Update agents.py

agents.py

@@ -1,139 +1,39 @@
-# agents.py
 import os
 import random
-from collections import Counter
-from typing import List, Dict, Any
-
-# Accept either env var name
-GLM_API_KEY = os.getenv("ZHIPUAI_API_KEY") or os.getenv("zhipuai_api_key")
+from zhipuai import ZhipuAI
 
+API_KEY = os.getenv("zhipuai_api_key")
+client = ZhipuAI(api_key=API_KEY)
 
 class AnalyzerAgent:
-    def analyze(self, per_question: Dict[str, Dict[str, Any]]) -> Dict[str, Any]:
-        topic_stats = {}
-        for qid, info in per_question.items():
-            topics = info.get("topics") or []
-            user = info.get("user")
-            correct = info.get("correct")
-            is_correct = (correct is not None and user is not None and str(user).strip() == str(correct).strip())
-            for t in topics:
-                if t not in topic_stats:
-                    topic_stats[t] = {"correct": 0, "total": 0}
-                topic_stats[t]["total"] += 1
-                if is_correct:
-                    topic_stats[t]["correct"] += 1
-
-        topic_accuracy = {}
-        weak_topics = []
-        for t, stats in topic_stats.items():
-            total = stats["total"]
-            acc = round((stats["correct"] / total) * 100, 2) if total > 0 else 0.0
-            topic_accuracy[t] = {"accuracy_percent": acc, "total": total}
-            if total >= 3 and acc < 65.0:
-                weak_topics.append(t)
-
-        recommendation = "Focus on: " + ", ".join(weak_topics) if weak_topics else "No major weak topics detected."
-
-        return {"topic_accuracy": topic_accuracy, "weak_topics": weak_topics, "recommendation": recommendation}
-
+    def analyze(self, answers, correct_answers):
+        score = 0
+        feedback = []
+        for qid, user_ans in answers.items():
+            if user_ans == correct_answers.get(qid):
+                score += 1
+            else:
+                feedback.append(f"Q{qid}: Correct was {correct_answers.get(qid)}")
+        return score, feedback
 
 class CoachAgent:
-    def coach(self, analysis: Dict[str, Any], level: str, subject: str) -> Dict[str, Any]:
-        weak = analysis.get("weak_topics", [])
-        if not weak:
-            tips = [
-                "Revise key topics and practice mixed mock papers.",
-                "Time yourself when attempting past papers.",
-                "Review incorrect answers and understand mistakes."
-            ]
-        else:
-            tips = [
-                f"Focus 20–30 minutes daily on {weak[0]}. Break it to small tasks.",
-                "Practice targeted short questions and review solutions.",
-                "Explain topics to a peer to strengthen memory."
-            ]
-
-        practice = []
-        for t in weak[:3]:
-            practice.append({"text": f"Practice task on {t}", "topic": t})
-
-        return {"tips": tips, "study_plan": "20 min/day weak topics + weekly full mock", "practice": practice}
-
+    def give_feedback(self, feedback):
+        if not feedback:
+            return "Excellent! You answered all correctly."
+        return "Review these: " + "; ".join(feedback)
 
 class PredictiveAgent:
-    def __init__(self):
-        self.api_key = GLM_API_KEY
-
-    def _top_topics(self, question_bank: List[Dict], subject: str, k=6):
-        subj_key = f"Form5_{subject}"
-        counter = Counter()
-        for q in question_bank:
-            if q.get("subject") != subj_key:
-                continue
-            for t in q.get("topics", []):
-                counter[t] += 1
-        return [t for t, _ in counter.most_common(k)]
-
-    def generate_predictions(self, level: str, subject: str, n: int = 5, question_bank: List[Dict] = None) -> List[Dict]:
-        preds = []
-        base = 900000
-        topics = self._top_topics(question_bank or [], subject) if question_bank else []
-        if not topics:
-            fallback = {
-                "BM": ["perbendaharaan_kata", "tatabahasa"],
-                "English": ["vocabulary", "grammar"],
-                "Math": ["algebra", "geometry"],
-                "History": ["events", "dates"],
-                "Science": ["physics", "chemistry"],
-                "MoralStudies": ["ethics", "values"]
-            }
-            topics = fallback.get(subject, ["general"])
-
-        # Not calling GLM here by default; heuristics used. If you want GLM, we can wire it (needs API + endpoint)
-        for i in range(n):
-            topic = topics[i % len(topics)]
-            q = self._heuristic(subject, topic, i + 1)
-            q["id"] = base + i
-            q["source"] = "predicted"
-            q["confidence"] = round(random.uniform(0.35, 0.75), 2)
-            preds.append(q)
-        return preds
-
-    def _heuristic(self, subject: str, topic: str, idx: int) -> Dict:
-        if subject == "BM":
-            text = "Pilih sinonim bagi perkataan 'gembira'."
-            choices = ["Sedih", "Gembira", "Marah", "Letih"]
-            correct = "Gembira"
-        elif subject == "English":
-            text = "Choose the correct synonym for 'happy'."
-            choices = ["Sad", "Joyful", "Angry", "Tired"]
-            correct = "Joyful"
-        elif subject == "Math":
-            text = "If 2x + 3 = 11, what is x?"
-            choices = ["2", "3", "4", "5"]
-            correct = "4"
-        elif subject == "Science":
-            text = "What is the SI unit of force?"
-            choices = ["Joule", "Newton", "Pascal", "Watt"]
-            correct = "Newton"
-        elif subject == "History":
-            text = "Which year is associated with Malayan independence?"
-            choices = ["1945", "1957", "1963", "1975"]
-            correct = "1957"
-        elif subject == "MoralStudies":
-            text = "Which value best represents mutual respect?"
-            choices = ["Greed", "Respect", "Laziness", "Selfishness"]
-            correct = "Respect"
-        else:
-            text = f"Practice question on {topic}."
-            choices = ["A", "B", "C", "D"]
-            correct = "A"
-
-        return {"text": text, "choices": choices, "correct_answer": correct, "topics": [topic], "difficulty": 3}
+    def predict_questions(self, past_questions, subject):
+        """
+        Use GLM4.5 to predict potential questions based on past trends.
+        """
+        prompt = f"Analyze these past SPM {subject} questions and predict possible future ones:\n{past_questions[:1000]}"
+        resp = client.chat.completions.create(
+            model="glm-4-5",
+            messages=[{"role": "user", "content": prompt}]
+        )
+        return resp.choices[0].message["content"]
 
-    def summary(self, level: str, subject: str, question_bank: List[Dict] = None) -> Dict:
-        topics = self._top_topics(question_bank or [], subject) if question_bank else []
-        return {"level": level, "subject": subject, "top_topics": topics, "note": "Heuristic predictions — for practice only."}