mirror of
https://github.com/cline/cline.git
synced 2026-09-19 02:05:44 +08:00
76 lines
3.6 KiB
Plaintext
76 lines
3.6 KiB
Plaintext
---
|
|
title: "Automatic Context Summarization"
|
|
sidebarTitle: "Auto Compact"
|
|
---
|
|
|
|
When your conversation approaches the model's context window limit, Cline automatically summarizes it to free up space and keep working.
|
|
|
|
<Frame>
|
|
<img
|
|
src="https://storage.googleapis.com/cline_public_images/docs/assets/condensing.png"
|
|
alt="Auto-compact feature condensing conversation context"
|
|
/>
|
|
</Frame>
|
|
|
|
## How It Works
|
|
|
|
Cline monitors token usage during your conversation. When you're getting close to the limit, he:
|
|
|
|
1. Creates a comprehensive summary of everything that's happened
|
|
2. Preserves all the technical details, code changes, and decisions
|
|
3. Replaces the conversation history with the summary
|
|
4. Continues exactly where he left off
|
|
|
|
You'll see a summarization tool call when this happens, showing the total cost like any other api call in the chat view.
|
|
|
|
## Why This Matters
|
|
|
|
Previously, Cline would truncate older messages when hitting context limits. This meant losing important context from earlier in the conversation.
|
|
|
|
Now with summarization:
|
|
- All technical decisions and code patterns are preserved
|
|
- File changes and project context remain intact
|
|
- Cline remembers everything he's done
|
|
- You can work on much larger projects without interruption
|
|
|
|
<Tip>
|
|
Context Summarization synergizes beautifully with [Focus Chain](/features/focus-chain). When Focus Chain is enabled, todo lists persist across summarizations. This means Cline can work on long-horizon tasks that span multiple context windows while staying on track with the todo list guiding him through each reset.
|
|
</Tip>
|
|
|
|
## Technical Details
|
|
|
|
The summarization happens through your configured API provider using the same model you're already using. It leverages prompt caching to minimize costs.
|
|
|
|
1. Cline uses a [summarization prompt](https://github.com/cline/cline/blob/main/src/core/prompts/contextManagement.ts) to request a summary of the conversation.
|
|
|
|
2. Once the summary is generated, Cline replaces the conversation history with a [continuation prompt](https://github.com/cline/cline/blob/main/src/core/prompts/contextManagement.ts#L69) that asks Cline to keep working and provides the summary as context.
|
|
|
|
Different models have different context window thresholds for when auto-summarization kicks in. You can see how thresholds are determined in [context-window-utils.ts](https://github.com/cline/cline/blob/main/src/core/context/context-management/context-window-utils.ts).
|
|
|
|
## Cost Considerations
|
|
|
|
Summarization leverages your existing prompt cache from the conversation, so it costs about the same as any other tool call.
|
|
|
|
Since most input tokens are already cached, you're primarily paying for the summary generation (output tokens), making it very cost-effective.
|
|
|
|
## Restoring Context with Checkpoints
|
|
|
|
You can use [checkpoints](/features/checkpoints) to restore your task state from before a summarization occurred. This means you never truly lose context - you can always roll back to previous versions of your conversation.
|
|
|
|
<Note>
|
|
Editing a message before a summarization tool call will work similarly to a checkpoint, allowing you to restore the conversation to that point.
|
|
</Note>
|
|
|
|
## Next Generation Model Support
|
|
|
|
Auto Compact uses advanced LLM-based summarization which we've found works significantly better for next-generation models. We currently support this feature for the following models:
|
|
|
|
- **Claude 4 series**
|
|
- **Gemini 2.5 series**
|
|
- **GPT-5**
|
|
- **Grok 4**
|
|
|
|
<Note>
|
|
When using other models, Cline automatically falls back to the standard rule-based context truncation method, even if Auto Compact is enabled in settings.
|
|
</Note>
|