> [!NOTE]
> Temporarily disabled Google Drive connections with appropriate UI indicators and error messages.
### What changed?
- Added checks to prevent users from connecting to Google Drive in both the connections tab and integrations view
- Added error messages explaining that Google Drive connections are temporarily disabled
- Updated UI to visually indicate that Google Drive is disabled:
- Added "Temporarily disabled" status indicator in the integrations list
- Added explanatory text in multiple locations
- Disabled the connect button for Google Drive specifically
Improved browser extension memory saving with better content handling and added markdown conversion.
### What changed?
- Enhanced memory content handling in the background script to prioritize different content types (explicit content, highlighted text, markdown, HTML, or URL)
- Added HTML to markdown conversion using TurndownService when saving entire pages
- Improved HTML handling by removing script tags before processing
- Updated the web app to display the saved URL from metadata when available
- Added turndown library and its type definitions as dependencies
This PR updates the README with several improvements:
- Added a light/dark mode compatible logo using the `<picture>` element
- Added a tagline: "Your AI second brain for saving and organizing everything that matters"
- Added badges for Web App, Chrome Extension, and Raycast Extension
- Added a developer resources section with links to the Developer Console and Documentation
- Added detailed sections for the Browser Extension and Raycast Extension features
- Fixed minor typos and grammar issues
- Updated all screenshots with newer versions
- Added a new logo-light-fullmark.svg file for light mode display
- Removed the "Quick Start for Contributors" section as it's covered in the [CONTRIBUTING.md](http://CONTRIBUTING.md)
### Relocated logo file and removed unnecessary configuration files.
### What changed?
- Moved `logo.svg` to `apps/web/public/logo-fullmark.svg`
- Updated the logo path in `README.md` to reflect the new location
- Removed empty `.npmrc` file
- Removed `apps/web/public/_headers` file that contained Next.js static caching configuration
### Improved mobile responsiveness across chat interface and memory list with better loading states.
### What changed?
- Added responsive padding in chat page for mobile devices
- Enhanced header layout for chat titles with proper truncation and responsive text sizes
- Replaced the simple loading spinner in memory list with skeleton loading cards
- Improved message container width constraints on mobile devices
### Added streaming support to the Supermemory middleware and improved memory handling in the AI SDK integration.
### What changed?
- Refactored the middleware architecture to support both streaming and non-streaming responses
- Extracted memory prompt functionality into a separate module (`memory-prompt.ts`)
- Added memory saving capability for streaming responses
- Improved the formatting of memory content with a "User Supermemories:" prefix
- Added utility function to filter out supermemories from content
- Created a new streaming example in the test app with a dedicated route and page
- Updated version from 1.3.0 to 1.3.1 in package.json
- Simplified installation instructions in [README.m](http://README.md)d
### TL;DR
Added OpenAI SDK middleware support for SuperMemory integration, allowing direct memory injection without AI SDK dependency.
### What changed?
- Added `withSupermemory` middleware for OpenAI SDK that automatically injects relevant memories into chat completions
- Implemented memory search and injection functionality for OpenAI clients
- Restructured the OpenAI module to separate tools and middleware functionality
- Updated README with comprehensive documentation and examples for the new OpenAI middleware
- Added test implementation with a Next.js API route example
- Reorganized package exports to support the new structure
- Changed the logo image source in App.tsx to use a file based svg rather than url one.
- Enhanced the loading indicator with an animated SVG.
- Adjusted styles for better alignment and spacing in the loading section.
- Added the dark-transparent.svg file to the public directory.
### TL;DR
Added support for conversation grouping in Supermemory middleware through a new `conversationId` parameter.
### What changed?
- Added a new `conversationId` option to the `withSupermemory` function to group messages into a single document for contextual memory generation
- Updated the middleware to use this conversation ID when adding memories, using a `customId` format of `conversation:{conversationId}`
- Created a new `getConversationContent` function that extracts the full conversation content from the prompt parameters
- Enhanced memory storage to save entire conversations rather than just the last user message
- Updated documentation and examples to demonstrate the new parameter usage
### How to test?
1. Import the `withSupermemory` function from the package
2. Create a model with memory using the new `conversationId` parameter:
```typescript
const modelWithMemory = withSupermemory(openai("gpt-4"), "user-123", {
conversationId: "conversation-456",
mode: "full",
addMemory: "always"
})
```
3. Use the model in a conversation and verify that messages are grouped by the conversation ID
4. Check that memories are being stored with the custom ID format `conversation:{conversationId}`
### Why make this change?
This enhancement improves the contextual understanding of the AI by allowing related messages to be grouped together as a single conversation document. By using a conversation ID, the system can maintain coherent memory across multiple interactions within the same conversation thread, providing better context retrieval and more relevant responses.
