Files
stackpilot/backend/main.py
T
menzeljandClaude Opus 5 e650aa6833
CI / check (push) Successful in 12m31s
CI / build-and-push (push) Successful in 1m56s
Add API tokens for scripts and CI (0.57.0)
A session token is the wrong credential for automation. It expires in an hour,
it is minted by typing a password, and revoking it signs every one of that
person's devices out. So automation gets its own credential, revocable on its
own, and showing up in the audit log as itself.

Three decisions worth recording, because each one is a place this could have
been built wrong.

**Only a hash is stored.** This is the opposite call from registry passwords one
release ago, and for a concrete reason: a registry password has to be handed
back to the registry, so it must be recoverable and is encrypted. A token is
only ever compared against, so it does not need to be — and not keeping it is
the difference between leaking the database and leaking everything the database
protects. It is shown once and cannot be recovered; a readable prefix is kept so
rows are still identifiable in the UI and the audit log. The hash is SHA-256,
deliberately not bcrypt: bcrypt is slow to make guessing low-entropy human
passwords expensive, and a token is 256 bits of secrets output, so the cost
would buy nothing and would land on every single API request.

**The scope is not folded into the User object.** get_current_user returns a
session-attached row; downgrading its role in place to represent a read-only
token would be written back to the database the next time anything committed
that user — logout-everywhere does exactly that. So the token row is stashed on
request.state and require_admin consults it, leaving the User untouched. The
same lookup caps a token at its owner's authority rather than trusting the scope
alone, so a demoted admin's token drops to read-only with them and a disabled
account's tokens stop working.

**A token cannot make itself permanent.** Creating tokens and creating users now
require a signed-in session, via a require_session dependency that rejects
token-authenticated requests. Without it, a leaked CI credential could mint a
second one and survive its own revocation — the failure mode where revoking the
leak does nothing. This is the one behaviour change for existing installs:
scripted user creation now needs a login.

The WebSocket routes still take JWTs only. They carry logs, the terminal and the
deploy console, which a CI job has no use for, and leaving them alone keeps the
token surface to the REST API.

19 tests, covering what is stored, that a read token really is read-only while
its owner is an admin, that demoting and disabling the owner both take effect,
expiry, tampering, the throttle on last-used writes, and that a token can
neither mint another nor create a user. Verified end to end against a running
app: two tokens, both scopes, revocation, and no plaintext anywhere in the
database or the list response.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-18 00:53:58 +02:00

160 lines
5.1 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 (
audit,
auth,
backups,
containers,
dashboard,
destinations,
editor,
files,
images,
networks,
ports,
registries,
schedules,
secrets,
settings as settings_router,
stacks,
system,
templates,
tokens,
volumes,
ws,
)
from services import (
backup_destination_service,
image_status_store,
logo_service,
registry_service,
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)
# Private registry credentials: into the in-memory cache the update checker
# reads, and into the config.json the Docker CLI reads.
try:
with Session(engine) as session:
known = registry_service.reload(session)
if known:
logger.info("Loaded credentials for %d registr%s", known, "y" if known == 1 else "ies")
except Exception as exc: # noqa: BLE001
logger.warning("Could not load registry credentials: %s", exc)
update_task = asyncio.create_task(update_service.background_loop())
schedule_task = asyncio.create_task(schedule_service.scheduler_loop())
# App logos. Deliberately a task and not awaited: the catalog is a network
# download, and a box with no outbound internet must still start instantly
# (it just keeps the built-in glyphs).
logo_task = asyncio.create_task(logo_service.catalog_loop())
logger.info("StackPilot backend ready on port %s", settings.PORT)
yield
update_task.cancel()
schedule_task.cancel()
logo_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(tokens.router)
app.include_router(registries.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(ws.router)
@app.get("/api/health")
def health() -> dict:
return {"status": "ok", "version": APP_VERSION}