wcgw 0.0.9__tar.gz → 0.0.10__tar.gz

wcgw-0.0.10/PKG-INFO

@@ -0,0 +1,97 @@
+Metadata-Version: 2.3
+Name: wcgw
+Version: 0.0.10
+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>
+Requires-Python: <3.13,>=3.8
+Requires-Dist: fastapi>=0.115.0
+Requires-Dist: mypy>=1.11.2
+Requires-Dist: openai>=1.46.0
+Requires-Dist: petname>=2.6
+Requires-Dist: pexpect>=4.9.0
+Requires-Dist: pydantic>=2.9.2
+Requires-Dist: pyte>=0.8.2
+Requires-Dist: python-dotenv>=1.0.1
+Requires-Dist: rich>=13.8.1
+Requires-Dist: shell>=1.0.1
+Requires-Dist: tiktoken==0.7.0
+Requires-Dist: toml>=0.10.2
+Requires-Dist: typer>=0.12.5
+Requires-Dist: types-pexpect>=4.9.0.20240806
+Requires-Dist: uvicorn>=0.31.0
+Requires-Dist: websockets>=13.1
+Description-Content-Type: text/markdown
+
+# Enable shell access on chatgpt.com
+A custom gpt on chatgpt web app to interact with your local shell.
+
+### 🚀 Highlights
+- ⚡ **Full Shell Access**: No restrictions, complete control.
+- ⚡ **Create, Execute, Iterate**: Ask the gpt to keep running compiler checks till all errors are fixed, or ask it to keep checking for the status of a long running command till it's done.
+- ⚡ **Interactive Command Handling**: [beta] Supports interactive commands using arrow keys, interrupt, and ansi escape sequences. 
+
+###  🪜 Steps: 
+1. Run the [cli client](https://github.com/rusiaaman/wcgw?tab=readme-ov-file#client) in any directory of choice.
+2. Share the generated id with this GPT: `https://chatgpt.com/g/g-Us0AAXkRh-wcgw-giving-shell-access`
+3. The custom GPT can now run any command on your cli
+
+## Client
+
+### Option 1: using pip
+Supports python >=3.8 and <3.13
+```sh
+$ pip3 install wcgw
+$ wcgw
+```
+
+### Option 2: using uv
+```sh
+$ curl -LsSf https://astral.sh/uv/install.sh | sh
+$ uv tool run --python 3.12 wcgw
+```
+
+This will print a UUID that you need to share with the gpt.
+
+
+## Chat
+Open the following link or search the "wcgw" custom gpt using "Explore GPTs" on chatgpt.com
+
+https://chatgpt.com/g/g-Us0AAXkRh-wcgw-giving-shell-access
+
+Finally, let the chatgpt know your user id in any format. E.g., "user_id=<your uuid>" followed by rest of your instructions.
+
+NOTE: you can resume a broken connection 
+`wcgw --client-uuid $previous_uuid`
+
+# How it works
+Your commands are relayed through a server I've hosted at https://wcgw.arcfu.com. The code for that is at `src/relay/serve.py`. 
+
+Chat gpt sends a request to the relay server using the user id that you share with it. The relay server holds a websocket with the terminal cilent against the user id and acts as a proxy to pass the request.
+
+It's secure in both the directions. Either a malicious actor or a malicious Chatgpt has to correctly guess your UUID for any security breach. 
+
+NOTE: the relay server doesn't store any data. If you don't trust it then you may host the server on your own and create a custom gpt. Create an issue and I'll be happy to share the full instructions and schema I've given in the custom GPT configuration. 
+
+# Showcase
+
+## Create a todo app using react + typescript + vite
+https://chatgpt.com/share/6717d94d-756c-8005-98a6-d021c7b586aa
+
+## Write unit tests for all files in my current repo
+[Todo]
+
+
+# [Optional] Local shell access with openai API key
+
+Add `OPENAI_API_KEY` and `OPENAI_ORG_ID` env variables.
+
+Clone the repo and run to install `wcgw_local` command
+
+`pip install .`
+
+Then run 
+
+`wcgw_local  --limit 0.1` # Cost limit $0.1 
+
+You can now directly write messages or press enter key to open vim for multiline message and text pasting.

wcgw-0.0.10/README.md

@@ -0,0 +1,72 @@
+# Enable shell access on chatgpt.com
+A custom gpt on chatgpt web app to interact with your local shell.
+
+### 🚀 Highlights
+- ⚡ **Full Shell Access**: No restrictions, complete control.
+- ⚡ **Create, Execute, Iterate**: Ask the gpt to keep running compiler checks till all errors are fixed, or ask it to keep checking for the status of a long running command till it's done.
+- ⚡ **Interactive Command Handling**: [beta] Supports interactive commands using arrow keys, interrupt, and ansi escape sequences. 
+
+###  🪜 Steps: 
+1. Run the [cli client](https://github.com/rusiaaman/wcgw?tab=readme-ov-file#client) in any directory of choice.
+2. Share the generated id with this GPT: `https://chatgpt.com/g/g-Us0AAXkRh-wcgw-giving-shell-access`
+3. The custom GPT can now run any command on your cli
+
+## Client
+
+### Option 1: using pip
+Supports python >=3.8 and <3.13
+```sh
+$ pip3 install wcgw
+$ wcgw
+```
+
+### Option 2: using uv
+```sh
+$ curl -LsSf https://astral.sh/uv/install.sh | sh
+$ uv tool run --python 3.12 wcgw
+```
+
+This will print a UUID that you need to share with the gpt.
+
+
+## Chat
+Open the following link or search the "wcgw" custom gpt using "Explore GPTs" on chatgpt.com
+
+https://chatgpt.com/g/g-Us0AAXkRh-wcgw-giving-shell-access
+
+Finally, let the chatgpt know your user id in any format. E.g., "user_id=<your uuid>" followed by rest of your instructions.
+
+NOTE: you can resume a broken connection 
+`wcgw --client-uuid $previous_uuid`
+
+# How it works
+Your commands are relayed through a server I've hosted at https://wcgw.arcfu.com. The code for that is at `src/relay/serve.py`. 
+
+Chat gpt sends a request to the relay server using the user id that you share with it. The relay server holds a websocket with the terminal cilent against the user id and acts as a proxy to pass the request.
+
+It's secure in both the directions. Either a malicious actor or a malicious Chatgpt has to correctly guess your UUID for any security breach. 
+
+NOTE: the relay server doesn't store any data. If you don't trust it then you may host the server on your own and create a custom gpt. Create an issue and I'll be happy to share the full instructions and schema I've given in the custom GPT configuration. 
+
+# Showcase
+
+## Create a todo app using react + typescript + vite
+https://chatgpt.com/share/6717d94d-756c-8005-98a6-d021c7b586aa
+
+## Write unit tests for all files in my current repo
+[Todo]
+
+
+# [Optional] Local shell access with openai API key
+
+Add `OPENAI_API_KEY` and `OPENAI_ORG_ID` env variables.
+
+Clone the repo and run to install `wcgw_local` command
+
+`pip install .`
+
+Then run 
+
+`wcgw_local  --limit 0.1` # Cost limit $0.1 
+
+You can now directly write messages or press enter key to open vim for multiline message and text pasting.

{wcgw-0.0.9 → wcgw-0.0.10}/pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 authors = [{ name = "Aman Rusia", email = "gapypi@arcfu.com" }]
 name = "wcgw"
-version = "0.0.9"
+version = "0.0.10"
 description = "What could go wrong giving full shell access to chatgpt?"
 readme = "README.md"
 requires-python = ">=3.8, <3.13"
@@ -21,6 +21,7 @@ dependencies = [
     "fastapi>=0.115.0",
     "uvicorn>=0.31.0",
     "websockets>=13.1",
+    "pydantic>=2.9.2",
 ]
 
 [project.urls]

{wcgw-0.0.9 → wcgw-0.0.10}/src/wcgw/basic.py

@@ -16,7 +16,7 @@ from openai.types.chat import (
     ParsedChatCompletionMessage,
 )
 import rich
-import petname
+import petname  # type: ignore[import-untyped]
 from typer import Typer
 import uuid
 
@@ -30,7 +30,6 @@ from .tools import (
     Confirmation,
     DoneFlag,
     Writefile,
-    get_is_waiting_user_input,
     get_tool_output,
     SHELL,
     start_shell,
@@ -92,29 +91,22 @@ def parse_user_message_special(msg: str) -> ChatCompletionUserMessageParam:
         if line.startswith("%"):
             args = line[1:].strip().split(" ")
             command = args[0]
-            assert command == 'image'
+            assert command == "image"
             image_path = args[1]
-            with open(image_path, 'rb') as f:
+            with open(image_path, "rb") as f:
                 image_bytes = f.read()
                 image_b64 = base64.b64encode(image_bytes).decode("utf-8")
                 image_type = mimetypes.guess_type(image_path)[0]
-                dataurl=f'data:{image_type};base64,{image_b64}'
-            parts.append({
-                'type': 'image_url',
-                'image_url': {
-                    'url': dataurl,
-                    'detail': 'auto'
-                }
-            })
+                dataurl = f"data:{image_type};base64,{image_b64}"
+            parts.append(
+                {"type": "image_url", "image_url": {"url": dataurl, "detail": "auto"}}
+            )
         else:
-            if len(parts) > 0 and parts[-1]['type'] == 'text':
-                parts[-1]['text'] += '\n' + line
+            if len(parts) > 0 and parts[-1]["type"] == "text":
+                parts[-1]["text"] += "\n" + line
             else:
-                parts.append({'type': 'text', 'text': line})
-    return {
-        'role': 'user',
-        'content': parts
-    }
+                parts.append({"type": "text", "text": line})
+    return {"role": "user", "content": parts}
 
 
 app = Typer(pretty_exceptions_show_locals=False)
@@ -146,7 +138,7 @@ def loop(
         if history[1]["role"] != "user":
             raise ValueError("Invalid history file, second message should be user")
         first_message = ""
-        waiting_for_assistant = history[-1]['role'] != 'assistant'
+        waiting_for_assistant = history[-1]["role"] != "assistant"
 
     my_dir = os.path.dirname(__file__)
     config_file = os.path.join(my_dir, "..", "..", "config.toml")
@@ -161,9 +153,6 @@ def loop(
     enc = tiktoken.encoding_for_model(
         config.model if not config.model.startswith("o1") else "gpt-4o"
     )
-    is_waiting_user_input = get_is_waiting_user_input(
-        config.model, config.cost_file[config.model]
-    )
 
     tools = [
         openai.pydantic_function_tool(
@@ -290,7 +279,7 @@ System information:
                     )
                     system_console.print(f"\nTotal cost: {config.cost_unit}{cost:.3f}")
                     output_toks += output_toks_
-                    
+
                     _histories.append(item)
                     for tool_call_id, toolcallargs in tool_call_args_by_id.items():
                         for toolindex, tool_args in toolcallargs.items():
@@ -300,7 +289,7 @@ System information:
                                     enc,
                                     limit - cost,
                                     loop,
-                                    is_waiting_user_input,
+                                    max_tokens=2048,
                                 )
                             except Exception as e:
                                 output_or_done = (
@@ -322,42 +311,49 @@ System information:
                                     f"\nTotal cost: {config.cost_unit}{cost:.3f}"
                                 )
                                 return output_or_done.task_output, cost
-                                
+
                             output = output_or_done
 
                             if isinstance(output, ImageData):
                                 randomId = petname.Generate(2, "-")
                                 if not image_histories:
-                                    image_histories.extend([
-                                        {
-                                            'role': 'assistant',
-                                            'content': f'Share images with ids: {randomId}'
-
-                                        },
-                                        {
-                                            'role': 'user',
-                                            'content': [{
-                                                'type': 'image_url',
-                                                'image_url': {
-                                                    'url': output.dataurl,
-                                                    'detail': 'auto'
-                                                }
-                                            }]
-                                        }]
+                                    image_histories.extend(
+                                        [
+                                            {
+                                                "role": "assistant",
+                                                "content": f"Share images with ids: {randomId}",
+                                            },
+                                            {
+                                                "role": "user",
+                                                "content": [
+                                                    {
+                                                        "type": "image_url",
+                                                        "image_url": {
+                                                            "url": output.dataurl,
+                                                            "detail": "auto",
+                                                        },
+                                                    }
+                                                ],
+                                            },
+                                        ]
                                     )
                                 else:
-                                    image_histories[0]['content'] += ', ' + randomId
-                                    image_histories[1]["content"].append({ # type: ignore
-                                        'type': 'image_url',
-                                        'image_url': {
-                                            'url': output.dataurl,
-                                            'detail': 'auto'
+                                    image_histories[0]["content"] += ", " + randomId
+                                    second_content = image_histories[1]["content"]
+                                    assert isinstance(second_content, list)
+                                    second_content.append(
+                                        {
+                                            "type": "image_url",
+                                            "image_url": {
+                                                "url": output.dataurl,
+                                                "detail": "auto",
+                                            },
                                         }
-                                    })
+                                    )
 
                                 item = {
                                     "role": "tool",
-                                    "content": f'Ask user for image id: {randomId}',
+                                    "content": f"Ask user for image id: {randomId}",
                                     "tool_call_id": tool_call_id + str(toolindex),
                                 }
                             else:

{wcgw-0.0.9 → wcgw-0.0.10}/src/wcgw/tools.py

@@ -5,14 +5,23 @@ import mimetypes
 import sys
 import threading
 import traceback
-from typing import Callable, Literal, NewType, Optional, ParamSpec, Sequence, TypeVar, TypedDict
+from typing import (
+    Callable,
+    Literal,
+    NewType,
+    Optional,
+    ParamSpec,
+    Sequence,
+    TypeVar,
+    TypedDict,
+)
 import uuid
 from pydantic import BaseModel, TypeAdapter
 from websockets.sync.client import connect as syncconnect
 
 import os
 import tiktoken
-import petname  # type: ignore[import]
+import petname  # type: ignore[import-untyped]
 import pexpect
 from typer import Typer
 import websockets
@@ -68,14 +77,14 @@ class Writefile(BaseModel):
     file_content: str
 
 
-def start_shell():
+def start_shell() -> pexpect.spawn:
     SHELL = pexpect.spawn(
         "/bin/bash --noprofile --norc",
-        env={**os.environ, **{"PS1": "#@@"}},
+        env={**os.environ, **{"PS1": "#@@"}},  # type: ignore[arg-type]
         echo=False,
         encoding="utf-8",
         timeout=TIMEOUT,
-    )  # type: ignore[arg-type]
+    )
     SHELL.expect("#@@")
     SHELL.sendline("stty -icanon -echo")
     SHELL.expect("#@@")
@@ -119,17 +128,6 @@ BASH_CLF_OUTPUT = Literal["running", "waiting_for_input", "wont_exit"]
 BASH_STATE: BASH_CLF_OUTPUT = "running"
 
 
-def get_output_of_last_command(enc: tiktoken.Encoding) -> str:
-    global SHELL, BASH_STATE
-    output = render_terminal_output(SHELL.before)
-
-    tokens = enc.encode(output)
-    if len(tokens) >= 2048:
-        output = "...(truncated)\n" + enc.decode(tokens[-2047:])
-
-    return output
-
-
 WAITING_INPUT_MESSAGE = """A command is already running waiting for input. NOTE: You can't run multiple shell sessions, likely a previous program hasn't exited. 
 1. Get its output using `send_ascii: [10]`
 2. Use `send_ascii` to give inputs to the running program, don't use `execute_command` OR
@@ -137,9 +135,7 @@ WAITING_INPUT_MESSAGE = """A command is already running waiting for input. NOTE:
 
 
 def execute_bash(
-    enc: tiktoken.Encoding,
-    bash_arg: ExecuteBash,
-    is_waiting_user_input: Callable[[str], tuple[BASH_CLF_OUTPUT, float]],
+    enc: tiktoken.Encoding, bash_arg: ExecuteBash, max_tokens: Optional[int]
 ) -> tuple[str, float]:
     global SHELL, BASH_STATE
     try:
@@ -186,38 +182,33 @@ def execute_bash(
         SHELL = start_shell()
         raise
 
-    wait = timeout = 5
+    wait = 5
     index = SHELL.expect(["#@@", pexpect.TIMEOUT], timeout=wait)
     running = ""
     while index == 1:
         if wait > TIMEOUT:
             raise TimeoutError("Timeout while waiting for shell prompt")
 
-        text = SHELL.before
+        BASH_STATE = "waiting_for_input"
+        text = SHELL.before or ""
         print(text[len(running) :])
         running = text
 
         text = render_terminal_output(text)
-        BASH_STATE, cost = is_waiting_user_input(text)
-        if BASH_STATE == "waiting_for_input" or BASH_STATE == "wont_exit":
-            tokens = enc.encode(text)
+        tokens = enc.encode(text)
 
-            if len(tokens) >= 2048:
-                text = "...(truncated)\n" + enc.decode(tokens[-2047:])
+        if max_tokens and len(tokens) >= max_tokens:
+            text = "...(truncated)\n" + enc.decode(tokens[-(max_tokens - 1) :])
 
-            last_line = (
-                "(pending)" if BASH_STATE == "waiting_for_input" else "(won't exit)"
-            )
-            return text + f"\n{last_line}", cost
-        index = SHELL.expect(["#@@", pexpect.TIMEOUT], timeout=wait)
-        wait += timeout
+        last_line = "(pending)"
+        return text + f"\n{last_line}", 0
 
     assert isinstance(SHELL.before, str)
     output = render_terminal_output(SHELL.before)
 
     tokens = enc.encode(output)
-    if len(tokens) >= 2048:
-        output = "...(truncated)\n" + enc.decode(tokens[-2047:])
+    if max_tokens and len(tokens) >= max_tokens:
+        output = "...(truncated)\n" + enc.decode(tokens[-(max_tokens - 1) :])
 
     try:
         exit_code = _get_exit_code()
@@ -236,7 +227,7 @@ def execute_bash(
 
 class ReadImage(BaseModel):
     file_path: str
-    type: Literal['ReadImage'] = 'ReadImage'
+    type: Literal["ReadImage"] = "ReadImage"
 
 
 def serve_image_in_bg(file_path: str, client_uuid: str, name: str) -> None:
@@ -258,11 +249,11 @@ def serve_image_in_bg(file_path: str, client_uuid: str, name: str) -> None:
             print(f"Connection closed for UUID: {client_uuid}, retrying")
             serve_image_in_bg(file_path, client_uuid, name)
 
+
 class ImageData(BaseModel):
     dataurl: str
 
 
-
 Param = ParamSpec("Param")
 
 T = TypeVar("T")
@@ -281,6 +272,7 @@ def ensure_no_previous_output(func: Callable[Param, T]) -> Callable[Param, T]:
 
     return wrapper
 
+
 @ensure_no_previous_output
 def read_image_from_shell(file_path: str) -> ImageData:
     if not os.path.isabs(file_path):
@@ -297,8 +289,8 @@ def read_image_from_shell(file_path: str) -> ImageData:
         image_bytes = image_file.read()
         image_b64 = base64.b64encode(image_bytes).decode("utf-8")
         image_type = mimetypes.guess_type(file_path)[0]
-        return ImageData(dataurl=f'data:{image_type};base64,{image_b64}')
-    
+        return ImageData(dataurl=f"data:{image_type};base64,{image_b64}")
+
 
 @ensure_no_previous_output
 def write_file(writefile: Writefile) -> str:
@@ -349,11 +341,17 @@ def which_tool(args: str) -> BaseModel:
 
 
 def get_tool_output(
-    args: dict | Confirmation | ExecuteBash | Writefile | AIAssistant | DoneFlag | ReadImage,
+    args: dict[object, object]
+    | Confirmation
+    | ExecuteBash
+    | Writefile
+    | AIAssistant
+    | DoneFlag
+    | ReadImage,
     enc: tiktoken.Encoding,
     limit: float,
     loop_call: Callable[[str, float], tuple[str, float]],
-    is_waiting_user_input: Callable[[str], tuple[BASH_CLF_OUTPUT, float]],
+    max_tokens: Optional[int],
 ) -> tuple[str | ImageData | DoneFlag, float]:
     if isinstance(args, dict):
         adapter = TypeAdapter[
@@ -362,13 +360,13 @@ def get_tool_output(
         arg = adapter.validate_python(args)
     else:
         arg = args
-    output: tuple[str | DoneFlag, float]
+    output: tuple[str | DoneFlag | ImageData, float]
     if isinstance(arg, Confirmation):
         console.print("Calling ask confirmation tool")
         output = ask_confirmation(arg), 0.0
     elif isinstance(arg, ExecuteBash):
         console.print("Calling execute bash tool")
-        output = execute_bash(enc, arg, is_waiting_user_input)
+        output = execute_bash(enc, arg, max_tokens)
     elif isinstance(arg, Writefile):
         console.print("Calling write file tool")
         output = write_file(arg), 0
@@ -391,7 +389,9 @@ def get_tool_output(
 History = list[ChatCompletionMessageParam]
 
 
-def get_is_waiting_user_input(model: Models, cost_data: CostData):
+def get_is_waiting_user_input(
+    model: Models, cost_data: CostData
+) -> Callable[[str], tuple[BASH_CLF_OUTPUT, float]]:
     enc = tiktoken.encoding_for_model(model if not model.startswith("o1") else "gpt-4o")
     system_prompt = """You need to classify if a bash program is waiting for user input based on its stdout, or if it won't exit. You'll be given the output of any program.
     Return `waiting_for_input` if the program is waiting for INTERACTIVE input only, Return 'running' if it's waiting for external resources or just waiting to finish.
@@ -451,7 +451,7 @@ def execute_user_input() -> None:
                         ExecuteBash(
                             send_ascii=[ord(x) for x in user_input] + [ord("\n")]
                         ),
-                        lambda x: ("waiting_for_input", 0),
+                        max_tokens=None,
                     )[0]
                 )
             except Exception as e:
@@ -467,31 +467,25 @@ async def register_client(server_url: str, client_uuid: str = "") -> None:
 
     # Create the WebSocket connection
     async with websockets.connect(f"{server_url}/{client_uuid}") as websocket:
-        print(f"Connected. Share this user id with the chatbot: {client_uuid} \nLink: https://chatgpt.com/g/g-Us0AAXkRh-wcgw-giving-shell-access")
+        print(
+            f"Connected. Share this user id with the chatbot: {client_uuid} \nLink: https://chatgpt.com/g/g-Us0AAXkRh-wcgw-giving-shell-access"
+        )
         try:
             while True:
                 # Wait to receive data from the server
                 message = await websocket.recv()
                 mdata = Mdata.model_validate_json(message)
                 with execution_lock:
-                    # is_waiting_user_input = get_is_waiting_user_input(
-                    #     default_model, default_cost
-                    # )
-                    is_waiting_user_input = lambda x: ("waiting_for_input", 0)
                     try:
                         output, cost = get_tool_output(
-                            mdata.data,
-                            default_enc,
-                            0.0,
-                            lambda x, y: ("", 0),
-                            is_waiting_user_input,
+                            mdata.data, default_enc, 0.0, lambda x, y: ("", 0), None
                         )
                         curr_cost += cost
                         print(f"{curr_cost=}")
                     except Exception as e:
                         output = f"GOT EXCEPTION while calling tool. Error: {e}"
                         traceback.print_exc()
-                    assert not isinstance(output, DoneFlag)
+                    assert isinstance(output, str)
                     await websocket.send(output)
 
         except (websockets.ConnectionClosed, ConnectionError):
@@ -499,14 +493,17 @@ async def register_client(server_url: str, client_uuid: str = "") -> None:
             await register_client(server_url, client_uuid)
 
 
-def run() -> None:
-    if len(sys.argv) > 1:
-        server_url = sys.argv[1]
-    else:
-        server_url = "wss://wcgw.arcfu.com/register"
+run = Typer(pretty_exceptions_show_locals=False, no_args_is_help=True)
+
 
+@run.command()
+def app(
+    server_url: str = "wss://wcgw.arcfu.com/register", client_uuid: Optional[str] = None
+) -> None:
     thread1 = threading.Thread(target=execute_user_input)
-    thread2 = threading.Thread(target=asyncio.run, args=(register_client(server_url),))
+    thread2 = threading.Thread(
+        target=asyncio.run, args=(register_client(server_url, client_uuid or ""),)
+    )
 
     thread1.start()
     thread2.start()

{wcgw-0.0.9 → wcgw-0.0.10}/uv.lock

@@ -1023,7 +1023,7 @@ wheels = [
 
 [[package]]
 name = "wcgw"
-version = "0.0.9"
+version = "0.0.10"
 source = { editable = "." }
 dependencies = [
     { name = "fastapi" },
@@ -1031,6 +1031,7 @@ dependencies = [
     { name = "openai" },
     { name = "petname" },
     { name = "pexpect" },
+    { name = "pydantic" },
     { name = "pyte" },
     { name = "python-dotenv" },
     { name = "rich" },
@@ -1058,6 +1059,7 @@ requires-dist = [
     { name = "openai", specifier = ">=1.46.0" },
     { name = "petname", specifier = ">=2.6" },
     { name = "pexpect", specifier = ">=4.9.0" },
+    { name = "pydantic", specifier = ">=2.9.2" },
     { name = "pyte", specifier = ">=0.8.2" },
     { name = "python-dotenv", specifier = ">=1.0.1" },
     { name = "rich", specifier = ">=13.8.1" },

wcgw-0.0.9/PKG-INFO

@@ -1,63 +0,0 @@
-Metadata-Version: 2.3
-Name: wcgw
-Version: 0.0.9
-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>
-Requires-Python: <3.13,>=3.8
-Requires-Dist: fastapi>=0.115.0
-Requires-Dist: mypy>=1.11.2
-Requires-Dist: openai>=1.46.0
-Requires-Dist: petname>=2.6
-Requires-Dist: pexpect>=4.9.0
-Requires-Dist: pyte>=0.8.2
-Requires-Dist: python-dotenv>=1.0.1
-Requires-Dist: rich>=13.8.1
-Requires-Dist: shell>=1.0.1
-Requires-Dist: tiktoken==0.7.0
-Requires-Dist: toml>=0.10.2
-Requires-Dist: typer>=0.12.5
-Requires-Dist: types-pexpect>=4.9.0.20240806
-Requires-Dist: uvicorn>=0.31.0
-Requires-Dist: websockets>=13.1
-Description-Content-Type: text/markdown
-
-# Shell access to chatgpt.com
-
-### 🚀 Highlights
-- ⚡ **Full Shell Access**: No restrictions, complete control.
-- ⚡ **Create, Execute, Iterate**: Seamless workflow for development and execution.
-- ⚡ **Interactive Command Handling**: Supports interactive commands with ease.
-
-
-###  🪜 Steps: 
-1. Run the [cli client](https://github.com/rusiaaman/wcgw?tab=readme-ov-file#client) in any directory of choice.
-2. Share the generated id with the GPT: `https://chatgpt.com/g/g-Us0AAXkRh-wcgw-giving-shell-access`
-3. The custom GPT can now run any command on your cli
-
-## Client
-
-### Option 1: using pip
-```sh
-$ pip install wcgw
-$ wcgw
-```
-
-### Option 2: using uv
-```sh
-$ curl -LsSf https://astral.sh/uv/install.sh | sh
-$ uv tool run wcgw
-```
-
-This will print a UUID that you need to share with the gpt.
-
-
-## Chat
-https://chatgpt.com/g/g-Us0AAXkRh-wcgw-giving-shell-access
-
-Add user id the client generated to the first message along with the instructions.
-
-# How it works
-Your commands are relayed through a server I've hosted at https://wcgw.arcfu.com. The code for that is at `src/relay/serve.py`. 
-
-The user id that you share with chatgpt is added in the request it sents to the relay server which holds a websocket with the terminal client.

wcgw-0.0.9/README.md

@@ -1,39 +0,0 @@
-# Shell access to chatgpt.com
-
-### 🚀 Highlights
-- ⚡ **Full Shell Access**: No restrictions, complete control.
-- ⚡ **Create, Execute, Iterate**: Seamless workflow for development and execution.
-- ⚡ **Interactive Command Handling**: Supports interactive commands with ease.
-
-
-###  🪜 Steps: 
-1. Run the [cli client](https://github.com/rusiaaman/wcgw?tab=readme-ov-file#client) in any directory of choice.
-2. Share the generated id with the GPT: `https://chatgpt.com/g/g-Us0AAXkRh-wcgw-giving-shell-access`
-3. The custom GPT can now run any command on your cli
-
-## Client
-
-### Option 1: using pip
-```sh
-$ pip install wcgw
-$ wcgw
-```
-
-### Option 2: using uv
-```sh
-$ curl -LsSf https://astral.sh/uv/install.sh | sh
-$ uv tool run wcgw
-```
-
-This will print a UUID that you need to share with the gpt.
-
-
-## Chat
-https://chatgpt.com/g/g-Us0AAXkRh-wcgw-giving-shell-access
-
-Add user id the client generated to the first message along with the instructions.
-
-# How it works
-Your commands are relayed through a server I've hosted at https://wcgw.arcfu.com. The code for that is at `src/relay/serve.py`. 
-
-The user id that you share with chatgpt is added in the request it sents to the relay server which holds a websocket with the terminal client.