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.
88 lines
3.1 KiB
Python
88 lines
3.1 KiB
Python
"""Regression tests for the terminal config → env fallback bridge.
|
|
|
|
``terminal_tool._get_env_config()`` reads all settings from TERMINAL_* env
|
|
vars, which the CLI / gateway / TUI-PTY launchers bridge from config.yaml at
|
|
startup. Processes that skip every launcher bridge (``hermes serve`` and the
|
|
Desktop app's in-process agents, the desktop cron ticker, ACP) used to fall
|
|
back silently to the local backend even when config.yaml selected
|
|
``terminal.backend: docker`` — commands the user intended to sandbox ran on
|
|
the host (#63141 / #54449 / #61115 / #65696).
|
|
|
|
``_ensure_terminal_env_bridged()`` closes that hole at the chokepoint: when
|
|
TERMINAL_ENV is unset, backfill TERMINAL_* from config.yaml before the
|
|
local default applies. An explicitly-set TERMINAL_ENV always wins.
|
|
"""
|
|
|
|
import os
|
|
|
|
import pytest
|
|
|
|
import tools.terminal_tool as terminal_tool
|
|
from hermes_constants import get_hermes_home
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _reset_bridge_state(monkeypatch):
|
|
"""Each test starts with an un-attempted bridge and no TERMINAL_ENV."""
|
|
monkeypatch.setattr(terminal_tool, "_terminal_config_bridge_attempted", False)
|
|
monkeypatch.delenv("TERMINAL_ENV", raising=False)
|
|
monkeypatch.delenv("TERMINAL_CWD", raising=False)
|
|
monkeypatch.delenv("TERMINAL_DOCKER_IMAGE", raising=False)
|
|
# The config layer caches by (path, mtime, size); leave it alone — each
|
|
# test writes its own config.yaml which changes the signature.
|
|
yield
|
|
|
|
|
|
def _write_config(text: str) -> None:
|
|
home = get_hermes_home()
|
|
home.mkdir(parents=True, exist_ok=True)
|
|
(home / "config.yaml").write_text(text)
|
|
|
|
|
|
def test_unset_terminal_env_backfills_backend_from_config():
|
|
"""The core #63141 fix: config's docker backend reaches _get_env_config
|
|
even when no launcher bridged TERMINAL_ENV into this process."""
|
|
_write_config(
|
|
"terminal:\n"
|
|
" backend: docker\n"
|
|
" docker_image: custom/image:1\n"
|
|
)
|
|
|
|
config = terminal_tool._get_env_config()
|
|
|
|
assert config["env_type"] == "docker"
|
|
assert config["docker_image"] == "custom/image:1"
|
|
assert os.environ.get("TERMINAL_ENV") == "docker"
|
|
|
|
|
|
def test_explicit_terminal_env_wins_over_config(monkeypatch):
|
|
"""An explicit env choice (launcher bridge or .env) is never overridden —
|
|
honor explicit choice vs accidental fallback."""
|
|
_write_config("terminal:\n backend: docker\n")
|
|
monkeypatch.setenv("TERMINAL_ENV", "local")
|
|
|
|
config = terminal_tool._get_env_config()
|
|
|
|
assert config["env_type"] == "local"
|
|
|
|
|
|
def test_bridge_only_attempted_once(monkeypatch):
|
|
"""The config load runs at most once per process when TERMINAL_ENV stays
|
|
unset (e.g. empty config) — later calls skip the bridge entirely."""
|
|
calls = []
|
|
|
|
import hermes_cli.config as config_mod
|
|
|
|
real = config_mod.apply_terminal_config_to_env
|
|
|
|
def _counting(*a, **k):
|
|
calls.append(1)
|
|
return real(*a, **k)
|
|
|
|
monkeypatch.setattr(config_mod, "apply_terminal_config_to_env", _counting)
|
|
_write_config("{}\n")
|
|
|
|
terminal_tool._get_env_config()
|
|
terminal_tool._get_env_config()
|
|
|
|
assert len(calls) == 1
|