Files
stackpilot/backend/routers/images.py
T
menzeljandClaude Opus 5 57231e4a67
CI / check (push) Successful in 13m19s
CI / build-and-push (push) Successful in 1m57s
Show live progress while pruning volumes, and ask first (0.62.0)
The volume prune gets the same treatment as the image prune in 0.61.0:
the candidates are listed and removed one by one in the background, and
the Volumes page shows a progress bar (x / y, the volume being removed,
failures) followed by a toast with the space freed.

The button also used to delete without asking, and a bare docker volume
prune only removes anonymous volumes on Engine 23+ with no way to include
named ones. It now opens a confirmation dialog with an explicit -a option
that warns it also takes the data of every stack that is down.

- Candidates: volumes no container (running or stopped) mounts, local
  scope only, and anonymous (com.docker.volume.anonymous) unless -a.
  Volumes from pre-23 daemons carry no such label, so they only go with
  -a, which errs on the side of keeping data.
- Removed without force, so a volume mounted since the listing is
  refused; one refusal does not stop the rest.
- No closing daemon prune: nothing is left over, and on a pre-23 daemon an
  unfiltered one would delete named volumes too.
- Freed space is the sum of the deleted volumes' sizes (volumes share no
  data), from the size cache, which is invalidated afterwards.
- POST /api/volumes/prune takes all= and background=; without background
  it still waits and returns {VolumesDeleted, SpaceReclaimed}.
  GET /api/volumes/prune-status is admin-only.
- volume_sizes() ("Compute sizes") now uses the long-timeout client; it
  walks every volume and could hit the same 60s limit.

The progress machinery moved into services/prune_job.py (PruneJob,
PrunePlan) and, on the frontend, the usePruneJob hook and PruneProgress
component, shared by both pages. The status now carries a phase
(preparing / removing / finishing) so the parts without a count say what
they are doing.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-18 10:23:51 +02:00

184 lines
6.2 KiB
Python

"""Image listing, update checks and vulnerability scanning."""
from __future__ import annotations
import json
from fastapi import APIRouter, Depends, HTTPException, Query, Request, Response
from sqlmodel import Session
from auth import get_current_user, require_admin
from database import engine, get_session
from models.image_scan import ImageScan, ScanDetail, ScanRequest, ScanSummary
from models.user import User
from services import audit_service, image_service, scan_service, update_service
from services.prune_job import PruneBusy
router = APIRouter(prefix="/api/images", tags=["images"])
def _ip(request: Request) -> str:
return request.client.host if request.client else "unknown"
@router.get("")
def list_images(_user: User = Depends(get_current_user)) -> list[dict]:
return image_service.list_images()
@router.get("/updates")
def updates(_user: User = Depends(get_current_user)) -> dict:
return update_service.get_cache()
@router.post("/check")
async def check(_user: User = Depends(require_admin)) -> dict:
return await update_service.check_all()
@router.post("/prune")
def prune(
request: Request,
response: Response,
all_unused: bool = Query(False, alias="all"),
background: bool = Query(False),
user: User = Depends(require_admin),
) -> dict:
"""Remove unused images (``all=true``: also unused tagged ones, ``-a``).
Waits for the result by default. ``background=true`` returns 202 with the
initial status at once and leaves the caller to poll /prune-status, which
is what the UI does: a large prune can outlast the proxy's read timeout.
"""
username, ip = user.username, _ip(request)
def audit(result: dict) -> None:
# Docker lists every untagging too; only "Deleted" entries are images.
deleted = sum(1 for entry in result["ImagesDeleted"] if "Deleted" in entry)
# Its own session: in the background case the request's is long closed.
with Session(engine) as own:
audit_service.record(
own, user=username, action="image.prune", target="*",
detail=(
f"all={all_unused} deleted={deleted} "
f"reclaimed={result['SpaceReclaimed']}"
),
ip=ip,
)
try:
if background:
response.status_code = 202
return image_service.start_prune(all_unused, on_done=audit)
result = image_service.prune_images(all_unused)
except PruneBusy as exc:
raise HTTPException(status_code=409, detail=str(exc)) from exc
audit(result)
return result
@router.get("/prune-status")
def prune_status(_admin: User = Depends(require_admin)) -> dict:
"""Progress of a running (or the last) prune. Admin-only like the prune."""
return image_service.prune_status()
# --------------------------------------------------------------------------- #
# Vulnerability scanning
# --------------------------------------------------------------------------- #
def _summary(row: ImageScan, stale: bool = False) -> ScanSummary:
return ScanSummary(
image=row.image,
digest=row.digest,
scanner=row.scanner,
critical=row.critical,
high=row.high,
medium=row.medium,
low=row.low,
unknown=row.unknown,
fixable=row.fixable,
total=scan_service.total(row),
scanned_at=row.scanned_at,
duration_ms=row.duration_ms,
error=row.error,
stale=stale,
)
@router.get("/scans", response_model=list[ScanSummary])
def list_scans(
session: Session = Depends(get_session),
_user: User = Depends(get_current_user),
) -> list[ScanSummary]:
"""Every cached scan result. Cheap — no scanning happens here."""
rows = scan_service.all_scans(session).values()
return [_summary(row, scan_service.is_stale(row)) for row in rows]
@router.get("/scan", response_model=ScanDetail)
def scan_detail(
image: str = Query(...),
session: Session = Depends(get_session),
_user: User = Depends(get_current_user),
) -> ScanDetail:
row = scan_service.all_scans(session).get(image)
if not row:
raise HTTPException(status_code=404, detail=f"'{image}' has not been scanned")
try:
findings = json.loads(row.findings or "[]")
except json.JSONDecodeError:
findings = []
return ScanDetail(
**_summary(row, scan_service.is_stale(row)).model_dump(), findings=findings
)
@router.post("/scan", response_model=ScanSummary)
async def scan_image(
body: ScanRequest,
request: Request,
session: Session = Depends(get_session),
user: User = Depends(require_admin),
) -> ScanSummary:
"""Scan one image. Takes a while — the scanner runs as a container."""
image = (body.image or "").strip()
if not image:
raise HTTPException(status_code=400, detail="An image is required")
row = await scan_service.scan(session, image)
audit_service.record(
session, user=user.username, action="image.scan", target=image,
detail=row.error or f"{scan_service.total(row)} finding(s), {row.fixable} fixable",
ip=_ip(request),
)
if row.error:
# The row is stored either way, so the UI can show why it failed.
raise HTTPException(status_code=502, detail=row.error)
return _summary(row)
@router.post("/scan-all")
async def scan_all(
request: Request,
session: Session = Depends(get_session),
user: User = Depends(require_admin),
) -> dict:
"""Scan every image a stack is using. Serial, and one sweep at a time."""
images = sorted({row["tag"] for row in image_service.list_images() if row["stacks"]})
try:
result = await scan_service.sweep(session, images)
except scan_service.ScanError as exc:
raise HTTPException(status_code=409, detail=str(exc)) from exc
audit_service.record(
session, user=user.username, action="image.scan-all", target="*",
detail=f"{result['scanned']} scanned, {result['failed']} failed",
ip=_ip(request),
)
return result
@router.get("/scan-status")
def scan_status(_user: User = Depends(get_current_user)) -> dict:
"""Progress of a running sweep, so the button can show it."""
return scan_service.sweep_status()