Skip to content

[Condense] Add docs for intelligent condense experimental feature #187

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mrubens merged 1 commit into from
May 14, 2025
Merged

[Condense] Add docs for intelligent condense experimental feature #187

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions docs/features/experimental/experimental-features.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,12 @@ To enable or disable experimental features:

The following experimental features are currently available:

### Intelligently condense the context window

If enabled, Roo uses an LLM to summarize the past conversation when the context window is almost full. This summary attempts to dramatically shrink the number of tokens in the context while preserving useful information. If disabled, Roo drops past messages using a sliding window when the context window is full.

**Disclaimer**: Currently the costs associated with summarizing the conversation are not included in the cost displayed in the UI.

### Power Steering

When enabled, Roo will remind the model about the details of its current mode definition more frequently. This will lead to stronger adherence to role definitions and custom instructions, but will use more tokens per message.
Expand Down