fix(llm): STT prompt that keeps unclear speech; reasoning off (~60 s → ~3 s)

Live check on synthetic speech (espeak) via OpenRouter gemini-2.5-flash: 3–5 s per clip, silence → no speech. Refs #116 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 11:29:40 +03:00
parent 7443b61974
commit d700608825
3 changed files with 6 additions and 3 deletions
@@ -66,6 +66,7 @@ async def test_openrouter_sends_audio_and_returns_transcript() -> None:
    assert await stt.transcribe(audio) == "Сегодня плохо спал."
    body = sent[0]
    assert body["model"] == "google/gemini-2.5-flash" and body["temperature"] == 0
+    assert body["reasoning"] == {"enabled": False}
    part = body["messages"][1]["content"][1]
    assert part["type"] == "input_audio" and part["input_audio"]["format"] == "wav"
    assert base64.b64decode(part["input_audio"]["data"]) == audio