Files
hermes-agent/tests/hermes_cli/test_cli_steer_busy_path.py
T
teknium1 d10bb2ab6f test: make tests/ mirror the source tree; drop issue numbers from filenames
`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.
2026-09-13 09:18:02 -07:00

147 lines
5.8 KiB
Python

"""Regression tests for classic-CLI mid-run /steer dispatch.
Background
----------
/steer sent while the agent is running used to be queued through
``self._pending_input`` alongside ordinary user input. ``process_loop``
pulls from that queue and calls ``process_command()`` — but while the
agent is running, ``process_loop`` is blocked inside ``self.chat()``.
By the time the queued /steer was pulled, ``_agent_running`` had
already flipped back to False, so ``process_command()`` took the idle
fallback (``"No agent running; queued as next turn"``) and delivered
the steer as an ordinary next-turn message.
The fix dispatches /steer inline on the UI thread when the agent is
running — matching the existing pattern for /model — so the steer
reaches ``agent.steer()`` (thread-safe) without touching the queue.
These tests exercise the detector + inline dispatch without starting a
prompt_toolkit app.
"""
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 TestSteerInlineDetector:
"""_should_handle_steer_command_inline gates the busy-path fast dispatch."""
def test_detects_steer_when_agent_running(self):
cli = _make_cli()
cli._agent_running = True
assert cli._should_handle_steer_command_inline("/steer focus on error handling") is True
def test_ignores_steer_when_agent_idle(self):
"""Idle-path /steer should fall through to the normal process_loop
dispatch so the queue-style fallback message is emitted."""
cli = _make_cli()
cli._agent_running = False
assert cli._should_handle_steer_command_inline("/steer do something") is False
def test_ignores_non_slash_input(self):
cli = _make_cli()
cli._agent_running = True
assert cli._should_handle_steer_command_inline("steer without slash") is False
assert cli._should_handle_steer_command_inline("") is False
def test_ignores_other_slash_commands(self):
cli = _make_cli()
cli._agent_running = True
assert cli._should_handle_steer_command_inline("/queue hello") is False
assert cli._should_handle_steer_command_inline("/stop") is False
assert cli._should_handle_steer_command_inline("/help") is False
def test_ignores_steer_with_attached_images(self):
"""Image payloads take the normal path; steer doesn't accept images."""
cli = _make_cli()
cli._agent_running = True
assert cli._should_handle_steer_command_inline("/steer text", has_images=True) is False
class TestSteerBusyPathDispatch:
"""When the detector fires, process_command('/steer ...') must call
agent.steer() directly rather than the idle-path fallback."""
def test_process_command_routes_to_agent_steer(self):
"""With _agent_running=True and agent.steer present, /steer reaches
agent.steer(payload), NOT _pending_input."""
cli = _make_cli()
cli._agent_running = True
cli.agent = MagicMock()
cli.agent.steer = MagicMock(return_value=True)
# Make sure the idle-path fallback would be observable if taken
cli._pending_input = MagicMock()
cli.process_command("/steer focus on errors")
cli.agent.steer.assert_called_once_with("focus on errors")
cli._pending_input.put.assert_not_called()
def test_idle_path_queues_as_next_turn(self):
"""Control — when the agent is NOT running, /steer correctly falls
back to next-turn queue semantics. Demonstrates why the fix was
needed: the queue path only works when you can actually drain it."""
cli = _make_cli()
cli._agent_running = False
cli.agent = MagicMock()
cli.agent.steer = MagicMock(return_value=True)
cli._pending_input = MagicMock()
cli.process_command("/steer would-be-next-turn")
# Idle path does NOT call agent.steer
cli.agent.steer.assert_not_called()
# It puts the payload in the queue as a normal next-turn message
cli._pending_input.put.assert_called_once_with("would-be-next-turn")
if __name__ == "__main__": # pragma: no cover
import pytest
pytest.main([__file__, "-v"])