ChatGPT AI

Generates new code by sending selected text or entire file context to OpenAI's GPT models (GPT-4, GPT-3.5, or Codex) via either official ChatGPT API or unofficial proxy, with streaming response delivery directly into the VS Code editor. The extension maintains conversation context across follow-up queries, allowing iterative refinement of generated code without re-specifying the original intent.

Analyzes selected code snippets by sending them to OpenAI models with an implicit 'find bugs' system prompt, returning identified issues, potential runtime errors, and logic problems as streamed text responses. The analysis is stateless per invocation — each bug-finding request is independent and does not maintain conversation context.

Provides a dedicated sidebar panel in VS Code for chat-based interaction with OpenAI models, displaying conversation history (user queries and AI responses) in chronological order. Users type queries in an input box at the bottom of the panel, and responses appear above with full conversation context preserved within the session. The sidebar panel is always accessible and can be toggled via VS Code's sidebar toggle button.

When generated code is inserted into the editor via right-click context menu actions or sidebar chat, the extension automatically adjusts indentation to match the current cursor position and surrounding code context. This pattern prevents broken indentation that would require manual fixing, allowing seamless code insertion into nested structures (functions, classes, conditionals).

Extension is free to install and use from VS Code Marketplace, but requires either a free ChatGPT account (ChatGPTUnofficialProxyAPI mode with token refresh every 8 hours) or an OpenAI API key with per-token billing (ChatGPTAPI mode). No subscription required for the extension itself, but users incur OpenAI API costs if using official API mode. Unofficial proxy mode is free but unreliable and violates OpenAI terms of service.

Converts selected code snippets into human-readable explanations or auto-generated documentation by sending code to OpenAI models with explanation/documentation system prompts. Responses are streamed into the sidebar chat panel and can be toggled between markdown-rendered and raw text display, supporting both quick understanding and copy-paste documentation workflows.

Analyzes selected code and generates refactored versions with optimization suggestions by sending code to OpenAI models with implicit refactoring prompts. The extension returns improved code variants with explanations of changes, which can be manually copied back into the editor or used as reference for manual refactoring.

Generates code implementations based on comment descriptions by sending comments and surrounding code context to OpenAI models, returning completed code that matches the comment intent. The generated code is streamed into the editor with automatic indentation correction, allowing developers to write comments first and let AI fill in implementation.

Maintains conversation context across multiple user queries in the sidebar chat panel, allowing follow-up questions about previously generated code or explanations without re-specifying context. The extension stores conversation history within the session and sends previous exchanges to OpenAI as context for subsequent queries, enabling iterative code refinement and clarification.

Supports two distinct authentication modes: official OpenAI ChatGPT API (via API key with per-token billing) and unofficial ChatGPT proxy API (via web access token with free ChatGPT subscription). Users configure authentication in VS Code settings, and the extension automatically routes requests to the selected API endpoint. ChatGPTUnofficialProxyAPI mode requires periodic token refresh (every ~8 hours) via manual re-authentication or automated Python script.

Allows users to specify analysis context scope via sidebar options: no context (general queries), selected text only, current file, or all open files. The extension sends the selected context to OpenAI models along with the user query, enabling code analysis that accounts for file-level or workspace-level dependencies. Context selection is user-controlled per query, allowing flexible scope management without configuration.

Streams OpenAI API responses character-by-character into the VS Code sidebar chat panel, displaying results in real-time as they are generated. Users can toggle between markdown-rendered display (formatted text, code blocks, lists) and raw text display, allowing both readable presentation and copy-paste workflows. Streaming provides perceived responsiveness and allows users to start reading responses before generation completes.

Integrates six predefined code actions (explain, document, refactor, find bugs, complete, ask question) as right-click context menu items in the VS Code editor. When a user right-clicks on selected code, they can invoke any action directly without typing commands, with the selected text automatically passed as context to the OpenAI API. This pattern reduces friction for common code analysis workflows.