twinny

Generates real-time code suggestions by analyzing both prefix (code before cursor) and suffix (code after cursor) context using model-specific FIM templates. The system formats prompts with proper stop tokens for different AI models (Ollama, OpenAI, Anthropic, CodeLlama) and streams completions as the developer types, enabling structurally-aware code generation that understands bidirectional context rather than just left-to-right prediction.

Abstracts multiple AI provider APIs (Ollama, OpenAI, Anthropic, LM Studio, Hugging Face) behind a BaseProvider interface, allowing developers to switch providers via VS Code settings without code changes. The Provider Manager handles authentication, endpoint configuration, model selection, and request/response translation, enabling a single extension to work with local inference servers, commercial APIs, and custom endpoints through a unified configuration UI.

Analyzes selected code (functions, classes, modules) and generates documentation strings (docstrings, JSDoc comments) using the AI model with a documentation template. The system extracts code structure and purpose, passes it to the AI with documentation format specifications, and returns formatted documentation that can be inserted above code definitions, enabling developers to quickly add comprehensive documentation without manual writing.

Streams code completion tokens in real-time as they are generated by the AI model, displaying suggestions to the user with minimal latency. The system manages streaming connections, buffers tokens for display, and handles connection interruptions gracefully, enabling responsive code completion that feels natural and doesn't block the editor while waiting for full responses.

Renders code snippets in chat messages with syntax highlighting appropriate to the detected programming language, and formats code blocks with proper indentation and line breaks. The system detects language from code context or explicit language tags, applies syntax highlighting rules, and preserves code structure for readability in the chat interface, enabling clear code discussion without formatting degradation.

Builds a vector database of workspace files using embeddings, enabling semantic search to retrieve relevant code context for completions. The system indexes workspace files on activation, stores embeddings locally, and retrieves the most similar code snippets based on semantic similarity rather than keyword matching, improving completion relevance by providing the model with contextually similar code examples from the codebase.

Provides a VS Code sidebar chat interface (SidebarProvider) that maintains multi-turn conversation history with the AI model while allowing users to reference selected code, ask questions about code, and execute AI-powered code transformations. The chat component manages conversation state, renders messages with syntax highlighting, and integrates with the completion provider to enable contextual discussions about code without leaving the editor.

Provides user-configurable prompt templates for common code generation tasks (refactoring, type addition, test generation, documentation, git commit messages) that can be customized via VS Code settings. The template system uses placeholder variables (e.g., {code}, {language}) that are substituted at runtime, enabling developers to define task-specific prompts without modifying extension code and ensuring consistent prompt formatting across different AI models.

Integrates with the Symmetry P2P network (SymmetryService) to enable developers to share AI inference resources across a distributed network of peers. The system allows users to contribute their local compute resources (GPU/CPU) to the network and access inference from other peers, creating a decentralized alternative to centralized cloud AI services while maintaining privacy through peer-to-peer communication.

Analyzes staged or selected code changes and generates contextually appropriate git commit messages using the AI model. The system extracts diff information, passes it to the AI with a commit message template, and returns a suggested message that summarizes the changes, enabling developers to quickly generate meaningful commit messages without manual composition.

Enables developers to select code and request AI-powered refactoring transformations (simplification, optimization, style changes) through the chat interface or command palette. The system passes selected code with a refactoring template to the AI model, receives the transformed code, and displays it for review before applying changes, enabling safe code transformations with human oversight.

Analyzes selected code (typically JavaScript/TypeScript or Python) and generates appropriate type annotations using the AI model. The system extracts code context, passes it to the AI with a type annotation template, and returns suggested type definitions that can be inserted into the code, enabling developers to add type safety to dynamically-typed code without manual annotation.

Analyzes selected code (functions, classes, modules) and generates unit test cases using the AI model with a test generation template. The system extracts code structure, passes it to the AI with testing framework specifications, and returns test code that can be inserted into test files, enabling developers to quickly generate comprehensive test coverage without manual test writing.