From 6a73f7a8c736849790a711ffacb31fa15b73a332 Mon Sep 17 00:00:00 2001
From: Lasse Benninga <devops.pipeline@example.com>
Date: Tue, 14 Jul 2026 10:55:28 +0200
Subject: [PATCH 1/2] docs(week-9): add PR packaging template for reviewers

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 .github/PULL_REQUEST_TEMPLATE.md | 42 ++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)
 create mode 100644 .github/PULL_REQUEST_TEMPLATE.md

diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
new file mode 100644
index 0000000..d1f4d7e
--- /dev/null
+++ b/.github/PULL_REQUEST_TEMPLATE.md
@@ -0,0 +1,42 @@
+## What I built
+- Data-quality audit: `validation_queries.sql`
+- Star-schema views: `schema_setup.sql` (`vw_dim_zones`, `vw_fact_trips`)
+- Data dictionary: `data_dictionary.md`
+- Verification queries: `verification_results.sql`
+- Per-borough count screenshot: `assets/borough_count.png`
+- `## Findings` section added to this README with my actual audit numbers
+- AI usage: `AI_ASSIST.md`
+
+## How to review
+- SQL: read `schema_setup.sql` (grain + negative-fare filter + join keys) and `validation_queries.sql`.
+- Results: see the `## Findings` section in the README and `assets/borough_count.png`.
+- AI usage: `AI_ASSIST.md`.
+
+## How to run
+Run every query against **your own assigned schema** on the shared Azure Postgres (not `public`):
+
+```bash
+psql "<your Postgres connection string>" -f validation_queries.sql
+psql "<your Postgres connection string>" -f schema_setup.sql
+psql "<your Postgres connection string>" -f verification_results.sql
+```
+
+Prerequisite: your assigned schema on the shared instance; source tables `nyc_taxi.raw_trips` and `nyc_taxi.raw_zones` already loaded.
+
+## What reviewers should see (expected results)
+Fill in your actual audit numbers (from your `## Findings`):
+- Duplicate trips: <e.g. ~189>
+- NULL pickup/dropoff location IDs: <e.g. 5 / 5>
+- Negative `fare_amount` rows: <e.g. 182>
+- Orphaned `pickup_location_id` (not in raw_zones): <e.g. N>
+- Busiest borough by trip count: <e.g. Manhattan>
+
+## Known limitations / out of scope
+- <e.g. one verification query still returns more rows than expected>
+- Write "none" if everything in the assignment is done and working.
+
+## Self-check
+- [ ] `bash .hyf/test.sh` passes (completeness)
+- [ ] `vw_fact_trips` excludes `fare_amount < 0` and joins cleanly to `vw_dim_zones`
+- [ ] `## Findings` in the README contains real counts, not "I checked"
+- [ ] `assets/borough_count.png` is committed

From f3f6d9c342e39b5c35ca0abf2a9f07c2da23829b Mon Sep 17 00:00:00 2001
From: Lasse Benninga <devops.pipeline@example.com>
Date: Tue, 14 Jul 2026 10:55:28 +0200
Subject: [PATCH 2/2] ci(week-9): enforce PR template sections via
 pr-body-check workflow

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 .github/workflows/pr-body-check.yml | 52 +++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)
 create mode 100644 .github/workflows/pr-body-check.yml

diff --git a/.github/workflows/pr-body-check.yml b/.github/workflows/pr-body-check.yml
new file mode 100644
index 0000000..8d066d9
--- /dev/null
+++ b/.github/workflows/pr-body-check.yml
@@ -0,0 +1,52 @@
+name: PR body check
+
+# Fails the check when a pull request description is missing the sections from
+# .github/PULL_REQUEST_TEMPLATE.md. GitHub only auto-fills that template in the
+# web "compose" form and in `gh pr create` with no --body; a PR opened through
+# the REST API or `gh pr create --body "..."` (the path most AI tools take)
+# silently skips it. This check is the only thing that actually enforces it.
+#
+# Recovery is automatic: editing the PR description fires the `edited` event and
+# re-runs this check with the new body. No new commit or manual re-run needed.
+
+on:
+  pull_request:
+    types: [opened, edited, reopened, synchronize]
+    branches: [main]
+
+permissions:
+  contents: read
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check required sections are present
+        env:
+          PR_BODY: ${{ github.event.pull_request.body }}
+        run: |
+          set -euo pipefail
+          required=(
+            "## What I built"
+            "## How to review"
+            "## How to run"
+            "## What reviewers should see"
+            "## Self-check"
+          )
+          missing=()
+          for section in "${required[@]}"; do
+            if ! printf '%s' "$PR_BODY" | grep -qiF "$section"; then
+              missing+=("$section")
+            fi
+          done
+          if [ ${#missing[@]} -ne 0 ]; then
+            echo "::error::Your PR description is missing required sections. Start from the template (.github/PULL_REQUEST_TEMPLATE.md) and keep these headings:"
+            for m in "${missing[@]}"; do echo "  - $m"; done
+            echo ""
+            echo "If you (or an AI tool) opened this PR without the template, click 'Edit' on the"
+            echo "PR description, paste the template, and fill it in. Editing the description"
+            echo "re-runs this check automatically. A complete PR is easy to review and"
+            echo "reproducible: that is part of the assignment."
+            exit 1
+          fi
+          echo "All required PR sections present."