root/trading_bot_v4
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

critical: Position Manager monitoring failure - 08 loss incident (Dec 8, 2025)

Browse Source 
- Bug #73 recurrence: Position opened Dec 7 22:15 but PM never monitored
- Root cause: Container running OLD code from BEFORE Dec 7 fix (2:46 AM start < 2:46 AM commit)
- User lost 08 on unprotected SOL-PERP SHORT
- Fix: Rebuilt and restarted container with 3-layer safety system
- Status: VERIFIED deployed - all safety layers active
- Prevention: Container timestamp MUST be AFTER commit timestamp
This commit is contained in:
mindesbunister
2025-12-08 07:51:28 +01:00
parent 66c6f6dea5
commit 57c2565e63
7 changed files with 1012 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

97
cluster/run_v11_full_sweep.sh Executable file
View File

@@ -0,0 +1,97 @@
#!/bin/bash
# Launch V11 Full Parameter Sweep on EPYC Cluster
set -e
echo "================================================================"
echo "V11 FULL PARAMETER SWEEP - EXHAUSTIVE SEARCH"
echo "================================================================"
echo ""
echo "Grid: 26,244 combinations"
echo " - flip_threshold: 0.25, 0.3, 0.35, 0.4, 0.45, 0.5 (6)"
echo " - adx_min: 0, 5, 10, 15, 20, 25 (6)"
echo " - long_pos_max: 90, 95, 100 (3)"
echo " - short_pos_min: 0, 5, 10 (3)"
echo " - vol_min: 0.0, 0.5, 1.0 (3)"
echo " - entry_buffer_atr: 0.0, 0.05, 0.10 (3)"
echo " - rsi_long_min: 20, 25, 30 (3)"
echo " - rsi_short_max: 70, 75, 80 (3)"
echo ""
echo "Workers:"
echo " - worker1: 24 cores (24/7)"
echo " - worker2: 18 cores (7PM-6AM only)"
echo ""
echo "Estimated Duration: 8-12 hours"
echo "================================================================"
echo ""
cd "$(dirname "$0")"
# Check data file
if [ ! -f "data/solusdt_5m.csv" ]; then
echo "✗ Error: data/solusdt_5m.csv not found"
exit 1
fi
echo "✓ Market data found"
# Check worker script
if [ ! -f "v11_full_worker.py" ]; then
echo "✗ Error: v11_full_worker.py not found"
exit 1
fi
echo "✓ Worker script found"
# Make scripts executable
chmod +x v11_full_coordinator.py
chmod +x v11_full_worker.py
echo "✓ Scripts executable"
# Create results directory
mkdir -p v11_results
echo "✓ Results directory ready"
# Deploy worker to machines
echo ""
echo "📦 Deploying worker script to EPYC cluster..."
# Worker 1
echo " → worker1 (10.10.254.106)"
scp v11_full_worker.py root@10.10.254.106:/home/comprehensive_sweep/
scp ../backtester/v11_moneyline_all_filters.py root@10.10.254.106:/home/comprehensive_sweep/backtester/
# Worker 2 (via worker 1)
echo " → worker2 (10.20.254.100) via worker1"
ssh root@10.10.254.106 "scp /home/comprehensive_sweep/v11_full_worker.py root@10.20.254.100:/home/backtest_dual/backtest/"
ssh root@10.10.254.106 "scp /home/comprehensive_sweep/backtester/v11_moneyline_all_filters.py root@10.20.254.100:/home/backtest_dual/backtest/backtester/"
echo "✓ Workers deployed"
# Launch coordinator
echo ""
echo "🚀 Starting full sweep coordinator..."
nohup python3 v11_full_coordinator.py > coordinator_v11_full.log 2>&1 &
COORDINATOR_PID=$!
echo "✓ Coordinator started (PID: $COORDINATOR_PID)"
echo ""
echo "================================================================"
echo "MONITORING"
echo "================================================================"
echo "Live log: tail -f coordinator_v11_full.log"
echo "Database: sqlite3 exploration.db"
echo "Results: cluster/v11_results/*_results.csv"
echo ""
echo "Check status:"
echo " sqlite3 exploration.db \\"
echo " \"SELECT status, COUNT(*) FROM v11_full_chunks GROUP BY status\""
echo ""
echo "Top results so far:"
echo " sqlite3 exploration.db \\"
echo " \"SELECT params, pnl FROM v11_full_strategies \\"
echo " ORDER BY pnl DESC LIMIT 10\""
echo ""
echo "To stop sweep:"
echo " kill $COORDINATOR_PID"
echo ""
echo "Telegram notifications enabled (start/complete/stop)"
echo "================================================================"