agents.planning.llm_compiler_v3.config

Configuration models for LLM Compiler V3 Agent.

Classes

LLMCompilerV3Config	Configuration for LLM Compiler V3 Agent.
ToolExecutionConfig	Configuration for individual tool execution.

Module Contents

class agents.planning.llm_compiler_v3.config.LLMCompilerV3Config(/, **data)

Bases: pydantic.BaseModel

Configuration for LLM Compiler V3 Agent.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

data (Any)

create_execution_config()

Create configuration dictionary for execution.

Return type:

dict[str, Any]

get_engine_for_agent(agent_name)

Get the engine configuration for a specific agent.

Parameters:

agent_name (str)

Return type:

haive.core.engine.aug_llm.AugLLMConfig

get_tool_priority(tool_name)

Get priority for a tool (higher = more preferred).

Parameters:

tool_name (str)

Return type:

int

should_enable_tool(tool_name)

Check if a tool should be enabled based on configuration.

Parameters:

tool_name (str)

Return type:

bool

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class agents.planning.llm_compiler_v3.config.ToolExecutionConfig(/, **data)

Bases: pydantic.BaseModel

Configuration for individual tool execution.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

data (Any)

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].