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.
46 lines
1.6 KiB
Python
46 lines
1.6 KiB
Python
"""Test that tool_name is correctly persisted to the session DB for tool-result messages.
|
|
|
|
make_tool_result_message() sets tool_name on every tool-result dict at construction
|
|
time. This test verifies that the value survives the flush path into the session DB.
|
|
"""
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
from run_agent import AIAgent
|
|
from agent.tool_dispatch_helpers import make_tool_result_message
|
|
|
|
|
|
def _make_agent(session_db):
|
|
with (
|
|
patch("model_tools.get_tool_definitions", return_value=[]),
|
|
patch("model_tools.check_toolset_requirements", return_value={}),
|
|
patch("agent.process_bootstrap.OpenAI"),
|
|
):
|
|
return 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,
|
|
)
|
|
|
|
|
|
def test_tool_name_persisted_to_session_db():
|
|
"""tool_name set by make_tool_result_message must be passed through to
|
|
the batched flush so the column is populated on first write to the
|
|
session DB."""
|
|
session_db = MagicMock()
|
|
agent = _make_agent(session_db)
|
|
|
|
messages = [
|
|
{"role": "user", "content": "run a command"},
|
|
make_tool_result_message("terminal", "$ ls\nfile.txt", "c1"),
|
|
]
|
|
agent._flush_messages_to_session_db(messages)
|
|
|
|
assert session_db.append_messages_batch.call_count == 1
|
|
batch = session_db.append_messages_batch.call_args.kwargs["messages"]
|
|
tool_rows = [m for m in batch if m.get("role") == "tool"]
|
|
assert len(tool_rows) == 1
|
|
assert tool_rows[0]["tool_name"] == "terminal"
|