Live Router (Shadow)

Current selection

— · loading…

SHADOW

— no selection yet —

Regime (router heuristic) —

Avg score —

Lookback —

Eligible / total —

Selected at (BKK) —

Expires in —

Shadow mode: selection is logged every 30 min but does NOT modify plan.liveEnabled. After 7 days of forward verification (diag-router-forward-check.js), Phase 2 will gate live entries through this selection.

Regime detector · Phase 1a (silent log)

— · loading…

SILENT

— loading —

—

Vol ratio—30m σ ÷ 24h baseline

Ret 30m—close-to-close

Ret 1h—close-to-close

Range 30m—(max-min) ÷ mid

Vol 30m / 1h—stddev of |movePct|

Sample—5m decisions used

Phase 1a: 8-state classifier (VOLATILE_UP/DOWN, TRENDING_UP/DOWN, CHOP, POST_PUMP/DUMP, DRIFT) with 3-tick hysteresis. Updated every 1 min from btc5m_decisions. Use the history table below to verify state stability before wiring this into plan routing (Phase 2).

Regime detector · transition history

Last 30 state flips (only flips are persisted; tick-by-tick stays in realtime/market_regime).

Time (BKK)	From → To	Vol ratio	Ret 30m	Ret 1h	Sample
loading…

Eligible plans · 2h lookback

Plan	Trades	W/L	WR	PnL	In selected?
loading…

Regime picks

Heuristic from btc5m_decisions.score (1h average). Mapping is based on 24-48h backtest data — to be replaced by Phase 1 detector.

Regime	Plans	Why
UP	M	5m fast scalp · 77% WR in UP regime
DOWN	L, G	L slow tolerance · G multi-TF align
SIDE	A	Default safe / full pipeline

Final selection = topByWR ∪ regimePicks

Selection frequency · last 50 epochs

—

Plan	Picked	% of epochs	Bar
loading…

Selection history

Most recent 50. Each row = one 30-min epoch.

Time (BKK)	Regime	Score	Top by WR	Top by ROI	Selected (final)	Eligible
loading…