wcgw 0.1.0__tar.gz → 0.1.1__tar.gz

wcgw-0.1.1/.github/workflows/python-tests.yml

@@ -0,0 +1,30 @@
+name: Python Test
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11", "3.12"]
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: "${{ matrix.python-version }}"
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install build
+        pip install .[dev]  # Installs dependencies based on pyproject.toml
+    - name: Run tests
+      run: |
+        python -m unittest discover -s tests

wcgw-0.1.1/.python-version

@@ -0,0 +1 @@
+3.12

wcgw-0.1.1/PKG-INFO

@@ -0,0 +1,120 @@
+Metadata-Version: 2.3
+Name: wcgw
+Version: 0.1.1
+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,>=3.10
+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.
+
+[![Tests](https://github.com/rusiaaman/wcgw/actions/workflows/python-tests.yml/badge.svg?branch=main)](https://github.com/rusiaaman/wcgw/actions/workflows/python-tests.yml)
+[![Build](https://github.com/rusiaaman/wcgw/actions/workflows/python-publish.yml/badge.svg)](https://github.com/rusiaaman/wcgw/actions/workflows/python-publish.yml)
+
+### 🚀 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
+You need to keep running this client for GPT to access your shell. Run it in a version controlled project's root.
+
+### Option 1: using uv [Recommended]
+```sh
+$ curl -LsSf https://astral.sh/uv/install.sh | sh
+$ uv tool run --python 3.12 wcgw@latest
+```
+
+### Option 2: using pip
+Supports python >=3.10 and <3.13
+```sh
+$ pip3 install wcgw
+$ 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 client 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. 
+
+# Showcase
+
+## Unit tests and github actions
+[The first version of unit tests and github workflow to test on multiple python versions were written by the custom chatgpt](https://chatgpt.com/share/6717f922-8998-8005-b825-45d4b348b4dd)
+
+## Create a todo app using react + typescript + vite
+![Screenshot](https://github.com/rusiaaman/wcgw/blob/main/static/ss1.png?raw=true)
+
+
+# Privacy
+The relay server doesn't store any data. I can't access any information passing through it and only secure channels are used to communicate.
+
+You may host the server on your own and create a custom gpt using the following section.
+
+# Creating your own custom gpt and the relay server.
+I've used the following instructions and action json schema to create the custom GPT. (Replace wcgw.arcfu.com with the address to your server)
+
+https://github.com/rusiaaman/wcgw/blob/main/gpt_instructions.txt
+https://github.com/rusiaaman/wcgw/blob/main/gpt_action_json_schema.json
+
+Run the server 
+`gunicorn --worker-class uvicorn.workers.UvicornWorker --bind 0.0.0.0:443 src.relay.serve:app  --certfile fullchain.pem  --keyfile  privkey.pem`
+
+If you don't have public ip and domain name, you can use `ngrok` or similar services to get a https address to the api.
+
+The specify the server url in the `wcgw` command like so
+`wcgw --server-url https://your-url/register`
+
+# [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-0.1.1/README.md

@@ -0,0 +1,95 @@
+# Enable shell access on chatgpt.com
+A custom gpt on chatgpt web app to interact with your local shell.
+
+[![Tests](https://github.com/rusiaaman/wcgw/actions/workflows/python-tests.yml/badge.svg?branch=main)](https://github.com/rusiaaman/wcgw/actions/workflows/python-tests.yml)
+[![Build](https://github.com/rusiaaman/wcgw/actions/workflows/python-publish.yml/badge.svg)](https://github.com/rusiaaman/wcgw/actions/workflows/python-publish.yml)
+
+### 🚀 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
+You need to keep running this client for GPT to access your shell. Run it in a version controlled project's root.
+
+### Option 1: using uv [Recommended]
+```sh
+$ curl -LsSf https://astral.sh/uv/install.sh | sh
+$ uv tool run --python 3.12 wcgw@latest
+```
+
+### Option 2: using pip
+Supports python >=3.10 and <3.13
+```sh
+$ pip3 install wcgw
+$ 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 client 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. 
+
+# Showcase
+
+## Unit tests and github actions
+[The first version of unit tests and github workflow to test on multiple python versions were written by the custom chatgpt](https://chatgpt.com/share/6717f922-8998-8005-b825-45d4b348b4dd)
+
+## Create a todo app using react + typescript + vite
+![Screenshot](https://github.com/rusiaaman/wcgw/blob/main/static/ss1.png?raw=true)
+
+
+# Privacy
+The relay server doesn't store any data. I can't access any information passing through it and only secure channels are used to communicate.
+
+You may host the server on your own and create a custom gpt using the following section.
+
+# Creating your own custom gpt and the relay server.
+I've used the following instructions and action json schema to create the custom GPT. (Replace wcgw.arcfu.com with the address to your server)
+
+https://github.com/rusiaaman/wcgw/blob/main/gpt_instructions.txt
+https://github.com/rusiaaman/wcgw/blob/main/gpt_action_json_schema.json
+
+Run the server 
+`gunicorn --worker-class uvicorn.workers.UvicornWorker --bind 0.0.0.0:443 src.relay.serve:app  --certfile fullchain.pem  --keyfile  privkey.pem`
+
+If you don't have public ip and domain name, you can use `ngrok` or similar services to get a https address to the api.
+
+The specify the server url in the `wcgw` command like so
+`wcgw --server-url https://your-url/register`
+
+# [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-0.1.1/gpt_action_json_schema.json

@@ -0,0 +1,231 @@
+
+{
+  "openapi": "3.1.0",
+  "info": {
+    "title": "FastAPI",
+    "version": "0.1.0"
+  },
+  "servers": [
+    {"url": "https://wcgw.arcfu.com"}
+  ],
+  "paths": {
+    "/write_file": {
+      "post": {
+        "x-openai-isConsequential": false,
+        "summary": "Write File",
+        "operationId": "write_file_write_file__uuid__post",
+        "parameters": [
+          {
+            "name": "user_id",
+            "in": "query",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "format": "uuid",
+              "title": "User Id"
+            }
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/Writefile"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "string",
+                  "title": "Response Write File Write File  Uuid  Post"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/HTTPValidationError"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
+    "/execute_bash": {
+      "post": {
+        "x-openai-isConsequential": false,
+        "summary": "Execute Bash",
+        "operationId": "execute_bash_execute_bash__uuid__post",
+        "parameters": [
+          {
+            "name": "user_id",
+            "in": "query",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "format": "uuid",
+              "title": "User Id"
+            }
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ExecuteBash"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "string",
+                  "title": "Response Execute Bash Execute Bash  Uuid  Post"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/HTTPValidationError"
+                }
+              }
+            }
+          }
+        }
+      }
+    }
+  },
+  "components": {
+    "schemas": {
+      "ExecuteBash": {
+        "properties": {
+          "execute_command": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "title": "Execute Command"
+          },
+          "send_ascii": {
+            "anyOf": [
+              {
+                "items": {
+                  "anyOf": [
+                    {
+                      "type": "integer"
+                    },
+                    {
+                      "type": "string",
+                      "enum": [
+                        "Key-up",
+                        "Key-down",
+                        "Key-left",
+                        "Key-right",
+                        "Enter",
+                        "Ctrl-c"
+                      ]
+                    }
+                  ]
+                },
+                "type": "array"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "title": "Send Ascii"
+          }
+        },
+        "type": "object",
+        "title": "ExecuteBash"
+      },
+      "HTTPValidationError": {
+        "properties": {
+          "detail": {
+            "items": {
+              "$ref": "#/components/schemas/ValidationError"
+            },
+            "type": "array",
+            "title": "Detail"
+          }
+        },
+        "type": "object",
+        "title": "HTTPValidationError"
+      },
+      "ValidationError": {
+        "properties": {
+          "loc": {
+            "items": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "integer"
+                }
+              ]
+            },
+            "type": "array",
+            "title": "Location"
+          },
+          "msg": {
+            "type": "string",
+            "title": "Message"
+          },
+          "type": {
+            "type": "string",
+            "title": "Error Type"
+          }
+        },
+        "type": "object",
+        "required": [
+          "loc",
+          "msg",
+          "type"
+        ],
+        "title": "ValidationError"
+      },
+      "Writefile": {
+        "properties": {
+          "file_path": {
+            "type": "string",
+            "title": "File Path"
+          },
+          "file_content": {
+            "type": "string",
+            "title": "File Content"
+          }
+        },
+        "type": "object",
+        "required": [
+          "file_path",
+          "file_content"
+        ],
+        "title": "Writefile"
+      }
+    }
+  }
+}

wcgw-0.1.1/gpt_instructions.txt

@@ -0,0 +1,31 @@
+You're a cli assistant.
+
+Instructions:
+
+    - You should use the provided bash execution tool to run script to complete objective. 
+    - Do not use sudo. Do not use interactive commands. 
+    - Ask user for confirmation before running anything major
+
+
+To execute bash commands OR write files use the provided api `wcgw.arcfu.com`
+
+Instructions for `Execute Bash`:
+- Execute a bash script. This is stateful (beware with subsequent calls).
+- Execute commands using `execute_command` attribute.
+- Do not use interactive commands like nano. Prefer writing simpler commands.
+- Last line will always be `(exit <int code>)` except if
+- The last line is `(pending)` if the program is still running or waiting for your input. You can then send input using `send_ascii` attributes. You get status by sending new line `send_ascii: ["Enter"]` or `send_ascii: [10]`.
+- Optionally the last line is `(won't exit)` in which case you need to kill the process if you want to run a new command.
+- Optionally `exit shell has restarted` is the output, in which case environment resets, you can run fresh commands.
+- The first line might be `(...truncated)` if the output is too long.
+- Always run `pwd` if you get any file or directory not found error to make sure you're not lost.
+
+Instructions for `Write File`
+- Write content to a file. Provide file path and content. Use this instead of ExecuteBash for writing files.
+
+---
+
+Always critically think and debate with yourself to solve the problem. Understand the context and the code by reading as much resources as possible before writing a single piece of code.
+
+---
+Ask the user for the user_id `UUID` if they haven't provided in the first message.

{wcgw-0.1.0 → wcgw-0.1.1}/pyproject.toml

@@ -1,9 +1,10 @@
 [project]
+authors = [{ name = "Aman Rusia", email = "gapypi@arcfu.com" }]
 name = "wcgw"
-version = "0.1.0"
+version = "0.1.1"
 description = "What could go wrong giving full shell access to chatgpt?"
 readme = "README.md"
-requires-python = ">=3.12"
+requires-python = ">=3.10, <3.13"
 dependencies = [
     "openai>=1.46.0",
     "mypy>=1.11.2",
@@ -20,8 +21,12 @@ dependencies = [
     "fastapi>=0.115.0",
     "uvicorn>=0.31.0",
     "websockets>=13.1",
+    "pydantic>=2.9.2",
 ]
 
+[project.urls]
+Homepage = "https://github.com/rusiaaman/wcgw"
+
 [build-system]
 requires = ["hatchling"]
 build-backend = "hatchling.build"
@@ -32,8 +37,8 @@ wcgw = "wcgw:listen"
 
 [tool.uv]
 dev-dependencies = [
-    "ipython>=8.27.0",
     "mypy>=1.11.2",
     "types-toml>=0.10.8.20240310",
     "autoflake",
+    "ipython>=8.12.3",
 ]

{wcgw-0.1.0 → wcgw-0.1.1}/src/relay/serve.py

@@ -1,12 +1,14 @@
 import asyncio
+import base64
 import threading
 import time
-from typing import Callable, Coroutine, Literal, Optional, Sequence
+from typing import Any, Callable, Coroutine, DefaultDict, Literal, Optional, Sequence
 from uuid import UUID
 import fastapi
 from fastapi import WebSocket, WebSocketDisconnect
 from pydantic import BaseModel
 import uvicorn
+from fastapi.staticfiles import StaticFiles
 
 from dotenv import load_dotenv
 
@@ -35,6 +37,30 @@ clients: dict[UUID, Callable[[Mdata], Coroutine[None, None, None]]] = {}
 websockets: dict[UUID, WebSocket] = {}
 gpts: dict[UUID, Callable[[str], None]] = {}
 
+images: DefaultDict[UUID, dict[str, dict[str, Any]]] = DefaultDict(dict)
+
+
+@app.websocket("/register_serve_image/{uuid}")
+async def register_serve_image(websocket: WebSocket, uuid: UUID) -> None:
+    raise Exception("Disabled")
+    await websocket.accept()
+    received_data = await websocket.receive_json()
+    name = received_data["name"]
+    image_b64 = received_data["image_b64"]
+    image_bytes = base64.b64decode(image_b64)
+    images[uuid][name] = {
+        "content": image_bytes,
+        "media_type": received_data["media_type"],
+    }
+
+
+@app.get("/get_image/{uuid}/{name}")
+async def get_image(uuid: UUID, name: str) -> fastapi.responses.Response:
+    return fastapi.responses.Response(
+        content=images[uuid][name]["content"],
+        media_type=images[uuid][name]["media_type"],
+    )
+
 
 @app.websocket("/register/{uuid}")
 async def register_websocket(websocket: WebSocket, uuid: UUID) -> None:
@@ -60,9 +86,34 @@ async def register_websocket(websocket: WebSocket, uuid: UUID) -> None:
         print(f"Client {uuid} disconnected")
 
 
-@app.post("/action")
-async def chatgpt_server(json_data: Mdata) -> str:
-    user_id = json_data.user_id
+@app.post("/write_file")
+async def write_file(write_file_data: Writefile, user_id: UUID) -> str:
+    if user_id not in clients:
+        raise fastapi.HTTPException(
+            status_code=404, detail="User with the provided id not found"
+        )
+
+    results: Optional[str] = None
+
+    def put_results(result: str) -> None:
+        nonlocal results
+        results = result
+
+    gpts[user_id] = put_results
+
+    await clients[user_id](Mdata(data=write_file_data, user_id=user_id))
+
+    start_time = time.time()
+    while time.time() - start_time < 30:
+        if results is not None:
+            return results
+        await asyncio.sleep(0.1)
+
+    raise fastapi.HTTPException(status_code=500, detail="Timeout error")
+
+
+@app.post("/execute_bash")
+async def execute_bash(excute_bash_data: ExecuteBash, user_id: UUID) -> str:
     if user_id not in clients:
         raise fastapi.HTTPException(
             status_code=404, detail="User with the provided id not found"
@@ -76,7 +127,7 @@ async def chatgpt_server(json_data: Mdata) -> str:
 
     gpts[user_id] = put_results
 
-    await clients[user_id](json_data)
+    await clients[user_id](Mdata(data=excute_bash_data, user_id=user_id))
 
     start_time = time.time()
     while time.time() - start_time < 30:
@@ -87,6 +138,9 @@ async def chatgpt_server(json_data: Mdata) -> str:
     raise fastapi.HTTPException(status_code=500, detail="Timeout error")
 
 
+app.mount("/static", StaticFiles(directory="static"), name="static")
+
+
 def run() -> None:
     load_dotenv()
 

wcgw-0.1.1/src/relay/static/privacy.txt

@@ -0,0 +1,7 @@
+Privacy Policy
+I do not collect, store, or share any personal data.
+The data from your terminal is not stored anywhere and it's not logged or collected in any form.
+There is a relay webserver for connecting your terminal to chatgpt the source code for which is open at https://github.com/rusiaaman/wcgw/tree/main/src/relay that you can run on your own.
+Other than the relay webserver there is no further involvement of my servers or services.
+Feel free to me contact at info@arcfu.com for questions on privacy or anything else.
+