.forgejo/workflows/build.yml

@@ -1374,15 +1374,16 @@ jobs:
           # CID is empty until the app container exists, so this is safe to
           # arm now and still covers a failure before that point.
           CID=""
+          CID_ALL=""
           cleanup() {
             rc=$?
-            if [ -n "$CID" ]; then
+            for c in $CID $CID_ALL; do
               # The log ONLY on failure — a boot that never answered must fail
               # with the reason visible rather than as a bare timeout (rule
               # 156), while a green run has nothing to say.
-              [ $rc -eq 0 ] || docker logs "$CID" 2>&1 | tail -40
-              docker rm -f "$CID" >/dev/null 2>&1 || true
-            fi
+              [ $rc -eq 0 ] || docker logs "$c" 2>&1 | tail -40
+              docker rm -f "$c" >/dev/null 2>&1 || true
+            done
             docker network rm "$NET" >/dev/null 2>&1 || true
             # Preserve the real status, which a trap ending on a successful
             # `docker rm` would otherwise mask.
@@ -1511,6 +1512,51 @@ jobs:
           docker run --rm --network "$NET" "$CANDIDATE" shell -c \
             "python3 -c \"import urllib.request; print(urllib.request.urlopen('http://$WEB_IP:8080/api/health', timeout=5).read().decode())\""
 
+          # 4. THE DEFAULT ROLE. Everything above boots `web` explicitly, so
+          #    until now nothing had ever started the shape the single-
+          #    container layout actually runs — supervisord bringing up
+          #    hypercorn plus one celery process per lane. The milestone is
+          #    named for that shape and CI had never once executed it.
+          #
+          #    Deliberately NO command: this is `docker run <image>` with
+          #    nothing after it, so it checks the Dockerfile's CMD and the
+          #    entrypoint's default together with the role itself. An adopter
+          #    who writes no `command:` gets exactly this.
+          #
+          #    `healthcheck_all` is the right assertion and was itself never
+          #    run: it passes only when hypercorn answers AND every lane in
+          #    the table is answering the broker. A web-only check would go
+          #    green with every worker dead, which is the failure mode
+          #    consolidation creates.
+          #
+          #    Cheap because ml ships at 0 slots and disabled, so nothing
+          #    loads a model — the lane answers `inspect` with its consumers
+          #    cancelled, which is what "healthy" means for a disabled lane.
+          echo "smoke: the default role boots every lane under supervisord"
+          CID_ALL=$(docker run -d $ENVOPTS "$CANDIDATE")
+          lanes_up=""
+          for i in $(seq 1 60); do
+            if docker exec "$CID_ALL" python -m backend.app.scripts.healthcheck_all; then
+              lanes_up=1
+              break
+            fi
+            if [ "$(docker inspect -f '{{.State.Running}}' "$CID_ALL" 2>/dev/null)" != "true" ]; then
+              echo "smoke: FAILED — the all-role container exited during boot." >&2
+              exit 1
+            fi
+            sleep 3
+          done
+          if [ -z "$lanes_up" ]; then
+            echo "smoke: FAILED — supervisord came up but the composite" >&2
+            echo "smoke: healthcheck never passed: either hypercorn did not" >&2
+            echo "smoke: answer or a lane is not consuming. Its log follows." >&2
+            exit 1
+          fi
+          echo "smoke: every lane answered"
+          # Say WHICH processes supervisord is running, so a lane that is
+          # merely restart-looping is visible rather than inferred.
+          docker exec "$CID_ALL" supervisorctl -c "${SUPERVISOR_CONF:-/tmp/supervisord.conf}" status || true
+
           echo "smoke: all checks passed against $CANDIDATE, with egress blocked"
 
   # Move the channel tags — the whole point of the gate.

Dockerfile

@@ -127,4 +127,15 @@ ENV FC_VERSION=${FC_VERSION}
 EXPOSE 8080
 
 ENTRYPOINT ["./entrypoint.sh"]
-CMD ["web"]
+# The DEFAULT is the whole application, not one lane of it.
+#
+# `docker run fabledcurator` with no command starts hypercorn plus every
+# worker lane under supervisord — the shape an adopter wants and the shape the
+# consolidated stack runs. It was `web`, which meant the single-container
+# layout only worked if you knew to ask for it by name, and a compose file
+# that forgot `command:` got a web server with nothing processing its queues:
+# a gallery that loads, accepts an import, and never finishes one.
+#
+# The multi-service stack is unaffected — every service there names its role
+# explicitly, which is exactly what makes it the multi-service stack.
+CMD ["all"]

docker-compose.single.yml

@@ -59,10 +59,10 @@ services:
 
   fabledcurator:
     image: git.fabledsword.com/bvandeusen/fabledcurator:latest
-    # Everything: hypercorn plus one celery process per lane, under
-    # supervisord, whose config is generated from the application's own lane
-    # table so the two cannot disagree.
-    command: ["all"]
+    # No `command:`. Everything — hypercorn plus one celery process per lane
+    # under supervisord — is what the image does by default, and supervisord's
+    # config is generated from the application's own lane table so the two
+    # cannot disagree. `command: ["all"]` still works and means the same thing.
     # tini as PID 1, in front of supervisord. supervisord reaps its own
     # children, but a container's PID 1 also inherits orphans from anywhere
     # below — celery's prefork pool and gallery-dl's subprocesses both make

entrypoint.sh

@@ -1,7 +1,11 @@
 #!/usr/bin/env bash
 set -euo pipefail
 
-ROLE="${1:-web}"
+# Defaults to the whole application (see the Dockerfile's CMD). Kept in step
+# with that CMD deliberately: they are two doors to the same decision, and a
+# disagreement between them would only show up as `docker run --entrypoint`
+# behaving differently from `docker run`.
+ROLE="${1:-all}"
 shift || true
 
 case "$ROLE" in