.refresh_pending_calls,
-            outputs=[call_dropdown, screenshot_image, conversation_chatbot, submit_btn]
+            outputs=[call_dropdown, screenshot_image, conversation_chatbot, submit_btn, click_actions_group, actions_group]
         )
     
     return demo

{cua_agent-0.4.22.dist-info → cua_agent-0.4.24.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cua-agent
-Version: 0.4.22
+Version: 0.4.24
 Summary: CUA (Computer Use) Agent for AI-driven computer interaction
 Author-Email: TryCua <gh@trycua.com>
 Requires-Python: >=3.12

{cua_agent-0.4.22.dist-info → cua_agent-0.4.24.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
@@ -23,7 +23,7 @@ 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=2Jk3Bh-Jctya8GUG-qtYbdi-1qDdwOtcAlUeiIqsoIE,26584
+agent/human_tool/ui.py,sha256=c5IbzVbj6dTtrswK3KKo6svjatQhQHHwzFA848U2Cw0,28130
 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
@@ -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-0.4.22.dist-info/METADATA,sha256=pJw4ucNwM-cTifQAAz9I4Zw547lq4dbF06leL4qxFTY,12712
-cua_agent-0.4.22.dist-info/WHEEL,sha256=9P2ygRxDrTJz3gsagc0Z96ukrxjr-LFBGOgv3AuKlCA,90
-cua_agent-0.4.22.dist-info/entry_points.txt,sha256=6OYgBcLyFCUgeqLgnvMyOJxPCWzgy7se4rLPKtNonMs,34
-cua_agent-0.4.22.dist-info/RECORD,,
+cua_agent-0.4.24.dist-info/METADATA,sha256=-yvFHUziugRMdDqtf_NDVnQfcNbHKut_rr-yswIDYkM,12712
+cua_agent-0.4.24.dist-info/WHEEL,sha256=9P2ygRxDrTJz3gsagc0Z96ukrxjr-LFBGOgv3AuKlCA,90
+cua_agent-0.4.24.dist-info/entry_points.txt,sha256=6OYgBcLyFCUgeqLgnvMyOJxPCWzgy7se4rLPKtNonMs,34
+cua_agent-0.4.24.dist-info/RECORD,,