mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +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.
50 lines
1.5 KiB
Python
50 lines
1.5 KiB
Python
"""Unit tests for hermes_cli.toolset_validation (see #38798).
|
|
|
|
Pure logic — the validity predicate is injected, so these tests need neither the
|
|
tool registry nor a running Hermes.
|
|
"""
|
|
|
|
import pytest
|
|
|
|
from hermes_cli.toolset_validation import validate_platform_toolsets
|
|
|
|
# A representative set of real toolset names. `hermes` is deliberately absent —
|
|
# that is the corruption #38798 reported (`hermes-cli` rewritten to `hermes`).
|
|
_KNOWN = {
|
|
"hermes-cli",
|
|
"hermes-telegram",
|
|
"hermes-discord",
|
|
"terminal",
|
|
"web",
|
|
}
|
|
|
|
|
|
def _is_valid(name):
|
|
return name in _KNOWN
|
|
|
|
|
|
|
|
|
|
def test_38798_corruption_warns_and_suggests_correct_name():
|
|
# The exact reported shape: cli holds 'hermes' instead of 'hermes-cli'.
|
|
warnings = validate_platform_toolsets({"cli": ["hermes"]}, _is_valid)
|
|
unknown = [w for w in warnings if "unknown toolset 'hermes'" in w]
|
|
assert len(unknown) == 1
|
|
# Actionable: points at the valid name the entry should have been.
|
|
assert "did you mean 'hermes-cli'?" in unknown[0]
|
|
# And the zero-valid-toolsets safety net fires.
|
|
assert any("zero valid toolsets" in w for w in warnings)
|
|
|
|
|
|
def test_mixed_valid_and_invalid_flags_only_the_invalid():
|
|
cfg = {"cli": ["hermes-cli"], "discord": ["bogus"]}
|
|
warnings = validate_platform_toolsets(cfg, _is_valid)
|
|
# One valid entry exists, so no zero-valid warning.
|
|
assert not any("zero valid toolsets" in w for w in warnings)
|
|
assert len(warnings) == 1
|
|
assert "platform 'discord'" in warnings[0]
|
|
assert "unknown toolset 'bogus'" in warnings[0]
|
|
|
|
|
|
|
|
|