Graph Grammar Constructor
Ki · Single Ability
The Problem
The network diagram is stored as static patterns, leading to rule blindness and no generativity in graph construction.
The Operation
The model is directed to identify recurring structural patterns and extract each as a candidate graph grammar: a start axiom plus production rules. Verify that the rules generate the full observed pattern family by testing against at least three instances. Classify each grammar by generative capacity and rank by compactness. Map query matching to grammar intersection rather than instance similarity. Validate that structural mutation via rule substitution produces only well-formed outputs. The constraint: never store patterns as static exemplars alone.
The Structure
The reasoning structure is a disassemble-transform-reassemble pattern that breaks the problem apart, modifies each piece, and reconstructs. The loop runs until all inputs are processed or no new progress emerges.
If patterns are stored as static instances without extracting the generative rules that produce them, graph grammar construction was not performed.
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.