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.
62 lines
1.8 KiB
Python
62 lines
1.8 KiB
Python
"""Tests for the ranked fuzzy scorer used by the searchable curses pickers."""
|
|
from hermes_cli.curses_ui import (
|
|
_SearchState,
|
|
_filter_indices,
|
|
_fuzzy_score,
|
|
_handle_active_search_key,
|
|
_is_boundary,
|
|
_token_score,
|
|
)
|
|
|
|
|
|
class _FakeCurses:
|
|
KEY_BACKSPACE = 263
|
|
KEY_DOWN = 258
|
|
KEY_ENTER = 343
|
|
|
|
|
|
|
|
|
|
def test_scorer_matches_typescript_reference():
|
|
"""Score parity with ui-tui/web fuzzy.ts. These exact values are produced
|
|
by the TS fuzzyScoreMulti for the same inputs (verified via a cross-language
|
|
harness); keep the Python port byte-identical so all three surfaces rank
|
|
consistently. If you change the scoring constants, update the TS copies too.
|
|
"""
|
|
cases = {
|
|
("gpt-4o", "g4o"): 15.94,
|
|
("gpt-4o", "gpt"): 28.94,
|
|
("claude-sonnet-4", "sonnet"): 33.85,
|
|
("claude-sonnet-4", "clad snnt"): 30.70,
|
|
("GptO", "gpto"): 57.96, # camelCase boundary on the original-case 'O'
|
|
}
|
|
for (label, query), expected in cases.items():
|
|
score = _fuzzy_score(label, query)
|
|
assert score is not None
|
|
assert round(score, 2) == expected, f"{label!r}/{query!r}: {score} != {expected}"
|
|
|
|
|
|
|
|
|
|
def test_esc_clears_query_and_signals_changed():
|
|
# Esc during active search clears the filter (restores full list) and
|
|
# signals `changed` so the driver resets scroll/cursor.
|
|
search = _SearchState(active=True, query="gpt")
|
|
handled, confirm, changed = _handle_active_search_key(_FakeCurses, 27, search)
|
|
assert (handled, confirm, changed) == (True, False, True)
|
|
assert search.active is False
|
|
assert search.query == ""
|
|
|
|
# Esc with no query: still stops search, but nothing changed.
|
|
search2 = _SearchState(active=True, query="")
|
|
assert _handle_active_search_key(_FakeCurses, 27, search2) == (True, False, False)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|