Skip to content

Environment

Environments define the execution context for agents, including available tools, state, and any external resources needed during task execution.

View source

Environment

Bases: ABC, TraceableMixin, ConfigurableMixin

Manages the state and tools available during a task execution.

Subclasses must implement: - setup_state(task_data) -> Any: Initialize environment state from task data - create_tools() -> Dict[str, Any]: Create tools keyed by name

create_tools abstractmethod 

create_tools() -> Dict[str, Any]

Creates tools that can interact with the environment's state.

RETURNS DESCRIPTION
Dict[str, Any]

Dict mapping tool names to tool instances

gather_config 

gather_config() -> dict[str, Any]

Gather configuration from this environment.

Output fields:

  • type - Component class name
  • gathered_at - ISO timestamp
  • tool_count - Number of tools
  • tool_names - List of tool names
RETURNS DESCRIPTION
dict[str, Any]

Dictionary containing environment configuration.

gather_traces 

gather_traces() -> dict[str, Any]

Gather execution traces from this environment and its tools.

Output fields:

  • type - Component class name
  • gathered_at - ISO timestamp
  • tool_count - Number of tools in environment
  • tools - Dictionary of tool traces keyed by tool name
RETURNS DESCRIPTION
dict[str, Any]

Dictionary containing environment execution traces.

get_tool 

get_tool(name: str) -> Optional[Any]

Get a tool by name.

PARAMETER DESCRIPTION
name

Tool name

TYPE: str

RETURNS DESCRIPTION
Optional[Any]

The tool, or None if not found

get_tools 

get_tools() -> Dict[str, Any]

Get all tools as a dict.

setup_state abstractmethod 

setup_state(task_data: dict) -> Any

Initializes the environment's state from task data.

Tools and agent-provided helpers

Some agent adapters expose helper tools or user-simulation tools that can be used by the Environment. See the framework-specific interface pages for details: