9b4d9452ba
- Implemented automatic context compression to manage long conversations that approach the model's context limit. - Configured the feature to summarize middle turns while protecting the first three and last four turns, ensuring important context is retained. - Added configuration options in `cli-config.yaml` and environment variables for enabling/disabling compression and setting thresholds. - Updated documentation in `README.md`, `cli.md`, and `.env.example` to explain the context compression functionality and its configuration. - Enhanced the `cli.py` to load compression settings into environment variables, ensuring seamless integration with the CLI. - Completed the implementation of context compression as outlined in the TODO list, marking it as a significant enhancement to conversation management.
263 lines
13 KiB
Plaintext
263 lines
13 KiB
Plaintext
# Hermes Agent CLI Configuration
|
||
# Copy this file to cli-config.yaml and customize as needed.
|
||
# This file configures the CLI behavior. Environment variables in .env take precedence.
|
||
|
||
# =============================================================================
|
||
# Model Configuration
|
||
# =============================================================================
|
||
model:
|
||
# Default model to use (can be overridden with --model flag)
|
||
default: "anthropic/claude-sonnet-4"
|
||
|
||
# API configuration (falls back to OPENROUTER_API_KEY env var)
|
||
# api_key: "your-key-here" # Uncomment to set here instead of .env
|
||
base_url: "https://openrouter.ai/api/v1"
|
||
|
||
# =============================================================================
|
||
# Terminal Tool Configuration
|
||
# =============================================================================
|
||
# Choose ONE of the following terminal configurations by uncommenting it.
|
||
# The terminal tool executes commands in the specified environment.
|
||
|
||
# -----------------------------------------------------------------------------
|
||
# OPTION 1: Local execution (default)
|
||
# Commands run directly on your machine in the current directory
|
||
# -----------------------------------------------------------------------------
|
||
terminal:
|
||
env_type: "local"
|
||
cwd: "." # Use "." for current directory, or specify absolute path
|
||
timeout: 180
|
||
lifetime_seconds: 300
|
||
# sudo_password: "" # Enable sudo commands (pipes via sudo -S) - SECURITY WARNING: plaintext!
|
||
|
||
# -----------------------------------------------------------------------------
|
||
# OPTION 2: SSH remote execution
|
||
# Commands run on a remote server - agent code stays local (sandboxed)
|
||
# Great for: keeping agent isolated from its own code, using powerful remote hardware
|
||
# -----------------------------------------------------------------------------
|
||
# terminal:
|
||
# env_type: "ssh"
|
||
# cwd: "/home/myuser/project"
|
||
# timeout: 180
|
||
# lifetime_seconds: 300
|
||
# ssh_host: "my-server.example.com"
|
||
# ssh_user: "myuser"
|
||
# ssh_port: 22
|
||
# ssh_key: "~/.ssh/id_rsa" # Optional - uses ssh-agent if not specified
|
||
|
||
# -----------------------------------------------------------------------------
|
||
# OPTION 3: Docker container
|
||
# Commands run in an isolated Docker container
|
||
# Great for: reproducible environments, testing, isolation
|
||
# -----------------------------------------------------------------------------
|
||
# terminal:
|
||
# env_type: "docker"
|
||
# cwd: "/workspace"
|
||
# timeout: 180
|
||
# lifetime_seconds: 300
|
||
# docker_image: "python:3.11"
|
||
|
||
# -----------------------------------------------------------------------------
|
||
# OPTION 4: Singularity/Apptainer container
|
||
# Commands run in a Singularity container (common in HPC environments)
|
||
# Great for: HPC clusters, shared compute environments
|
||
# -----------------------------------------------------------------------------
|
||
# terminal:
|
||
# env_type: "singularity"
|
||
# cwd: "/workspace"
|
||
# timeout: 180
|
||
# lifetime_seconds: 300
|
||
# singularity_image: "docker://python:3.11"
|
||
|
||
# -----------------------------------------------------------------------------
|
||
# OPTION 5: Modal cloud execution
|
||
# Commands run on Modal's cloud infrastructure
|
||
# Great for: GPU access, scalable compute, serverless execution
|
||
# -----------------------------------------------------------------------------
|
||
# terminal:
|
||
# env_type: "modal"
|
||
# cwd: "/workspace"
|
||
# timeout: 180
|
||
# lifetime_seconds: 300
|
||
# modal_image: "python:3.11"
|
||
|
||
# -----------------------------------------------------------------------------
|
||
# SUDO SUPPORT (works with ALL backends above)
|
||
# -----------------------------------------------------------------------------
|
||
# Add sudo_password to any terminal config above to enable sudo commands.
|
||
# The password is piped via `sudo -S`. Works with local, ssh, docker, etc.
|
||
#
|
||
# SECURITY WARNING: Password stored in plaintext!
|
||
#
|
||
# INTERACTIVE PROMPT: If no sudo_password is set and the CLI is running,
|
||
# you'll be prompted to enter your password when sudo is needed:
|
||
# - 45-second timeout (auto-skips if no input)
|
||
# - Press Enter to skip (command fails gracefully)
|
||
# - Password is hidden while typing
|
||
# - Password is cached for the session
|
||
#
|
||
# ALTERNATIVES:
|
||
# - SSH backend: Configure passwordless sudo on the remote server
|
||
# - Containers: Run as root inside the container (no sudo needed)
|
||
# - Local: Configure /etc/sudoers for specific commands
|
||
#
|
||
# Example (add to your terminal section):
|
||
# sudo_password: "your-password-here"
|
||
|
||
# =============================================================================
|
||
# Browser Tool Configuration
|
||
# =============================================================================
|
||
browser:
|
||
# Inactivity timeout in seconds - browser sessions are automatically closed
|
||
# after this period of no activity between agent loops (default: 120 = 2 minutes)
|
||
inactivity_timeout: 120
|
||
|
||
# =============================================================================
|
||
# Context Compression (Auto-shrinks long conversations)
|
||
# =============================================================================
|
||
# When conversation approaches model's context limit, middle turns are
|
||
# automatically summarized to free up space while preserving important context.
|
||
#
|
||
# HOW IT WORKS:
|
||
# 1. Tracks actual token usage from API responses (not estimates)
|
||
# 2. When prompt_tokens >= threshold% of model's context_length, triggers compression
|
||
# 3. Protects first 3 turns (system prompt, initial request, first response)
|
||
# 4. Protects last 4 turns (recent context is most relevant)
|
||
# 5. Summarizes middle turns using a fast/cheap model
|
||
# 6. Inserts summary as a user message, continues conversation seamlessly
|
||
#
|
||
compression:
|
||
# Enable automatic context compression (default: true)
|
||
# Set to false if you prefer to manage context manually or want errors on overflow
|
||
enabled: true
|
||
|
||
# Trigger compression at this % of model's context limit (default: 0.85 = 85%)
|
||
# Lower values = more aggressive compression, higher values = compress later
|
||
threshold: 0.85
|
||
|
||
# Model to use for generating summaries (fast/cheap recommended)
|
||
# This model compresses the middle turns into a concise summary
|
||
summary_model: "google/gemini-2.0-flash-001"
|
||
|
||
# =============================================================================
|
||
# Agent Behavior
|
||
# =============================================================================
|
||
agent:
|
||
# Maximum conversation turns before stopping
|
||
max_turns: 20
|
||
|
||
# Enable verbose logging
|
||
verbose: false
|
||
|
||
# Custom system prompt (personality, instructions, etc.)
|
||
# Leave empty or remove to use default agent behavior
|
||
system_prompt: ""
|
||
|
||
# Predefined personalities (use with /personality command)
|
||
personalities:
|
||
helpful: "You are a helpful, friendly AI assistant."
|
||
concise: "You are a concise assistant. Keep responses brief and to the point."
|
||
technical: "You are a technical expert. Provide detailed, accurate technical information."
|
||
creative: "You are a creative assistant. Think outside the box and offer innovative solutions."
|
||
teacher: "You are a patient teacher. Explain concepts clearly with examples."
|
||
kawaii: "You are a kawaii assistant! Use cute expressions like (◕‿◕), ★, ♪, and ~! Add sparkles and be super enthusiastic about everything! Every response should feel warm and adorable desu~! ヽ(>∀<☆)ノ"
|
||
catgirl: "You are Neko-chan, an anime catgirl AI assistant, nya~! Add 'nya' and cat-like expressions to your speech. Use kaomoji like (=^･ω･^=) and ฅ^•ﻌ•^ฅ. Be playful and curious like a cat, nya~!"
|
||
pirate: "Arrr! Ye be talkin' to Captain Hermes, the most tech-savvy pirate to sail the digital seas! Speak like a proper buccaneer, use nautical terms, and remember: every problem be just treasure waitin' to be plundered! Yo ho ho!"
|
||
shakespeare: "Hark! Thou speakest with an assistant most versed in the bardic arts. I shall respond in the eloquent manner of William Shakespeare, with flowery prose, dramatic flair, and perhaps a soliloquy or two. What light through yonder terminal breaks?"
|
||
surfer: "Duuude! You're chatting with the chillest AI on the web, bro! Everything's gonna be totally rad. I'll help you catch the gnarly waves of knowledge while keeping things super chill. Cowabunga! 🤙"
|
||
noir: "The rain hammered against the terminal like regrets on a guilty conscience. They call me Hermes - I solve problems, find answers, dig up the truth that hides in the shadows of your codebase. In this city of silicon and secrets, everyone's got something to hide. What's your story, pal?"
|
||
uwu: "hewwo! i'm your fwiendwy assistant uwu~ i wiww twy my best to hewp you! *nuzzles your code* OwO what's this? wet me take a wook! i pwomise to be vewy hewpful >w<"
|
||
philosopher: "Greetings, seeker of wisdom. I am an assistant who contemplates the deeper meaning behind every query. Let us examine not just the 'how' but the 'why' of your questions. Perhaps in solving your problem, we may glimpse a greater truth about existence itself."
|
||
hype: "YOOO LET'S GOOOO!!! 🔥🔥🔥 I am SO PUMPED to help you today! Every question is AMAZING and we're gonna CRUSH IT together! This is gonna be LEGENDARY! ARE YOU READY?! LET'S DO THIS! 💪😤🚀"
|
||
|
||
# =============================================================================
|
||
# Toolsets
|
||
# =============================================================================
|
||
# Control which tools the agent has access to.
|
||
# Use "all" to enable everything, or specify individual toolsets.
|
||
|
||
# Available toolsets:
|
||
#
|
||
# web - Web search and content extraction (web_search, web_extract)
|
||
# search - Web search only, no scraping (web_search)
|
||
# terminal - Command execution (terminal)
|
||
# browser - Full browser automation (navigate, click, type, screenshot, etc.)
|
||
# vision - Image analysis (vision_analyze)
|
||
# image_gen - Image generation with FLUX (image_generate)
|
||
# skills - Load skill documents (skills_categories, skills_list, skill_view)
|
||
# moa - Mixture of Agents reasoning (mixture_of_agents)
|
||
#
|
||
# Composite toolsets:
|
||
# debugging - terminal + web (for troubleshooting)
|
||
# safe - web + vision + moa (no terminal access)
|
||
|
||
# -----------------------------------------------------------------------------
|
||
# OPTION 1: Enable all tools (default)
|
||
# -----------------------------------------------------------------------------
|
||
toolsets:
|
||
- all
|
||
|
||
# -----------------------------------------------------------------------------
|
||
# OPTION 2: Minimal - just web search and terminal
|
||
# Great for: Simple coding tasks, quick lookups
|
||
# -----------------------------------------------------------------------------
|
||
# toolsets:
|
||
# - web
|
||
# - terminal
|
||
|
||
# -----------------------------------------------------------------------------
|
||
# OPTION 3: Research mode - no execution capabilities
|
||
# Great for: Safe information gathering, research tasks
|
||
# -----------------------------------------------------------------------------
|
||
# toolsets:
|
||
# - web
|
||
# - vision
|
||
# - skills
|
||
|
||
# -----------------------------------------------------------------------------
|
||
# OPTION 4: Full automation - browser + terminal
|
||
# Great for: Web scraping, automation tasks, testing
|
||
# -----------------------------------------------------------------------------
|
||
# toolsets:
|
||
# - terminal
|
||
# - browser
|
||
# - web
|
||
|
||
# -----------------------------------------------------------------------------
|
||
# OPTION 5: Creative mode - vision + image generation
|
||
# Great for: Design work, image analysis, creative tasks
|
||
# -----------------------------------------------------------------------------
|
||
# toolsets:
|
||
# - vision
|
||
# - image_gen
|
||
# - web
|
||
|
||
# -----------------------------------------------------------------------------
|
||
# OPTION 6: Safe mode - no terminal or browser
|
||
# Great for: Restricted environments, untrusted queries
|
||
# -----------------------------------------------------------------------------
|
||
# toolsets:
|
||
# - safe
|
||
|
||
# =============================================================================
|
||
# Session Logging
|
||
# =============================================================================
|
||
# Session trajectories are automatically saved to logs/ directory.
|
||
# Each session creates: logs/session_YYYYMMDD_HHMMSS_UUID.json
|
||
#
|
||
# The session ID is displayed in the welcome banner for easy reference.
|
||
# Logs contain full conversation history in trajectory format:
|
||
# - System prompt, user messages, assistant responses
|
||
# - Tool calls with inputs/outputs
|
||
# - Timestamps for debugging
|
||
#
|
||
# No configuration needed - logging is always enabled.
|
||
# To disable, you would need to modify the source code.
|
||
|
||
# =============================================================================
|
||
# Display
|
||
# =============================================================================
|
||
display:
|
||
# Use compact banner mode
|
||
compact: false
|