-- Phase 4 운영 점검 SQL — 4-A (study_question_jobs) + 4-B (study_quiz_session_jobs)
-- 사용:
--   ssh gpu 'docker exec -i hyungi_document_server-postgres-1 psql -U pkm pkm' < scripts/phase4_health.sql
-- 또는 개별 SECTION 만 골라 실행. 모든 섹션은 read-only.

\echo '── 1. 4-A study_question_jobs status × error_code 분포 ──'
SELECT
    status,
    COALESCE(error_code, '(none)') AS error_code,
    COUNT(*) AS cnt
FROM study_question_jobs
GROUP BY status, error_code
ORDER BY status, error_code;

\echo ''
\echo '── 2. 4-B study_quiz_session_jobs status × error_code 분포 ──'
SELECT
    status,
    COALESCE(error_code, '(none)') AS error_code,
    COUNT(*) AS cnt
FROM study_quiz_session_jobs
GROUP BY status, error_code
ORDER BY status, error_code;

\echo ''
\echo '── 3. 4-B study_quiz_session_analysis confidence 분포 (calibrated) ──'
SELECT
    COALESCE(confidence, '(null)') AS confidence,
    COUNT(*) AS cnt,
    COUNT(*) FILTER (WHERE is_stale) AS stale_count
FROM study_quiz_session_analysis
GROUP BY confidence
ORDER BY
    CASE COALESCE(confidence, '(null)')
        WHEN 'high' THEN 0
        WHEN 'medium' THEN 1
        WHEN 'low' THEN 2
        ELSE 3
    END;

\echo ''
\echo '── 4. 4-B confidence calibration 차이 (job.payload 기반) ──'
\echo '   model_confidence_raw vs calibrated_confidence — 자료 부족 cap 작동 빈도 측정'
SELECT
    payload->>'model_confidence_raw' AS model_raw,
    payload->>'calibrated_confidence' AS calibrated,
    (payload->>'ctx_docs_count')::int AS docs_n,
    (payload->>'ready_explanation_count')::int AS ready_n,
    COUNT(*) AS cnt
FROM study_quiz_session_jobs
WHERE status = 'completed'
  AND payload IS NOT NULL
  AND payload ? 'model_confidence_raw'
GROUP BY model_raw, calibrated, docs_n, ready_n
ORDER BY cnt DESC
LIMIT 20;

\echo ''
\echo '── 5. 4-A/4-B 최근 7일 처리 지연 (created_at → completed_at) ──'
\echo '   p50/p95/max 단순 ROUND(EXTRACT). 4-A 와 4-B 분리.'
SELECT
    'study_question_jobs' AS source,
    COUNT(*) AS terminal_n,
    ROUND(AVG(EXTRACT(EPOCH FROM (completed_at - created_at)))::numeric, 1) AS avg_sec,
    ROUND(MAX(EXTRACT(EPOCH FROM (completed_at - created_at)))::numeric, 1) AS max_sec,
    ROUND((PERCENTILE_CONT(0.5) WITHIN GROUP (
        ORDER BY EXTRACT(EPOCH FROM (completed_at - created_at))
    ))::numeric, 1) AS p50_sec,
    ROUND((PERCENTILE_CONT(0.95) WITHIN GROUP (
        ORDER BY EXTRACT(EPOCH FROM (completed_at - created_at))
    ))::numeric, 1) AS p95_sec
FROM study_question_jobs
WHERE created_at >= NOW() - INTERVAL '7 days'
  AND completed_at IS NOT NULL
UNION ALL
SELECT
    'study_quiz_session_jobs',
    COUNT(*),
    ROUND(AVG(EXTRACT(EPOCH FROM (completed_at - created_at)))::numeric, 1),
    ROUND(MAX(EXTRACT(EPOCH FROM (completed_at - created_at)))::numeric, 1),
    ROUND((PERCENTILE_CONT(0.5) WITHIN GROUP (
        ORDER BY EXTRACT(EPOCH FROM (completed_at - created_at))
    ))::numeric, 1),
    ROUND((PERCENTILE_CONT(0.95) WITHIN GROUP (
        ORDER BY EXTRACT(EPOCH FROM (completed_at - created_at))
    ))::numeric, 1)
FROM study_quiz_session_jobs
WHERE created_at >= NOW() - INTERVAL '7 days'
  AND completed_at IS NOT NULL;

\echo ''
\echo '── 6. 4-A/4-B skipped 사유 분포 (어떤 데이터 부족이 가장 많이 막는가) ──'
SELECT
    'study_question_jobs' AS source,
    error_code,
    COUNT(*) AS cnt
FROM study_question_jobs
WHERE status = 'skipped'
GROUP BY error_code
UNION ALL
SELECT
    'study_quiz_session_jobs',
    error_code,
    COUNT(*)
FROM study_quiz_session_jobs
WHERE status = 'skipped'
GROUP BY error_code
ORDER BY source, cnt DESC;

\echo ''
\echo '── 7. 4-B guard_fail / parse_fail / llm_timeout 비율 (전체 job 대비) ──'
SELECT
    error_code,
    COUNT(*) AS cnt,
    ROUND(100.0 * COUNT(*) / NULLIF((SELECT COUNT(*) FROM study_quiz_session_jobs), 0), 1) AS pct
FROM study_quiz_session_jobs
WHERE error_code IN ('guard_fail', 'parse_fail', 'llm_timeout', 'unknown')
GROUP BY error_code
ORDER BY cnt DESC;