AI Assistant by JetBrains

Generates contextually appropriate code completions using JetBrains' proprietary Mellum LLM, which is optimized for developer workflows and syntax awareness across 10+ programming languages. The extension analyzes the current file context, detects the active programming language, and produces completions that respect language-specific syntax rules and project conventions. Completions are delivered inline within the editor with latency optimized for real-time developer interaction.

Provides a natural language chat interface that maintains awareness of the current file, project structure, and code context. The chat system allows developers to ask questions about code, request explanations, and iteratively refine prompts while the AI maintains conversation history and project context. The interface is built into VS Code's sidebar or panel UI and integrates with the Mellum LLM backend for language understanding and code-aware responses.

Automatically infers project context from the currently open file, active editor state, and workspace metadata without requiring developers to explicitly select files or directories for analysis. The system detects the programming language, identifies related files (imports, dependencies), and builds a mental model of the codebase scope. Context scope is limited to files accessible within VS Code; the extension does not directly access the file system outside the editor.

Collects telemetry data from the extension to improve product features and user experience. The system tracks usage patterns, feature adoption, and error conditions, transmitting this data to JetBrains servers for analysis. Telemetry collection is enabled by default, but an opt-out mechanism is not documented in the marketplace or extension documentation, requiring users to consult external privacy policies.

Enables the AI to propose and apply changes across multiple files in a single interaction through an 'Edit' or 'Agentic' mode. This mode orchestrates multiple AI models (specific models undocumented) to decompose complex refactoring or feature-addition tasks, generate code changes, and apply them directly to the codebase. The system operates with human-in-the-loop supervision, requiring developer approval before changes are committed, and integrates with VS Code's file system and editor APIs to apply diffs.

Analyzes staged or uncommitted code changes and generates contextually appropriate commit messages using the Mellum LLM. The system examines diffs, understands the semantic intent of changes, and produces commit messages that follow conventional commit formats or project-specific conventions. This capability integrates with VS Code's source control UI and can be triggered from the commit dialog or command palette.

Generates human-readable explanations of code functions, classes, or entire files, and can automatically produce documentation in language-appropriate formats (docstrings for Python, JSDoc for JavaScript, etc.). The system analyzes code structure, detects the programming language, and produces documentation that matches the language's standard conventions. Documentation can be inserted directly into the code or displayed in the chat interface.

Analyzes code to identify potential bugs, performance issues, and optimization opportunities, then presents findings and suggestions through the chat interface or inline comments. The system uses static analysis patterns combined with Mellum's code understanding to detect common pitfalls (null pointer dereferences, inefficient loops, etc.) and suggests improvements. Suggestions are presented as conversational recommendations rather than enforced linting rules.

Automatically detects the programming language of the current file and generates code completions, snippets, and full functions in the appropriate language syntax. The system maintains language-specific knowledge for Java, Kotlin, Python, JavaScript, TypeScript, C#, C++, PHP, Go, Rust, and others, ensuring that generated code respects language idioms, type systems, and standard libraries. Language detection is automatic based on file extension and editor state.

Manages authentication and licensing through JetBrains Account integration, automatically granting free AI EAP (Early Access Program) licenses on first login and supporting existing JetBrains AI subscriptions. The system handles token management, license validation, and subscription status checking through JetBrains' backend services. Users authenticate once and the extension maintains session state across VS Code restarts.

Executes all AI model inference on JetBrains-hosted cloud servers rather than locally, enabling access to powerful models (Mellum and multi-model orchestration) without requiring local GPU resources. The system transmits code context and requests to cloud endpoints, processes them server-side, and returns results to the IDE. Network latency and cloud service availability directly impact user experience, though specific SLAs and latency targets are undocumented.

Integrates the AI chat interface and controls into VS Code's native sidebar or panel UI, making the assistant accessible alongside other VS Code panels (Explorer, Source Control, etc.). The system also registers commands in the command palette, allowing keyboard-driven access to AI features without relying on mouse navigation. UI state is preserved across editor sessions.