kodeagent.orchestrator.Planner

class kodeagent.orchestrator.Planner(model_name: str, litellm_params: dict | None = None, max_retries: int = 3, usage_tracker: UsageTracker | None = None, tracer_manager: AbstractTracerManager | None = None)

Given a task, generate and maintain a step-by-step plan to solve it.

Create a planner using the given model.

Parameters:

• model_name – The name of the LLM to use.

• litellm_params – LiteLLM parameters.

• max_retries – Maximum number of retries for LLM calls.

• usage_tracker – Optional UsageTracker instance to record usage.

• tracer_manager – Optional AbstractTracerManager for hierarchical tracing.

__init__(model_name: str, litellm_params: dict | None = None, max_retries: int = 3, usage_tracker: UsageTracker | None = None, tracer_manager: AbstractTracerManager | None = None)

Create a planner using the given model.

Parameters:

• model_name – The name of the LLM to use.

• litellm_params – LiteLLM parameters.

• max_retries – Maximum number of retries for LLM calls.

• usage_tracker – Optional UsageTracker instance to record usage.

• tracer_manager – Optional AbstractTracerManager for hierarchical tracing.

Methods

__init__(model_name[, litellm_params, ...])	Create a planner using the given model.
create_plan(task, agent_type[, parent_trace])	Create a plan to solve the given task and store it.
get_formatted_plan([scope])	Convert the agent's plan into a Markdown checklist.
get_steps_done()	Returns the completed steps from the current plan.
get_steps_pending()	Returns the pending steps from the current plan.
reset()	Reset the planner state.
update_plan(thought, observation, task_id[, ...])	Update the plan based on the last thought and observation.