menzeljandClaude Opus 5
09bed274eb
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
142 lines
4.3 KiB
Python
142 lines
4.3 KiB
Python
"""StackPilot backend — FastAPI application entry point."""
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import logging
|
|
from contextlib import asynccontextmanager
|
|
|
|
from fastapi import FastAPI, Request
|
|
from fastapi.middleware.cors import CORSMiddleware
|
|
from fastapi.responses import JSONResponse
|
|
from sqlmodel import Session
|
|
|
|
from config import settings
|
|
from version import APP_VERSION
|
|
from database import engine, init_db
|
|
from docker_client import DockerError
|
|
from routers import (
|
|
agents,
|
|
audit,
|
|
auth,
|
|
backups,
|
|
containers,
|
|
dashboard,
|
|
destinations,
|
|
editor,
|
|
files,
|
|
images,
|
|
networks,
|
|
ports,
|
|
schedules,
|
|
secrets,
|
|
settings as settings_router,
|
|
stacks,
|
|
system,
|
|
templates,
|
|
volumes,
|
|
ws,
|
|
)
|
|
from services import (
|
|
backup_destination_service,
|
|
image_status_store,
|
|
schedule_service,
|
|
stack_lock_service,
|
|
template_service,
|
|
update_service,
|
|
)
|
|
|
|
logging.basicConfig(level=logging.INFO)
|
|
logger = logging.getLogger("stackpilot")
|
|
|
|
|
|
@asynccontextmanager
|
|
async def lifespan(app: FastAPI):
|
|
init_db()
|
|
# Register stacks that already exist on disk.
|
|
try:
|
|
with Session(engine) as session:
|
|
stacks.sync_discovered_stacks(session)
|
|
except Exception as exc: # noqa: BLE001
|
|
logger.warning("Stack discovery failed: %s", exc)
|
|
# One-off: encrypt backup-destination credentials written before they were
|
|
# stored encrypted (see services/crypto_service.py).
|
|
try:
|
|
with Session(engine) as session:
|
|
encrypted = backup_destination_service.migrate_plaintext_configs(session)
|
|
if encrypted:
|
|
logger.info("Encrypted %d backup destination config(s) at rest", encrypted)
|
|
except Exception as exc: # noqa: BLE001
|
|
logger.warning("Destination config encryption migration failed: %s", exc)
|
|
try:
|
|
moved = template_service.migrate_legacy_db_templates()
|
|
if moved:
|
|
logger.info("Migrated %d custom template(s) from the database to folders", moved)
|
|
except Exception as exc: # noqa: BLE001
|
|
logger.warning("Legacy template migration failed: %s", exc)
|
|
# Runtime state that used to live in module dicts and was lost on restart.
|
|
try:
|
|
with Session(engine) as session:
|
|
stale = stack_lock_service.prune_expired(session)
|
|
if stale:
|
|
logger.info("Cleared %d stale stack lock(s) from a previous run", stale)
|
|
except Exception as exc: # noqa: BLE001
|
|
logger.warning("Could not prune stack locks: %s", exc)
|
|
try:
|
|
restored = image_status_store.install()
|
|
logger.info("Restored %d cached image update status(es)", restored)
|
|
except Exception as exc: # noqa: BLE001
|
|
logger.warning("Could not restore the image update cache: %s", exc)
|
|
|
|
update_task = asyncio.create_task(update_service.background_loop())
|
|
schedule_task = asyncio.create_task(schedule_service.scheduler_loop())
|
|
logger.info("StackPilot backend ready on port %s", settings.PORT)
|
|
yield
|
|
update_task.cancel()
|
|
schedule_task.cancel()
|
|
|
|
|
|
app = FastAPI(title="StackPilot", version=APP_VERSION, lifespan=lifespan)
|
|
|
|
app.add_middleware(
|
|
CORSMiddleware,
|
|
allow_origins=settings.CORS_ORIGINS,
|
|
allow_credentials=True,
|
|
allow_methods=["*"],
|
|
allow_headers=["*"],
|
|
)
|
|
|
|
|
|
@app.exception_handler(DockerError)
|
|
async def docker_error_handler(_request: Request, exc: DockerError):
|
|
return JSONResponse(
|
|
status_code=502,
|
|
content={"error": exc.error, "detail": exc.detail},
|
|
)
|
|
|
|
|
|
app.include_router(auth.router)
|
|
app.include_router(stacks.router)
|
|
app.include_router(secrets.router)
|
|
app.include_router(containers.router)
|
|
app.include_router(dashboard.router)
|
|
app.include_router(system.router)
|
|
app.include_router(volumes.router)
|
|
app.include_router(editor.router)
|
|
app.include_router(files.router)
|
|
app.include_router(images.router)
|
|
app.include_router(ports.router)
|
|
app.include_router(templates.router)
|
|
app.include_router(audit.router)
|
|
app.include_router(settings_router.router)
|
|
app.include_router(backups.router)
|
|
app.include_router(destinations.router)
|
|
app.include_router(schedules.router)
|
|
app.include_router(networks.router)
|
|
app.include_router(agents.router)
|
|
app.include_router(ws.router)
|
|
|
|
|
|
@app.get("/api/health")
|
|
def health() -> dict:
|
|
return {"status": "ok", "version": APP_VERSION}
|