Context Compaction

Automatic context window management

The compaction command manages context window compaction settings.

Invocations of praisonai compaction … shown here reach their handler as of PraisonAI PR #4329 (release ≥ the merge date, 2026-08-24). Older releases silently billed this exact command to an LLM at ~2.5k tokens with exit 0 — see issue #4327. Upgrade with pip install -U praisonai.

Quick Start

# Show compaction status
praisonai compaction status

Usage

Show Status

praisonai compaction status

Expected Output:

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

Set Strategy

praisonai compaction set sliding

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

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

• Context Compaction Feature