Update main.py

main.py

@@ -100,26 +100,37 @@ async def analyze(data: ReviewInput, x_api_key: str = Header(None)):
     if len(data.text.split()) < 20:
         raise HTTPException(status_code=400, detail="⚠️ Review too short for analysis (min. 20 words).")
 
-    global log_store  # ✅ Needed for logging
+    global log_store
 
     try:
+        # === Generate Summary ===
         summary = (
             summarize_review(data.text, max_len=40, min_len=8)
             if data.verbosity.lower() == "brief"
             else smart_summarize(data.text, n_clusters=2 if data.intelligence else 1)
         )
 
+        # === Sentiment + Emotion ===
         sentiment_pipeline = pipeline("sentiment-analysis", model=data.model)
         sentiment = sentiment_pipeline(data.text)[0]
+
         emotion_raw = detect_emotion(data.text)
-        emotion = emotion_raw["label"] if isinstance(emotion_raw, dict) and "label" in emotion_raw else str(emotion_raw)
+        emotion = (
+            emotion_raw[0]["label"]
+            if isinstance(emotion_raw, list) and isinstance(emotion_raw[0], dict)
+            else str(emotion_raw)
+        )
+
         churn_risk = assess_churn_risk(sentiment["label"], emotion)
+
+        # === Auto-detect metadata ===
         industry = detect_industry(data.text) if not data.industry or "auto" in data.industry.lower() else data.industry
         product_category = detect_product_category(data.text) if not data.product_category or "auto" in data.product_category.lower() else data.product_category
 
+        # === Optional: Pain Points ===
         pain_points = extract_pain_points(data.text) if data.aspects else []
 
-        # ✅ Log churn entry
+        # === Log entry ===
         log_store.append({
             "timestamp": datetime.now(),
             "product": product_category,
@@ -129,6 +140,7 @@ async def analyze(data: ReviewInput, x_api_key: str = Header(None)):
         if len(log_store) > 1000:
             log_store = log_store[-1000:]
 
+        # === Final API Response ===
         response = {
             "summary": summary,
             "sentiment": sentiment,
@@ -172,7 +184,7 @@ async def bulk_analyze(data: BulkReviewInput, token: str = Query(None)):
     if token != VALID_API_KEY:
         raise HTTPException(status_code=401, detail="❌ Unauthorized: Invalid API token")
 
-    global log_store  # ✅ Needed to log bulk churn
+    global log_store
 
     try:
         results = []
@@ -188,7 +200,15 @@ async def bulk_analyze(data: BulkReviewInput, token: str = Query(None)):
 
             summary = smart_summarize(review_text, n_clusters=2 if data.intelligence else 1)
             sentiment = sentiment_pipeline(review_text)[0]
-            emotion = detect_emotion(review_text)
+
+            # ✅ Fix emotion return shape
+            emotion_raw = detect_emotion(review_text)
+            emotion = (
+                emotion_raw[0]["label"]
+                if isinstance(emotion_raw, list) and isinstance(emotion_raw[0], dict)
+                else str(emotion_raw)
+            )
+
             churn = assess_churn_risk(sentiment["label"], emotion)
             pain = extract_pain_points(review_text) if data.aspects else []
 
@@ -209,11 +229,12 @@ async def bulk_analyze(data: BulkReviewInput, token: str = Query(None)):
                 "pain_points": pain
             }
 
+            # ✅ Optional follow-up
             if data.follow_up and i < len(data.follow_up):
                 follow_q = data.follow_up[i]
                 result["follow_up"] = answer_followup(review_text, follow_q)
 
-            # ✅ Log churn
+            # ✅ Log churn entry
             log_store.append({
                 "timestamp": datetime.now(),
                 "product": prod,
@@ -223,6 +244,7 @@ async def bulk_analyze(data: BulkReviewInput, token: str = Query(None)):
 
             results.append(result)
 
+        # ✅ Cap log size
         if len(log_store) > 1000:
             log_store = log_store[-1000:]