wcgw 1.5.2__tar.gz → 1.5.3__tar.gz

{wcgw-1.5.2 → wcgw-1.5.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: wcgw
-Version: 1.5.2
+Version: 1.5.3
 Summary: What could go wrong giving full shell access to chatgpt?
 Project-URL: Homepage, https://github.com/rusiaaman/wcgw
 Author-email: Aman Rusia <gapypi@arcfu.com>

{wcgw-1.5.2 → wcgw-1.5.3}/pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 authors = [{ name = "Aman Rusia", email = "gapypi@arcfu.com" }]
 name = "wcgw"
-version = "1.5.2"
+version = "1.5.3"
 description = "What could go wrong giving full shell access to chatgpt?"
 readme = "README.md"
 requires-python = ">=3.11, <3.13"

{wcgw-1.5.2 → wcgw-1.5.3}/src/wcgw/client/anthropic_client.py

@@ -182,6 +182,9 @@ def loop(
 - Send text input to the running program.
 - Send send_specials=["Enter"] to recheck status of a running program.
 - Only one of send_text, send_specials, send_ascii should be provided.
+- This returns within 5 seconds, for heavy programs keep checking status for upto 10 turns before asking user to continue checking again.
+    - Programs don't hang easily, so most likely explanation for no output is usually that the program is still running, and you need to check status again usign ["Enter"].
+
 """,
         ),
         ToolParam(
@@ -236,6 +239,12 @@ def loop(
             name="ScreenShot",
             description="""
 - Capture screenshot of the linux os on docker.
+- All actions on UI using mouse and keyboard return within 0.5 seconds.
+    * So if you're doing something that takes longer for UI to update like heavy page loading, keep checking UI for update usign ScreenShot upto 10 turns. 
+    * Notice for smallest of the loading icons to check if your action worked.
+    * After 10 turns of no change, ask user for permission to keep checking.
+    * If you don't notice even slightest of the change, it's likely you clicked on the wrong place.
+
 """,
         ),
         ToolParam(
@@ -244,6 +253,7 @@ def loop(
             description="""
 - Interact with the linux os on docker using mouse.
 - Uses xdotool
+- About left_click_drag: the current mouse position will be used as the starting point, click and drag to the given x, y coordinates. Useful in things like sliders, moving things around, etc.
 """,
         ),
         ToolParam(

{wcgw-1.5.2 → wcgw-1.5.3}/src/wcgw/client/computer_use.py

@@ -26,6 +26,7 @@ from ..types_ import (
 OUTPUT_DIR = "/tmp/outputs"
 TYPING_DELAY_MS = 12
 TYPING_GROUP_SIZE = 50
+SLEEP_TIME_MAX_S = 3
 
 Action = Literal[
     "key",
@@ -187,12 +188,15 @@ class ComputerTool:
         text: str | None = None,
         coordinate: tuple[int, int] | None = None,
         do_left_click_on_move: bool | None = None,
+        take_after_delay_seconds: int | None = None,
         **kwargs: Any,
     ) -> ToolResult:
         if action == "get_screen_info":
             assert docker_image_id is not None
             self.docker_image_id = docker_image_id
             self.get_screen_info()
+            if take_after_delay_seconds is not None:
+                time.sleep(min(take_after_delay_seconds, SLEEP_TIME_MAX_S))
             screenshot_res = self.screenshot()
             return ToolResult(
                 output=f"width: {self.width}, height: {self.height}, display_num: {self.display_num}",
@@ -396,6 +400,7 @@ def run_computer_tool(
     elif isinstance(action, ScreenShot):
         result = Computer(
             action="screenshot",
+            screenshot_delay=action.take_after_delay_seconds,
         )
     elif isinstance(action, Keyboard):
         result = Computer(

{wcgw-1.5.2 → wcgw-1.5.3}/src/wcgw/client/mcp_server/server.py

@@ -28,9 +28,9 @@ from ...types_ import (
     ScreenShot,
     GetScreenInfo,
 )
-from ..computer_use import Computer
+from ..computer_use import SLEEP_TIME_MAX_S
 
-tools.TIMEOUT = 3
+tools.TIMEOUT = SLEEP_TIME_MAX_S
 
 server = Server("wcgw")
 
@@ -102,6 +102,8 @@ async def handle_list_tools() -> list[types.Tool]:
 - Send text input to the running program.
 - Send send_specials=["Enter"] to recheck status of a running program.
 - Only one of send_text, send_specials, send_ascii should be provided.
+- This returns within 3 seconds, for heavy programs keep checking status for upto 10 turns before asking user to continue checking again.
+    - Programs don't hang easily, so most likely explanation for no output is usually that the program is still running, and you need to check status again usign ["Enter"].
 """,
         ),
         ToolParam(
@@ -164,6 +166,11 @@ async def handle_list_tools() -> list[types.Tool]:
             name="ScreenShot",
             description="""
 - Capture screenshot of the linux os on docker.
+- All actions on UI using mouse and keyboard return within 0.5 seconds.
+    * So if you're doing something that takes longer for UI to update like heavy page loading, keep checking UI for update usign ScreenShot upto 10 turns. 
+    * Notice for smallest of the loading icons to check if your action worked.
+    * After 10 turns of no change, ask user for permission to keep checking.
+    * If you don't notice even slightest of the change, it's likely you clicked on the wrong place.
 """,
         ),
         ToolParam(
@@ -172,6 +179,7 @@ async def handle_list_tools() -> list[types.Tool]:
             description="""
 - Interact with the linux os on docker using mouse.
 - Uses xdotool
+- About left_click_drag: the current mouse position will be used as the starting point, click and drag to the given x, y coordinates. Useful in things like sliders, moving things around, etc.
 """,
         ),
         ToolParam(
@@ -257,27 +265,18 @@ async def handle_call_tool(
 
 async def main() -> None:
     version = importlib.metadata.version("wcgw")
-    while True:
-        try:
-            # Run the server using stdin/stdout streams
-            async with mcp.server.stdio.stdio_server() as (read_stream, write_stream):
-                await server.run(
-                    read_stream,
-                    write_stream,
-                    InitializationOptions(
-                        server_name="wcgw",
-                        server_version=version,
-                        capabilities=server.get_capabilities(
-                            notification_options=NotificationOptions(),
-                            experimental_capabilities={},
-                        ),
-                    ),
-                    raise_exceptions=False,
-                )
-        except BaseException as e:
-            print(f"Server encountered an error: {e}", file=sys.stderr)
-            print("Stack trace:", file=sys.stderr)
-            traceback.print_exc(file=sys.stderr)
-            print("Restarting server in 5 seconds...", file=sys.stderr)
-            await asyncio.sleep(5)
-            continue
+    # Run the server using stdin/stdout streams
+    async with mcp.server.stdio.stdio_server() as (read_stream, write_stream):
+        await server.run(
+            read_stream,
+            write_stream,
+            InitializationOptions(
+                server_name="wcgw",
+                server_version=version,
+                capabilities=server.get_capabilities(
+                    notification_options=NotificationOptions(),
+                    experimental_capabilities={},
+                ),
+            ),
+            raise_exceptions=False,
+        )

{wcgw-1.5.2 → wcgw-1.5.3}/src/wcgw/types_.py

@@ -60,6 +60,7 @@ class GetScreenInfo(BaseModel):
 
 class ScreenShot(BaseModel):
     type: Literal["ScreenShot"]
+    take_after_delay_seconds: int
 
 
 class MouseMove(BaseModel):

{wcgw-1.5.2 → wcgw-1.5.3}/uv.lock

@@ -860,7 +860,7 @@ wheels = [
 
 [[package]]
 name = "wcgw"
-version = "1.5.1"
+version = "1.5.2"
 source = { editable = "." }
 dependencies = [
     { name = "anthropic" },

wcgw-1.5.2/claude_desktop_config.json

@@ -1,15 +0,0 @@
-{
-  "mcpServers": {
-    "wcgw": {
-      "command": "uvx",
-      "args": [
-        "--from",
-        "wcgw",
-        "wcgw_mcp"
-      ],
-      "protocol": "mcp",
-      "defaultModel": "claude-3-sonnet",
-      "maxTokens": 4096
-    }
-  }
-}