mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +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.
81 lines
2.1 KiB
Python
81 lines
2.1 KiB
Python
"""Tests for terminal command exit code semantic interpretation."""
|
|
|
|
import pytest
|
|
|
|
from tools.terminal_tool import _interpret_exit_code
|
|
|
|
|
|
class TestInterpretExitCode:
|
|
"""Test _interpret_exit_code returns correct notes for known command semantics."""
|
|
|
|
# ---- exit code 0 always returns None ----
|
|
|
|
def test_success_returns_none(self):
|
|
assert _interpret_exit_code("grep foo bar", 0) is None
|
|
assert _interpret_exit_code("diff a b", 0) is None
|
|
assert _interpret_exit_code("test -f /etc/passwd", 0) is None
|
|
|
|
# ---- grep / rg family: exit 1 = no matches ----
|
|
|
|
@pytest.mark.parametrize("cmd", [
|
|
"grep 'pattern' file.txt",
|
|
"egrep 'pattern' file.txt",
|
|
"fgrep 'pattern' file.txt",
|
|
"rg 'foo' .",
|
|
"ag 'foo' .",
|
|
"ack 'foo' .",
|
|
])
|
|
def test_grep_family_no_matches(self, cmd):
|
|
result = _interpret_exit_code(cmd, 1)
|
|
assert result is not None
|
|
assert "no matches" in result.lower()
|
|
|
|
|
|
# ---- diff: exit 1 = files differ ----
|
|
|
|
def test_diff_files_differ(self):
|
|
result = _interpret_exit_code("diff file1 file2", 1)
|
|
assert result is not None
|
|
assert "differ" in result.lower()
|
|
|
|
def test_colordiff_files_differ(self):
|
|
result = _interpret_exit_code("colordiff file1 file2", 1)
|
|
assert result is not None
|
|
assert "differ" in result.lower()
|
|
|
|
|
|
# ---- test / [: exit 1 = condition false ----
|
|
|
|
def test_test_condition_false(self):
|
|
result = _interpret_exit_code("test -f /nonexistent", 1)
|
|
assert result is not None
|
|
assert "false" in result.lower()
|
|
|
|
|
|
# ---- find: exit 1 = partial success ----
|
|
|
|
|
|
# ---- curl: various informational codes ----
|
|
|
|
|
|
# ---- git: exit 1 is context-dependent ----
|
|
|
|
|
|
# ---- pipeline / chain handling ----
|
|
|
|
|
|
# ---- full paths ----
|
|
|
|
|
|
# ---- env var prefix ----
|
|
|
|
|
|
# ---- unknown commands return None ----
|
|
|
|
|
|
# ---- edge cases ----
|
|
|
|
|
|
def test_only_env_vars(self):
|
|
"""Command with only env var assignments, no actual command."""
|
|
assert _interpret_exit_code("FOO=bar", 1) is None
|