Execution Config • AI Agent SDK

ExecutionConfig: Configuration for agent execution limits.

ExecutionConfig

Defined in the Feature Configs module.

AI Agent

Configuration for agent execution limits.

Consolidates: max_iter, max_rpm, max_execution_time, max_retry_limit, allow_code_execution, code_execution_mode, rate_limiter

Properties

ResponseField int

No description available.

ResponseField Optional[int]

No description available.

ResponseField Optional[int]

No description available.

ResponseField Optional[int]

No description available.

ResponseField int

No description available.

ResponseField float

No description available.

ResponseField float

No description available.

ResponseField float

No description available.

ResponseField int

No description available.

ResponseField bool

No description available.

ResponseField str

No description available.

ResponseField bool

No description available.

ResponseField Optional

No description available.

ResponseField Optional

No description available.

ResponseField Union[bool, ContextCompactionPolicy]

No description available.

ResponseField Union[bool, PreCompactionMemoryFlushConfig]

No description available.

ResponseField Optional[int]

No description available.

ResponseField Optional[CompactionStrategy]

No description available.

ResponseField Optional[float]

No description available.

ResponseField Any

No description available.

ResponseField Optional[bool]

No description available.

ResponseField Union[bool, int]

No description available.

ResponseField bool

No description available.

ResponseField Optional[str]

No description available.

ResponseField Optional[str]

No description available.

Methods

resolved_max_steps()

Single, unified step budget honoured by both tool-execution loops.

resolved_max_tool_calls()

Per-turn tool-call guardrail (max parallel tool calls in one response).

Internal & Generic Methods

from_dict: Create ExecutionConfig from dictionary.
to_dict: Convert to dictionary.

Usage

python

# Simple preset
    Agent(execution="thorough")

    # With config
    Agent(execution=ExecutionConfig(
        max_iter=50,
        max_rpm=100,
        max_execution_time=300,
        max_retry_limit=5,
    ))

    # With code execution and rate limiter
    Agent(execution=ExecutionConfig(
        code_execution=True,
        code_mode="safe",
        rate_limiter=my_limiter,
    ))

    # With token budget guard
    Agent(execution=ExecutionConfig(
        max_budget=0.50,              # Hard USD limit per agent run
        on_budget_exceeded="stop",    # "stop" | "warn" | callable
    ))

Source

View on GitHub

praisonaiagents/config/feature_configs.py at line 870

Execution Config • AI Agent SDK