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.
132 lines
4.1 KiB
Python
132 lines
4.1 KiB
Python
from types import ModuleType, SimpleNamespace
|
|
from unittest.mock import MagicMock, patch
|
|
import json
|
|
import sys
|
|
|
|
from run_agent import AIAgent
|
|
|
|
|
|
def _mock_response(*, usage: dict, content: str = "done"):
|
|
msg = SimpleNamespace(content=content, tool_calls=None)
|
|
choice = SimpleNamespace(message=msg, finish_reason="stop")
|
|
return SimpleNamespace(
|
|
choices=[choice],
|
|
model="test/model",
|
|
usage=SimpleNamespace(**usage),
|
|
)
|
|
|
|
|
|
def _make_agent(session_db, *, platform: str):
|
|
with (
|
|
patch("model_tools.get_tool_definitions", return_value=[]),
|
|
patch("model_tools.check_toolset_requirements", return_value={}),
|
|
patch("agent.process_bootstrap.OpenAI"),
|
|
):
|
|
agent = AIAgent(
|
|
api_key="test-key",
|
|
base_url="https://openrouter.ai/api/v1",
|
|
quiet_mode=True,
|
|
skip_context_files=True,
|
|
skip_memory=True,
|
|
session_db=session_db,
|
|
session_id=f"{platform}-session",
|
|
platform=platform,
|
|
)
|
|
agent.client = MagicMock()
|
|
agent.client.chat.completions.create.return_value = _mock_response(
|
|
usage={
|
|
"prompt_tokens": 11,
|
|
"completion_tokens": 7,
|
|
"total_tokens": 18,
|
|
}
|
|
)
|
|
return agent
|
|
|
|
|
|
def test_run_conversation_persists_tokens_for_telegram_sessions():
|
|
session_db = MagicMock()
|
|
agent = _make_agent(session_db, platform="telegram")
|
|
|
|
result = agent.run_conversation("hello")
|
|
|
|
assert result["final_response"] == "done"
|
|
# Per-call deltas are enqueued for the SessionDB background writer
|
|
# (queue_token_counts) rather than written inline on the turn thread.
|
|
session_db.queue_token_counts.assert_called_once()
|
|
assert session_db.queue_token_counts.call_args.args[0] == "telegram-session"
|
|
|
|
|
|
|
|
|
|
def test_session_search_lazily_opens_db_when_entrypoint_did_not_pass_one(monkeypatch):
|
|
sentinel_db = object()
|
|
captured = {}
|
|
|
|
class FakeSessionDB:
|
|
def __new__(cls):
|
|
return sentinel_db
|
|
|
|
hermes_state = ModuleType("hermes_state")
|
|
hermes_state.SessionDB = FakeSessionDB
|
|
monkeypatch.setitem(sys.modules, "hermes_state", hermes_state)
|
|
hermes_state_registry = ModuleType("hermes_state_registry")
|
|
hermes_state_registry.acquire = lambda db_path=None: sentinel_db
|
|
monkeypatch.setitem(sys.modules, "hermes_state_registry", hermes_state_registry)
|
|
|
|
session_search_mod = ModuleType("tools.session_search_tool")
|
|
|
|
def fake_session_search(**kwargs):
|
|
captured.update(kwargs)
|
|
return json.dumps({"success": True, "results": []})
|
|
|
|
session_search_mod.session_search = fake_session_search
|
|
monkeypatch.setitem(sys.modules, "tools.session_search_tool", session_search_mod)
|
|
|
|
agent = _make_agent(None, platform="acp")
|
|
result = json.loads(agent._invoke_tool(
|
|
"session_search",
|
|
{"query": "Hermes", "detail": "full"},
|
|
"task-id",
|
|
))
|
|
|
|
assert result["success"] is True
|
|
assert captured["db"] is sentinel_db
|
|
assert captured["query"] == "Hermes"
|
|
assert captured["detail"] == "full"
|
|
assert agent._session_db is sentinel_db
|
|
|
|
|
|
def test_sequential_session_search_forwards_detail(monkeypatch):
|
|
session_db = MagicMock()
|
|
captured = {}
|
|
|
|
session_search_mod = ModuleType("tools.session_search_tool")
|
|
|
|
def fake_session_search(**kwargs):
|
|
captured.update(kwargs)
|
|
return json.dumps({"success": True, "results": []})
|
|
|
|
session_search_mod.session_search = fake_session_search
|
|
monkeypatch.setitem(sys.modules, "tools.session_search_tool", session_search_mod)
|
|
|
|
agent = _make_agent(session_db, platform="acp")
|
|
tool_call = SimpleNamespace(
|
|
id="search-1",
|
|
function=SimpleNamespace(
|
|
name="session_search",
|
|
arguments=json.dumps({"query": "Hermes", "detail": "full"}),
|
|
),
|
|
)
|
|
assistant_message = SimpleNamespace(tool_calls=[tool_call])
|
|
messages = []
|
|
|
|
agent._execute_tool_calls_sequential(
|
|
assistant_message,
|
|
messages,
|
|
"task-id",
|
|
)
|
|
|
|
assert captured["db"] is session_db
|
|
assert captured["query"] == "Hermes"
|
|
assert captured["detail"] == "full"
|