> ## Documentation Index
> Fetch the complete documentation index at: https://docs.51ultron.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Compression Engine

> Three-layer cascade compression that keeps Ultron sessions running indefinitely without losing context.

Long sessions accumulate tokens. Without compression, every conversation would hit context limits and require a restart. Ultron's compression engine prevents that — automatically, without losing the information that matters.

## Three-layer cascade

```text theme={null}
Context approaching token limit
    ↓
Layer 1: MicroCompact
    Scans all tool outputs in the conversation
    Removes outputs from old turns (Read, Bash, Grep, Glob, WebSearch, Scrape)
    Keeps recent outputs intact
    Replaces cleared content with: [tool output cleared — content was X chars]
    No API call required
    ↓ (if still over limit)
Layer 2: Session Memory Compact
    Uses stored memories as the compression baseline
    Preserves: minimum 10K tokens of context, minimum 5 text messages
    Targets: maximum 40K tokens in active window
    Prevents cutting tool_use / tool_result pairs (API invariant)
    No API call required
    ↓ (if still over limit)
Layer 3: API Digest
    Full LLM summary via fast model
    Strips all images (replaced with [image] placeholders)
    Re-injects 50K token budget of critical content:
        ├── Recent files (max 5 files, max 5K each)
        ├── Active skill instructions
        └── Project instructions
    One API call required
```

## CompactBoundary

After each compression, a boundary marker is inserted into the conversation:

```json theme={null}
{
  "type": "compact_boundary",
  "compactType": "auto",
  "preCompactTokenCount": 87420,
  "preservedSegment": {
    "summaryMessageUuid": "msg_abc123",
    "preservedMessageUuids": ["msg_xyz789", "msg_def456"]
  }
}
```

All subsequent operations only process messages after the last boundary. This prevents re-compressing content that was already compressed in a previous pass.

## What is never compressed away

* Active tool calls and their results (current turn)
* The last 5 messages with substantive text content
* Memories injected at session start
* The user's profile context
* Any content marked with a "must-retain" pre-compression hook

## When compression triggers

Compression is fully automatic. It triggers when the active context window approaches the model's limit. You don't need to manage it, restart sessions, or summarize manually.

<Info>
  Sessions can run for hours across dozens of tool calls without hitting limits. The compression engine handles it invisibly.
</Info>