continue capabilities
12 mapped capabilities, each graded and dated. This is the diagnosis — the migration guide is the cure.
Capabilities
Autonomous agent mode
provisionalverified 2 days agoAn autonomous coding assistant that reads files, makes multi-file changes, runs terminal commands, and handles complex multi-step tasks from a single natural-language instruction. Before each tool use the agent requests approval by default; users click Continue to approve or Cancel to reject.
CLI and headless/background agents (cn)
provisionalverified 2 days agoThe Continue CLI (cn) runs the AI agent from the terminal in interactive TUI mode or non-interactive headless mode, enabling scripted automation, CI/CD integration, and background coding tasks without an IDE.
Context providers (@-mentions for chat context)
provisionalverified 2 days agoIn chat and agent mode, users type @ to attach specific context sources — files, terminal output, git diffs, and more — so the model has precise, relevant information without pasting manually.
Continue Hub / Mission Control (shareable assistants and blocks)
provisionalverified 2 days agoMission Control is Continue's cloud dashboard for creating, sharing, and running AI agents and reusable configuration blocks (models, rules, prompts, MCP servers). Teams compose and publish assistants that any team member can install with a single click.
Full model choice and BYOK (bring your own key)
provisionalverified 2 days agoUsers supply their own API keys for any supported model provider, or run models locally. There is no locked-in model — every provider and model is user-configurable via config.yaml.
IDE extension surfaces (VS Code and JetBrains)
provisionalverified 2 days agoContinue ships as a native extension for Visual Studio Code and as a plugin for JetBrains IDEs. Both surfaces provide autocomplete, chat, inline edit, and agent mode within the editor.
In-editor AI chat
provisionalverified 2 days agoAn interactive AI assistant panel embedded in the IDE for asking questions, analyzing code, and getting guidance without leaving the editor. Supports three sub-modes: Chat (no tools), Plan Mode (read-only tools), and Agent Mode (full tool access).
Inline edit (targeted code modification)
provisionalverified 2 days agoSelect a code region, press Cmd/Ctrl+I, describe the change in natural language, and a diff is streamed inline. Designed for focused, single-function changes such as refactoring, adding comments, generating tests, or converting between languages.
Inline tab autocomplete
provisionalverified 2 days agoProvides AI-powered inline code suggestions as you type, which you accept with Tab. Supports single-line and multi-line completions triggered automatically or manually.
MCP (Model Context Protocol) tool extension
provisionalverified 2 days agoContinue supports the Model Context Protocol standard, allowing any MCP server to be added as a tool extension for the AI agent. This enables integration with external data sources, APIs, databases, and custom tooling.
Plan, pricing, and feature gating
provisionalverified 2 days agoContinue's core IDE extension and CLI are free and open-source (Apache 2.0). Cloud/team features in Mission Control are gated behind paid tiers. Model costs are paid directly to whichever provider the user configures (BYOK).
Rules and custom prompts (slash commands)
provisionalverified 2 days agoRules are persistent instructions injected into the system message for every Agent, Chat, and Edit request. Prompts are reusable slash-command templates invoked with a / prefix for specific tasks.