Perf: serve stacks list from one Docker call; registry host → 10.10.6.10 (0.21.6)

Stacks overview and detail were doing an N+1 inspect storm: list_stacks
called containers_for_stack AND compute_status (which re-fetched) per
stack, and containers.list(sparse=False) full-inspects every container
plus c.image triggered an image-inspect each. For N stacks that was
~2N*(1 list + M inspects + M image-inspects) sequential socket round
trips (~1s for just 2 stacks, growing linearly).

- compose_service.stack_status_summaries(): one low-level
  api.containers(all=True) summary call grouped by compose project label
  → whole list served in a single Docker round-trip (~10x faster).
- compute_status() takes optional pre-fetched containers; get_stack and
  _stack_summary no longer double-fetch.
- containers_for_stack() reads the image name from the inspect it already
  has instead of c.image (drops the per-container image-inspect).
- Same batching applied to the agent's stack list/detail.

Also: Forgejo (registry + git) moved to 10.10.6.10:3020 — updated image
refs in docker-compose.yml, agent/Dockerfile, agent/docker-compose.yml.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

agent/Dockerfile

@@ -1,6 +1,6 @@
 # The agent reuses the backend image (same compose/Docker code + deps) and
 # just runs a different ASGI app. Build the backend image first.
-ARG BACKEND_IMAGE=10.10.5.10:3020/menzelj/stackpilot-backend:latest
+ARG BACKEND_IMAGE=10.10.6.10:3020/menzelj/stackpilot-backend:latest
 FROM ${BACKEND_IMAGE}
 
 ENV STACKS_DIR=/opt/stacks \

agent/docker-compose.yml

@@ -3,11 +3,11 @@
 # token you enter when adding this host in the central StackPilot UI).
 services:
   agent:
-    image: 10.10.5.10:3020/menzelj/stackpilot-agent:latest
+    image: 10.10.6.10:3020/menzelj/stackpilot-agent:latest
     build:
       context: .
       args:
-        BACKEND_IMAGE: 10.10.5.10:3020/menzelj/stackpilot-backend:latest
+        BACKEND_IMAGE: 10.10.6.10:3020/menzelj/stackpilot-backend:latest
     restart: unless-stopped
     environment:
       - AGENT_TOKEN=${AGENT_TOKEN:?set AGENT_TOKEN in .env}

backend/agent_app.py

@@ -62,7 +62,7 @@ def _map_docker(exc: DockerError):
         raise HTTPException(status_code=code, detail=exc.detail or exc.error)
     raise exc  # falls through to the global 502 DockerError handler
 
-AGENT_VERSION = "0.21.5"
+AGENT_VERSION = "0.21.6"
 
 
 # --------------------------------------------------------------------------- #
@@ -137,20 +137,31 @@ def _file_guard(fn, *args, **kwargs):
 # --------------------------------------------------------------------------- #
 
 
-def _summary(stack_id: str) -> dict:
-    try:
-        containers = compose_service.containers_for_stack(stack_id)
-        status = compose_service.compute_status(stack_id)
-    except DockerError:
-        containers = []
-        status = "unknown"
+def _summary(stack_id: str, summaries: dict | None = None) -> dict:
+    if summaries is None:
+        try:
+            containers = compose_service.containers_for_stack(stack_id)
+            total = len(containers)
+            running = sum(1 for c in containers if c.state == "running")
+            status = compose_service.compute_status(stack_id, containers)
+        except DockerError:
+            total = running = 0
+            status = "unknown"
+    else:
+        info = summaries.get(stack_id)
+        total = info["total"] if info else 0
+        running = info["running"] if info else 0
+        if compose_service.is_busy(stack_id):
+            status = "updating"
+        else:
+            status = info["status"] if info else "stopped"
     return {
         "id": stack_id,
         "name": stack_id,
         "description": None,
         "status": status,
-        "service_count": len(containers),
-        "running_count": sum(1 for c in containers if c.state == "running"),
+        "service_count": total,
+        "running_count": running,
         "created_at": None,
         "updated_at": None,
     }
@@ -245,7 +256,11 @@ def system() -> dict:
 
 @app.get("/agent/stacks", dependencies=[Depends(verify_token)])
 def list_stacks() -> list[dict]:
-    return [_summary(sid) for sid in compose_service.discover_stacks()]
+    try:
+        summaries = compose_service.stack_status_summaries()
+    except DockerError:
+        summaries = {}
+    return [_summary(sid, summaries) for sid in compose_service.discover_stacks()]
 
 
 @app.get("/agent/stacks/stats", dependencies=[Depends(verify_token)])
@@ -259,8 +274,9 @@ def get_stack(stack_id: str) -> dict:
     if not os.path.isdir(directory):
         raise HTTPException(status_code=404, detail=f"Stack '{stack_id}' not found")
     try:
-        containers = [asdict(c) for c in compose_service.containers_for_stack(stack_id)]
-        status = compose_service.compute_status(stack_id)
+        raw = compose_service.containers_for_stack(stack_id)
+        containers = [asdict(c) for c in raw]
+        status = compose_service.compute_status(stack_id, raw)
     except DockerError:
         containers = []
         status = "unknown"

backend/main.py

@@ -55,7 +55,7 @@ async def lifespan(app: FastAPI):
     schedule_task.cancel()
 
 
-app = FastAPI(title="StackPilot", version="0.21.5", lifespan=lifespan)
+app = FastAPI(title="StackPilot", version="0.21.6", lifespan=lifespan)
 
 app.add_middleware(
     CORSMiddleware,

backend/routers/stacks.py

@@ -58,20 +58,37 @@ def _get_stack_or_404(session: Session, stack_id: str) -> Stack:
     return stack
 
 
-def _stack_summary(stack: Stack) -> dict:
-    try:
-        containers = compose_service.containers_for_stack(stack.id)
-        status = compose_service.compute_status(stack.id)
-    except DockerError:
-        containers = []
-        status = "unknown"
+def _stack_summary(stack: Stack, summaries: dict | None = None) -> dict:
+    """Build a list-row summary.
+
+    Pass ``summaries`` (from :func:`compose_service.stack_status_summaries`) to
+    serve the whole stacks list from a single Docker call. Without it (single
+    create/update/clone responses), fall back to one direct query for this stack.
+    """
+    if summaries is None:
+        try:
+            containers = compose_service.containers_for_stack(stack.id)
+            total = len(containers)
+            running = sum(1 for c in containers if c.state == "running")
+            status = compose_service.compute_status(stack.id, containers)
+        except DockerError:
+            total = running = 0
+            status = "unknown"
+    else:
+        info = summaries.get(stack.id)
+        total = info["total"] if info else 0
+        running = info["running"] if info else 0
+        if compose_service.is_busy(stack.id):
+            status = "updating"
+        else:
+            status = info["status"] if info else "stopped"
     return {
         "id": stack.id,
         "name": stack.name,
         "description": stack.description,
         "status": status,
-        "service_count": len(containers),
-        "running_count": sum(1 for c in containers if c.state == "running"),
+        "service_count": total,
+        "running_count": running,
         "created_at": stack.created_at,
         "updated_at": stack.updated_at,
     }
@@ -89,7 +106,11 @@ def list_stacks(
 ) -> list[dict]:
     sync_discovered_stacks(session)
     stacks = session.exec(select(Stack)).all()
-    return [_stack_summary(s) for s in stacks]
+    try:
+        summaries = compose_service.stack_status_summaries()
+    except DockerError:
+        summaries = {}
+    return [_stack_summary(s, summaries) for s in stacks]
 
 
 @router.post("", status_code=201)
@@ -130,9 +151,10 @@ def get_stack(
 ) -> dict:
     stack = _get_stack_or_404(session, stack_id)
     try:
-        containers = [asdict(c) for c in compose_service.containers_for_stack(stack_id)]
-        status = compose_service.compute_status(stack_id)
-    except DockerError as exc:
+        raw = compose_service.containers_for_stack(stack_id)
+        containers = [asdict(c) for c in raw]
+        status = compose_service.compute_status(stack_id, raw)
+    except DockerError:
         containers = []
         status = "unknown"
     return {

backend/services/compose_service.py

@@ -184,7 +184,10 @@ def containers_for_stack(stack_id: str) -> list[ContainerInfo]:
                 id=c.id,
                 name=c.name,
                 service=c.labels.get(SERVICE_LABEL, c.name),
-                image=(c.image.tags[0] if c.image and c.image.tags else attrs.get("Config", {}).get("Image", "")),
+                # Use the configured image name from the inspect we already have;
+                # reading c.image.tags would trigger a separate image-inspect call
+                # per container.
+                image=attrs.get("Config", {}).get("Image", "") or attrs.get("Image", ""),
                 state=state.get("Status", c.status),
                 status=attrs.get("State", {}).get("Status", c.status),
                 health=health,
@@ -207,21 +210,14 @@ def clear_busy(stack_id: str) -> None:
     _BUSY.discard(stack_id)
 
 
-def compute_status(stack_id: str) -> str:
-    if stack_id in _BUSY:
-        return "updating"
-    try:
-        containers = containers_for_stack(stack_id)
-    except DockerError:
-        return "unknown"
-    if not containers:
+def is_busy(stack_id: str) -> bool:
+    return stack_id in _BUSY
+
+
+def _status_from_states(states: list[str]) -> str:
+    if not states:
         return "stopped"
-    states = [c.state for c in containers]
-    if any(s in ("dead",) for s in states):
-        return "error"
-    if any(
-        c.state == "exited" and _nonzero_exit(c) for c in containers
-    ):
+    if any(s == "dead" for s in states):
         return "error"
     running = [s for s in states if s == "running"]
     if len(running) == len(states):
@@ -231,10 +227,44 @@ def compute_status(stack_id: str) -> str:
     return "stopped"
 
 
-def _nonzero_exit(c: ContainerInfo) -> bool:
-    # We only have the textual state here; treat plain "exited" as stopped, not
-    # an error unless health says otherwise. Detailed exit codes handled in detail view.
-    return False
+def compute_status(stack_id: str, containers: Optional[list[ContainerInfo]] = None) -> str:
+    """Status for one stack. Pass already-fetched ``containers`` to avoid a
+    redundant Docker round-trip (the detail view already has them)."""
+    if stack_id in _BUSY:
+        return "updating"
+    try:
+        if containers is None:
+            containers = containers_for_stack(stack_id)
+    except DockerError:
+        return "unknown"
+    return _status_from_states([c.state for c in containers])
+
+
+def stack_status_summaries() -> dict[str, dict]:
+    """One cheap Docker call → ``{project: {status, total, running}}`` for every
+    stack at once.
+
+    Uses the low-level container *summary* list (``GET /containers/json``, no
+    per-container inspect) grouped by the compose project label. This is far
+    cheaper than calling :func:`containers_for_stack` (which full-inspects every
+    container) once per stack for the overview — turning the stacks list from
+    O(stacks × containers) Docker round-trips into a single one.
+    """
+    client = get_client()
+    raw = safe_call(client.api.containers, all=True)
+    by_project: dict[str, list[str]] = {}
+    for c in raw:
+        project = (c.get("Labels") or {}).get(COMPOSE_LABEL)
+        if project:
+            by_project.setdefault(project, []).append(c.get("State", ""))
+    return {
+        project: {
+            "status": _status_from_states(states),
+            "total": len(states),
+            "running": sum(1 for s in states if s == "running"),
+        }
+        for project, states in by_project.items()
+    }
 
 
 # --------------------------------------------------------------------------- #

docker-compose.yml

@@ -1,6 +1,6 @@
 services:
   backend:
-    image: 10.10.5.10:3020/menzelj/stackpilot-backend:latest
+    image: 10.10.6.10:3020/menzelj/stackpilot-backend:latest
     build: ./backend
     restart: unless-stopped
     environment:
@@ -38,7 +38,7 @@ services:
     #   - "5008:5008"
 
   frontend:
-    image: 10.10.5.10:3020/menzelj/stackpilot-frontend:latest
+    image: 10.10.6.10:3020/menzelj/stackpilot-frontend:latest
     build: ./frontend
     restart: unless-stopped
     depends_on:

frontend/package.json

@@ -1,7 +1,7 @@
 {
   "name": "stackpilot-frontend",
   "private": true,
-  "version": "0.21.5",
+  "version": "0.21.6",
   "type": "module",
   "scripts": {
     "dev": "vite",