mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +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.
76 lines
3 KiB
Python
76 lines
3 KiB
Python
"""Tests for the fail-closed pre-write syntax gate on write_file.
|
|
|
|
Structured formats with an in-process linter (JSON/YAML/TOML) are validated
|
|
BEFORE any bytes touch disk: a candidate write that doesn't parse is refused
|
|
outright -- nothing lands on disk -- instead of being written and merely
|
|
reported afterward via the post-write lint delta.
|
|
|
|
These run against a REAL LocalEnvironment (actual shell commands / actual
|
|
files under tmp_path), matching the existing pattern in
|
|
tests/tools/test_file_write_safety.py::TestAtomicWrite.
|
|
"""
|
|
|
|
import json
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from tools.environments.local import LocalEnvironment
|
|
from tools.file_operations import ShellFileOperations
|
|
|
|
|
|
@pytest.fixture
|
|
def ops(tmp_path: Path):
|
|
env = LocalEnvironment(cwd=str(tmp_path))
|
|
return ShellFileOperations(env, cwd=str(tmp_path))
|
|
|
|
|
|
class TestFailClosedSyntaxGate:
|
|
def test_invalid_json_refused_file_not_created(self, ops, tmp_path: Path):
|
|
target = tmp_path / "config.json"
|
|
res = ops.write_file(str(target), '{"a": 1,') # truncated / invalid
|
|
assert res.error is not None
|
|
assert "json" in res.error.lower()
|
|
assert not target.exists(), "invalid JSON must NOT be written to disk"
|
|
|
|
|
|
def test_valid_json_written_exactly(self, ops, tmp_path: Path):
|
|
target = tmp_path / "config.json"
|
|
content = json.dumps({"a": 1, "b": [1, 2, 3]})
|
|
res = ops.write_file(str(target), content)
|
|
assert res.error is None, res.error
|
|
assert target.read_text() == content
|
|
|
|
|
|
def test_invalid_python_is_NOT_hard_refused(self, ops, tmp_path: Path):
|
|
"""Deliberate scope decision: .py keeps the pre-existing NON-BLOCKING
|
|
lint-delta report rather than a hard refusal (see
|
|
``_FAIL_CLOSED_INPROC_EXTS`` in tools/file_operations.py for why --
|
|
this codebase's own test suite writes arbitrary non-Python content
|
|
through *.py paths as generic write-mechanics fixtures)."""
|
|
target = tmp_path / "broken.py"
|
|
bad_python = "def foo(:\n pass\n"
|
|
res = ops.write_file(str(target), bad_python)
|
|
assert res.error is None, res.error
|
|
assert target.read_text() == bad_python
|
|
# Still surfaced via the (non-blocking) lint report:
|
|
assert res.lint is not None
|
|
assert res.lint.get("status") == "error"
|
|
assert "SyntaxError" in res.lint.get("output", "")
|
|
|
|
|
|
def test_custom_tagged_yaml_is_valid_and_written(self, ops, tmp_path: Path):
|
|
"""Application-defined tags (CloudFormation !Sub/!Ref, Ansible !vault)
|
|
are valid YAML syntax; only the *consumer* defines their constructors.
|
|
The gate is syntax-only and must let them through."""
|
|
target = tmp_path / "template.yaml"
|
|
content = (
|
|
"Resources:\n"
|
|
" Bucket:\n"
|
|
" Type: AWS::S3::Bucket\n"
|
|
" Properties:\n"
|
|
" BucketName: !Sub '${AWS::StackName}-bucket'\n"
|
|
)
|
|
res = ops.write_file(str(target), content)
|
|
assert res.error is None, res.error
|
|
assert target.read_text() == content
|