cim_summary/backend/sql/setup_pg_cron_cleanup.sql

-- ============================================================
-- ALTERNATIVE: PG_CRON AUTOMATED CLEANUP
-- ============================================================
-- NOTE: The primary cleanup runs as a Firebase scheduled
-- function (cleanupOldData in index.ts). This pg_cron
-- approach is an ALTERNATIVE if you prefer database-level
-- scheduling instead.
--
-- Supabase includes pg_cron. This script creates scheduled
-- jobs that automatically enforce retention policies.
--
-- PREREQUISITE: pg_cron extension must be enabled.
-- Go to Supabase Dashboard → Database → Extensions → enable pg_cron
--
-- SCHEDULE: Runs daily at 03:00 UTC (off-peak)
-- ============================================================

-- Enable the pg_cron extension (if not already enabled)
CREATE EXTENSION IF NOT EXISTS pg_cron;

-- Grant usage to postgres role (required on Supabase)
GRANT USAGE ON SCHEMA cron TO postgres;

-- ============================================================
-- Create the cleanup function
-- ============================================================
CREATE OR REPLACE FUNCTION public.cleanup_old_data()
RETURNS jsonb
LANGUAGE plpgsql
SECURITY DEFINER
AS $$
DECLARE
  result jsonb := '{}'::jsonb;
  deleted_count bigint;
BEGIN
  -- 1. Processing jobs: completed/failed older than 30 days
  DELETE FROM processing_jobs
  WHERE status IN ('completed', 'failed')
    AND completed_at < NOW() - INTERVAL '30 days';
  GET DIAGNOSTICS deleted_count = ROW_COUNT;
  result := result || jsonb_build_object('processing_jobs', deleted_count);

  -- 2. Execution events: older than 30 days
  DELETE FROM execution_events
  WHERE created_at < NOW() - INTERVAL '30 days';
  GET DIAGNOSTICS deleted_count = ROW_COUNT;
  result := result || jsonb_build_object('execution_events', deleted_count);

  -- 3. Session events: older than 30 days
  DELETE FROM session_events
  WHERE created_at < NOW() - INTERVAL '30 days';
  GET DIAGNOSTICS deleted_count = ROW_COUNT;
  result := result || jsonb_build_object('session_events', deleted_count);

  -- 4. Performance metrics: older than 90 days
  DELETE FROM performance_metrics
  WHERE created_at < NOW() - INTERVAL '90 days';
  GET DIAGNOSTICS deleted_count = ROW_COUNT;
  result := result || jsonb_build_object('performance_metrics', deleted_count);

  -- 5. Vector similarity searches: older than 90 days
  DELETE FROM vector_similarity_searches
  WHERE created_at < NOW() - INTERVAL '90 days';
  GET DIAGNOSTICS deleted_count = ROW_COUNT;
  result := result || jsonb_build_object('vector_similarity_searches', deleted_count);

  -- 6. Service health checks: older than 30 days (INFR-01)
  DELETE FROM service_health_checks
  WHERE created_at < NOW() - INTERVAL '30 days';
  GET DIAGNOSTICS deleted_count = ROW_COUNT;
  result := result || jsonb_build_object('service_health_checks', deleted_count);

  -- 7. Alert events: resolved older than 30 days (INFR-01)
  DELETE FROM alert_events
  WHERE status = 'resolved'
    AND created_at < NOW() - INTERVAL '30 days';
  GET DIAGNOSTICS deleted_count = ROW_COUNT;
  result := result || jsonb_build_object('alert_events', deleted_count);

  -- 8. Agent executions: older than 90 days
  DELETE FROM agent_executions
  WHERE created_at < NOW() - INTERVAL '90 days';
  GET DIAGNOSTICS deleted_count = ROW_COUNT;
  result := result || jsonb_build_object('agent_executions', deleted_count);

  -- 9. Processing quality metrics: older than 90 days
  DELETE FROM processing_quality_metrics
  WHERE created_at < NOW() - INTERVAL '90 days';
  GET DIAGNOSTICS deleted_count = ROW_COUNT;
  result := result || jsonb_build_object('processing_quality_metrics', deleted_count);

  -- 10. Agentic RAG sessions: completed older than 90 days
  DELETE FROM agentic_rag_sessions
  WHERE status IN ('completed', 'failed')
    AND created_at < NOW() - INTERVAL '90 days';
  GET DIAGNOSTICS deleted_count = ROW_COUNT;
  result := result || jsonb_build_object('agentic_rag_sessions', deleted_count);

  -- 11. Null out extracted_text for completed documents older than 30 days
  UPDATE documents
  SET extracted_text = NULL
  WHERE status = 'completed'
    AND analysis_data IS NOT NULL
    AND extracted_text IS NOT NULL
    AND created_at < NOW() - INTERVAL '30 days';
  GET DIAGNOSTICS deleted_count = ROW_COUNT;
  result := result || jsonb_build_object('documents_text_nulled', deleted_count);

  RETURN result;
END;
$$;

-- ============================================================
-- Schedule the cron job: daily at 03:00 UTC
-- ============================================================
SELECT cron.schedule(
  'daily-cleanup-old-data',          -- job name
  '0 3 * * *',                       -- cron expression: 3 AM UTC daily
  $$SELECT public.cleanup_old_data()$$
);

-- ============================================================
-- Verify the job was created
-- ============================================================
SELECT * FROM cron.job WHERE jobname = 'daily-cleanup-old-data';

-- ============================================================
-- MANAGEMENT COMMANDS (for reference)
-- ============================================================

-- View all scheduled jobs:
-- SELECT * FROM cron.job;

-- View recent job runs and results:
-- SELECT * FROM cron.job_run_details ORDER BY start_time DESC LIMIT 20;

-- Run cleanup manually (to test):
-- SELECT public.cleanup_old_data();

-- Unschedule the job:
-- SELECT cron.unschedule('daily-cleanup-old-data');

-- Change schedule to weekly (Sundays at 3 AM):
-- SELECT cron.unschedule('daily-cleanup-old-data');
-- SELECT cron.schedule('weekly-cleanup-old-data', '0 3 * * 0', $$SELECT public.cleanup_old_data()$$);