mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
39975613b1
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.
52 lines
1.8 KiB
Python
52 lines
1.8 KiB
Python
"""Tests for the cua-driver telemetry opt-in policy.
|
|
|
|
cua-driver ships anonymous PostHog telemetry ENABLED by default upstream.
|
|
Hermes disables it unless the user opts in via
|
|
``computer_use.cua_telemetry: true``. The policy is applied by injecting
|
|
``CUA_DRIVER_RS_TELEMETRY_ENABLED=0`` into every cua-driver child env.
|
|
|
|
These assert the behavior contract (default disables, opt-in leaves the var
|
|
untouched, config failure fails safe toward disabled), not specific config
|
|
snapshots.
|
|
"""
|
|
|
|
from unittest.mock import patch
|
|
|
|
from tools.computer_use import cua_backend
|
|
|
|
|
|
_VAR = "CUA_DRIVER_RS_TELEMETRY_ENABLED"
|
|
|
|
|
|
class TestTelemetryDisabledFlag:
|
|
|
|
def test_explicit_false_disables(self):
|
|
with patch("hermes_cli.config.load_config",
|
|
return_value={"computer_use": {"cua_telemetry": False}}):
|
|
assert cua_backend._cua_telemetry_disabled() is True
|
|
|
|
|
|
def test_config_load_failure_fails_safe(self):
|
|
# Unreadable config => default to disabling telemetry (privacy-safe).
|
|
with patch("hermes_cli.config.load_config", side_effect=RuntimeError("boom")):
|
|
assert cua_backend._cua_telemetry_disabled() is True
|
|
|
|
|
|
|
|
class TestChildEnv:
|
|
def test_disabled_injects_var_zero(self):
|
|
with patch.object(cua_backend, "_cua_telemetry_disabled", return_value=True):
|
|
env = cua_backend.cua_driver_child_env({"PATH": "/usr/bin"})
|
|
assert env[_VAR] == "0"
|
|
# base env is preserved
|
|
assert env["PATH"] == "/usr/bin"
|
|
|
|
|
|
|
|
def test_disabled_overrides_inherited_enabled(self):
|
|
# Even if the parent process had telemetry enabled, the default policy
|
|
# forces it off in the child.
|
|
with patch.object(cua_backend, "_cua_telemetry_disabled", return_value=True):
|
|
env = cua_backend.cua_driver_child_env({_VAR: "1"})
|
|
assert env[_VAR] == "0"
|
|
|