Skip to main content

​
Overview

The CompressionManager automatically compresses verbose tool results when the context grows too large, keeping your agent within its context window limits while preserving key information.

​
Quick Start

import { Agent, CompressionManager, openai } from "@radaros/core";

const agent = new Agent({
  name: "research-agent",
  model: openai("gpt-4o"),
  compressToolResults: true, // enable with defaults
});

​
Custom Configuration

import { Agent, CompressionManager, openai } from "@radaros/core";

const compressionManager = new CompressionManager({
  compressAfter: 5,        // compress after 5 tool results
  tokenLimit: 50000,       // or when context exceeds 50K tokens
  model: openai("gpt-4o-mini"), // cheap model for compression
  instructions: "Summarize preserving all numbers and dates",
});

const agent = new Agent({
  name: "data-agent",
  model: openai("gpt-4o"),
  compressionManager,
});

​
Configuration Options

OptionTypeDefaultDescription
compressAfternumber3Compress after N uncompressed tool results
tokenLimitnumber—Compress when total context exceeds this token count
modelModelProviderAgent’s modelModel used for compression summaries
instructionsstringBuilt-in promptCustom compression prompt

​
How It Works

  1. Threshold Detection: After each tool result, the manager checks if compression is needed (count-based or token-based)
  2. Selective Compression: Only tool results over 200 characters are compressed — short results pass through unchanged
  3. Parallel Compression: Multiple tool results are compressed concurrently for speed
  4. Fact Preservation: The built-in prompt preserves numbers, dates, IDs, URLs, and proper nouns

​
Integration with Loop Hooks

CompressionManager integrates via the beforeLLMCall loop hook. It runs before the existing ContextCompactor, giving you layered context management:
  1. Compression (summarize individual tool results)
  2. Compaction (trim overall context if still too large)
  3. User hooks (custom transformations)