Upcoming Platform Improvements
We're working on several improvements to make your experience with ISMS Copilot faster, more cost-effective, and easier to use—especially in long conversations.
Update: Message compaction is now live for Think mode! Automatic conversation compaction enables indefinite Think mode conversations without hitting token limits. When approaching the ~150,000 token threshold, the system automatically summarizes earlier messages in the background, allowing you to continue seamlessly. See the Product Changelog for details.
Message Compaction - Now Live for Think Mode ✓
Automatic conversation compaction is now available for Think mode (Claude Opus 4.6). When your Think mode conversation approaches the context limit, the backend automatically summarizes older messages while preserving key context, enabling you to continue indefinitely.
What's Working Now:
Infinite Think Mode Conversations: No more "conversation too long" errors in Think mode
Automatic Summarization: Backend compacts older messages when approaching ~150,000 tokens
Visual Feedback: Brief "Compacting our conversation..." indicator appears during the process
Seamless Experience: Conversations resume normally after a few seconds with full context preserved
Still In Progress:
Fast Mode Support: Compaction for Fast mode and other AI models coming soon
Usage Optimization: Further reductions in token consumption for long conversations
Additional Long Conversation Improvements
Along with compaction, we're working on:
In-chat warnings when a conversation is using significant credits, with smart suggestions on when compaction will help vs. when to start fresh
Clearer token usage information so you can see exactly how much each message costs and why
Visual indicators showing conversation health and compaction status
Smarter document detection
Every message currently triggers a separate check to see if you're requesting document analysis. We're optimizing this process to skip unnecessary checks and reduce background token usage you never see.
Fairer billing model
We're reviewing whether to charge only for new content (your latest message and the AI's response) rather than the full conversation history that gets resent with each message. This would make long conversations far more affordable.
These improvements are in development. We'll update this article and notify users as features roll out.
When will these ship?
Message compaction for Think mode is now live. Additional improvements including Fast mode support, document detection optimization, and billing model changes are actively in progress.
Have questions or suggestions? Contact our support team—we're listening.