Ollama Code Fixer - AI Coding Assistant

Analyzes selected code blocks using local Ollama models (default: CodeLlama 7B) to identify syntax errors, logic bugs, and runtime issues, then generates corrected code with explanations. The extension sends the selected code as context to the local Ollama API endpoint (default http://localhost:11434), receives the fixed version, and presents it in a preview before applying changes. This approach eliminates cloud dependency and API costs while maintaining full code privacy on the developer's machine.

Sends selected code to the local Ollama model with an optimization prompt, requesting improvements to algorithmic efficiency, memory usage, and code readability. The model analyzes the code structure and generates refactored versions with explanations of optimizations applied (e.g., reducing time complexity, removing redundant operations, improving variable naming). Results are previewed in the editor before application, with optional automatic backup of the original code.

Provides a dedicated chat panel in the VS Code sidebar for conversational interaction with the local Ollama model. Developers can ask questions about code, request explanations, discuss design decisions, or get coding advice in a multi-turn conversation. Chat context includes the current file and selected code, allowing the model to provide contextually relevant responses. All conversation stays local and private.

Optionally automates starting and stopping the local Ollama server based on extension usage. When enabled via configuration (`autoStartOllama`), the extension detects if Ollama is not running and automatically starts it before executing operations. This eliminates the need for developers to manually start Ollama in a separate terminal. Server lifecycle is managed transparently in the background.

Provides the extension interface in multiple languages (English, Russian, Ukrainian) through configuration. Developers can set the UI language via the `ollamaCodeFixer.language` setting, and all menus, buttons, and messages are displayed in the selected language. Localization is static (not dynamic language detection) and requires configuration change to switch languages.

Processes selected code through the local Ollama model to generate natural language explanations of what the code does, how it works, and why specific patterns are used. The extension sends code context to the model and receives human-readable explanations that help developers understand complex logic, unfamiliar patterns, or legacy code. A separate 'Add Comments' operation generates inline code comments at appropriate locations.

Analyzes selected code and generates unit tests using the local Ollama model, with documented support for edge case identification and coverage. The model receives the function/method as context and produces test cases covering normal inputs, boundary conditions, error states, and edge cases. Generated tests are formatted for the detected language (Jest for JavaScript, pytest for Python, etc.) and can be inserted above, below, or in a new file based on configuration.

Sends selected code to the Ollama model with a refactoring prompt requesting structural and architectural improvements. The model suggests changes to code organization, design patterns, separation of concerns, and maintainability without changing functionality. Refactoring suggestions are presented in preview mode before application, allowing developers to review and accept changes selectively.

Analyzes selected code using the local Ollama model to identify common security vulnerabilities (SQL injection, XSS, insecure cryptography, hardcoded secrets, etc.) and suggests fixes. The model receives code context and returns identified vulnerabilities with severity levels and corrected code examples. Results are presented in preview mode before application, allowing developers to understand and approve security fixes.

Accepts natural language descriptions or requirements from the developer (via command palette or prompt) and generates complete, functional code using the local Ollama model. The model receives the description as context and produces code in the language of the current editor file. Generated code is inserted at the cursor position or in a new file based on configuration, with optional preview before application.

Converts code from one programming language to another using the local Ollama model. The developer selects code and specifies a target language (via command or configuration), and the model generates semantically equivalent code in the target language. Translation preserves logic and functionality while adapting to language-specific idioms, libraries, and best practices. Results are previewed before application.

Provides a sidebar UI panel for selecting, installing, and switching between Ollama models without leaving VS Code. Developers can view available models, download new models via the Ollama CLI integration, and switch the active model for subsequent operations. The extension stores the selected model in configuration and applies it to all operations. Supports any model compatible with the Ollama API, not restricted to specific models.

Implements a flexible code insertion system with multiple modes (replace, above, below, new file) and optional preview-before-apply workflow. Before applying any generated or modified code, developers can review changes in a preview panel and choose to accept, reject, or edit them. Optional automatic backup of original code is created before modifications. Configuration options control whether preview is mandatory or changes are auto-applied.