hermes-agent/tests/computer_use/test_cua_cli_fallback_env.py
Teknium 39975613b1
test: prune wave 2 + speed fixes — 28,106 → 19,757 test functions, suite wall 315s → 294s
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.
2026-07-29 13:39:40 -07:00

58 lines
2 KiB
Python

"""Regression test: the cua-driver CLI-fallback transport must sanitize the
subprocess environment like every other cua-driver spawn site.
``_CuaDriverSession._call_tool_via_cli()`` (the EAGAIN/silent-empty MCP
fallback) invoked ``subprocess.run`` with no ``env=`` at all, so the
third-party ``cua-driver`` binary inherited the full, unsanitized parent
environment — including provider API keys and other Hermes-managed
secrets that ``_lifecycle_coro``'s primary MCP spawn already strips via
``_sanitize_subprocess_env(cua_driver_child_env())``.
"""
import json
from unittest.mock import MagicMock
from tools.computer_use.cua_backend import _CuaDriverSession
def _make_session() -> _CuaDriverSession:
# _call_tool_via_cli() doesn't touch any instance state (bridge/session/
# capabilities); bypass __init__ so the test doesn't need a real
# _AsyncBridge.
return object.__new__(_CuaDriverSession)
def _fake_completed_process(stdout: str) -> MagicMock:
proc = MagicMock()
proc.stdout = stdout
proc.stderr = ""
proc.returncode = 0
return proc
def test_cli_fallback_strips_provider_secret_from_subprocess_env(monkeypatch):
monkeypatch.setenv("ANTHROPIC_API_KEY", "«redacted:sk-…»")
monkeypatch.setenv("PATH", "/usr/bin:/bin")
monkeypatch.setattr(
"tools.computer_use.cua_backend.resolve_cua_driver_cmd",
lambda: "/resolved/cua-driver",
)
captured = {}
def fake_run(cmd, **kwargs):
captured["env"] = kwargs.get("env")
return _fake_completed_process(json.dumps({"tree_markdown": "root"}))
monkeypatch.setattr("subprocess.run", fake_run)
session = _make_session()
result = session._call_tool_via_cli("list_windows", {}, timeout=5.0)
assert result["isError"] is False
assert captured["env"] is not None, "subprocess.run must receive an explicit env="
assert "ANTHROPIC_API_KEY" not in captured["env"]
# Sanitization filters secrets, not everything — an ordinary var survives.
assert captured["env"].get("PATH") == "/usr/bin:/bin"