Base code

backend/database/migrations/006_add_exa_provider.sql

@@ -0,0 +1,17 @@
+-- Add EXA to subscription plans
+ALTER TABLE subscription_plans 
+ADD COLUMN exa_calls_limit INT DEFAULT 0;
+
+-- Add EXA to usage summaries
+ALTER TABLE usage_summaries 
+ADD COLUMN exa_calls INT DEFAULT 0;
+
+ALTER TABLE usage_summaries 
+ADD COLUMN exa_cost FLOAT DEFAULT 0.0;
+
+-- Update default limits for existing plans
+UPDATE subscription_plans SET exa_calls_limit = 100 WHERE tier = 'free';
+UPDATE subscription_plans SET exa_calls_limit = 500 WHERE tier = 'basic';
+UPDATE subscription_plans SET exa_calls_limit = 2000 WHERE tier = 'pro';
+UPDATE subscription_plans SET exa_calls_limit = 0 WHERE tier = 'enterprise';
+

backend/database/migrations/add_business_info_table.sql

@@ -0,0 +1,27 @@
+-- Migration: Add user_business_info table
+-- Description: Creates table for storing business information when users don't have websites
+-- Date: 2024-01-XX
+
+CREATE TABLE IF NOT EXISTS user_business_info (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    user_id INTEGER,
+    business_description TEXT NOT NULL,
+    industry VARCHAR(100),
+    target_audience TEXT,
+    business_goals TEXT,
+    created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
+    updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
+);
+
+-- Create index for faster user lookups
+CREATE INDEX IF NOT EXISTS idx_user_business_info_user_id ON user_business_info(user_id);
+
+-- Add trigger to automatically update updated_at timestamp
+CREATE TRIGGER IF NOT EXISTS update_user_business_info_timestamp 
+    AFTER UPDATE ON user_business_info
+    FOR EACH ROW
+BEGIN
+    UPDATE user_business_info 
+    SET updated_at = CURRENT_TIMESTAMP 
+    WHERE id = NEW.id;
+END;

backend/database/migrations/add_persona_data_table.sql

@@ -0,0 +1,26 @@
+-- Migration: Add persona_data table for onboarding step 4
+-- Created: 2025-10-10
+-- Description: Adds table to store persona generation data from onboarding step 4
+
+CREATE TABLE IF NOT EXISTS persona_data (
+    id SERIAL PRIMARY KEY,
+    session_id INTEGER NOT NULL,
+    core_persona JSONB,
+    platform_personas JSONB,
+    quality_metrics JSONB,
+    selected_platforms JSONB,
+    created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
+    updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
+    FOREIGN KEY (session_id) REFERENCES onboarding_sessions(id) ON DELETE CASCADE
+);
+
+-- Add index for better query performance
+CREATE INDEX IF NOT EXISTS idx_persona_data_session_id ON persona_data(session_id);
+CREATE INDEX IF NOT EXISTS idx_persona_data_created_at ON persona_data(created_at);
+
+-- Add comment to table
+COMMENT ON TABLE persona_data IS 'Stores persona generation data from onboarding step 4';
+COMMENT ON COLUMN persona_data.core_persona IS 'Core persona data (demographics, psychographics, etc.)';
+COMMENT ON COLUMN persona_data.platform_personas IS 'Platform-specific personas (LinkedIn, Twitter, etc.)';
+COMMENT ON COLUMN persona_data.quality_metrics IS 'Quality assessment metrics';
+COMMENT ON COLUMN persona_data.selected_platforms IS 'Array of selected platforms';

backend/database/migrations/add_user_id_to_task_execution_logs.sql

@@ -0,0 +1,20 @@
+-- Migration: Add user_id column to task_execution_logs for user isolation
+-- Date: 2025-01-XX
+-- Purpose: Enable user isolation tracking in scheduler task execution logs
+
+-- Add user_id column (nullable for backward compatibility with existing records)
+ALTER TABLE task_execution_logs 
+ADD COLUMN user_id INTEGER NULL;
+
+-- Create index for efficient user filtering and queries
+CREATE INDEX IF NOT EXISTS idx_task_execution_logs_user_id 
+ON task_execution_logs(user_id);
+
+-- Create composite index for common query patterns (user_id + status + execution_date)
+CREATE INDEX IF NOT EXISTS idx_task_execution_logs_user_status_date 
+ON task_execution_logs(user_id, status, execution_date);
+
+-- Note: Backfilling existing records would require joining with monitoring_tasks 
+-- and enhanced_content_strategies tables. This can be done in a separate migration
+-- or during a maintenance window. For now, existing records will have user_id = NULL.
+

backend/database/migrations/create_blog_writer_tasks.sql

@@ -0,0 +1,149 @@
+-- Blog Writer Task Persistence Tables
+-- Creates tables for storing task state, progress, and metrics
+
+-- Tasks table - stores main task information
+CREATE TABLE IF NOT EXISTS blog_writer_tasks (
+    id VARCHAR(36) PRIMARY KEY,
+    user_id VARCHAR(36) NOT NULL,
+    task_type VARCHAR(50) NOT NULL, -- 'research', 'outline', 'content', 'seo', 'medium_generation'
+    status VARCHAR(20) NOT NULL DEFAULT 'pending', -- 'pending', 'running', 'completed', 'failed', 'cancelled'
+    request_data JSONB, -- Original request parameters
+    result_data JSONB, -- Final result data
+    error_data JSONB, -- Error information if failed
+    created_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
+    updated_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
+    completed_at TIMESTAMP WITH TIME ZONE,
+    correlation_id VARCHAR(36), -- For request tracing
+    operation VARCHAR(100), -- Specific operation being performed
+    retry_count INTEGER DEFAULT 0, -- Number of retry attempts
+    max_retries INTEGER DEFAULT 3, -- Maximum retry attempts allowed
+    priority INTEGER DEFAULT 0, -- Task priority (higher = more important)
+    metadata JSONB -- Additional metadata
+);
+
+-- Task progress table - stores progress updates
+CREATE TABLE IF NOT EXISTS blog_writer_task_progress (
+    id SERIAL PRIMARY KEY,
+    task_id VARCHAR(36) NOT NULL REFERENCES blog_writer_tasks(id) ON DELETE CASCADE,
+    timestamp TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
+    message TEXT NOT NULL,
+    percentage DECIMAL(5,2) DEFAULT 0.00, -- 0.00 to 100.00
+    progress_type VARCHAR(50) DEFAULT 'info', -- 'info', 'warning', 'error', 'success'
+    metadata JSONB -- Additional progress metadata
+);
+
+-- Task metrics table - stores performance metrics
+CREATE TABLE IF NOT EXISTS blog_writer_task_metrics (
+    id SERIAL PRIMARY KEY,
+    task_id VARCHAR(36) NOT NULL REFERENCES blog_writer_tasks(id) ON DELETE CASCADE,
+    operation VARCHAR(100) NOT NULL,
+    duration_ms INTEGER NOT NULL,
+    token_usage JSONB, -- Token usage statistics
+    api_calls INTEGER DEFAULT 0,
+    cache_hits INTEGER DEFAULT 0,
+    cache_misses INTEGER DEFAULT 0,
+    error_count INTEGER DEFAULT 0,
+    created_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
+    metadata JSONB -- Additional metrics
+);
+
+-- Task recovery table - stores recovery information
+CREATE TABLE IF NOT EXISTS blog_writer_task_recovery (
+    id SERIAL PRIMARY KEY,
+    task_id VARCHAR(36) NOT NULL REFERENCES blog_writer_tasks(id) ON DELETE CASCADE,
+    recovery_reason VARCHAR(100) NOT NULL, -- 'server_restart', 'timeout', 'error'
+    recovery_action VARCHAR(100) NOT NULL, -- 'resume', 'retry', 'fail'
+    checkpoint_data JSONB, -- State at recovery point
+    recovered_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
+    recovery_successful BOOLEAN DEFAULT FALSE,
+    metadata JSONB
+);
+
+-- Indexes for performance
+CREATE INDEX IF NOT EXISTS idx_blog_writer_tasks_user_id ON blog_writer_tasks(user_id);
+CREATE INDEX IF NOT EXISTS idx_blog_writer_tasks_status ON blog_writer_tasks(status);
+CREATE INDEX IF NOT EXISTS idx_blog_writer_tasks_created_at ON blog_writer_tasks(created_at);
+CREATE INDEX IF NOT EXISTS idx_blog_writer_tasks_task_type ON blog_writer_tasks(task_type);
+CREATE INDEX IF NOT EXISTS idx_blog_writer_tasks_correlation_id ON blog_writer_tasks(correlation_id);
+
+CREATE INDEX IF NOT EXISTS idx_blog_writer_task_progress_task_id ON blog_writer_task_progress(task_id);
+CREATE INDEX IF NOT EXISTS idx_blog_writer_task_progress_timestamp ON blog_writer_task_progress(timestamp);
+
+CREATE INDEX IF NOT EXISTS idx_blog_writer_task_metrics_task_id ON blog_writer_task_metrics(task_id);
+CREATE INDEX IF NOT EXISTS idx_blog_writer_task_metrics_operation ON blog_writer_task_metrics(operation);
+CREATE INDEX IF NOT EXISTS idx_blog_writer_task_metrics_created_at ON blog_writer_task_metrics(created_at);
+
+CREATE INDEX IF NOT EXISTS idx_blog_writer_task_recovery_task_id ON blog_writer_task_recovery(task_id);
+CREATE INDEX IF NOT EXISTS idx_blog_writer_task_recovery_recovered_at ON blog_writer_task_recovery(recovered_at);
+
+-- Function to automatically update updated_at timestamp
+CREATE OR REPLACE FUNCTION update_blog_writer_tasks_updated_at()
+RETURNS TRIGGER AS $$
+BEGIN
+    NEW.updated_at = NOW();
+    RETURN NEW;
+END;
+$$ language 'plpgsql';
+
+-- Trigger to automatically update updated_at
+CREATE TRIGGER update_blog_writer_tasks_updated_at
+    BEFORE UPDATE ON blog_writer_tasks
+    FOR EACH ROW
+    EXECUTE FUNCTION update_blog_writer_tasks_updated_at();
+
+-- Function to clean up old completed tasks (older than 7 days)
+CREATE OR REPLACE FUNCTION cleanup_old_blog_writer_tasks()
+RETURNS INTEGER AS $$
+DECLARE
+    deleted_count INTEGER;
+BEGIN
+    DELETE FROM blog_writer_tasks 
+    WHERE status IN ('completed', 'failed', 'cancelled') 
+    AND created_at < NOW() - INTERVAL '7 days';
+    
+    GET DIAGNOSTICS deleted_count = ROW_COUNT;
+    RETURN deleted_count;
+END;
+$$ language 'plpgsql';
+
+-- Create a view for task analytics
+CREATE OR REPLACE VIEW blog_writer_task_analytics AS
+SELECT 
+    task_type,
+    status,
+    COUNT(*) as task_count,
+    AVG(EXTRACT(EPOCH FROM (completed_at - created_at))) as avg_duration_seconds,
+    AVG(EXTRACT(EPOCH FROM (updated_at - created_at))) as avg_processing_time_seconds,
+    COUNT(CASE WHEN status = 'completed' THEN 1 END) as completed_count,
+    COUNT(CASE WHEN status = 'failed' THEN 1 END) as failed_count,
+    COUNT(CASE WHEN status = 'running' THEN 1 END) as running_count,
+    ROUND(
+        COUNT(CASE WHEN status = 'completed' THEN 1 END) * 100.0 / COUNT(*), 
+        2
+    ) as success_rate_percentage
+FROM blog_writer_tasks
+WHERE created_at >= NOW() - INTERVAL '30 days'
+GROUP BY task_type, status
+ORDER BY task_type, status;
+
+-- Create a view for performance metrics
+CREATE OR REPLACE VIEW blog_writer_performance_metrics AS
+SELECT 
+    t.task_type,
+    t.operation,
+    COUNT(m.id) as metric_count,
+    AVG(m.duration_ms) as avg_duration_ms,
+    MIN(m.duration_ms) as min_duration_ms,
+    MAX(m.duration_ms) as max_duration_ms,
+    SUM(m.api_calls) as total_api_calls,
+    SUM(m.cache_hits) as total_cache_hits,
+    SUM(m.cache_misses) as total_cache_misses,
+    ROUND(
+        SUM(m.cache_hits) * 100.0 / NULLIF(SUM(m.cache_hits + m.cache_misses), 0), 
+        2
+    ) as cache_hit_rate_percentage
+FROM blog_writer_tasks t
+LEFT JOIN blog_writer_task_metrics m ON t.id = m.task_id
+WHERE t.created_at >= NOW() - INTERVAL '7 days'
+GROUP BY t.task_type, t.operation
+ORDER BY t.task_type, t.operation;

backend/database/migrations/update_onboarding_user_id_to_string.sql

@@ -0,0 +1,16 @@
+-- Migration: Update onboarding_sessions.user_id from INTEGER to STRING
+-- This migration updates the user_id column to support Clerk user IDs (strings)
+
+-- Step 1: Alter the user_id column type from INTEGER to VARCHAR(255)
+ALTER TABLE onboarding_sessions 
+ALTER COLUMN user_id TYPE VARCHAR(255);
+
+-- Step 2: Create an index on user_id for faster lookups
+CREATE INDEX IF NOT EXISTS idx_onboarding_sessions_user_id ON onboarding_sessions(user_id);
+
+-- Note: This migration assumes no existing data needs to be preserved
+-- If you have existing data with integer user_ids, you may need to:
+-- 1. Backup the data first
+-- 2. Clear the table or convert the integers to strings
+-- 3. Then apply this migration
+