Method get_mllm_feedback

src/agent.py:402–459

(self, section: Section, video_path: str, round_number: int = 1)

        return False

    def get_mllm_feedback(self, section: Section, video_path: str, round_number: int = 1) -> VideoFeedback:
        print(f"🤖 {self.learning_topic} Using MLLM to analyze video ({round_number}/{self.feedback_rounds}): {section.id}")

        current_code = self.section_codes[section.id]
        positions = self.extractor.extract_grid_positions(current_code)
        position_table = self.extractor.generate_position_table(positions)
        analysis_prompt = get_prompt4_layout_feedback(section=section, position_table=position_table)

        def _parse_layout(feedback_content):
            has_layout_issues, suggested_improvements = False, []
            try:
                data = json.loads(feedback_content)
                lay = data.get("layout", {})
                has_layout_issues = bool(lay.get("has_issues", False))
                for it in lay.get("improvements", []) or []:
                    if isinstance(it, dict):
                        prob = str(it.get("problem", "")).strip()
                        sol = str(it.get("solution", "")).strip()
                        if prob or sol:
                            suggested_improvements.append(f"[LAYOUT] Problem: {prob}; Solution: {sol}")

            except json.JSONDecodeError:
                print(f"⚠️ {self.learning_topic} JSON parse failed, fallback to keyword analysis")

                for m in re.finditer(
                    r"Problem:\s*(.*?);\s*Solution:\s*(.*?)(?=\n|$)", feedback_content, flags=re.IGNORECASE | re.DOTALL
                ):
                    suggested_improvements.append(f"[LAYOUT] Problem: {m.group(1).strip()}; Solution: {m.group(2).strip()}")

                if not suggested_improvements:
                    for sol in re.findall(r"Solution\s*:\s*(.+)", feedback_content, flags=re.IGNORECASE):
                        suggested_improvements.append(f"[LAYOUT] Problem: ; Solution: {sol.strip()}")

            return has_layout_issues, suggested_improvements

        try:
            response = request_gemini_video_img(prompt=analysis_prompt, video_path=video_path, image_path=self.GRID_IMG_PATH)
            feedback_content = extract_answer_from_response(response)
            has_layout_issues, suggested_improvements = _parse_layout(feedback_content)
            feedback = VideoFeedback(
                section_id=section.id,
                video_path=video_path,
                has_issues=has_layout_issues,
                suggested_improvements=suggested_improvements,
                raw_response=feedback_content,
            )
            self.video_feedbacks[f"{section.id}_round{round_number}"] = feedback
            return feedback

        except Exception as e:
            print(f"❌ {self.learning_topic} MLLM analysis failed: {str(e)}")
            return VideoFeedback(
                section_id=section.id,
                video_path=video_path,
                has_issues=False,
                suggested_improvements=[],
                raw_response=f"Error: {str(e)}",
            )