anti
30750d294d
The swarm controller (port 8770) exposed 9 routes with zero app-layer auth, and swarmctl --tls defaulted off — anyone able to reach the port could enroll workers (minting CA-signed certs + private keys), deploy, or tear down the fleet. Two fail-closed layers: - require_operator_cert gates every operator route (enroll/deploy/ teardown/hosts/check/deckies). When mTLS is on, the peer cert's CN must be an operator identity (decnet-master/swarmctl); worker and updater@* certs are rejected. Plaintext loopback (single-host master) is accepted as the local operator — the docker.sock boundary. - swarmctl refuses to bind a routable interface without --tls, so a network-exposed plaintext control plane can never start. /heartbeat keeps its worker fingerprint pinning. Closes the two ASVS criticals (control-plane no-auth, unauthenticated cert minting).
67 lines
2.1 KiB
Python
67 lines
2.1 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
"""DELETE /swarm/hosts/{uuid} — decommission a worker.
|
|
|
|
Removes the DeckyShard rows bound to the host (portable cascade — MySQL
|
|
and SQLite both honor it via the repo layer), deletes the SwarmHost row,
|
|
and best-effort-cleans the per-worker bundle directory on the master.
|
|
|
|
Also asks the worker agent to wipe its own install (keeping logs). A
|
|
dead/unreachable worker does not block master-side cleanup.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import pathlib
|
|
|
|
from fastapi import APIRouter, Depends, HTTPException, status
|
|
|
|
from decnet.logging import get_logger
|
|
from decnet.swarm.client import AgentClient
|
|
from decnet.web.db.repository import BaseRepository
|
|
from decnet.web.dependencies import get_repo
|
|
from decnet.web.router.swarm._mtls import PeerCert, require_operator_cert
|
|
|
|
log = get_logger("swarm.decommission")
|
|
router = APIRouter()
|
|
|
|
|
|
@router.delete(
|
|
"/hosts/{uuid}",
|
|
status_code=status.HTTP_204_NO_CONTENT,
|
|
tags=["Swarm Hosts"],
|
|
responses={404: {"description": "No host with this UUID is enrolled"}},
|
|
)
|
|
async def api_decommission_host(
|
|
uuid: str,
|
|
repo: BaseRepository = Depends(get_repo),
|
|
_operator: PeerCert = Depends(require_operator_cert),
|
|
) -> None:
|
|
row = await repo.get_swarm_host_by_uuid(uuid)
|
|
if row is None:
|
|
raise HTTPException(status_code=404, detail="host not found")
|
|
|
|
try:
|
|
async with AgentClient(host=row) as agent:
|
|
await agent.self_destruct()
|
|
except Exception:
|
|
log.exception(
|
|
"decommission: self-destruct dispatch failed host=%s — "
|
|
"proceeding with master-side cleanup anyway",
|
|
row.get("name"),
|
|
)
|
|
|
|
await repo.delete_decky_shards_for_host(uuid)
|
|
await repo.delete_swarm_host(uuid)
|
|
|
|
# Best-effort bundle cleanup; if the dir was moved manually, don't fail.
|
|
bundle_dir = pathlib.Path(row.get("cert_bundle_path") or "")
|
|
if bundle_dir.is_dir():
|
|
for child in bundle_dir.iterdir():
|
|
try:
|
|
child.unlink()
|
|
except OSError:
|
|
pass
|
|
try:
|
|
bundle_dir.rmdir()
|
|
except OSError:
|
|
pass
|