From 45129a86bfd8b6da7ccff9bc040567591468859d Mon Sep 17 00:00:00 2001
From: Kaxil Naik <kaxilnaik@gmail.com>
Date: Thu, 30 Apr 2026 01:57:19 +0100
Subject: [PATCH] Guard registry-build sync against partial extracts

`aws s3 sync` exits 0 silently when its source directory is missing or
empty, so a partial `breeze registry extract-data` failure (one provider
errors mid-run, Eleventy still produces a tree, sync uploads stale or
empty JSON) would currently report green while leaving the live registry
in an inconsistent state.

This adds the same pre-sync content guards `registry-backfill.yml` got
in PR #66027: for incremental builds, assert each target provider's HTML
directory + API directory + `versions.json` exist and are non-empty;
for full builds, assert the top-level `index.html`, `api/providers.json`
listing, and at least one provider subtree under `api/providers/` are
present. Any missing artifact aborts the sync with `::error::` before
S3 is touched.
---
 .github/workflows/registry-build.yml | 46 ++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/.github/workflows/registry-build.yml b/.github/workflows/registry-build.yml
index d6e323ae14232..5b9c89c1794ef 100644
--- a/.github/workflows/registry-build.yml
+++ b/.github/workflows/registry-build.yml
@@ -260,6 +260,52 @@ jobs:
           retention-days: 7
           if-no-files-found: error
 
+      - name: "Verify build emitted expected content"
+        env:
+          PROVIDER: ${{ inputs.provider }}
+        run: |
+          # Guard against silent no-op syncs. `aws s3 sync` exits 0 when the
+          # source dir is missing or empty, so without this a partial build
+          # (e.g. extract_metadata.py errored mid-run) would report green
+          # while uploading nothing or stale state. Mirrors the per-provider
+          # guard in the "Sync backfilled version pages to S3" step in
+          # registry-backfill.yml.
+          if [[ -n "${PROVIDER}" ]]; then
+            # Incremental: verify each target provider's pages and versions JSON exist.
+            for pid in ${PROVIDER}; do
+              LOCAL_PROV_DIR="registry/_site/providers/${pid}/"
+              LOCAL_API_DIR="registry/_site/api/providers/${pid}/"
+              LOCAL_VERSIONS_JSON="${LOCAL_API_DIR}versions.json"
+              if [ ! -d "${LOCAL_PROV_DIR}" ] || [ -z "$(ls -A "${LOCAL_PROV_DIR}" 2>/dev/null)" ]; then
+                echo "::error::Build did not emit ${LOCAL_PROV_DIR} -- aborting sync."
+                exit 1
+              fi
+              if [ ! -d "${LOCAL_API_DIR}" ] || [ -z "$(ls -A "${LOCAL_API_DIR}" 2>/dev/null)" ]; then
+                echo "::error::Build did not emit ${LOCAL_API_DIR} -- aborting sync."
+                exit 1
+              fi
+              if [ ! -s "${LOCAL_VERSIONS_JSON}" ]; then
+                echo "::error::${LOCAL_VERSIONS_JSON} missing or empty -- aborting sync."
+                exit 1
+              fi
+            done
+          else
+            # Full build: verify the top-level homepage and provider listing.
+            if [ ! -s "registry/_site/index.html" ]; then
+              echo "::error::Full build did not emit registry/_site/index.html -- aborting sync."
+              exit 1
+            fi
+            if [ ! -s "registry/_site/api/providers.json" ]; then
+              echo "::error::registry/_site/api/providers.json missing or empty -- aborting sync."
+              exit 1
+            fi
+            API_PROVIDERS_DIR="registry/_site/api/providers/"
+            if [ ! -d "${API_PROVIDERS_DIR}" ] || [ -z "$(ls -A "${API_PROVIDERS_DIR}" 2>/dev/null)" ]; then
+              echo "::error::${API_PROVIDERS_DIR} is missing or empty -- aborting sync."
+              exit 1
+            fi
+          fi
+
       - name: "Sync registry to S3"
         env:
           S3_BUCKET: ${{ steps.destination.outputs.bucket }}