Roo Code

Install Roo Code Extension

1. 1. Please open VS Code
2. 2. Go to the Extensions view (Or Click Ctrl + Shift + X)
3. 3. Search for "Roo Code"
4. 4. Click Install on the Roo Code extension

Open Roo Code Settings

1. 1. Click on the Roo Code icon in the VS Code sidebar
2. 2.When you first click Roo Code, you will be prompted to select an LLM provider. Please choose "Use another provider", or you can click the settings button in the upper-right corner to configure your provider.

Configure API Provider

1. 1. In the API Provider dropdown, select OpenAI Compatible
2. 2. Enter the following details:
• Base URL: https://inference.canopywave.io/v1
• API Key: Your CanopyWave API key
• Model ID: Choose a model (e.g. moonshotai/kimi-k2-thinking, deepseek/deepseek-chat-v3.2). You are free to choose the model.

Test the Integration

1. 1. Enter a message, for example “Please create a survey page for me about favorite animals.”
2. 2. Roo Code should respond and offer to create the file

Advanced AI Workflow

1. Plan & Act Dual Mode Switching: Supports first generating a structured technical proposal and execution plan (Plan Mode) for user review, then seamlessly transitioning into autonomous code modification and execution (Act Mode) after confirmation, ensuring safety and control over impactful changes.
2. Deep Codebase Understanding: Automatically scans the entire repository to build a holistic understanding of project structure, dependencies, and architectural patterns before implementing complex features or refactors.
3. Checkpoint-Based Iteration: Creates implicit checkpoints during key development stages, allowing the workflow to resume, adjust, or iterate efficiently without losing prior context.

Autonomous Development Capabilities

1. End-to-End Task Execution: Interprets natural language requirements to autonomously browse, edit, and refactor code, execute terminal commands, run tests, debug issues, and iteratively improve solutions until completion.
2. Tool-Driven Reasoning: Actively decides when to read files, search across the codebase, or execute commands, coordinating multiple tools to solve real-world engineering tasks.
3. Error Detection & Self-Correction: Continuously analyzes build outputs, test results, and runtime errors, automatically applying fixes and re-running validations.

Extensibility & Control

1. Configurable Project Rules: Respects project-level configuration and conventions, enabling consistent adherence to defined coding styles, frameworks, and architectural constraints.
2. Scalable Context Management: Maintains long-running task context across complex development sessions, intelligently prioritizing relevant information to stay focused and effective.