Compressor · DeepSeek Harness plugin

Key features

• A slim port of Headroom.
• A tool run leaves a long log / JSON / diff.
• Compresses tool output and cuts up to 20% of context, without affecting the model's context cache or agent performance.
• Only a small part of it is useful.
• This plugin shortens that output before the next turn, keeps the original on disk, leaves the already-sent prefix alone so the cache stays valid, and gives the agent a tool to pull the full context back.