Files
hermes-agent/toolsets.py
teknium1 69aa35a51c Add messaging platform enhancements: STT, stickers, Discord UX, Slack, pairing, hooks
Major feature additions inspired by OpenClaw/ClawdBot integration analysis:

Voice Message Transcription (STT):
- Auto-transcribe voice/audio messages via OpenAI Whisper API
- Download voice to ~/.hermes/audio_cache/ on Telegram/Discord/WhatsApp
- Inject transcript as text so all models can understand voice input
- Configurable model (whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe)

Telegram Sticker Understanding:
- Describe static stickers via vision tool with JSON-backed cache
- Cache keyed by file_unique_id avoids redundant API calls
- Animated/video stickers get emoji-based fallback description

Discord Rich UX:
- Native slash commands (/ask, /reset, /status, /stop) via app_commands
- Button-based exec approvals (Allow Once / Always Allow / Deny)
- ExecApprovalView with user authorization and timeout handling

Slack Integration:
- Full SlackAdapter using slack-bolt with Socket Mode
- DMs, channel messages (mention-gated), /hermes slash command
- File attachment handling with bot-token-authenticated downloads

DM Pairing System:
- Code-based user authorization as alternative to static allowlists
- 8-char codes from unambiguous alphabet, 1-hour expiry
- Rate limiting, lockout after failed attempts, chmod 0600 on data
- CLI: hermes pairing list/approve/revoke/clear-pending

Event Hook System:
- File-based hook discovery from ~/.hermes/hooks/
- HOOK.yaml + handler.py per hook, sync/async handler support
- Events: gateway:startup, session:start/reset, agent:start/step/end
- Wildcard matching (command:* catches all command events)

Cross-Channel Messaging:
- send_message agent tool for delivering to any connected platform
- Enables cron job delivery and cross-platform notifications

Human-Like Response Pacing:
- Configurable delays between message chunks (off/natural/custom)
- HERMES_HUMAN_DELAY_MODE env var with min/max ms settings

Warm Injection Message Style:
- Retrofitted image vision messages with friendly kawaii-consistent tone
- All new injection messages (STT, stickers, errors) use warm style

Also: updated config migration to prompt for optional keys interactively,
bumped config version, updated README, AGENTS.md, .env.example,
cli-config.yaml.example, install scripts, pyproject.toml, and toolsets.
2026-02-15 21:38:59 -08:00

537 lines
17 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#!/usr/bin/env python3
"""
Toolsets Module
This module provides a flexible system for defining and managing tool aliases/toolsets.
Toolsets allow you to group tools together for specific scenarios and can be composed
from individual tools or other toolsets.
Features:
- Define custom toolsets with specific tools
- Compose toolsets from other toolsets
- Built-in common toolsets for typical use cases
- Easy extension for new toolsets
- Support for dynamic toolset resolution
Usage:
from toolsets import get_toolset, resolve_toolset, get_all_toolsets
# Get tools for a specific toolset
tools = get_toolset("research")
# Resolve a toolset to get all tool names (including from composed toolsets)
all_tools = resolve_toolset("full_stack")
"""
from typing import List, Dict, Any, Set, Optional
import json
# Core toolset definitions
# These can include individual tools or reference other toolsets
TOOLSETS = {
# Basic toolsets - individual tool categories
"web": {
"description": "Web research and content extraction tools",
"tools": ["web_search", "web_extract"],
"includes": [] # No other toolsets included
},
"search": {
"description": "Web search only (no content extraction/scraping)",
"tools": ["web_search"],
"includes": []
},
"vision": {
"description": "Image analysis and vision tools",
"tools": ["vision_analyze"],
"includes": []
},
"image_gen": {
"description": "Creative generation tools (images)",
"tools": ["image_generate"],
"includes": []
},
"terminal": {
"description": "Terminal/command execution tools",
"tools": ["terminal"],
"includes": []
},
"moa": {
"description": "Advanced reasoning and problem-solving tools",
"tools": ["mixture_of_agents"],
"includes": []
},
"skills": {
"description": "Access skill documents with specialized instructions and knowledge",
"tools": ["skills_list", "skill_view"],
"includes": []
},
"browser": {
"description": "Browser automation for web interaction (navigate, click, type, scroll, iframes, hold-click) with web search for finding URLs",
"tools": [
"browser_navigate", "browser_snapshot", "browser_click",
"browser_type", "browser_scroll", "browser_back",
"browser_press", "browser_close", "browser_get_images",
"browser_vision", "web_search"
],
"includes": []
},
"cronjob": {
"description": "Cronjob management tools - schedule, list, and remove automated tasks (CLI-only)",
"tools": ["schedule_cronjob", "list_cronjobs", "remove_cronjob"],
"includes": []
},
"rl": {
"description": "RL training tools for running reinforcement learning on Tinker-Atropos",
"tools": [
"rl_list_environments", "rl_select_environment",
"rl_get_current_config", "rl_edit_config",
"rl_start_training", "rl_check_status",
"rl_stop_training", "rl_get_results",
"rl_list_runs", "rl_test_inference"
],
"includes": []
},
"file": {
"description": "File manipulation tools: read, write, patch (with fuzzy matching), and search (content + files)",
"tools": ["read_file", "write_file", "patch", "search"],
"includes": []
},
"tts": {
"description": "Text-to-speech: convert text to audio with Edge TTS (free), ElevenLabs, or OpenAI",
"tools": ["text_to_speech"],
"includes": []
},
# Scenario-specific toolsets
"debugging": {
"description": "Debugging and troubleshooting toolkit",
"tools": ["terminal"],
"includes": ["web", "file"] # For searching error messages and solutions, and file operations
},
"safe": {
"description": "Safe toolkit without terminal access",
"tools": ["mixture_of_agents"],
"includes": ["web", "vision", "creative"]
},
# ==========================================================================
# CLI-specific toolsets (only available when running via cli.py)
# ==========================================================================
"hermes-cli": {
"description": "Full interactive CLI toolset - all default tools plus cronjob management",
"tools": [
# Web tools
"web_search", "web_extract",
# Terminal
"terminal",
# File manipulation
"read_file", "write_file", "patch", "search",
# Vision
"vision_analyze",
# Image generation
"image_generate",
# MoA
"mixture_of_agents",
# Skills
"skills_list", "skill_view",
# Browser
"browser_navigate", "browser_snapshot", "browser_click",
"browser_type", "browser_scroll", "browser_back",
"browser_press", "browser_close", "browser_get_images",
"browser_vision",
# Text-to-speech
"text_to_speech",
# Cronjob management (CLI-only)
"schedule_cronjob", "list_cronjobs", "remove_cronjob"
],
"includes": []
},
# ==========================================================================
# Messaging Platform-Specific Toolsets
# ==========================================================================
"hermes-telegram": {
"description": "Telegram bot toolset - full access for personal use (terminal has safety checks)",
"tools": [
# Terminal - enabled with dangerous command approval system
"terminal",
# File manipulation
"read_file", "write_file", "patch", "search",
# Web tools
"web_search", "web_extract",
# Vision - analyze images sent by users
"vision_analyze",
# Image generation
"image_generate",
# Text-to-speech
"text_to_speech",
# Skills - access knowledge base
"skills_list", "skill_view",
# Cronjob management - let users schedule tasks
"schedule_cronjob", "list_cronjobs", "remove_cronjob",
# Cross-channel messaging
"send_message"
],
"includes": []
},
"hermes-discord": {
"description": "Discord bot toolset - full access (terminal has safety checks via dangerous command approval)",
"tools": [
# Terminal - enabled with dangerous command approval system
"terminal",
# File manipulation
"read_file", "write_file", "patch", "search",
# Web tools
"web_search", "web_extract",
# Vision - analyze images sent by users
"vision_analyze",
# Image generation
"image_generate",
# Text-to-speech
"text_to_speech",
# Skills - access knowledge base
"skills_list", "skill_view",
# Cronjob management - let users schedule tasks
"schedule_cronjob", "list_cronjobs", "remove_cronjob",
# Cross-channel messaging
"send_message"
],
"includes": []
},
"hermes-whatsapp": {
"description": "WhatsApp bot toolset - similar to Telegram (personal messaging, more trusted)",
"tools": [
# Web tools
"web_search", "web_extract",
# Terminal - only for trusted personal accounts
"terminal",
# File manipulation
"read_file", "write_file", "patch", "search",
# Vision
"vision_analyze",
# Image generation
"image_generate",
# Text-to-speech
"text_to_speech",
# Skills
"skills_list", "skill_view",
# Cronjob management
"schedule_cronjob", "list_cronjobs", "remove_cronjob",
# Cross-channel messaging
"send_message"
],
"includes": []
},
"hermes-slack": {
"description": "Slack bot toolset - full access for workspace use (terminal has safety checks)",
"tools": [
# Terminal - enabled with dangerous command approval system
"terminal",
# File manipulation
"read_file", "write_file", "patch", "search",
# Web tools
"web_search", "web_extract",
# Vision - analyze images sent by users
"vision_analyze",
# Image generation
"image_generate",
# Text-to-speech
"text_to_speech",
# Skills - access knowledge base
"skills_list", "skill_view",
# Cronjob management - let users schedule tasks
"schedule_cronjob", "list_cronjobs", "remove_cronjob",
# Cross-channel messaging
"send_message"
],
"includes": []
},
"hermes-gateway": {
"description": "Gateway toolset - union of all messaging platform tools",
"tools": [],
"includes": ["hermes-telegram", "hermes-discord", "hermes-whatsapp", "hermes-slack"]
}
}
def get_toolset(name: str) -> Optional[Dict[str, Any]]:
"""
Get a toolset definition by name.
Args:
name (str): Name of the toolset
Returns:
Dict: Toolset definition with description, tools, and includes
None: If toolset not found
"""
# Return toolset definition
return TOOLSETS.get(name)
def resolve_toolset(name: str, visited: Set[str] = None) -> List[str]:
"""
Recursively resolve a toolset to get all tool names.
This function handles toolset composition by recursively resolving
included toolsets and combining all tools.
Args:
name (str): Name of the toolset to resolve
visited (Set[str]): Set of already visited toolsets (for cycle detection)
Returns:
List[str]: List of all tool names in the toolset
"""
if visited is None:
visited = set()
# Special aliases that represent all tools across every toolset
# This ensures future toolsets are automatically included without changes.
if name in {"all", "*"}:
all_tools: Set[str] = set()
for toolset_name in get_toolset_names():
# Use a fresh visited set per branch to avoid cross-branch contamination
resolved = resolve_toolset(toolset_name, visited.copy())
all_tools.update(resolved)
return list(all_tools)
# Check for cycles
if name in visited:
print(f"⚠️ Circular dependency detected in toolset '{name}'")
return []
visited.add(name)
# Get toolset definition
toolset = TOOLSETS.get(name)
if not toolset:
return []
# Collect direct tools
tools = set(toolset.get("tools", []))
# Recursively resolve included toolsets
for included_name in toolset.get("includes", []):
included_tools = resolve_toolset(included_name, visited.copy())
tools.update(included_tools)
return list(tools)
def resolve_multiple_toolsets(toolset_names: List[str]) -> List[str]:
"""
Resolve multiple toolsets and combine their tools.
Args:
toolset_names (List[str]): List of toolset names to resolve
Returns:
List[str]: Combined list of all tool names (deduplicated)
"""
all_tools = set()
for name in toolset_names:
tools = resolve_toolset(name)
all_tools.update(tools)
return list(all_tools)
def get_all_toolsets() -> Dict[str, Dict[str, Any]]:
"""
Get all available toolsets with their definitions.
Returns:
Dict: All toolset definitions
"""
return TOOLSETS.copy()
def get_toolset_names() -> List[str]:
"""
Get names of all available toolsets (excluding aliases).
Returns:
List[str]: List of toolset names
"""
return list(TOOLSETS.keys())
def validate_toolset(name: str) -> bool:
"""
Check if a toolset name is valid.
Args:
name (str): Toolset name to validate
Returns:
bool: True if valid, False otherwise
"""
# Accept special alias names for convenience
if name in {"all", "*"}:
return True
return name in TOOLSETS
def create_custom_toolset(
name: str,
description: str,
tools: List[str] = None,
includes: List[str] = None
) -> None:
"""
Create a custom toolset at runtime.
Args:
name (str): Name for the new toolset
description (str): Description of the toolset
tools (List[str]): Direct tools to include
includes (List[str]): Other toolsets to include
"""
TOOLSETS[name] = {
"description": description,
"tools": tools or [],
"includes": includes or []
}
def get_toolset_info(name: str) -> Dict[str, Any]:
"""
Get detailed information about a toolset including resolved tools.
Args:
name (str): Toolset name
Returns:
Dict: Detailed toolset information
"""
toolset = get_toolset(name)
if not toolset:
return None
resolved_tools = resolve_toolset(name)
return {
"name": name,
"description": toolset["description"],
"direct_tools": toolset["tools"],
"includes": toolset["includes"],
"resolved_tools": resolved_tools,
"tool_count": len(resolved_tools),
"is_composite": len(toolset["includes"]) > 0
}
def print_toolset_tree(name: str, indent: int = 0) -> None:
"""
Print a tree view of a toolset and its composition.
Args:
name (str): Toolset name
indent (int): Current indentation level
"""
prefix = " " * indent
toolset = get_toolset(name)
if not toolset:
print(f"{prefix}❌ Unknown toolset: {name}")
return
# Print toolset name and description
print(f"{prefix}📦 {name}: {toolset['description']}")
# Print direct tools
if toolset["tools"]:
print(f"{prefix} 🔧 Tools: {', '.join(toolset['tools'])}")
# Print included toolsets
if toolset["includes"]:
print(f"{prefix} 📂 Includes:")
for included in toolset["includes"]:
print_toolset_tree(included, indent + 2)
if __name__ == "__main__":
"""
Demo and testing of the toolsets system
"""
print("🎯 Toolsets System Demo")
print("=" * 60)
# Show all available toolsets
print("\n📦 Available Toolsets:")
print("-" * 40)
for name, toolset in get_all_toolsets().items():
info = get_toolset_info(name)
composite = "📂" if info["is_composite"] else "🔧"
print(f"{composite} {name:20} - {toolset['description']}")
print(f" Tools: {len(info['resolved_tools'])} total")
# Demo toolset resolution
print("\n🔍 Toolset Resolution Examples:")
print("-" * 40)
examples = ["research", "development", "full_stack", "minimal", "safe"]
for name in examples:
tools = resolve_toolset(name)
print(f"\n{name}:")
print(f" Resolved to {len(tools)} tools: {', '.join(sorted(tools))}")
# Show toolset composition tree
print("\n🌳 Toolset Composition Tree:")
print("-" * 40)
print("\nExample: 'content_creation' toolset:")
print_toolset_tree("content_creation")
print("\nExample: 'full_stack' toolset:")
print_toolset_tree("full_stack")
# Demo multiple toolset resolution
print("\n🔗 Multiple Toolset Resolution:")
print("-" * 40)
combined = resolve_multiple_toolsets(["minimal", "vision", "reasoning"])
print(f"Combining ['minimal', 'vision', 'reasoning']:")
print(f" Result: {', '.join(sorted(combined))}")
# Demo custom toolset creation
print("\n Custom Toolset Creation:")
print("-" * 40)
create_custom_toolset(
name="my_custom",
description="My custom toolset for specific tasks",
tools=["web_search"],
includes=["terminal", "vision"]
)
custom_info = get_toolset_info("my_custom")
print(f"Created 'my_custom' toolset:")
print(f" Description: {custom_info['description']}")
print(f" Resolved tools: {', '.join(custom_info['resolved_tools'])}")