[DEV] Overwrite current env in the action

.github/workflows/recce_ci.yml

@@ -6,19 +6,24 @@ on:
 jobs:
   check-pull-request:
     name: Prepare for Recce
+    env:
+      GITHUB_TOKEN: ${{ secrets.GH_TOKEN }}
+      RECCE_STATE_PASSWORD: ${{ secrets.RECCE_STATE_PASSWORD }}
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
         with:
-          fetch-depth: 0
+          fetch-depth: 1
 
       - uses: actions/setup-python@v5
         with:
           python-version: "3.10"
           cache: "pip"
 
       - name: Install dependencies
-        run: pip install -r requirements.txt
+        run: |
+          pip install -r requirements.txt
+          pip install -U recce
 
       - name: Trigger the dbt cloud job and fetch artifacts for Recce
         uses: datarecce/dbt-cloud-action@main
@@ -27,34 +32,37 @@ jobs:
           dbt_cloud_token: ${{ secrets.DBT_CLOUD_API_TOKEN }}
           dbt_cloud_account_id: 62083
           dbt_cloud_base_job_id: 747906
-          dbt_cloud_current_job_id: 747907
+          dbt_cloud_current_job_id: 768650
+          git_sha: ${{ github.event.pull_request.head.sha }}
+          schema_override: "PR_${{ github.event.pull_request.number }}"
           failure_on_error: true
 
       - uses: "google-github-actions/auth@v2"
         id: google-auth
         with:
           credentials_json: ${{ secrets.GCP_SERVICE_ACCOUNT_KEY_JSON }}
 
-      - name: Run Recce in cloud mode
+      - name: Run dbt
+        run: |
+          pwd
+          tree -L 1
+          dbt deps
+          dbt docs generate --select state:modified --defer --state target-base
         env:
           BQ_PROJECT: ${{ steps.google-auth.outputs.project_id }}
-          BQ_DATASET: recce_ci
+          BQ_DATASET: "PR_${{ github.event.pull_request.number }}"
           BQ_KEYFILE_PATH: ${{ steps.google-auth.outputs.credentials_file_path }}
-          GITHUB_TOKEN: ${{ secrets.GH_TOKEN }}
-          RECCE_STATE_PASSWORD: ${{ secrets.RECCE_STATE_PASSWORD }}
-        run: recce run --cloud
 
-      - name: Prepare Recce Summary
-        id: recce-summary
+      - name: Run Recce in cloud mode
+        run: recce run --cloud
         env:
           BQ_PROJECT: ${{ steps.google-auth.outputs.project_id }}
-          BQ_DATASET: recce_ci
+          BQ_DATASET: "PR_${{ github.event.pull_request.number }}"
           BQ_KEYFILE_PATH: ${{ steps.google-auth.outputs.credentials_file_path }}
-          GITHUB_TOKEN: ${{ secrets.GH_TOKEN }}
-          RECCE_STATE_PASSWORD: ${{ secrets.RECCE_STATE_PASSWORD }}
-        run: |
-          set -eo pipefail
 
+      - name: Prepare Recce Summary
+        id: recce-summary
+        run: |
           recce summary --cloud > recce_summary.md
 
           # Add next steps message
@@ -76,6 +84,10 @@ jobs:
             For the full summary, please check the Job Summary page: ${{github.server_url}}/${{github.repository}}/actions/runs/${{github.run_id}}
             " >> recce_summary.md
           fi
+        env:
+          BQ_PROJECT: ${{ steps.google-auth.outputs.project_id }}
+          BQ_DATASET: "PR_${{ github.event.pull_request.number }}"
+          BQ_KEYFILE_PATH: ${{ steps.google-auth.outputs.credentials_file_path }}
 
       - name: Comment on pull request
         uses: thollander/actions-comment-pull-request@v2

models/marts/customers.sql

@@ -18,7 +18,7 @@ customer_orders_summary as (
         orders.customer_id,
 
         count(distinct orders.order_id) as count_lifetime_orders,
-        count(distinct orders.order_id) > 1 as is_repeat_buyer,
+        count(distinct orders.order_id) > 2 as is_repeat_buyer,
         min(orders.ordered_at) as first_ordered_at,
         max(orders.ordered_at) as last_ordered_at,
         sum(orders.subtotal) as lifetime_spend_pretax,

recce.yml

@@ -0,0 +1,13 @@
+# Preset Checks
+# Please see https://datarecce.io/docs/features/preset-checks/
+checks:
+- name: Row count diff
+  description: Check the row count diff for all table models.
+  type: row_count_diff
+  params:
+    select: state:modified,config.materialized:table
+- name: Schema diff
+  description: Check the schema diff for all nodes.
+  type: schema_diff
+  params:
+    select: state:modified,config.materialized:table

requirements.txt

@@ -249,7 +249,7 @@ pyyaml==6.0.1
     #   dbt-core
     #   dbt-semantic-interfaces
     #   pre-commit
-recce==0.37.0
+recce~=0.37.0
     # via -r requirements.in
 referencing==0.35.1
     # via