M6.5: enroll lasuite-docs (recipe #5, multi-service + S3/MinIO) — install verified green

9-service stack (frontend/backend/celery/y-provider/docspec/postgres/redis/minio/nginx) converges
9/9 and serves the SPA; install 2 passed on host. Root-caused a deploy timeout: cold-pulling ~9
large images exceeds abra's default 300s convergence TIMEOUT -> bumped to 900 via EXTRA_ENV (the
generic per-recipe mechanism, no harness surgery). upgrade/backup use a postgres marker (docs/docs)
exercising the pg_backup.sh DB-dump hook; verifying next.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

tests/lasuite-docs/recipe_meta.py

@@ -0,0 +1,17 @@
+# Per-recipe harness config for lasuite-docs (recipe #5 — multi-service + object-storage/S3).
+# Stack: app(frontend) + backend(Django/impress) + celery + y-provider + docspec + db(postgres) +
+# redis + minio(S3) + web(nginx). OIDC settings are config-only (validated by `manage.py check`, not
+# fetched at boot), so the stack starts healthy with placeholder OIDC; login isn't exercised in CI.
+# Many services -> generous timeouts.
+HEALTH_PATH = "/"
+HEALTH_OK = (200, 301, 302)
+DEPLOY_TIMEOUT = 900
+HTTP_TIMEOUT = 600
+
+
+def EXTRA_ENV(domain):
+    # abra's internal per-deploy convergence timeout (the recipe's TIMEOUT env, default 300s) is too
+    # short for this 9-service stack on a COLD image cache (~9 large images: impress frontend/backend,
+    # minio, postgres18, redis, docspec, y-provider). Cold pulls exceed 300s -> "deploy timed out 🟠".
+    # Bump it so the harness deploy waits long enough; verified the stack converges 9/9 once pulled.
+    return {"TIMEOUT": "900"}

tests/lasuite-docs/test_backup.py

@@ -0,0 +1,33 @@
+"""lasuite-docs — backup/restore stage (D2): write a postgres marker, backup (pg_backup.sh pre-hook
+dumps the DB), mutate (drop it), restore (post-hook reloads), assert the restored DB matches.
+
+Exercises the recipe's real DB-dump backup hook (postgres + minio are both backupbot-labelled); the
+postgres marker is the meaningful Docs-metadata data path."""
+import os
+import sys
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "runner"))
+from harness import lifecycle  # noqa: E402
+
+
+def _psql(domain, sql):
+    cmd = f'PGPASSWORD=$(cat /run/secrets/postgres_p) psql -U docs -d docs -tAc "{sql}"'
+    return lifecycle.exec_in_app(domain, ["sh", "-c", cmd], service="db").strip()
+
+
+def test_backup_mutate_restore(deployed, meta):
+    domain = deployed
+
+    _psql(domain, "CREATE TABLE IF NOT EXISTS ci_marker(v text); DELETE FROM ci_marker; "
+                  "INSERT INTO ci_marker VALUES('original');")
+    assert _psql(domain, "SELECT v FROM ci_marker;") == "original"
+    lifecycle.backup_app(domain)
+
+    _psql(domain, "DROP TABLE ci_marker;")
+    assert _psql(domain, "SELECT to_regclass('public.ci_marker');") in ("", "NULL"), "drop did not take"
+
+    lifecycle.restore_app(domain)
+    lifecycle.wait_healthy(domain, ok_codes=tuple(meta["HEALTH_OK"]), path=meta["HEALTH_PATH"],
+                           deploy_timeout=meta["DEPLOY_TIMEOUT"], http_timeout=meta["HTTP_TIMEOUT"])
+    assert _psql(domain, "SELECT v FROM ci_marker;") == "original", \
+        "restore did not return the pre-mutation postgres state"

tests/lasuite-docs/test_install.py

@@ -0,0 +1,33 @@
+"""lasuite-docs — install stage (recipe #5, multi-service + object-storage/S3). D2 install: the
+multi-service stack (frontend + Django backend + celery + y-provider + docspec + postgres + redis +
+minio + nginx) converges and serves the app over real HTTPS through the gateway.
+
+Login is OIDC-gated (no live OIDC provider in CI), so the functional assertion is that the frontend
+SPA is served (unauthenticated landing), not an authenticated flow."""
+import os
+import sys
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "runner"))
+from harness import lifecycle  # noqa: E402
+
+
+def test_http_reachable(deployed_app):
+    status = lifecycle.http_get(deployed_app, "/")
+    assert status in (200, 301, 302), f"expected 2xx/3xx from {deployed_app}, got {status}"
+
+
+def test_playwright_loads_frontend(deployed_app):
+    """A real browser loads the live Docs frontend (the SPA shell) over HTTPS."""
+    from playwright.sync_api import sync_playwright
+
+    url = f"https://{deployed_app}/"
+    with sync_playwright() as p:
+        browser = p.chromium.launch(args=["--no-sandbox"])
+        try:
+            ctx = browser.new_context(ignore_https_errors=True)
+            page = ctx.new_page()
+            resp = page.goto(url, wait_until="domcontentloaded", timeout=60000)
+            assert resp is not None and resp.status in (200, 301, 302), f"page status {resp and resp.status}"
+            assert "<html" in page.content().lower(), "no HTML served by the frontend"
+        finally:
+            browser.close()

tests/lasuite-docs/test_upgrade.py

@@ -0,0 +1,45 @@
+"""lasuite-docs — upgrade stage (D2): deploy the previous published version, write a DB marker,
+upgrade to current/$REF, assert the app stays healthy and the postgres data survives.
+
+Docs metadata lives in postgres, so the marker is a row in a dedicated `ci_marker` table (the app's
+own Django migrations don't touch it), read back via `psql` in the `db` service."""
+import os
+import sys
+
+import pytest
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "runner"))
+from harness import lifecycle  # noqa: E402
+
+
+def _psql(domain, sql):
+    cmd = f'PGPASSWORD=$(cat /run/secrets/postgres_p) psql -U docs -d docs -tAc "{sql}"'
+    return lifecycle.exec_in_app(domain, ["sh", "-c", cmd], service="db").strip()
+
+
+@pytest.fixture
+def old_app(recipe, app_domain, meta, request):
+    prev = lifecycle.previous_version(recipe)
+    if not prev:
+        pytest.skip(f"{recipe}: no previous published version to upgrade from")
+    lifecycle.janitor()
+    request.addfinalizer(lambda: lifecycle.teardown_app(app_domain))
+    lifecycle.deploy_app(recipe, app_domain, version=prev)
+    lifecycle.wait_healthy(app_domain, ok_codes=tuple(meta["HEALTH_OK"]), path=meta["HEALTH_PATH"],
+                           deploy_timeout=meta["DEPLOY_TIMEOUT"], http_timeout=meta["HTTP_TIMEOUT"])
+    return app_domain, prev
+
+
+def test_upgrade_preserves_data(old_app, meta):
+    domain, prev = old_app
+    _psql(domain, "CREATE TABLE IF NOT EXISTS ci_marker(v text); DELETE FROM ci_marker; "
+                  "INSERT INTO ci_marker VALUES('upgrade-survives');")
+    assert _psql(domain, "SELECT v FROM ci_marker;") == "upgrade-survives"
+
+    lifecycle.upgrade_app(domain, version=os.environ.get("VERSION") or None)
+    lifecycle.wait_healthy(domain, ok_codes=tuple(meta["HEALTH_OK"]), path=meta["HEALTH_PATH"],
+                           deploy_timeout=meta["DEPLOY_TIMEOUT"], http_timeout=meta["HTTP_TIMEOUT"])
+
+    assert lifecycle.http_get(domain, "/") in (200, 301, 302)
+    assert _psql(domain, "SELECT v FROM ci_marker;") == "upgrade-survives", \
+        "postgres data did not survive the upgrade"