Files
app/backend/app/cloud/connector.py
T
stroblmeandClaude Opus 5 c3ea884d72 Hold a new dashboard back until someone publishes it
A dashboard went live the moment it was created — an empty document straight to
the panels — while a new flow starts as a draft. It now works the way flows do:
published means `dashboard.json` exists, so every dashboard on every running
installation is already published and nothing needs migrating. Only the ones
created from here on start as drafts.

Mirroring FlowStore turned up a latent 500: discarding the draft of a dashboard
that had never been published unlinked its only file, and the read that followed
raised out of a 200 handler. It answers 400 now, the way a flow does.

Publishing all of them was 2N requests, because a publish has to name the
version it expects and the summaries did not carry one. They do now — and so do
the flow summaries, which had the same defect nobody had written down.

A panel had no way to hear about any of this. A publish, or a change to which
dashboards a panel carries, now puts one event on the bus and the screen
refetches what changed: no reload, so a wall display never blanks or asks for
its credential again. The subtle half is that a socket's message allowlist was
computed once at handshake — a reassigned panel would have fetched its new
document and then shown tiles that never updated.

The panels dialog logged non-superusers out. Every write in it needs a
superuser, not only the checkboxes the report mentioned, so the dialog is
read-only for everyone else. The logout itself was `main.tsx` treating 403 as a
dead session, against the contract deps.py spells out: only a 401 ends a
session, and a 403 now says so rather than silently signing someone out.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uq8mtNb97A7praJLyeEYgs
2026-08-21 14:32:57 +02:00

446 lines
18 KiB
Python

"""The link this installation opens to its portal.
Same shape as the remote-worker agent, with the direction of the favour
reversed: there, a GPU box dials the engine so the engine can give it work;
here, the engine dials the portal so the portal can pass on what a browser
asked for. Both exist because the interesting machine is the one nobody can
route to.
A proxied request is dispatched straight into this process's own ASGI app
rather than over localhost HTTP. That matters beyond saving a hop: HTTP
trigger nodes install themselves into ``app.routes`` while flows run, and an
in-process transport sees that table live, with no port, TLS or self-address
to discover.
"""
from __future__ import annotations
import asyncio
import base64
import contextlib
import logging
import time
from datetime import timedelta
from typing import Any
import httpx
from fastapi import FastAPI
from app.cloud import config as cloud_config
from app.core.config import settings
logger = logging.getLogger(__name__)
PROTOCOL = 1
HEARTBEAT_S = 20.0
STATUS_S = 60.0
MAX_BACKOFF_S = 30.0
CHUNK_BYTES = 256 * 1024
MAX_WS_MESSAGE = 1024 * 1024
#: Only the versioned API is served over the tunnel. The MCP mount and the
#: OAuth endpoints live outside it and stay local-only.
ALLOWED_PREFIX = "/api/v1/"
class CloudConnector:
"""Holds one websocket to the portal open, and answers over it."""
def __init__(self, app: FastAPI) -> None:
self._app = app
self._calls: dict[str, asyncio.Task[None]] = {}
self._streams: dict[str, asyncio.Task[None]] = {}
self._connected = False
self._connected_since: float | None = None
self._last_error: str | None = None
# -------------------------------------------------------------------------
# Status, for the local settings screen
# -------------------------------------------------------------------------
def status(self) -> dict[str, Any]:
config = cloud_config.load()
return {
"enrolled": config is not None,
"connected": self._connected,
"portal_url": config.portal_url if config else None,
# Where a browser reaches the portal, which is not always where
# this process does: enrolment may have named a container.
"issuer": config.issuer if config else None,
"portal_account": config.portal_account if config else None,
"installation_id": config.installation_id if config else None,
"last_error": self._last_error,
"connected_since": self._connected_since,
}
# -------------------------------------------------------------------------
# The connection
# -------------------------------------------------------------------------
async def serve_forever(self) -> None:
backoff = 1.0
while True:
config = cloud_config.load()
if config is None:
# Disconnected locally while we were running.
return
try:
await self._session(config)
backoff = 1.0
except asyncio.CancelledError:
raise
except Exception as exc:
self._connected = False
self._connected_since = None
self._last_error = str(exc)
logger.warning("Portal link down: %s — retrying in %.0fs", exc, backoff)
await asyncio.sleep(backoff)
backoff = min(MAX_BACKOFF_S, backoff * 2)
async def _session(self, config: cloud_config.CloudConfig) -> None:
import websockets
url = f"{config.ws_url}?token={config.token}"
async with websockets.connect(
url, max_size=MAX_WS_MESSAGE, ping_interval=20
) as socket:
await socket.send(
_dump({"op": "hello", "protocol": PROTOCOL, "app_version": _version()})
)
welcome = _load(await socket.recv())
if welcome.get("op") != "welcome":
raise RuntimeError(
str(welcome.get("reason") or "refused by the portal")
)
self._adopt_owner(config, welcome.get("owner"))
self._connected = True
self._connected_since = time.time()
self._last_error = None
logger.info(
"Attached to the portal as installation %s", config.installation_id
)
keepalive = asyncio.create_task(self._keepalive(socket, config))
try:
async for raw in socket:
frame = _load(raw)
op = frame.get("op")
if op == "req":
self._start_call(socket, frame)
elif op == "cancel":
self._cancel(str(frame.get("id") or ""))
elif op == "ws_open":
self._start_stream(socket, frame)
elif op == "ws_close":
self._cancel_stream(str(frame.get("id") or ""))
finally:
keepalive.cancel()
self._connected = False
self._connected_since = None
for task in list(self._calls.values()) + list(self._streams.values()):
task.cancel()
self._calls.clear()
self._streams.clear()
@staticmethod
def _adopt_owner(config: cloud_config.CloudConfig, owner: Any) -> None:
"""Map the enrolling account to the portal account that owns us.
Enrolment does this itself. This is for the enrolments that predate
per-user mapping: without it their owner would be refused here until
somebody enrolled the machine again — which, for a machine reached only
through the portal, means standing in front of it. Runs on every attach
because it is a no-op once the mapping is there.
Never moves a mapping somebody else holds: that would be this code
guessing at something enrolment was told.
"""
from sqlmodel import Session, select
from app.core.db import engine
from app.models import User
if not owner:
return
owner_id = str(owner)
try:
with Session(engine) as session:
if session.exec(
select(User).where(User.portal_sub == owner_id)
).first():
return
user = session.get(User, config.local_user_id)
if user is None or user.portal_sub:
return
user.portal_sub = owner_id
session.add(user)
session.commit()
logger.info("Mapped %s to the portal account that owns us", user.email)
except Exception:
# A mapping that could not be written is not a reason to drop the
# link: everything else this connection does still works.
logger.exception("Could not map the enrolling account to the portal owner")
async def _keepalive(self, socket: Any, config: cloud_config.CloudConfig) -> None:
"""Heartbeats, plus a health snapshot the portal can show while offline."""
last_status = 0.0
while True:
now = time.time()
if now - last_status >= STATUS_S or last_status == 0.0:
summary = await self._health_summary(config)
await socket.send(
_dump(
{"op": "status", "summary": summary, "app_version": _version()}
)
)
last_status = now
else:
await socket.send(_dump({"op": "heartbeat"}))
await asyncio.sleep(HEARTBEAT_S)
async def _health_summary(
self, config: cloud_config.CloudConfig
) -> dict[str, Any] | None:
"""This installation's own health, as the dashboard reads it.
Fetched through the same in-process transport as everything else, with
a short-lived local token: the observability API is authenticated, and
this process is entitled to mint one for the enrolling user.
"""
from app.core import security
token = security.create_access_token(config.local_user_id, timedelta(minutes=5))
try:
async with self._client() as client:
response = await client.get(
"/api/v1/observability/summary",
headers={"Authorization": f"Bearer {token}"},
)
if response.status_code == 200:
summary: dict[str, Any] = response.json()
return summary
except Exception:
logger.debug("Could not collect a health summary for the portal")
return None
# -------------------------------------------------------------------------
# Proxied requests
# -------------------------------------------------------------------------
def _client(self) -> httpx.AsyncClient:
return httpx.AsyncClient(
transport=httpx.ASGITransport(app=self._app),
base_url="http://installation.local",
timeout=httpx.Timeout(300.0, connect=5.0),
)
def _start_call(self, socket: Any, frame: dict[str, Any]) -> None:
call_id = str(frame.get("id") or "")
if not call_id:
return
task = asyncio.create_task(self._serve(socket, frame))
self._calls[call_id] = task
task.add_done_callback(lambda _t: self._calls.pop(call_id, None))
async def _serve(self, socket: Any, frame: dict[str, Any]) -> None:
call_id = str(frame["id"])
path = str(frame.get("path") or "")
try:
if not path.startswith(ALLOWED_PREFIX):
# Defence in depth: the hub only ever forwards API paths, and
# an installation that trusted anything else would be an SSRF
# gadget aimed at its own process.
await socket.send(
_dump({"op": "err", "id": call_id, "message": "path not allowed"})
)
return
body = frame.get("body")
content = base64.b64decode(body) if body else None
query = str(frame.get("query") or "")
headers = dict(frame.get("headers") or {})
# Set here rather than trusted from the frame: a browser can send
# any header it likes through the proxy, and this one decides where
# a pairing device's credential is minted. Arriving on this socket
# is the only thing that makes it true, and the value is this
# process's own so nothing off the network can imitate it.
headers[cloud_config.VIA_HEADER] = cloud_config.VIA_PORTAL
async with self._client() as client:
request = client.build_request(
str(frame.get("method") or "GET"),
f"{path}?{query}" if query else path,
headers=headers,
content=content,
)
response = await client.send(request, stream=True)
try:
await socket.send(
_dump(
{
"op": "res",
"id": call_id,
"status": response.status_code,
"headers": dict(response.headers),
}
)
)
async for chunk in response.aiter_bytes(CHUNK_BYTES):
await socket.send(
_dump(
{
"op": "res_body",
"id": call_id,
"body": base64.b64encode(chunk).decode("ascii"),
"done": False,
}
)
)
await socket.send(
_dump({"op": "res_body", "id": call_id, "done": True})
)
finally:
await response.aclose()
except asyncio.CancelledError:
raise
except Exception as exc:
logger.warning("Proxied %s failed: %s", path, exc)
with contextlib.suppress(Exception):
await socket.send(
_dump({"op": "err", "id": call_id, "message": str(exc)})
)
def _cancel(self, call_id: str) -> None:
task = self._calls.pop(call_id, None)
if task is not None:
task.cancel()
# -------------------------------------------------------------------------
# Bridged live stream
# -------------------------------------------------------------------------
def _start_stream(self, socket: Any, frame: dict[str, Any]) -> None:
stream_id = str(frame.get("id") or "")
if not stream_id:
return
task = asyncio.create_task(self._stream(socket, frame))
self._streams[stream_id] = task
task.add_done_callback(lambda _t: self._streams.pop(stream_id, None))
async def _stream(self, socket: Any, frame: dict[str, Any]) -> None:
"""Feed the engine's live events down the tunnel.
The flows websocket is subscribed to directly rather than dialled:
httpx cannot speak websocket, and everything that endpoint does — check
the token, send a snapshot, forward the bus — is a few lines against
objects this process already holds. The snapshot is built by the route
itself, so the two cannot drift apart behind the portal's back.
"""
from sqlmodel import Session
from app.api.deps import user_from_token
from app.api.routes.flows import (
event_for_panel,
panel_scope,
snapshot_payload,
)
from app.core.db import engine
from app.flow.events import event_bus
stream_id = str(frame["id"])
path = str(frame.get("path") or "")
query = str(frame.get("query") or "")
token = _query_value(query, "token")
if not path.startswith(ALLOWED_PREFIX) or not path.endswith("/flows/ws"):
await socket.send(_dump({"op": "ws_close", "id": stream_id, "code": 1008}))
return
with Session(engine) as session:
if user_from_token(session, token) is None:
await socket.send(
_dump({"op": "ws_close", "id": stream_id, "code": 1008})
)
return
only = panel_scope(token, self._app)
await socket.send(_dump({"op": "ws_open_ok", "id": stream_id}))
controller = getattr(self._app.state, "flow_controller", None)
if controller is not None:
await socket.send(
_dump(
{
"op": "ws_msg",
"id": stream_id,
"text": _dump(snapshot_payload(controller, only)),
}
)
)
try:
async with event_bus.subscribe() as queue:
while True:
event = await queue.get()
if only is not None and event.get("type") == "dashboard_changed":
# What this screen shows may have just changed under
# it. Rescope, then resend the snapshot so a dashboard
# it has only now been assigned draws values instead of
# blanks. ``or set()`` is the point: a panel that was
# deleted scopes to nothing, and None would widen this
# socket to everything on the bus.
only = panel_scope(token, self._app) or set()
if controller is not None:
catch_up = snapshot_payload(controller, only)
await socket.send(
_dump(
{
"op": "ws_msg",
"id": stream_id,
"text": _dump(catch_up),
}
)
)
elif only is not None and not event_for_panel(event, only):
continue
await socket.send(
_dump({"op": "ws_msg", "id": stream_id, "text": _dump(event)})
)
except asyncio.CancelledError:
raise
except Exception as exc:
logger.debug("Live stream %s ended: %s", stream_id, exc)
with contextlib.suppress(Exception):
await socket.send(
_dump({"op": "ws_close", "id": stream_id, "code": 1011})
)
def _cancel_stream(self, stream_id: str) -> None:
task = self._streams.pop(stream_id, None)
if task is not None:
task.cancel()
def _dump(payload: Any) -> str:
import json
return json.dumps(payload, default=str)
def _load(raw: Any) -> dict[str, Any]:
import json
data: dict[str, Any] = json.loads(raw)
return data
def _query_value(query: str, key: str) -> str:
from urllib.parse import parse_qs
values = parse_qs(query).get(key) or [""]
return values[0]
def _version() -> str:
return settings.VERSION if hasattr(settings, "VERSION") else "0.1.0"