gateway/modules/chat/documents/documentGeneration.py

import logging
from typing import Any, Dict, List, Optional
from datetime import datetime, UTC
import re
from modules.shared.timezoneUtils import get_utc_timestamp
from .documentUtility import (
    getFileExtension,
    getMimeTypeFromExtension,
    detectMimeTypeFromContent,
    detectMimeTypeFromData,
    convertDocumentDataToString
)

logger = logging.getLogger(__name__)

class DocumentGenerator:
    def __init__(self, service):
        self.service = service

    def processActionResultDocuments(self, action_result, action, workflow) -> List[Dict[str, Any]]:
        """
        Process documents produced by AI actions and convert them to ChatDocument format.
        This function handles AI-generated document data, not document references.
        Returns a list of processed document dictionaries.
        """
        try:
            # Read documents from the standard documents field (not data.documents)
            documents = action_result.documents if action_result and hasattr(action_result, 'documents') else []
            
            if not documents:
                logger.info(f"No documents found in action_result.documents for {action.execMethod}.{action.execAction}")
                return []
            
            logger.info(f"Processing {len(documents)} documents from action_result.documents")
            
            # Process each document from the AI action result
            processed_documents = []
            for doc in documents:
                processed_doc = self.processSingleDocument(doc, action)
                if processed_doc:
                    processed_documents.append(processed_doc)
            
            logger.info(f"Successfully processed {len(processed_documents)} documents")
            return processed_documents
        except Exception as e:
            logger.error(f"Error processing action result documents: {str(e)}")
            return []

    def processSingleDocument(self, doc: Any, action) -> Optional[Dict[str, Any]]:
        """Process a single document from action result with simplified logic"""
        try:
            # ActionDocument objects have documentName, documentData, and mimeType
            mime_type = doc.mimeType
            if mime_type == "application/octet-stream":
                content = doc.documentData
                mime_type = detectMimeTypeFromContent(content, doc.documentName, self.service)
            
            return {
                'fileName': doc.documentName,
                'fileSize': len(str(doc.documentData)),
                'mimeType': mime_type,
                'content': doc.documentData,
                'document': doc
            }
        except Exception as e:
            logger.error(f"Error processing single document: {str(e)}")
            return None

    def createDocumentsFromActionResult(self, action_result, action, workflow, message_id=None) -> List[Any]:
        """
        Create actual document objects from action result and store them in the system.
        Returns a list of created document objects with proper workflow context.
        """
        try:
            logger.info(f"Creating documents from action result for {action.execMethod}.{action.execAction}")
            logger.info(f"Action result documents count: {len(action_result.documents) if action_result.documents else 0}")
            
            processed_docs = self.processActionResultDocuments(action_result, action, workflow)
            logger.info(f"Processed {len(processed_docs)} documents")
            
            created_documents = []
            for i, doc_data in enumerate(processed_docs):
                try:
                    document_name = doc_data['fileName']
                    document_data = doc_data['content']
                    mime_type = doc_data['mimeType']
                    
                    logger.info(f"Creating document {i+1}: {document_name} (mime: {mime_type}, content length: {len(str(document_data))})")
                    
                    # Convert document data to string content
                    content = convertDocumentDataToString(document_data, getFileExtension(document_name))
                    
                    # Skip empty or minimal content
                    minimal_content_patterns = ['{}', '[]', 'null', '""', "''"]
                    if not content or content.strip() == "" or content.strip() in minimal_content_patterns:
                        logger.warning(f"Empty or minimal content for document {document_name}, skipping")
                        continue
                    
                    logger.info(f"Document {document_name} has content: {len(content)} characters")
                    
                    # Create document with file in one step
                    document = self.service.createDocument(
                        fileName=document_name,
                        mimeType=mime_type,
                        content=content,
                        base64encoded=False,
                        messageId=message_id
                    )
                    if document:
                        # Set workflow context on the document if possible
                        self._setDocumentWorkflowContext(document, action, workflow)
                        created_documents.append(document)
                        logger.info(f"Successfully created ChatDocument: {document_name} (ID: {document.id if hasattr(document, 'id') else 'N/A'}, fileId: {document.fileId if hasattr(document, 'fileId') else 'N/A'})")
                    else:
                        logger.error(f"Failed to create ChatDocument object for {document_name}")
                except Exception as e:
                    logger.error(f"Error creating document {doc_data.get('fileName', 'unknown')}: {str(e)}")
                    continue
            
            logger.info(f"Successfully created {len(created_documents)} documents")
            return created_documents
        except Exception as e:
            logger.error(f"Error creating documents from action result: {str(e)}")
            return []

    def _setDocumentWorkflowContext(self, document, action, workflow):
        """Set workflow context on a document for proper routing and labeling"""
        try:
            # Get current workflow context from service center
            workflow_context = self.service.getWorkflowContext()
            workflow_stats = self.service.getWorkflowStats()
            
            current_round = workflow_context.get('currentRound', 0)
            current_task = workflow_context.get('currentTask', 0)
            current_action = workflow_context.get('currentAction', 0)
            
            # Try to set workflow context attributes if they exist
            if hasattr(document, 'roundNumber'):
                document.roundNumber = current_round
            if hasattr(document, 'taskNumber'):
                document.taskNumber = current_task
            if hasattr(document, 'actionNumber'):
                document.actionNumber = current_action
            if hasattr(document, 'actionId'):
                document.actionId = action.id if hasattr(action, 'id') else None
            
            # Set additional workflow metadata if available
            if hasattr(document, 'workflowId'):
                document.workflowId = workflow_stats.get('workflowId', workflow.id if hasattr(workflow, 'id') else None)
            if hasattr(document, 'workflowStatus'):
                document.workflowStatus = workflow_stats.get('workflowStatus', workflow.status if hasattr(workflow, 'status') else 'unknown')
            
            logger.debug(f"Set workflow context on document: Round {current_round}, Task {current_task}, Action {current_action}")
            logger.debug(f"Document workflow metadata: ID={document.workflowId if hasattr(document, 'workflowId') else 'N/A'}, Status={document.workflowStatus if hasattr(document, 'workflowStatus') else 'N/A'}")
            
        except Exception as e:
            logger.warning(f"Could not set workflow context on document: {str(e)}")