package.json

{
  "name": "gptutor",
  "displayName": "GPTutor (🤖‚🤖)",
  "repository": {
    "type": "git",
    "url": "https://github.com/GPTutor/gptutor-extension"
  },
  "description": "A VS Code extension for AI Pair Programming and Smart Contract Development.",
  "publisher": "gptutor",
  "version": "1.1.0",
  "engines": {
    "vscode": "^1.75.0"
  },
  "categories": [
    "Other"
  ],
  "icon": "out/resources/extensionIcon.png",
  "activationEvents": [
    "onView:gptutor.chatView"
  ],
  "main": "out/extension.js",
  "scripts": {
    "vscode:prepublish": "npm run compile",
    "compile": "tsc -p ./ && copyfiles -u 1 \"src/resources/**/*\" out && copyfiles -u 1 \"src/media/**/*\" out",
    "watch": "tsc -watch -p ./",
    "pretest": "npm run compile && npm run lint",
    "lint": "eslint src --ext ts",
    "test": "node ./out/test/runTest.js",
    "publish": "npm run compile && vsce package && vsce publish",
    "package": "vsce package"
  },
  "contributes": {
    "configuration": {
      "title": "GPTutor",
      "properties": {
        "GPTutor.openaiApiKey": {
          "type": "string",
          "default": "",
          "description": "OpenAI API Key"
        },
        "GPTutor.openaiTemperature": {
          "type": "number",
          "default": 0.8,
          "description": "Temperature is a parameter that controls the “creativity” or randomness of the text generated by GPT-3. A higher temperature (e.g., 0.7) results in more diverse and creative output, while a lower temperature (e.g., 0.2) makes the output more deterministic and focused.\nIn practice, temperature affects the probability distribution over the possible tokens at each step of the generation process. A temperature of 0 would make the model completely deterministic, always choosing the most likely token."
        },
        "GPTutor.openaiBasePath": {
          "type": "string",
          "default": "",
          "description": "Override OpenAI base path, leave it blank for default"
        },
        "GPTutor.openaiModel": {
          "type": "string",
          "default": "gpt-3.5-turbo",
          "enum": [
            "gpt-3.5-turbo",
            "gpt-4",
            "gpt-3.5-turbo-0301",
            "gpt-4-0314"
          ],
          "enumDescriptions": [
            "Default model, use by ChatGPT",
            "GPT-4 can handle longer code and provide a superior response. Yet it is more expensive. You may need to apply for the access of GPT-4."
          ],
          "description": "OpenAI Model Selection"
        },
        "GPTutor.outputLanguage": {
          "type": "string",
          "default": "English",
          "enum": [
            "Afrikaans",
            "Albanian",
            "Amharic",
            "Arabic",
            "Armenian",
            "Assamese",
            "Aymara",
            "Azerbaijani",
            "Bambara",
            "Basque",
            "Belarusian",
            "Bengali",
            "Bhojpuri",
            "Bosnian",
            "Bulgarian",
            "Catalan",
            "Cebuano",
            "Chinese (Simplified)",
            "Chinese (Traditional)",
            "Corsican",
            "Croatian",
            "Czech",
            "Danish",
            "Dhivehi",
            "Dogri",
            "Dutch",
            "English",
            "Esperanto",
            "Estonian",
            "Ewe",
            "Filipino (Tagalog)",
            "Finnish",
            "French",
            "Frisian",
            "Galician",
            "Georgian",
            "German",
            "Greek",
            "Guarani",
            "Gujarati",
            "Haitian Creole",
            "Hausa",
            "Hawaiian",
            "Hebrew",
            "Hindi",
            "Hmong",
            "Hungarian",
            "Icelandic",
            "Igbo",
            "Ilocano",
            "Indonesian",
            "Irish",
            "Italian",
            "Japanese",
            "Javanese",
            "Kannada",
            "Kazakh",
            "Khmer",
            "Kinyarwanda",
            "Konkani",
            "Korean",
            "Krio",
            "Kurdish",
            "Kurdish (Sorani)",
            "Kyrgyz",
            "Lao",
            "Latin",
            "Latvian",
            "Lingala",
            "Lithuanian",
            "Luganda",
            "Luxembourgish",
            "Macedonian",
            "Maithili",
            "Malagasy",
            "Malay",
            "Malayalam",
            "Maltese",
            "Maori",
            "Marathi",
            "Meiteilon (Manipuri)",
            "Mizo",
            "Mongolian",
            "Myanmar (Burmese)",
            "Nepali",
            "Norwegian",
            "Nyanja (Chichewa)",
            "Odia (Oriya)",
            "Oromo",
            "Pashto",
            "Persian",
            "Polish",
            "Portuguese (Portugal, Brazil)",
            "Punjabi",
            "Quechua",
            "Romanian",
            "Russian",
            "Samoan",
            "Sanskrit",
            "Scots Gaelic",
            "Sepedi",
            "Serbian",
            "Sesotho",
            "Shona",
            "Sindhi",
            "Sinhala (Sinhalese)",
            "Slovak",
            "Slovenian",
            "Somali",
            "Spanish",
            "Sundanese",
            "Swahili",
            "Swedish",
            "Tagalog (Filipino)",
            "Tajik",
            "Tamil",
            "Tatar",
            "Telugu",
            "Thai",
            "Tigrinya",
            "Tsonga",
            "Turkish",
            "Turkmen",
            "Twi (Akan)",
            "Ukrainian",
            "Urdu",
            "Uyghur",
            "Uzbek",
            "Vietnamese",
            "Welsh",
            "Xhosa",
            "Yiddish",
            "Yoruba",
            "Zulu"
          ],
          "description": "Output language, this value will replace the ${outputLanguage} value in prompt."
        },
        "GPTutor.instructionForSpecificLanguage": {
          "type": "object",
          "description": "instruction after the prompt when user choose specific language. This can help the generated content to be more localized.",
          "default": {
            "Chinese (Traditional)": "請使用繁體中文與臺灣地區用語，不要用簡體字與中國大陸地區的用詞。比方請用「程式碼」而不是「代码」。"
          }
        },
        "GPTutor.prompts": {
          "type": "object",
          "description": "Prompts for GPTutor when you hover over a code block.",
          "default": {
            "global": {
              "explain": {
                "display_name": "🧑‍🏫 Explain",
                "type": "chatgpt-prompt",
                "prompt": [
                  {
                    "role": "system",
                    "content": "You are a Senior ${languageId} Developer \n I will provide some ${languageId} code, and it will be your job to explain the  ${languageId} code I selected."
                  },
                  {
                    "role": "user",
                    "content": "Other context about the selected code is in the following triple backquote (```) \n```\n${codeContext}\n```\n. The ${languageId} code I selected is in the following triple backquote (```) \n```\n${selectedCode}\n```\n. You don't need to repeat the selected code again. Please focus on explain target ${languageId} code. Output in ${outputLanguage}."
                  }
                ]
              },
              "comment": {
                "display_name": "📝 Comment",
                "type": "chatgpt-prompt",
                "prompt": [
                  {
                    "role": "system",
                    "content": "I want you to act as a professional ${languageId} Commenter. \n I will provide some code about ${languageId}, \n and it will be your job to add or rewrite comment on the provided ${languageId} code in ${outputLanguage}. You should only edit command, but keep the code the same."
                  },
                  {
                    "role": "user",
                    "content": "Here are some context of the code in the following triple backquote, don't output them: \n```\n${codeContext}\n```\n Here are the ${languageId} code I want you to add comment in the following triple backquote:\n```\n${selectedCode}\n```\n. Only return the code after modified. return the code with the triple backquote (```). Add or rewrite the comment in the given code in ${outputLanguage}."
                  }
                ]
              },
              "Review": {
                "display_name": "🕵️ Review",
                "type": "chatgpt-prompt",
                "prompt": [
                  {
                    "role": "system",
                    "content": "You are a Senior ${languageId} Developer \n I will provide some ${languageId} code, and it will be your job to do code review on the ${languageId} code I selected."
                  },
                  {
                    "role": "user",
                    "content": "Here is the full code context in the following triple backquote if needed. \n```\n${codeContext}\n```\n.\n\nHere is the selected code in the triple backquote: \n```\n${selectedCode}\n```\n\nGiven the selected ${languageId} code, I want you to do the following:\n\n1. if there is a problem, such as bug or security concern, with the selected code, modify the selected ${languageId} code and return it with the triple backquote (```). Add or rewrite the comment in the code in ${outputLanguage}.\n\n2. Then, check again if there is a security concern with the original code, modified code, and the context. List each of the concern.\n\n3. Refine and Review this code again \n Please think carefully. And Review this code to be better. \n If it is already quite secure and efficient, then you don't need to output anything in this step. Please focus on the selected code, but you may reference the full code context for more information. \nOutput in ${outputLanguage}."
                  }
                ]
              }
            },
            "specificLanguage": {
              "move": {
                "explain": {
                  "display_name": "🧑‍🏫 Explain",
                  "type": "chatgpt-prompt",
                  "prompt": [
                    {
                      "role": "system",
                      "content": "Move is an open source language for writing safe smart contracts. It's format is similar to Rust. You are a Senior ${languageId} Developer \n I will provide some ${languageId} code, and it will be your job to explain the  ${languageId} code I selected."
                    },
                    {
                      "role": "user",
                      "content": "Other context about the selected code is in the following triple backquote (```) \n```\n${codeContext}\n```\n. The ${languageId} code I selected is in the following triple backquote (```) \n```\n${selectedCode}\n```\n. Please focus on explain target ${languageId} code. Output in ${outputLanguage}."
                    }
                  ]
                },
                "comment": {
                  "display_name": "📝 Comment",
                  "type": "chatgpt-prompt",
                  "prompt": [
                    {
                      "role": "system",
                      "content": "Move is an open source language for writing safe smart contracts. It's format is similar to Rust. I want you to act as a professional ${languageId} Commenter. \n I will provide some code about ${languageId}, \n and it will be your job to add or rewrite comment on the provided ${languageId} code in ${outputLanguage}. You should only edit command, but keep the code the same."
                    },
                    {
                      "role": "user",
                      "content": "Here are some context of the code in the following triple backquote, don't output them: \n```\n${codeContext}\n```\n\n Here are the ${languageId} code I want you to add comment: \n```\n${selectedCode}\n```\n. Only return the code after modified. return the code in the triple backquote (```). Add or rewrite the comment in the given code in ${outputLanguage}, but keep the variable name the same."
                    }
                  ]
                },
                "Review": {
                  "display_name": "🕵️ Review",
                  "type": "chatgpt-prompt",
                  "prompt": [
                    {
                      "role": "system",
                      "content": "Move is an open source language for writing safe smart contracts. It's format is similar to Rust. You are a Senior ${languageId} Developer \n I will provide some ${languageId} code, and it will be your job to do code review on the ${languageId} code I selected."
                    },
                    {
                      "role": "user",
                      "content": "Here is the full code context in the following triple backquote if needed. \n```\n${codeContext}\n```\n.\n\nHere is the selected code in the triple backquote: \n```\n${selectedCode}\n```\n\nGiven the selected ${languageId} code, I want you to do the following:\n\n1. if there is a problem, such as bug or security concern, with the selected code, modify the selected ${languageId} code and return it with the triple backquote (```). Add or rewrite the comment in the code in ${outputLanguage}.\n\n2. Then, check again if there is a security concern with the original code, modified code, and the context. List each of the concern.\n\n3. Refine and Review this code again \n Please think carefully. And Review this code to be better. \n If it is already quite secure and efficient, then you don't need to output anything in this step. Please focus on the selected code, but you may reference the full code context for more information. \nOutput in ${outputLanguage}."
                    }
                  ]
                }
              }
            }
          }
        },
        "GPTutor.promptsForInputBox": {
          "type": "object",
          "default": {
            "global": {
              "default": {
                "display_name": "🤖 Code Generate",
                "type": "chatgpt-prompt",
                "prompt": [
                  {
                    "role": "system",
                    "content": "You are a helpful assistant that generate the ${languageId} code according to user's instruction and the context.Your output code should be surrounded with triple backquote (```) and new line. Please make very very sure to generate code snippets in the correct ${languageId} format. You dont need to interact with user but just generate all code directly. Please follow this convention throughout our conversation."
                  },
                  {
                    "role": "user",
                    "content": "Instruction: ${user_input}"
                  }
                ]
              },
              "rewriter": {
                "display_name": "🤖 Rewrite",
                "type": "chatgpt-prompt",
                "prompt": [
                  {
                    "role": "system",
                    "content": "You are a helpful assistant that rewrite the selected ${languageId} code with the user's instruction and according to the provided context. Make sure the rewrited code fit the context, instead of use undefined variable. Your output should be surrounded with triple backquote (```) and new line. Please follow this convention throughout our conversation.\nHere are some context about the code to help you rewrite, delimited by the following triple backquote (```): \n```\n${codeContext}\n```\n. If there is no selected code provided, ignore selected code and generate code directly according to instruction."
                  },
                  {
                    "role": "user",
                    "content": "Instruction: ${user_input}\nselected ${languageId} code: \n```\n${selectedCode}\n```\n"
                  }
                ]
              },
              "tailwind": {
                "display_name": "🤖 Tailwind Rewrite",
                "type": "chatgpt-prompt",
                "prompt": [
                  {
                    "role": "system",
                    "content": "You are a helpful assistant that rewrite the html code with the user's instruction in Tailwind CSS class. Your output should be surrounded with triple backquote (```) and new line, such as: \n```\n<div>Hi</div>\n```\n. Make sure each HTML tag is start with < and end with >. Please make very very sure to generate code snippets in the correct HTML format. Please follow this convention throughout our conversation."
                  },
                  {
                    "role": "user",
                    "content": "Instruction: ${user_input}\n\nThe code:\n```\n${selectedCode}\n```\n"
                  }
                ]
              }
            },
            "specificLanguage": {
              "python": {
                "fastAPI Master": {
                  "display_name": "🤖 FastAPI Master",
                  "type": "chatgpt-prompt",
                  "prompt": [
                    {
                      "role": "user",
                      "content": "You are a master python coder in fastapi! Complete the ${languageId} fastAPI code below with the instruction text delimited by triple backquote (```). \n\n\n\n\n```\n${user_input}\n```\nOutput your explain and comment in ${outputLanguage} but the code and variable name should be in English."
                    }
                  ]
                }
              },
              "move": {
                "CoinCreater": {
                  "display_name": "🪙 Coin Creator",
                  "type": "chatgpt-prompt",
                  "prompt": [
                    {
                      "role": "system",
                      "content": "You are a helpful assistant that generate the move code according to user's instruction and the context. Your output code should be surrounded with triple backquote (```) and new line. Please make very very sure to generate code snippets in the correct move format (which is similar to Rust). You don't need to interact with user or ask further information but just generate code directly. Rewrite the move code below with the user's instruction: \n```move\n// Copyright (c) Mysten Labs, Inc.\n// SPDX-License-Identifier: Apache-2.0\n\n/// Example coin with a trusted manager responsible for minting/burning (e.g., a stablecoin)\n/// By convention, modules defining custom coin types use upper case names, in contrast to\n/// ordinary modules, which use camel case.\nmodule fungible_coin::managed {\n    use std::option;\n    use sui::coin::{Self, Coin, TreasuryCap};\n    use sui::transfer;\n    use sui::tx_context::{Self, TxContext};\n    use sui::url;\n\n    /// Name of the coin. By convention, this type has the same name as its parent module\n    /// and has no fields. The full type of the coin defined by this module will be `COIN<MANAGED>`.\n    struct MANAGED has drop {}\n\n    /// Register the managed currency to acquire its `TreasuryCap`. Because\n    /// this is a module initializer, it ensures the currency only gets\n    /// registered once.\n    fun init(witness: MANAGED, ctx: &mut TxContext) {\n        // Get a treasury cap for the coin and give it to the transaction sender\n        let decimals = 2;\n        let symbol = b\"SYMBOL_OF_THE_COIN\";\n        let name = b\"NAME_OF_THE_COIN\";\n        let description =  b\"DESCRIPTION_OF_THE_COIN\";\n        let icon_url = option::some(url::new_unsafe_from_bytes(b\"https://blog.sui.io/content/images/2023/04/Sui_Droplet_Logo_Blue-3.png\"));\n        \n        let (treasury_cap, metadata) = coin::create_currency<MANAGED>(witness, decimals, symbol, name, description, icon_url, ctx);\n        transfer::public_freeze_object(metadata);\n        coin::mint_and_transfer(&mut treasury_cap, 100000, tx_context::sender(ctx), ctx);\n        transfer::public_transfer(treasury_cap, tx_context::sender(ctx))\n        \n    }\n\n    /// Manager can mint new coins\n    public entry fun mint(\n        treasury_cap: &mut TreasuryCap<MANAGED>, amount: u64, recipient: address, ctx: &mut TxContext\n    ) {\n        coin::mint_and_transfer(treasury_cap, amount, recipient, ctx)\n    }\n\n    /// Manager can burn coins\n    public entry fun burn(treasury_cap: &mut TreasuryCap<MANAGED>, coin: Coin<MANAGED>) {\n        coin::burn(treasury_cap, coin);\n    }\n\n}\n// Publish it by running `sui client publish . --gas COIN_OBJECT_ID --gas-budget 300000000 --skip-dependency-verification`\n```\n"
                    },
                    {
                      "role": "user",
                      "content": "Instruction: ${user_input}"
                    }
                  ]
                }
              },
              "javascript": {
                "default": {
                  "display_name": "🤖 React Helper",
                  "type": "chatgpt-prompt",
                  "prompt": [
                    {
                      "role": "user",
                      "content": "You are a react generator! \n\nHere are the code before the cursor delimited by triple backquote (```): \n```\n${codeBefore}\n```\n\n\nAnd here are the code after the cursor delimited by triple backquote (```): \n```\n${codeAfter}\n```\n\n\nHere is the code selected by the user delimited by triple backquote (```): \n```\n${selectedCode}\n```\n\n\nComplete the react code on the cursor or refactor the selected code with the instruction text delimited by triple backquote (```). \n\n\n\n\n```\n${user_input}\n```\nOutput your explain and comment in ${outputLanguage} but the code and variable name should be in English."
                    }
                  ]
                }
              }
            }
          },
          "description": "Prompts for GPTutor when you chat with it in the input box"
        }
      }
    },
    "commands": [
      {
        "command": "Initialize GPTutor",
        "title": "GPTutor: init"
      },
      {
        "command": "Set OpenAI API Key",
        "title": "GPTutor: setKey"
      },
      {
        "command": "Delete OpenAI API Key",
        "title": "GPTutor: deleteKey"
      },
      {
        "command": "Set Model",
        "title": "GPTutor: setModel"
      },
      {
        "command": "GPTutor Active",
        "title": "GPTutor: active"
      },
      {
        "command": "GPTutor Edit Prompts",
        "title": "GPTutor: edit prompts"
      },
      {
        "command": "GPTutor Reset Prompts Config",
        "title": "GPTutor: reset prompts"
      }
    ],
    "menus": {
      "editor/context": [],
      "commandPalette": []
    },
    "viewsContainers": {
      "activitybar": [
        {
          "id": "gptutor",
          "title": "GPTutor",
          "icon": "out/resources/icon.png"
        }
      ]
    },
    "views": {
      "gptutor": [
        {
          "type": "webview",
          "id": "GPTutor.chatView",
          "name": "GPTutor"
        }
      ]
    }
  },
  "devDependencies": {
    "@types/glob": "^8.1.0",
    "@types/mocha": "^10.0.1",
    "@types/node": "16.x",
    "@types/vscode": "^1.75.0",
    "@typescript-eslint/eslint-plugin": "^5.53.0",
    "@typescript-eslint/parser": "^5.53.0",
    "@vscode/test-cli": "^0.0.4",
    "@vscode/test-electron": "^2.3.8",
    "eslint": "^8.34.0",
    "glob": "^8.1.0",
    "mocha": "^10.2.0",
    "typescript": "^4.9.5",
    "vscode-extension-tester": "^5.7.1"
  },
  "dependencies": {
    "axios": "^1.4.0",
    "command-exists": "^1.2.9",
    "copyfiles": "^2.4.1",
    "openai": "^4.20.1",
    "vscode-languageclient": "^6.1.4"
  }
}