kkt

Durable constrained optimization execution loop for long-running coding work. Use when a coding agent should capture user meaning, discover repo constraints and validation paths, build an optimization model and execution contract, create a file-backed workspace, execute with continuation, validate with evidence, re-optimize when new facts invalidate the plan, and continue through goal-mode tools until acceptance criteria or stop conditions are met.

Deep constrained optimization modeling for coding and product-engineering decisions. Use when a coding agent should capture user meaning, discover repo constraints and validation paths, inspect the system, identify objectives, system state, decision variables, domains, hard and soft constraint contracts, selected-plan binding constraints, execution-contract implications, multiple feasible models or architectures, sensitivity analysis, and interactive user tradeoffs before any implementation.

Execute an existing KKT model with deterministic drift guardrails. Use when a coding agent should pick up a completed kkt-model workspace, preserve the optimized model and guardrail contract, check model-readiness before mutation, implement the selected plan, validate with evidence, and finish without the long-running kkt-loop continuation machinery.

Constrained optimization workflow for ordinary coding requests. Use when a coding agent should capture user meaning, discover repo constraints and validation paths, build a mathematical-style optimization model, derive an execution contract, select a feasible implementation plan, execute the change, validate with evidence, and finish with a constraint audit.