mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
Second, deeper pass over tools/gateway/hermes_cli plus first pass over the trees wave 1 missed (acp, acp_adapter, skills, computer_use, docker, dashboard, conformance, monitoring, secret_sources, hermes_state, providers). Same rubric as wave 1 (AGENTS.md test policy); security, alternation/caching invariants, issue-number regressions, and E2E kept. Real test-quality fixes found and rooted out along the way: - tests/tools/test_command_guards.py made real auxiliary-LLM HTTPS calls (DEFAULT_CONFIG smart-approval leaked in) — pinned approval mode=manual via autouse fixture: 17.4s → 0.4s. - test_model_switch_custom_providers.py / test_user_providers_model_switch.py silently probed live provider catalogs (~2s/test) — stubbed cached_provider_model_ids/provider_model_ids/fetch_api_models. - test_telegram_noise_filter.py: 15-platform copy-paste matrix over shared gateway.run logic → 3 representative platforms (55s → 3.9s). - test_gateway_shutdown.py: stop()'s 5s interrupt-deadline loop spun on MagicMock agents — interrupt.side_effect now clears _running_agents (22s → 1.0s). - test_gateway_inactivity_timeout.py poll-harness timings shrunk 3-5x (24s → 1.1s); test_mcp_stability.py backoff/SIGTERM-grace sleeps patched (15.4s → 2.5s); test_async_delegation.py negative-drain wait 5s → 0.5s. - test_telegram_init_deadline.py: loop-block margin restored to 1.0s with rationale comment — the watchdog-dump assertion needs the loop blocked well past deadline+grace under parallel load (flaked once in the 40-worker verification run at a 0.2s margin). Verification: full hermetic suite via scripts/run_tests.sh — 2,438 files, 21,718 tests passed, 0 failed, 293.9s wall. Suite totals vs original baseline: 46,820 → 19,757 test functions (−57.8%), wall 583.5s → 293.9s (−50%), subprocess CPU 13,564s → 11,623s.
128 lines
4 KiB
Python
128 lines
4 KiB
Python
"""Focused tests for dashboard PTY reconnect breadcrumbs."""
|
|
|
|
import json
|
|
import sys
|
|
from pathlib import Path
|
|
from urllib.parse import urlencode
|
|
|
|
import pytest
|
|
|
|
|
|
pytestmark = pytest.mark.skipif(
|
|
sys.platform.startswith("win"), reason="PTY bridge is POSIX-only"
|
|
)
|
|
|
|
|
|
class _OneFrameBridge:
|
|
def __init__(self):
|
|
self._sent = False
|
|
self.closed = False
|
|
|
|
@classmethod
|
|
def spawn(cls, *args, **kwargs):
|
|
return cls()
|
|
|
|
def read(self, timeout):
|
|
if not self._sent:
|
|
self._sent = True
|
|
return b"ready"
|
|
return None
|
|
|
|
def resize(self, *, cols, rows):
|
|
pass
|
|
|
|
def write(self, raw):
|
|
pass
|
|
|
|
def close(self):
|
|
self.closed = True
|
|
|
|
|
|
@pytest.fixture
|
|
def pty_client(monkeypatch, _isolate_hermes_home):
|
|
from starlette.testclient import TestClient
|
|
|
|
import hermes_cli.web_server as ws
|
|
|
|
monkeypatch.setattr(ws, "_DASHBOARD_EMBEDDED_CHAT_ENABLED", True)
|
|
monkeypatch.setattr(ws.PtyBridge, "spawn", _OneFrameBridge.spawn)
|
|
ws.app.state.pty_active_session_files = {}
|
|
|
|
client = TestClient(ws.app)
|
|
return ws, client, ws._SESSION_TOKEN
|
|
|
|
|
|
def _url(token: str, **params: str) -> str:
|
|
return f"/api/pty?{urlencode({'token': token, **params})}"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_fresh_param_ignores_channel_active_session_file(pty_client, monkeypatch):
|
|
"""Explicit fresh starts must not resurrect the prior channel session."""
|
|
ws, client, token = pty_client
|
|
channel = "fresh-chan"
|
|
active_file = ws._active_session_file_for_channel(ws.app, channel)
|
|
active_file.write_text(json.dumps({"session_id": "sess-old"}), encoding="utf-8")
|
|
captured = {}
|
|
|
|
def fake_resolve(resume=None, sidecar_url=None, profile=None, active_session_file=None):
|
|
captured["active_session_file"] = active_session_file
|
|
captured["resume"] = resume
|
|
return (["fake-hermes-tui"], None, None)
|
|
|
|
monkeypatch.setattr(ws, "_resolve_chat_argv", fake_resolve)
|
|
|
|
with client.websocket_connect(_url(token, channel=channel, fresh="1")) as conn:
|
|
assert conn.receive_bytes() == b"ready"
|
|
|
|
assert captured["resume"] is None
|
|
assert captured["active_session_file"] == str(active_file)
|
|
assert not active_file.exists()
|
|
|
|
|
|
def test_child_eof_closes_socket_and_bridge(pty_client, monkeypatch):
|
|
"""Child EOF must close the WS server-side and reap the PTY.
|
|
|
|
Regression for the FD leak (#54028): the reader task hits EOF when the
|
|
PTY child exits, but if the browser's socket is half-open (no FIN), the
|
|
writer loop's ``ws.receive()`` would block forever and the PTY fds would
|
|
never be closed. The reader now closes the WebSocket on EOF so the
|
|
handler's ``finally`` runs ``bridge.close()``.
|
|
"""
|
|
ws, client, token = pty_client
|
|
bridges = []
|
|
|
|
class _RecordingBridge(_OneFrameBridge):
|
|
@classmethod
|
|
def spawn(cls, *args, **kwargs):
|
|
b = cls()
|
|
bridges.append(b)
|
|
return b
|
|
|
|
monkeypatch.setattr(ws.PtyBridge, "spawn", _RecordingBridge.spawn)
|
|
monkeypatch.setattr(
|
|
ws, "_resolve_chat_argv", lambda **kw: (["fake-hermes-tui"], None, None)
|
|
)
|
|
|
|
# The client never sends a disconnect of its own — it only reads the one
|
|
# frame then the server side must tear everything down on child EOF.
|
|
with client.websocket_connect(_url(token, channel="eof-chan")) as conn:
|
|
assert conn.receive_bytes() == b"ready"
|
|
# Server closes the socket after the child EOFs; receiving again
|
|
# surfaces the close rather than hanging.
|
|
with pytest.raises(Exception):
|
|
conn.receive_bytes()
|
|
|
|
assert len(bridges) == 1
|
|
# bridge.close() runs in the handler's `finally` via asyncio.to_thread,
|
|
# which can lag the client-side context exit by a tick or two. Poll briefly
|
|
# instead of asserting immediately so the teardown isn't a race.
|
|
import time
|
|
|
|
deadline = time.monotonic() + 5.0
|
|
while not bridges[0].closed and time.monotonic() < deadline:
|
|
time.sleep(0.01)
|
|
assert bridges[0].closed is True
|