AgentConfig¶

Configuration options for agent behavior.

Quick Example¶

from mamba_agents import Agent, AgentConfig, CompactionConfig

config = AgentConfig(
    system_prompt="You are a helpful assistant.",
    max_iterations=15,
    track_context=True,
    auto_compact=True,
    context=CompactionConfig(
        strategy="hybrid",
        trigger_threshold_tokens=50000,
    ),
)

agent = Agent("gpt-4o", config=config)

Configuration Options¶

Option	Type	Default	Description
`system_prompt`	str	None	System prompt for the agent
`max_iterations`	int	10	Maximum tool-calling iterations
`track_context`	bool	True	Enable message tracking
`auto_compact`	bool	True	Auto-compact when threshold reached
`graceful_tool_errors`	bool	True	Convert tool exceptions to ModelRetry
`context`	CompactionConfig	None	Custom compaction settings
`tokenizer`	TokenizerConfig	None	Custom tokenizer settings

API Reference¶

AgentConfig ¶

Bases: BaseModel

Configuration for agent execution.

ATTRIBUTE	DESCRIPTION
`max_iterations`	Maximum tool-calling iterations before stopping. TYPE: `int`
`system_prompt`	System prompt for the agent. Can be a string or TemplateConfig. TYPE: `str \| TemplateConfig`
`context`	Context compaction configuration. None uses settings default. TYPE: `CompactionConfig \| None`
`tokenizer`	Tokenizer configuration. None uses settings default. TYPE: `TokenizerConfig \| None`
`track_context`	Whether to track messages internally across runs. TYPE: `bool`
`auto_compact`	Whether to automatically compact when threshold is reached. TYPE: `bool`