Praison AI

Context Compaction

Automatic context window management

The compaction command manages context window compaction settings.

Quick Start

bash
# Show compaction status
praisonai compaction status

Usage

Show Status

bash
praisonai compaction status

Expected Output:

╭─ Context Compaction ─────────────────────────────────────────────────────────╮
│  Strategy: sliding                                                           │
│  Max Tokens: 8,000                                                           │
│  Preserve Recent: 3 messages                                                 │
╰──────────────────────────────────────────────────────────────────────────────╯

Set Strategy

bash
praisonai compaction set sliding

Available strategies: truncate, sliding, summarize, smart, llm_summarize, prune

Show Stats

bash
praisonai compaction stats

Python API

python
from praisonaiagents.compaction import (
    ContextCompactor, CompactionStrategy
)

compactor = ContextCompactor(
    max_tokens=4000,
    strategy=CompactionStrategy.SLIDING,
    preserve_recent=3
)

messages = [...]  # Your conversation history
compacted, result = compactor.compact(messages)

print(f"Compression: {result.compression_ratio:.1%}")

See Also