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.
52 lines
1.5 KiB
Python
52 lines
1.5 KiB
Python
"""Tests for tools.skills_ast_audit — opt-in AST diagnostic scanner."""
|
|
|
|
import sys
|
|
|
|
from tools.skills_ast_audit import ast_scan_path, format_ast_report
|
|
|
|
|
|
def _pids(findings):
|
|
return [pid for (_f, _l, pid, _d) in findings]
|
|
|
|
|
|
def test_bypass_payload_detected(tmp_path):
|
|
"""The exact bypass shape from #7072 is caught."""
|
|
f = tmp_path / "exfil.py"
|
|
f.write_text(
|
|
"import importlib\n"
|
|
"parts = ['o', 's']\n"
|
|
"m = importlib.import_module(''.join(parts))\n"
|
|
"e = m.__dict__[''.join(['e','n','v'])]\n"
|
|
)
|
|
pids = _pids(ast_scan_path(f))
|
|
assert "dynamic_import" in pids
|
|
assert "importlib_import" in pids
|
|
assert "dict_access" in pids
|
|
|
|
|
|
def test_syntax_error_does_not_crash(tmp_path):
|
|
f = tmp_path / "bad.py"
|
|
f.write_text("def broken(\n")
|
|
assert ast_scan_path(f) == []
|
|
|
|
|
|
def test_recursion_error_does_not_crash(tmp_path):
|
|
f = tmp_path / "deep.py"
|
|
f.write_text("a" + ".x" * 5000 + "\n")
|
|
orig = sys.getrecursionlimit()
|
|
sys.setrecursionlimit(200)
|
|
try:
|
|
result = ast_scan_path(f)
|
|
finally:
|
|
sys.setrecursionlimit(orig)
|
|
assert isinstance(result, list)
|
|
|
|
|
|
def test_format_report_with_findings():
|
|
findings = [
|
|
("a.py", 1, "importlib_import", "import importlib — ..."),
|
|
("a.py", 3, "dynamic_import", "importlib.import_module() — ..."),
|
|
]
|
|
out = format_ast_report(findings, skill_name="test")
|
|
assert "test" in out and "a.py" in out and "L1" in out and "L3" in out
|
|
assert "diagnostic hints" in out
|