teknium1
d10bb2ab6f
`scripts/run_tests.sh tests/<dir>/` is how a change gets its regression
coverage run, so a test filed under the wrong directory is a test nobody
runs when that code changes. Two kinds of drift had accumulated.
Parallel directories for one source package, folded into the mirror:
tests/acp -> tests/acp_adapter (its __init__/conftest move with it)
tests/cli -> tests/hermes_cli (prompt_toolkit fixture merged into
hermes_cli/conftest.py)
tests/run_agent -> tests/agent (backoff fixture becomes
agent/conftest.py)
tests/relay -> tests/gateway/relay
tests/state -> tests/hermes_state
246 loose files at tests/ root, routed by the package they import/patch:
hermes_cli, hermes_state, agent, gateway, tools, plugins, tui_gateway, cron.
Installer and desktop-update script tests go to tests/scripts/{install,
desktop_update}/. 43 tests of root-level modules (batch_runner, utils,
hermes_constants, packaging) stay at the root.
Filenames drop their issue numbers (95 files: test_89315_x.py -> test_x.py);
the number stays in the module docstring where it has context.
Collisions: test_cli_skin_integration.py existed in both tests/ and tests/cli
with different subsets — merged into one (10 tests, all kept);
run_agent/test_pre_compress_memory_context.py -> agent/..._handoff.py;
tests/test_account_usage.py -> agent/test_account_usage_fetch.py;
tests/test_web_server.py -> hermes_cli/test_web_server_ws_ping.py.
Deleted: test_minisweagent_path.py (empty since PR #2804),
test_model_picker_scroll.py (tested a private copy of the logic, imported
nothing), test_process_loop_event_loop_warning.py (asserted asyncio behaviour,
imported nothing from Hermes).
Repo-root path arithmetic (Path(__file__).parents[N], dirname chains) is
bumped for the 202 files that changed depth and verified by evaluating every
such expression against the new location. classify_changes' desktop-updater
lane prefix, tests-os.yml's ignore glob and every in-tree path comment follow
the moves. tests/test_tests_tree_layout.py keeps the tree from drifting back.
124 lines
3.3 KiB
Python
124 lines
3.3 KiB
Python
"""Tests for ACP pre-edit approval gating."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import tempfile
|
|
from pathlib import Path
|
|
|
|
from acp_adapter.edit_approval import (
|
|
EditProposal,
|
|
build_acp_edit_tool_call,
|
|
set_edit_approval_requester,
|
|
should_auto_approve_edit,
|
|
)
|
|
from model_tools import handle_function_call
|
|
|
|
|
|
def teardown_function() -> None:
|
|
set_edit_approval_requester(None)
|
|
|
|
|
|
def test_acp_permission_tool_call_uses_edit_kind_and_diff_content():
|
|
proposal = EditProposal(
|
|
tool_name="write_file",
|
|
path="demo.txt",
|
|
old_text="old\n",
|
|
new_text="new\n",
|
|
arguments={"path": "demo.txt", "content": "new\n"},
|
|
)
|
|
|
|
tool_call = build_acp_edit_tool_call(proposal)
|
|
|
|
assert tool_call.kind == "edit"
|
|
assert tool_call.status == "pending"
|
|
assert tool_call.rawInput == {"tool": "write_file", "arguments": proposal.arguments}
|
|
assert len(tool_call.content) == 1
|
|
diff = tool_call.content[0]
|
|
assert diff.path == "demo.txt"
|
|
assert diff.oldText == "old\n"
|
|
assert diff.newText == "new\n"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_requester_exception_denies_and_does_not_mutate(tmp_path):
|
|
target = tmp_path / "sample.txt"
|
|
target.write_text("before\n", encoding="utf-8")
|
|
|
|
def boom(_proposal):
|
|
raise RuntimeError("zed disconnected")
|
|
|
|
set_edit_approval_requester(boom)
|
|
|
|
result = json.loads(
|
|
handle_function_call(
|
|
"write_file",
|
|
{"path": str(target), "content": "after\n"},
|
|
task_id="acp-edit-exception",
|
|
)
|
|
)
|
|
|
|
assert "error" in result
|
|
assert "Edit approval denied" in result["error"]
|
|
assert target.read_text(encoding="utf-8") == "before\n"
|
|
|
|
|
|
def test_patch_replace_rejection_does_not_mutate(tmp_path):
|
|
target = tmp_path / "sample.txt"
|
|
target.write_text("alpha\nbeta\n", encoding="utf-8")
|
|
|
|
set_edit_approval_requester(lambda _proposal: False)
|
|
|
|
result = json.loads(
|
|
handle_function_call(
|
|
"patch",
|
|
{
|
|
"mode": "replace",
|
|
"path": str(target),
|
|
"old_string": "beta\n",
|
|
"new_string": "gamma\n",
|
|
},
|
|
task_id="acp-patch-reject",
|
|
)
|
|
)
|
|
|
|
assert "error" in result
|
|
assert "Edit approval denied" in result["error"]
|
|
assert target.read_text(encoding="utf-8") == "alpha\nbeta\n"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_workspace_auto_approval_allows_workspace_and_tmp_but_not_sensitive(tmp_path):
|
|
workspace_file = tmp_path / "src.py"
|
|
# Use tempfile.gettempdir() so this test exercises the same code path on
|
|
# Linux (`/tmp`), macOS (`/private/var/folders/...`) and Windows
|
|
# (`%LOCALAPPDATA%\Temp`). Before the fix this branch only worked on Linux.
|
|
tmp_file = Path(tempfile.gettempdir()) / "hermes-acp-auto-approve-test.txt"
|
|
env_file = tmp_path / ".env"
|
|
|
|
assert should_auto_approve_edit(
|
|
EditProposal("write_file", str(workspace_file), None, "x", {}),
|
|
"workspace_session",
|
|
str(tmp_path),
|
|
)
|
|
assert should_auto_approve_edit(
|
|
EditProposal("write_file", str(tmp_file), None, "x", {}),
|
|
"workspace_session",
|
|
str(tmp_path),
|
|
)
|
|
assert not should_auto_approve_edit(
|
|
EditProposal("write_file", str(env_file), None, "SECRET=x", {}),
|
|
"session",
|
|
str(tmp_path),
|
|
)
|