Goal Stack Integrity Auditor
Ki · Reasoning
The Problem
The marketing campaign's social media engagement goal has drifted into a means-ends inversion, prioritizing likes over sales.
The Operation
This cognitive operation forces the model to state top-level goal as single sentence. List all subgoals; trace each back to top-level goal by explaining how it advances the main objective. If any subgoal cannot be traced back, flag as potential goal drift. For flagged subgoals, classify as means-ends inversion, subgoal hijacking, or mission creep. Check whether current action directly serves a connected subgoal or has drifted. Let subgoal operate without explicit link primary goal is rejected.
The Structure
Under the hood, the reasoning follows a chain of custody audit that traces the provenance of every claim. The loop runs until all inputs are processed or no new progress emerges.
If a subgoal has displaced the original objective without the priority inversion being flagged, goal stack integrity auditing has failed.
Haki · Reasoning-Multi
Cross-Domain Suppression
In Haki mode, the API retrieves the primary ability first, then fans out to three synergy roles that compound its reasoning.
When retrieved in Haki mode, the primary ability is augmented with failure guards extracted from 3 abilities in different cognitive domains. Each guard blocks a specific reasoning failure the primary alone wouldn't catch. A self-check forces verification before output. The result is cross-domain coverage that no single ability can reach alone.