SirStone 167bcc4ce5 fix(SAC_LSTM_Bot): MA history self-truncation — read before > redirect; campaign v2 attempt-3 prep (#60) ...

$(cat f) inside a command redirected to f saw the already-truncated file,
so every eval cycle wiped ma_history_*.txt back to one leading-space value
and degraded the composite best-gate to last-cycle mean. Read is hoisted
into its own statement; unquoted expansion + tail -n keeps exactly the last
MA_WINDOW values. Verified: fresh/5+/6+ cycle edges reproduce sliding window.

2026-08-23 07:02:36 +02:00

..

docs

docs(SAC_LSTM_Bot): v2 restart saga, twin-freeze correction, pacing decisions

2026-08-22 21:26:24 +02:00

src

feat(SAC_LSTM_Bot): campaign v2 levers — aggression/anti-ram reward shaping + stability knob overrides (part 2)

2026-08-22 19:44:58 +02:00

tests

feat(SAC_LSTM_Bot): campaign v2 levers — aggression/anti-ram reward shaping + stability knob overrides (part 2)

2026-08-22 19:44:58 +02:00

config.nims

feat(SAC_LSTM_Bot): main bot integration (#48)

2026-08-21 20:19:05 +02:00

make_twin.sh

fix(SAC_LSTM_Bot): freeze mirror-twin via eval-mode gate in twin launcher

2026-08-22 21:09:07 +02:00

SAC_LSTM_Bot.json

feat(SAC_LSTM_Bot): training harness (#49)

2026-08-21 21:51:27 +02:00

SAC_LSTM_Bot.nimble

feat(SAC_LSTM_Bot): project scaffold (#38)

2026-08-20 23:33:43 +02:00

SAC_LSTM_Bot.sh

feat(SAC_LSTM_Bot): training harness (#49)

2026-08-21 21:51:27 +02:00

sac_train.sh

fix(SAC_LSTM_Bot): MA history self-truncation — read before > redirect; campaign v2 attempt-3 prep (#60)

2026-08-23 07:02:36 +02:00