Update ml_engine/processor.py

ml_engine/processor.py

@@ -1,5 +1,6 @@
 # ============================================================
-# 🧠 ml_engine/processor.py (V36.0 - GEM-Architect: The Cybernetic Processor)
+# 🧠 ml_engine/processor.py 
+# (V37.0 - GEM-Architect: Context-Aware Cybernetic Processor)
 # ============================================================
 
 import asyncio
@@ -40,23 +41,22 @@ MODEL_V3_PATH = os.path.join(BASE_DIR, "ml_models", "DeepSteward_V3_Production.j
 MODEL_V3_FEAT = os.path.join(BASE_DIR, "ml_models", "DeepSteward_V3_Features.json")
 
 # ============================================================
-# 🎛️ SYSTEM LIMITS & THRESHOLDS (Dynamic DNA Container)
+# 🎛️ SYSTEM LIMITS & THRESHOLDS (Fallback / Global)
 # ============================================================
 class SystemLimits:
     """
     GEM-Architect: The Dynamic Constitution.
-    يتم تحديث هذه القيم آلياً بواسطة AdaptiveHub بناءً على حالة السوق (Bull/Bear/etc).
+    يتم تحديث هذه القيم آلياً بواسطة AdaptiveHub وتستخدم كقيم احتياطية (Fallback)
+    في حال لم يتم توفير dynamic_limits للعملة.
     """
     
     # --- Layer 1 (Data Manager Control) ---
-    L1_MIN_AFFINITY_SCORE = 15.0  # سيتم الكتابة عليها من الـ DNA
+    L1_MIN_AFFINITY_SCORE = 15.0  
     
     # --- Layer 2 Weights (Dynamic) ---
-    # هذه الأوزان تتغير حسب أداء النماذج (Tactical Loop) وحالة السوق
     L2_WEIGHT_TITAN    = 0.40
     L2_WEIGHT_PATTERNS = 0.30
     L2_WEIGHT_MC       = 0.10
-    # (Hydra/Sniper قد يساهمون في L2 أو L4 حسب التصميم)
 
     # إعدادات الأنماط (تتغير حسب الاستراتيجية)
     PATTERN_TF_WEIGHTS = {'15m': 0.40, '1h': 0.30, '5m': 0.20, '4h': 0.10, '1d': 0.00}
@@ -71,10 +71,8 @@ class SystemLimits:
 
     # --- Layer 4 (Sniper & Execution) ---
     L4_ENTRY_THRESHOLD  = 0.40
-    # أوزان داخلية لـ Sniper (ML vs OrderBook)
     L4_WEIGHT_ML        = 0.60
     L4_WEIGHT_OB        = 0.40
-    # نسبة الجدار المسموح بها (تتغير جذرياً بين Bull و Bear)
     L4_OB_WALL_RATIO    = 0.40
 
     # --- Layer 0: Hydra & Guardian Thresholds ---
@@ -94,12 +92,10 @@ class SystemLimits:
 
     @classmethod
     def update_from_dict(cls, config: Dict[str, Any]):
-        """تحديث القيم من AdaptiveHub"""
         if not config: return
         for k, v in config.items():
             if hasattr(cls, k): 
                 setattr(cls, k, v)
-        # print(f"🔄 [SystemLimits] Updated. TitanW={cls.L2_WEIGHT_TITAN:.2f}, WallRatio={cls.L4_OB_WALL_RATIO}")
 
 # ============================================================
 # 🧠 MLProcessor Class
@@ -127,7 +123,7 @@ class MLProcessor:
                 v3_features_map_path=MODEL_V3_FEAT
             )
 
-        print(f"🧠 [MLProcessor V36.0] Cybernetic Control Active.")
+        print(f"🧠 [MLProcessor V37.0] Context-Aware Cybernetics Active.")
 
     async def initialize(self):
         if self.initialized: return
@@ -137,7 +133,6 @@ class MLProcessor:
             if self.titan: tasks.append(self.titan.initialize())
             
             if self.pattern_engine: 
-                # التكوين الأولي (سيتم تحديثه لاحقاً ديناميكياً)
                 self.pattern_engine.configure_thresholds(
                     weights=SystemLimits.PATTERN_TF_WEIGHTS, 
                     bull_thresh=SystemLimits.PATTERN_THRESH_BULLISH, 
@@ -151,7 +146,6 @@ class MLProcessor:
                 tasks.append(self.oracle.initialize())
             
             if self.sniper: 
-                # التكوين الأولي
                 if hasattr(self.sniper, 'configure_settings'): 
                     self.sniper.configure_settings(
                         threshold=SystemLimits.L4_ENTRY_THRESHOLD, 
@@ -173,7 +167,6 @@ class MLProcessor:
                 else:
                     self.guardian_legacy.initialize()
                 
-                # تطبيق العتبات المبدئية
                 self.guardian_legacy.configure_thresholds(
                     v2_panic=SystemLimits.LEGACY_V2_PANIC_THRESH,
                     v3_hard=SystemLimits.LEGACY_V3_HARD_THRESH,
@@ -192,7 +185,8 @@ class MLProcessor:
     async def process_compound_signal(self, raw_data: Dict[str, Any]) -> Optional[Dict[str, Any]]:
         """
         L2 Processing:
-        هنا يتم دمج الدرجات بناءً على الأوزان الديناميكية الحالية (SystemLimits).
+        Uses 'dynamic_limits' from raw_data if available (Per-Asset Overrides),
+        otherwise falls back to SystemLimits (Global).
         """
         if not self.initialized: await self.initialize()
         
@@ -200,6 +194,9 @@ class MLProcessor:
         ohlcv_data = raw_data.get('ohlcv')
         current_price = raw_data.get('current_price', 0.0)
         
+        # ✅ EXTRACT DYNAMIC LIMITS (Priority: Local > Global)
+        limits = raw_data.get('dynamic_limits', {})
+        
         if not symbol or not ohlcv_data: return None
         
         try:
@@ -210,12 +207,12 @@ class MLProcessor:
                 titan_res = await asyncio.to_thread(self.titan.predict, ohlcv_data)
                 score_titan = titan_res.get('score', 0.5)
 
-            # 2. Pattern Engine (Inject Dynamic Config First)
+            # 2. Pattern Engine
             score_patterns = 0.5
             pattern_res = {}
             pattern_name = "Neutral"
             if self.pattern_engine:
-                # تحديث التكوين قبل التحليل لضمان استخدام أحدث أوزان الاستراتيجية
+                # Use Global config for pattern internal TFs for now
                 self.pattern_engine.configure_thresholds(
                     weights=SystemLimits.PATTERN_TF_WEIGHTS,
                     bull_thresh=SystemLimits.PATTERN_THRESH_BULLISH,
@@ -233,13 +230,11 @@ class MLProcessor:
                 mc_score = 0.5 + (raw_mc * 5.0)
                 mc_score = max(0.0, min(1.0, mc_score))
 
-            # 4. Hybrid Calculation (Using Dynamic Weights from SystemLimits)
-            # هذه الأوزان يتم تحديثها بواسطة AdaptiveHub
-            w_titan = SystemLimits.L2_WEIGHT_TITAN
-            w_patt = SystemLimits.L2_WEIGHT_PATTERNS
-            w_mc = SystemLimits.L2_WEIGHT_MC
+            # 4. Hybrid Calculation (USING DYNAMIC WEIGHTS)
+            w_titan = limits.get('w_titan', SystemLimits.L2_WEIGHT_TITAN)
+            w_patt = limits.get('w_patt', SystemLimits.L2_WEIGHT_PATTERNS)
+            w_mc = SystemLimits.L2_WEIGHT_MC 
             
-            # تطبيع الأوزان (لضمان أن مجموعها 1.0 تقريباً)
             total_w = w_titan + w_patt + w_mc
             if total_w <= 0: total_w = 1.0
             
@@ -248,7 +243,10 @@ class MLProcessor:
             return {
                 'symbol': symbol, 
                 'current_price': current_price, 
-                'enhanced_final_score': hybrid_score, 
+                'enhanced_final_score': hybrid_score,
+                # Pass limits forward for next layers
+                'dynamic_limits': limits,
+                'asset_regime': raw_data.get('asset_regime', 'UNKNOWN'),
                 'titan_score': score_titan, 
                 'patterns_score': score_patterns, 
                 'mc_score': mc_score, 
@@ -269,39 +267,48 @@ class MLProcessor:
     async def consult_oracle(self, symbol_data: Dict[str, Any]) -> Dict[str, Any]:
         """
         L3 Processing:
-        Oracle يستخدم العتبة الحالية من SystemLimits.
+        Oracle uses specific threshold from dynamic_limits (Per-Asset).
         """
         if not self.initialized: await self.initialize()
         
+        # ✅ EXTRACT DYNAMIC THRESHOLD
+        limits = symbol_data.get('dynamic_limits', {})
+        threshold = limits.get('l3_oracle_thresh', SystemLimits.L3_CONFIDENCE_THRESHOLD)
+        
         if self.oracle:
-            # تحديث العتبة ديناميكياً
             if hasattr(self.oracle, 'set_threshold'):
-                self.oracle.set_threshold(SystemLimits.L3_CONFIDENCE_THRESHOLD)
+                self.oracle.set_threshold(threshold)
                 
             decision = await self.oracle.predict(symbol_data)
             conf = decision.get('confidence', 0.0)
             
-            # طبقة أمان إضافية (Redundant Safety)
-            if decision.get('action') in ['WATCH', 'BUY'] and conf < SystemLimits.L3_CONFIDENCE_THRESHOLD:
+            # Dynamic Veto based on Context
+            if decision.get('action') in ['WATCH', 'BUY'] and conf < threshold:
                 decision['action'] = 'WAIT'
-                decision['reason'] = f"Processor Veto: Conf {conf:.2f} < Limit {SystemLimits.L3_CONFIDENCE_THRESHOLD}"
+                decision['reason'] = f"Context Veto: Conf {conf:.2f} < Limit {threshold:.2f} ({limits.get('regime','Global')})"
             
             return decision
         return {'action': 'WAIT', 'reason': 'Oracle Engine Missing'}
 
-    async def check_sniper_entry(self, ohlcv_1m_data: List, order_book_data: Dict[str, Any]) -> Dict[str, Any]:
+    async def check_sniper_entry(self, ohlcv_1m_data: List, order_book_data: Dict[str, Any], context_data: Dict = None) -> Dict[str, Any]:
         """
         L4 Processing:
-        Sniper يستلم إعدادات دفتر الطلبات (DNA) قبل اتخاذ القرار.
+        Sniper uses specific wall ratio and thresholds from dynamic_limits.
         """
         if not self.initialized: await self.initialize()
         
+        # ✅ EXTRACT DYNAMIC CONFIG
+        limits = context_data.get('dynamic_limits', {}) if context_data else {}
+        
+        thresh = limits.get('l4_sniper_thresh', SystemLimits.L4_ENTRY_THRESHOLD)
+        wall_r = limits.get('l4_ob_wall_ratio', SystemLimits.L4_OB_WALL_RATIO)
+
         if self.sniper: 
-            # ✅ الحقن الديناميكي لإعدادات Sniper قبل التنفيذ
+            # Inject Dynamic Config before check
             if hasattr(self.sniper, 'configure_settings'):
                 self.sniper.configure_settings(
-                    threshold=SystemLimits.L4_ENTRY_THRESHOLD,
-                    wall_ratio=SystemLimits.L4_OB_WALL_RATIO,
+                    threshold=thresh,
+                    wall_ratio=wall_r,
                     w_ml=SystemLimits.L4_WEIGHT_ML,
                     w_ob=SystemLimits.L4_WEIGHT_OB
                 )
@@ -313,7 +320,8 @@ class MLProcessor:
     def consult_dual_guardians(self, symbol, ohlcv_1m, ohlcv_5m, ohlcv_15m, trade_context, order_book_snapshot=None):
         """
         L0 Guardians:
-        الحراس يستخدمون العتبات الديناميكية (Panic Thresholds) التي قد تختلف بين Bull و Bear.
+        Ideally, trade_context should also carry 'dynamic_limits' if we want per-asset guarding.
+        For now, we use Global SystemLimits which are updated by AdaptiveHub to reflect 'General Market State'.
         """
         response = {'action': 'HOLD', 'detailed_log': '', 'probs': {}}
         
@@ -325,7 +333,7 @@ class MLProcessor:
             p_crash = h_probs.get('crash', 0.0)
             p_giveback = h_probs.get('giveback', 0.0)
             
-            # استخدام العتبات الحية
+            # Using Global SystemLimits (updated by Hub)
             if hydra_result['action'] == 'HOLD':
                 if p_crash >= SystemLimits.HYDRA_CRASH_THRESH:
                     hydra_result['action'] = 'EXIT_HARD'
@@ -337,7 +345,6 @@ class MLProcessor:
         # 2. Legacy (Volume-Aware Veto)
         legacy_result = {'action': 'HOLD', 'reason': 'Disabled', 'scores': {}}
         if self.guardian_legacy and self.guardian_legacy.initialized:
-            # تحديث العتبات قبل التحليل
             self.guardian_legacy.configure_thresholds(
                 v2_panic=SystemLimits.LEGACY_V2_PANIC_THRESH,
                 v3_hard=SystemLimits.LEGACY_V3_HARD_THRESH,
@@ -354,7 +361,7 @@ class MLProcessor:
                 volume_30m_usd=vol_30m
             )
 
-        # 3. Final Arbitration & Display
+        # 3. Final Arbitration
         h_probs = hydra_result.get('probs', {})
         l_scores = legacy_result.get('scores', {})