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.
116 lines
4.5 KiB
Python
116 lines
4.5 KiB
Python
"""Regression tests for the Docker terminal network toggle.
|
|
|
|
Ported from NanoClaw PR #2713's opt-in egress lockdown idea. Hermes already
|
|
has DockerEnvironment(network=False), but the terminal config path did not
|
|
expose it, so operators could not request networkless Docker execution from
|
|
config.yaml.
|
|
"""
|
|
|
|
import tools.terminal_tool as terminal_tool
|
|
from tools.environments import docker as docker_env
|
|
|
|
|
|
def test_terminal_env_config_reads_docker_network_toggle(monkeypatch):
|
|
monkeypatch.setenv("TERMINAL_DOCKER_NETWORK", "false")
|
|
|
|
config = terminal_tool._get_env_config()
|
|
|
|
assert config["docker_network"] is False
|
|
|
|
|
|
def test_sibling_container_config_sites_carry_docker_network():
|
|
"""Every container_config dict that carries docker_run_as_host_user must
|
|
also carry docker_network — otherwise that code path silently falls back
|
|
to networked containers while the terminal path honors the lockdown
|
|
(the probe/exec asymmetry reported on issue #46358).
|
|
"""
|
|
import ast
|
|
import inspect
|
|
|
|
import tools.code_execution_tool as code_execution_tool
|
|
import tools.file_tools as file_tools
|
|
|
|
for module in (terminal_tool, file_tools, code_execution_tool):
|
|
tree = ast.parse(inspect.getsource(module))
|
|
sites = 0
|
|
for node in ast.walk(tree):
|
|
if not isinstance(node, ast.Dict):
|
|
continue
|
|
keys = {k.value for k in node.keys if isinstance(k, ast.Constant)}
|
|
if "docker_run_as_host_user" in keys:
|
|
sites += 1
|
|
assert "docker_network" in keys, (
|
|
f"{module.__name__} builds a container_config with "
|
|
f"docker_run_as_host_user but without docker_network "
|
|
f"(line {node.lineno})"
|
|
)
|
|
assert sites >= 1, f"expected at least one container_config site in {module.__name__}"
|
|
|
|
|
|
def _reuse_guard_harness(monkeypatch, *, existing_mode: str, network: bool):
|
|
"""Drive DockerEnvironment through the cross-process reuse path with a
|
|
fake existing container whose NetworkMode is *existing_mode*.
|
|
|
|
Returns the list of docker commands issued.
|
|
"""
|
|
commands = []
|
|
|
|
def fake_run(cmd, *args, **kwargs):
|
|
commands.append(cmd)
|
|
|
|
class Result:
|
|
returncode = 0
|
|
stderr = ""
|
|
stdout = ""
|
|
|
|
if len(cmd) > 1 and cmd[1] == "ps":
|
|
# Matches the egress-aware reuse probe: with egress off the
|
|
# format string is ID\tState\tEgressLabel and docker renders a
|
|
# missing label as "<no value>".
|
|
Result.stdout = "existing-container-id\trunning\t<no value>\n"
|
|
elif len(cmd) > 1 and cmd[1] == "inspect":
|
|
Result.stdout = f"{existing_mode}\n"
|
|
elif len(cmd) > 1 and cmd[1] == "run":
|
|
Result.stdout = "fresh-container-id\n"
|
|
return Result()
|
|
|
|
monkeypatch.setattr(docker_env, "find_docker", lambda: "/usr/bin/docker")
|
|
monkeypatch.setattr(docker_env.subprocess, "run", fake_run)
|
|
monkeypatch.setattr(docker_env.DockerEnvironment, "_storage_opt_supported", lambda self: False)
|
|
|
|
docker_env.DockerEnvironment(
|
|
image="python:3.11",
|
|
cwd="/workspace",
|
|
timeout=60,
|
|
task_id="reuse-guard-test",
|
|
network=network,
|
|
persist_across_processes=True,
|
|
)
|
|
return commands
|
|
|
|
|
|
def test_reuse_rejects_networked_container_when_lockdown_requested(monkeypatch):
|
|
commands = _reuse_guard_harness(monkeypatch, existing_mode="bridge", network=False)
|
|
|
|
assert any(cmd[1:3] == ["rm", "-f"] for cmd in commands), (
|
|
"bridge-networked container must be removed when docker_network=false"
|
|
)
|
|
run_cmd = next(cmd for cmd in commands if len(cmd) > 2 and cmd[1:3] == ["run", "-d"])
|
|
assert "--network=none" in run_cmd
|
|
|
|
|
|
def test_reuse_keeps_airgapped_container_when_lockdown_requested(monkeypatch):
|
|
commands = _reuse_guard_harness(monkeypatch, existing_mode="none", network=False)
|
|
|
|
assert not any(cmd[1] == "rm" for cmd in commands)
|
|
assert not any(cmd[1] == "run" for cmd in commands), "matching container must be reused"
|
|
|
|
|
|
def test_reuse_skips_inspect_when_network_enabled(monkeypatch):
|
|
commands = _reuse_guard_harness(monkeypatch, existing_mode="none", network=True)
|
|
|
|
# Default-network config never churns containers, even air-gapped ones
|
|
# (operators may have created them via docker_extra_args).
|
|
assert not any(cmd[1] == "inspect" for cmd in commands)
|
|
assert not any(cmd[1] == "rm" for cmd in commands)
|
|
assert not any(cmd[1] == "run" for cmd in commands)
|