feat: Complete 7-feature production migration

.env.example

@@ -6,7 +6,7 @@ JUDGE_BACKEND=stub
 # LLM Judge (only used when JUDGE_BACKEND=llm)
 OLLAMA_HOST=http://localhost:11434
 JUDGE_MODEL=llama3.2:1b
-JUDGE_TIMEOUT_SECS=12
+JUDGE_TIMEOUT_SECS=60
 
 # ============================================================
 # MODEL SERVICE CONFIGURATION
@@ -15,17 +15,17 @@ JUDGE_TIMEOUT_SECS=12
 # Configuration file path
 CONFIG_PATH=configs/dev/config.yaml
 
-# Primary model (8-feature production model)
-PRIMARY_MODEL_PATH=models/dev/model_8feat.pkl
-PRIMARY_META_PATH=models/dev/model_8feat_meta.json
+# Primary model (7-feature production model)
+PRIMARY_MODEL_PATH=models/dev/model_7feat.pkl
+PRIMARY_META_PATH=models/dev/model_7feat_meta.json
 
 # Shadow testing (DISABLED for production)
 SHADOW_ENABLED=false
-SHADOW_MODEL_PATH=models/dev/model_7feat.pkl
-SHADOW_META_PATH=models/dev/model_7feat_meta.json
+SHADOW_MODEL_PATH=models/dev/model_8feat.pkl
+SHADOW_META_PATH=models/dev/model_8feat_meta.json
 
 # Service URLs
-MODEL_SVC_URL=http://localhost:9000
+MODEL_SVC_URL=http://localhost:8002
 GATEWAY_PORT=8000
 MODEL_SVC_PORT=9000
 

configs/dev/config.yaml

@@ -6,18 +6,18 @@
 model_service:
   # Primary model (production)
   primary:
-    path: "models/dev/model_8feat.pkl"
-    meta_path: "models/dev/model_8feat_meta.json"
-    name: "8-feature-production-v1"
-    description: "8-feature URL model with IsHTTPS (PR-AUC: 99.92%)"
-  
+    path: "models/dev/model_7feat.pkl"
+    meta_path: "models/dev/model_7feat_meta.json"
+    name: "7-feature-production-v1"
+    description: "7-feature URL model without IsHTTPS (PR-AUC: 99.88%)"
+
   # Shadow model (DISABLED for production)
   shadow:
     enabled: false
-    path: "models/dev/model_7feat.pkl"
-    meta_path: "models/dev/model_7feat_meta.json"
-    name: "7-feature-baseline"
-    description: "7-feature URL model without IsHTTPS (research only)"
+    path: "models/dev/model_8feat.pkl"
+    meta_path: "models/dev/model_8feat_meta.json"
+    name: "8-feature-baseline"
+    description: "8-feature URL model with IsHTTPS (research only)"
     log_path: "outputs/shadow_predictions.jsonl"
 
 # Gateway Configuration

configs/dev/thresholds.json

@@ -1,12 +1,27 @@
 {
-  "optimal_threshold": 0.35,
-  "gray_zone_low": 0.004,
-  "gray_zone_high": 0.9990000000000006,
-  "gray_zone_rate": 0.10936468383276894,
-  "f1_score_at_optimal": 0.002766509680600472,
-  "decision_distribution": {
-    "allow_rate": 0.48099162992780015,
-    "review_rate": 0.10936468383276894,
-    "block_rate": 0.4096436862394309
-  }
+  "model": "xgb",
+  "class_mapping": {
+    "phish": 0,
+    "legit": 1
+  },
+  "calibration": {
+    "method": "isotonic",
+    "cv": 5
+  },
+  "thresholds": {
+    "optimal_threshold": 0.49999999999999994,
+    "gray_zone_low": 0.011,
+    "gray_zone_high": 0.9979999999999727,
+    "gray_zone_rate": 0.11994973697101356,
+    "f1_score_at_optimal": 0.9939829924548755,
+    "decision_distribution": {
+      "allow_rate": 0.5199241794986476,
+      "review_rate": 0.11994973697101356,
+      "block_rate": 0.36012608353033887
+    }
+  },
+  "data": {
+    "file": "data\\processed\\phiusiil_features_v2.csv"
+  },
+  "seed": 42
 }

configs/dev/thresholds_7feat.json

@@ -0,0 +1,33 @@
+{
+  "model": "xgb_7feat",
+  "features": [
+    "TLDLegitimateProb",
+    "CharContinuationRate",
+    "SpacialCharRatioInURL",
+    "URLCharProb",
+    "LetterRatioInURL",
+    "NoOfOtherSpecialCharsInURL",
+    "DomainLength"
+  ],
+  "class_mapping": {
+    "phish": 0,
+    "legit": 1
+  },
+  "calibration": {
+    "method": "isotonic",
+    "cv": 5
+  },
+  "thresholds": {
+    "optimal_threshold": 0.49999999999999994,
+    "gray_zone_low": 0.011,
+    "gray_zone_high": 0.9979999999999727,
+    "gray_zone_rate": 0.11994973697101356,
+    "f1_score_at_optimal": 0.9939829924548755,
+    "decision_distribution": {
+      "allow_rate": 0.5199241794986476,
+      "review_rate": 0.11994973697101356,
+      "block_rate": 0.36012608353033887
+    }
+  },
+  "seed": 42
+}

configs/dev/thresholds_8feat.json

@@ -1,14 +1,14 @@
 {
   "model": "xgb_8feat",
   "features": [
-    "IsHTTPS",
     "TLDLegitimateProb",
     "CharContinuationRate",
     "SpacialCharRatioInURL",
     "URLCharProb",
     "LetterRatioInURL",
     "NoOfOtherSpecialCharsInURL",
-    "DomainLength"
+    "DomainLength",
+    "IsHTTPS"
   ],
   "class_mapping": {
     "phish": 0,
@@ -19,16 +19,11 @@
     "cv": 5
   },
   "thresholds": {
-    "optimal_threshold": 0.35,
-    "gray_zone_low": 0.004,
-    "gray_zone_high": 0.9990000000000006,
-    "gray_zone_rate": 0.10936468383276894,
-    "f1_score_at_optimal": 0.002766509680600472,
-    "decision_distribution": {
-      "allow_rate": 0.48099162992780015,
-      "review_rate": 0.10936468383276894,
-      "block_rate": 0.4096436862394309
-    }
+    "optimal_threshold": 0.3599999999999999,
+    "gray_zone_low": 0.003,
+    "gray_zone_high": 0.3599999999999999,
+    "gray_zone_rate": 0.13355909100589952,
+    "f1_score_at_optimal": 0.9971890180308938
   },
   "seed": 42
 }