jgrusewski 4aca6330f0 feat(ml-backtesting): hard-SL trigger in stop_check_isv ...

sl_distance = max(pnl_ema_loss, atr_mid_ema) per
pearl_blend_formulas_must_have_permanent_floor. Fires force-flat
(3, 0) when unrealized_pl_per_lot drops below -sl_distance.
Multi-horizon mask averaging + trail trigger land in Tasks 5-6.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-20 00:04:07 +02:00

..

fixtures

feat(ml-backtesting): bytecode VM dispatcher for Strategy compositions (C13)

2026-05-18 09:26:22 +02:00

checkpoint_smoke.rs

chore(ml-alpha): drop 'v2' naming — greenfield, no backward compat

2026-05-19 08:58:28 +02:00

decision_floor_coldstart.rs

feat(ml-backtesting): cold-start stopgap — max-confidence bytecode policy (Q1/Tier1)

2026-05-19 22:00:52 +02:00

lob_sim_fixtures.rs

feat(ml-backtesting): cold-start stopgap — max-confidence bytecode policy (Q1/Tier1)

2026-05-19 22:00:52 +02:00

lob_sim_fuzz.rs

test(ml-backtesting): Ring 2 invariant fuzz at N ∈ {1, 16, 256} (C10)

2026-05-18 09:00:49 +02:00

lob_sim_integrated_fuzz.rs

feat(ml-backtesting): cold-start stopgap — max-confidence bytecode policy (Q1/Tier1)

2026-05-19 22:00:52 +02:00

parallel_sim_correctness.rs

feat(ml-backtesting): cold-start stopgap — max-confidence bytecode policy (Q1/Tier1)

2026-05-19 22:00:52 +02:00

ring3_replay.rs

test(ml-backtesting): Ring 3 production-day replay validation (C17)

2026-05-18 10:09:49 +02:00

stop_controller.rs

feat(ml-backtesting): hard-SL trigger in stop_check_isv

2026-05-20 00:04:07 +02:00

threshold_and_cost.rs

feat(ml-backtesting): cold-start stopgap — max-confidence bytecode policy (Q1/Tier1)

2026-05-19 22:00:52 +02:00

trainer_parity.rs

feat(ml-backtesting): BacktestHarness orchestrator + Ring 1b parity (C8)

2026-05-18 08:52:49 +02:00