Add CI and deploy summaries

.gitea/workflows/deploy-controller.py

@@ -294,10 +294,47 @@ def follow(run_id, phase):
         time.sleep(3)
 
 
+def summary(run_id):
+    directory = run_directory(run_id)
+    request = json.loads((directory / 'request.json').read_text())
+    release = request['release']
+    plan_file = directory / 'plan.json'
+    lines = [
+        f'## Deploy `{release["sha"]}`',
+        '',
+        f'- Mode: `{request["mode"]}`',
+        f'- Refresh third-party images: `{request["refresh_images"]}`',
+    ]
+    if not plan_file.exists():
+        lines.extend(['', 'Plan was not created. Check the controller log.'])
+        print('\n'.join(lines))
+        return
+    plan = json.loads(plan_file.read_text())
+    lines.extend(['', '### Selected services'])
+    count = 0
+    for kind, services in plan['selected'].items():
+        for service in services:
+            lines.append(f'- `{kind}`: `{service}`')
+            count += 1
+    if not count:
+        lines.append('- None')
+    lines.extend(['', '### Selected Helm releases'])
+    lines.extend(f'- `{release}`' for release in plan.get('helm', []))
+    if not plan.get('helm'):
+        lines.append('- None')
+    lines.extend(['', '### Images pinned in the checked release'])
+    lines.extend(f'- `{image}@{digest}`' for image, digest in sorted(release['images'].items()))
+    lines.extend(['', '### Removed resources requiring manual review'])
+    lines.extend(f'- `{item}`' for item in plan.get('removed', []))
+    if not plan.get('removed'):
+        lines.append('- None')
+    print('\n'.join(lines))
+
+
 def main():
     os.umask(0o077)
     parser = argparse.ArgumentParser(description=__doc__)
-    parser.add_argument('action', choices=('start', 'execute', 'recover', 'status', 'follow'))
+    parser.add_argument('action', choices=('start', 'execute', 'recover', 'status', 'follow', 'summary'))
     parser.add_argument('run_id')
     parser.add_argument('phase', nargs='?', choices=('apply', 'verify', 'smoke'))
     parser.add_argument('--retry', action='store_true', help='Retry failed recovery checks; never repeat apply')
@@ -315,6 +352,8 @@ def main():
         if (directory / 'plan.json').exists():
             plan = json.loads((directory / 'plan.json').read_text())
             print(json.dumps({k: plan[k] for k in ('sha', 'selected', 'helm', 'removed')}, indent=2))
+    elif args.action == 'summary':
+        summary(args.run_id)
     elif not follow(args.run_id, args.phase):
         sys.exit(1)
 

.gitea/workflows/release.py

@@ -231,6 +231,8 @@ def build(output):
             )
             signature.write_text(image + '\n')
         release = {'version': 1, 'sha': sha, 'images': {}, 'inputs': {}}
+        built = []
+        reused = []
         for name, (context, dockerfile) in IMAGES.items():
             image = f'gcr.forust.xyz/forust/{name}'
             inputs = fingerprint(context, dockerfile)
@@ -255,8 +257,10 @@ def build(output):
             if exists:
                 print(f'Reuse {name}: inputs unchanged')
                 digest = old_digest
+                reused.append((name, image, digest))
             else:
                 print(f'Build {name}', flush=True)
+                built.append((name, image))
                 metadata = Path(docker_config) / 'metadata.json'
                 command(
                     'docker',
@@ -286,6 +290,23 @@ def build(output):
             release['inputs'][image] = inputs
         validate_release(release, sha)
         output.write_text(json.dumps(release, indent=2) + '\n')
+        summary = os.environ.get('GITHUB_STEP_SUMMARY')
+        if summary:
+            lines = [f'## Image release for `{sha}`', '', '### Built']
+            lines.extend(f'- `{name}` — `{image}`' for name, image in built)
+            if not built:
+                lines.append('- None')
+            lines.extend(['', '### Reused from successful CI'])
+            lines.extend(f'- `{name}` — `{image}@{digest}`' for name, image, digest in reused)
+            if not reused:
+                lines.append('- None')
+            lines.extend(['', '### Release digests'])
+            lines.extend(
+                f'- `{name}` — `{image}@{release["images"][image]}`'
+                for name in IMAGES
+                for image in [f'gcr.forust.xyz/forust/{name}']
+            )
+            Path(summary).write_text('\n'.join(lines) + '\n')
     finally:
         # Cleanup errors must neither leak credentials nor mask the original build error.
         try:

.gitea/workflows/ssh-run.sh

@@ -40,7 +40,31 @@ PY
     done
     exit "$rc"
     ;;
-  apply|verify|smoke)
+  apply)
+    result=0
+    for attempt in 1 2 3; do
+      rc=0
+      # shellcheck disable=SC2029 # The run ID and operation are validated local arguments, not remote variables.
+      ssh "${ssh_opts[@]}" "$DEPLOY_USER@$DEPLOY_HOST" python3 "$controller" follow "$DEPLOY_RUN_ID" apply || rc=$?
+      [ "$rc" -eq 0 ] && break
+      [ "$rc" -eq 255 ] || { result="$rc"; break; }
+      echo "SSH disconnected; reconnecting to the existing deploy ($attempt/3)"
+      if [ "$attempt" -eq 3 ]; then result=255; break; fi
+      sleep 5
+    done
+    if [ -n "${GITHUB_STEP_SUMMARY:-}" ]; then
+      rc=0
+      # shellcheck disable=SC2029 # The run ID is validated above.
+      ssh "${ssh_opts[@]}" "$DEPLOY_USER@$DEPLOY_HOST" python3 "$controller" summary "$DEPLOY_RUN_ID" >"$key_dir/deploy-summary.md" || rc=$?
+      if [ "$rc" -eq 0 ]; then
+        cat "$key_dir/deploy-summary.md" >>"$GITHUB_STEP_SUMMARY"
+      else
+        echo 'Deploy summary is unavailable. Check the controller log.' >>"$GITHUB_STEP_SUMMARY"
+      fi
+    fi
+    exit "$result"
+    ;;
+  verify|smoke)
     for attempt in 1 2 3; do
       rc=0
       # shellcheck disable=SC2029 # The run ID and operation are validated local arguments, not remote variables.