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.
115 lines
4 KiB
Python
115 lines
4 KiB
Python
"""Unit tests for scripts/docker_rebootstrap_nous_session.py.
|
|
|
|
The boot-time re-seed is the load-bearing "does not clobber a healthy session"
|
|
guard: it may overwrite the on-disk Nous provider entry when that entry is
|
|
provably terminal (quarantine marker + no usable tokens), or when an
|
|
orchestrator seed is demonstrably newer. Older/incomparable seeds must no-op.
|
|
These are pure-stdlib tmp_path tests (no container build).
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import importlib.util
|
|
import json
|
|
from pathlib import Path
|
|
|
|
# Import the stdlib-only boot helper by path (it lives under scripts/, not an
|
|
# installed package) — mirrors the repo's other scripts/-helper tests.
|
|
_SCRIPT = Path(__file__).resolve().parents[2] / "scripts" / "docker_rebootstrap_nous_session.py"
|
|
_spec = importlib.util.spec_from_file_location("docker_rebootstrap_nous_session", _SCRIPT)
|
|
mod = importlib.util.module_from_spec(_spec)
|
|
_spec.loader.exec_module(mod)
|
|
|
|
|
|
def _terminal_nous_state():
|
|
"""On-disk shape after a terminal quarantine: tokens cleared, marker set."""
|
|
return {
|
|
"portal_base_url": "https://portal.example.com",
|
|
"client_id": "hermes-cli-vps",
|
|
"last_auth_error": {
|
|
"provider": "nous",
|
|
"code": "invalid_grant",
|
|
"relogin_required": True,
|
|
},
|
|
}
|
|
|
|
|
|
def _healthy_nous_state():
|
|
return {
|
|
"portal_base_url": "https://portal.example.com",
|
|
"client_id": "hermes-cli-vps",
|
|
"access_token": "live-at",
|
|
"refresh_token": "live-rt",
|
|
}
|
|
|
|
|
|
def _write_auth(tmp_path: Path, providers: dict) -> str:
|
|
p = tmp_path / "auth.json"
|
|
p.write_text(json.dumps({"version": 1, "providers": providers}))
|
|
return str(p)
|
|
|
|
|
|
_FRESH_SEED = json.dumps({
|
|
"version": 1,
|
|
"providers": {
|
|
"nous": {
|
|
"portal_base_url": "https://portal.example.com",
|
|
"client_id": "hermes-cli-vps",
|
|
"access_token": "FRESH-at",
|
|
"refresh_token": "FRESH-rt",
|
|
}
|
|
},
|
|
})
|
|
|
|
|
|
def test_reseeds_terminal_entry(tmp_path):
|
|
"""Terminal on-disk entry + valid seed → providers.nous replaced."""
|
|
auth = _write_auth(tmp_path, {"nous": _terminal_nous_state()})
|
|
result = mod.reseed_if_terminal(auth, _FRESH_SEED)
|
|
assert result == "reseeded"
|
|
store = json.loads(Path(auth).read_text())
|
|
assert store["providers"]["nous"]["refresh_token"] == "FRESH-rt"
|
|
assert "last_auth_error" not in store["providers"]["nous"]
|
|
|
|
|
|
def test_does_not_clobber_healthy_entry(tmp_path):
|
|
"""LOAD-BEARING: a healthy (live-token) entry must never be overwritten."""
|
|
auth = _write_auth(tmp_path, {"nous": _healthy_nous_state()})
|
|
result = mod.reseed_if_terminal(auth, _FRESH_SEED)
|
|
assert result == "not_terminal"
|
|
store = json.loads(Path(auth).read_text())
|
|
# Untouched — still the live tokens, not the seed.
|
|
assert store["providers"]["nous"]["refresh_token"] == "live-rt"
|
|
|
|
|
|
def test_marker_but_live_token_is_not_terminal(tmp_path):
|
|
"""Stale marker + a live token present → NOT terminal (don't clobber)."""
|
|
state = _terminal_nous_state()
|
|
state["refresh_token"] = "somehow-live"
|
|
auth = _write_auth(tmp_path, {"nous": state})
|
|
assert mod.reseed_if_terminal(auth, _FRESH_SEED) == "not_terminal"
|
|
|
|
|
|
def test_timezone_less_local_timestamp_is_incomparable(tmp_path):
|
|
auth = _write_auth(tmp_path, {"nous": {
|
|
**_healthy_nous_state(),
|
|
"obtained_at": "2026-07-14T19:00:00",
|
|
}})
|
|
seed = json.dumps({
|
|
"providers": {
|
|
"nous": {
|
|
"client_id": "hermes-cli-vps",
|
|
"access_token": "FRESH-at",
|
|
"refresh_token": "FRESH-rt",
|
|
"obtained_at": "2026-07-14T19:05:00Z",
|
|
}
|
|
},
|
|
})
|
|
|
|
assert mod.reseed_if_terminal(auth, seed) == "not_terminal"
|
|
|
|
|
|
def test_terminal_entry_missing_marker_is_not_terminal(tmp_path):
|
|
"""No last_auth_error at all (e.g. a merely-expired but not-quarantined
|
|
entry) → not terminal, no re-seed."""
|
|
auth = _write_auth(tmp_path, {"nous": {"client_id": "hermes-cli-vps"}})
|
|
assert mod.reseed_if_terminal(auth, _FRESH_SEED) == "not_terminal"
|