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.
99 lines
3.4 KiB
Python
99 lines
3.4 KiB
Python
"""Tests for the unified STT language resolution (_resolve_stt_language).
|
|
|
|
Class-level contract: EVERY provider resolves its language hint through one
|
|
helper with the order:
|
|
|
|
stt.<provider>.language > stt.language (global) > HERMES_LOCAL_STT_LANGUAGE > None
|
|
|
|
Regression coverage for the "STT transcribes the wrong language" issue class
|
|
(#55551, #50181 and siblings):
|
|
- xAI no longer silently forces "en" when nothing is configured
|
|
- the global ``stt.language`` key reaches every provider
|
|
- per-provider language still wins over the global key
|
|
"""
|
|
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
from tools.transcription_tools import _resolve_stt_language
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _clear_lang_env(monkeypatch):
|
|
monkeypatch.delenv("HERMES_LOCAL_STT_LANGUAGE", raising=False)
|
|
|
|
|
|
class TestResolveSttLanguage:
|
|
def test_provider_language_wins(self):
|
|
cfg = {"language": "en", "groq": {"language": "he"}}
|
|
assert _resolve_stt_language("groq", cfg) == "he"
|
|
|
|
def test_global_language_fallback(self):
|
|
cfg = {"language": "hu", "groq": {}}
|
|
assert _resolve_stt_language("groq", cfg) == "hu"
|
|
|
|
|
|
def test_value_is_stripped(self):
|
|
cfg = {"language": " ja "}
|
|
assert _resolve_stt_language("local", cfg) == "ja"
|
|
|
|
|
|
class TestXaiNoForcedEnglish:
|
|
"""xAI previously defaulted language to "en" — auto-detect must be the default."""
|
|
|
|
def test_no_language_sent_by_default(self, tmp_path, monkeypatch):
|
|
import tools.transcription_tools as tt
|
|
audio = tmp_path / "a.ogg"
|
|
audio.write_bytes(b"x")
|
|
captured = {}
|
|
|
|
class _Resp:
|
|
status_code = 200
|
|
|
|
@staticmethod
|
|
def json():
|
|
return {"text": "hola", "language": "es", "duration": 1.0}
|
|
|
|
import requests as _requests
|
|
|
|
def fake_post(url, **kwargs):
|
|
captured["data"] = kwargs.get("data")
|
|
return _Resp()
|
|
|
|
monkeypatch.setattr(_requests, "post", fake_post)
|
|
with patch.object(tt, "_load_stt_config", return_value={}), \
|
|
patch("tools.xai_http.resolve_xai_http_credentials",
|
|
return_value={"api_key": "xai-test", "base_url": "https://api.x.ai/v1"}):
|
|
result = tt._transcribe_xai(str(audio), "grok-stt")
|
|
|
|
assert result["success"] is True
|
|
assert "language" not in (captured["data"] or {}), \
|
|
"xAI must auto-detect when no language is configured (was forced to 'en')"
|
|
|
|
def test_global_language_reaches_xai(self, tmp_path, monkeypatch):
|
|
import tools.transcription_tools as tt
|
|
audio = tmp_path / "a.ogg"
|
|
audio.write_bytes(b"x")
|
|
captured = {}
|
|
|
|
class _Resp:
|
|
status_code = 200
|
|
|
|
@staticmethod
|
|
def json():
|
|
return {"text": "ok", "language": "he", "duration": 1.0}
|
|
|
|
import requests as _requests
|
|
|
|
monkeypatch.setattr(
|
|
_requests, "post",
|
|
lambda url, **kw: captured.update(data=kw.get("data")) or _Resp(),
|
|
)
|
|
with patch.object(tt, "_load_stt_config", return_value={"language": "he"}), \
|
|
patch("tools.xai_http.resolve_xai_http_credentials",
|
|
return_value={"api_key": "xai-test", "base_url": "https://api.x.ai/v1"}):
|
|
result = tt._transcribe_xai(str(audio), "grok-stt")
|
|
|
|
assert result["success"] is True
|
|
assert captured["data"]["language"] == "he"
|