Package com.tnsai.planning.tasklist
package com.tnsai.planning.tasklist
Task list execution system for the Ralph Pattern.
This package implements the three principles of the Ralph Pattern:
- Task List Driven -
TaskListdrives execution - Clean Context - Fresh refinement loop per task via
TaskListExecutor - Progress Memory - Cross-task learning via
ProgressMemory
Quick Start
// 1. Create a task list from PRD
TaskList tasks = PRDParser.parse(Path.of("prd.json"));
// 2. Execute with progress memory
TaskListResult result = TaskListExecutor.builder()
.taskList(tasks)
.progressMemory(ProgressMemory.inMemory())
.maxIterationsPerTask(5)
.build()
.execute(agent);
// 3. Check results
System.out.printf("Completed: %d/%d%n",
result.completedCount(), result.totalCount());
GOAP Bridge
Planning actions from GOAP can be converted to a task list:
List<PlanningAction> plan = planner.plan(goals, actions, beliefs);
TaskList tasks = TaskList.fromPlannerOutput("GOAP Plan", plan);
- Author:
- TnsAI Team
- See Also:
-
ClassDescriptionParser for PRD (Product Requirements Document) JSON files.Persistent learning store for cross-task knowledge transfer.A recorded learning from task execution.A single task in a task list.Builder for TaskItem.An ordered list of tasks to execute.Executes a task list using iterative refinement for each task.Builder for TaskListExecutor.Result of executing a complete task list.Execution status of a task item.