refs #739: document DB-owned task and few-shot policy

database/adb/129_sgmp_std25_weekly_au_evaluation_criteria.sql

@@ -0,0 +1,29 @@
+-- STD-25 is a period AU metric, not the daily AU_FLAG metric.
+-- Keep the evaluation evidence explicit so the LLM judge accepts the valid
+-- weekly result shape produced by the NL2SQL tool.
+
+UPDATE sg_ai_qa_question
+   SET expected_focus = 'Weekly AU: use one as-of snapshot (BASE_DT=2026-07-15), '
+       || 'count DISTINCT GUID whose LAST_CONN_DT is in the inclusive seven-day window '
+       || '(2026-07-09 through 2026-07-15), with STD_USER_YN=''Y'' and EXPT_USER_YN=''N''. '
+       || 'This is one aggregate result, not daily rows. Do not substitute daily AU_FLAG=1 for the period definition.',
+       baseline_sql = TO_CLOB('SELECT COUNT(DISTINCT u."GUID") AS "RECENT_7DAY_AU"' || CHR(10)
+         || 'FROM "SGMP_POC"."CZN_COMN_USER_MST" u' || CHR(10)
+         || 'WHERE u."BASE_DT" = DATE ''2026-07-15''' || CHR(10)
+         || '  AND u."LAST_CONN_DT" BETWEEN DATE ''2026-07-09'' AND DATE ''2026-07-15''' || CHR(10)
+         || '  AND u."STD_USER_YN" = ''Y''' || CHR(10)
+         || '  AND u."EXPT_USER_YN" = ''N'''),
+       baseline_answer = 'RECENT_7DAY_AU=0',
+       evaluation_rule_json = '{"required_sql_terms":["CZN_COMN_USER_MST","LAST_CONN_DT","STD_USER_YN","EXPT_USER_YN","COUNT"],"recommended_sql_terms":["BASE_DT"],"forbidden_sql_terms":["AU_FLAG"],"required_result_shape":"SINGLE_AGGREGATE"}',
+       updated_at = SYSTIMESTAMP
+ WHERE question_code = 'STD-25';
+
+/
+
+COMMIT;
+
+/
+
+SELECT question_code, expected_focus, baseline_sql, baseline_answer, evaluation_rule_json
+  FROM sg_ai_qa_question
+ WHERE question_code = 'STD-25';