ChatGPT [deprecated]

Provides a persistent sidebar panel within VS Code where users can compose arbitrary prompts and receive streaming responses from OpenAI's API. The extension maintains conversation history within the session, allows editing and resending previous prompts, and automatically handles response continuation when API responses are truncated, combining fragmented outputs into coherent answers without user intervention.

Enables users to generate new files or code blocks directly from AI suggestions via a single-click action in the sidebar. The extension parses AI-generated code responses and provides a clickable interface to create files in the project workspace or insert code into the current editor, bypassing manual copy-paste workflows.

Allows users to select code in the editor, send it to ChatGPT with a fix/modify request, and receive suggestions that can be applied back to the editor. The extension integrates with VS Code's selection API to capture highlighted code, passes it as context to the AI, and provides mechanisms to replace or insert the modified code directly into the file.

Allows users to select between multiple OpenAI models (GPT-4, GPT-3.5, GPT-3, Codex) via extension settings, with all requests routed directly to OpenAI's API using a user-provided API key. The extension abstracts model selection into a configuration option, enabling users to switch models without code changes and manage API costs by choosing appropriate model tiers.

Captures the entire conversation history from a session and exports it to a markdown file, preserving prompts, responses, and formatting. The export includes timestamps or conversation order, enabling users to archive discussions, share them with team members, or reference them later outside the IDE.

Enables users to define custom prompt prefixes that are automatically prepended to user queries before sending to the API. This allows users to establish consistent context, tone, or instructions (e.g., 'You are a TypeScript expert') without repeating them in every prompt, reducing prompt engineering overhead and improving response consistency.

Streams responses from OpenAI's API in real-time to the sidebar, displaying partial results as they arrive. Users can interrupt streaming at any time to stop token consumption, and the extension provides a 'stop response' action to halt further API calls and preserve remaining token quota.

Maintains a history of all prompts sent during a session and allows users to select, edit, and resend previous prompts without retyping them. This enables iterative refinement of queries, A/B testing different prompt variations, and quick re-execution of similar requests with minor modifications.