Files

teknium 7ea17bb957 Update environment configuration and enhance tool definitions

- Modified `.env.example` to set default terminal environment to 'local' and updated Docker, Singularity, and Modal image references to use 'python:3.11-slim'.
- Updated `package.json` to include Node.js engine requirements and modified post-install script for better user guidance.
- Enhanced `pyproject.toml` to reflect new dependencies and optional dependencies for modal and development environments.
- Improved `README.md` with additional setup instructions for Singularity and Node.js dependencies, along with clearer toolset documentation.
- Refactored `model_tools.py` to include new tool definitions and ensure consistency across toolsets.
- Updated architecture documentation to clarify tool structure and registration processes.

2026-01-29 22:36:07 +00:00

2.7 KiB

Raw Blame History

Tools

Tools are functions that extend the agent's capabilities. Each tool is defined with an OpenAI-compatible JSON schema and an async handler function.

Tool Structure

Each tool module in tools/ exports:

Schema definitions - OpenAI function-calling format
Handler functions - Async functions that execute the tool

# Example: tools/web_tools.py

# Schema definition
WEB_SEARCH_SCHEMA = {
    "type": "function",
    "function": {
        "name": "web_search",
        "description": "Search the web for information",
        "parameters": {
            "type": "object",
            "properties": {
                "query": {"type": "string", "description": "Search query"}
            },
            "required": ["query"]
        }
    }
}

# Handler function
async def web_search(query: str) -> dict:
    """Execute web search and return results."""
    # Implementation...
    return {"results": [...]}

Tool Categories

Category	Module	Tools
Web	`web_tools.py`	`web_search`, `web_extract`, `web_crawl`
Terminal	`terminal_tool.py`	`terminal` (local/docker/singularity/modal backends)
Browser	`browser_tool.py`	`browser_navigate`, `browser_click`, `browser_type`, etc.
Vision	`vision_tools.py`	`vision_analyze`
Image Gen	`image_generation_tool.py`	`image_generate`
Reasoning	`mixture_of_agents_tool.py`	`mixture_of_agents`

Tool Registration

Tools are registered in model_tools.py:

# model_tools.py
TOOL_SCHEMAS = [
    *WEB_TOOL_SCHEMAS,
    *TERMINAL_TOOL_SCHEMAS,
    *BROWSER_TOOL_SCHEMAS,
    # ...
]

TOOL_HANDLERS = {
    "web_search": web_search,
    "terminal": terminal_tool,
    "browser_navigate": browser_navigate,
    # ...
}

Toolsets

Tools are grouped into toolsets for logical organization (see toolsets.py):

TOOLSETS = {
    "web": {
        "description": "Web search and content extraction",
        "tools": ["web_search", "web_extract", "web_crawl"]
    },
    "terminal": {
        "description": "Command execution",
        "tools": ["terminal"]
    },
    # ...
}

Adding a New Tool

Create handler function in tools/your_tool.py
Define JSON schema following OpenAI format
Register in model_tools.py (schemas and handlers)
Add to appropriate toolset in toolsets.py
Update tools/__init__.py exports

Stateful Tools

Some tools maintain state across calls within a session:

Terminal: Keeps container/sandbox running between commands
Browser: Maintains browser session for multi-step navigation

State is managed per task_id and cleaned up automatically.

2.7 KiB Raw Blame History