Files
roboco/tests/unit/api/test_websocket_idle_timeout.py
T
Renn F 4da0245dac [F064][F065][F066] websocket: non-blocking fan-out, finally-disconnect, idle timeout
F064: the bridge forwarder awaited every conn.send_text in a gather with no
per-connection queue and no send timeout — one slow WS client back-pressured
ALL event delivery to ALL clients (head-of-line blocking on the listen loop).
Each connect_* now registers a _ClientConnection (bounded asyncio.Queue(256) +
sender task); broadcasts enqueue via put_nowait (drop + structlog warn on
QueueFull) and return immediately. The sender drains the queue with each send
wrapped in wait_for(SEND_TIMEOUT=10s). Unregistered legacy sockets (set
directly into a subscription set, bypassing connect_*) get a timeout-bounded
fallback send task held in _pending_sends (ruff RUF006). disconnect cancels +
drops the sender.

F065: route handlers caught only WebSocketDisconnect with no finally — a
non-clean exit (anyio closed-resource, CancelledError, transport error)
propagated without manager.disconnect, leaking the dead socket into every
subscription set forever. Added finally: manager.disconnect(websocket) to all
5 handlers (disconnect is idempotent).

F066: no server-side heartbeat/idle timeout — a half-open socket from a dead
container blocked receive_text forever and was never reaped. receive_text now
wraps in wait_for(IDLE_TIMEOUT_SECONDS=90s); on TimeoutError, log + fall
through to the F065 finally. Named module constants (no config.py precedent for
WS tuning; callers/tests patch them).

TDD: 22 new tests across 3 files (handler cleanup, idle timeout, send queue),
non-flaky across repeats; 1 existing test adapted with a yield for the new
async fan-out (assertion unchanged). ruff/mypy clean, 421 unit/api tests pass.
No type:ignore/noqa.
2026-06-28 17:25:28 +02:00

205 lines
7.4 KiB
Python

"""F066: server-side idle timeout reaps half-open WS sockets.
The keepalive was client-driven (respond to ``"ping"`` with ``"pong"``); the
server never sent its own ping and never timed out a silent client. If an
agent container died leaving the TCP socket half-open, ``receive_text()``
blocked forever and ``disconnect`` was never called.
The fix wraps ``receive_text()`` in
``asyncio.wait_for(..., timeout=IDLE_TIMEOUT_SECONDS)`` per handler; on
``asyncio.TimeoutError`` the finally (from F065) disconnects the idle
socket. ``IDLE_TIMEOUT_SECONDS`` is a named module constant (ruff PLR2004).
Deterministic: the slow-socket test patches ``IDLE_TIMEOUT_SECONDS`` to a
tiny value (0.05s) and uses a ``receive_text`` that returns a never-resolved
``Future`` — so the test asserts a prompt disconnect in well under a second,
never relying on real wall-clock timing of the default timeout.
"""
from __future__ import annotations
import asyncio
from unittest.mock import AsyncMock, MagicMock
from uuid import uuid4
import pytest
from fastapi import WebSocketDisconnect
from roboco.api.websocket import (
IDLE_TIMEOUT_SECONDS,
ConnectionManager,
agent_stream,
channel_stream,
notification_stream,
session_stream,
system_stream,
)
def _mock_ws_for_receive(receive_side_effect: object) -> MagicMock:
ws = MagicMock()
ws.accept = AsyncMock()
ws.close = AsyncMock()
ws.send_json = AsyncMock()
ws.send_text = AsyncMock()
if isinstance(receive_side_effect, asyncio.Future):
# A never-resolving Future means "hang forever" (half-open socket).
# AsyncMock treats a non-callable side_effect as an iterable, which a
# Future isn't — so install a real async receive_text that awaits it.
hang_future = receive_side_effect
async def _hang_forever() -> str:
await hang_future # never resolves; wait_for cancels it on timeout.
return ""
ws.receive_text = _hang_forever
else:
ws.receive_text = AsyncMock(side_effect=receive_side_effect)
ws.headers = {}
ws.query_params = {}
return ws
# ---------------------------------------------------------------------------
# Constant shape
# ---------------------------------------------------------------------------
def test_idle_timeout_seconds_is_a_named_module_constant() -> None:
"""IDLE_TIMEOUT_SECONDS must be a module-level constant (ruff PLR2004)."""
assert isinstance(IDLE_TIMEOUT_SECONDS, int | float)
assert IDLE_TIMEOUT_SECONDS > 0
# ---------------------------------------------------------------------------
# Half-open socket is reaped after the idle timeout (deterministic)
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_system_stream_reaps_silent_socket_after_idle_timeout() -> None:
"""A silent half-open socket (receive_text never returns) is reaped after
the idle timeout — the wait_for raises TimeoutError and the finally
disconnects. Deterministic: tiny patched timeout + never-resolving Future."""
mgr = ConnectionManager()
hang_future: asyncio.Future[str] = asyncio.Future()
ws = _mock_ws_for_receive(hang_future)
await mgr.connect_system(ws)
with pytest.MonkeyPatch.context() as mp:
mp.setattr("roboco.api.websocket.manager", mgr)
mp.setattr("roboco.api.websocket.IDLE_TIMEOUT_SECONDS", 0.05)
# Must return promptly (well under 2s), not block for the real default.
await asyncio.wait_for(system_stream(ws), timeout=2.0)
assert ws not in mgr.system_connections
@pytest.mark.asyncio
async def test_notification_stream_reaps_silent_socket_after_idle_timeout(
monkeypatch: pytest.MonkeyPatch,
) -> None:
agent_id = uuid4()
mgr = ConnectionManager()
hang_future: asyncio.Future[str] = asyncio.Future()
ws = _mock_ws_for_receive(hang_future)
monkeypatch.setattr(
"roboco.api.websocket.validate_agent_exists", AsyncMock(return_value=True)
)
monkeypatch.setattr("roboco.api.websocket.manager", mgr)
monkeypatch.setattr("roboco.api.websocket.IDLE_TIMEOUT_SECONDS", 0.05)
await asyncio.wait_for(notification_stream(ws, agent_id), timeout=2.0)
assert ws not in mgr.notification_connections.get(agent_id, set())
@pytest.mark.asyncio
async def test_channel_stream_reaps_silent_socket_after_idle_timeout(
monkeypatch: pytest.MonkeyPatch,
) -> None:
channel_id = uuid4()
agent_id = uuid4()
mgr = ConnectionManager()
hang_future: asyncio.Future[str] = asyncio.Future()
ws = _mock_ws_for_receive(hang_future)
ws.query_params = {"agent_id": str(agent_id)}
monkeypatch.setattr(
"roboco.api.websocket.validate_channel_access", AsyncMock(return_value=True)
)
monkeypatch.setattr("roboco.api.websocket.manager", mgr)
monkeypatch.setattr("roboco.api.websocket.IDLE_TIMEOUT_SECONDS", 0.05)
await asyncio.wait_for(channel_stream(ws, channel_id), timeout=2.0)
assert ws not in mgr.channel_connections.get(channel_id, set())
@pytest.mark.asyncio
async def test_agent_stream_reaps_silent_socket_after_idle_timeout(
monkeypatch: pytest.MonkeyPatch,
) -> None:
target_id = uuid4()
viewer_id = uuid4()
mgr = ConnectionManager()
hang_future: asyncio.Future[str] = asyncio.Future()
ws = _mock_ws_for_receive(hang_future)
ws.query_params = {"viewer_id": str(viewer_id)}
monkeypatch.setattr(
"roboco.api.websocket.validate_agent_exists", AsyncMock(return_value=True)
)
monkeypatch.setattr("roboco.api.websocket.manager", mgr)
monkeypatch.setattr("roboco.api.websocket.IDLE_TIMEOUT_SECONDS", 0.05)
await asyncio.wait_for(agent_stream(ws, target_id), timeout=2.0)
assert ws not in mgr.agent_connections.get(target_id, set())
@pytest.mark.asyncio
async def test_session_stream_reaps_silent_socket_after_idle_timeout(
monkeypatch: pytest.MonkeyPatch,
) -> None:
session_id = uuid4()
agent_id = uuid4()
mgr = ConnectionManager()
hang_future: asyncio.Future[str] = asyncio.Future()
ws = _mock_ws_for_receive(hang_future)
ws.query_params = {"agent_id": str(agent_id)}
monkeypatch.setattr(
"roboco.api.websocket.validate_agent_exists", AsyncMock(return_value=True)
)
monkeypatch.setattr("roboco.api.websocket.manager", mgr)
monkeypatch.setattr("roboco.api.websocket.IDLE_TIMEOUT_SECONDS", 0.05)
await asyncio.wait_for(session_stream(ws, session_id), timeout=2.0)
assert ws not in mgr.session_connections.get(session_id, set())
# ---------------------------------------------------------------------------
# Regression: ping/pong within the idle window keeps the socket alive
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_ping_within_idle_window_does_not_disconnect() -> None:
"""A client that sends ping before the idle timeout elapses is NOT
disconnected — the wait_for resets on each successful receive_text."""
mgr = ConnectionManager()
ws = _mock_ws_for_receive(["ping", WebSocketDisconnect()])
await mgr.connect_system(ws)
with pytest.MonkeyPatch.context() as mp:
mp.setattr("roboco.api.websocket.manager", mgr)
mp.setattr("roboco.api.websocket.IDLE_TIMEOUT_SECONDS", 30)
await system_stream(ws)
# Disconnected only because of the WebSocketDisconnect, not the timeout.
assert ws not in mgr.system_connections
ws.send_text.assert_awaited_with("pong")