jgrusewski 99332003a4 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).

2026-05-09 18:04:00 +02:00

..

2026-03-10-zero-cpu-hotpath.md

…

2026-03-11-dqn-factored-actions.md

…

2026-03-13-gpu-test-workflow.md

…

2026-03-14-kanidm-netbird-sso.md

…

2026-03-15-fused-cuda-training.md

…

2026-03-16-gpu-iql-her-porting.md

…

2026-03-17-candle-hard-refactor.md

…

2026-03-17-cuda-candle-elimination.md

…

2026-03-18-full-gpu-forward-passes.md

…

2026-03-18-gpu-dedup-consolidation.md

…

2026-03-18-gpu-resident-pipeline.md

…

2026-03-21-h100-epoch-optimization-phase1.md

…

2026-03-21-h100-epoch-optimization-phase2.md

…

2026-03-21-h100-epoch-optimization-phase3.md

…

2026-03-21-h100-epoch-optimization-phase4.md

…

2026-03-21-training-profiles.md

…

2026-03-22-gpu-composite-reward.md

…

2026-03-22-gpu-segment-tree.md

…

2026-03-23-9-exposure-dual-distributional.md

…

2026-03-23-stable-distributional-loss.md

…

2026-03-24-c51-loss-convergence.md

…

2026-03-24-financial-metrics-pipeline.md

…

2026-03-24-master-trading-agent.md

…

2026-03-24-remaining-gpu-features.md

…

2026-03-25-boundary-trade-counting.md

…

2026-03-25-config-unification.md

…

2026-03-25-eliminate-nvrtc.md

…

2026-03-25-reward-v6-fixes.md

…

2026-03-25-trade-lifecycle-fix.md

…

2026-03-26-eval-cleanup.md

…

2026-03-26-final-fixes-before-h100.md

…

2026-03-27-bf16-native-completion.md

…

2026-03-27-bug-fixes.md

…

2026-03-27-full-bf16-rewrite.md

…

2026-03-27-gpu-hot-path-performance.md

…

2026-03-27-gradient-stability.md

…

2026-03-27-hive-findings-fixes.md

…

2026-03-27-trade-physics-refactor.md

…

2026-03-27-training-kernel-unification.md

…

2026-03-29-drawdown-aware-training.md

…

2026-03-29-generalization-gap.md

…

2026-03-29-novel-generalization.md

…

2026-03-30-dqn-gems-implementation.md

…

2026-03-30-gems-and-pearls-generalization.md

…

2026-03-31-databento-download-workflow.md

…

2026-03-31-feature-precompute-pipeline.md

…

2026-03-31-imbalance-bars-and-cleanup.md

…

2026-04-01-h100-gpu-optimization.md

…

2026-04-02-autobatchsizer-vram-budget.md

…

2026-04-02-mega-graph-sub10s-epochs.md

…

2026-04-02-mega-graph-training-loop-refactor.md

…

2026-04-02-zero-copy-fxcache-pipeline.md

…

2026-04-02-zero-copy-walk-forward.md

…

2026-04-03-argo-fxcache-infrastructure-fix.md

…

2026-04-03-feature-extraction-pipeline-fix.md

…

2026-04-03-hyperopt-fxcache-migration.md

…

2026-04-04-c51-loss-accumulator-fix.md

…

2026-04-04-cuda-kernel-safety.md

…

2026-04-04-feature-extraction-pipeline-fix.md

…

2026-04-04-gpu-test-fixes.md

…

2026-04-05-gpu-regime-and-training-hang-fix.md

…

2026-04-06-h100-maximum-performance.md

…

2026-04-06-per-prefix-sum.md

…

2026-04-06-per-tree-fix-and-zero-sync-readback.md

…

2026-04-07-reward-v7-gems-pearls.md

…

2026-04-07-reward-v7.md

…

2026-04-07-reward-v8-master.md

…

2026-04-07-reward-v71-fixes.md

…

2026-04-08-advantage-standardization.md

…

2026-04-08-h100-epoch-optimization-v2.md

…

2026-04-08-h100-graph-optimizations.md

…

2026-04-08-hierarchical-4branch.md

…

2026-04-08-magnitude-branch-fix.md

…

2026-04-08-per-branch-loss-weighting.md

…

2026-04-08-volume-bar-pipeline.md

…

2026-04-09-adv-logits-layout-fix.md

…

2026-04-09-h100-nan-fix.md

…

2026-04-10-argo-pipeline-redesign.md

…

2026-04-10-bf16-elimination.md

…

2026-04-10-cublaslt-migration.md

…

2026-04-10-dead-code-gpu-profiling.md

…

2026-04-11-abi-complete.md

…

2026-04-11-abi-foundation.md

…

2026-04-11-action-diversity-iqn4branch.md

…

2026-04-11-exp-collector-zero-copy.md

…

2026-04-11-varstore-elimination.md

…

2026-04-12-adaptive-c51-vrange.md

…

2026-04-12-dsr-reward-restructure.md

…

2026-04-13-iql-full-integration.md

…

2026-04-13-single-cublas-handle.md

…

2026-04-14-adaptive-training-dynamics.md

…

2026-04-14-cross-pollinated-branch-intelligence.md

…

2026-04-14-direction-conditioned-magnitude.md

…

2026-04-15-oos-generalization-enhancement.md

plan: OOS Generalization Enhancement — 9 tasks, 10 components

2026-04-15 20:33:03 +02:00

2026-04-15-oos-performance-enhancement.md

plan: add Tasks 9d-9e — Q-mean drift regularization + new component LR warmup

2026-04-15 19:43:50 +02:00

2026-04-15-supervised-architecture-transfer.md

…

2026-04-16-introspective-state-vector.md

plan: Introspective State Vector — 9 tasks, pure GPU implementation

2026-04-16 22:46:54 +02:00

2026-04-16-learned-risk-management.md

plan: Learned Risk Management — 6 tasks, 5th branch risk_budget [0,1]

2026-04-16 01:32:16 +02:00

2026-04-16-self-improving-training-loop.md

plan: Self-Improving Training Loop — 6 tasks, 9 enrichments

2026-04-16 17:34:14 +02:00

2026-04-16-tick-microstructure-intelligence.md

plan: Tick Microstructure Intelligence — 4 tasks, OFI_DIM 8→20

2026-04-17 00:02:02 +02:00

2026-04-16-trade-plan-head.md

plan: Trade Plan Head — 5 tasks, hierarchical plan-based trading

2026-04-17 00:48:18 +02:00

2026-04-16-training-environment-alignment.md

plan: Training Environment Alignment — 5 tasks, 3 phases

2026-04-16 21:49:19 +02:00

2026-04-17-unified-cublas-training-graph.md

plan: rewrite Task 9 for child graph architecture

2026-04-17 23:58:32 +02:00

2026-04-18-multi-stream-phase2.md

plan: Phase 2 multi-stream parallelism — 7 tasks

2026-04-18 16:07:06 +02:00

2026-04-18-unified-single-graph.md

plan: unified single-graph — 5 tasks, zero ungraphed kernel launches

2026-04-18 21:26:40 +02:00

2026-04-19-kernel-optimization-phase3.md

feat: target_dim 4→6 + spec v5 with pearls (bar duration, book CoM, retrospective hold)

2026-04-19 23:47:04 +02:00

2026-04-19-kernel-optimization.md

plan: kernel optimization — 8 tasks, 7 kernels → cuBLAS + batch-parallel

2026-04-19 12:15:04 +02:00

2026-04-19-ofi-momentum-dense-reward.md

plan: OFI momentum + dense micro-reward — 9 tasks, full gradient flow

2026-04-19 23:21:24 +02:00

2026-04-19-true-single-graph.md

plan: true single-graph — 7 tasks, zero CPU on hot path

2026-04-19 00:06:05 +02:00

2026-04-20-adaptive-learning-dynamics.md

plan: adaptive learning dynamics — 19 tasks across 5 phases

2026-04-20 19:12:41 +02:00

2026-04-20-unified-state-layout.md

plan: unified state layout implementation — 8 tasks

2026-04-20 14:36:03 +02:00

2026-04-21-policy-quality-phase2.md

plan(policy-quality): reframe DELETE tasks per no-functionality-removal rule

2026-04-22 11:18:28 +02:00

2026-04-21-policy-quality.md

docs(policy-quality): main-branch workflow — cut feat/wip branches

2026-04-21 21:06:33 +02:00

2026-04-24-dqn-v2-plan-1-substrate.md

plan(dqn-v2): Plan 1 substrate + refactor complete (Tasks 9-17)

2026-04-24 18:29:34 +02:00

2026-04-24-dqn-v2-plan-2-temporal-core.md

plan(dqn-v2): Plan 2 revision — GPU-drives architecture + Mamba2 validation scope

2026-04-24 19:04:56 +02:00

2026-04-24-dqn-v2-plan-3-behavioural.md

plan(dqn-v2): mark Tasks 8+9 LANDED; 11/12 done

2026-04-25 09:15:43 +02:00

2026-04-24-dqn-v2-plan-4-supervised-concepts.md

plan(dqn-v2): Plan 4 Task 2c GRN — further decomposed into 2c.1/2c.2/2c.3+4/2c.5

2026-04-25 11:53:10 +02:00

2026-04-24-dqn-v2-plan-5-validation.md

plan(dqn-v2): Plan 5 — validation substrate + final pass implementation plan

2026-04-24 10:06:25 +02:00

2026-04-27-distributional-rl-thompson-plan-A-phase-0.md

plan(dqn): Thompson sampling rollout — Plans A+B+C+D (4 sequential phases)

2026-04-27 08:10:42 +02:00

2026-04-27-distributional-rl-thompson-plan-B-phase-1.md

plan(dqn): Thompson sampling rollout — Plans A+B+C+D (4 sequential phases)

2026-04-27 08:10:42 +02:00

2026-04-27-distributional-rl-thompson-plan-C-phase-2.md

fix(dqn): Plan C T2 amendment — match production adaptive C51 support

2026-04-29 17:26:22 +02:00

2026-04-27-distributional-rl-thompson-plan-D-phase-3.md

plan(dqn): Thompson sampling rollout — Plans A+B+C+D (4 sequential phases)

2026-04-27 08:10:42 +02:00

2026-04-27-moe-regime-redesign.md

spec+plan(moe): correct gate input dim 42 → STATE_DIM=128

2026-04-27 18:22:40 +02:00

2026-04-29-numerical-stability-sp1-f1-nan-root-cause.md

plan(dqn): SP1 numerical stability — F1 NaN root-cause investigation

2026-04-29 23:21:26 +02:00

2026-04-29-numerical-stability-sp2-sp3.md

plan(dqn): SP2 + SP3 implementation — fused NaN kernel + 5-mechanism Q-stability

2026-04-30 08:49:36 +02:00

2026-04-30-sp4-signal-driven-magnitude-control.md

fix(sp4): migrate fast/slow grad-norm EMA update to GPU per feedback_no_cpu_compute_strict

2026-05-01 14:07:10 +02:00

2026-05-01-sp5-magnitude-differentiation-and-eval-collapse.md

docs(sp5): comprehensive implementation plan — 4 layers, ~21 tasks

2026-05-01 20:01:27 +02:00

2026-05-02-sp6-per-branch-consumer-infrastructure-refactor.md

docs(sp6): implementation plan — 3-sub-project parallel refactor (Pearls 2, 3, 5)

2026-05-02 01:47:07 +02:00

2026-05-03-sp7-loss-balance-controller.md

plan(sp7): v2 — fix 5 self-review violations from v1

2026-05-03 00:35:07 +02:00

2026-05-04-sp11-reward-as-controlled-subsystem.md

plan(sp11): patch all 5 violations + 2 gaps from review

2026-05-04 00:40:36 +02:00

2026-05-04-sp13-redefine-success-for-predictive-skill.md

chore(sp13): script bug fix + Layer B implementation notes

2026-05-05 08:27:49 +02:00

2026-05-05-sp14-aux-q-wire-earned-gradient-flow.md

plan(sp14): implementation plan for spec v3

2026-05-05 17:36:56 +02:00

2026-05-06-sp15-trader-discipline-and-recovery.md

plan(sp15): fix 3 critical compile-breakers from third review

2026-05-06 10:32:10 +02:00

2026-05-07-sp14-layer-c-separate-aux-trunk.md

feat(sp14-c.5b): atomic contract migration — h_s2 → h_s2_aux + revert zero-fills

2026-05-08 03:01:13 +02:00

2026-05-08-sp16-hold-collapse-structural-fix.md

fix(sp16-t3): Wiener-optimal adaptive α per pearl — hold_cost_scale + min_hold_temperature

2026-05-08 18:56:58 +02:00

2026-05-08-sp17-dueling-q-network.md

docs(sp17): copy plan file to feat/sp17-dueling branch

2026-05-08 20:57:28 +02:00

2026-05-08-sp18-reward-shape-hold-attractor.md

docs(sp18): copy spec + plan to feat/sp18-combined branch

2026-05-09 00:25:06 +02:00

2026-05-09-sp19-20-wr-first.md

plan(sp19+20): WR-first reward implementation plan

2026-05-09 18:04:00 +02:00