Documentation Index
Fetch the complete documentation index at: https://docs.praison.ai/llms.txt
Use this file to discover all available pages before exploring further.
The compaction command manages context window compaction settings.
Quick Start
# Show compaction status
praisonai compaction status
Usage
Show Status
praisonai compaction status
╭─ Context Compaction ─────────────────────────────────────────────────────────╮
│ Strategy: sliding │
│ Max Tokens: 8,000 │
│ Preserve Recent: 3 messages │
╰──────────────────────────────────────────────────────────────────────────────╯
Set Strategy
praisonai compaction set sliding
truncate, sliding, summarize, smart
Show Stats
praisonai compaction stats
Python API
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
