app/backend/fluksio/api/routes/panels.py

"""Panels: which dashboards a device shows, and how it gets a credential.

A wall tablet has no keyboard, so it cannot log in. It asks for a code instead,
shows it on the wall, and somebody with an account types that code into the
panels dialog to say which panel the device is. The device polls, collects the
credential the approval minted, and never asks again.

A screen hanging somewhere this instance is not reachable from does the
same thing through the portal, which forwards those two calls down the tunnel
without a session — a device with no credential is the whole point of them —
and mints the credential itself when the approval comes. Which side minted it
changes nothing about what it may do: the scope check is here either way.

The credential is scoped: ``fluksio.api.deps`` lets it reach the dashboards that
panel was assigned, the messages their widgets bind to, and nothing else.
Removing the panel revokes it; so does bumping the panel's nonce, which is how
one screen is re-paired without disturbing what it was showing.
"""

from __future__ import annotations

import secrets
import time
from datetime import timedelta
from typing import Any, cast

import httpx
import redis
from fastapi import APIRouter, Depends, HTTPException, Request
from fastapi.concurrency import run_in_threadpool
from pydantic import BaseModel, Field

from fluksio.api.deps import CurrentUser, get_current_active_superuser, get_current_user
from fluksio.cloud import config as cloud_config
from fluksio.core import security
from fluksio.core.config import settings
from fluksio.flow.events import event_bus
from fluksio.flow.panels import (
    PanelDef,
    PanelsConfig,
    edit_lock,
    find,
    read_config,
    write_config,
)
from fluksio.flow.state import CONNECT_TIMEOUT_S, SOCKET_TIMEOUT_S
from fluksio.models import Message

#: Gated per route rather than on the router: the two pairing endpoints are the
#: only unauthenticated ones in the app, because a device with no credential is
#: the whole point of them.
router = APIRouter(prefix="/panels", tags=["panels"])

#: Long, because a panel is a screen somebody hung once and left running, with
#: no keyboard to sign in again with. Same reasoning as a remote worker's.
TOKEN_DAYS = 365

#: How long a device's code is worth typing. Long enough to walk to a computer.
PAIR_TTL = 600

#: No I/O/0/1: the code is read off a wall and typed on a keyboard.
CODE_ALPHABET = "ABCDEFGHJKLMNPQRSTUVWXYZ23456789"
CODE_LENGTH = 6

#: Refuse to grow past this. Codes are free to ask for and cost memory.
MAX_PENDING = 50


class _Pending(BaseModel):
    """A device waiting to be told what it is."""

    #: Held by the device, never shown.
    secret: str
    #: Wall-clock rather than monotonic: an entry outlives the process that
    #: minted it, and monotonic clocks are not comparable across processes.
    expires: float
    token: str = ""
    panel: str = ""
    #: What the request looked like, shown to whoever approves the code so
    #: they can tell the screen in the hall from one they were not expecting.
    #: Self-reported and worth what that is worth.
    device: str = ""
    #: Whether it came down the tunnel. A device that reached the portal
    #: cannot reach this instance, so its credential has to be minted
    #: where it can collect it.
    remote: bool = False


#: The entry itself, one key per code, expiring on its own.
_PENDING_KEY = "panels:pair"
#: An index of the live codes, so :data:`MAX_PENDING` means the same thing to
#: every worker. Scored by expiry, which is how it is pruned.
_PENDING_INDEX = "panels:pair:__codes__"


class _PendingStore:
    """The codes waiting for somebody to say what they are.

    A device's poll lands on whichever API worker the proxy picked, and a
    screen pairing through the portal lands on whichever one holds the tunnel
    — so a code minted by one worker has to be findable from the next. Redis
    is where this instance already keeps what must outlive a process.

    Without one there is one process by definition (the pip install, and the
    tests), and a dictionary is the same thing for it.
    """

    def __init__(self) -> None:
        self._local: dict[str, _Pending] = {}
        self._redis: redis.Redis | None = (
            redis.Redis(
                host=settings.REDIS_HOST,
                port=settings.REDIS_PORT,
                decode_responses=True,
                # A silent Redis must fail this request, not hold it open.
                socket_timeout=SOCKET_TIMEOUT_S,
                socket_connect_timeout=CONNECT_TIMEOUT_S,
                health_check_interval=30,
            )
            if settings.REDIS_HOST
            else None
        )

    def _key(self, code: str) -> str:
        return f"{_PENDING_KEY}:{code}"

    def count(self) -> int:
        """How many are waiting, the expired ones dropped first."""
        now = time.time()
        if self._redis is None:
            for code in [c for c, e in self._local.items() if e.expires < now]:
                del self._local[code]
            return len(self._local)
        self._redis.zremrangebyscore(_PENDING_INDEX, "-inf", now)
        return int(cast(int, self._redis.zcard(_PENDING_INDEX)))

    def add(self, code: str, entry: _Pending) -> bool:
        """Claim this code, or say that somebody already holds it."""
        if self._redis is None:
            if code in self._local:
                return False
            self._local[code] = entry
            return True
        if not self._redis.set(
            self._key(code), entry.model_dump_json(), ex=PAIR_TTL, nx=True
        ):
            return False
        self._redis.zadd(_PENDING_INDEX, {code: entry.expires})
        return True

    def get(self, code: str) -> _Pending | None:
        if self._redis is None:
            entry = self._local.get(code)
        else:
            raw = cast("str | None", self._redis.get(self._key(code)))
            entry = _Pending.model_validate_json(raw) if raw else None
        return entry if entry is not None and entry.expires >= time.time() else None

    def save(self, code: str, entry: _Pending) -> None:
        """Write an approval back, without moving what it expires at."""
        if self._redis is None:
            self._local[code] = entry
            return
        self._redis.set(
            self._key(code),
            entry.model_dump_json(),
            ex=max(1, int(entry.expires - time.time())),
        )

    def drop(self, code: str) -> None:
        if self._redis is None:
            self._local.pop(code, None)
            return
        self._redis.delete(self._key(code))
        self._redis.zrem(_PENDING_INDEX, code)


_pending = _PendingStore()


class PairStarted(BaseModel):
    """What the device puts on the wall, and what it polls with."""

    code: str
    #: Held by the device, never shown. Without it the code alone would let
    #: anyone who reads it off the wall collect the credential first.
    secret: str
    expires_in: int = PAIR_TTL


class PairStatus(BaseModel):
    """Nothing yet, or the credential and the panel it is for."""

    access_token: str | None = None
    panel: str | None = None


class PairRequest(BaseModel):
    code: str


class PendingDevice(BaseModel):
    """Who is asking, as far as the request itself says."""

    device: str
    remote: bool = False


def _describe(request: Request) -> str:
    """A line naming the device behind a pairing request.

    # ponytail: the raw user agent, trimmed. Parse it into "iPad · Safari" if
    # it reads badly on the approval screen.
    """
    agent = request.headers.get("user-agent", "").strip()[:120]
    forwarded = request.headers.get("x-forwarded-for", "").split(",")[0].strip()
    # Proxied requests are replayed into this process over an ASGI transport,
    # which reports every caller as localhost; the forwarded address is the
    # only true one there, and behind the local reverse proxy it is too.
    address = forwarded or (request.client.host if request.client else "")
    return " · ".join(part for part in (agent or "Unknown device", address) if part)


def _mint_at_hub(panel_id: str) -> str:
    """Ask the portal for this panel's credential.

    A device that arrived through the portal cannot reach this instance, so
    a token this instance signed would be one it could never present: the
    portal verifies what crosses its tunnel, and it verifies against its own
    key. It mints, we say which panel — and the scope check here decides the
    rest, on this call and on every later one.
    """
    config = cloud_config.load()
    if config is None:
        raise HTTPException(
            status_code=409,
            detail="That device came through a portal this instance is no "
            "longer enrolled with",
        )
    try:
        response = httpx.post(
            f"{config.portal_url.rstrip('/')}/api/v1/panel-tokens/",
            headers={"Authorization": f"Bearer {config.token}"},
            json={"panel": panel_id},
            timeout=15.0,
        )
    except httpx.HTTPError as exc:
        raise HTTPException(
            status_code=502, detail=f"Could not reach the portal: {exc}"
        ) from exc
    if response.status_code != 200:
        raise HTTPException(
            status_code=502,
            detail=f"The portal refused to mint a credential ({response.status_code})",
        )
    token: str = response.json()["access_token"]
    return token


class PanelsPublic(BaseModel):
    """The panels, and the address a device should be pointed at.

    The address is the server's own, because the browser's origin is not a
    reliable answer to it: an admin working through the portal is on the
    portal's origin, and this one is for a screen on this network.

    An instance enrolled with a portal has a second address, built by the
    dialog from what ``/cloud/status`` reports rather than from here — a panel
    is not the thing that knows whether remote access is on.
    """

    panels: list[PanelDef] = Field(default_factory=list)
    #: Whatever this instance was told it is reachable at. The same setting
    #: the password-reset links are built from, so an instance that has it
    #: wrong has it wrong in both places.
    frontend_host: str = ""


def _public(config: PanelsConfig) -> PanelsPublic:
    return PanelsPublic(
        panels=config.panels, frontend_host=settings.FRONTEND_HOST.rstrip("/")
    )


@router.get("/", response_model=PanelsPublic, dependencies=[Depends(get_current_user)])
async def read_panels() -> Any:
    """Every panel, what each one shows, and where to point a device."""
    return _public(await run_in_threadpool(read_config))


@router.put(
    "/",
    response_model=PanelsPublic,
    dependencies=[Depends(get_current_active_superuser)],
)
async def save_panels(body: PanelsConfig) -> Any:
    """Replace the panels. Takes effect on the devices' next read.

    A panel that disappears here takes its credential with it, so this is also
    how a device is unpaired along with its assignment. Re-pairing one screen
    and keeping the assignment is ``/{panel_id}/unpair`` below.
    """
    seen = set()
    for panel in body.panels:
        if panel.id in seen:
            raise HTTPException(
                status_code=422, detail=f"Two panels named {panel.id!r}"
            )
        seen.add(panel.id)

    def _save() -> None:
        # Read and write under one lock. The nonce belongs to this
        # instance, not to whoever is writing the panels back: a client
        # holding an older copy must not be able to undo a revocation by
        # saving an arrangement — and reading it in a separate step from
        # writing it is exactly how an unpair in between was undone.
        with edit_lock:
            stored = {p.id: p.nonce for p in read_config().panels}
            for panel in body.panels:
                panel.nonce = stored.get(panel.id, 0)
            write_config(body)

    await run_in_threadpool(_save)
    # Which dashboards hang on which panel just changed. An empty name says
    # that much and no more: every screen listening rescopes and refetches
    # what it shows, rather than waiting for whenever it next reads.
    event_bus.publish({"type": "dashboard_changed", "dashboard": "", "ts": time.time()})
    return _public(body)


@router.post("/pair", response_model=PairStarted)
def start_pairing(request: Request) -> Any:
    """A device asks to be adopted. Unauthenticated, by necessity.

    All this hands out is a code that means nothing until somebody with an
    account approves it, so the worst an unwelcome caller achieves is an entry
    that expires ten minutes later. Reachable from the internet when this
    instance is enrolled with a portal, which is what the cap and the
    portal's own per-address limits are between.
    """
    if _pending.count() >= MAX_PENDING:
        raise HTTPException(
            status_code=429, detail="Too many devices are waiting to be paired"
        )

    remote = secrets.compare_digest(
        request.headers.get(cloud_config.VIA_HEADER, ""), cloud_config.VIA_PORTAL
    )
    entry = _Pending(
        secret=secrets.token_urlsafe(16),
        expires=time.time() + PAIR_TTL,
        device=_describe(request),
        remote=remote,
    )
    # Claiming the code is what settles a collision, rather than looking first:
    # between the look and the write sits another worker doing the same thing.
    for _ in range(10):
        code = "".join(secrets.choice(CODE_ALPHABET) for _ in range(CODE_LENGTH))
        if _pending.add(code, entry):
            break
    else:
        raise HTTPException(status_code=503, detail="Could not mint a pairing code")
    return PairStarted(code=code, secret=entry.secret)


@router.get("/pair/{code}", response_model=PairStatus)
def poll_pairing(code: str, secret: str = "") -> Any:
    """Has anyone claimed this device yet?

    Answers the same 404 for a code that never existed, one that expired and
    one polled with the wrong secret: a caller reading a code off a wall learns
    nothing by guessing.
    """
    entry = _pending.get(code)
    if entry is None or not secrets.compare_digest(entry.secret, secret):
        raise HTTPException(
            status_code=404, detail="No pairing is waiting on that code"
        )
    if not entry.token:
        return PairStatus()

    # Handed over once. A credential left lying in the store is a second copy
    # of it, and the device has the only one it needs.
    _pending.drop(code)
    return PairStatus(access_token=entry.token, panel=entry.panel)


@router.get(
    "/pair/{code}/device",
    response_model=PendingDevice,
    dependencies=[Depends(get_current_active_superuser)],
)
def pending_device(code: str) -> Any:
    """What is waiting on this code, before anyone says what it is.

    Approving a code adopts whatever is holding it, so it is worth seeing that
    it looks like the screen you just hung.
    """
    entry = _pending.get(code.strip().upper())
    if entry is None:
        raise HTTPException(status_code=404, detail="No device is waiting on that code")
    return PendingDevice(device=entry.device, remote=entry.remote)


@router.post(
    "/{panel_id}/pair",
    response_model=Message,
    dependencies=[Depends(get_current_active_superuser)],
)
def approve_pairing(panel_id: str, body: PairRequest, current_user: CurrentUser) -> Any:
    """Say which panel the device showing this code is.

    A credential minted here names the approver, so what the panel does stays
    attributable to a person rather than to nobody. One minted by the portal —
    for a device that reached this instance only through it — names the
    account this instance was enrolled with instead, since that is the one
    every portal-borne request already acts as.
    """
    panel = find(panel_id)
    if panel is None:
        raise HTTPException(status_code=404, detail=f"No panel named {panel_id!r}")

    code = body.code.strip().upper()
    entry = _pending.get(code)
    if entry is None:
        raise HTTPException(
            status_code=404,
            detail="No device is waiting on that code — check it again",
        )

    if entry.remote:
        entry.token = _mint_at_hub(panel_id)
    else:
        entry.token = security.create_panel_token(
            panel_id, current_user.id, timedelta(days=TOKEN_DAYS), panel.nonce
        )
    entry.panel = panel_id
    _pending.save(code, entry)
    return Message(message=f"Paired {entry.device} with {panel_id}")


@router.post(
    "/{panel_id}/unpair",
    response_model=Message,
    dependencies=[Depends(get_current_active_superuser)],
)
async def unpair_panel(panel_id: str) -> Any:
    """Stop honouring this panel's credential, and keep the panel.

    Bumping the nonce refuses the screen hanging there on its next request, so
    it goes back to showing a pairing code — while the panel, the dashboards it
    was assigned and their arrangement stay exactly as they were. Deleting the
    panel is still what throws all three away together.

    A credential the portal minted for a remote screen carries no nonce, so
    this does not reach it; that one is revoked at the hub.
    """

    def _unpair() -> bool:
        with edit_lock:
            config = read_config()
            panel = next((p for p in config.panels if p.id == panel_id), None)
            if panel is None:
                return False
            panel.nonce += 1
            write_config(config)
            return True

    if not await run_in_threadpool(_unpair):
        raise HTTPException(status_code=404, detail=f"No panel named {panel_id!r}")
    # The screen is still holding a socket. One event and it refetches, which
    # is where it meets the 401 that sends it back to the pairing code.
    event_bus.publish({"type": "dashboard_changed", "dashboard": "", "ts": time.time()})
    return Message(message=f"Unpaired {panel_id}")


@router.get(
    "/{panel_id}", response_model=PanelDef, dependencies=[Depends(get_current_user)]
)
async def read_panel(panel_id: str) -> Any:
    """One panel — read by a person, or by the device holding its credential.

    Declared after the pairing routes so a device polling ``/panels/pair/...``
    is never mistaken for someone reading a panel named ``pair``.
    """
    panel = await run_in_threadpool(find, panel_id)
    if panel is None:
        raise HTTPException(status_code=404, detail=f"No panel named {panel_id!r}")
    return panel