style(rl): F1.1 code review fixes — separator + comments

Code-quality review found 2 Important + 2 Minor issues; applied all 4:
- separator style: ────── → ============ (file convention)
- restored split sub-headers: outputs (6) / Welford state (4)
- restored full safety-net comment with issue #4 reference
- added inline value hints on every constant (per spec block)

Zero functional change — comments and whitespace only.
This commit is contained in:
jgrusewski
2026-05-31 11:49:37 +02:00
parent c1a0143311
commit 6353deed15

View File

@@ -1502,42 +1502,44 @@ pub const RL_EVAL_IQN_TAU_MIN_NORMAL_INDEX: usize = 693; // 0.10
pub const RL_EVAL_ENTROPY_COEF_MIN_NORMAL_INDEX: usize = 694; // 0.01
pub const RL_EVAL_PPO_CLIP_EPS_MIN_NORMAL_INDEX: usize = 695; // 0.05
// ──────────────────────────────────────────────────────────────────
// ============================================================
// Regime observer (spec: 2026-05-31-regime-observer-design.md v3)
// Unified state-machine signals for risk-stack controllers.
// ──────────────────────────────────────────────────────────────────
// ============================================================
// regime_observer outputs (6 surface signals + 4 internal Welford state)
pub const RL_REGIME_DEAD_ZONE_FLAG_INDEX: usize = 696;
pub const RL_REGIME_DEAD_ZONE_DURATION_INDEX: usize = 697;
pub const RL_REGIME_DEAD_ZONE_TIMEOUT_FLAG_INDEX: usize = 698;
pub const RL_REGIME_RECOVERY_FACTOR_INDEX: usize = 699;
pub const RL_REGIME_SESSION_PNL_VARIANCE_EMA_INDEX: usize = 700;
pub const RL_REGIME_TAIL_EVENT_RECENCY_INDEX: usize = 701;
pub const RL_REGIME_SESSION_PNL_VAR_M2_INDEX: usize = 702;
pub const RL_REGIME_SESSION_PNL_VAR_MEAN_INDEX: usize = 703;
pub const RL_REGIME_SESSION_PNL_VAR_COUNT_INDEX: usize = 704;
pub const RL_REGIME_PREV_WORST_PNL_INDEX: usize = 705;
// regime_observer outputs (6 surface signals)
pub const RL_REGIME_DEAD_ZONE_FLAG_INDEX: usize = 696; // 0/1
pub const RL_REGIME_DEAD_ZONE_DURATION_INDEX: usize = 697; // counter
pub const RL_REGIME_DEAD_ZONE_TIMEOUT_FLAG_INDEX: usize = 698; // 0/1 (safety net)
pub const RL_REGIME_RECOVERY_FACTOR_INDEX: usize = 699; // [0,1] (drift-free diag)
pub const RL_REGIME_SESSION_PNL_VARIANCE_EMA_INDEX: usize = 700; // σ²
pub const RL_REGIME_TAIL_EVENT_RECENCY_INDEX: usize = 701; // counter
// regime_observer internal Welford state (kept on device)
pub const RL_REGIME_SESSION_PNL_VAR_M2_INDEX: usize = 702; // Welford
pub const RL_REGIME_SESSION_PNL_VAR_MEAN_INDEX: usize = 703; // Welford
pub const RL_REGIME_SESSION_PNL_VAR_COUNT_INDEX: usize = 704; // Welford
pub const RL_REGIME_PREV_WORST_PNL_INDEX: usize = 705; // Δ source
// Kelly resurrection (consumed by Kelly kernel in F2)
pub const RL_KELLY_EPS_RECOVERY_LIVE_INDEX: usize = 706;
pub const RL_KELLY_EPS_RECOVERY_MIN_INDEX: usize = 707;
pub const RL_KELLY_EPS_RECOVERY_MAX_INDEX: usize = 708;
pub const RL_KELLY_EPS_RECOVERY_N_RECOVERY_INDEX: usize = 709;
pub const RL_KELLY_EPS_RECOVERY_LIVE_INDEX: usize = 706; // current ε value (drift-free)
pub const RL_KELLY_EPS_RECOVERY_MIN_INDEX: usize = 707; // config 0.05
pub const RL_KELLY_EPS_RECOVERY_MAX_INDEX: usize = 708; // config 0.50
pub const RL_KELLY_EPS_RECOVERY_N_RECOVERY_INDEX: usize = 709; // config 100
// Safety net
pub const RL_REGIME_DEAD_ZONE_MAX_DURATION_INDEX: usize = 710;
// Safety net: dead-zone timeout (issue #4 — bounded loss during prolonged adverse regime)
pub const RL_REGIME_DEAD_ZONE_MAX_DURATION_INDEX: usize = 710; // config 1000 steps
// IQN τ tail-boost (consumed in F5)
pub const RL_IQN_TAU_TAIL_BOOST_FACTOR_INDEX: usize = 711;
pub const RL_IQN_TAU_TAIL_BOOST_N_WINDOW_INDEX: usize = 712;
pub const RL_IQN_TAU_TAIL_BOOST_FACTOR_INDEX: usize = 711; // config 1.5
pub const RL_IQN_TAU_TAIL_BOOST_N_WINDOW_INDEX: usize = 712; // config 100
// regime_observer config
pub const RL_REGIME_TAIL_SIGMA_THRESHOLD_INDEX: usize = 713;
pub const RL_REGIME_TAIL_SIGMA_THRESHOLD_INDEX: usize = 713; // config 3.0
// Popart per-account max envelope (consumed by popart in F4)
pub const RL_POPART_MAX_ABS_REWARD_EMA_INDEX: usize = 714;
pub const RL_POPART_MAX_DECAY_ALPHA_INDEX: usize = 715;
pub const RL_POPART_MAX_ABS_REWARD_EMA_INDEX: usize = 714; // envelope-detector state
pub const RL_POPART_MAX_DECAY_ALPHA_INDEX: usize = 715; // config 0.01
/// Last RL-allocated slot index (exclusive).
/// Pre-risk-stack: 662. Post-Fix-B: 685. Post-v9 (warmup boundary): 696.