Files
hive/tools/tests/test_terminal_tools_security.py
T
Hundao 8cb0531959 fix(ci): unblock main CI, sort imports + install Playwright Chromium (#7172)
* fix(lint): organize imports in queen_orchestrator.create_queen

Ruff I001 blocks CI on every PR against main. The deferred imports
inside create_queen were not in alphabetical order between the queen
package and the framework package; ruff auto-fix moves
framework.config below the framework.agents.queen.nodes block.

No behavior change.

* fix(ci): install Playwright Chromium before Test Tools job

The new chart_tools smoke tests added in feabf327 require a Chromium
build for ECharts/Mermaid rendering, but the test-tools workflow only
ran `uv sync` and went straight to pytest. Three tests
(test_render_echarts_bar_chart, test_render_echarts_accepts_string_spec,
test_render_mermaid_flowchart) crash on every PR with:

    BrowserType.launch: Executable doesn't exist at
    /home/runner/.cache/ms-playwright/chromium_headless_shell-1208/...

Split the install/run into separate steps and add `playwright install
chromium` before pytest. Use `--with-deps` on Linux to pull system
libraries; Windows runners only need the browser binary.

* fix(tests): adapt test_file_state_cache to new file_ops API

The file_ops rewrite in feabf327 dropped the standalone hashline_edit
tool (the file_system_toolkits/hashline_edit/ directory was removed)
and switched edit_file to a mode-first signature
(mode, path, old_string, new_string, ...).

The test fixture still tried to look up "hashline_edit" via the MCP
tool manager and crashed with KeyError before any test could run, and
the edit_file calls were positional in the old order so they hit
"unknown mode 'e.py'" once the fixture was fixed.

Drop the stale hashline_edit lookup and pass mode="replace" explicitly
to every edit_file call. All 11 tests pass locally.

* fix(tests): skip terminal_tools tests on Windows (POSIX-only)

The new terminal_tools package added in feabf327 imports the Unix-only
`resource` module in tools/src/terminal_tools/common/limits.py to set
RLIMIT_CPU / RLIMIT_AS / RLIMIT_FSIZE on subprocesses. Five of the
six terminal_tools test files therefore crash on windows-latest with
`ModuleNotFoundError: No module named 'resource'` once their fixtures
trigger the import chain.

test_terminal_tools_pty.py already has the right module-level skip
(PTY is POSIX-only). Apply the same `pytestmark = skipif(win32)` to
the other five so the whole suite skips cleanly on Windows. The
terminal-tools package is bash-only by design (zsh refused at the
shell-resolver level), so a Windows port is out of scope.
2026-05-05 00:32:59 +08:00

107 lines
3.3 KiB
Python

"""Security/policy tests: zsh refusal, env stripping, destructive catalog."""
from __future__ import annotations
import sys
import pytest
pytestmark = pytest.mark.skipif(sys.platform == "win32", reason="terminal_tools is POSIX-only (uses resource module)")
def test_resolve_shell_rejects_zsh():
from terminal_tools.common.limits import ZshRefused, _resolve_shell
for path in ("/bin/zsh", "/usr/bin/zsh", "/usr/local/bin/zsh", "ZSH"):
with pytest.raises(ZshRefused):
_resolve_shell(path)
def test_resolve_shell_accepts_bash():
from terminal_tools.common.limits import _resolve_shell
assert _resolve_shell(True) == "/bin/bash"
assert _resolve_shell("/bin/bash") == "/bin/bash"
assert _resolve_shell(False) is None
def test_sanitized_env_strips_zsh_vars(monkeypatch):
from terminal_tools.common.limits import sanitized_env
monkeypatch.setenv("ZDOTDIR", "/some/path")
monkeypatch.setenv("ZSH_VERSION", "5.9")
monkeypatch.setenv("ZSH_NAME", "zsh")
monkeypatch.setenv("PATH", "/usr/bin:/bin")
env = sanitized_env()
assert "ZDOTDIR" not in env
assert "ZSH_VERSION" not in env
assert "ZSH_NAME" not in env
# Non-zsh vars survive
assert env["PATH"] == "/usr/bin:/bin"
def test_destructive_warning_catalog():
from terminal_tools.common.destructive_warning import get_warning
cases = [
("rm -rf /tmp/foo", "force-remove"),
("rm -r /tmp/foo", "recursively remove"),
("git reset --hard HEAD~1", "discard"),
("git push --force origin main", "remote history"),
("git push -f origin main", "remote history"),
("git commit --amend -m 'x'", "rewrite"),
("DROP TABLE users;", "drop or truncate"),
("DELETE FROM users;", "delete rows"),
("kubectl delete pod foo", "Kubernetes"),
("terraform destroy", "Terraform"),
]
for cmd, expected in cases:
warning = get_warning(cmd)
assert warning is not None, f"expected warning for {cmd!r}"
assert expected in warning, f"warning {warning!r} should mention {expected!r}"
def test_destructive_warning_clean_commands():
from terminal_tools.common.destructive_warning import get_warning
for cmd in ["ls -la", "echo hi", "git status", "git commit -m 'x'"]:
assert get_warning(cmd) is None, f"unexpected warning for {cmd!r}"
def test_semantic_exit_grep():
from terminal_tools.common.semantic_exit import classify
status, msg = classify("grep foo /tmp/x", 0)
assert status == "ok"
status, msg = classify("grep foo /tmp/x", 1)
assert status == "ok"
assert "No matches" in msg
status, msg = classify("grep foo /tmp/x", 2)
assert status == "error"
def test_semantic_exit_default():
from terminal_tools.common.semantic_exit import classify
status, msg = classify("ls", 0)
assert status == "ok"
assert msg is None
status, msg = classify("ls", 1)
assert status == "error"
def test_semantic_exit_signaled():
from terminal_tools.common.semantic_exit import classify
status, msg = classify("sleep 999", -15, signaled=True)
assert status == "signal"
def test_semantic_exit_timed_out():
from terminal_tools.common.semantic_exit import classify
status, msg = classify("sleep 999", None, timed_out=True)
assert status == "error"
assert "timed out" in msg.lower()