Your Copilot

Enables connection to any self-hosted or third-party LLM server that implements the OpenAI API standard (e.g., LM Studio, Ollama, vLLM). The extension abstracts away server-specific implementation details by normalizing requests to the OpenAI API contract, allowing users to swap LLM backends without code changes. Configuration requires only a server URL (with http/https protocol) and optional API token, stored in VS Code settings.

Streams LLM responses token-by-token directly into the editor as they are generated, providing immediate visual feedback without waiting for full response completion. The streaming feature is configurable and can be disabled if the LLM server doesn't support streaming or if performance overhead is unacceptable. Streaming is implemented via HTTP chunked transfer encoding to the OpenAI-compatible endpoint.

Automatically includes the current active file's content and context in LLM requests without explicit user action. The extension infers which files are relevant to the current coding task and includes them in the prompt context sent to the LLM server. Implementation details of the 'smart' file selection algorithm are not documented, but the feature is described as enabling context-aware suggestions that reference the current file's code structure and semantics.

Accepts natural language descriptions or code comments and generates code suggestions by sending prompts to the configured LLM server. The extension acts as a thin client that marshals user intent into OpenAI API-compatible requests and renders the LLM's response back into the editor. Code quality and relevance are entirely dependent on the underlying LLM model's capabilities; the extension provides no post-processing, validation, or refinement of generated code.

Integrates with VS Code's extension system to provide activation, configuration, and command execution through the command palette and settings UI. The extension registers commands (exact command names not documented) that users can invoke via Ctrl+Shift+P or bind to custom keybindings. Configuration is managed through VS Code's settings.json or UI, storing LLM server URL, API token, and streaming preference.

Upcoming feature (not yet implemented) that will provide fast, language-specific code completion without network requests by running lightweight models locally or caching completions. This feature is planned to enable low-latency, context-aware suggestions for common completion patterns (variable names, method calls, imports) without the overhead of sending requests to the LLM server. Implementation approach is not documented.

Upcoming feature (not yet implemented) that will augment LLM prompts with relevant project documentation and codebase history to improve suggestion accuracy and relevance. This feature would enable the LLM to reference project-specific patterns, APIs, and conventions without manual context inclusion. Implementation approach (vector embeddings, semantic search, indexing strategy) is not documented.

Upcoming feature (not yet implemented) that will enable the LLM to autonomously perform multi-step tasks such as refactoring code, detecting bugs, and generating documentation without explicit user prompts for each step. This feature would implement agentic workflows where the LLM can plan, execute, and validate changes across multiple files. Implementation approach (planning algorithms, state management, validation logic) is not documented.

The extension explicitly does not store or transmit user code to cloud services. All code context is sent only to the user-configured LLM server (which may be local or on-premises), and no data is retained by the extension after the request completes. This is a privacy-first design that contrasts with cloud-dependent copilots that store code snippets for analytics or model improvement.

The extension is available for free on the VS Code Marketplace with no usage limits, paid tiers, or subscription requirements. Users only pay for the LLM server infrastructure they choose to run (e.g., cloud compute for Ollama, local hardware for LM Studio). This pricing model eliminates per-request costs or seat-based licensing, making the extension cost-effective for teams with existing LLM infrastructure.