How Chat Works

How Chat Core Functionality Works

When you start a chat conversation, Continue:

1. Gathers Context: Uses any selected code sections and @-mentioned context
2. Constructs Prompt: Combines your input with relevant context
3. Sends to Model: Prompts the configured AI model for a response
4. Streams Response: Returns the AI response in real-time to the sidebar

How Context Management Works

What Context Is Automatically Included

• Selected code in your editor
• Current file context when relevant
• Previous conversation history in the session

How to Add Manual Context

• @Files - Reference specific files

How Response Handling Works

Each code section in the AI response includes action buttons:

• Apply to current file - Replace selected code
• Insert at cursor - Add code at cursor position
• Copy - Copy code to clipboard

How Session Management Works

• Use Cmd/Ctrl + L (VS Code) or Cmd/Ctrl + J (JetBrains) to start a new session
• Clears all previous context for a fresh start
• Helpful for switching between different tasks

What Advanced Features Are Available

How to Use Prompt Inspection

View the exact prompt sent to the AI model in the prompt logs for debugging and optimization.

Context

Learn more about how you can bring in context:

• Codebase Context
• Documentation Context
• Built-in Context Providers

---

Chat is designed to feel like a natural conversation while maintaining full transparency about what context is being used.