Files
stackpilot/backend/routers/stacks.py
T
menzeljandClaude Opus 5 09bed274eb
CI / check (push) Successful in 7m4s
CI / build-and-push (push) Successful in 1m47s
Lock stacks during compose runs, cache stats, persist runtime state (0.47.0)
F7 — Nothing stopped two compose operations landing on the same stack. There
was a busy flag, but is_busy() was only ever read to colour the status column;
no lifecycle handler consulted it before acting. Two tabs, or auto-update
picking up a stack somebody had just clicked, both ran pull + up -d against the
same project and raced over recreating containers.

Lifecycle calls, the two deploy WebSockets and the auto-update pass now take a
real lock; a second caller gets 409 (or an error frame and close 4409) and
auto-update skips and retries next cycle. The lock is a row rather than a set
in one worker's memory, so it holds across workers and across a restart, and it
carries an expiry — a worker killed mid-deploy would otherwise strand the stack
with no fix short of editing the database.

F10 — /api/stacks/stats sampled every running container on every call, one
blocking daemon request each, and both the dashboard and the stacks list poll
it every five seconds. Two tabs on a 40-container host meant a sustained ~16
samples a second. Cached for 4s behind a lock so concurrent callers share one
sweep, the same shape dashboard_service already used for its fleet aggregate.

F11 — Three module dicts assumed exactly one uvicorn worker without saying so
and were lost on restart. The busy set is the lock above. The image update
cache is now mirrored to SQLite, so a restart shows the badges immediately
instead of blanking them for up to an hour, and the already-notified marks come
back with them rather than re-announcing the same updates. The login rate
limiter is a table, so it cannot be cleared by getting the process to restart
and no longer multiplies by the worker count.

The constraint that shaped this: compose_service and update_service are shared
with the agent, which has no database. Neither may import one. So the lock is a
separate service the central app enforces at its own entry points, and update
persistence is an opt-in callback the central app registers in its lifespan —
the agent registers nothing and behaves exactly as before. A test asserts
update_service never imports the database, since that is the kind of thing a
later change breaks silently.

Both new nets were checked by reverting the fix: dropping the lock from
_lifecycle fails six tests, removing the stats cache fails the one that names
the behaviour.

Also wires up cache pruning in the same sweep — without it both the dict and
the table grew one entry per image tag ever run, for the life of the install.

31 new tests (729 total).

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dk43rmEeRfYi5wsLDbmfyG
2026-08-31 13:43:39 +02:00

486 lines
17 KiB
Python

"""Stack CRUD + lifecycle endpoints."""
from __future__ import annotations
import os
from dataclasses import asdict
from fastapi import APIRouter, Depends, HTTPException, Query, Request
from fastapi.responses import FileResponse
from sqlmodel import Session, select
from auth import get_current_user, require_admin
from database import get_session
from docker_client import DockerError
from models.stack import (
ConvertRequest,
ConvertResponse,
Stack,
StackCloneRequest,
StackCreate,
StackUpdate,
)
from models.setting import (
EVENT_PULL_FAILED,
EVENT_STACK_ERROR,
EVENT_STACK_START,
EVENT_STACK_STOP,
)
from models.auto_update import AutoUpdateRead, AutoUpdateWrite
from models.user import User
from services import (
audit_service,
auto_update_service,
compose_service,
notify_service,
stack_lock_service,
stats_service,
update_service,
)
from services.convert_service import convert_docker_run
router = APIRouter(prefix="/api/stacks", tags=["stacks"])
# --------------------------------------------------------------------------- #
# helpers
# --------------------------------------------------------------------------- #
def _client_ip(request: Request) -> str:
return request.client.host if request.client else "unknown"
def sync_discovered_stacks(session: Session) -> None:
"""Register any on-disk stacks not yet in the database."""
known = {s.id for s in session.exec(select(Stack)).all()}
for stack_id in compose_service.discover_stacks():
if stack_id not in known:
stack = Stack(id=stack_id, name=stack_id)
session.add(stack)
session.commit()
def _get_stack_or_404(session: Session, stack_id: str) -> Stack:
stack = session.get(Stack, stack_id)
if not stack:
raise HTTPException(status_code=404, detail=f"Stack '{stack_id}' not found")
return stack
def _stack_summary(
stack: Stack, summaries: dict | None = None, busy: dict[str, str] | None = None
) -> dict:
"""Build a list-row summary.
Pass ``summaries`` (from :func:`compose_service.stack_status_summaries`) and
``busy`` (from :func:`stack_lock_service.active`) to serve the whole stacks
list from one Docker call and one query. Without them (single
create/update/clone responses), fall back to one direct query for this stack.
"""
busy = busy or {}
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 stack.id in busy:
status = "updating"
else:
status = info["status"] if info else "stopped"
return {
"id": stack.id,
"name": stack.name,
"description": stack.description,
"status": status,
"service_count": total,
"running_count": running,
"created_at": stack.created_at,
"updated_at": stack.updated_at,
}
# --------------------------------------------------------------------------- #
# CRUD
# --------------------------------------------------------------------------- #
@router.get("")
def list_stacks(
session: Session = Depends(get_session),
_user: User = Depends(get_current_user),
) -> list[dict]:
sync_discovered_stacks(session)
stacks = session.exec(select(Stack)).all()
try:
summaries = compose_service.stack_status_summaries()
except DockerError:
summaries = {}
busy = stack_lock_service.active(session)
return [_stack_summary(s, summaries, busy) for s in stacks]
@router.post("", status_code=201)
def create_stack(
body: StackCreate,
request: Request,
session: Session = Depends(get_session),
user: User = Depends(require_admin),
) -> dict:
stack_id = compose_service.slugify(body.name)
if session.get(Stack, stack_id) or os.path.isdir(compose_service.stack_dir(stack_id)):
raise HTTPException(status_code=409, detail=f"Stack '{stack_id}' already exists")
compose_service.write_compose(stack_id, body.yaml or "services:\n")
if body.env:
compose_service.write_env(stack_id, body.env)
stack = Stack(id=stack_id, name=body.name, description=body.description)
session.add(stack)
session.commit()
session.refresh(stack)
audit_service.record(
session, user=user.username, action="stack.create", target=stack_id,
ip=_client_ip(request),
)
return _stack_summary(stack)
@router.get("/stats")
def stacks_stats(_user: User = Depends(get_current_user)) -> dict:
"""Live CPU (cores) and memory usage per stack, with assigned limits."""
return stats_service.stack_stats()
@router.get("/updates")
def stacks_updates(_user: User = Depends(get_current_user)) -> dict:
"""Per-stack image-update availability, read from the cached registry
digests (no live registry calls — safe for the list to poll)."""
return update_service.stacks_update_summary()
@router.get("/{stack_id}")
def get_stack(
stack_id: str,
session: Session = Depends(get_session),
user: User = Depends(get_current_user),
) -> dict:
stack = _get_stack_or_404(session, stack_id)
try:
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 {
"id": stack.id,
"name": stack.name,
"description": stack.description,
"status": status,
"yaml": compose_service.read_compose(stack_id),
# The .env is where credentials live by convention, so it is withheld
# from the read-only role — same reasoning as the admin-only file
# browser. Non-admins still get status, services and the compose file.
"env": compose_service.read_env(stack_id) if user.role == "admin" else "",
"containers": containers,
"created_at": stack.created_at,
"updated_at": stack.updated_at,
}
@router.put("/{stack_id}")
def update_stack(
stack_id: str,
body: StackUpdate,
request: Request,
session: Session = Depends(get_session),
user: User = Depends(require_admin),
) -> dict:
stack = _get_stack_or_404(session, stack_id)
if body.yaml is not None:
compose_service.write_compose(stack_id, body.yaml)
if body.env is not None:
compose_service.write_env(stack_id, body.env)
if body.name is not None:
stack.name = body.name
if body.description is not None:
stack.description = body.description
stack.updated_at = compose_service.now()
session.add(stack)
session.commit()
session.refresh(stack)
audit_service.record(
session, user=user.username, action="stack.update", target=stack_id,
ip=_client_ip(request),
)
return _stack_summary(stack)
@router.delete("/{stack_id}")
async def delete_stack(
stack_id: str,
request: Request,
delete_files: bool = Query(True),
session: Session = Depends(get_session),
user: User = Depends(require_admin),
) -> dict:
stack = _get_stack_or_404(session, stack_id)
try:
await compose_service.down(stack_id)
except Exception: # noqa: BLE001 - best-effort teardown
pass
if delete_files:
compose_service.delete_stack_files(stack_id)
session.delete(stack)
session.commit()
audit_service.record(
session, user=user.username, action="stack.delete", target=stack_id,
detail=f"delete_files={delete_files}", ip=_client_ip(request),
)
return {"ok": True}
@router.post("/{stack_id}/clone")
def clone_stack(
stack_id: str,
body: StackCloneRequest,
request: Request,
session: Session = Depends(get_session),
user: User = Depends(require_admin),
) -> dict:
_get_stack_or_404(session, stack_id)
new_id = compose_service.slugify(body.name)
if session.get(Stack, new_id):
raise HTTPException(status_code=409, detail=f"Stack '{new_id}' already exists")
try:
compose_service.clone_stack_files(stack_id, new_id)
except compose_service.StackFileError as exc:
raise HTTPException(status_code=409, detail=str(exc)) from exc
stack = Stack(id=new_id, name=body.name)
session.add(stack)
session.commit()
session.refresh(stack)
audit_service.record(
session, user=user.username, action="stack.clone",
target=new_id, detail=f"from {stack_id}", ip=_client_ip(request),
)
return _stack_summary(stack)
# --------------------------------------------------------------------------- #
# lifecycle
# --------------------------------------------------------------------------- #
# which lifecycle actions emit a notification on success
_START_ACTIONS = {"start", "restart", "update"}
_STOP_ACTIONS = {"stop", "down"}
async def _notify_lifecycle(action_name: str, stack_id: str, ok: bool, detail: str, session) -> None:
try:
if not ok:
event = EVENT_PULL_FAILED if action_name in ("pull", "update") else EVENT_STACK_ERROR
await notify_service.notify(
event,
f"Stack '{stack_id}' {action_name} failed",
detail or f"compose {action_name} returned a non-zero exit code.",
session,
)
elif action_name in _START_ACTIONS:
await notify_service.notify(
EVENT_STACK_START, f"Stack '{stack_id}' started",
f"compose {action_name} completed successfully.", session,
)
elif action_name in _STOP_ACTIONS:
await notify_service.notify(
EVENT_STACK_STOP, f"Stack '{stack_id}' stopped",
f"compose {action_name} completed successfully.", session,
)
except Exception: # noqa: BLE001 - notifications are best-effort
pass
async def _lifecycle(action_fn, action_name, stack_id, request, session, user):
_get_stack_or_404(session, stack_id)
# One compose operation per stack. Without this two tabs (or auto-update
# landing on a stack somebody just clicked) both run pull + up -d against
# the same project and race over recreating containers.
try:
with stack_lock_service.hold(session, stack_id, action_name, user.username):
result = await action_fn(stack_id)
except stack_lock_service.StackBusy as exc:
raise HTTPException(
status_code=409,
detail=f"Stack '{stack_id}' is busy: {exc.action} in progress",
) from exc
audit_service.record(
session, user=user.username, action=f"stack.{action_name}", target=stack_id,
detail=f"rc={result.get('returncode')}", ip=_client_ip(request),
)
ok = result.get("returncode") in (0, None)
stderr = result.get("stderr", "").strip()[-2000:]
await _notify_lifecycle(action_name, stack_id, ok, stderr, session)
if not ok:
raise HTTPException(
status_code=500,
detail={
"error": f"compose {action_name} failed",
"detail": stderr,
},
)
return result
@router.post("/{stack_id}/start")
async def start_stack(stack_id: str, request: Request, session: Session = Depends(get_session), user: User = Depends(require_admin)):
return await _lifecycle(compose_service.up, "start", stack_id, request, session, user)
@router.post("/{stack_id}/stop")
async def stop_stack(stack_id: str, request: Request, session: Session = Depends(get_session), user: User = Depends(require_admin)):
return await _lifecycle(compose_service.stop, "stop", stack_id, request, session, user)
@router.post("/{stack_id}/restart")
async def restart_stack(stack_id: str, request: Request, session: Session = Depends(get_session), user: User = Depends(require_admin)):
return await _lifecycle(compose_service.restart, "restart", stack_id, request, session, user)
@router.post("/{stack_id}/pull")
async def pull_stack(stack_id: str, request: Request, session: Session = Depends(get_session), user: User = Depends(require_admin)):
result = await _lifecycle(compose_service.pull, "pull", stack_id, request, session, user)
update_service.refresh_stack_local(stack_id)
return result
@router.post("/{stack_id}/update")
async def update_stack_images(stack_id: str, request: Request, session: Session = Depends(get_session), user: User = Depends(require_admin)):
result = await _lifecycle(compose_service.update, "update", stack_id, request, session, user)
update_service.refresh_stack_local(stack_id)
return result
@router.post("/{stack_id}/down")
async def down_stack(stack_id: str, request: Request, session: Session = Depends(get_session), user: User = Depends(require_admin)):
return await _lifecycle(compose_service.down, "down", stack_id, request, session, user)
# --------------------------------------------------------------------------- #
# logs / export / convert
# --------------------------------------------------------------------------- #
@router.get("/{stack_id}/logs")
async def stack_logs(
stack_id: str,
tail: int = Query(200, le=2000),
session: Session = Depends(get_session),
_user: User = Depends(get_current_user),
) -> dict:
_get_stack_or_404(session, stack_id)
result = await compose_service.logs(stack_id, tail=tail)
return {"logs": result.get("stdout", "") + result.get("stderr", "")}
@router.get("/{stack_id}/services/{service}/logs")
async def service_logs(
stack_id: str,
service: str,
tail: int = Query(200, le=2000),
session: Session = Depends(get_session),
_user: User = Depends(get_current_user),
) -> dict:
_get_stack_or_404(session, stack_id)
result = await compose_service.logs(stack_id, service=service, tail=tail)
return {"logs": result.get("stdout", "") + result.get("stderr", "")}
@router.get("/{stack_id}/export")
def export_stack(
stack_id: str,
session: Session = Depends(get_session),
_admin: User = Depends(require_admin),
):
"""Download the whole stack folder as a tarball. Admin only: the archive
contains the ``.env`` and every ``.secrets/*`` file verbatim."""
import tarfile
import tempfile
_get_stack_or_404(session, stack_id) # 404s if unknown
directory = compose_service.stack_dir(stack_id)
if not os.path.isdir(directory):
raise HTTPException(status_code=404, detail="Stack directory missing")
tmp = tempfile.NamedTemporaryFile(delete=False, suffix=".tar.gz")
with tarfile.open(tmp.name, "w:gz") as tar:
tar.add(directory, arcname=stack_id)
date = compose_service.now().strftime("%Y%m%d")
return FileResponse(
tmp.name,
media_type="application/gzip",
filename=f"stack-{stack_id}-{date}.tar.gz",
)
@router.post("/convert", response_model=ConvertResponse)
def convert(
body: ConvertRequest,
_user: User = Depends(get_current_user),
) -> ConvertResponse:
try:
return ConvertResponse(yaml=convert_docker_run(body.command))
except ValueError as exc:
raise HTTPException(status_code=400, detail=str(exc)) from exc
# --------------------------------------------------------------------------- #
# Auto-update policy (Watchtower-style) — local stacks
# --------------------------------------------------------------------------- #
@router.get("/{stack_id}/auto-update", response_model=AutoUpdateRead)
def get_auto_update(
stack_id: str,
session: Session = Depends(get_session),
_user: User = Depends(get_current_user),
) -> dict:
policy = auto_update_service.get_policy(session, stack_id)
return auto_update_service.to_read(session, policy, stack_id)
@router.put("/{stack_id}/auto-update", response_model=AutoUpdateRead)
def set_auto_update(
stack_id: str,
body: AutoUpdateWrite,
request: Request,
session: Session = Depends(get_session),
user: User = Depends(require_admin),
) -> dict:
policy = auto_update_service.upsert_policy(session, stack_id, body.enabled, body.redeploy)
audit_service.record(
session, user=user.username, action="stack.auto_update",
target=stack_id, detail=f"enabled={body.enabled} redeploy={body.redeploy}",
ip=_client_ip(request),
)
return auto_update_service.to_read(session, policy, stack_id)
@router.post("/{stack_id}/auto-update/run", response_model=AutoUpdateRead)
async def run_auto_update(
stack_id: str,
session: Session = Depends(get_session),
user: User = Depends(require_admin),
) -> dict:
policy = auto_update_service.get_policy(session, stack_id)
if policy is None:
raise HTTPException(status_code=404, detail="No auto-update policy for this stack")
await auto_update_service.run_policy(session, policy)
session.refresh(policy)
return auto_update_service.to_read(session, policy, stack_id)