d1152d797c
xAI's /v1/stt now answers HTTP 400 "Field 'language' is required when 'format' is true", so every transcription with stt.language "" (auto-detect) failed on both the server path and the Desktop client-direct path. Send the inverse-text-normalization flag only when a language is resolved; the model field is still always named. Comments updated: the server default moved from grok-voice-transcribe-1.0 to 2.0 between Sep 17 and Sep 21, so the pin is about determinism and a 1.0 rollback knob, not about escaping a 1.0 default. Live: auto-detect on origin/main -> HTTP 400; with this change -> transcript returned for 2.0 and pinned 1.0; language=en still sends format=true. (cherry picked from commit 1ff4887819a12a5e37e9cbea7f31b5cc6b040857)
103 lines
3.6 KiB
Python
103 lines
3.6 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')"
|
|
# /v1/stt returns HTTP 400 for format=true without a language, so auto-detect drops it.
|
|
assert "format" not in (captured["data"] or {}), \
|
|
"format=true must not be sent without a language (xAI rejects it with HTTP 400)"
|
|
|
|
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"
|