mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +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.
43 lines
1.4 KiB
Python
43 lines
1.4 KiB
Python
"""Tests for Unicode dash normalization in /insights command flag parsing.
|
|
|
|
Telegram on iOS auto-converts -- to em/en dashes. The /insights handler
|
|
normalizes these before parsing --days and --source flags.
|
|
"""
|
|
import re
|
|
import pytest
|
|
|
|
|
|
# The regex from gateway/run.py insights handler
|
|
_UNICODE_DASH_RE = re.compile(r'[\u2012\u2013\u2014\u2015](days|source)')
|
|
|
|
|
|
def _normalize_insights_args(raw: str) -> str:
|
|
"""Apply the same normalization as the /insights handler."""
|
|
return _UNICODE_DASH_RE.sub(r'--\1', raw)
|
|
|
|
|
|
class TestInsightsUnicodeDashFlags:
|
|
"""--days and --source must survive iOS Unicode dash conversion."""
|
|
|
|
@pytest.mark.parametrize("input_str,expected", [
|
|
# Standard double hyphen (baseline)
|
|
("--days 7", "--days 7"),
|
|
("--source telegram", "--source telegram"),
|
|
# Em dash (U+2014)
|
|
("\u2014days 7", "--days 7"),
|
|
("\u2014source telegram", "--source telegram"),
|
|
# En dash (U+2013)
|
|
("\u2013days 7", "--days 7"),
|
|
("\u2013source telegram", "--source telegram"),
|
|
# Figure dash (U+2012)
|
|
("\u2012days 7", "--days 7"),
|
|
# Horizontal bar (U+2015)
|
|
("\u2015days 7", "--days 7"),
|
|
# Combined flags with em dashes
|
|
("\u2014days 30 \u2014source cli", "--days 30 --source cli"),
|
|
])
|
|
def test_unicode_dash_normalized(self, input_str, expected):
|
|
result = _normalize_insights_args(input_str)
|
|
assert result == expected
|
|
|
|
|