Files
foxhunt/docs/superpowers
jgrusewski 3bfbcd7137 plan(dqn-v2): Plan 4 reality reconciliation
Plan 4 was drafted 2026-04-24 against an earlier Plan 3 design. After
Plan 3 landed (commits 44539d8f4..3cb083f18), the pre-plan gate
referenced slot names that don't exist in the landed implementation:

- PLAN_PARAMS_0_EMA_INDEX → became READINESS_EMA_INDEX (Task 4)
- STATE_KL_THRESHOLD_EMA_INDEX → eliminated; Task 7 uses kernel-internal
  trailing-EMA-of-self pattern (no separate threshold slot)
- TEMPORAL_REWARD_{PERSIST,REGIME_SHIFT,CONSISTENCY}_EMA_INDEX → consolidated
  into rc[5] → ISV[68] REWARD_BONUS_EMA_INDEX via Plan 3 Task 6a/6b/6c

Updated:
- Pre-plan slot-existence check matches landed slot names
- Validation-doc gate softened: Plan 3 Argo Tier 1 PASS becomes OPTIONAL;
  local 5-epoch multi-fold smoke is the de-facto gate (user choice
  to proceed without burning Argo cycles)
- Status table at top shows landed Plan 3 baseline (ISV_TOTAL_DIM=87,
  PS_STRIDE=43, fingerprint at [85,86]) and per-task difficulty estimate
- Reality-reconciliation note documents the rename trail

No task body changes; subsequent commits will revise individual task
specs as they become next-up for execution.
2026-04-25 09:21:36 +02:00
..