GitHub Copilot Chat

Enables developers to ask natural language questions about code directly within VS Code's sidebar chat interface, with automatic access to the current file, project structure, and custom instructions. The system maintains conversation history and can reference previously discussed code segments without requiring explicit re-pasting, using the editor's AST and symbol table for semantic understanding of code structure.

Triggered via Ctrl+I (Windows/Linux) or Cmd+I (macOS), this capability opens a focused chat prompt directly in the editor at the cursor position, allowing developers to request code generation, refactoring, or fixes that are applied directly to the file without context switching. The generated code is previewed inline before acceptance, with Tab key to accept or Escape to reject, maintaining the developer's workflow within the editor.

Analyzes code and generates natural language explanations of functionality, purpose, and behavior. Can create or improve code comments, generate docstrings, and produce high-level documentation of complex functions or modules. Explanations are tailored to the audience (junior developer, senior architect, etc.) based on custom instructions.

Analyzes code for missing error handling and generates appropriate exception handling patterns, try-catch blocks, and error recovery logic. Can suggest specific exception types based on the code context and add logging or error reporting based on project conventions.

Performs complex refactoring operations including method extraction, variable renaming across scopes, pattern replacement, and architectural restructuring. The agent understands code structure (via AST or symbol table) to ensure refactoring maintains correctness and can validate changes through tests.

Copilot Chat supports running multiple agent sessions in parallel, with a central session management UI that allows developers to track, switch between, and manage multiple concurrent tasks. Each session maintains its own conversation history and execution context, enabling developers to work on multiple features or refactoring tasks simultaneously without context loss. Sessions can be paused, resumed, or terminated independently.

Copilot CLI enables running agents in the background outside of VS Code, allowing long-running tasks (like multi-file refactoring or feature implementation) to execute without blocking the editor. Results can be reviewed and integrated back into the project, enabling developers to continue editing while agents work asynchronously. This decouples agent execution from the IDE, enabling more flexible workflows.

Analyzes failing tests or test-less code and generates comprehensive test cases (unit, integration, or end-to-end depending on context) with assertions, mocks, and edge case coverage. When tests fail, the agent can examine error messages, stack traces, and code logic to propose fixes that address root causes rather than symptoms, iterating until tests pass.

Enables developers to request end-to-end feature implementation or refactoring across multiple files, with the agent autonomously planning changes, executing edits, running tests, and self-correcting on failures. The agent maintains state across file edits, understands project structure via custom instructions, and can execute terminal commands to validate changes (e.g., running tests, linters, or build commands).

Provides non-intrusive inline code suggestions as developers type, rendered as faded ghost text that can be accepted with Tab or ignored by continuing to type. The system predicts not just the next line of code but the logical next edit in a sequence, learning from project patterns and custom instructions to suggest contextually appropriate completions that match the codebase's style and conventions.

Allows developers to define project-wide or task-specific context, coding guidelines, and conventions that persist across all Copilot Chat interactions. Custom instructions can specify architectural patterns, naming conventions, error handling standards, and domain-specific knowledge, which the AI uses to tailor all suggestions, explanations, and code generation to match the project's requirements.

Enables connection to external tools and services via the Model Context Protocol, allowing Copilot agents to access databases, APIs, documentation systems, and custom tools without hardcoded integrations. Developers can register MCP servers that expose capabilities (e.g., database queries, API calls, file system operations) which agents can invoke as part of their reasoning and execution flow.

Integrates with GitHub pull requests to provide inline code review suggestions, explain changes, identify potential issues, and help resolve merge conflicts. The agent can analyze diffs, suggest improvements, and in some cases (via cloud agents) create branches and open pull requests autonomously based on feature requests.

Allows developers to define custom agents with specialized personas, capabilities, and knowledge domains. Agents can be taught new skills through examples, documentation, or explicit instructions, enabling teams to create domain-specific assistants (e.g., security-focused agent, performance optimization agent) that apply specialized knowledge to code generation and analysis tasks.

Agents can execute terminal commands to validate changes, run tests, execute linters, and trigger builds. The agent analyzes command output (exit codes, stdout, stderr) to determine if changes are successful and can iterate on failures by proposing code fixes based on error messages.