hermes-agent/configs/trajectory_compression.yaml

# Trajectory Compression Configuration
# 
# Post-processes completed agent trajectories to fit within a target token budget.
# Compression preserves head/tail turns and summarizes middle content only as needed.

# Tokenizer settings for accurate token counting
tokenizer:
  # HuggingFace tokenizer name
  name: "moonshotai/Kimi-K2-Thinking"
  
  # Trust remote code (required for some tokenizers)
  trust_remote_code: true

# Compression targets and behavior
compression:
  # Target maximum tokens for compressed trajectory
  target_max_tokens: 29000
  
  # Target size for summary (in tokens)
  # This is factored into calculations when determining what to compress
  summary_target_tokens: 750

# Protected turns that should NEVER be compressed
protected_turns:
  # Always protect the first system message (tool definitions)
  first_system: true
  
  # Always protect the first human message (original request)
  first_human: true
  
  # Always protect the first gpt message (initial response/tool_call)
  first_gpt: true
  
  # Always protect the first tool response (result of first action)
  first_tool: true
  
  # Always protect the last 2 complete turn pairs (gpt+tool or gpt only)
  # This ensures the model's final actions and conclusions are preserved
  last_n_turns: 4

# LLM settings for generating summaries (OpenRouter only)
summarization:
  # Model to use for summarization (should be fast and cheap)
  # Using OpenRouter model path format
  model: "google/gemini-3-flash-preview"
  
  # OpenRouter API settings
  base_url: "https://openrouter.ai/api/v1"
  
  # Environment variable containing OpenRouter API key
  api_key_env: "OPENROUTER_API_KEY"
  
  # Temperature for summarization (lower = more deterministic)
  temperature: 0.3
  
  # Max retries for API failures
  max_retries: 3
  
  # Delay between retries (seconds)
  retry_delay: 2

# Output settings
output:
  # Add notice to system message about potential summarization
  add_summary_notice: true
  
  # Text to append to system message
  summary_notice_text: "\n\nSome of the conversation may be summarized to preserve context."
  
  # Output directory suffix (appended to input directory name)
  output_suffix: "_compressed"

# Processing settings
processing:
  # Number of parallel workers for batch processing
  num_workers: 4
  
  # Maximum concurrent API calls for summarization (async parallelism)
  max_concurrent_requests: 50
  
  # Skip trajectories that are already under target length
  skip_under_target: true
  
  # If true, save trajectories even if compression can't get under target
  # (will compress as much as possible)
  save_over_limit: true
  
  # Timeout per trajectory in seconds (skip if takes longer)
  # Helps avoid hanging on problematic entries
  per_trajectory_timeout: 300  # 5 minutes

# Metrics to track
metrics:
  # Log detailed compression statistics
  enabled: true
  
  # Save per-trajectory metrics in output
  per_trajectory: false
  
  # Metrics file name (saved in output directory)
  output_file: "compression_metrics.json"