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.
101 lines
3.6 KiB
Python
101 lines
3.6 KiB
Python
"""Tests that init_session() respects the configured cwd.
|
|
|
|
The bug: when terminal.cwd is set in config.yaml, the configured path was
|
|
displayed in the TUI banner but actual terminal commands ran in os.getcwd()
|
|
(the directory where ``hermes chat`` was started).
|
|
|
|
Root cause: init_session() captures the login shell environment by running
|
|
``pwd -P`` inside a ``bash -l -c`` bootstrap. Profile scripts (.bashrc,
|
|
.bash_profile, etc.) can change the working directory before ``pwd -P``
|
|
runs, so _update_cwd() overwrites self.cwd with the wrong directory.
|
|
|
|
Fix: the bootstrap now includes an explicit ``cd`` back to self.cwd before
|
|
running ``pwd -P``, so the configured cwd is always what gets recorded.
|
|
"""
|
|
|
|
from tempfile import TemporaryFile
|
|
from unittest.mock import MagicMock
|
|
|
|
from tools.environments.base import BaseEnvironment
|
|
|
|
|
|
class _TestableEnv(BaseEnvironment):
|
|
"""Concrete subclass for testing base class methods."""
|
|
|
|
def __init__(self, cwd="/tmp", timeout=10):
|
|
super().__init__(cwd=cwd, timeout=timeout)
|
|
|
|
def _run_bash(self, cmd_string, *, login=False, timeout=120, stdin_data=None):
|
|
raise NotImplementedError("Use mock")
|
|
|
|
def cleanup(self):
|
|
pass
|
|
|
|
|
|
class TestInitSessionCwdRespect:
|
|
"""init_session() must preserve the configured cwd."""
|
|
|
|
def test_bootstrap_contains_cd_to_configured_cwd(self):
|
|
"""The bootstrap script must cd to self.cwd before running pwd."""
|
|
env = _TestableEnv(cwd="/my/project")
|
|
|
|
# Capture the bootstrap script that init_session would pass to _run_bash
|
|
captured = {}
|
|
|
|
def mock_run_bash(cmd_string, *, login=False, timeout=120, stdin_data=None):
|
|
captured["cmd"] = cmd_string
|
|
mock = MagicMock()
|
|
mock.poll.return_value = 0
|
|
mock.returncode = 0
|
|
stdout = TemporaryFile(mode="w+b")
|
|
stdout.seek(0)
|
|
mock.stdout = stdout
|
|
return mock
|
|
|
|
env._run_bash = mock_run_bash
|
|
env.init_session()
|
|
|
|
assert "cmd" in captured, "init_session did not call _run_bash"
|
|
bootstrap = captured["cmd"]
|
|
|
|
# The cd must appear before pwd -P so the configured cwd is recorded
|
|
cd_pos = bootstrap.find("builtin cd")
|
|
pwd_pos = bootstrap.find("pwd -P")
|
|
assert cd_pos != -1, "bootstrap must contain 'builtin cd'"
|
|
assert pwd_pos != -1, "bootstrap must contain 'pwd -P'"
|
|
assert cd_pos < pwd_pos, (
|
|
"builtin cd must appear before pwd -P in the bootstrap so "
|
|
"the configured cwd is what gets recorded"
|
|
)
|
|
|
|
# The cd target must be the configured path (shlex.quote only adds
|
|
# quotes when the path contains shell-special characters)
|
|
assert "/my/project" in bootstrap, (
|
|
"bootstrap cd must target the configured cwd (/my/project)"
|
|
)
|
|
|
|
|
|
def test_bootstrap_cd_uses_shlex_quote(self):
|
|
"""Paths with spaces must be properly quoted in the bootstrap cd."""
|
|
env = _TestableEnv(cwd="/my project/with spaces")
|
|
|
|
captured = {}
|
|
|
|
def mock_run_bash(cmd_string, *, login=False, timeout=120, stdin_data=None):
|
|
captured["cmd"] = cmd_string
|
|
mock = MagicMock()
|
|
mock.poll.return_value = 0
|
|
mock.returncode = 0
|
|
stdout = TemporaryFile(mode="w+b")
|
|
stdout.seek(0)
|
|
mock.stdout = stdout
|
|
return mock
|
|
|
|
env._run_bash = mock_run_bash
|
|
env.init_session()
|
|
|
|
bootstrap = captured["cmd"]
|
|
# shlex.quote wraps paths with spaces in single quotes
|
|
assert "'/my project/with spaces'" in bootstrap, (
|
|
"bootstrap cd must properly quote paths with spaces"
|
|
)
|