stackpilot/backend/routers/ws.py

"""WebSocket endpoints for real-time log streaming and Docker events."""
from __future__ import annotations

import asyncio
import json
import logging
import urllib.parse

import contextlib

import websockets
from fastapi import APIRouter, Query, WebSocket, WebSocketDisconnect
from jose import JWTError
from sqlmodel import Session

from auth import decode_token
from database import engine
from models.agent import Agent
from models.setting import EVENT_STACK_ERROR, EVENT_STACK_START
from services import audit_service, compose_service, notify_service

logger = logging.getLogger("stackpilot.ws")

router = APIRouter(tags=["ws"])


async def _authorize(websocket: WebSocket, token: str | None) -> bool:
    """Validate the JWT supplied as a query param. Closes socket on failure."""
    if not token:
        await websocket.close(code=4401)
        return False
    try:
        decode_token(token, "access")
    except (JWTError, Exception):  # noqa: BLE001
        await websocket.close(code=4401)
        return False
    return True


async def _stream_logs(websocket: WebSocket, stack_id: str, service: str | None):
    """Stream `docker compose logs -f` output to the client."""
    args = ["logs", "--no-color", "--tail", "200", "--timestamps", "-f"]
    if service:
        args.append(service)
    try:
        async for line in compose_service.stream_compose(stack_id, args):
            await websocket.send_text(
                json.dumps(
                    {
                        "type": "log",
                        "stack_id": stack_id,
                        "service": service,
                        "line": line,
                    }
                )
            )
    except WebSocketDisconnect:
        raise
    except Exception as exc:  # noqa: BLE001
        await websocket.send_text(
            json.dumps({"type": "error", "detail": str(exc)})
        )


@router.websocket("/ws/logs/{stack_id}")
async def ws_stack_logs(
    websocket: WebSocket,
    stack_id: str,
    token: str | None = Query(default=None),
):
    await websocket.accept()
    if not await _authorize(websocket, token):
        return
    try:
        await _stream_logs(websocket, stack_id, None)
    except WebSocketDisconnect:
        pass


@router.websocket("/ws/logs/{stack_id}/{service}")
async def ws_service_logs(
    websocket: WebSocket,
    stack_id: str,
    service: str,
    token: str | None = Query(default=None),
):
    await websocket.accept()
    if not await _authorize(websocket, token):
        return
    try:
        await _stream_logs(websocket, stack_id, service)
    except WebSocketDisconnect:
        pass


@router.websocket("/ws/deploy/{stack_id}")
async def ws_deploy(
    websocket: WebSocket,
    stack_id: str,
    token: str | None = Query(default=None),
):
    """Run `docker compose up -d` and stream its output (image pulls, container
    creation) to the browser so the user sees deploy progress live. Records the
    same audit entry and notification as the REST `/start` endpoint."""
    await websocket.accept()
    if not await _authorize(websocket, token):
        return
    username = decode_token(token, "access").get("sub", "unknown") if token else "unknown"

    rc: int | None = None
    disconnected = False
    compose_service.mark_busy(stack_id)
    try:
        async for kind, payload in compose_service.stream_up(stack_id):
            if kind == "log":
                await websocket.send_text(json.dumps({"type": "log", "line": payload}))
            else:
                rc = payload
                await websocket.send_text(json.dumps({"type": "done", "returncode": rc}))
    except WebSocketDisconnect:
        # Client navigated away; the compose subprocess keeps running so the
        # deploy still completes in the background.
        disconnected = True
    except Exception as exc:  # noqa: BLE001
        with contextlib.suppress(Exception):
            await websocket.send_text(json.dumps({"type": "error", "detail": str(exc)}))
    finally:
        compose_service.clear_busy(stack_id)

    ok = rc in (0, None)
    try:
        with Session(engine) as session:
            audit_service.record(
                session, user=username, action="stack.start", target=stack_id,
                detail=f"rc={rc} (deploy console)", ip="ws",
            )
            if ok:
                await notify_service.notify(
                    EVENT_STACK_START, f"Stack '{stack_id}' started",
                    "compose up completed successfully.", session,
                )
            else:
                await notify_service.notify(
                    EVENT_STACK_ERROR, f"Stack '{stack_id}' start failed",
                    "compose up returned a non-zero exit code.", session,
                )
    except Exception:  # noqa: BLE001 - audit/notify are best-effort
        pass
    if not disconnected:
        with contextlib.suppress(Exception):
            await websocket.close()


@router.websocket("/ws/agent-logs/{agent_id}/{stack_id}")
async def ws_agent_logs(
    websocket: WebSocket,
    agent_id: int,
    stack_id: str,
    token: str | None = Query(default=None),
):
    """Proxy live compose logs from a remote agent through to the browser."""
    await websocket.accept()
    if not await _authorize(websocket, token):
        return

    with Session(engine) as session:
        agent = session.get(Agent, agent_id)
    if not agent:
        await websocket.send_text(json.dumps({"type": "error", "detail": "agent not found"}))
        await websocket.close()
        return

    base = agent.url.rstrip("/")
    ws_url = ("wss://" + base[8:] if base.startswith("https://")
              else "ws://" + base[7:] if base.startswith("http://")
              else "ws://" + base)
    # URL-encode the token: agent tokens may contain base64 chars (+ / =) that
    # would otherwise be mangled in the query string and rejected as 4401.
    ws_url += f"/agent/ws/logs/{stack_id}?token={urllib.parse.quote(agent.token, safe='')}"

    async def _err(detail: str) -> None:
        with contextlib.suppress(Exception):
            await websocket.send_text(json.dumps({"type": "error", "detail": detail}))

    # Connect to the agent. Surface connection problems (agent down, wrong URL,
    # an outdated agent that lacks /agent/ws/logs, TLS issues) instead of
    # silently dropping the socket.
    try:
        upstream = await websockets.connect(ws_url, open_timeout=10, ping_interval=20)
    except websockets.InvalidStatus as exc:
        code = getattr(getattr(exc, "response", None), "status_code", None)
        hint = " — the agent may be running an old version without live-log support; update it." if code == 404 else ""
        logger.warning("Agent log proxy: handshake to %s failed (%s)", agent.name, code)
        await _err(f"Agent '{agent.name}' rejected the log stream (HTTP {code}){hint}")
        with contextlib.suppress(Exception):
            await websocket.close()
        return
    except Exception as exc:  # noqa: BLE001
        logger.warning("Agent log proxy: cannot reach %s at %s: %s", agent.name, agent.url, exc)
        await _err(f"Could not connect to agent '{agent.name}' at {agent.url}: {exc}")
        with contextlib.suppress(Exception):
            await websocket.close()
        return

    try:
        async for message in upstream:
            await websocket.send_text(
                message if isinstance(message, str) else message.decode("utf-8", "replace")
            )
    except WebSocketDisconnect:
        pass
    except websockets.ConnectionClosed as exc:
        # Abnormal upstream close (e.g. 4401 bad token, or agent-side error).
        if exc.code not in (1000, 1001):
            await _err(f"Agent log stream closed unexpectedly (code {exc.code}).")
    except Exception as exc:  # noqa: BLE001
        logger.warning("Agent log proxy: stream error from %s: %s", agent.name, exc)
        await _err(str(exc))
    finally:
        with contextlib.suppress(Exception):
            await upstream.close()
        with contextlib.suppress(Exception):
            await websocket.close()


@router.websocket("/ws/agent-deploy/{agent_id}/{stack_id}")
async def ws_agent_deploy(
    websocket: WebSocket,
    agent_id: int,
    stack_id: str,
    token: str | None = Query(default=None),
):
    """Proxy a remote agent's `compose up` deploy stream through to the browser,
    then record the same audit entry as the REST agent lifecycle endpoint."""
    await websocket.accept()
    if not await _authorize(websocket, token):
        return
    username = decode_token(token, "access").get("sub", "unknown") if token else "unknown"

    with Session(engine) as session:
        agent = session.get(Agent, agent_id)
    if not agent:
        await websocket.send_text(json.dumps({"type": "error", "detail": "agent not found"}))
        await websocket.close()
        return

    base = agent.url.rstrip("/")
    ws_url = ("wss://" + base[8:] if base.startswith("https://")
              else "ws://" + base[7:] if base.startswith("http://")
              else "ws://" + base)
    ws_url += f"/agent/ws/deploy/{stack_id}?token={urllib.parse.quote(agent.token, safe='')}"

    async def _err(detail: str) -> None:
        with contextlib.suppress(Exception):
            await websocket.send_text(json.dumps({"type": "error", "detail": detail}))

    try:
        upstream = await websockets.connect(ws_url, open_timeout=10, ping_interval=20)
    except websockets.InvalidStatus as exc:
        code = getattr(getattr(exc, "response", None), "status_code", None)
        hint = " — the agent may be running an old version without deploy-console support; update it." if code == 404 else ""
        logger.warning("Agent deploy proxy: handshake to %s failed (%s)", agent.name, code)
        await _err(f"Agent '{agent.name}' rejected the deploy stream (HTTP {code}){hint}")
        with contextlib.suppress(Exception):
            await websocket.close()
        return
    except Exception as exc:  # noqa: BLE001
        logger.warning("Agent deploy proxy: cannot reach %s at %s: %s", agent.name, agent.url, exc)
        await _err(f"Could not connect to agent '{agent.name}' at {agent.url}: {exc}")
        with contextlib.suppress(Exception):
            await websocket.close()
        return

    rc: int | None = None
    try:
        async for message in upstream:
            text = message if isinstance(message, str) else message.decode("utf-8", "replace")
            with contextlib.suppress(Exception):
                msg = json.loads(text)
                if msg.get("type") == "done":
                    rc = msg.get("returncode")
            await websocket.send_text(text)
    except WebSocketDisconnect:
        pass
    except websockets.ConnectionClosed as exc:
        if exc.code not in (1000, 1001):
            await _err(f"Agent deploy stream closed unexpectedly (code {exc.code}).")
    except Exception as exc:  # noqa: BLE001
        logger.warning("Agent deploy proxy: stream error from %s: %s", agent.name, exc)
        await _err(str(exc))
    finally:
        with contextlib.suppress(Exception):
            await upstream.close()
        with contextlib.suppress(Exception):
            await websocket.close()

    with contextlib.suppress(Exception):
        with Session(engine) as session:
            audit_service.record(
                session, user=username, action="agent.stack.start",
                target=f"{agent.name}/{stack_id}", detail=f"rc={rc} (deploy console)", ip="ws",
            )


@router.websocket("/ws/events")
async def ws_events(
    websocket: WebSocket,
    token: str | None = Query(default=None),
):
    """Stream global Docker events (decoded subset)."""
    await websocket.accept()
    if not await _authorize(websocket, token):
        return
    from docker_client import get_client

    loop = asyncio.get_event_loop()
    queue: asyncio.Queue = asyncio.Queue()
    stop = asyncio.Event()

    def reader():
        try:
            client = get_client()
            for event in client.events(decode=True):
                if stop.is_set():
                    break
                loop.call_soon_threadsafe(queue.put_nowait, event)
        except Exception:  # noqa: BLE001
            pass

    task = loop.run_in_executor(None, reader)
    try:
        while True:
            event = await queue.get()
            actor = event.get("Actor", {}) or {}
            attrs = actor.get("Attributes", {}) or {}
            await websocket.send_text(
                json.dumps(
                    {
                        "type": "event",
                        "action": event.get("Action"),
                        "container": attrs.get("name"),
                        "stack": attrs.get("com.docker.compose.project"),
                    }
                )
            )
    except WebSocketDisconnect:
        pass
    finally:
        stop.set()
        task.cancel()