mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +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.
104 lines
3.9 KiB
Python
104 lines
3.9 KiB
Python
"""Tests for the skill_view path boundary check.
|
|
|
|
Regression test: the original check used a hardcoded "/" separator which
|
|
fails on Windows where Path.resolve() returns backslash-separated paths.
|
|
Now uses Path.is_relative_to() which handles all platforms correctly.
|
|
"""
|
|
|
|
import os
|
|
import pytest
|
|
from pathlib import Path
|
|
|
|
|
|
def _path_escapes_skill_dir(resolved: Path, skill_dir_resolved: Path) -> bool:
|
|
"""Reproduce the boundary check from tools/skills_tool.py.
|
|
|
|
Returns True when the resolved path is OUTSIDE the skill directory.
|
|
"""
|
|
return not resolved.is_relative_to(skill_dir_resolved)
|
|
|
|
|
|
class TestSkillViewPathBoundaryCheck:
|
|
"""Verify the path boundary check works on all platforms."""
|
|
|
|
def test_valid_subpath_allowed(self, tmp_path):
|
|
"""A file inside the skill directory must NOT be flagged."""
|
|
skill_dir = tmp_path / "skills" / "axolotl"
|
|
ref_file = skill_dir / "references" / "api.md"
|
|
skill_dir.mkdir(parents=True)
|
|
ref_file.parent.mkdir()
|
|
ref_file.write_text("content")
|
|
|
|
resolved = ref_file.resolve()
|
|
skill_dir_resolved = skill_dir.resolve()
|
|
|
|
assert _path_escapes_skill_dir(resolved, skill_dir_resolved) is False
|
|
|
|
|
|
def test_outside_path_blocked(self, tmp_path):
|
|
"""A file outside the skill directory must be flagged."""
|
|
skill_dir = tmp_path / "skills" / "axolotl"
|
|
skill_dir.mkdir(parents=True)
|
|
outside_file = tmp_path / "secret.env"
|
|
outside_file.write_text("SECRET=123")
|
|
|
|
resolved = outside_file.resolve()
|
|
skill_dir_resolved = skill_dir.resolve()
|
|
|
|
assert _path_escapes_skill_dir(resolved, skill_dir_resolved) is True
|
|
|
|
def test_sibling_skill_dir_blocked(self, tmp_path):
|
|
"""A file in a sibling skill directory must be flagged.
|
|
|
|
This catches prefix confusion: 'axolotl-v2' starts with 'axolotl'
|
|
as a string but is a different directory.
|
|
"""
|
|
skill_dir = tmp_path / "skills" / "axolotl"
|
|
sibling_dir = tmp_path / "skills" / "axolotl-v2"
|
|
skill_dir.mkdir(parents=True)
|
|
sibling_dir.mkdir(parents=True)
|
|
sibling_file = sibling_dir / "SKILL.md"
|
|
sibling_file.write_text("other skill")
|
|
|
|
resolved = sibling_file.resolve()
|
|
skill_dir_resolved = skill_dir.resolve()
|
|
|
|
assert _path_escapes_skill_dir(resolved, skill_dir_resolved) is True
|
|
|
|
def test_skill_dir_itself_allowed(self, tmp_path):
|
|
"""Requesting the skill directory itself must be allowed."""
|
|
skill_dir = tmp_path / "skills" / "axolotl"
|
|
skill_dir.mkdir(parents=True)
|
|
|
|
resolved = skill_dir.resolve()
|
|
skill_dir_resolved = skill_dir.resolve()
|
|
|
|
assert _path_escapes_skill_dir(resolved, skill_dir_resolved) is False
|
|
|
|
|
|
class TestOldCheckWouldFail:
|
|
"""Demonstrate the bug: the old hardcoded '/' check fails on Windows."""
|
|
|
|
def _old_path_escapes(self, resolved: Path, skill_dir_resolved: Path) -> bool:
|
|
"""The BROKEN check that used hardcoded '/'."""
|
|
return (
|
|
not str(resolved).startswith(str(skill_dir_resolved) + "/")
|
|
and resolved != skill_dir_resolved
|
|
)
|
|
|
|
@pytest.mark.skipif(os.sep == "/", reason="Bug only manifests on Windows")
|
|
def test_old_check_false_positive_on_windows(self, tmp_path):
|
|
"""On Windows, the old check incorrectly blocks valid subpaths."""
|
|
skill_dir = tmp_path / "skills" / "axolotl"
|
|
ref_file = skill_dir / "references" / "api.md"
|
|
skill_dir.mkdir(parents=True)
|
|
ref_file.parent.mkdir()
|
|
ref_file.write_text("content")
|
|
|
|
resolved = ref_file.resolve()
|
|
skill_dir_resolved = skill_dir.resolve()
|
|
|
|
# Old check says it escapes (WRONG on Windows)
|
|
assert self._old_path_escapes(resolved, skill_dir_resolved) is True
|
|
# New check correctly allows it
|
|
assert _path_escapes_skill_dir(resolved, skill_dir_resolved) is False
|