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.
73 lines
2.6 KiB
Python
73 lines
2.6 KiB
Python
from unittest.mock import MagicMock
|
|
|
|
import pytest
|
|
|
|
from tools.file_operations import ExecuteResult, ShellFileOperations, _search_stdout_and_limit
|
|
|
|
|
|
TIMEOUT = "[Command timed out after 60s]"
|
|
|
|
|
|
@pytest.fixture()
|
|
def ops():
|
|
env = MagicMock(cwd="/tmp/test")
|
|
env.execute.return_value = {"output": "", "returncode": 0}
|
|
return ShellFileOperations(env)
|
|
|
|
|
|
def timeout_output(*lines: str) -> str:
|
|
return "\n".join([*lines, TIMEOUT])
|
|
|
|
|
|
def path_exists_or(output: str, returncode: int = 124):
|
|
def execute(command, **kwargs):
|
|
if "test -e" in command:
|
|
return {"output": "exists", "returncode": 0}
|
|
return {"output": output, "returncode": returncode}
|
|
|
|
return execute
|
|
|
|
|
|
def assert_timed_out(result):
|
|
assert result.error is None
|
|
assert result.truncated is True
|
|
assert result.limit_reason == "search_timeout"
|
|
assert result.to_dict()["limit_reason"] == "search_timeout"
|
|
|
|
|
|
def test_timeout_helper_strips_only_trailing_marker():
|
|
assert _search_stdout_and_limit(ExecuteResult(timeout_output("a.py"), 124)) == ("a.py", "search_timeout")
|
|
assert _search_stdout_and_limit(ExecuteResult("a.py\nnot a marker", 0)) == ("a.py\nnot a marker", None)
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("target", "output_mode", "raw", "expected"),
|
|
[
|
|
("files", "content", timeout_output("src/a.py", "src/b.py"), ["src/a.py", "src/b.py"]),
|
|
("content", "files_only", timeout_output("src/a.py", "src/b.py"), ["src/a.py", "src/b.py"]),
|
|
("content", "content", timeout_output("src/a.py:10:foo", "src/b.py:20:foo"), ["src/a.py", "src/b.py"]),
|
|
],
|
|
)
|
|
def test_rg_timeout_returns_partial_results_without_marker(ops, monkeypatch, target, output_mode, raw, expected):
|
|
ops.env.execute.side_effect = path_exists_or(raw)
|
|
monkeypatch.setattr(ops, "_has_command", lambda cmd: cmd == "rg")
|
|
|
|
result = ops.search("foo", path="/big", target=target, output_mode=output_mode)
|
|
|
|
assert_timed_out(result)
|
|
if target == "content" and output_mode == "content":
|
|
assert [match.path for match in result.matches] == expected
|
|
assert all("timed out" not in match.content for match in result.matches)
|
|
else:
|
|
assert result.files == expected
|
|
assert all("timed out" not in path for path in result.files)
|
|
|
|
|
|
def test_real_rg_error_still_hard_fails(ops, monkeypatch):
|
|
ops.env.execute.side_effect = path_exists_or("rg: regex parse error:", returncode=2)
|
|
monkeypatch.setattr(ops, "_has_command", lambda cmd: cmd == "rg")
|
|
|
|
result = ops.search("[", path="/big", target="content")
|
|
|
|
assert result.error == "Search failed: rg: regex parse error:"
|
|
assert result.limit_reason is None
|