Implement persona generation system with platform-specific adaptations

Co-authored-by: ajay.calsoft <ajay.calsoft@gmail.com>

backend/api/onboarding.py

@@ -354,12 +354,29 @@ async def complete_onboarding():
                 detail="Cannot complete onboarding. At least one AI provider API key must be configured."
             )
         
+        # Generate writing persona from onboarding data
+        try:
+            from services.persona_analysis_service import PersonaAnalysisService
+            persona_service = PersonaAnalysisService()
+            
+            # Use user_id = 1 for now (assuming single user system)
+            user_id = 1
+            persona_result = persona_service.generate_persona_from_onboarding(user_id)
+            
+            if "error" not in persona_result:
+                logger.info(f"✅ Writing persona generated during onboarding completion: {persona_result.get('persona_id')}")
+            else:
+                logger.warning(f"⚠️ Persona generation failed during onboarding: {persona_result['error']}")
+        except Exception as e:
+            logger.warning(f"⚠️ Non-critical error generating persona during onboarding: {str(e)}")
+        
         progress.complete_onboarding()
         
         return {
             "message": "Onboarding completed successfully",
             "completed_at": progress.completed_at,
-            "completion_percentage": 100.0
+            "completion_percentage": 100.0,
+            "persona_generated": "error" not in persona_result if 'persona_result' in locals() else False
         }
     except HTTPException:
         raise
@@ -522,9 +539,11 @@ async def get_onboarding_summary():
         from services.database import get_db
         from services.website_analysis_service import WebsiteAnalysisService
         from services.research_preferences_service import ResearchPreferencesService
+        from services.persona_analysis_service import PersonaAnalysisService
         
         # Get current session (assuming session ID 1 for now)
         session_id = 1
+        user_id = 1  # Assuming single user system for now
         
         # Get API keys
         api_manager = get_api_key_manager()
@@ -548,18 +567,37 @@ async def get_onboarding_summary():
                 'brand_voice': research_preferences.get('writing_style', {}).get('complexity', 'Trustworthy and Expert')
             }
         
+        # Check persona generation readiness
+        persona_service = PersonaAnalysisService()
+        persona_readiness = None
+        try:
+            # Check if persona can be generated
+            onboarding_data = persona_service._collect_onboarding_data(user_id)
+            if onboarding_data:
+                data_sufficiency = persona_service._calculate_data_sufficiency(onboarding_data)
+                persona_readiness = {
+                    "ready": data_sufficiency >= 50.0,
+                    "data_sufficiency": data_sufficiency,
+                    "can_generate": website_analysis is not None
+                }
+        except Exception as e:
+            logger.warning(f"Could not check persona readiness: {str(e)}")
+            persona_readiness = {"ready": False, "error": str(e)}
+        
         return {
             "api_keys": api_keys,
             "website_url": website_analysis.get('website_url') if website_analysis else None,
             "style_analysis": website_analysis.get('style_analysis') if website_analysis else None,
             "research_preferences": research_preferences,
             "personalization_settings": personalization_settings,
+            "persona_readiness": persona_readiness,
             "integrations": {},  # TODO: Implement integrations data
             "capabilities": {
                 "ai_content": len(api_keys) > 0,
                 "style_analysis": website_analysis is not None,
                 "research_tools": research_preferences is not None,
                 "personalization": personalization_settings is not None,
+                "persona_generation": persona_readiness.get("ready", False) if persona_readiness else False,
                 "integrations": False  # TODO: Implement
             }
         }
@@ -607,4 +645,43 @@ async def get_research_preferences_data():
         return preferences
     except Exception as e:
         logger.error(f"Error getting research preferences data: {str(e)}")
+        raise HTTPException(status_code=500, detail="Internal server error")
+
+# New persona-related endpoints
+
+async def check_persona_generation_readiness(user_id: int = 1):
+    """Check if user has sufficient data for persona generation."""
+    try:
+        from api.persona import validate_persona_generation_readiness
+        return await validate_persona_generation_readiness(user_id)
+    except Exception as e:
+        logger.error(f"Error checking persona readiness: {str(e)}")
+        raise HTTPException(status_code=500, detail="Internal server error")
+
+async def generate_persona_preview(user_id: int = 1):
+    """Generate a preview of the writing persona without saving."""
+    try:
+        from api.persona import generate_persona_preview
+        return await generate_persona_preview(user_id)
+    except Exception as e:
+        logger.error(f"Error generating persona preview: {str(e)}")
+        raise HTTPException(status_code=500, detail="Internal server error")
+
+async def generate_writing_persona(user_id: int = 1):
+    """Generate and save a writing persona from onboarding data."""
+    try:
+        from api.persona import generate_persona, PersonaGenerationRequest
+        request = PersonaGenerationRequest(force_regenerate=False)
+        return await generate_persona(user_id, request)
+    except Exception as e:
+        logger.error(f"Error generating writing persona: {str(e)}")
+        raise HTTPException(status_code=500, detail="Internal server error")
+
+async def get_user_writing_personas(user_id: int = 1):
+    """Get all writing personas for the user."""
+    try:
+        from api.persona import get_user_personas
+        return await get_user_personas(user_id)
+    except Exception as e:
+        logger.error(f"Error getting user personas: {str(e)}")
         raise HTTPException(status_code=500, detail="Internal server error") 

backend/api/persona.py

@@ -0,0 +1,385 @@
+"""
+Persona API endpoints for ALwrity.
+Handles writing persona generation, management, and platform-specific adaptations.
+"""
+
+from fastapi import HTTPException, Depends
+from pydantic import BaseModel, Field
+from typing import Dict, Any, List, Optional
+from datetime import datetime
+from loguru import logger
+
+from services.persona_analysis_service import PersonaAnalysisService
+from services.database import get_db
+
+class PersonaGenerationRequest(BaseModel):
+    """Request model for persona generation."""
+    onboarding_session_id: Optional[int] = Field(None, description="Specific onboarding session ID to use")
+    force_regenerate: bool = Field(False, description="Force regeneration even if persona exists")
+
+class PersonaResponse(BaseModel):
+    """Response model for persona data."""
+    persona_id: int
+    persona_name: str
+    archetype: str
+    core_belief: str
+    confidence_score: float
+    platforms: List[str]
+    created_at: str
+
+class PlatformPersonaResponse(BaseModel):
+    """Response model for platform-specific persona."""
+    platform_type: str
+    sentence_metrics: Dict[str, Any]
+    lexical_features: Dict[str, Any]
+    content_format_rules: Dict[str, Any]
+    engagement_patterns: Dict[str, Any]
+    platform_best_practices: Dict[str, Any]
+
+class PersonaGenerationResponse(BaseModel):
+    """Response model for persona generation result."""
+    success: bool
+    persona_id: Optional[int] = None
+    message: str
+    confidence_score: Optional[float] = None
+    data_sufficiency: Optional[float] = None
+    platforms_generated: List[str] = []
+
+# Dependency to get persona service
+def get_persona_service() -> PersonaAnalysisService:
+    """Get the persona analysis service instance."""
+    return PersonaAnalysisService()
+
+async def generate_persona(user_id: int, request: PersonaGenerationRequest):
+    """Generate a new writing persona from onboarding data."""
+    try:
+        logger.info(f"Generating persona for user {user_id}")
+        
+        persona_service = get_persona_service()
+        
+        # Check if persona already exists and force_regenerate is False
+        if not request.force_regenerate:
+            existing_personas = persona_service.get_user_personas(user_id)
+            if existing_personas:
+                return PersonaGenerationResponse(
+                    success=False,
+                    message="Persona already exists. Use force_regenerate=true to create a new one.",
+                    persona_id=existing_personas[0]["id"]
+                )
+        
+        # Generate new persona
+        result = persona_service.generate_persona_from_onboarding(
+            user_id=user_id,
+            onboarding_session_id=request.onboarding_session_id
+        )
+        
+        if "error" in result:
+            return PersonaGenerationResponse(
+                success=False,
+                message=result["error"]
+            )
+        
+        return PersonaGenerationResponse(
+            success=True,
+            persona_id=result["persona_id"],
+            message="Persona generated successfully",
+            confidence_score=result["analysis_metadata"]["confidence_score"],
+            data_sufficiency=result["analysis_metadata"].get("data_sufficiency", 0.0),
+            platforms_generated=list(result["platform_personas"].keys())
+        )
+        
+    except Exception as e:
+        logger.error(f"Error generating persona: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"Failed to generate persona: {str(e)}")
+
+async def get_user_personas(user_id: int):
+    """Get all personas for a user."""
+    try:
+        persona_service = get_persona_service()
+        personas = persona_service.get_user_personas(user_id)
+        
+        return {
+            "personas": personas,
+            "total_count": len(personas)
+        }
+        
+    except Exception as e:
+        logger.error(f"Error getting user personas: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"Failed to get personas: {str(e)}")
+
+async def get_persona_details(user_id: int, persona_id: int):
+    """Get detailed information about a specific persona."""
+    try:
+        from services.database import get_db_session
+        from models.persona_models import WritingPersona, PlatformPersona
+        
+        session = get_db_session()
+        
+        # Get persona
+        persona = session.query(WritingPersona).filter(
+            WritingPersona.id == persona_id,
+            WritingPersona.user_id == user_id,
+            WritingPersona.is_active == True
+        ).first()
+        
+        if not persona:
+            raise HTTPException(status_code=404, detail="Persona not found")
+        
+        # Get platform adaptations
+        platform_personas = session.query(PlatformPersona).filter(
+            PlatformPersona.writing_persona_id == persona_id,
+            PlatformPersona.is_active == True
+        ).all()
+        
+        result = persona.to_dict()
+        result["platform_adaptations"] = [pp.to_dict() for pp in platform_personas]
+        
+        session.close()
+        return result
+        
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"Error getting persona details: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"Failed to get persona details: {str(e)}")
+
+async def get_platform_persona(user_id: int, platform: str):
+    """Get persona adaptation for a specific platform."""
+    try:
+        persona_service = get_persona_service()
+        platform_persona = persona_service.get_persona_for_platform(user_id, platform)
+        
+        if not platform_persona:
+            raise HTTPException(status_code=404, detail=f"No persona found for platform {platform}")
+        
+        return platform_persona
+        
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"Error getting platform persona: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"Failed to get platform persona: {str(e)}")
+
+async def update_persona(user_id: int, persona_id: int, update_data: Dict[str, Any]):
+    """Update an existing persona."""
+    try:
+        from services.database import get_db_session
+        from models.persona_models import WritingPersona
+        
+        session = get_db_session()
+        
+        persona = session.query(WritingPersona).filter(
+            WritingPersona.id == persona_id,
+            WritingPersona.user_id == user_id
+        ).first()
+        
+        if not persona:
+            raise HTTPException(status_code=404, detail="Persona not found")
+        
+        # Update allowed fields
+        updatable_fields = [
+            'persona_name', 'archetype', 'core_belief', 'brand_voice_description',
+            'linguistic_fingerprint', 'platform_adaptations'
+        ]
+        
+        for field in updatable_fields:
+            if field in update_data:
+                setattr(persona, field, update_data[field])
+        
+        persona.updated_at = datetime.utcnow()
+        session.commit()
+        session.close()
+        
+        return {
+            "message": "Persona updated successfully",
+            "persona_id": persona_id,
+            "updated_at": persona.updated_at.isoformat()
+        }
+        
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"Error updating persona: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"Failed to update persona: {str(e)}")
+
+async def delete_persona(user_id: int, persona_id: int):
+    """Delete a persona (soft delete by setting is_active=False)."""
+    try:
+        from services.database import get_db_session
+        from models.persona_models import WritingPersona, PlatformPersona
+        
+        session = get_db_session()
+        
+        persona = session.query(WritingPersona).filter(
+            WritingPersona.id == persona_id,
+            WritingPersona.user_id == user_id
+        ).first()
+        
+        if not persona:
+            raise HTTPException(status_code=404, detail="Persona not found")
+        
+        # Soft delete persona and platform adaptations
+        persona.is_active = False
+        persona.updated_at = datetime.utcnow()
+        
+        platform_personas = session.query(PlatformPersona).filter(
+            PlatformPersona.writing_persona_id == persona_id
+        ).all()
+        
+        for pp in platform_personas:
+            pp.is_active = False
+            pp.updated_at = datetime.utcnow()
+        
+        session.commit()
+        session.close()
+        
+        return {
+            "message": "Persona deleted successfully",
+            "persona_id": persona_id
+        }
+        
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"Error deleting persona: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"Failed to delete persona: {str(e)}")
+
+async def validate_persona_generation_readiness(user_id: int):
+    """Check if user has sufficient onboarding data for persona generation."""
+    try:
+        persona_service = get_persona_service()
+        
+        # Get onboarding data
+        onboarding_data = persona_service._collect_onboarding_data(user_id)
+        
+        if not onboarding_data:
+            return {
+                "ready": False,
+                "message": "No onboarding data found. Please complete onboarding first.",
+                "missing_steps": ["All onboarding steps"],
+                "data_sufficiency": 0.0
+            }
+        
+        data_sufficiency = persona_service._calculate_data_sufficiency(onboarding_data)
+        
+        missing_steps = []
+        if not onboarding_data.get("website_analysis"):
+            missing_steps.append("Website Analysis (Step 2)")
+        if not onboarding_data.get("research_preferences"):
+            missing_steps.append("Research Preferences (Step 3)")
+        
+        ready = data_sufficiency >= 50.0  # Require at least 50% data sufficiency
+        
+        return {
+            "ready": ready,
+            "message": "Ready for persona generation" if ready else "Insufficient data for reliable persona generation",
+            "missing_steps": missing_steps,
+            "data_sufficiency": data_sufficiency,
+            "recommendations": [
+                "Complete website analysis for better style detection",
+                "Provide research preferences for content type optimization"
+            ] if not ready else []
+        }
+        
+    except Exception as e:
+        logger.error(f"Error validating persona generation readiness: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"Failed to validate readiness: {str(e)}")
+
+async def generate_persona_preview(user_id: int):
+    """Generate a preview of what the persona would look like without saving."""
+    try:
+        persona_service = get_persona_service()
+        
+        # Get onboarding data
+        onboarding_data = persona_service._collect_onboarding_data(user_id)
+        
+        if not onboarding_data:
+            raise HTTPException(status_code=400, detail="No onboarding data available")
+        
+        # Generate core persona (without saving)
+        core_persona = persona_service._generate_core_persona(onboarding_data)
+        
+        if "error" in core_persona:
+            raise HTTPException(status_code=400, detail=core_persona["error"])
+        
+        # Generate sample platform adaptation (just one for preview)
+        sample_platform = "linkedin"
+        platform_preview = persona_service._generate_single_platform_persona(
+            core_persona, sample_platform, onboarding_data
+        )
+        
+        return {
+            "preview": {
+                "identity": core_persona.get("identity", {}),
+                "linguistic_fingerprint": core_persona.get("linguistic_fingerprint", {}),
+                "tonal_range": core_persona.get("tonal_range", {}),
+                "sample_platform": {
+                    "platform": sample_platform,
+                    "adaptation": platform_preview
+                }
+            },
+            "confidence_score": core_persona.get("confidence_score", 0.0),
+            "data_sufficiency": persona_service._calculate_data_sufficiency(onboarding_data)
+        }
+        
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"Error generating persona preview: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"Failed to generate preview: {str(e)}")
+
+async def get_supported_platforms():
+    """Get list of supported platforms for persona generation."""
+    return {
+        "platforms": [
+            {
+                "id": "twitter",
+                "name": "Twitter/X",
+                "description": "Microblogging platform optimized for short, engaging content",
+                "character_limit": 280,
+                "optimal_length": "120-150 characters"
+            },
+            {
+                "id": "linkedin",
+                "name": "LinkedIn",
+                "description": "Professional networking platform for thought leadership content",
+                "character_limit": 3000,
+                "optimal_length": "150-300 words"
+            },
+            {
+                "id": "instagram",
+                "name": "Instagram",
+                "description": "Visual-first platform with engaging captions",
+                "character_limit": 2200,
+                "optimal_length": "125-150 words"
+            },
+            {
+                "id": "facebook",
+                "name": "Facebook",
+                "description": "Social networking platform for community engagement",
+                "character_limit": 63206,
+                "optimal_length": "40-80 words"
+            },
+            {
+                "id": "blog",
+                "name": "Blog Posts",
+                "description": "Long-form content optimized for SEO and engagement",
+                "word_count": "800-2000 words",
+                "seo_optimized": True
+            },
+            {
+                "id": "medium",
+                "name": "Medium",
+                "description": "Publishing platform for storytelling and thought leadership",
+                "word_count": "1000-3000 words",
+                "storytelling_focus": True
+            },
+            {
+                "id": "substack",
+                "name": "Substack",
+                "description": "Newsletter platform for building subscriber relationships",
+                "format": "email newsletter",
+                "subscription_focus": True
+            }
+        ]
+    }

backend/api/persona_routes.py

@@ -0,0 +1,167 @@
+"""
+FastAPI routes for persona management.
+Integrates persona generation and management into the main API.
+"""
+
+from fastapi import APIRouter, HTTPException, Query
+from typing import Dict, Any, Optional
+
+from api.persona import (
+    generate_persona,
+    get_user_personas,
+    get_persona_details,
+    get_platform_persona,
+    update_persona,
+    delete_persona,
+    validate_persona_generation_readiness,
+    generate_persona_preview,
+    get_supported_platforms,
+    PersonaGenerationRequest
+)
+
+from services.persona_replication_engine import PersonaReplicationEngine
+
+# Create router
+router = APIRouter(prefix="/api/personas", tags=["personas"])
+
+@router.post("/generate")
+async def generate_persona_endpoint(
+    request: PersonaGenerationRequest,
+    user_id: int = Query(1, description="User ID")
+):
+    """Generate a new writing persona from onboarding data."""
+    return await generate_persona(user_id, request)
+
+@router.get("/user/{user_id}")
+async def get_user_personas_endpoint(user_id: int):
+    """Get all personas for a user."""
+    return await get_user_personas(user_id)
+
+@router.get("/{persona_id}")
+async def get_persona_details_endpoint(
+    persona_id: int,
+    user_id: int = Query(..., description="User ID")
+):
+    """Get detailed information about a specific persona."""
+    return await get_persona_details(user_id, persona_id)
+
+@router.get("/platform/{platform}")
+async def get_platform_persona_endpoint(
+    platform: str,
+    user_id: int = Query(1, description="User ID")
+):
+    """Get persona adaptation for a specific platform."""
+    return await get_platform_persona(user_id, platform)
+
+@router.put("/{persona_id}")
+async def update_persona_endpoint(
+    persona_id: int,
+    update_data: Dict[str, Any],
+    user_id: int = Query(..., description="User ID")
+):
+    """Update an existing persona."""
+    return await update_persona(user_id, persona_id, update_data)
+
+@router.delete("/{persona_id}")
+async def delete_persona_endpoint(
+    persona_id: int,
+    user_id: int = Query(..., description="User ID")
+):
+    """Delete a persona."""
+    return await delete_persona(user_id, persona_id)
+
+@router.get("/check/readiness")
+async def check_persona_readiness_endpoint(
+    user_id: int = Query(1, description="User ID")
+):
+    """Check if user has sufficient data for persona generation."""
+    return await validate_persona_generation_readiness(user_id)
+
+@router.get("/preview/generate")
+async def generate_preview_endpoint(
+    user_id: int = Query(1, description="User ID")
+):
+    """Generate a preview of the writing persona without saving."""
+    return await generate_persona_preview(user_id)
+
+@router.get("/platforms/supported")
+async def get_supported_platforms_endpoint():
+    """Get list of supported platforms for persona generation."""
+    return await get_supported_platforms()
+
+@router.post("/generate-content")
+async def generate_content_with_persona_endpoint(
+    request: Dict[str, Any]
+):
+    """Generate content using persona replication engine."""
+    try:
+        user_id = request.get("user_id", 1)
+        platform = request.get("platform")
+        content_request = request.get("content_request")
+        content_type = request.get("content_type", "post")
+        
+        if not platform or not content_request:
+            raise HTTPException(status_code=400, detail="Platform and content_request are required")
+        
+        engine = PersonaReplicationEngine()
+        result = engine.generate_content_with_persona(
+            user_id=user_id,
+            platform=platform,
+            content_request=content_request,
+            content_type=content_type
+        )
+        
+        return result
+        
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Content generation failed: {str(e)}")
+
+@router.get("/export/{platform}")
+async def export_persona_prompt_endpoint(
+    platform: str,
+    user_id: int = Query(1, description="User ID")
+):
+    """Export hardened persona prompt for external use."""
+    try:
+        engine = PersonaReplicationEngine()
+        export_package = engine.export_persona_for_external_use(user_id, platform)
+        
+        if "error" in export_package:
+            raise HTTPException(status_code=400, detail=export_package["error"])
+        
+        return export_package
+        
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Export failed: {str(e)}")
+
+@router.post("/validate-content")
+async def validate_content_endpoint(
+    request: Dict[str, Any]
+):
+    """Validate content against persona constraints."""
+    try:
+        user_id = request.get("user_id", 1)
+        platform = request.get("platform")
+        content = request.get("content")
+        
+        if not platform or not content:
+            raise HTTPException(status_code=400, detail="Platform and content are required")
+        
+        engine = PersonaReplicationEngine()
+        persona_data = engine.persona_service.get_persona_for_platform(user_id, platform)
+        
+        if not persona_data:
+            raise HTTPException(status_code=404, detail="No persona found for platform")
+        
+        validation_result = engine._validate_content_fidelity(content, persona_data, platform)
+        
+        return {
+            "validation_result": validation_result,
+            "persona_id": persona_data["core_persona"]["id"],
+            "platform": platform
+        }
+        
+    except HTTPException:
+        raise
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Validation failed: {str(e)}")

backend/app.py

@@ -374,6 +374,10 @@ app.include_router(content_planning_router)
 app.include_router(user_data_router)
 app.include_router(strategy_copilot_router)
 
+# Include persona router
+from api.persona_routes import router as persona_router
+app.include_router(persona_router)
+
 # SEO Dashboard endpoints
 @app.get("/api/seo-dashboard/data")
 async def seo_dashboard_data():

backend/deploy_persona_system.py

@@ -0,0 +1,197 @@
+#!/usr/bin/env python3
+"""
+Deployment script for the Persona System.
+Sets up database tables and validates the complete system.
+"""
+
+import sys
+import os
+
+# Add the backend directory to the Python path
+sys.path.append(os.path.dirname(os.path.abspath(__file__)))
+
+from loguru import logger
+
+def deploy_persona_system():
+    """Deploy the complete persona system."""
+    
+    logger.info("🚀 Deploying Persona System")
+    
+    try:
+        # Step 1: Create database tables
+        logger.info("📊 Step 1: Creating database tables...")
+        from scripts.create_persona_tables import create_persona_tables
+        create_persona_tables()
+        logger.info("✅ Database tables created")
+        
+        # Step 2: Validate Gemini integration
+        logger.info("🤖 Step 2: Validating Gemini integration...")
+        from services.llm_providers.gemini_provider import gemini_structured_json_response
+        
+        test_schema = {
+            "type": "object",
+            "properties": {
+                "status": {"type": "string"},
+                "timestamp": {"type": "string"}
+            },
+            "required": ["status"]
+        }
+        
+        test_response = gemini_structured_json_response(
+            prompt="Return status='ready' and current timestamp",
+            schema=test_schema,
+            temperature=0.1,
+            max_tokens=1024
+        )
+        
+        if "error" in test_response:
+            logger.warning(f"⚠️ Gemini test warning: {test_response['error']}")
+        else:
+            logger.info("✅ Gemini integration validated")
+        
+        # Step 3: Test persona service
+        logger.info("🧠 Step 3: Testing persona service...")
+        from services.persona_analysis_service import PersonaAnalysisService
+        persona_service = PersonaAnalysisService()
+        logger.info("✅ Persona service initialized")
+        
+        # Step 4: Test replication engine
+        logger.info("⚙️ Step 4: Testing replication engine...")
+        from services.persona_replication_engine import PersonaReplicationEngine
+        replication_engine = PersonaReplicationEngine()
+        logger.info("✅ Replication engine initialized")
+        
+        # Step 5: Validate API endpoints
+        logger.info("🌐 Step 5: Validating API endpoints...")
+        from api.persona_routes import router
+        logger.info(f"✅ Persona router configured with {len(router.routes)} routes")
+        
+        logger.info("🎉 Persona System deployed successfully!")
+        
+        # Print deployment summary
+        print_deployment_summary()
+        
+        return True
+        
+    except Exception as e:
+        logger.error(f"❌ Deployment failed: {str(e)}")
+        return False
+
+def print_deployment_summary():
+    """Print deployment summary and next steps."""
+    
+    logger.info("📋 PERSONA SYSTEM DEPLOYMENT SUMMARY")
+    logger.info("=" * 50)
+    
+    logger.info("✅ Database Tables:")
+    logger.info("   - writing_personas")
+    logger.info("   - platform_personas") 
+    logger.info("   - persona_analysis_results")
+    logger.info("   - persona_validation_results")
+    
+    logger.info("✅ Services:")
+    logger.info("   - PersonaAnalysisService")
+    logger.info("   - PersonaReplicationEngine")
+    
+    logger.info("✅ API Endpoints:")
+    logger.info("   - POST /api/personas/generate")
+    logger.info("   - GET /api/personas/user/{user_id}")
+    logger.info("   - GET /api/personas/platform/{platform}")
+    logger.info("   - GET /api/personas/export/{platform}")
+    
+    logger.info("✅ Platform Support:")
+    logger.info("   - Twitter/X, LinkedIn, Instagram, Facebook")
+    logger.info("   - Blog, Medium, Substack")
+    
+    logger.info("🔧 NEXT STEPS:")
+    logger.info("1. Complete onboarding with website analysis (Step 2)")
+    logger.info("2. Set research preferences (Step 3)")
+    logger.info("3. Generate persona in Final Step (Step 6)")
+    logger.info("4. Export hardened prompts for external AI systems")
+    logger.info("5. Use persona for consistent content generation")
+    
+    logger.info("=" * 50)
+
+def validate_deployment():
+    """Validate that all components are working correctly."""
+    
+    logger.info("🔍 Validating deployment...")
+    
+    validation_results = {
+        "database": False,
+        "gemini": False,
+        "persona_service": False,
+        "replication_engine": False,
+        "api_routes": False
+    }
+    
+    try:
+        # Test database
+        from services.database import get_db_session
+        session = get_db_session()
+        if session:
+            session.close()
+            validation_results["database"] = True
+            logger.info("✅ Database connection validated")
+        
+        # Test Gemini
+        from services.llm_providers.gemini_provider import get_gemini_api_key
+        api_key = get_gemini_api_key()
+        if api_key and api_key != "your_gemini_api_key_here":
+            validation_results["gemini"] = True
+            logger.info("✅ Gemini API key configured")
+        else:
+            logger.warning("⚠️ Gemini API key not configured")
+        
+        # Test services
+        from services.persona_analysis_service import PersonaAnalysisService
+        from services.persona_replication_engine import PersonaReplicationEngine
+        
+        PersonaAnalysisService()
+        PersonaReplicationEngine()
+        validation_results["persona_service"] = True
+        validation_results["replication_engine"] = True
+        logger.info("✅ Services validated")
+        
+        # Test API routes
+        from api.persona_routes import router
+        if len(router.routes) > 0:
+            validation_results["api_routes"] = True
+            logger.info("✅ API routes validated")
+        
+    except Exception as e:
+        logger.error(f"❌ Validation error: {str(e)}")
+    
+    # Summary
+    passed = sum(validation_results.values())
+    total = len(validation_results)
+    
+    logger.info(f"📊 Validation Results: {passed}/{total} components validated")
+    
+    if passed == total:
+        logger.info("🎉 All components validated successfully!")
+        return True
+    else:
+        logger.warning("⚠️ Some components failed validation")
+        for component, status in validation_results.items():
+            status_icon = "✅" if status else "❌"
+            logger.info(f"   {status_icon} {component}")
+        return False
+
+if __name__ == "__main__":
+    # Deploy system
+    deployment_success = deploy_persona_system()
+    
+    if deployment_success:
+        # Validate deployment
+        validation_success = validate_deployment()
+        
+        if validation_success:
+            logger.info("🎉 Persona System ready for production!")
+            sys.exit(0)
+        else:
+            logger.error("❌ Deployment validation failed")
+            sys.exit(1)
+    else:
+        logger.error("❌ Deployment failed")
+        sys.exit(1)

backend/models/persona_models.py

@@ -0,0 +1,234 @@
+"""
+Writing Persona Database Models
+Defines database schema for storing writing personas based on onboarding data analysis.
+Each persona represents a platform-specific writing style derived from user's onboarding data.
+"""
+
+from sqlalchemy import Column, Integer, String, Text, DateTime, Float, JSON, ForeignKey, Boolean
+from sqlalchemy.ext.declarative import declarative_base
+from sqlalchemy.orm import relationship
+from datetime import datetime
+
+Base = declarative_base()
+
+class WritingPersona(Base):
+    """Main writing persona model that stores the core persona profile."""
+    
+    __tablename__ = "writing_personas"
+    
+    # Primary fields
+    id = Column(Integer, primary_key=True)
+    user_id = Column(Integer, nullable=False)
+    persona_name = Column(String(255), nullable=False)  # e.g., "Professional LinkedIn Voice", "Casual Blog Writer"
+    
+    # Core Identity
+    archetype = Column(String(100), nullable=True)  # e.g., "The Pragmatic Futurist", "The Thoughtful Educator"
+    core_belief = Column(Text, nullable=True)  # Central philosophy or belief system
+    brand_voice_description = Column(Text, nullable=True)  # Detailed brand voice description
+    
+    # Linguistic Fingerprint - Quantitative Analysis
+    linguistic_fingerprint = Column(JSON, nullable=True)  # Complete linguistic analysis
+    
+    # Platform-specific adaptations
+    platform_adaptations = Column(JSON, nullable=True)  # How persona adapts across platforms
+    
+    # Source data tracking
+    onboarding_session_id = Column(Integer, nullable=True)  # Link to onboarding session
+    source_website_analysis = Column(JSON, nullable=True)  # Website analysis data used
+    source_research_preferences = Column(JSON, nullable=True)  # Research preferences used
+    
+    # AI Analysis metadata
+    ai_analysis_version = Column(String(50), nullable=True)  # Version of AI analysis used
+    confidence_score = Column(Float, nullable=True)  # AI confidence in persona accuracy
+    analysis_date = Column(DateTime, default=datetime.utcnow)
+    
+    # Metadata
+    created_at = Column(DateTime, default=datetime.utcnow)
+    updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
+    is_active = Column(Boolean, default=True)
+    
+    # Relationships
+    platform_personas = relationship("PlatformPersona", back_populates="writing_persona", cascade="all, delete-orphan")
+    
+    def __repr__(self):
+        return f"<WritingPersona(id={self.id}, name='{self.persona_name}', user_id={self.user_id})>"
+    
+    def to_dict(self):
+        """Convert model to dictionary."""
+        return {
+            'id': self.id,
+            'user_id': self.user_id,
+            'persona_name': self.persona_name,
+            'archetype': self.archetype,
+            'core_belief': self.core_belief,
+            'brand_voice_description': self.brand_voice_description,
+            'linguistic_fingerprint': self.linguistic_fingerprint,
+            'platform_adaptations': self.platform_adaptations,
+            'onboarding_session_id': self.onboarding_session_id,
+            'source_website_analysis': self.source_website_analysis,
+            'source_research_preferences': self.source_research_preferences,
+            'ai_analysis_version': self.ai_analysis_version,
+            'confidence_score': self.confidence_score,
+            'analysis_date': self.analysis_date.isoformat() if self.analysis_date else None,
+            'created_at': self.created_at.isoformat() if self.created_at else None,
+            'updated_at': self.updated_at.isoformat() if self.updated_at else None,
+            'is_active': self.is_active
+        }
+
+class PlatformPersona(Base):
+    """Platform-specific persona adaptations for different social media platforms and blogging."""
+    
+    __tablename__ = "platform_personas"
+    
+    # Primary fields
+    id = Column(Integer, primary_key=True)
+    writing_persona_id = Column(Integer, ForeignKey("writing_personas.id"), nullable=False)
+    platform_type = Column(String(50), nullable=False)  # twitter, linkedin, instagram, facebook, blog, medium, substack
+    
+    # Platform-specific linguistic constraints
+    sentence_metrics = Column(JSON, nullable=True)  # Platform-optimized sentence structure
+    lexical_features = Column(JSON, nullable=True)  # Platform-specific vocabulary and phrases
+    rhetorical_devices = Column(JSON, nullable=True)  # Platform-appropriate rhetorical patterns
+    tonal_range = Column(JSON, nullable=True)  # Permitted tones for this platform
+    stylistic_constraints = Column(JSON, nullable=True)  # Platform formatting rules
+    
+    # Platform-specific content guidelines
+    content_format_rules = Column(JSON, nullable=True)  # Character limits, hashtag usage, etc.
+    engagement_patterns = Column(JSON, nullable=True)  # How to engage on this platform
+    posting_frequency = Column(JSON, nullable=True)  # Optimal posting schedule
+    content_types = Column(JSON, nullable=True)  # Preferred content types for platform
+    
+    # Performance optimization
+    platform_best_practices = Column(JSON, nullable=True)  # Platform-specific best practices
+    algorithm_considerations = Column(JSON, nullable=True)  # Platform algorithm optimization
+    
+    # Metadata
+    created_at = Column(DateTime, default=datetime.utcnow)
+    updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
+    is_active = Column(Boolean, default=True)
+    
+    # Relationships
+    writing_persona = relationship("WritingPersona", back_populates="platform_personas")
+    
+    def __repr__(self):
+        return f"<PlatformPersona(id={self.id}, platform='{self.platform_type}', persona_id={self.writing_persona_id})>"
+    
+    def to_dict(self):
+        """Convert model to dictionary."""
+        return {
+            'id': self.id,
+            'writing_persona_id': self.writing_persona_id,
+            'platform_type': self.platform_type,
+            'sentence_metrics': self.sentence_metrics,
+            'lexical_features': self.lexical_features,
+            'rhetorical_devices': self.rhetorical_devices,
+            'tonal_range': self.tonal_range,
+            'stylistic_constraints': self.stylistic_constraints,
+            'content_format_rules': self.content_format_rules,
+            'engagement_patterns': self.engagement_patterns,
+            'posting_frequency': self.posting_frequency,
+            'content_types': self.content_types,
+            'platform_best_practices': self.platform_best_practices,
+            'algorithm_considerations': self.algorithm_considerations,
+            'created_at': self.created_at.isoformat() if self.created_at else None,
+            'updated_at': self.updated_at.isoformat() if self.updated_at else None,
+            'is_active': self.is_active
+        }
+
+class PersonaAnalysisResult(Base):
+    """Stores AI analysis results used to generate personas."""
+    
+    __tablename__ = "persona_analysis_results"
+    
+    id = Column(Integer, primary_key=True)
+    user_id = Column(Integer, nullable=False)
+    writing_persona_id = Column(Integer, ForeignKey("writing_personas.id"), nullable=True)
+    
+    # Analysis input data
+    analysis_prompt = Column(Text, nullable=True)  # The prompt used for analysis
+    input_data = Column(JSON, nullable=True)  # Raw input data from onboarding
+    
+    # AI Analysis results
+    linguistic_analysis = Column(JSON, nullable=True)  # Detailed linguistic fingerprint analysis
+    personality_analysis = Column(JSON, nullable=True)  # Personality and archetype analysis
+    platform_recommendations = Column(JSON, nullable=True)  # Platform-specific recommendations
+    style_guidelines = Column(JSON, nullable=True)  # Generated style guidelines
+    
+    # Quality metrics
+    analysis_confidence = Column(Float, nullable=True)  # AI confidence in analysis
+    data_sufficiency_score = Column(Float, nullable=True)  # How much data was available for analysis
+    recommendation_quality = Column(Float, nullable=True)  # Quality of generated recommendations
+    
+    # AI service metadata
+    ai_provider = Column(String(50), nullable=True)  # gemini, openai, anthropic
+    model_version = Column(String(100), nullable=True)  # Specific model version used
+    processing_time = Column(Float, nullable=True)  # Processing time in seconds
+    
+    # Metadata
+    created_at = Column(DateTime, default=datetime.utcnow)
+    
+    def __repr__(self):
+        return f"<PersonaAnalysisResult(id={self.id}, user_id={self.user_id}, provider='{self.ai_provider}')>"
+    
+    def to_dict(self):
+        """Convert model to dictionary."""
+        return {
+            'id': self.id,
+            'user_id': self.user_id,
+            'writing_persona_id': self.writing_persona_id,
+            'analysis_prompt': self.analysis_prompt,
+            'input_data': self.input_data,
+            'linguistic_analysis': self.linguistic_analysis,
+            'personality_analysis': self.personality_analysis,
+            'platform_recommendations': self.platform_recommendations,
+            'style_guidelines': self.style_guidelines,
+            'analysis_confidence': self.analysis_confidence,
+            'data_sufficiency_score': self.data_sufficiency_score,
+            'recommendation_quality': self.recommendation_quality,
+            'ai_provider': self.ai_provider,
+            'model_version': self.model_version,
+            'processing_time': self.processing_time,
+            'created_at': self.created_at.isoformat() if self.created_at else None
+        }
+
+class PersonaValidationResult(Base):
+    """Stores validation results for generated personas."""
+    
+    __tablename__ = "persona_validation_results"
+    
+    id = Column(Integer, primary_key=True)
+    writing_persona_id = Column(Integer, ForeignKey("writing_personas.id"), nullable=False)
+    platform_persona_id = Column(Integer, ForeignKey("platform_personas.id"), nullable=True)
+    
+    # Validation metrics
+    stylometric_accuracy = Column(Float, nullable=True)  # How well persona matches original style
+    consistency_score = Column(Float, nullable=True)  # Consistency across generated content
+    platform_compliance = Column(Float, nullable=True)  # How well adapted to platform constraints
+    
+    # Test results
+    sample_outputs = Column(JSON, nullable=True)  # Sample content generated with persona
+    validation_feedback = Column(JSON, nullable=True)  # User or automated feedback
+    improvement_suggestions = Column(JSON, nullable=True)  # Suggestions for persona refinement
+    
+    # Metadata
+    validation_date = Column(DateTime, default=datetime.utcnow)
+    validator_type = Column(String(50), nullable=True)  # automated, user, ai_review
+    
+    def __repr__(self):
+        return f"<PersonaValidationResult(id={self.id}, persona_id={self.writing_persona_id}, accuracy={self.stylometric_accuracy})>"
+    
+    def to_dict(self):
+        """Convert model to dictionary."""
+        return {
+            'id': self.id,
+            'writing_persona_id': self.writing_persona_id,
+            'platform_persona_id': self.platform_persona_id,
+            'stylometric_accuracy': self.stylometric_accuracy,
+            'consistency_score': self.consistency_score,
+            'platform_compliance': self.platform_compliance,
+            'sample_outputs': self.sample_outputs,
+            'validation_feedback': self.validation_feedback,
+            'improvement_suggestions': self.improvement_suggestions,
+            'validation_date': self.validation_date.isoformat() if self.validation_date else None,
+            'validator_type': self.validator_type
+        }

backend/scripts/create_all_tables.py

@@ -13,6 +13,7 @@ sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 from services.database import engine
 from models.enhanced_strategy_models import Base as EnhancedStrategyBase
 from models.monitoring_models import Base as MonitoringBase
+from models.persona_models import Base as PersonaBase
 from loguru import logger
 
 def create_all_tables():
@@ -30,6 +31,11 @@ def create_all_tables():
         MonitoringBase.metadata.create_all(bind=engine)
         logger.info("✅ Monitoring tables created!")
         
+        # Step 3: Create persona tables
+        logger.info("Step 3: Creating persona tables...")
+        PersonaBase.metadata.create_all(bind=engine)
+        logger.info("✅ Persona tables created!")
+        
         logger.info("✅ All tables created successfully!")
         
     except Exception as e:

backend/scripts/create_persona_tables.py

@@ -0,0 +1,53 @@
+#!/usr/bin/env python3
+"""
+Script to create persona database tables.
+This script creates the new persona-related tables for storing writing personas.
+"""
+
+import sys
+import os
+
+# Add the backend directory to the Python path
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from services.database import engine
+from models.persona_models import Base as PersonaBase
+from loguru import logger
+
+def create_persona_tables():
+    """Create all persona-related tables"""
+    try:
+        logger.info("Creating persona database tables...")
+        
+        # Create persona tables
+        logger.info("Creating persona tables...")
+        PersonaBase.metadata.create_all(bind=engine)
+        logger.info("✅ Persona tables created!")
+        
+        logger.info("✅ All persona tables created successfully!")
+        
+        # Verify tables were created
+        from sqlalchemy import inspect
+        inspector = inspect(engine)
+        tables = inspector.get_table_names()
+        
+        persona_tables = [
+            'writing_personas',
+            'platform_personas', 
+            'persona_analysis_results',
+            'persona_validation_results'
+        ]
+        
+        created_tables = [table for table in persona_tables if table in tables]
+        logger.info(f"✅ Verified tables created: {created_tables}")
+        
+        if len(created_tables) != len(persona_tables):
+            missing = [table for table in persona_tables if table not in created_tables]
+            logger.warning(f"⚠️ Missing tables: {missing}")
+        
+    except Exception as e:
+        logger.error(f"❌ Error creating persona tables: {e}")
+        sys.exit(1)
+
+if __name__ == "__main__":
+    create_persona_tables()

backend/services/database.py

@@ -17,6 +17,7 @@ from models.content_planning import Base as ContentPlanningBase
 from models.enhanced_strategy_models import Base as EnhancedStrategyBase
 # Monitoring models now use the same base as enhanced strategy models
 from models.monitoring_models import Base as MonitoringBase
+from models.persona_models import Base as PersonaBase
 
 # Database configuration
 DATABASE_URL = os.getenv('DATABASE_URL', 'sqlite:///./alwrity.db')
@@ -57,7 +58,8 @@ def init_database():
         ContentPlanningBase.metadata.create_all(bind=engine)
         EnhancedStrategyBase.metadata.create_all(bind=engine)
         MonitoringBase.metadata.create_all(bind=engine)
-        logger.info("Database initialized successfully with all models")
+        PersonaBase.metadata.create_all(bind=engine)
+        logger.info("Database initialized successfully with all models including personas")
     except SQLAlchemyError as e:
         logger.error(f"Error initializing database: {str(e)}")
         raise

backend/services/persona_analysis_service.py

@@ -0,0 +1,668 @@
+"""
+Persona Analysis Service
+Uses Gemini structured responses to analyze onboarding data and create writing personas.
+"""
+
+from typing import Dict, Any, List, Optional
+from sqlalchemy.orm import Session
+from loguru import logger
+from datetime import datetime
+import json
+
+from services.database import get_db_session
+from models.onboarding import OnboardingSession, WebsiteAnalysis, ResearchPreferences
+from models.persona_models import WritingPersona, PlatformPersona, PersonaAnalysisResult
+from services.llm_providers.gemini_provider import gemini_structured_json_response
+
+class PersonaAnalysisService:
+    """Service for analyzing onboarding data and generating writing personas using Gemini AI."""
+    
+    def __init__(self):
+        """Initialize the persona analysis service."""
+        logger.info("PersonaAnalysisService initialized")
+    
+    def generate_persona_from_onboarding(self, user_id: int, onboarding_session_id: int = None) -> Dict[str, Any]:
+        """
+        Generate a comprehensive writing persona from user's onboarding data.
+        
+        Args:
+            user_id: User ID to generate persona for
+            onboarding_session_id: Optional specific onboarding session ID
+            
+        Returns:
+            Generated persona data with platform adaptations
+        """
+        try:
+            logger.info(f"Generating persona for user {user_id}")
+            
+            # Get onboarding data
+            onboarding_data = self._collect_onboarding_data(user_id, onboarding_session_id)
+            
+            if not onboarding_data:
+                logger.warning(f"No onboarding data found for user {user_id}")
+                return {"error": "No onboarding data available for persona generation"}
+            
+            # Generate core persona using Gemini
+            core_persona = self._generate_core_persona(onboarding_data)
+            
+            if "error" in core_persona:
+                return core_persona
+            
+            # Generate platform-specific adaptations
+            platform_personas = self._generate_platform_adaptations(core_persona, onboarding_data)
+            
+            # Save to database
+            saved_persona = self._save_persona_to_db(user_id, core_persona, platform_personas, onboarding_data)
+            
+            return {
+                "persona_id": saved_persona.id,
+                "core_persona": core_persona,
+                "platform_personas": platform_personas,
+                "analysis_metadata": {
+                    "confidence_score": core_persona.get("confidence_score", 0.0),
+                    "data_sufficiency": self._calculate_data_sufficiency(onboarding_data),
+                    "generated_at": datetime.utcnow().isoformat()
+                }
+            }
+            
+        except Exception as e:
+            logger.error(f"Error generating persona for user {user_id}: {str(e)}")
+            return {"error": f"Failed to generate persona: {str(e)}"}
+    
+    def _collect_onboarding_data(self, user_id: int, session_id: int = None) -> Optional[Dict[str, Any]]:
+        """Collect comprehensive onboarding data for persona analysis."""
+        try:
+            session = get_db_session()
+            
+            # Find onboarding session
+            if session_id:
+                onboarding_session = session.query(OnboardingSession).filter(
+                    OnboardingSession.id == session_id,
+                    OnboardingSession.user_id == user_id
+                ).first()
+            else:
+                onboarding_session = session.query(OnboardingSession).filter(
+                    OnboardingSession.user_id == user_id
+                ).order_by(OnboardingSession.updated_at.desc()).first()
+            
+            if not onboarding_session:
+                return None
+            
+            # Get website analysis
+            website_analysis = session.query(WebsiteAnalysis).filter(
+                WebsiteAnalysis.session_id == onboarding_session.id
+            ).first()
+            
+            # Get research preferences
+            research_prefs = session.query(ResearchPreferences).filter(
+                ResearchPreferences.session_id == onboarding_session.id
+            ).first()
+            
+            # Compile comprehensive data
+            onboarding_data = {
+                "session_info": {
+                    "session_id": onboarding_session.id,
+                    "current_step": onboarding_session.current_step,
+                    "progress": onboarding_session.progress,
+                    "started_at": onboarding_session.started_at.isoformat() if onboarding_session.started_at else None
+                },
+                "website_analysis": website_analysis.to_dict() if website_analysis else None,
+                "research_preferences": research_prefs.to_dict() if research_prefs else None
+            }
+            
+            session.close()
+            return onboarding_data
+            
+        except Exception as e:
+            logger.error(f"Error collecting onboarding data: {str(e)}")
+            return None
+    
+    def _generate_core_persona(self, onboarding_data: Dict[str, Any]) -> Dict[str, Any]:
+        """Generate core writing persona using Gemini structured response."""
+        
+        # Build analysis prompt
+        prompt = self._build_persona_analysis_prompt(onboarding_data)
+        
+        # Define schema for structured response
+        persona_schema = {
+            "type": "object",
+            "properties": {
+                "identity": {
+                    "type": "object",
+                    "properties": {
+                        "persona_name": {"type": "string"},
+                        "archetype": {"type": "string"},
+                        "core_belief": {"type": "string"},
+                        "brand_voice_description": {"type": "string"}
+                    },
+                    "required": ["persona_name", "archetype", "core_belief"]
+                },
+                "linguistic_fingerprint": {
+                    "type": "object",
+                    "properties": {
+                        "sentence_metrics": {
+                            "type": "object",
+                            "properties": {
+                                "average_sentence_length_words": {"type": "number"},
+                                "preferred_sentence_type": {"type": "string"},
+                                "active_to_passive_ratio": {"type": "string"},
+                                "complexity_level": {"type": "string"}
+                            }
+                        },
+                        "lexical_features": {
+                            "type": "object",
+                            "properties": {
+                                "go_to_words": {"type": "array", "items": {"type": "string"}},
+                                "go_to_phrases": {"type": "array", "items": {"type": "string"}},
+                                "avoid_words": {"type": "array", "items": {"type": "string"}},
+                                "contractions": {"type": "string"},
+                                "filler_words": {"type": "string"},
+                                "vocabulary_level": {"type": "string"}
+                            }
+                        },
+                        "rhetorical_devices": {
+                            "type": "object",
+                            "properties": {
+                                "metaphors": {"type": "string"},
+                                "analogies": {"type": "string"},
+                                "rhetorical_questions": {"type": "string"},
+                                "storytelling_style": {"type": "string"}
+                            }
+                        }
+                    }
+                },
+                "tonal_range": {
+                    "type": "object",
+                    "properties": {
+                        "default_tone": {"type": "string"},
+                        "permissible_tones": {"type": "array", "items": {"type": "string"}},
+                        "forbidden_tones": {"type": "array", "items": {"type": "string"}},
+                        "emotional_range": {"type": "string"}
+                    }
+                },
+                "stylistic_constraints": {
+                    "type": "object",
+                    "properties": {
+                        "punctuation": {
+                            "type": "object",
+                            "properties": {
+                                "ellipses": {"type": "string"},
+                                "em_dash": {"type": "string"},
+                                "exclamation_points": {"type": "string"}
+                            }
+                        },
+                        "formatting": {
+                            "type": "object",
+                            "properties": {
+                                "paragraphs": {"type": "string"},
+                                "lists": {"type": "string"},
+                                "markdown": {"type": "string"}
+                            }
+                        }
+                    }
+                },
+                "confidence_score": {"type": "number"},
+                "analysis_notes": {"type": "string"}
+            },
+            "required": ["identity", "linguistic_fingerprint", "tonal_range", "confidence_score"]
+        }
+        
+        try:
+            # Generate structured response using Gemini
+            response = gemini_structured_json_response(
+                prompt=prompt,
+                schema=persona_schema,
+                temperature=0.2,  # Low temperature for consistent analysis
+                max_tokens=8192,
+                system_prompt="You are an expert writing style analyst and persona developer. Analyze the provided data to create a precise, actionable writing persona."
+            )
+            
+            if "error" in response:
+                logger.error(f"Gemini API error: {response['error']}")
+                return {"error": f"AI analysis failed: {response['error']}"}
+            
+            logger.info("✅ Core persona generated successfully")
+            return response
+            
+        except Exception as e:
+            logger.error(f"Error generating core persona: {str(e)}")
+            return {"error": f"Failed to generate core persona: {str(e)}"}
+    
+    def _generate_platform_adaptations(self, core_persona: Dict[str, Any], onboarding_data: Dict[str, Any]) -> Dict[str, Any]:
+        """Generate platform-specific persona adaptations."""
+        
+        platforms = ["twitter", "linkedin", "instagram", "facebook", "blog", "medium", "substack"]
+        platform_personas = {}
+        
+        for platform in platforms:
+            try:
+                platform_persona = self._generate_single_platform_persona(core_persona, platform, onboarding_data)
+                if "error" not in platform_persona:
+                    platform_personas[platform] = platform_persona
+                else:
+                    logger.warning(f"Failed to generate {platform} persona: {platform_persona['error']}")
+            except Exception as e:
+                logger.error(f"Error generating {platform} persona: {str(e)}")
+        
+        return platform_personas
+    
+    def _generate_single_platform_persona(self, core_persona: Dict[str, Any], platform: str, onboarding_data: Dict[str, Any]) -> Dict[str, Any]:
+        """Generate persona adaptation for a specific platform."""
+        
+        prompt = self._build_platform_adaptation_prompt(core_persona, platform, onboarding_data)
+        
+        # Platform-specific schema
+        platform_schema = {
+            "type": "object",
+            "properties": {
+                "platform_type": {"type": "string"},
+                "sentence_metrics": {
+                    "type": "object",
+                    "properties": {
+                        "max_sentence_length": {"type": "number"},
+                        "optimal_sentence_length": {"type": "number"},
+                        "sentence_variety": {"type": "string"}
+                    }
+                },
+                "lexical_adaptations": {
+                    "type": "object",
+                    "properties": {
+                        "platform_specific_words": {"type": "array", "items": {"type": "string"}},
+                        "hashtag_strategy": {"type": "string"},
+                        "emoji_usage": {"type": "string"},
+                        "mention_strategy": {"type": "string"}
+                    }
+                },
+                "content_format_rules": {
+                    "type": "object",
+                    "properties": {
+                        "character_limit": {"type": "number"},
+                        "paragraph_structure": {"type": "string"},
+                        "call_to_action_style": {"type": "string"},
+                        "link_placement": {"type": "string"}
+                    }
+                },
+                "engagement_patterns": {
+                    "type": "object",
+                    "properties": {
+                        "posting_frequency": {"type": "string"},
+                        "optimal_posting_times": {"type": "array", "items": {"type": "string"}},
+                        "engagement_tactics": {"type": "array", "items": {"type": "string"}},
+                        "community_interaction": {"type": "string"}
+                    }
+                },
+                "platform_best_practices": {
+                    "type": "array",
+                    "items": {"type": "string"}
+                }
+            },
+            "required": ["platform_type", "sentence_metrics", "content_format_rules", "engagement_patterns"]
+        }
+        
+        try:
+            response = gemini_structured_json_response(
+                prompt=prompt,
+                schema=platform_schema,
+                temperature=0.2,
+                max_tokens=4096,
+                system_prompt=f"You are an expert in {platform} content strategy and platform-specific writing optimization."
+            )
+            
+            return response
+            
+        except Exception as e:
+            logger.error(f"Error generating {platform} persona: {str(e)}")
+            return {"error": f"Failed to generate {platform} persona: {str(e)}"}
+    
+    def _build_persona_analysis_prompt(self, onboarding_data: Dict[str, Any]) -> str:
+        """Build the main persona analysis prompt."""
+        
+        website_analysis = onboarding_data.get("website_analysis", {})
+        research_prefs = onboarding_data.get("research_preferences", {})
+        
+        prompt = f"""
+PERSONA GENERATION TASK: Create a comprehensive writing persona based on user onboarding data.
+
+ONBOARDING DATA ANALYSIS:
+
+Website Analysis:
+- URL: {website_analysis.get('website_url', 'Not provided')}
+- Writing Style: {json.dumps(website_analysis.get('writing_style', {}), indent=2)}
+- Content Characteristics: {json.dumps(website_analysis.get('content_characteristics', {}), indent=2)}
+- Target Audience: {json.dumps(website_analysis.get('target_audience', {}), indent=2)}
+- Content Type: {json.dumps(website_analysis.get('content_type', {}), indent=2)}
+- Style Patterns: {json.dumps(website_analysis.get('style_patterns', {}), indent=2)}
+
+Research Preferences:
+- Research Depth: {research_prefs.get('research_depth', 'Not set')}
+- Content Types: {research_prefs.get('content_types', [])}
+- Auto Research: {research_prefs.get('auto_research', False)}
+- Factual Content: {research_prefs.get('factual_content', False)}
+
+PERSONA GENERATION REQUIREMENTS:
+
+1. IDENTITY CREATION:
+   - Create a memorable persona name that captures the essence of the writing style
+   - Define a clear archetype (e.g., "The Pragmatic Futurist", "The Thoughtful Educator")
+   - Articulate a core belief that drives the writing philosophy
+   - Write a comprehensive brand voice description
+
+2. LINGUISTIC FINGERPRINT (Quantitative Analysis):
+   - Calculate average sentence length based on website analysis
+   - Determine preferred sentence types (simple, compound, complex)
+   - Analyze active vs passive voice ratio
+   - Identify go-to words and phrases from the content analysis
+   - List words and phrases to avoid
+   - Determine contraction usage patterns
+   - Assess vocabulary complexity level
+
+3. RHETORICAL ANALYSIS:
+   - Identify metaphor patterns and themes
+   - Analyze analogy usage
+   - Assess rhetorical question frequency and style
+   - Determine storytelling approach
+
+4. TONAL RANGE:
+   - Define the default tone
+   - List permissible tones for different contexts
+   - Identify forbidden tones that don't match the brand
+   - Describe emotional range and expression
+
+5. STYLISTIC CONSTRAINTS:
+   - Define punctuation preferences and rules
+   - Set formatting guidelines
+   - Establish paragraph structure preferences
+
+ANALYSIS INSTRUCTIONS:
+- Base your analysis on the actual data provided from the website analysis
+- If data is limited, make reasonable inferences but note the confidence level
+- Ensure the persona is actionable and specific enough for AI content generation
+- Provide a confidence score (0-100) based on data availability and quality
+- Include analysis notes explaining your reasoning
+
+Generate a comprehensive persona profile that can be used to replicate this writing style across different platforms.
+"""
+        
+        return prompt
+    
+    def _build_platform_adaptation_prompt(self, core_persona: Dict[str, Any], platform: str, onboarding_data: Dict[str, Any]) -> str:
+        """Build prompt for platform-specific persona adaptation."""
+        
+        platform_constraints = self._get_platform_constraints(platform)
+        
+        prompt = f"""
+PLATFORM ADAPTATION TASK: Adapt the core writing persona for {platform.upper()}.
+
+CORE PERSONA:
+{json.dumps(core_persona, indent=2)}
+
+PLATFORM: {platform.upper()}
+
+PLATFORM CONSTRAINTS:
+{json.dumps(platform_constraints, indent=2)}
+
+ADAPTATION REQUIREMENTS:
+
+1. SENTENCE METRICS:
+   - Adjust sentence length for platform optimal performance
+   - Adapt sentence variety for platform engagement
+   - Consider platform reading patterns
+
+2. LEXICAL ADAPTATIONS:
+   - Identify platform-specific vocabulary and slang
+   - Define hashtag strategy (if applicable)
+   - Set emoji usage guidelines
+   - Establish mention and tagging strategy
+
+3. CONTENT FORMAT RULES:
+   - Respect character/word limits
+   - Optimize paragraph structure for platform
+   - Define call-to-action style
+   - Set link placement strategy
+
+4. ENGAGEMENT PATTERNS:
+   - Determine optimal posting frequency
+   - Identify best posting times for audience
+   - Define engagement tactics
+   - Set community interaction guidelines
+
+5. PLATFORM BEST PRACTICES:
+   - List platform-specific optimization techniques
+   - Consider algorithm preferences
+   - Include trending format adaptations
+
+INSTRUCTIONS:
+- Maintain the core persona identity while optimizing for platform performance
+- Ensure all adaptations align with the original brand voice
+- Consider platform-specific audience behavior
+- Provide actionable, specific guidelines
+
+Generate a platform-optimized persona adaptation that maintains brand consistency while maximizing platform performance.
+"""
+        
+        return prompt
+    
+    def _get_platform_constraints(self, platform: str) -> Dict[str, Any]:
+        """Get platform-specific constraints and best practices."""
+        
+        constraints = {
+            "twitter": {
+                "character_limit": 280,
+                "optimal_length": "120-150 characters",
+                "hashtag_limit": 3,
+                "image_support": True,
+                "thread_support": True,
+                "link_shortening": True
+            },
+            "linkedin": {
+                "character_limit": 3000,
+                "optimal_length": "150-300 words",
+                "professional_tone": True,
+                "hashtag_limit": 5,
+                "rich_media": True,
+                "long_form": True
+            },
+            "instagram": {
+                "caption_limit": 2200,
+                "optimal_length": "125-150 words",
+                "hashtag_limit": 30,
+                "visual_first": True,
+                "story_support": True,
+                "emoji_friendly": True
+            },
+            "facebook": {
+                "character_limit": 63206,
+                "optimal_length": "40-80 words",
+                "algorithm_favors": "engagement",
+                "link_preview": True,
+                "event_support": True,
+                "group_sharing": True
+            },
+            "blog": {
+                "word_count": "800-2000 words",
+                "seo_important": True,
+                "header_structure": True,
+                "internal_linking": True,
+                "meta_descriptions": True,
+                "readability_score": True
+            },
+            "medium": {
+                "word_count": "1000-3000 words",
+                "storytelling_focus": True,
+                "subtitle_support": True,
+                "publication_support": True,
+                "clap_optimization": True,
+                "follower_building": True
+            },
+            "substack": {
+                "newsletter_format": True,
+                "email_optimization": True,
+                "subscription_focus": True,
+                "long_form": True,
+                "personal_connection": True,
+                "monetization_support": True
+            }
+        }
+        
+        return constraints.get(platform, {})
+    
+    def _save_persona_to_db(self, user_id: int, core_persona: Dict[str, Any], platform_personas: Dict[str, Any], onboarding_data: Dict[str, Any]) -> WritingPersona:
+        """Save generated persona to database."""
+        try:
+            session = get_db_session()
+            
+            # Create main persona record
+            writing_persona = WritingPersona(
+                user_id=user_id,
+                persona_name=core_persona.get("identity", {}).get("persona_name", "Generated Persona"),
+                archetype=core_persona.get("identity", {}).get("archetype"),
+                core_belief=core_persona.get("identity", {}).get("core_belief"),
+                brand_voice_description=core_persona.get("identity", {}).get("brand_voice_description"),
+                linguistic_fingerprint=core_persona.get("linguistic_fingerprint", {}),
+                platform_adaptations={"platforms": list(platform_personas.keys())},
+                onboarding_session_id=onboarding_data.get("session_info", {}).get("session_id"),
+                source_website_analysis=onboarding_data.get("website_analysis"),
+                source_research_preferences=onboarding_data.get("research_preferences"),
+                ai_analysis_version="gemini_v1.0",
+                confidence_score=core_persona.get("confidence_score", 0.0)
+            )
+            
+            session.add(writing_persona)
+            session.commit()
+            session.refresh(writing_persona)
+            
+            # Create platform-specific persona records
+            for platform, platform_data in platform_personas.items():
+                platform_persona = PlatformPersona(
+                    writing_persona_id=writing_persona.id,
+                    platform_type=platform,
+                    sentence_metrics=platform_data.get("sentence_metrics", {}),
+                    lexical_features=platform_data.get("lexical_adaptations", {}),
+                    rhetorical_devices=core_persona.get("linguistic_fingerprint", {}).get("rhetorical_devices", {}),
+                    tonal_range=core_persona.get("tonal_range", {}),
+                    stylistic_constraints=core_persona.get("stylistic_constraints", {}),
+                    content_format_rules=platform_data.get("content_format_rules", {}),
+                    engagement_patterns=platform_data.get("engagement_patterns", {}),
+                    platform_best_practices={"practices": platform_data.get("platform_best_practices", [])}
+                )
+                session.add(platform_persona)
+            
+            # Save analysis result
+            analysis_result = PersonaAnalysisResult(
+                user_id=user_id,
+                writing_persona_id=writing_persona.id,
+                analysis_prompt=self._build_persona_analysis_prompt(onboarding_data)[:5000],  # Truncate for storage
+                input_data=onboarding_data,
+                linguistic_analysis=core_persona.get("linguistic_fingerprint", {}),
+                personality_analysis=core_persona.get("identity", {}),
+                platform_recommendations=platform_personas,
+                style_guidelines=core_persona.get("stylistic_constraints", {}),
+                analysis_confidence=core_persona.get("confidence_score", 0.0),
+                data_sufficiency_score=self._calculate_data_sufficiency(onboarding_data),
+                ai_provider="gemini",
+                model_version="gemini-2.5-flash"
+            )
+            session.add(analysis_result)
+            
+            session.commit()
+            session.close()
+            
+            logger.info(f"✅ Persona saved to database with ID: {writing_persona.id}")
+            return writing_persona
+            
+        except Exception as e:
+            logger.error(f"Error saving persona to database: {str(e)}")
+            if session:
+                session.rollback()
+                session.close()
+            raise
+    
+    def _calculate_data_sufficiency(self, onboarding_data: Dict[str, Any]) -> float:
+        """Calculate how sufficient the onboarding data is for persona generation."""
+        score = 0.0
+        
+        website_analysis = onboarding_data.get("website_analysis", {})
+        research_prefs = onboarding_data.get("research_preferences", {})
+        
+        # Website analysis components (70% of score)
+        if website_analysis.get("writing_style"):
+            score += 25
+        if website_analysis.get("content_characteristics"):
+            score += 20
+        if website_analysis.get("target_audience"):
+            score += 15
+        if website_analysis.get("style_patterns"):
+            score += 10
+        
+        # Research preferences components (30% of score)
+        if research_prefs.get("research_depth"):
+            score += 10
+        if research_prefs.get("content_types"):
+            score += 10
+        if research_prefs.get("writing_style"):
+            score += 10
+        
+        return min(score, 100.0)
+    
+    def get_user_personas(self, user_id: int) -> List[Dict[str, Any]]:
+        """Get all personas for a user."""
+        try:
+            session = get_db_session()
+            
+            personas = session.query(WritingPersona).filter(
+                WritingPersona.user_id == user_id,
+                WritingPersona.is_active == True
+            ).all()
+            
+            result = []
+            for persona in personas:
+                persona_dict = persona.to_dict()
+                
+                # Get platform personas
+                platform_personas = session.query(PlatformPersona).filter(
+                    PlatformPersona.writing_persona_id == persona.id,
+                    PlatformPersona.is_active == True
+                ).all()
+                
+                persona_dict["platforms"] = [pp.to_dict() for pp in platform_personas]
+                result.append(persona_dict)
+            
+            session.close()
+            return result
+            
+        except Exception as e:
+            logger.error(f"Error getting user personas: {str(e)}")
+            return []
+    
+    def get_persona_for_platform(self, user_id: int, platform: str) -> Optional[Dict[str, Any]]:
+        """Get the best persona for a specific platform."""
+        try:
+            session = get_db_session()
+            
+            # Get the most recent active persona
+            persona = session.query(WritingPersona).filter(
+                WritingPersona.user_id == user_id,
+                WritingPersona.is_active == True
+            ).order_by(WritingPersona.created_at.desc()).first()
+            
+            if not persona:
+                return None
+            
+            # Get platform-specific adaptation
+            platform_persona = session.query(PlatformPersona).filter(
+                PlatformPersona.writing_persona_id == persona.id,
+                PlatformPersona.platform_type == platform,
+                PlatformPersona.is_active == True
+            ).first()
+            
+            result = {
+                "core_persona": persona.to_dict(),
+                "platform_adaptation": platform_persona.to_dict() if platform_persona else None
+            }
+            
+            session.close()
+            return result
+            
+        except Exception as e:
+            logger.error(f"Error getting persona for platform {platform}: {str(e)}")
+            return None

backend/services/persona_replication_engine.py

@@ -0,0 +1,506 @@
+"""
+Persona Replication Engine
+Implements the hardened persona replication system for high-fidelity content generation.
+Based on quantitative analysis and structured constraints.
+"""
+
+from typing import Dict, Any, List, Optional
+from loguru import logger
+import json
+
+from services.llm_providers.gemini_provider import gemini_structured_json_response
+from services.persona_analysis_service import PersonaAnalysisService
+
+class PersonaReplicationEngine:
+    """
+    High-fidelity persona replication engine that generates content 
+    indistinguishable from the original author's work.
+    """
+    
+    def __init__(self):
+        """Initialize the persona replication engine."""
+        self.persona_service = PersonaAnalysisService()
+        logger.info("PersonaReplicationEngine initialized")
+    
+    def generate_content_with_persona(self, 
+                                    user_id: int, 
+                                    platform: str, 
+                                    content_request: str, 
+                                    content_type: str = "post") -> Dict[str, Any]:
+        """
+        Generate content using the hardened persona replication system.
+        
+        Args:
+            user_id: User ID for persona lookup
+            platform: Target platform (twitter, linkedin, blog, etc.)
+            content_request: What content to generate
+            content_type: Type of content (post, article, thread, etc.)
+            
+        Returns:
+            Generated content with persona fidelity metrics
+        """
+        try:
+            logger.info(f"Generating {content_type} for {platform} using persona replication")
+            
+            # Get platform-specific persona
+            persona_data = self.persona_service.get_persona_for_platform(user_id, platform)
+            
+            if not persona_data:
+                return {"error": "No persona found for user and platform"}
+            
+            # Build hardened system prompt
+            system_prompt = self._build_hardened_system_prompt(persona_data, platform)
+            
+            # Build content generation prompt
+            content_prompt = self._build_content_prompt(content_request, content_type, platform, persona_data)
+            
+            # Generate content with strict persona constraints
+            content_result = self._generate_constrained_content(
+                system_prompt, content_prompt, platform, persona_data
+            )
+            
+            if "error" in content_result:
+                return content_result
+            
+            # Validate content against persona
+            validation_result = self._validate_content_fidelity(
+                content_result["content"], persona_data, platform
+            )
+            
+            return {
+                "content": content_result["content"],
+                "persona_fidelity_score": validation_result["fidelity_score"],
+                "platform_optimization_score": validation_result["platform_score"],
+                "persona_compliance": validation_result["compliance_check"],
+                "generation_metadata": {
+                    "persona_id": persona_data["core_persona"]["id"],
+                    "platform": platform,
+                    "content_type": content_type,
+                    "generated_at": content_result.get("generated_at"),
+                    "constraints_applied": validation_result["constraints_checked"]
+                }
+            }
+            
+        except Exception as e:
+            logger.error(f"Error in persona replication engine: {str(e)}")
+            return {"error": f"Content generation failed: {str(e)}"}
+    
+    def _build_hardened_system_prompt(self, persona_data: Dict[str, Any], platform: str) -> str:
+        """Build the hardened system prompt for persona replication."""
+        
+        core_persona = persona_data["core_persona"]
+        platform_adaptation = persona_data.get("platform_adaptation", {})
+        
+        # Extract key persona elements
+        identity = core_persona.get("linguistic_fingerprint", {})
+        sentence_metrics = identity.get("sentence_metrics", {})
+        lexical_features = identity.get("lexical_features", {})
+        rhetorical_devices = identity.get("rhetorical_devices", {})
+        tonal_range = core_persona.get("tonal_range", {})
+        
+        # Platform-specific constraints
+        platform_constraints = platform_adaptation.get("content_format_rules", {})
+        engagement_patterns = platform_adaptation.get("engagement_patterns", {})
+        
+        system_prompt = f"""# COMMAND PROTOCOL: PERSONA REPLICATION ENGINE
+# MODEL: [GEMINI-2.5-FLASH]
+# PERSONA: [{core_persona.get('persona_name', 'Generated Persona')}]
+# PLATFORM: [{platform.upper()}]
+# MODE: STRICT MIMICRY
+
+## PRIMARY DIRECTIVE:
+You are now {core_persona.get('persona_name', 'the generated persona')}. Your sole function is to generate {platform} content that is linguistically indistinguishable from the authentic writing of this persona. You must output content that passes stylometric analysis as their work.
+
+## PERSONA PROFILE (IMMUTABLE):
+- **Identity:** {core_persona.get('archetype', 'Professional Writer')}. Core belief: {core_persona.get('core_belief', 'Quality content drives engagement')}.
+- **Tone:** {tonal_range.get('default_tone', 'professional')}. Permissible tones: {', '.join(tonal_range.get('permissible_tones', []))}.
+- **Style:** Average sentence length: {sentence_metrics.get('average_sentence_length_words', 15)} words. Preferred type: {sentence_metrics.get('preferred_sentence_type', 'simple_and_compound')}. Active voice ratio: {sentence_metrics.get('active_to_passive_ratio', '80:20')}.
+- **Lexical Command:** 
+  - USE: {', '.join(lexical_features.get('go_to_words', [])[:5])}
+  - PHRASES: {', '.join(lexical_features.get('go_to_phrases', [])[:3])}
+  - AVOID: {', '.join(lexical_features.get('avoid_words', [])[:5])}
+- **Rhetorical Style:** {rhetorical_devices.get('metaphors', 'minimal metaphors')}, {rhetorical_devices.get('rhetorical_questions', 'occasional questions')}.
+
+## PLATFORM CONSTRAINTS ({platform.upper()}):
+- **Format:** {self._get_platform_format_rules(platform, platform_constraints)}
+- **Engagement:** {engagement_patterns.get('posting_frequency', 'regular posting')}
+- **Optimization:** {self._get_platform_optimization_rules(platform)}
+
+## OPERATIONAL PARAMETERS:
+1. **Fidelity Check:** Before generating, simulate a stylometric analysis of your draft. Does it match the profile's sentence length, word choice, and rhetorical patterns? If not, revise.
+2. **Platform Compliance:** Ensure content meets {platform} best practices and constraints.
+3. **Error State:** If you cannot generate content that meets the Persona Profile standards, output only: "[PERSONA_VIOLATION: Cannot comply without breaking character parameters]".
+4. **Output Format:** Your output must be PURE CONTENT for {platform}. No introductory clauses. No markdown unless platform supports it.
+
+## ACKNOWLEDGEMENT:
+You must silently acknowledge this protocol and begin all responses in character. No confirmation is necessary.
+
+// END PROTOCOL"""
+        
+        return system_prompt
+    
+    def _build_content_prompt(self, content_request: str, content_type: str, platform: str, persona_data: Dict[str, Any]) -> str:
+        """Build the content generation prompt."""
+        
+        platform_adaptation = persona_data.get("platform_adaptation", {})
+        content_format_rules = platform_adaptation.get("content_format_rules", {})
+        
+        prompt = f"""Generate a {content_type} for {platform} about: {content_request}
+
+CONTENT REQUIREMENTS:
+- Platform: {platform}
+- Type: {content_type}
+- Topic: {content_request}
+
+PLATFORM SPECIFICATIONS:
+- Character/Word Limit: {content_format_rules.get('character_limit', 'No limit')}
+- Optimal Length: {content_format_rules.get('optimal_length', 'Platform appropriate')}
+- Format Requirements: {content_format_rules.get('paragraph_structure', 'Standard')}
+
+PERSONA COMPLIANCE:
+- Must match the established linguistic fingerprint
+- Must use the specified lexical features
+- Must maintain the defined tonal range
+- Must follow platform-specific adaptations
+
+Generate content that is indistinguishable from the original author's work while optimized for {platform} performance."""
+        
+        return prompt
+    
+    def _generate_constrained_content(self, system_prompt: str, content_prompt: str, platform: str, persona_data: Dict[str, Any]) -> Dict[str, Any]:
+        """Generate content with strict persona constraints."""
+        
+        # Define content generation schema
+        content_schema = {
+            "type": "object",
+            "properties": {
+                "content": {"type": "string"},
+                "persona_compliance_check": {
+                    "type": "object",
+                    "properties": {
+                        "sentence_length_check": {"type": "boolean"},
+                        "lexical_compliance": {"type": "boolean"},
+                        "tonal_compliance": {"type": "boolean"},
+                        "platform_optimization": {"type": "boolean"}
+                    }
+                },
+                "platform_specific_elements": {
+                    "type": "object",
+                    "properties": {
+                        "hashtags": {"type": "array", "items": {"type": "string"}},
+                        "mentions": {"type": "array", "items": {"type": "string"}},
+                        "call_to_action": {"type": "string"},
+                        "engagement_hooks": {"type": "array", "items": {"type": "string"}}
+                    }
+                },
+                "confidence_score": {"type": "number"}
+            },
+            "required": ["content", "persona_compliance_check", "confidence_score"]
+        }
+        
+        try:
+            response = gemini_structured_json_response(
+                prompt=content_prompt,
+                schema=content_schema,
+                temperature=0.1,  # Very low temperature for consistent persona replication
+                max_tokens=4096,
+                system_prompt=system_prompt
+            )
+            
+            if "error" in response:
+                return {"error": f"Content generation failed: {response['error']}"}
+            
+            response["generated_at"] = logger.info("Content generated with persona constraints")
+            return response
+            
+        except Exception as e:
+            logger.error(f"Error generating constrained content: {str(e)}")
+            return {"error": f"Content generation error: {str(e)}"}
+    
+    def _validate_content_fidelity(self, content: str, persona_data: Dict[str, Any], platform: str) -> Dict[str, Any]:
+        """Validate generated content against persona constraints."""
+        
+        try:
+            # Basic validation metrics
+            validation_result = {
+                "fidelity_score": 0.0,
+                "platform_score": 0.0,
+                "compliance_check": {},
+                "constraints_checked": []
+            }
+            
+            core_persona = persona_data["core_persona"]
+            platform_adaptation = persona_data.get("platform_adaptation", {})
+            
+            # Check sentence length compliance
+            sentences = content.split('.')
+            avg_length = sum(len(s.split()) for s in sentences if s.strip()) / max(len([s for s in sentences if s.strip()]), 1)
+            
+            target_length = core_persona.get("linguistic_fingerprint", {}).get("sentence_metrics", {}).get("average_sentence_length_words", 15)
+            length_compliance = abs(avg_length - target_length) <= 5  # Allow 5-word variance
+            
+            validation_result["compliance_check"]["sentence_length"] = length_compliance
+            validation_result["constraints_checked"].append("sentence_length")
+            
+            # Check lexical compliance
+            lexical_features = core_persona.get("linguistic_fingerprint", {}).get("lexical_features", {})
+            go_to_words = lexical_features.get("go_to_words", [])
+            avoid_words = lexical_features.get("avoid_words", [])
+            
+            content_lower = content.lower()
+            uses_go_to_words = any(word.lower() in content_lower for word in go_to_words[:3])
+            avoids_bad_words = not any(word.lower() in content_lower for word in avoid_words)
+            
+            lexical_compliance = uses_go_to_words and avoids_bad_words
+            validation_result["compliance_check"]["lexical_features"] = lexical_compliance
+            validation_result["constraints_checked"].append("lexical_features")
+            
+            # Check platform constraints
+            platform_constraints = platform_adaptation.get("content_format_rules", {})
+            char_limit = platform_constraints.get("character_limit")
+            
+            platform_compliance = True
+            if char_limit and len(content) > char_limit:
+                platform_compliance = False
+            
+            validation_result["compliance_check"]["platform_constraints"] = platform_compliance
+            validation_result["constraints_checked"].append("platform_constraints")
+            
+            # Calculate overall scores
+            compliance_checks = validation_result["compliance_check"]
+            fidelity_score = sum(compliance_checks.values()) / len(compliance_checks) * 100
+            platform_score = 100 if platform_compliance else 50  # Heavy penalty for platform violations
+            
+            validation_result["fidelity_score"] = fidelity_score
+            validation_result["platform_score"] = platform_score
+            
+            logger.info(f"Content validation: Fidelity={fidelity_score}%, Platform={platform_score}%")
+            return validation_result
+            
+        except Exception as e:
+            logger.error(f"Error validating content fidelity: {str(e)}")
+            return {
+                "fidelity_score": 0.0,
+                "platform_score": 0.0,
+                "compliance_check": {"error": str(e)},
+                "constraints_checked": []
+            }
+    
+    def _get_platform_format_rules(self, platform: str, constraints: Dict[str, Any]) -> str:
+        """Get formatted platform rules for system prompt."""
+        
+        char_limit = constraints.get("character_limit", "No limit")
+        optimal_length = constraints.get("optimal_length", "Platform appropriate")
+        
+        return f"Character limit: {char_limit}, Optimal length: {optimal_length}"
+    
+    def _get_platform_optimization_rules(self, platform: str) -> str:
+        """Get platform optimization rules."""
+        
+        rules = {
+            "twitter": "Use hashtags strategically (max 3), engage with questions, optimize for retweets",
+            "linkedin": "Professional tone, thought leadership focus, encourage professional discussion",
+            "instagram": "Visual-first approach, emoji usage, story-friendly format",
+            "facebook": "Community engagement, shareable content, algorithm-friendly",
+            "blog": "SEO-optimized, scannable format, internal linking",
+            "medium": "Storytelling focus, publication-ready, clap optimization",
+            "substack": "Newsletter format, subscriber value, email-friendly"
+        }
+        
+        return rules.get(platform, "Platform-appropriate optimization")
+    
+    def create_hardened_persona_prompt(self, persona_data: Dict[str, Any], platform: str) -> str:
+        """
+        Create the hardened persona prompt for direct use in AI interfaces.
+        This is the fire-and-forget prompt that can be copied into any AI system.
+        """
+        
+        core_persona = persona_data["core_persona"]
+        platform_adaptation = persona_data.get("platform_adaptation", {})
+        
+        # Extract quantitative data
+        linguistic = core_persona.get("linguistic_fingerprint", {})
+        sentence_metrics = linguistic.get("sentence_metrics", {})
+        lexical_features = linguistic.get("lexical_features", {})
+        rhetorical_devices = linguistic.get("rhetorical_devices", {})
+        tonal_range = core_persona.get("tonal_range", {})
+        
+        hardened_prompt = f"""# COMMAND PROTOCOL: PERSONA REPLICATION ENGINE
+# MODEL: [AI-MODEL]
+# PERSONA: [{core_persona.get('persona_name', 'Generated Persona')}]
+# PLATFORM: [{platform.upper()}]
+# MODE: STRICT MIMICRY
+
+## PRIMARY DIRECTIVE:
+You are now {core_persona.get('persona_name', 'the persona')}. Your sole function is to generate {platform} content that is linguistically indistinguishable from the authentic writing of this persona. You must output content that passes stylometric analysis as their work.
+
+## PERSONA PROFILE (IMMUTABLE):
+- **Identity:** {core_persona.get('archetype', 'Professional Writer')}. Core belief: {core_persona.get('core_belief', 'Quality content drives engagement')}.
+- **Tone:** {tonal_range.get('default_tone', 'professional')}. {f"Permissible: {', '.join(tonal_range.get('permissible_tones', []))}" if tonal_range.get('permissible_tones') else ''}. {f"Forbidden: {', '.join(tonal_range.get('forbidden_tones', []))}" if tonal_range.get('forbidden_tones') else ''}.
+- **Style:** Avg sentence: {sentence_metrics.get('average_sentence_length_words', 15)} words. Type: {sentence_metrics.get('preferred_sentence_type', 'simple_and_compound')}. Active voice: {sentence_metrics.get('active_to_passive_ratio', '80:20')}.
+- **Lexical Command:** 
+  - USE: {', '.join(lexical_features.get('go_to_words', [])[:5]) if lexical_features.get('go_to_words') else 'professional vocabulary'}
+  - PHRASES: {', '.join(lexical_features.get('go_to_phrases', [])[:3]) if lexical_features.get('go_to_phrases') else 'natural transitions'}
+  - AVOID: {', '.join(lexical_features.get('avoid_words', [])[:5]) if lexical_features.get('avoid_words') else 'corporate jargon'}
+- **Rhetorical Style:** {rhetorical_devices.get('metaphors', 'minimal metaphors')}, {rhetorical_devices.get('rhetorical_questions', 'occasional questions')}.
+
+## PLATFORM CONSTRAINTS ({platform.upper()}):
+{self._format_platform_constraints(platform, platform_adaptation)}
+
+## OPERATIONAL PARAMETERS:
+1. **Fidelity Check:** Before generating, verify your draft matches the profile's sentence length ({sentence_metrics.get('average_sentence_length_words', 15)} words avg), word choice, and rhetorical patterns. If not, revise.
+2. **Platform Compliance:** Ensure content meets {platform} format requirements and optimization rules.
+3. **Error State:** If you cannot generate content meeting Persona Profile standards, output: "[PERSONA_VIOLATION: Cannot comply without breaking character parameters]".
+4. **Output Format:** Generate PURE {platform.upper()} CONTENT. No introductory text. No explanations. Only the requested content.
+
+## ACKNOWLEDGEMENT:
+You must silently acknowledge this protocol and begin all responses in character. No confirmation necessary.
+
+// END PROTOCOL
+
+---
+
+## USAGE INSTRUCTIONS:
+1. Copy this entire prompt into your AI system's System Message/Instructions field
+2. Use normal user prompts to request content (e.g., "Write a post about AI trends")
+3. The AI will generate content that matches the persona's style exactly
+4. No additional prompting or style instructions needed
+
+## QUALITY ASSURANCE:
+- Generated content should pass stylometric analysis as the original author
+- Sentence length should average {sentence_metrics.get('average_sentence_length_words', 15)} words
+- Must use specified vocabulary and avoid forbidden words
+- Must maintain {tonal_range.get('default_tone', 'professional')} tone throughout
+- Must comply with {platform} format and engagement requirements"""
+        
+        return hardened_prompt
+    
+    def _format_platform_constraints(self, platform: str, platform_adaptation: Dict[str, Any]) -> str:
+        """Format platform constraints for the hardened prompt."""
+        
+        content_rules = platform_adaptation.get("content_format_rules", {})
+        engagement = platform_adaptation.get("engagement_patterns", {})
+        
+        constraints = []
+        
+        if content_rules.get("character_limit"):
+            constraints.append(f"Character limit: {content_rules['character_limit']}")
+        
+        if content_rules.get("optimal_length"):
+            constraints.append(f"Optimal length: {content_rules['optimal_length']}")
+        
+        if engagement.get("posting_frequency"):
+            constraints.append(f"Frequency: {engagement['posting_frequency']}")
+        
+        if platform == "twitter":
+            constraints.extend([
+                "Max 3 hashtags",
+                "Thread-friendly format",
+                "Engagement-optimized"
+            ])
+        elif platform == "linkedin":
+            constraints.extend([
+                "Professional networking focus",
+                "Thought leadership tone",
+                "Business value emphasis"
+            ])
+        elif platform == "blog":
+            constraints.extend([
+                "SEO-optimized structure",
+                "Scannable format",
+                "Clear headings"
+            ])
+        
+        return "- " + "\n- ".join(constraints) if constraints else "- Standard platform optimization"
+    
+    def export_persona_for_external_use(self, user_id: int, platform: str) -> Dict[str, Any]:
+        """
+        Export a complete persona package for use in external AI systems.
+        This creates a self-contained persona replication system.
+        """
+        try:
+            # Get persona data
+            persona_data = self.persona_service.get_persona_for_platform(user_id, platform)
+            
+            if not persona_data:
+                return {"error": "No persona found"}
+            
+            # Create hardened prompt
+            hardened_prompt = self.create_hardened_persona_prompt(persona_data, platform)
+            
+            # Create usage examples
+            examples = self._generate_usage_examples(persona_data, platform)
+            
+            # Create validation checklist
+            validation_checklist = self._create_validation_checklist(persona_data, platform)
+            
+            export_package = {
+                "persona_metadata": {
+                    "persona_id": persona_data["core_persona"]["id"],
+                    "persona_name": persona_data["core_persona"]["persona_name"],
+                    "platform": platform,
+                    "generated_at": datetime.utcnow().isoformat(),
+                    "confidence_score": persona_data["core_persona"].get("confidence_score", 0.0)
+                },
+                "hardened_system_prompt": hardened_prompt,
+                "usage_examples": examples,
+                "validation_checklist": validation_checklist,
+                "quick_reference": {
+                    "avg_sentence_length": persona_data["core_persona"].get("linguistic_fingerprint", {}).get("sentence_metrics", {}).get("average_sentence_length_words", 15),
+                    "go_to_words": persona_data["core_persona"].get("linguistic_fingerprint", {}).get("lexical_features", {}).get("go_to_words", [])[:5],
+                    "default_tone": persona_data["core_persona"].get("tonal_range", {}).get("default_tone", "professional"),
+                    "platform_limit": persona_data.get("platform_adaptation", {}).get("content_format_rules", {}).get("character_limit", "No limit")
+                }
+            }
+            
+            logger.info(f"✅ Persona export package created for {platform}")
+            return export_package
+            
+        except Exception as e:
+            logger.error(f"Error exporting persona: {str(e)}")
+            return {"error": f"Export failed: {str(e)}"}
+    
+    def _generate_usage_examples(self, persona_data: Dict[str, Any], platform: str) -> List[Dict[str, Any]]:
+        """Generate usage examples for the exported persona."""
+        
+        examples = [
+            {
+                "request": f"Write a {platform} post about AI trends",
+                "expected_style": "Should match persona's sentence length and lexical features",
+                "validation_points": [
+                    "Check average sentence length",
+                    "Verify use of go-to words",
+                    "Confirm tonal compliance",
+                    f"Ensure {platform} optimization"
+                ]
+            },
+            {
+                "request": f"Create {platform} content about productivity tips",
+                "expected_style": "Should maintain consistent voice and rhetorical patterns",
+                "validation_points": [
+                    "Verify rhetorical device usage",
+                    "Check for forbidden words",
+                    "Confirm platform constraints",
+                    "Validate engagement elements"
+                ]
+            }
+        ]
+        
+        return examples
+    
+    def _create_validation_checklist(self, persona_data: Dict[str, Any], platform: str) -> List[str]:
+        """Create a validation checklist for generated content."""
+        
+        core_persona = persona_data["core_persona"]
+        linguistic = core_persona.get("linguistic_fingerprint", {})
+        
+        checklist = [
+            f"✓ Average sentence length ~{linguistic.get('sentence_metrics', {}).get('average_sentence_length_words', 15)} words",
+            f"✓ Uses go-to words: {', '.join(linguistic.get('lexical_features', {}).get('go_to_words', [])[:3])}",
+            f"✓ Avoids forbidden words: {', '.join(linguistic.get('lexical_features', {}).get('avoid_words', [])[:3])}",
+            f"✓ Maintains {core_persona.get('tonal_range', {}).get('default_tone', 'professional')} tone",
+            f"✓ Follows {platform} format requirements",
+            f"✓ Includes appropriate {platform} engagement elements"
+        ]
+        
+        return checklist

backend/test_persona_system.py

@@ -0,0 +1,202 @@
+#!/usr/bin/env python3
+"""
+Test script for the persona generation system.
+Tests the complete flow from onboarding data to persona creation.
+"""
+
+import sys
+import os
+import json
+from datetime import datetime
+
+# Add the backend directory to the Python path
+sys.path.append(os.path.dirname(os.path.abspath(__file__)))
+
+from loguru import logger
+
+def test_persona_system():
+    """Test the complete persona generation system."""
+    
+    logger.info("🧪 Testing Persona Generation System")
+    
+    try:
+        # Test 1: Check database models
+        logger.info("📊 Test 1: Checking database models...")
+        from models.persona_models import WritingPersona, PlatformPersona, PersonaAnalysisResult
+        logger.info("✅ Persona models imported successfully")
+        
+        # Test 2: Check service initialization
+        logger.info("🔧 Test 2: Testing service initialization...")
+        from services.persona_analysis_service import PersonaAnalysisService
+        persona_service = PersonaAnalysisService()
+        logger.info("✅ PersonaAnalysisService initialized successfully")
+        
+        # Test 3: Create sample onboarding data
+        logger.info("📝 Test 3: Creating sample onboarding data...")
+        sample_onboarding_data = create_sample_onboarding_data()
+        logger.info("✅ Sample onboarding data created")
+        
+        # Test 4: Test core persona generation
+        logger.info("🤖 Test 4: Testing core persona generation...")
+        core_persona = persona_service._generate_core_persona(sample_onboarding_data)
+        
+        if "error" in core_persona:
+            logger.error(f"❌ Core persona generation failed: {core_persona['error']}")
+            return False
+        else:
+            logger.info("✅ Core persona generated successfully")
+            logger.info(f"   Persona Name: {core_persona.get('identity', {}).get('persona_name', 'N/A')}")
+            logger.info(f"   Archetype: {core_persona.get('identity', {}).get('archetype', 'N/A')}")
+            logger.info(f"   Confidence: {core_persona.get('confidence_score', 0)}%")
+        
+        # Test 5: Test platform adaptations
+        logger.info("📱 Test 5: Testing platform adaptations...")
+        platforms = ["twitter", "linkedin", "blog"]
+        
+        for platform in platforms:
+            platform_persona = persona_service._generate_single_platform_persona(
+                core_persona, platform, sample_onboarding_data
+            )
+            
+            if "error" in platform_persona:
+                logger.warning(f"⚠️ {platform} persona generation failed: {platform_persona['error']}")
+            else:
+                logger.info(f"✅ {platform} persona generated successfully")
+        
+        # Test 6: Test data sufficiency calculation
+        logger.info("📊 Test 6: Testing data sufficiency calculation...")
+        data_sufficiency = persona_service._calculate_data_sufficiency(sample_onboarding_data)
+        logger.info(f"✅ Data sufficiency calculated: {data_sufficiency}%")
+        
+        logger.info("🎉 All persona system tests completed successfully!")
+        return True
+        
+    except Exception as e:
+        logger.error(f"❌ Persona system test failed: {str(e)}")
+        return False
+
+def create_sample_onboarding_data():
+    """Create realistic sample onboarding data for testing."""
+    
+    return {
+        "session_info": {
+            "session_id": 1,
+            "current_step": 6,
+            "progress": 100.0,
+            "started_at": datetime.utcnow().isoformat()
+        },
+        "website_analysis": {
+            "id": 1,
+            "website_url": "https://techstartup.example.com",
+            "writing_style": {
+                "tone": "professional",
+                "voice": "authoritative",
+                "complexity": "intermediate",
+                "engagement_level": "high"
+            },
+            "content_characteristics": {
+                "sentence_structure": "varied",
+                "vocabulary": "technical",
+                "paragraph_organization": "logical",
+                "average_sentence_length": 15.2
+            },
+            "target_audience": {
+                "demographics": ["startup founders", "tech professionals", "investors"],
+                "expertise_level": "intermediate",
+                "industry_focus": "technology"
+            },
+            "content_type": {
+                "primary_type": "blog",
+                "secondary_types": ["case_study", "tutorial"],
+                "purpose": "educational"
+            },
+            "style_patterns": {
+                "common_phrases": ["let's dive in", "the key insight", "bottom line"],
+                "sentence_starters": ["Here's the thing:", "The reality is", "Consider this:"],
+                "rhetorical_devices": ["metaphors", "data_points", "examples"]
+            },
+            "style_guidelines": {
+                "tone_guidelines": "Maintain professional but approachable tone",
+                "structure_guidelines": "Use clear headings and bullet points",
+                "voice_guidelines": "Confident and knowledgeable without being condescending"
+            },
+            "status": "completed"
+        },
+        "research_preferences": {
+            "id": 1,
+            "research_depth": "Comprehensive",
+            "content_types": ["blog", "case_study", "whitepaper"],
+            "auto_research": True,
+            "factual_content": True,
+            "writing_style": {
+                "tone": "professional",
+                "voice": "authoritative",
+                "complexity": "intermediate"
+            }
+        }
+    }
+
+def test_gemini_structured_response():
+    """Test Gemini structured response functionality."""
+    
+    logger.info("🔬 Testing Gemini Structured Response")
+    
+    try:
+        from services.llm_providers.gemini_provider import gemini_structured_json_response
+        
+        # Simple test schema
+        test_schema = {
+            "type": "object",
+            "properties": {
+                "test_field": {"type": "string"},
+                "confidence": {"type": "number"}
+            },
+            "required": ["test_field", "confidence"]
+        }
+        
+        test_prompt = "Generate a test response with test_field='Hello World' and confidence=95.5"
+        
+        response = gemini_structured_json_response(
+            prompt=test_prompt,
+            schema=test_schema,
+            temperature=0.1,
+            max_tokens=1024
+        )
+        
+        if "error" in response:
+            logger.error(f"❌ Gemini test failed: {response['error']}")
+            return False
+        else:
+            logger.info(f"✅ Gemini structured response test successful: {response}")
+            return True
+            
+    except Exception as e:
+        logger.error(f"❌ Gemini test error: {str(e)}")
+        return False
+
+def run_comprehensive_test():
+    """Run comprehensive test of the persona system."""
+    
+    logger.info("🚀 Starting Comprehensive Persona System Test")
+    
+    # Test 1: Gemini functionality
+    gemini_works = test_gemini_structured_response()
+    
+    # Test 2: Persona system
+    persona_works = test_persona_system()
+    
+    # Summary
+    logger.info("📋 Test Summary:")
+    logger.info(f"   Gemini Structured Response: {'✅ PASS' if gemini_works else '❌ FAIL'}")
+    logger.info(f"   Persona Generation System: {'✅ PASS' if persona_works else '❌ FAIL'}")
+    
+    if gemini_works and persona_works:
+        logger.info("🎉 All tests passed! Persona system is ready for production.")
+        return True
+    else:
+        logger.error("❌ Some tests failed. Please check the logs and fix issues.")
+        return False
+
+if __name__ == "__main__":
+    success = run_comprehensive_test()
+    sys.exit(0 if success else 1)