plan(sp19+20): WR-first reward implementation plan
Implements the spec at docs/superpowers/specs/2026-05-09-sp19-20-wr-first-design.md
(commit 9d9ca3e6e). 38 top-level tasks across 8 phases:
- Pre-Phase: branch + worktree + 10 ISV slot reservations
- Phase 0: 7 behavioral test stubs (failing scaffold)
- Phase 1: 3 ISV producer kernels (stats, EMAs, controllers)
- Phase 2: Reward kernel + atomic SP18 D-leg / SP12 v3 replacement
- Phase 3: Hold opp-cost dual emission + replay buffer schema
- Phase 4: n-step credit distributor + SP18 B-leg trace reset fix
- Phase 5: Aux→Q confidence gate at Bellman target
- Phase 6: 7 behavioral tests pass — L40S deployment gate
- Phase 7: L40S smoke + 50e×3s×3f full validation + close-out
Plan follows TDD discipline (write failing test → run-fail → implement →
run-pass → commit) with bite-sized 2-5 minute steps. All file paths
exact, all kernel code complete, no placeholders.
Self-review confirmed: spec coverage complete, no placeholders, type
consistency across phases (Sp20EmasInputs, ISV slot constants, aux_conf
schema field).