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.
89 lines
2.3 KiB
Python
89 lines
2.3 KiB
Python
"""Tests for the local-only Nous session classifier exposed on /api/status."""
|
|
|
|
import base64
|
|
import json
|
|
import time
|
|
|
|
import hermes_cli.auth as auth
|
|
from hermes_cli.auth import (
|
|
NOUS_SESSION_TERMINAL,
|
|
NOUS_SESSION_UNKNOWN,
|
|
NOUS_SESSION_VALID,
|
|
get_nous_session_validity,
|
|
)
|
|
|
|
|
|
def _invoke_jwt(*, seconds: int = 3600) -> str:
|
|
def _encode(value: dict) -> str:
|
|
raw = json.dumps(value, separators=(",", ":")).encode()
|
|
return base64.urlsafe_b64encode(raw).rstrip(b"=").decode()
|
|
|
|
return ".".join(
|
|
(
|
|
_encode({"alg": "none", "typ": "JWT"}),
|
|
_encode(
|
|
{
|
|
"sub": "test-user",
|
|
"scope": auth.DEFAULT_NOUS_SCOPE,
|
|
"exp": int(time.time() + seconds),
|
|
}
|
|
),
|
|
"signature",
|
|
)
|
|
)
|
|
|
|
|
|
def _fail_if_live_auth_is_used(*args, **kwargs):
|
|
raise AssertionError("session validity must not resolve or refresh credentials")
|
|
|
|
|
|
def _block_live_auth(monkeypatch):
|
|
monkeypatch.setattr(auth, "get_nous_auth_status", _fail_if_live_auth_is_used)
|
|
monkeypatch.setattr(
|
|
auth,
|
|
"resolve_nous_runtime_credentials",
|
|
_fail_if_live_auth_is_used,
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ── get_nous_auth_status_local — refresh-free display snapshot ──
|
|
|
|
|
|
def test_local_status_not_logged_in_after_terminal_quarantine(monkeypatch):
|
|
monkeypatch.setattr(
|
|
auth,
|
|
"get_provider_auth_state",
|
|
lambda provider: {
|
|
"last_auth_error": {
|
|
"relogin_required": True,
|
|
"code": "invalid_grant",
|
|
},
|
|
},
|
|
)
|
|
_block_live_auth(monkeypatch)
|
|
|
|
status = auth.get_nous_auth_status_local()
|
|
assert status["logged_in"] is False
|
|
assert status["relogin_required"] is True
|
|
assert status["error_code"] == "invalid_grant"
|
|
|
|
|
|
def test_local_status_repeated_polling_never_uses_live_auth(monkeypatch):
|
|
monkeypatch.setattr(
|
|
auth,
|
|
"get_provider_auth_state",
|
|
lambda provider: {
|
|
"access_token": _invoke_jwt(),
|
|
"refresh_token": "rt",
|
|
"scope": auth.DEFAULT_NOUS_SCOPE,
|
|
},
|
|
)
|
|
_block_live_auth(monkeypatch)
|
|
|
|
assert all(
|
|
auth.get_nous_auth_status_local()["logged_in"] for _ in range(10)
|
|
)
|