ChatGPT Copilot

Routes chat requests to 15+ configurable AI providers (OpenAI, Anthropic, Google, Ollama, GitHub Copilot, DeepSeek, Azure, Groq, Perplexity, xAI, Mistral, Together, OpenRouter) through a single VS Code sidebar conversation window. Users configure API keys per provider and select which model/provider to use; the extension abstracts provider-specific API differences and handles streaming response aggregation back into the chat UI. Supports both cloud-hosted and local models (Ollama) without code changes.

Generates new code or entire files by accepting multiple files and images as context via @mention syntax, then streaming AI-generated code directly into the editor or creating new files. The extension parses @-prefixed references, loads file contents into the chat context, and passes them to the selected LLM. Generated code can be inserted inline with one-click application or created as new files. Supports multimodal input (images + code) for visual-to-code generation workflows.

Integrates GitHub Copilot as a provider option, allowing users with existing GitHub Copilot subscriptions to use their Copilot models (GPT-4o, Claude Sonnet 4, o3-mini, Gemini 2.5 Pro) through the ChatGPT Copilot extension. Uses VS Code's native GitHub authentication (no separate API key required), automatically detecting GitHub Copilot subscription status. Routes requests to GitHub's Copilot API endpoints.

Supports any OpenAI-compatible API endpoint (self-hosted models, private deployments, alternative providers) by accepting a custom base URL and API key. The extension treats OpenAI-compatible endpoints as a provider option, allowing users to point to their own model servers or private cloud deployments. Useful for organizations running self-hosted LLMs or using alternative providers with OpenAI-compatible APIs.

Allows users to reference multiple files in a single chat prompt using @filename syntax, automatically loading file contents into the chat context. The extension parses @-prefixed references, resolves them to workspace files, and includes their full contents in the prompt sent to the LLM. Supports both relative and absolute file paths, and allows mixing multiple files with text and images in a single message.

Operates without collecting usage telemetry, analytics, or user behavior data. The extension does not send information about prompts, code, files, or interactions to the publisher or third parties (beyond the configured LLM provider). Conversation history and custom prompts are retained locally (storage location unknown but assumed to be local VS Code storage). No tracking pixels, analytics SDKs, or telemetry libraries are included.

Provides a dedicated sidebar panel in VS Code for chat conversations, displaying messages in a threaded format with streaming responses. The sidebar UI includes conversation history, message editing (to resend modified prompts), and visual indicators for message status (sending, complete, error). Integrates with VS Code's sidebar layout, allowing users to resize, collapse, or move the chat panel alongside other sidebar panels (Explorer, Source Control, etc.).

Applies AI-suggested code changes directly to the editor with a single click, without requiring manual copy-paste. When the LLM suggests code modifications (refactoring, bug fixes, optimizations), the extension detects code blocks in the response and provides clickable 'apply' buttons that insert the suggestion at the cursor position or replace selected text. Supports both full-file replacements and partial edits.

Exports entire chat conversations to Markdown format for documentation, knowledge retention, or sharing. The extension maintains conversation history within the sidebar chat window, allowing users to edit and resend previous prompts, and provides batch export functionality to save conversations as .md files. Supports conversation editing (modify previous prompts and re-run) and selective export.

Stores and retrieves custom prompts via a prompt manager (v4.6+) accessible via #-symbol search within the chat. Users can create, edit, and organize reusable prompt templates that can be prefixed to any chat message. Supports custom prompt prefixes that are automatically prepended to user prompts before sending to the LLM, enabling consistent system instructions or role-playing without manual repetition.

Enables LLMs to call external tools and functions through two mechanisms: (1) native tool calling APIs for models that support them (OpenAI function calling, Anthropic tool_use), and (2) prompt-based tool calling (v4.9+) for models without native support, where the LLM outputs tool calls as structured text that the extension parses and executes. Integrates with Model Context Protocol (MCP, v4.7+) to allow users to 'bring your own tools' for custom integrations. Supports both built-in tools and user-defined tool schemas.

Streams AI responses in real-time to the VS Code sidebar chat window, displaying tokens as they arrive from the LLM provider without waiting for full response completion. The extension buffers streaming chunks from the provider API, aggregates them into the chat message, and updates the UI incrementally. Supports streaming for all configured providers (cloud and local Ollama). Provides visual feedback (e.g., loading indicators) while streaming is in progress.

Accepts images (screenshots, diagrams, wireframes) as input alongside text prompts and code files via @mention syntax. Passes images to multimodal LLM providers (Google Gemini, Claude, GPT-4 Vision) for visual understanding and code generation. Enables workflows like converting a UI screenshot to HTML/CSS, generating code from architecture diagrams, or creating tests from visual specifications. Image context is included in the same chat message as text prompts and code references.

Supports reasoning models (OpenAI o1, o3, DeepSeek R1) that perform extended chain-of-thought reasoning before generating responses. These models take longer to generate responses but produce higher-quality solutions for complex problems. The extension routes requests to reasoning models like any other provider, displays streaming reasoning steps (if available), and presents final responses. Reasoning models have different configuration requirements (e.g., no system prompts, no tool calling in some cases).

Executes open-source models (Llama, Qwen, CodeLlama, Mistral, etc.) locally via Ollama without sending code or prompts to cloud APIs. The extension connects to a local Ollama instance (running on localhost:11434 by default), routes requests to the local model, and streams responses back. Supports all Ollama-compatible models and enables fully offline code generation and analysis. No API keys required for local models.