Never lose context in long conversations. The Continuity Engine automatically extracts, summarizes, and preserves the most important information from your chats.
When conversations grow long, AI assistants typically forget earlier context due to token limits. The Continuity Engine solves this by intelligently extracting and preserving key information - goals, decisions, requirements, and important references - so the AI never loses track of what matters.
Think of it as giving the AI a "working memory" that persists across the entire conversation, no matter how long it gets.
Automatically extracts goals, decisions, and requirements from your conversation.
Pin important messages to ensure they're never forgotten or compressed.
Intelligently compresses older messages while preserving essential context.
Store persistent facts, preferences, and constraints across all conversations.
The Continuity Engine uses a three-tier architecture to manage context efficiently:
The most recent messages (typically last 20) are kept in full detail. These provide immediate context and are never compressed.
Older messages are distilled into a structured summary containing goals, decisions, requirements, open questions, and important references. This preserves meaning while dramatically reducing token count.
Critical information that you explicitly pin is preserved verbatim and never compressed. Perfect for key decisions, important code snippets, or crucial requirements.
The circular indicator in your chat header shows the current context preservation ratio - a measure of how much original context has been retained:
| Ratio | Color | Status |
|---|---|---|
| 70-100% | Green | Healthy - minimal compression |
| 40-69% | Amber | Moderate - some summarization applied |
| <40% | Red | Heavy compression - consider pinning key items |
Pro Tip
Click the context indicator to open the Summary Drawer, where you can view extracted context, manage pinned items, and manually trigger compaction.
Goals, decisions, requirements, and references are automatically identified and added to the rolling summary.
Pin any message to ensure its content is never compressed or forgotten. Perfect for critical decisions and important code.
Three levels of compaction (light, deep, aggressive) allow fine-tuned control over how much context is preserved vs. token savings.
Store persistent preferences, facts, constraints, and definitions that apply across all your conversations.
Mark specific messages to be excluded from the rolling summary, useful for off-topic discussions or sensitive content.