Update agents.py

agents.py

@@ -2,74 +2,53 @@ import os
 import random
 from zhipuai import ZhipuAI
 
-# Initialize ZhipuAI
-client = ZhipuAI(api_key=os.getenv("ZHIPUAI_API_KEY", "demo-key"))
+# Load API key
+ZHIPU_API_KEY = os.getenv("zhipuai_api_key")
 
 class AnalyzerAgent:
-    """Grades answers and provides analysis."""
-
-    def analyze(self, answers, questions):
-        correct = 0
-        total = len(questions)
-        for q in questions:
-            qid = str(q.get("id"))
-            if qid in answers and answers[qid] == q.get("answer"):
-                correct += 1
-        return f"Score: {correct}/{total}"
-
-    def get_detailed_feedback(self, answers, questions):
-        feedback = []
-        for q in questions:
-            qid = str(q.get("id"))
-            if qid not in answers:
-                feedback.append(f"Q{qid}: Not attempted")
-            elif answers[qid] == q.get("answer"):
-                feedback.append(f"Q{qid}: Correct ✅")
+    """Analyzes student answers against scheme."""
+    def analyze(self, student_answers, correct_answers):
+        score = 0
+        analysis = []
+        for i, (ans, correct) in enumerate(zip(student_answers, correct_answers)):
+            if ans == correct:
+                score += 1
+                analysis.append(f"Q{i+1}: ✅ Correct")
             else:
-                feedback.append(f"Q{qid}: Incorrect ❌ (Correct: {q.get('answer')})")
-        return "\n".join(feedback)
-
+                analysis.append(f"Q{i+1}: ❌ Wrong (Correct: {correct})")
+        return score, analysis
 
 class CoachAgent:
-    """Provides motivational coaching based on analysis."""
-
-    def provide_guidance(self, analysis_text):
-        prompt = (
-            "You are a supportive SPM exam coach. "
-            "Given the analysis of a student's answers, "
-            "provide encouragement, study tips, and focus areas.\n\n"
-            f"Analysis:\n{analysis_text}"
-        )
-        resp = client.chat.completions.create(
+    """Provides AI feedback for essays and weak areas."""
+    def __init__(self):
+        self.client = ZhipuAI(api_key=ZHIPU_API_KEY)
+
+    def coach(self, essay_text):
+        if not essay_text.strip():
+            return "⚠️ No essay text provided."
+        prompt = f"Provide constructive feedback and improvement tips for this essay:\n\n{essay_text}"
+        resp = self.client.chat.completions.create(
             model="glm-4",
             messages=[{"role": "user", "content": prompt}]
         )
         return resp.choices[0].message["content"]
 
-
 class PredictiveAgent:
-    """Generates AI-predicted practice questions."""
+    """Forecasts likely SPM 2025–2026 questions based on past papers."""
+    def __init__(self):
+        self.client = ZhipuAI(api_key=ZHIPU_API_KEY)
 
-    def generate_predicted_questions(self, subject, count=5):
+    def predict(self, subject, year_range="2018-2024"):
         prompt = (
-            f"Generate {count} multiple-choice practice questions for SPM {subject}. "
-            "Each question should include: text, four choices (A-D), and correct answer."
+            f"Analyze Malaysian SPM {subject} past papers from {year_range}.\n"
+            f"Identify recurring patterns and predict 5 high-probability questions for upcoming exams."
         )
-        resp = client.chat.completions.create(
+        resp = self.client.chat.completions.create(
             model="glm-4",
             messages=[{"role": "user", "content": prompt}]
         )
-        # Parse output into simple mock questions (demo version)
-        questions = []
-        for i in range(count):
-            questions.append({
-                "id": 900000 + i,
-                "text": f"Practice predicted question {i+1} on {subject}",
-                "choices": ["A", "B", "C", "D"],
-                "answer": random.choice(["A", "B", "C", "D"]),
-                "source": "predicted"
-            })
-        return questions
+        return resp.choices[0].message["content"]
+