Add Deep Learning (LSTM) + Quick Wins automation features

Major improvements:
- Deep Learning integration with PyTorch LSTM (Bidirectional, 128→64 units)
- Hybrid predictor: 40% RandomForest + 60% Deep Learning
- LaunchAgent for automatic weekly tip generation (Tue/Fri 21:00)
- Health-Check system with auto-recovery and Telegram alerts
- Model caching and intelligent retraining logic
- Updated CSV data and generated tips
- Performance reports for recent draws

Technical details:
- PyTorch used instead of TensorFlow (Python 3.14 compatibility)
- Apple Silicon MPS acceleration support
- Sequence learning with 20-draw history
- Early stopping and learning rate scheduling

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

data/health_check.json

@@ -0,0 +1,34 @@
+{
+  "checks": [
+    {
+      "timestamp": "2026-01-06T10:11:32.908565",
+      "status": "OK",
+      "issues": [],
+      "warnings": [
+        "Learning State: No learning state found",
+        "Disk Space: 121.4 GB free (13.1%)"
+      ],
+      "recovered": []
+    },
+    {
+      "timestamp": "2026-01-07T09:13:37.832795",
+      "status": "OK",
+      "issues": [],
+      "warnings": [
+        "Learning State: No learning state found",
+        "Disk Space: 115.3 GB free (12.4%)"
+      ],
+      "recovered": []
+    },
+    {
+      "timestamp": "2026-01-07T09:17:51.274727",
+      "status": "OK",
+      "issues": [],
+      "warnings": [
+        "Learning State: No learning state found",
+        "Disk Space: 115.3 GB free (12.4%)"
+      ],
+      "recovered": []
+    }
+  ]
+}