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.
79 lines
2.4 KiB
Python
79 lines
2.4 KiB
Python
import json
|
|
from types import SimpleNamespace
|
|
|
|
|
|
def _tool_call(name: str, arguments):
|
|
return SimpleNamespace(
|
|
id="call_1",
|
|
type="function",
|
|
function=SimpleNamespace(name=name, arguments=arguments),
|
|
)
|
|
|
|
|
|
def _response_with_tool_call(arguments):
|
|
assistant = SimpleNamespace(
|
|
content=None,
|
|
reasoning=None,
|
|
tool_calls=[_tool_call("read_file", arguments)],
|
|
)
|
|
choice = SimpleNamespace(message=assistant, finish_reason="tool_calls")
|
|
return SimpleNamespace(choices=[choice], usage=None)
|
|
|
|
|
|
class _FakeChatCompletions:
|
|
def __init__(self):
|
|
self.calls = 0
|
|
|
|
def create(self, **kwargs):
|
|
self.calls += 1
|
|
if self.calls == 1:
|
|
return _response_with_tool_call({"path": "README.md"})
|
|
return SimpleNamespace(
|
|
choices=[
|
|
SimpleNamespace(
|
|
message=SimpleNamespace(content="done", reasoning=None, tool_calls=[]),
|
|
finish_reason="stop",
|
|
)
|
|
],
|
|
usage=None,
|
|
)
|
|
|
|
|
|
class _FakeClient:
|
|
def __init__(self):
|
|
self.chat = SimpleNamespace(completions=_FakeChatCompletions())
|
|
|
|
|
|
def test_tool_call_validation_accepts_dict_arguments(monkeypatch):
|
|
from run_agent import AIAgent
|
|
|
|
monkeypatch.setattr("agent.process_bootstrap.OpenAI", lambda **kwargs: _FakeClient())
|
|
monkeypatch.setattr(
|
|
"model_tools.get_tool_definitions",
|
|
lambda *args, **kwargs: [{"function": {"name": "read_file"}}],
|
|
)
|
|
monkeypatch.setattr(
|
|
"model_tools.handle_function_call",
|
|
lambda name, args, task_id=None, **kwargs: json.dumps({"ok": True, "args": args}),
|
|
)
|
|
|
|
agent = AIAgent(
|
|
model="test-model",
|
|
api_key="test-key",
|
|
base_url="http://localhost:8080/v1",
|
|
platform="cli",
|
|
max_iterations=3,
|
|
quiet_mode=True,
|
|
skip_memory=True,
|
|
)
|
|
agent._disable_streaming = True
|
|
|
|
result = agent.run_conversation("read the file")
|
|
|
|
# The conversation hits max_iterations=3 (3 tool turns then forced summary).
|
|
# PR #34470 adds an explainer suffix to abnormal turn endings so users
|
|
# understand why the response is short instead of seeing a blank reply.
|
|
# The exact suffix wording is owned by conversation_loop; this test only
|
|
# cares that the model's actual text ('done') survives at the start.
|
|
assert result["final_response"].startswith("done")
|