mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
39975613b1
Second, deeper pass over tools/gateway/hermes_cli plus first pass over the trees wave 1 missed (acp, acp_adapter, skills, computer_use, docker, dashboard, conformance, monitoring, secret_sources, hermes_state, providers). Same rubric as wave 1 (AGENTS.md test policy); security, alternation/caching invariants, issue-number regressions, and E2E kept. Real test-quality fixes found and rooted out along the way: - tests/tools/test_command_guards.py made real auxiliary-LLM HTTPS calls (DEFAULT_CONFIG smart-approval leaked in) — pinned approval mode=manual via autouse fixture: 17.4s → 0.4s. - test_model_switch_custom_providers.py / test_user_providers_model_switch.py silently probed live provider catalogs (~2s/test) — stubbed cached_provider_model_ids/provider_model_ids/fetch_api_models. - test_telegram_noise_filter.py: 15-platform copy-paste matrix over shared gateway.run logic → 3 representative platforms (55s → 3.9s). - test_gateway_shutdown.py: stop()'s 5s interrupt-deadline loop spun on MagicMock agents — interrupt.side_effect now clears _running_agents (22s → 1.0s). - test_gateway_inactivity_timeout.py poll-harness timings shrunk 3-5x (24s → 1.1s); test_mcp_stability.py backoff/SIGTERM-grace sleeps patched (15.4s → 2.5s); test_async_delegation.py negative-drain wait 5s → 0.5s. - test_telegram_init_deadline.py: loop-block margin restored to 1.0s with rationale comment — the watchdog-dump assertion needs the loop blocked well past deadline+grace under parallel load (flaked once in the 40-worker verification run at a 0.2s margin). Verification: full hermetic suite via scripts/run_tests.sh — 2,438 files, 21,718 tests passed, 0 failed, 293.9s wall. Suite totals vs original baseline: 46,820 → 19,757 test functions (−57.8%), wall 583.5s → 293.9s (−50%), subprocess CPU 13,564s → 11,623s.
66 lines
1.7 KiB
Python
66 lines
1.7 KiB
Python
"""Regression tests for arrow-key decoding in the curses menus.
|
|
|
|
Root cause these guard against: on many terminals/terminfo entries, cursor
|
|
keys are delivered to ``getch()`` as raw CSI/SS3 escape byte sequences
|
|
(``27, 91, 66`` for arrow-down) even when ``keypad(True)`` is set. The menus
|
|
used to treat the leading ``27`` as ESC/cancel, which dumped the setup wizard's
|
|
provider/model picker into its numbered "Select [1-N]" fallback the instant a
|
|
user pressed up or down.
|
|
"""
|
|
import sys
|
|
|
|
import pytest
|
|
|
|
# curses (and its _curses C extension) is Unix-only; skip the whole module on Windows.
|
|
if sys.platform == "win32":
|
|
pytest.skip("curses is not available on Windows", allow_module_level=True)
|
|
import curses
|
|
|
|
from hermes_cli.curses_ui import (
|
|
NAV_CANCEL,
|
|
NAV_DOWN,
|
|
NAV_NONE,
|
|
NAV_SELECT,
|
|
NAV_UP,
|
|
read_menu_key,
|
|
)
|
|
|
|
|
|
class FakeStdscr:
|
|
"""Minimal stdscr stand-in that replays a queue of getch() byte returns.
|
|
|
|
``getch`` pops from ``keys``; an empty queue yields ``-1`` (matching curses
|
|
non-blocking behavior). ``timeout`` is recorded but otherwise inert.
|
|
"""
|
|
|
|
def __init__(self, keys):
|
|
self.keys = list(keys)
|
|
self.timeouts = []
|
|
|
|
def getch(self):
|
|
return self.keys.pop(0) if self.keys else -1
|
|
|
|
def timeout(self, ms):
|
|
self.timeouts.append(ms)
|
|
|
|
|
|
|
|
|
|
def test_raw_ss3_arrow_keys_decode():
|
|
# Application cursor mode: ESC O B / ESC O A
|
|
assert read_menu_key(FakeStdscr([27, ord("O"), ord("B")])) == NAV_DOWN
|
|
assert read_menu_key(FakeStdscr([27, ord("O"), ord("A")])) == NAV_UP
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_enter_variants_select():
|
|
assert read_menu_key(FakeStdscr([10])) == NAV_SELECT
|
|
assert read_menu_key(FakeStdscr([13])) == NAV_SELECT
|
|
assert read_menu_key(FakeStdscr([curses.KEY_ENTER])) == NAV_SELECT
|
|
|
|
|
|
|
|
|