`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.
141 lines
5.3 KiB
Python
141 lines
5.3 KiB
Python
"""Regression tests for classic-CLI mid-run /bg and /btw dispatch.
|
|
|
|
Background
|
|
----------
|
|
``/bg`` (formerly ``/background``) exists to start independent work while
|
|
the current turn keeps running. Typed while the agent was busy it went into
|
|
``self._pending_input`` like ordinary input, and ``process_loop`` is blocked
|
|
inside ``self.chat()`` for the whole run, so the background task only started
|
|
once the foreground turn had finished. That is the one moment it was not
|
|
needed (#75221).
|
|
|
|
``/steer`` had the identical problem and was fixed by dispatching inline on
|
|
the UI thread; the command's own ``CommandDef`` already declares
|
|
``busy_policy="dispatch"``, which the gateway honours and the classic CLI
|
|
never consulted.
|
|
|
|
These tests exercise the detector without starting a prompt_toolkit app,
|
|
mirroring tests/hermes_cli/test_cli_steer_busy_path.py.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import importlib
|
|
import sys
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
|
|
def _make_cli():
|
|
"""Create a HermesCLI instance with prompt_toolkit stubbed out."""
|
|
_clean_config = {
|
|
"model": {
|
|
"default": "anthropic/claude-opus-4.6",
|
|
"base_url": "https://openrouter.ai/api/v1",
|
|
"provider": "auto",
|
|
},
|
|
"display": {"compact": False, "tool_progress": "all"},
|
|
"agent": {},
|
|
"terminal": {"env_type": "local"},
|
|
}
|
|
clean_env = {"LLM_MODEL": "", "HERMES_MAX_ITERATIONS": ""}
|
|
prompt_toolkit_stubs = {
|
|
"prompt_toolkit": MagicMock(),
|
|
"prompt_toolkit.history": MagicMock(),
|
|
"prompt_toolkit.styles": MagicMock(),
|
|
"prompt_toolkit.patch_stdout": MagicMock(),
|
|
"prompt_toolkit.application": MagicMock(),
|
|
"prompt_toolkit.layout": MagicMock(),
|
|
"prompt_toolkit.layout.processors": MagicMock(),
|
|
"prompt_toolkit.filters": MagicMock(),
|
|
"prompt_toolkit.layout.dimension": MagicMock(),
|
|
"prompt_toolkit.layout.menus": MagicMock(),
|
|
"prompt_toolkit.widgets": MagicMock(),
|
|
"prompt_toolkit.key_binding": MagicMock(),
|
|
"prompt_toolkit.completion": MagicMock(),
|
|
"prompt_toolkit.formatted_text": MagicMock(),
|
|
"prompt_toolkit.auto_suggest": MagicMock(),
|
|
}
|
|
with patch.dict(sys.modules, prompt_toolkit_stubs), patch.dict(
|
|
"os.environ", clean_env, clear=False
|
|
):
|
|
import cli as _cli_mod
|
|
|
|
_cli_mod = importlib.reload(_cli_mod)
|
|
with patch.object(_cli_mod, "get_tool_definitions", return_value=[]), patch.dict(
|
|
_cli_mod.__dict__, {"CLI_CONFIG": _clean_config}
|
|
):
|
|
return _cli_mod.HermesCLI()
|
|
|
|
|
|
class TestBackgroundInlineDetector:
|
|
def test_detects_background_when_agent_running(self):
|
|
cli = _make_cli()
|
|
cli._agent_running = True
|
|
assert cli._should_handle_background_command_inline(
|
|
"/bg inspect the test failures"
|
|
) is True
|
|
|
|
def test_detects_both_commands(self):
|
|
cli = _make_cli()
|
|
cli._agent_running = True
|
|
assert cli._should_handle_background_command_inline("/bg do work") is True
|
|
assert cli._should_handle_background_command_inline("/btw do work") is True
|
|
|
|
def test_background_alias_still_resolves_to_bg(self):
|
|
"""The retired /background spelling no longer resolves to a command."""
|
|
cli = _make_cli()
|
|
cli._agent_running = True
|
|
assert cli._should_handle_background_command_inline(
|
|
"/background do work"
|
|
) is False
|
|
|
|
def test_ignores_background_when_agent_idle(self):
|
|
"""Idle input falls through to the normal process_loop dispatch."""
|
|
cli = _make_cli()
|
|
cli._agent_running = False
|
|
assert cli._should_handle_background_command_inline("/bg do work") is False
|
|
|
|
def test_ignores_non_slash_input(self):
|
|
cli = _make_cli()
|
|
cli._agent_running = True
|
|
assert cli._should_handle_background_command_inline("bg without slash") is False
|
|
assert cli._should_handle_background_command_inline("") is False
|
|
|
|
def test_ignores_other_slash_commands(self):
|
|
cli = _make_cli()
|
|
cli._agent_running = True
|
|
assert cli._should_handle_background_command_inline("/steer hello") is False
|
|
assert cli._should_handle_background_command_inline("/queue hello") is False
|
|
assert cli._should_handle_background_command_inline("/stop") is False
|
|
|
|
def test_ignores_background_with_attached_images(self):
|
|
"""Image payloads take the normal path."""
|
|
cli = _make_cli()
|
|
cli._agent_running = True
|
|
assert cli._should_handle_background_command_inline(
|
|
"/bg look at this", has_images=True
|
|
) is False
|
|
|
|
def test_case_and_whitespace_tolerant(self):
|
|
cli = _make_cli()
|
|
cli._agent_running = True
|
|
assert cli._should_handle_background_command_inline("/BG do work") is True
|
|
|
|
|
|
class TestBackgroundBusyPolicyContract:
|
|
"""The registry already declares the intent this detector implements."""
|
|
|
|
def test_bg_and_btw_declare_dispatch_while_busy(self):
|
|
from hermes_cli.commands import resolve_command
|
|
|
|
for name in ("bg", "btw"):
|
|
cmd = resolve_command(name)
|
|
assert cmd is not None
|
|
assert cmd.name == name
|
|
assert cmd.busy_policy == "dispatch"
|
|
|
|
def test_background_name_is_retired(self):
|
|
from hermes_cli.commands import resolve_command
|
|
|
|
assert resolve_command("background") is None
|