> ## Documentation Index > Fetch the complete documentation index at: https://praison.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Context Optimizer CLI > CLI reference for context optimization strategies and configuration ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} from praisonaiagents import Agent agent = Agent(name="optimizer", instructions="Optimise agent prompts and configurations.") agent.start("Optimise this agent's system prompt for better accuracy.") ``` Configure context optimization behaviour via CLI flags and interactive commands. The user chats in the CLI; context flags compact history before the model hits token limits. ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} graph LR subgraph "Optimizer CLI" Chat[💬 praisonai chat] --> Flags[⚙️ Context flags] Flags --> Compact[🗜️ Auto-compact] Compact --> Session[✅ Session stays in budget] end classDef agent fill:#8B0000,stroke:#7C90A0,color:#fff classDef process fill:#189AB4,stroke:#7C90A0,color:#fff classDef output fill:#10B981,stroke:#7C90A0,color:#fff class Chat agent class Flags,Compact process class Session output ``` ## How It Works ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} sequenceDiagram participant User participant Agent participant Feature as Context Optimizer CLI User->>Agent: Request Agent->>Feature: Process request Feature-->>Agent: Result Agent-->>User: Response ``` ## Quick Start ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai chat --context-strategy smart --context-auto-compact ``` Inside the session, compact manually when needed: ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} > /context compact ``` ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai chat \ --context-strategy smart \ --context-threshold 0.7 \ --no-context-auto-compact ``` Or set defaults in `config.yaml`: ```yaml theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} context: auto_compact: true compact_threshold: 0.8 strategy: smart ``` ## CLI Flags ### Strategy ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} # Smart optimizer (default, recommended) praisonai chat --context-strategy smart # Simple truncation praisonai chat --context-strategy truncate # Sliding window praisonai chat --context-strategy sliding_window # Summarize old messages praisonai chat --context-strategy summarize # Prune old tool outputs praisonai chat --context-strategy prune_tools ``` | Strategy | Description | Best For | | ---------------- | ----------------------- | -------------------- | | `smart` | Intelligent combination | General use | | `truncate` | Remove oldest messages | Fast, simple | | `sliding_window` | Keep recent N messages | Conversation flow | | `summarize` | Compress old messages | Context preservation | | `prune_tools` | Truncate tool outputs | Tool-heavy workflows | ### Auto-Compaction ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} # Enable (default) praisonai chat --context-auto-compact # Disable praisonai chat --no-context-auto-compact ``` ### Threshold ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} # Trigger at 80% usage (default) praisonai chat --context-threshold 0.8 # More aggressive (70%) praisonai chat --context-threshold 0.7 # Less aggressive (90%) praisonai chat --context-threshold 0.9 ``` ## Interactive Commands ### Manual Compaction ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} > /context compact ``` **Output:** ``` Optimizing context... ✓ Optimized: 45,000 → 30,000 tokens Saved 15,000 tokens (33.3%) Strategy: smart ``` ### View Optimization History ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} > /context history ``` **Output:** ``` Optimization History Time Event Tokens Saved ---------------------------------------------------------------------- 2024-01-07T12:00:00 overflow_detected 45,000 - 2024-01-07T12:00:01 auto_compact 45,000 -15,000 ``` ### View Current Config ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} > /context config ``` Shows auto\_compact, threshold, and strategy settings. ## Environment Variables ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} export PRAISONAI_CONTEXT_AUTO_COMPACT=true export PRAISONAI_CONTEXT_THRESHOLD=0.8 export PRAISONAI_CONTEXT_STRATEGY=smart ``` ## config.yaml ```yaml theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} context: auto_compact: true compact_threshold: 0.8 strategy: smart compression_min_gain_pct: 5.0 compression_max_attempts: 3 ``` ## Strategy Details ### Smart (Recommended) Combines multiple strategies intelligently: 1. First tries non-destructive pruning 2. Falls back to sliding window 3. Uses truncation as last resort ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai chat --context-strategy smart ``` ### Truncate Simply removes oldest messages until under budget. ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai chat --context-strategy truncate ``` ### Sliding Window Keeps the most recent N messages that fit in budget. ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai chat --context-strategy sliding_window ``` ### Summarize Compresses old messages into a summary (requires LLM call). ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai chat --context-strategy summarize ``` ### Prune Tools Truncates old tool outputs while preserving recent ones. ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai chat --context-strategy prune_tools ``` ## Troubleshooting ### Context still overflowing ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} # Lower threshold praisonai chat --context-threshold 0.6 # Use more aggressive strategy praisonai chat --context-strategy truncate ``` ### Losing important context ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} # Use smart strategy praisonai chat --context-strategy smart # Or increase threshold praisonai chat --context-threshold 0.9 ``` ### Auto-compact not triggering ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} # Check if enabled > /context config # Verify threshold > /context stats ``` ## Best Practices `smart` combines pruning, sliding window, and summarisation — use it unless you have a specific reason not to. Trigger compaction at 0.7–0.8 so optimisation runs before the model hard-fails on context overflow. Check token usage before manually compacting — `/context history` shows what each compaction saved. ## Related Python API and strategy reference Watch optimisation in action Set token budgets per session Long-session compaction deep-dive