See all the latest major updates on the What’s New page.
253.31033
- Bug fixes and improvements for Agents integration
253.30387.97
- Codex by OpenAI is now available as one of the coding agents in the AI Chat.
- You can now sign in with your existing ChatGPT account to access Codex.
252.26199.202
NEW: Introducing Claude Agent – now seamlessly integrated into JetBrains AI Assistant’s chat and included in the JetBrains AI subscription!
What’s new:
- Claude Agent, powered by Anthropic’s Agent SDK, is now available in the AI Chat.
- Track quota consumption and top up AI credits directly in the AI widget.
252.25557.171
- Fixed a case where the IDE might freeze when opening a project
252.23892.520
- Next Edit Suggestions is now in preview, offering real-time code modification recommendations as you type.
2025.2
- Project rules – Guide AI with coding standards and tech stack, shared across your team.
- Attach images in the chat (for Anthropic and OpenAI models).
- New file types supported for code completion – The list of supported file types now includes SQL, YAML, JSON, Markdown, and more.
- Local multiline completion is now available for Java and C++.
- Choose your preferred local models for code completion – Connect models like Qwen2.5, Codestral, or the open-source Mellum.
- Context improvements – Add folders, reference the project structure, and attach images in the chat (for Anthropic models).
- Updated model selector – Auto model selection in chat based on performance and cost. Visual cues indicating models' cost, reasoning strength, and experimental status.
- Auto-imports in Edit mode – missing imports are added automatically after code changes are applied.
- Card verification for the Free tier – This is required for some Free and Trial users to prevent abuse (no charges).
Learn more in the blog post!
251.23774.42.28.x
- New LLMs in chat: GPT-4.1, GPT-4.1 mini, GPT-4.1 nano
- Even more LLMs: o3 and o4-mini
- New LLM from Google: Google’s Gemini 2.5 Flash (Experimental)
- Removed from model selector in chat: Gemini 1.5 Flash, Gemini 1.5 Pro, OpenAI o1-mini
251.23774.42.x
- New subscription tiers (AI Free, AI Pro, AI Ultimate). Learn more
- Offline mode – Use local models for AI-powered help without an internet connection.
- Multi-file edits [Beta] – Apply changes across multiple files directly from the chat using advanced RAG.
- Web search from chat – Use /web to fetch documentation and answers directly from the internet.
- Apply snippets from chat – Instantly insert suggested code into the right spot in your project.
- MCP server integration [Beta] – Connect custom tools to AI Assistant via the Model Communication Protocol.
- Restrict AI usage with .aiignore – Control where AI Assistant can operate in your codebase.
- Expanded LLM support in chat: Gemini 2.5
251.23774.40
- MCP server integration for custom tools in AI Assistant
- Web search in chat
- Multi-file changes in Edit mode
- Restrict usage of AI Assistant in specific files or folders using .aiignore
243.23654.270
New models are available in chat:
- Claude 3.7 Sonnet
- OpenAI GPT-4.5
- Gemini 2.0 Flash
243.23654.270
New models and model providers are available in chat:
- Support for Claude 3.5 Sonnet and Claude 3.5 Haiku models by Anthropic
- OpenAI o1, o1-mini, o3-mini models
- Support for LM Studio
243.22562.251
- Improved navigation for symbol references in chat.
- Resolved issues with selection and scrolling in chat.
2024.3
- AI chat model selection: Choose from multiple AI models, including Google Gemini, OpenAI, Anthropic or your own local model via Ollama or LM Studio.
- Advanced code completion with broader language support: Cloud code completion now supports more languages, including JavaScript, TypeScript, HTML, C#, C++, Go, PHP, Ruby, and Scala.
- Inline AI prompts: Enter your prompts directly in the editor, and AI Assistant will recognize it and generate a suggestion.
- Context management in chat: View and manage every element included as context.
- Integrated IDE Documentation: Access your IDE's documentation directly within the AI chat.
- AI-powered quick fixes: Accelerate error resolution with intelligent, context-aware quick fixes.
- File-wide code generation: Streamline edits across an entire file for Java and Kotlin.
Learn more in the blog post!