Reasoning Granularity Controller
Ki · Single Ability
The Problem
Timeline is stuck at a single level, using only high-level checks regardless of complexity changes.
The Operation
This ability makes the model identify the current reasoning granularity and compare it against what the problem demands. Classify the mismatch as too coarse, too fine, or matched using explicit criteria per level. If too coarse, decompose the analysis into finer sub-components until resolution matches need. Verify that adjusted granularity captures all decision-relevant distinctions. Map granularity transitions across the chain to ensure consistency. If it detects apply uniform granularity problem mixed resolution, it halts and corrects.
The Structure
This ability runs on a partitioned rule application that uses different reasoning rules in different contexts. The loop continues until the output stabilizes and further iterations produce no change.
If the analysis dwells at a single level of detail without adjusting granularity to match each sub-question's needs, granularity control was inactive.
Haki · Multi Ability
Synergy Topology
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, these four abilities don't run in sequence. They merge into a single injection where the dependency grounds the reasoning context, the amplifier sharpens the primary's output, and the alternative provides a fallback path if the primary's topology cannot converge. The result is a multi-angle reasoning scaffold that covers failure modes no single ability can reach alone.
Appears in Use Cases