kodeagent.kodeagent.Agent

class kodeagent.kodeagent.Agent(model_name: str, *, name: str | None = None, description: str | None = None, tools: list[~collections.abc.Callable] = <factory>, litellm_params: dict = <factory>, persona: str | None = None, system_prompt: str | None = None, max_iterations: int = 20, filter_tools_for_task: bool = False, max_retries: int = 3, work_dir: str | None = None, tracing_type: ~typing.Literal['langfuse', 'langsmith'] | None = None)

An abstract agent. Base class for all types of agents.

__init__(model_name: str, *, name: str | None = None, description: str | None = None, tools: list[~collections.abc.Callable] = <factory>, litellm_params: dict = <factory>, persona: str | None = None, system_prompt: str | None = None, max_iterations: int = 20, filter_tools_for_task: bool = False, max_retries: int = 3, work_dir: str | None = None, tracing_type: ~typing.Literal['langfuse', 'langsmith'] | None = None) → None

Methods

__init__(model_name, *[, name, description, ...])
add_output_file(path)	Record a file generated during task execution.
add_to_history(message)	Add a chat message to the agent's message history.
clear_history()	Clear the agent's message history.
get_history()	Get a formatted string of the agent's message history, excluding the system prompt
get_system_prompt_content()	Return the formatted system prompt string for this agent.
get_tools_description([tools])	Generate a description of all the tools available to the agent.
get_usage_metrics()	Get raw usage metrics as a dictionary.
get_usage_report([include_breakdown])	Get a formatted report of LLM usage for the current/last task.
init_history()	Initialize the agent's message history, e.g., with a system prompt.
normalize_content(content)	Convert message content to a readable string for Observer.
parse_text_response(text)	Parse a text response from the LLM into a ChatMessage.
post_run()	Hook intended to run after the main agent loop.
pre_run()	Hook intended to run before the main agent loop.
response(rtype, value[, channel, metadata])	Prepare a response to be sent by the agent.
run(task[, files, task_id, max_iterations, ...])	Execute a task using the agent.
salvage_response()	When an agent fails to find an answer, salvage what information could be gathered.

Attributes

HISTORY_TRUNCATE_CHARS
artifacts	Returns the list of output files generated during task execution.
current_plan	Returns the current plan for the task.
current_trace
description
filter_tools_for_task
final_answer_found
max_iterations
max_retries
msg_idx_of_new_task
name
persona
planner
purpose	Describe the name, purpose of, and tools available to an agent.
system_prompt
task
tracing_type
work_dir
model_name
tools
litellm_params
id
tool_name_to_func
tool_names
chat_history
usage_tracker
tracer_manager
observer
is_visual_model
task_output_files