# Per-recipe harness config for lasuite-drive (Phase 2 Q3.2 — multi-service + object-storage/S3 + # WOPI office, OIDC-dependent). Sibling of lasuite-docs (same La Suite / impress lineage). # # Stack: app(frontend SPA) + backend(Django/drive) + celery + celery-beat + db(postgres) + redis + # mailcatcher + minio(S3) + minio-createbuckets(one-shot) + collabora(WOPI office). ~10 services → # generous timeouts. # # Health: the React SPA is served at `/` by the `app` service and returns 200 unauthenticated # (login is OIDC-gated, exercised by the SSO functional tests, not by the install health check). HEALTH_PATH = "/" HEALTH_OK = (200, 301, 302) # This is the heaviest stack in the Phase-2 set: 12 services incl. BOTH office backends # (collabora/code ~1GB + onlyoffice/documentserver ~2GB) plus impress front/backend, postgres, # minio, redis, nginx. Cold image pull + onlyoffice's multi-minute internal boot exceed the # default abra TIMEOUT (300s) and even 900s, so allow a wide window (abra TIMEOUT below stays # under DEPLOY_TIMEOUT so the Python subprocess never kills abra mid-wait). DEPLOY_TIMEOUT = 1800 HTTP_TIMEOUT = 900 # Base deploy/lifecycle proven cold-green @2026-05-28 (install: pass; 12 services incl. # onlyoffice+collabora) once the Docker Hub rate limit was fixed. The keycloak SSO dep is now # enabled: declaring DEPS triggers the orchestrator's setup_custom_tests step (deploy keycloak + # provision realm/client/user + run tests/lasuite-drive/setup_custom_tests.sh to wire OIDC env + # in-place redeploy). functional/test_oidc_with_keycloak.py then exercises the SSO flow. DEPS = ["keycloak"] # Q3.2a (plan-lasuite-drive-oidc-robustness.md Part A): wire OIDC at INSTALL time, not via a # post-deploy in-place `--chaos` redeploy. The orchestrator provisions the per-run realm on the # live-warm keycloak BEFORE the single `abra app deploy`, and tests/lasuite-drive/install_steps.sh # writes the OIDC env + client secret into the .env that one deploy reads. This eliminates the flaky # 12-service reconverge (collabora WOPI-discovery race; JOURNAL Step 0). Drive boots fine with OIDC # env set because keycloak is live-warm (discovery reachable at boot). setup_custom_tests.sh now # only triggers the post-deploy MinIO bucket one-shot. OIDC_AT_INSTALL = True def READY_PROBE(domain): """Readiness signals beyond replica-convergence + the app HEALTH_PATH (Q3.2/F2-12). collabora's coolwsd reports its container 1/1 'running' while still doing jail/config init, and its WOPI discovery endpoint 404s until ready — so the harness waits for `/hosting/discovery` → 200 on the collabora sibling host after the install deploy AND after the upgrade chaos redeploy. This is what makes the heavy prev→PR-head crossover reliably green (the new collabora 25.04.9.x finishes init within swarm's healthcheck retries; abra's own converge monitor was too impatient — F2-12).""" label, _, rest = domain.partition(".") return [{"host": f"collabora-{domain}", "path": "/hosting/discovery", "ok": (200,)}] def EXTRA_ENV(domain): # Two of lasuite-drive's services route on DOMAIN-DERIVED **nested** subdomains — # `MINIO_DOMAIN="minio.${DOMAIN}"` and `COLLABORA_DOMAIN="collabora.${DOMAIN}"`. The cc-ci # wildcard TLS cert is `*.ci.commoninternet.net` (single label only), so a 2-label name like # `minio.lasuite-drive-pr0-abc.ci.commoninternet.net` is NOT covered → TLS failure on those # routers. Flatten each to a single-label SIBLING under the wildcard (`minio-`, # `collabora-`) so the existing wildcard cert covers them and Traefik routes them with # no cert/gateway change. See DECISIONS.md "Phase 2 — nested DOMAIN-derived subdomains". # `AWS_S3_DOMAIN_REPLACE` derives from MINIO_DOMAIN in-compose, so setting MINIO_DOMAIN is enough. return { "MINIO_DOMAIN": f"minio-{domain}", "COLLABORA_DOMAIN": f"collabora-{domain}", # abra's internal per-deploy convergence timeout (recipe TIMEOUT env, default 300s) is too # short for this 12-service stack on a cold image cache (impress frontend/backend, minio, # postgres, redis, collabora ~1GB, onlyoffice ~2GB). Bump so abra waits long enough for # convergence; kept under DEPLOY_TIMEOUT (1800) so Python never kills abra mid-wait. "TIMEOUT": "1500", }