Spaces:
Paused
Paused
Update learning_hub/adaptive_hub.py
Browse files- learning_hub/adaptive_hub.py +68 -69
learning_hub/adaptive_hub.py
CHANGED
|
@@ -1,11 +1,10 @@
|
|
| 1 |
# ==============================================================================
|
| 2 |
# 🧠 learning_hub/adaptive_hub.py
|
| 3 |
-
# (
|
| 4 |
# ==============================================================================
|
| 5 |
-
#
|
| 6 |
-
# 1.
|
| 7 |
-
# 2.
|
| 8 |
-
# 3. حقن الإعدادات في باقي أجزاء النظام.
|
| 9 |
# ==============================================================================
|
| 10 |
|
| 11 |
import json
|
|
@@ -15,7 +14,7 @@ from datetime import datetime
|
|
| 15 |
from collections import deque
|
| 16 |
from typing import Dict, Any, List, Optional
|
| 17 |
|
| 18 |
-
# استيراد الحدود المركزية
|
| 19 |
from ml_engine.processor import SystemLimits
|
| 20 |
|
| 21 |
class StrategyDNA:
|
|
@@ -23,11 +22,13 @@ class StrategyDNA:
|
|
| 23 |
تعريف هيكلية البيانات لكل استراتيجية.
|
| 24 |
هذا هو 'الجينوم' الذي سيتم تعديله بواسطة التعلم.
|
| 25 |
"""
|
| 26 |
-
def __init__(self, name, model_weights, ob_settings, filters):
|
| 27 |
self.name = name
|
| 28 |
self.model_weights = model_weights # أوزان النماذج (Titan, Sniper, etc.)
|
| 29 |
self.ob_settings = ob_settings # إعدادات دفتر الطلبات (Wall Ratio, etc.)
|
| 30 |
self.filters = filters # فلاتر L1 (Thresholds)
|
|
|
|
|
|
|
| 31 |
self.stats = {"wins": 0, "losses": 0, "win_rate": 0.0}
|
| 32 |
|
| 33 |
def to_dict(self):
|
|
@@ -38,18 +39,18 @@ class AdaptiveHub:
|
|
| 38 |
self.r2 = r2_service
|
| 39 |
self.dna_file_key = "learning/strategic_dna_v2.json"
|
| 40 |
|
| 41 |
-
# الحالة الحالية للسوق
|
| 42 |
self.current_market_regime = "RANGE"
|
| 43 |
|
| 44 |
-
# مخزن الحمض النووي
|
| 45 |
self.strategies: Dict[str, StrategyDNA] = {}
|
| 46 |
|
| 47 |
-
# معدل التعلم التكتيكي
|
| 48 |
-
self.TACTICAL_LEARNING_RATE = 0.05
|
| 49 |
self.MIN_WEIGHT = 0.10
|
| 50 |
self.MAX_WEIGHT = 0.90
|
| 51 |
|
| 52 |
-
print("🧠 [AdaptiveHub
|
| 53 |
|
| 54 |
async def initialize(self):
|
| 55 |
"""تحميل الـ DNA من R2 أو إنشاء الافتراضي"""
|
|
@@ -67,55 +68,63 @@ class AdaptiveHub:
|
|
| 67 |
else:
|
| 68 |
self._create_default_dna()
|
| 69 |
|
| 70 |
-
# تطبيق الإعدادات فوراً
|
| 71 |
self._inject_current_parameters()
|
| 72 |
|
| 73 |
except Exception as e:
|
| 74 |
print(f"❌ [AdaptiveHub] Init Failed: {e}")
|
|
|
|
| 75 |
self._create_default_dna()
|
| 76 |
|
| 77 |
def _create_default_dna(self):
|
| 78 |
-
"""إنشاء الإعدادات الافتراضية (
|
| 79 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
self.strategies["BULL"] = StrategyDNA(
|
| 81 |
name="BULL",
|
| 82 |
-
model_weights={"titan": 0.40, "patterns": 0.30, "sniper": 0.20, "hydra": 0.10},
|
| 83 |
-
ob_settings={"wall_ratio_limit": 0.60, "imbalance_thresh": 0.5},
|
| 84 |
-
filters={"l1_min_score": 15.0, "l3_conf_thresh": 0.60}
|
|
|
|
| 85 |
)
|
| 86 |
|
| 87 |
-
# 2. BEAR MARKET DNA 🐻
|
| 88 |
self.strategies["BEAR"] = StrategyDNA(
|
| 89 |
name="BEAR",
|
| 90 |
-
model_weights={"titan": 0.20, "patterns": 0.10, "sniper": 0.30, "hydra": 0.40
|
| 91 |
-
ob_settings={"wall_ratio_limit": 0.30, "imbalance_thresh": 0.7},
|
| 92 |
-
filters={"l1_min_score": 40.0, "l3_conf_thresh": 0.75}
|
|
|
|
| 93 |
)
|
| 94 |
|
| 95 |
-
# 3. RANGE MARKET DNA ↔️
|
| 96 |
self.strategies["RANGE"] = StrategyDNA(
|
| 97 |
name="RANGE",
|
| 98 |
-
model_weights={"titan": 0.30, "patterns": 0.40, "sniper": 0.20, "hydra": 0.10
|
| 99 |
ob_settings={"wall_ratio_limit": 0.40, "imbalance_thresh": 0.6},
|
| 100 |
-
filters={"l1_min_score": 25.0, "l3_conf_thresh": 0.65}
|
|
|
|
| 101 |
)
|
| 102 |
-
|
| 103 |
-
# 4. DEAD MARKET DNA 💀
|
| 104 |
self.strategies["DEAD"] = StrategyDNA(
|
| 105 |
name="DEAD",
|
| 106 |
-
model_weights={"titan": 0.25, "patterns": 0.25, "sniper": 0.25, "hydra": 0.25
|
| 107 |
-
ob_settings={"wall_ratio_limit": 0.20, "imbalance_thresh": 0.8},
|
| 108 |
-
filters={"l1_min_score": 50.0, "l3_conf_thresh": 0.80}
|
|
|
|
| 109 |
)
|
| 110 |
|
| 111 |
def _load_from_dict(self, data):
|
| 112 |
-
"""تحويل JSON إلى كائنات StrategyDNA"""
|
| 113 |
for key, val in data.get("strategies", {}).items():
|
| 114 |
self.strategies[key] = StrategyDNA(
|
| 115 |
name=val["name"],
|
| 116 |
model_weights=val["model_weights"],
|
| 117 |
ob_settings=val["ob_settings"],
|
| 118 |
-
filters=val["filters"]
|
|
|
|
| 119 |
)
|
| 120 |
self.strategies[key].stats = val.get("stats", {"wins":0, "losses":0})
|
| 121 |
|
|
@@ -125,40 +134,26 @@ class AdaptiveHub:
|
|
| 125 |
# ⚡ The Tactical Loop: Real-time Weight Adjustment
|
| 126 |
# ==========================================================================
|
| 127 |
async def register_trade_outcome(self, trade_data: Dict[str, Any]):
|
| 128 |
-
"""
|
| 129 |
-
يتم استدعاؤها عند إغلاق الصفقة.
|
| 130 |
-
تقوم بتعديل أوزان النماذج بناءً على من ساهم في القرار.
|
| 131 |
-
"""
|
| 132 |
try:
|
| 133 |
pnl = trade_data.get('profit_pct', 0.0)
|
| 134 |
is_win = pnl > 0
|
| 135 |
|
| 136 |
-
# معرفة الاستراتيجية التي كانت نشطة وقت الدخول (نفترض الحالية للتبسيط الآن)
|
| 137 |
active_dna = self.strategies[self.current_market_regime]
|
| 138 |
|
| 139 |
-
# تحديث إحصائيات الاستراتيجية
|
| 140 |
if is_win: active_dna.stats["wins"] += 1
|
| 141 |
else: active_dna.stats["losses"] += 1
|
| 142 |
|
| 143 |
-
# تحليل المساهمين (Decision Components)
|
| 144 |
-
# نفترض أن trade_data يحتوي على 'decision_data' بها تفاصيل المساهمة
|
| 145 |
decision_data = trade_data.get('decision_data', {})
|
| 146 |
-
components = decision_data.get('components', {})
|
| 147 |
-
|
| 148 |
-
# التعديل التكتيكي للأوزان
|
| 149 |
-
# إذا ربحت الصفقة، نزيد وزن النماذج التي كانت درجاتها عالية
|
| 150 |
-
# إذا خسرت، نعاقب النماذج التي كانت درجاتها عالية (لأنها خدعتنا)
|
| 151 |
|
| 152 |
print(f"⚖️ [Tactical Learning] Adjusting weights for {self.current_market_regime}...")
|
| 153 |
|
| 154 |
changes_log = []
|
| 155 |
|
| 156 |
-
# قائمة النماذج التي نراقبها
|
| 157 |
model_keys = {
|
| 158 |
'titan_score': 'titan',
|
| 159 |
'patterns_score': 'patterns',
|
| 160 |
-
'sniper_score': 'sniper',
|
| 161 |
-
# Hydra usually acts as a veto/exit, but if used for entry logic:
|
| 162 |
'hydra_score': 'hydra'
|
| 163 |
}
|
| 164 |
|
|
@@ -166,15 +161,11 @@ class AdaptiveHub:
|
|
| 166 |
score = float(components.get(score_key, 0.5))
|
| 167 |
current_w = active_dna.model_weights.get(model_name, 0.25)
|
| 168 |
|
| 169 |
-
# منطق المكافأة والعقاب
|
| 170 |
-
# نعدل الوزن فقط إذا كان النموذج "واثقاً" (score > 0.6)
|
| 171 |
if score > 0.6:
|
| 172 |
if is_win:
|
| 173 |
-
# النموذج كان واثقاً وأصاب -> زيادة الوزن
|
| 174 |
new_w = min(self.MAX_WEIGHT, current_w + self.TACTICAL_LEARNING_RATE)
|
| 175 |
change = "⬆️"
|
| 176 |
else:
|
| 177 |
-
# النموذج كان واثقاً وأخطأ -> تقليل الوزن
|
| 178 |
new_w = max(self.MIN_WEIGHT, current_w - self.TACTICAL_LEARNING_RATE)
|
| 179 |
change = "⬇️"
|
| 180 |
|
|
@@ -183,7 +174,6 @@ class AdaptiveHub:
|
|
| 183 |
|
| 184 |
if changes_log:
|
| 185 |
print(f" -> Adjustments: {', '.join(changes_log)}")
|
| 186 |
-
# إعادة الحقن وحفظ الحالة
|
| 187 |
self._inject_current_parameters()
|
| 188 |
await self._save_state_to_r2()
|
| 189 |
else:
|
|
@@ -194,26 +184,29 @@ class AdaptiveHub:
|
|
| 194 |
traceback.print_exc()
|
| 195 |
|
| 196 |
# ==========================================================================
|
| 197 |
-
# 💉 Parameter Injection (The
|
| 198 |
# ==========================================================================
|
| 199 |
def _inject_current_parameters(self):
|
| 200 |
"""
|
| 201 |
نقل الإعدادات من الـ DNA النشط إلى SystemLimits
|
| 202 |
-
ليستخدمها Processor و DataManager
|
| 203 |
"""
|
|
|
|
|
|
|
|
|
|
|
|
|
| 204 |
active_dna = self.strategies[self.current_market_regime]
|
| 205 |
|
| 206 |
print(f"💉 [AdaptiveHub] Injecting DNA for regime: {self.current_market_regime}")
|
| 207 |
|
| 208 |
# 1. حقن أوزان الطبقة الثانية (L2 Weights)
|
| 209 |
-
# ملاحظة: نقوم بتطبيع الأوزان (Normalization) لتساوي 1.0 تقريباً
|
| 210 |
mw = active_dna.model_weights
|
| 211 |
total_w = sum(mw.values()) if sum(mw.values()) > 0 else 1.0
|
| 212 |
|
| 213 |
SystemLimits.L2_WEIGHT_TITAN = mw.get("titan", 0.4) / total_w
|
| 214 |
SystemLimits.L2_WEIGHT_PATTERNS = mw.get("patterns", 0.3) / total_w
|
| 215 |
-
|
| 216 |
-
#
|
| 217 |
|
| 218 |
# 2. حقن عتبات الفلتر الأولي (L1)
|
| 219 |
SystemLimits.L1_MIN_AFFINITY_SCORE = active_dna.filters.get("l1_min_score", 20.0)
|
|
@@ -221,19 +214,26 @@ class AdaptiveHub:
|
|
| 221 |
# 3. حقن عتبات الثقة (L3 Oracle)
|
| 222 |
SystemLimits.L3_CONFIDENCE_THRESHOLD = active_dna.filters.get("l3_conf_thresh", 0.65)
|
| 223 |
|
| 224 |
-
# 4. حقن إعدادات دفتر الطلبات (
|
| 225 |
-
# سنحتاج لقراءة هذه القيم من SystemLimits داخل SniperEngine
|
| 226 |
SystemLimits.L4_OB_WALL_RATIO = active_dna.ob_settings.get("wall_ratio_limit", 0.4)
|
| 227 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 228 |
# طباعة الملخص
|
| 229 |
-
print(f" -> Weights:
|
| 230 |
-
print(f" ->
|
| 231 |
|
| 232 |
# ==========================================================================
|
| 233 |
# 🎮 External Control & Utilities
|
| 234 |
# ==========================================================================
|
| 235 |
def update_market_regime(self, new_regime: str):
|
| 236 |
-
"""تغيير حالة السوق يدوياً أو آلياً"""
|
| 237 |
if new_regime in self.strategies:
|
| 238 |
self.current_market_regime = new_regime
|
| 239 |
print(f"🔄 [AdaptiveHub] Regime Switched to: {new_regime}")
|
|
@@ -242,16 +242,15 @@ class AdaptiveHub:
|
|
| 242 |
print(f"⚠️ [AdaptiveHub] Unknown regime: {new_regime}")
|
| 243 |
|
| 244 |
def get_status(self):
|
| 245 |
-
dna = self.strategies
|
|
|
|
| 246 |
mw = dna.model_weights
|
|
|
|
| 247 |
return (f"Regime: {self.current_market_regime} | "
|
| 248 |
-
f"W[Ti:{mw.get('titan'):.2f}
|
|
|
|
| 249 |
f"Wins: {dna.stats['wins']}")
|
| 250 |
|
| 251 |
-
def get_active_ob_settings(self):
|
| 252 |
-
"""دالة مساعدة لـ SniperEngine لجلب إعدادات الـ OB الحالية"""
|
| 253 |
-
return self.strategies[self.current_market_regime].ob_settings
|
| 254 |
-
|
| 255 |
async def _save_state_to_r2(self):
|
| 256 |
if not self.r2: return
|
| 257 |
try:
|
|
|
|
| 1 |
# ==============================================================================
|
| 2 |
# 🧠 learning_hub/adaptive_hub.py
|
| 3 |
+
# (V45.0 - GEM-Architect: The Cybernetic Strategy Core & Guardian Link)
|
| 4 |
# ==============================================================================
|
| 5 |
+
# التحديثات:
|
| 6 |
+
# 1. دعم حقن إعدادات الحراس (Guardians) القادمة من الباكتست.
|
| 7 |
+
# 2. ضمان تحميل وحفظ كافة المتغيرات الجديدة في StrategyDNA.
|
|
|
|
| 8 |
# ==============================================================================
|
| 9 |
|
| 10 |
import json
|
|
|
|
| 14 |
from collections import deque
|
| 15 |
from typing import Dict, Any, List, Optional
|
| 16 |
|
| 17 |
+
# استيراد الحدود المركزية (The Shared Whiteboard)
|
| 18 |
from ml_engine.processor import SystemLimits
|
| 19 |
|
| 20 |
class StrategyDNA:
|
|
|
|
| 22 |
تعريف هيكلية البيانات لكل استراتيجية.
|
| 23 |
هذا هو 'الجينوم' الذي سيتم تعديله بواسطة التعلم.
|
| 24 |
"""
|
| 25 |
+
def __init__(self, name, model_weights, ob_settings, filters, guard_settings=None):
|
| 26 |
self.name = name
|
| 27 |
self.model_weights = model_weights # أوزان النماذج (Titan, Sniper, etc.)
|
| 28 |
self.ob_settings = ob_settings # إعدادات دفتر الطلبات (Wall Ratio, etc.)
|
| 29 |
self.filters = filters # فلاتر L1 (Thresholds)
|
| 30 |
+
# ✅ إضافة إعدادات الحراس (جديد)
|
| 31 |
+
self.guard_settings = guard_settings if guard_settings else {}
|
| 32 |
self.stats = {"wins": 0, "losses": 0, "win_rate": 0.0}
|
| 33 |
|
| 34 |
def to_dict(self):
|
|
|
|
| 39 |
self.r2 = r2_service
|
| 40 |
self.dna_file_key = "learning/strategic_dna_v2.json"
|
| 41 |
|
| 42 |
+
# الحالة الحالية للسوق
|
| 43 |
self.current_market_regime = "RANGE"
|
| 44 |
|
| 45 |
+
# مخزن الحمض النووي
|
| 46 |
self.strategies: Dict[str, StrategyDNA] = {}
|
| 47 |
|
| 48 |
+
# معدل التعلم التكتيكي
|
| 49 |
+
self.TACTICAL_LEARNING_RATE = 0.05
|
| 50 |
self.MIN_WEIGHT = 0.10
|
| 51 |
self.MAX_WEIGHT = 0.90
|
| 52 |
|
| 53 |
+
print("🧠 [AdaptiveHub V45.0] Cybernetic Strategy Core Initialized.")
|
| 54 |
|
| 55 |
async def initialize(self):
|
| 56 |
"""تحميل الـ DNA من R2 أو إنشاء الافتراضي"""
|
|
|
|
| 68 |
else:
|
| 69 |
self._create_default_dna()
|
| 70 |
|
| 71 |
+
# تطبيق الإعدادات فوراً (Hot Reload)
|
| 72 |
self._inject_current_parameters()
|
| 73 |
|
| 74 |
except Exception as e:
|
| 75 |
print(f"❌ [AdaptiveHub] Init Failed: {e}")
|
| 76 |
+
traceback.print_exc()
|
| 77 |
self._create_default_dna()
|
| 78 |
|
| 79 |
def _create_default_dna(self):
|
| 80 |
+
"""إنشاء الإعدادات الافتراضية (في حال عدم وجود ملف)"""
|
| 81 |
+
# قيم افتراضية للحراس
|
| 82 |
+
default_guards = {
|
| 83 |
+
"hydra_crash": 0.60, "hydra_giveback": 0.70,
|
| 84 |
+
"legacy_v2": 0.95, "legacy_v3": 0.95
|
| 85 |
+
}
|
| 86 |
+
|
| 87 |
self.strategies["BULL"] = StrategyDNA(
|
| 88 |
name="BULL",
|
| 89 |
+
model_weights={"titan": 0.40, "patterns": 0.30, "sniper": 0.20, "hydra": 0.10, "mc": 0.0},
|
| 90 |
+
ob_settings={"wall_ratio_limit": 0.60, "imbalance_thresh": 0.5},
|
| 91 |
+
filters={"l1_min_score": 15.0, "l3_conf_thresh": 0.60},
|
| 92 |
+
guard_settings=default_guards
|
| 93 |
)
|
| 94 |
|
|
|
|
| 95 |
self.strategies["BEAR"] = StrategyDNA(
|
| 96 |
name="BEAR",
|
| 97 |
+
model_weights={"titan": 0.20, "patterns": 0.10, "sniper": 0.30, "hydra": 0.40, "mc": 0.0},
|
| 98 |
+
ob_settings={"wall_ratio_limit": 0.30, "imbalance_thresh": 0.7},
|
| 99 |
+
filters={"l1_min_score": 40.0, "l3_conf_thresh": 0.75},
|
| 100 |
+
guard_settings=default_guards
|
| 101 |
)
|
| 102 |
|
|
|
|
| 103 |
self.strategies["RANGE"] = StrategyDNA(
|
| 104 |
name="RANGE",
|
| 105 |
+
model_weights={"titan": 0.30, "patterns": 0.40, "sniper": 0.20, "hydra": 0.10, "mc": 0.0},
|
| 106 |
ob_settings={"wall_ratio_limit": 0.40, "imbalance_thresh": 0.6},
|
| 107 |
+
filters={"l1_min_score": 25.0, "l3_conf_thresh": 0.65},
|
| 108 |
+
guard_settings=default_guards
|
| 109 |
)
|
| 110 |
+
|
|
|
|
| 111 |
self.strategies["DEAD"] = StrategyDNA(
|
| 112 |
name="DEAD",
|
| 113 |
+
model_weights={"titan": 0.25, "patterns": 0.25, "sniper": 0.25, "hydra": 0.25, "mc": 0.0},
|
| 114 |
+
ob_settings={"wall_ratio_limit": 0.20, "imbalance_thresh": 0.8},
|
| 115 |
+
filters={"l1_min_score": 50.0, "l3_conf_thresh": 0.80},
|
| 116 |
+
guard_settings=default_guards
|
| 117 |
)
|
| 118 |
|
| 119 |
def _load_from_dict(self, data):
|
| 120 |
+
"""تحويل JSON إلى كائنات StrategyDNA مع دعم الحقول الجديدة"""
|
| 121 |
for key, val in data.get("strategies", {}).items():
|
| 122 |
self.strategies[key] = StrategyDNA(
|
| 123 |
name=val["name"],
|
| 124 |
model_weights=val["model_weights"],
|
| 125 |
ob_settings=val["ob_settings"],
|
| 126 |
+
filters=val["filters"],
|
| 127 |
+
guard_settings=val.get("guard_settings", {}) # ✅ تحميل إعدادات الحراس
|
| 128 |
)
|
| 129 |
self.strategies[key].stats = val.get("stats", {"wins":0, "losses":0})
|
| 130 |
|
|
|
|
| 134 |
# ⚡ The Tactical Loop: Real-time Weight Adjustment
|
| 135 |
# ==========================================================================
|
| 136 |
async def register_trade_outcome(self, trade_data: Dict[str, Any]):
|
|
|
|
|
|
|
|
|
|
|
|
|
| 137 |
try:
|
| 138 |
pnl = trade_data.get('profit_pct', 0.0)
|
| 139 |
is_win = pnl > 0
|
| 140 |
|
|
|
|
| 141 |
active_dna = self.strategies[self.current_market_regime]
|
| 142 |
|
|
|
|
| 143 |
if is_win: active_dna.stats["wins"] += 1
|
| 144 |
else: active_dna.stats["losses"] += 1
|
| 145 |
|
|
|
|
|
|
|
| 146 |
decision_data = trade_data.get('decision_data', {})
|
| 147 |
+
components = decision_data.get('components', {})
|
|
|
|
|
|
|
|
|
|
|
|
|
| 148 |
|
| 149 |
print(f"⚖️ [Tactical Learning] Adjusting weights for {self.current_market_regime}...")
|
| 150 |
|
| 151 |
changes_log = []
|
| 152 |
|
|
|
|
| 153 |
model_keys = {
|
| 154 |
'titan_score': 'titan',
|
| 155 |
'patterns_score': 'patterns',
|
| 156 |
+
'sniper_score': 'sniper',
|
|
|
|
| 157 |
'hydra_score': 'hydra'
|
| 158 |
}
|
| 159 |
|
|
|
|
| 161 |
score = float(components.get(score_key, 0.5))
|
| 162 |
current_w = active_dna.model_weights.get(model_name, 0.25)
|
| 163 |
|
|
|
|
|
|
|
| 164 |
if score > 0.6:
|
| 165 |
if is_win:
|
|
|
|
| 166 |
new_w = min(self.MAX_WEIGHT, current_w + self.TACTICAL_LEARNING_RATE)
|
| 167 |
change = "⬆️"
|
| 168 |
else:
|
|
|
|
| 169 |
new_w = max(self.MIN_WEIGHT, current_w - self.TACTICAL_LEARNING_RATE)
|
| 170 |
change = "⬇️"
|
| 171 |
|
|
|
|
| 174 |
|
| 175 |
if changes_log:
|
| 176 |
print(f" -> Adjustments: {', '.join(changes_log)}")
|
|
|
|
| 177 |
self._inject_current_parameters()
|
| 178 |
await self._save_state_to_r2()
|
| 179 |
else:
|
|
|
|
| 184 |
traceback.print_exc()
|
| 185 |
|
| 186 |
# ==========================================================================
|
| 187 |
+
# 💉 Parameter Injection (The Vital Link)
|
| 188 |
# ==========================================================================
|
| 189 |
def _inject_current_parameters(self):
|
| 190 |
"""
|
| 191 |
نقل الإعدادات من الـ DNA النشط إلى SystemLimits
|
| 192 |
+
ليستخدمها Processor و DataManager والحراس.
|
| 193 |
"""
|
| 194 |
+
if self.current_market_regime not in self.strategies:
|
| 195 |
+
print(f"⚠️ [AdaptiveHub] Regime {self.current_market_regime} not found in strategies.")
|
| 196 |
+
return
|
| 197 |
+
|
| 198 |
active_dna = self.strategies[self.current_market_regime]
|
| 199 |
|
| 200 |
print(f"💉 [AdaptiveHub] Injecting DNA for regime: {self.current_market_regime}")
|
| 201 |
|
| 202 |
# 1. حقن أوزان الطبقة الثانية (L2 Weights)
|
|
|
|
| 203 |
mw = active_dna.model_weights
|
| 204 |
total_w = sum(mw.values()) if sum(mw.values()) > 0 else 1.0
|
| 205 |
|
| 206 |
SystemLimits.L2_WEIGHT_TITAN = mw.get("titan", 0.4) / total_w
|
| 207 |
SystemLimits.L2_WEIGHT_PATTERNS = mw.get("patterns", 0.3) / total_w
|
| 208 |
+
SystemLimits.L2_WEIGHT_MC = mw.get("mc", 0.1) / total_w
|
| 209 |
+
# Sniper/Hydra weights can be used here or in their respective logic
|
| 210 |
|
| 211 |
# 2. حقن عتبات الفلتر الأولي (L1)
|
| 212 |
SystemLimits.L1_MIN_AFFINITY_SCORE = active_dna.filters.get("l1_min_score", 20.0)
|
|
|
|
| 214 |
# 3. حقن عتبات الثقة (L3 Oracle)
|
| 215 |
SystemLimits.L3_CONFIDENCE_THRESHOLD = active_dna.filters.get("l3_conf_thresh", 0.65)
|
| 216 |
|
| 217 |
+
# 4. حقن إعدادات دفتر الطلبات (Sniper)
|
|
|
|
| 218 |
SystemLimits.L4_OB_WALL_RATIO = active_dna.ob_settings.get("wall_ratio_limit", 0.4)
|
| 219 |
|
| 220 |
+
# 5. 🔥 حقن إعدادات الحراس (الجديد)
|
| 221 |
+
gs = active_dna.guard_settings
|
| 222 |
+
if gs:
|
| 223 |
+
SystemLimits.HYDRA_CRASH_THRESH = gs.get('hydra_crash', 0.60)
|
| 224 |
+
SystemLimits.HYDRA_GIVEBACK_THRESH = gs.get('hydra_giveback', 0.70)
|
| 225 |
+
SystemLimits.LEGACY_V2_PANIC_THRESH = gs.get('legacy_v2', 0.95)
|
| 226 |
+
SystemLimits.LEGACY_V3_HARD_THRESH = gs.get('legacy_v3', 0.95)
|
| 227 |
+
print(f" 🛡️ Guards Updated: Hydra(C:{SystemLimits.HYDRA_CRASH_THRESH}/G:{SystemLimits.HYDRA_GIVEBACK_THRESH}) | Legacy(V2:{SystemLimits.LEGACY_V2_PANIC_THRESH})")
|
| 228 |
+
|
| 229 |
# طباعة الملخص
|
| 230 |
+
print(f" -> Weights: Ti={SystemLimits.L2_WEIGHT_TITAN:.2f}, Pat={SystemLimits.L2_WEIGHT_PATTERNS:.2f}")
|
| 231 |
+
print(f" -> L1 Thresh: {SystemLimits.L1_MIN_AFFINITY_SCORE}")
|
| 232 |
|
| 233 |
# ==========================================================================
|
| 234 |
# 🎮 External Control & Utilities
|
| 235 |
# ==========================================================================
|
| 236 |
def update_market_regime(self, new_regime: str):
|
|
|
|
| 237 |
if new_regime in self.strategies:
|
| 238 |
self.current_market_regime = new_regime
|
| 239 |
print(f"🔄 [AdaptiveHub] Regime Switched to: {new_regime}")
|
|
|
|
| 242 |
print(f"⚠️ [AdaptiveHub] Unknown regime: {new_regime}")
|
| 243 |
|
| 244 |
def get_status(self):
|
| 245 |
+
dna = self.strategies.get(self.current_market_regime)
|
| 246 |
+
if not dna: return "System Initializing..."
|
| 247 |
mw = dna.model_weights
|
| 248 |
+
gs = dna.guard_settings
|
| 249 |
return (f"Regime: {self.current_market_regime} | "
|
| 250 |
+
f"W[Ti:{mw.get('titan'):.2f}] | "
|
| 251 |
+
f"G[Hyd:{gs.get('hydra_crash',0.6):.2f}] | "
|
| 252 |
f"Wins: {dna.stats['wins']}")
|
| 253 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 254 |
async def _save_state_to_r2(self):
|
| 255 |
if not self.r2: return
|
| 256 |
try:
|