Update context_engine.py

context_engine.py

@@ -1,50 +1,44 @@
 """
 Nexari Context Engine (UPDATED)
+Author: Piyush
 Improvements:
- - Lazy-load emotion pipeline to avoid blocking imports/startup
- - Robust fallback and lighter memory usage
+ - Robust emotion pipeline usage & error handling
+ - Safer fallback when model not available
+ - Returns compact psychological profile instruction
 """
 
-from typing import Tuple
 from transformers import pipeline
-import threading
 
-_emotion_lock = threading.Lock()
-_emotion_classifier = None
-_emotion_checked = False
+print(">>> Context: Loading Emotion Analysis Model...")
+# load with top_k=1 by default
+try:
+    emotion_classifier = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", top_k=1)
+except Exception as e:
+    print(f"Context: Failed to load emotion model: {e}")
+    emotion_classifier = None
 
-def _load_emotion_model():
-    global _emotion_classifier, _emotion_checked
-    with _emotion_lock:
-        if _emotion_checked:
-            return
-        try:
-            _emotion_classifier = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", top_k=1)
-        except Exception as e:
-            print(f"Context: Failed to load emotion model: {e}")
-            _emotion_classifier = None
-        _emotion_checked = True
-
-def _safe_emotion_analysis(text: str) -> Tuple[str, float]:
-    if not _emotion_checked:
-        # spawn a background loader but don't block
-        threading.Thread(target=_load_emotion_model, daemon=True).start()
-        return ("neutral", 0.0)
-    if not _emotion_classifier:
+def _safe_emotion_analysis(text):
+    if not emotion_classifier:
         return ("neutral", 0.0)
     try:
-        res = _emotion_classifier(text)
+        # pipeline may return list of dicts or list-of-lists depending on version
+        res = emotion_classifier(text)
         if isinstance(res, list) and len(res) > 0:
+            # res could be [{'label':..., 'score':...}] or [['label',score],...]
             first = res[0]
             if isinstance(first, dict):
                 return (first.get('label', 'neutral'), float(first.get('score', 0.0)))
             elif isinstance(first, list) and len(first) > 0 and isinstance(first[0], dict):
                 return (first[0].get('label', 'neutral'), float(first[0].get('score', 0.0)))
+        return ("neutral", 0.0)
     except Exception as e:
         print(f"Emotion analysis error: {e}")
-    return ("neutral", 0.0)
+        return ("neutral", 0.0)
 
-def get_smart_context(user_text: str) -> str:
+def get_smart_context(user_text):
+    """
+    Analyzes the user's 'Vibe' and returns a short persona instruction.
+    """
     try:
         label, confidence = _safe_emotion_analysis(user_text)
         top_emotion = label.lower()