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.
93 lines
3.4 KiB
Python
93 lines
3.4 KiB
Python
"""Tests for the post-pull syntax guard in ``hermes update``.
|
|
|
|
When a bad commit lands on ``main`` with a syntax error in a critical file
|
|
(e.g. orphan merge-conflict markers in ``hermes_cli/config.py``), the CLI
|
|
becomes unbootable — every ``hermes`` invocation imports those files at
|
|
startup. The guard validates them after ``git pull`` and rolls back to the
|
|
pre-pull SHA on failure so the user's install stays runnable.
|
|
|
|
Reference incident: PR #28452 (May 18, 2026) shipped unresolved conflict
|
|
markers in ``hermes_cli/config.py``; users who ran ``hermes update`` in
|
|
the 7-minute window before #28458 landed could not run any ``hermes``
|
|
command afterward.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
from types import SimpleNamespace
|
|
|
|
from hermes_cli import main as hermes_main
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# _capture_head_sha
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def test_capture_head_sha_returns_stripped_sha(monkeypatch, tmp_path):
|
|
def fake_run(cmd, **kwargs):
|
|
assert cmd[-2:] == ["rev-parse", "HEAD"]
|
|
return SimpleNamespace(stdout="deadbeefcafe\n", returncode=0)
|
|
|
|
monkeypatch.setattr(hermes_main.subprocess, "run", fake_run)
|
|
|
|
assert hermes_main._capture_head_sha(["git"], tmp_path) == "deadbeefcafe"
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# _validate_critical_files_syntax
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def _populate_critical_tree(root: Path, *, broken_file: str | None = None) -> None:
|
|
"""Create stub files for every entry in ``_UPDATE_CRITICAL_FILES``.
|
|
|
|
If ``broken_file`` is given, that file gets orphan merge-conflict markers
|
|
(the exact failure mode from PR #28452).
|
|
"""
|
|
broken_payload = (
|
|
"x = {\n"
|
|
' "a": 1,\n'
|
|
"<<<<<<< HEAD\n"
|
|
' "b": 2,\n'
|
|
"=======\n"
|
|
' "c": 0b6d673e7,\n' # invalid binary literal — the actual error users saw
|
|
">>>>>>> 0b6d673e7\n"
|
|
"}\n"
|
|
)
|
|
for relpath in hermes_main._UPDATE_CRITICAL_FILES:
|
|
path = root / relpath
|
|
path.parent.mkdir(parents=True, exist_ok=True)
|
|
if relpath == broken_file:
|
|
path.write_text(broken_payload)
|
|
else:
|
|
path.write_text("# stub\n")
|
|
|
|
|
|
|
|
|
|
def test_validate_critical_files_syntax_tolerates_missing_files(tmp_path):
|
|
"""A refactor may legitimately remove one of the critical files — the
|
|
guard should skip missing files, not falsely flag the install as broken."""
|
|
# Populate everything except hermes_constants.py
|
|
for relpath in hermes_main._UPDATE_CRITICAL_FILES:
|
|
if relpath == "hermes_constants.py":
|
|
continue
|
|
path = tmp_path / relpath
|
|
path.parent.mkdir(parents=True, exist_ok=True)
|
|
path.write_text("# stub\n")
|
|
|
|
ok, failing_path, error = hermes_main._validate_critical_files_syntax(tmp_path)
|
|
|
|
assert ok is True
|
|
assert failing_path is None
|
|
assert error is None
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Repo invariant — the production tree itself must always pass the guard.
|
|
# This catches the case where ``main`` ships a syntax error before the next
|
|
# release; if a future ``hermes update`` would brick users, this test fails
|
|
# in CI first.
|
|
# ---------------------------------------------------------------------------
|
|
|