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.
42 lines
2.3 KiB
Python
42 lines
2.3 KiB
Python
import json
|
|
from agent.background_review import summarize_background_review_actions
|
|
from tools.skill_manager_tool import skill_manage
|
|
|
|
|
|
def _messages(args, data):
|
|
return [{"role": "assistant", "tool_calls": [{"id": "skill", "function": {
|
|
"name": "skill_manage", "arguments": json.dumps(args)}}]},
|
|
{"role": "tool", "tool_call_id": "skill", "content": json.dumps(data)}]
|
|
|
|
|
|
def test_applied_skill_operations_notify_with_names(tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
|
name = "notify-contract"
|
|
content = f"---\nname: {name}\ndescription: Use when checking notices. Verify applied writes.\n---\nRead the sample before editing.\n"
|
|
operations = [{"name": name, "action": "create", "content": content},
|
|
{"name": name, "action": "patch", "old_string": "sample", "new_string": "example"},
|
|
{"name": name, "action": "write_file", "file_path": "references/a.md", "file_content": "Check the example."},
|
|
{"name": name, "action": "remove_file", "file_path": "references/a.md"},
|
|
{"name": name, "action": "delete"}]
|
|
for op in operations:
|
|
data = json.loads(skill_manage(action="", name="", operations=[op]))
|
|
assert data["success"], data
|
|
messages = _messages({"operations": [op]}, data)
|
|
for mode in ("on", "verbose"):
|
|
actions = summarize_background_review_actions(messages, [], mode)
|
|
assert actions and all(name in line and "?" not in line for line in actions)
|
|
assert summarize_background_review_actions(messages, [], "off") == []
|
|
assert not (tmp_path / "skills" / name).exists()
|
|
|
|
|
|
def test_unapplied_skill_operations_never_notify():
|
|
args = {"operations": [{"name": "pending", "action": "create"}]}
|
|
for data in (
|
|
{"success": True, "staged": True, "message": "Write staged for approval."},
|
|
{"success": False, "results": [{"success": True, "name": "pending", "action": "create"}]},
|
|
{"success": True, "operations_applied": 0, "results": []},
|
|
{"success": True, "operations_applied": 1, "results": [{"success": False, "name": "pending", "action": "create"}]},
|
|
):
|
|
for mode in ("on", "verbose"):
|
|
assert summarize_background_review_actions(_messages(args, data), [], mode) == []
|