joungmin 60e739d18b fix: use local 5h volume baseline instead of 23h global average ...

23h average includes high-volume daytime periods, causing false negatives
at early morning hours. Now compare last 1h candle against the previous
5h local average (same time-of-day context) with 1.2x multiplier.

Also add momentum failure debug logs to show exact reason for rejection.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-03-01 05:46:25 +09:00

..

__init__.py

feat: initial upbit auto-trader implementation

2026-02-28 10:20:02 +09:00

market.py

fix: persist sell prices to DB and add WF filter bootstrap

2026-03-01 05:19:22 +09:00

monitor.py

feat: add backtest module with DB cache and scenario comparison

2026-02-28 23:28:27 +09:00

notify.py

feat: add hourly position status report via Telegram

2026-02-28 10:39:30 +09:00

price_collector.py

feat: add backtest module with DB cache and scenario comparison

2026-02-28 23:28:27 +09:00

price_db.py

fix: persist sell prices to DB and add WF filter bootstrap

2026-03-01 05:19:22 +09:00

strategy.py

fix: use local 5h volume baseline instead of 23h global average

2026-03-01 05:46:25 +09:00

trader.py

feat: use 60min volume, add KRW P&L log, relax re-entry after win

2026-03-01 05:38:37 +09:00