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.
59 lines
1.7 KiB
Python
59 lines
1.7 KiB
Python
"""Tests for tools.working_diff.collect_working_diff — the git collection
|
|
layer shared by the CLI and gateway ``/diff`` command.
|
|
|
|
Runs against real temporary git repositories (no mocks) so the staged /
|
|
unstaged / untracked semantics are proven against actual git behaviour.
|
|
"""
|
|
|
|
import shutil
|
|
import subprocess
|
|
|
|
import pytest
|
|
|
|
from tools.working_diff import collect_working_diff
|
|
|
|
pytestmark = pytest.mark.skipif(
|
|
shutil.which("git") is None, reason="git required for working-diff tests"
|
|
)
|
|
|
|
|
|
def _git(repo, *args):
|
|
subprocess.run(
|
|
["git", *args], cwd=repo, check=True, capture_output=True,
|
|
env={"HOME": str(repo), "GIT_AUTHOR_NAME": "t", "GIT_AUTHOR_EMAIL": "t@t",
|
|
"GIT_COMMITTER_NAME": "t", "GIT_COMMITTER_EMAIL": "t@t",
|
|
"PATH": __import__("os").environ["PATH"]},
|
|
)
|
|
|
|
|
|
@pytest.fixture()
|
|
def repo(tmp_path):
|
|
d = tmp_path / "repo"
|
|
d.mkdir()
|
|
_git(d, "init", "-q")
|
|
(d / "tracked.py").write_text("print('hello')\n")
|
|
_git(d, "add", "-A")
|
|
_git(d, "commit", "-q", "-m", "init")
|
|
return d
|
|
|
|
|
|
def test_clean_repo_reports_empty(repo):
|
|
result = collect_working_diff(str(repo))
|
|
assert result["success"] is True
|
|
assert result.get("empty") is True
|
|
assert result["diff"] == ""
|
|
|
|
|
|
def test_unstaged_change_appears_in_default_mode(repo):
|
|
(repo / "tracked.py").write_text("print('changed')\n")
|
|
result = collect_working_diff(str(repo))
|
|
assert result["success"] is True
|
|
assert "-print('hello')" in result["diff"]
|
|
assert "+print('changed')" in result["diff"]
|
|
assert "tracked.py" in result["stat"]
|
|
|
|
|
|
def test_unknown_mode_rejected(repo):
|
|
result = collect_working_diff(str(repo), mode="bogus")
|
|
assert result["success"] is False
|
|
assert "bogus" in result["error"]
|