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.
98 lines
3.2 KiB
Python
98 lines
3.2 KiB
Python
"""Malformed model tool arguments are rejected at the dispatch boundary."""
|
|
|
|
import json
|
|
from types import SimpleNamespace
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
import pytest
|
|
|
|
from run_agent import AIAgent
|
|
|
|
|
|
def _make_agent() -> AIAgent:
|
|
tool_defs = [
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "web_search",
|
|
"description": "search",
|
|
"parameters": {"type": "object", "properties": {}},
|
|
},
|
|
}
|
|
]
|
|
with (
|
|
patch("model_tools.get_tool_definitions", return_value=tool_defs),
|
|
patch("model_tools.check_toolset_requirements", return_value={}),
|
|
patch("hermes_cli.config.load_config", return_value={}),
|
|
patch("agent.process_bootstrap.OpenAI"),
|
|
):
|
|
agent = AIAgent(
|
|
api_key="test-key-1234567890",
|
|
base_url="https://openrouter.ai/api/v1",
|
|
quiet_mode=True,
|
|
skip_context_files=True,
|
|
skip_memory=True,
|
|
)
|
|
agent.client = MagicMock()
|
|
agent._flush_messages_to_session_db = MagicMock()
|
|
return agent
|
|
|
|
|
|
def _tool_call(call_id: str, arguments: str):
|
|
return SimpleNamespace(
|
|
id=call_id,
|
|
type="function",
|
|
function=SimpleNamespace(name="web_search", arguments=arguments),
|
|
)
|
|
|
|
|
|
@pytest.mark.parametrize("dispatch_mode", ["sequential", "concurrent"])
|
|
@pytest.mark.parametrize(
|
|
"bad_arguments",
|
|
[
|
|
pytest.param("not-json", id="malformed-json"),
|
|
pytest.param('"scalar"', id="scalar"),
|
|
pytest.param("[]", id="list"),
|
|
pytest.param("", id="empty"),
|
|
pytest.param('{"query": "cut off', id="truncated"),
|
|
],
|
|
)
|
|
def test_malformed_arguments_are_rejected_without_blocking_valid_sibling(
|
|
dispatch_mode: str,
|
|
bad_arguments: str,
|
|
):
|
|
agent = _make_agent()
|
|
assistant_message = SimpleNamespace(
|
|
content="",
|
|
tool_calls=[
|
|
_tool_call("call-bad", bad_arguments),
|
|
_tool_call("call-good", '{"query": "valid"}'),
|
|
],
|
|
)
|
|
messages = []
|
|
executed = []
|
|
|
|
def fake_dispatch(name, args, task_id, *positional, **kwargs):
|
|
call_id = kwargs.get("tool_call_id") or (positional[0] if positional else None)
|
|
executed.append((name, args, call_id))
|
|
return json.dumps({"ok": args["query"]})
|
|
|
|
with (
|
|
patch("model_tools.handle_function_call", side_effect=fake_dispatch),
|
|
patch.object(agent, "_invoke_tool", side_effect=fake_dispatch),
|
|
patch(
|
|
"agent.tool_executor.maybe_persist_tool_result",
|
|
side_effect=lambda **kwargs: kwargs["content"],
|
|
),
|
|
):
|
|
execute = getattr(agent, f"_execute_tool_calls_{dispatch_mode}")
|
|
execute(assistant_message, messages, "task-1")
|
|
|
|
assert executed == [("web_search", {"query": "valid"}, "call-good")]
|
|
assert [message["tool_call_id"] for message in messages] == ["call-bad", "call-good"]
|
|
assert len([message for message in messages if message["tool_call_id"] == "call-bad"]) == 1
|
|
|
|
assert '"error": "Invalid tool arguments"' in messages[0]["content"]
|
|
assert "JSON object" in messages[0]["content"]
|
|
assert json.loads(messages[1]["content"]) == {"ok": "valid"}
|