name: "f2dq"
version: "1.0.2"  # dbt_f2dq: modernized fork (dbt_utils 1.4.1); dual-read re_data_* keys
config-version: 2

require-dbt-version: [">=1.0.0", "<2.0.0"]

profile: "f2dq_postgres"

target-path: "target" # directory which will store compiled SQL files
clean-targets: ["target", "dbt_modules", "dbt_packages"]

on-run-end:
  # Dual-read: f2dq:save_test_history or legacy re_data:save_test_history
  - "{% if var('f2dq:save_test_history') or var('re_data:save_test_history', false) %} {{ f2dq.save_test_history(results) }} {% endif %}"

vars:
  f2dq:max_columns_in_query: 10
  # The metric bucket is the run's calendar day: [midnight of the run date, +1d).
  #
  # re_data used [run_date - 1d, run_date) - i.e. the bucket ENDED at midnight at
  # the start of the run day. Any row stamped during the run (models that set
  # `dbt_updated_at = CURRENT_DATETIME()`) therefore fell outside the bucket the
  # run had just written it into, and incremental merges that re-stamp rows every
  # run made those rows land in the wrong bucket or never. row_count came out 0/1
  # against tables that plainly had rows. Anchoring the bucket on the run date
  # instead of the day before keeps `interval_length_sec` at 86400 and the daily
  # series intact, but includes everything written on the day being measured.
  f2dq:time_window_start: '{{ run_started_at.strftime("%Y-%m-%d 00:00:00") }}'
  f2dq:time_window_end: '{{ (run_started_at + modules.datetime.timedelta(1)).strftime("%Y-%m-%d 00:00:00") }}'
  # Also emit `global__<metric>` (whole-table) alongside the windowed series, so
  # metrics stay meaningful for models whose time_filter holds historical
  # timestamps that miss the current bucket.
  f2dq:emit_global_metrics: true
  f2dq:anomaly_detection_look_back_days: 30
  f2dq:select: null
  f2dq:anomalies_filtered: f2dq_anomalies

  f2dq:alerting_z_score: 3

  f2dq:save_test_history: false
  f2dq:show_warns_as_alerts: false

  f2dq:anomaly_detector:
    name: modified_z_score
    threshold: 3

  f2dq:store_table_samples: false

  f2dq:metrics_groups:
    table_metrics:
      table:
        - row_count
        - freshness

    column_metrics:
      column:
        numeric:
          - min
          - max
          - avg
          - stddev
          - variance
          - nulls_count
          - nulls_percent
        text:
          - min_length
          - max_length
          - avg_length
          - nulls_count
          - missing_count
          - nulls_percent
          - missing_percent
        boolean:
          - count_true
          - count_false
          - nulls_count
          - nulls_percent

  f2dq:default_metrics:
    - table_metrics
    - column_metrics

models:
  f2dq:
    +schema: f2dq
    internal:
      +schema: f2dq_internal