-- ============================================================
-- CHECK TABLE SIZES - Run in Supabase SQL Editor
-- ============================================================
-- Part 1: Shows all public tables with sizes (auto-discovers)
-- Part 2: Cleanup candidate counts (only for tables that exist)
-- ============================================================

-- PART 1: All public table sizes
SELECT
  c.relname AS table_name,
  pg_size_pretty(pg_total_relation_size(c.oid)) AS total_size,
  pg_size_pretty(pg_relation_size(c.oid)) AS data_size,
  pg_size_pretty(pg_total_relation_size(c.oid) - pg_relation_size(c.oid)) AS index_size,
  c.reltuples::bigint AS estimated_rows
FROM pg_class c
JOIN pg_namespace n ON n.oid = c.relnamespace
WHERE n.nspname = 'public'
  AND c.relkind = 'r'
ORDER BY pg_total_relation_size(c.oid) DESC;

-- PART 2: Cleanup candidates (safe — checks table existence before querying)
DO $$
DECLARE
  rec RECORD;
  row_count bigint;
  cleanup_count bigint;
  query text;
BEGIN
  RAISE NOTICE '--- CLEANUP CANDIDATE BREAKDOWN ---';

  -- Processing jobs
  IF EXISTS (SELECT 1 FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace WHERE n.nspname = 'public' AND c.relname = 'processing_jobs') THEN
    SELECT count(*), count(*) FILTER (WHERE status IN ('completed', 'failed') AND completed_at < NOW() - INTERVAL '30 days')
    INTO row_count, cleanup_count FROM processing_jobs;
    RAISE NOTICE 'processing_jobs: % total, % cleanup candidates (completed/failed > 30d)', row_count, cleanup_count;
  END IF;

  -- Vector similarity searches
  IF EXISTS (SELECT 1 FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace WHERE n.nspname = 'public' AND c.relname = 'vector_similarity_searches') THEN
    SELECT count(*), count(*) FILTER (WHERE created_at < NOW() - INTERVAL '90 days')
    INTO row_count, cleanup_count FROM vector_similarity_searches;
    RAISE NOTICE 'vector_similarity_searches: % total, % cleanup candidates (> 90d)', row_count, cleanup_count;
  END IF;

  -- Session events
  IF EXISTS (SELECT 1 FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace WHERE n.nspname = 'public' AND c.relname = 'session_events') THEN
    SELECT count(*), count(*) FILTER (WHERE created_at < NOW() - INTERVAL '30 days')
    INTO row_count, cleanup_count FROM session_events;
    RAISE NOTICE 'session_events: % total, % cleanup candidates (> 30d)', row_count, cleanup_count;
  END IF;

  -- Execution events
  IF EXISTS (SELECT 1 FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace WHERE n.nspname = 'public' AND c.relname = 'execution_events') THEN
    SELECT count(*), count(*) FILTER (WHERE created_at < NOW() - INTERVAL '30 days')
    INTO row_count, cleanup_count FROM execution_events;
    RAISE NOTICE 'execution_events: % total, % cleanup candidates (> 30d)', row_count, cleanup_count;
  END IF;

  -- Performance metrics
  IF EXISTS (SELECT 1 FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace WHERE n.nspname = 'public' AND c.relname = 'performance_metrics') THEN
    SELECT count(*), count(*) FILTER (WHERE created_at < NOW() - INTERVAL '90 days')
    INTO row_count, cleanup_count FROM performance_metrics;
    RAISE NOTICE 'performance_metrics: % total, % cleanup candidates (> 90d)', row_count, cleanup_count;
  END IF;

  -- Service health checks
  IF EXISTS (SELECT 1 FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace WHERE n.nspname = 'public' AND c.relname = 'service_health_checks') THEN
    SELECT count(*), count(*) FILTER (WHERE created_at < NOW() - INTERVAL '30 days')
    INTO row_count, cleanup_count FROM service_health_checks;
    RAISE NOTICE 'service_health_checks: % total, % cleanup candidates (> 30d)', row_count, cleanup_count;
  END IF;

  -- Alert events
  IF EXISTS (SELECT 1 FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace WHERE n.nspname = 'public' AND c.relname = 'alert_events') THEN
    SELECT count(*), count(*) FILTER (WHERE created_at < NOW() - INTERVAL '30 days')
    INTO row_count, cleanup_count FROM alert_events;
    RAISE NOTICE 'alert_events: % total, % cleanup candidates (> 30d)', row_count, cleanup_count;
  END IF;

  -- Agent executions
  IF EXISTS (SELECT 1 FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace WHERE n.nspname = 'public' AND c.relname = 'agent_executions') THEN
    SELECT count(*), count(*) FILTER (WHERE created_at < NOW() - INTERVAL '90 days')
    INTO row_count, cleanup_count FROM agent_executions;
    RAISE NOTICE 'agent_executions: % total, % cleanup candidates (> 90d)', row_count, cleanup_count;
  END IF;

  -- Agentic RAG sessions
  IF EXISTS (SELECT 1 FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace WHERE n.nspname = 'public' AND c.relname = 'agentic_rag_sessions') THEN
    SELECT count(*), count(*) FILTER (WHERE created_at < NOW() - INTERVAL '90 days')
    INTO row_count, cleanup_count FROM agentic_rag_sessions;
    RAISE NOTICE 'agentic_rag_sessions: % total, % cleanup candidates (> 90d)', row_count, cleanup_count;
  END IF;

  -- Processing quality metrics
  IF EXISTS (SELECT 1 FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace WHERE n.nspname = 'public' AND c.relname = 'processing_quality_metrics') THEN
    SELECT count(*), count(*) FILTER (WHERE created_at < NOW() - INTERVAL '90 days')
    INTO row_count, cleanup_count FROM processing_quality_metrics;
    RAISE NOTICE 'processing_quality_metrics: % total, % cleanup candidates (> 90d)', row_count, cleanup_count;
  END IF;

  -- Documents extracted_text
  IF EXISTS (SELECT 1 FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace WHERE n.nspname = 'public' AND c.relname = 'documents') THEN
    SELECT count(*), count(*) FILTER (WHERE status = 'completed' AND analysis_data IS NOT NULL AND extracted_text IS NOT NULL AND created_at < NOW() - INTERVAL '30 days')
    INTO row_count, cleanup_count FROM documents;
    RAISE NOTICE 'documents (extracted_text nullable): % total, % cleanup candidates (completed > 30d with analysis_data)', row_count, cleanup_count;
  END IF;

  RAISE NOTICE '--- END CLEANUP BREAKDOWN ---';
END $$;