src/interface/feedback_ui_integration.py

"""
Feedback UI integration for structured error category selection.
Integrates with the existing verification interface to provide structured feedback capture.
"""

import gradio as gr
from typing import Dict, List, Optional, Tuple, Any
from datetime import datetime

from config.prompt_management.feedback_system import FeedbackSystem
from config.prompt_management.data_models import (
    ErrorType, ErrorSubcategory, QuestionIssueType, ReferralProblemType, ScenarioType
)


class FeedbackUIIntegration:
    """
    UI integration for structured feedback capture.
    
    Provides Gradio components for:
    - Structured error category selection
    - Predefined subcategories from documentation
    - Pattern analysis display for reviewers
    - Integration with existing verification interface
    """
    
    def __init__(self, feedback_system: Optional[FeedbackSystem] = None):
        """
        Initialize the feedback UI integration.
        
        Args:
            feedback_system: Optional feedback system instance. If None, creates default.
        """
        self.feedback_system = feedback_system or FeedbackSystem()
        
        # Define UI options based on data models
        self.error_type_options = [
            ("Wrong Classification", "wrong_classification"),
            ("Severity Misjudgment", "severity_misjudgment"),
            ("Missed Indicators", "missed_indicators"),
            ("False Positive", "false_positive"),
            ("Context Misunderstanding", "context_misunderstanding"),
            ("Language Interpretation", "language_interpretation")
        ]
        
        self.subcategory_mapping = {
            "wrong_classification": [
                ("GREEN → YELLOW", "green_to_yellow"),
                ("GREEN → RED", "green_to_red"),
                ("YELLOW → GREEN", "yellow_to_green"),
                ("YELLOW → RED", "yellow_to_red"),
                ("RED → GREEN", "red_to_green"),
                ("RED → YELLOW", "red_to_yellow")
            ],
            "severity_misjudgment": [
                ("Underestimated Distress", "underestimated_distress"),
                ("Overestimated Distress", "overestimated_distress")
            ],
            "missed_indicators": [
                ("Emotional Indicators", "emotional_indicators"),
                ("Spiritual Indicators", "spiritual_indicators"),
                ("Social Indicators", "social_indicators")
            ],
            "false_positive": [
                ("Misinterpreted Statement", "misinterpreted_statement"),
                ("Cultural Misunderstanding", "cultural_misunderstanding")
            ],
            "context_misunderstanding": [
                ("Ignored History", "ignored_history"),
                ("Missed Defensive Response", "missed_defensive_response")
            ],
            "language_interpretation": [
                ("Literal Interpretation", "literal_interpretation"),
                ("Missed Subtext", "missed_subtext")
            ]
        }
        
        self.question_issue_options = [
            ("Inappropriate Question", "inappropriate_question"),
            ("Insensitive Language", "insensitive_language"),
            ("Wrong Scenario Targeting", "wrong_scenario_targeting"),
            ("Unclear Question", "unclear_question"),
            ("Leading Question", "leading_question")
        ]
        
        self.referral_problem_options = [
            ("Incomplete Summary", "incomplete_summary"),
            ("Missing Contact Info", "missing_contact_info"),
            ("Incorrect Urgency", "incorrect_urgency"),
            ("Poor Context Description", "poor_context_description")
        ]
        
        self.scenario_options = [
            ("Loss of Interest", "loss_of_interest"),
            ("Loss of Loved One", "loss_of_loved_one"),
            ("No Support", "no_support"),
            ("Vague Stress", "vague_stress"),
            ("Sleep Issues", "sleep_issues"),
            ("Spiritual Practice Change", "spiritual_practice_change")
        ]
    
    def create_classification_error_interface(self) -> gr.Group:
        """
        Create UI components for recording classification errors.
        
        Returns:
            gr.Group: Gradio group containing classification error interface
        """
        with gr.Group() as classification_group:
            gr.Markdown("### Classification Error Feedback")
            
            with gr.Row():
                error_type = gr.Dropdown(
                    choices=[label for label, _ in self.error_type_options],
                    label="Error Type",
                    info="Select the type of classification error"
                )
                
                subcategory = gr.Dropdown(
                    choices=[],
                    label="Subcategory",
                    info="Specific subcategory (updates based on error type)"
                )
            
            with gr.Row():
                expected_category = gr.Dropdown(
                    choices=["GREEN", "YELLOW", "RED"],
                    label="Expected Category",
                    info="What the classification should have been"
                )
                
                actual_category = gr.Dropdown(
                    choices=["GREEN", "YELLOW", "RED"],
                    label="Actual Category",
                    info="What the system classified it as"
                )
            
            message_content = gr.Textbox(
                label="Patient Message",
                placeholder="Enter the patient message that was misclassified...",
                lines=3,
                info="The original patient message"
            )
            
            reviewer_comments = gr.Textbox(
                label="Reviewer Comments",
                placeholder="Explain why this is an error and what should have happened...",
                lines=3,
                info="Detailed explanation of the error"
            )
            
            confidence_level = gr.Slider(
                minimum=0.0,
                maximum=1.0,
                value=0.8,
                step=0.1,
                label="Confidence Level",
                info="How confident are you in this feedback?"
            )
            
            submit_error = gr.Button("Record Classification Error", variant="primary")
            error_result = gr.Textbox(label="Result", interactive=False)
            
            # Update subcategory options when error type changes
            def update_subcategories(error_type_label):
                if not error_type_label:
                    return gr.Dropdown(choices=[])
                
                # Find the error type value
                error_type_value = None
                for label, value in self.error_type_options:
                    if label == error_type_label:
                        error_type_value = value
                        break
                
                if error_type_value and error_type_value in self.subcategory_mapping:
                    choices = [label for label, _ in self.subcategory_mapping[error_type_value]]
                    return gr.Dropdown(choices=choices)
                else:
                    return gr.Dropdown(choices=[])
            
            error_type.change(
                fn=update_subcategories,
                inputs=[error_type],
                outputs=[subcategory]
            )
            
            # Handle error submission
            def submit_classification_error(error_type_label, subcategory_label, expected, actual, 
                                          message, comments, confidence):
                try:
                    # Convert labels to values
                    error_type_value = None
                    for label, value in self.error_type_options:
                        if label == error_type_label:
                            error_type_value = value
                            break
                    
                    if not error_type_value:
                        return "Error: Invalid error type selected"
                    
                    subcategory_value = None
                    if error_type_value in self.subcategory_mapping:
                        for label, value in self.subcategory_mapping[error_type_value]:
                            if label == subcategory_label:
                                subcategory_value = value
                                break
                    
                    if not subcategory_value:
                        return "Error: Invalid subcategory selected"
                    
                    # Validate required fields
                    if not all([expected, actual, message, comments]):
                        return "Error: All fields are required"
                    
                    # Record the error
                    error_id = self.feedback_system.record_classification_error(
                        error_type=ErrorType(error_type_value),
                        subcategory=ErrorSubcategory(subcategory_value),
                        expected_category=expected,
                        actual_category=actual,
                        message_content=message,
                        reviewer_comments=comments,
                        confidence_level=confidence,
                        session_id=f"ui_session_{datetime.now().strftime('%Y%m%d_%H%M%S')}",
                        additional_context={"source": "ui_interface"}
                    )
                    
                    return f"✓ Classification error recorded successfully (ID: {error_id[:8]}...)"
                    
                except Exception as e:
                    return f"Error recording classification error: {str(e)}"
            
            submit_error.click(
                fn=submit_classification_error,
                inputs=[error_type, subcategory, expected_category, actual_category, 
                       message_content, reviewer_comments, confidence_level],
                outputs=[error_result]
            )
        
        return classification_group
    
    def create_question_issue_interface(self) -> gr.Group:
        """
        Create UI components for recording question issues.
        
        Returns:
            gr.Group: Gradio group containing question issue interface
        """
        with gr.Group() as question_group:
            gr.Markdown("### Question Issue Feedback")
            
            with gr.Row():
                issue_type = gr.Dropdown(
                    choices=[label for label, _ in self.question_issue_options],
                    label="Issue Type",
                    info="Type of issue with the generated question"
                )
                
                scenario_type = gr.Dropdown(
                    choices=[label for label, _ in self.scenario_options],
                    label="Scenario Type",
                    info="The scenario the question was targeting"
                )
            
            question_content = gr.Textbox(
                label="Problematic Question",
                placeholder="Enter the question that has issues...",
                lines=2,
                info="The generated question that needs improvement"
            )
            
            reviewer_comments = gr.Textbox(
                label="Issue Description",
                placeholder="Explain what's wrong with this question...",
                lines=3,
                info="Detailed explanation of the issue"
            )
            
            with gr.Row():
                severity = gr.Dropdown(
                    choices=["low", "medium", "high"],
                    label="Severity",
                    value="medium",
                    info="How severe is this issue?"
                )
            
            suggested_improvement = gr.Textbox(
                label="Suggested Improvement (Optional)",
                placeholder="Suggest a better question...",
                lines=2,
                info="Optional suggestion for how to improve the question"
            )
            
            submit_question = gr.Button("Record Question Issue", variant="primary")
            question_result = gr.Textbox(label="Result", interactive=False)
            
            # Handle question issue submission
            def submit_question_issue(issue_type_label, scenario_label, question, comments, 
                                    severity_val, improvement):
                try:
                    # Convert labels to values
                    issue_type_value = None
                    for label, value in self.question_issue_options:
                        if label == issue_type_label:
                            issue_type_value = value
                            break
                    
                    scenario_value = None
                    for label, value in self.scenario_options:
                        if label == scenario_label:
                            scenario_value = value
                            break
                    
                    if not all([issue_type_value, scenario_value, question, comments, severity_val]):
                        return "Error: All required fields must be filled"
                    
                    # Record the issue
                    issue_id = self.feedback_system.record_question_issue(
                        issue_type=QuestionIssueType(issue_type_value),
                        question_content=question,
                        scenario_type=ScenarioType(scenario_value),
                        reviewer_comments=comments,
                        severity=severity_val,
                        session_id=f"ui_session_{datetime.now().strftime('%Y%m%d_%H%M%S')}",
                        suggested_improvement=improvement if improvement else None
                    )
                    
                    return f"✓ Question issue recorded successfully (ID: {issue_id[:8]}...)"
                    
                except Exception as e:
                    return f"Error recording question issue: {str(e)}"
            
            submit_question.click(
                fn=submit_question_issue,
                inputs=[issue_type, scenario_type, question_content, reviewer_comments, 
                       severity, suggested_improvement],
                outputs=[question_result]
            )
        
        return question_group
    
    def create_pattern_analysis_display(self) -> gr.Group:
        """
        Create UI components for displaying error pattern analysis.
        
        Returns:
            gr.Group: Gradio group containing pattern analysis display
        """
        with gr.Group() as pattern_group:
            gr.Markdown("### Error Pattern Analysis")
            
            refresh_patterns = gr.Button("Refresh Pattern Analysis", variant="secondary")
            
            pattern_display = gr.Markdown(
                value="Click 'Refresh Pattern Analysis' to see current error patterns and improvement suggestions.",
                label="Pattern Analysis Results"
            )
            
            # Handle pattern analysis refresh
            def refresh_pattern_analysis():
                try:
                    # Get feedback summary
                    summary = self.feedback_system.get_feedback_summary()
                    
                    # Analyze patterns
                    patterns = self.feedback_system.analyze_error_patterns(min_frequency=2)
                    
                    # Format results
                    result = "## Current Feedback Summary\n\n"
                    result += f"- **Total Errors:** {summary['total_errors']}\n"
                    result += f"- **Total Question Issues:** {summary['total_question_issues']}\n"
                    result += f"- **Total Referral Problems:** {summary['total_referral_problems']}\n"
                    result += f"- **Average Confidence:** {summary['average_confidence']:.2f}\n"
                    result += f"- **Recent Errors:** {summary['recent_errors']}\n\n"
                    
                    if patterns:
                        result += "## Identified Error Patterns\n\n"
                        for i, pattern in enumerate(patterns[:5], 1):  # Top 5 patterns
                            result += f"### {i}. {pattern.pattern_type.replace('_', ' ').title()}\n"
                            result += f"- **Frequency:** {pattern.frequency}\n"
                            result += f"- **Description:** {pattern.description}\n"
                            result += f"- **Confidence:** {pattern.confidence_score:.2f}\n"
                            result += "- **Suggested Improvements:**\n"
                            for suggestion in pattern.suggested_improvements[:3]:  # Top 3 suggestions
                                result += f"  - {suggestion}\n"
                            result += "\n"
                    else:
                        result += "## No Significant Patterns Detected\n\n"
                        result += "Not enough data to identify patterns (minimum 2 occurrences required).\n\n"
                    
                    # Add top improvement suggestions
                    if summary['improvement_suggestions']:
                        result += "## Top Improvement Suggestions\n\n"
                        for i, suggestion in enumerate(summary['improvement_suggestions'][:5], 1):
                            result += f"{i}. {suggestion}\n"
                    
                    return result
                    
                except Exception as e:
                    return f"Error analyzing patterns: {str(e)}"
            
            refresh_patterns.click(
                fn=refresh_pattern_analysis,
                outputs=[pattern_display]
            )
        
        return pattern_group
    
    def create_complete_feedback_interface(self) -> gr.Tabs:
        """
        Create the complete feedback interface with all components.
        
        Returns:
            gr.Tabs: Complete feedback interface with multiple tabs
        """
        with gr.Tabs() as feedback_tabs:
            with gr.Tab("Classification Errors"):
                self.create_classification_error_interface()
            
            with gr.Tab("Question Issues"):
                self.create_question_issue_interface()
            
            with gr.Tab("Pattern Analysis"):
                self.create_pattern_analysis_display()
        
        return feedback_tabs


def create_feedback_ui_demo():
    """
    Create a demo of the feedback UI integration.
    
    Returns:
        gr.Blocks: Gradio interface for testing feedback UI
    """
    feedback_ui = FeedbackUIIntegration()
    
    with gr.Blocks(title="Structured Feedback System Demo") as demo:
        gr.Markdown("# Structured Feedback System")
        gr.Markdown("This interface allows reviewers to provide structured feedback on AI classifications, questions, and referrals.")
        
        feedback_ui.create_complete_feedback_interface()
        
        gr.Markdown("---")
        gr.Markdown("**Note:** This is a demonstration of the structured feedback capture system. In production, this would be integrated with the main verification interface.")
    
    return demo


if __name__ == "__main__":
    # Run the demo
    demo = create_feedback_ui_demo()
    demo.launch(share=False, server_name="127.0.0.1", server_port=7861)