Files
skills/tests/test_hub_voice_model.py
T
Kevin Veen-BirkenbachandClaude Opus 5.5 a438a2f54e feat(orchestrator): speak into every text field of the hub (requirement 013)
Requirement 013 and its implementation: page-mic.js puts a microphone on every textarea and text input, records with MediaRecorder and inserts the transcript at the cursor; Escape cancels. /api/stt transcribes with the local whisper.cpp model ggml-small-q8_0 (pinned to commit 5359861c and its sha256) in a per-request temp dir, capped at 60 s and 5 MiB, and returns German or English only, retranscribing a clip detected as another language in both and keeping the surer one. Without a model the button is disabled and names the install row. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).

🎯 Fix: 72 %
💥 Break: 12 %
💸 Tokens: –
⏱️ Velocity: –
🛡️ Security: 100 %
🏆 Score: 63
🚦 Gate: ⛔ fix 72 % < 90, break 12 % > 5

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-14 21:37:26 +00:00

37 lines
1.5 KiB
Python

from __future__ import annotations
import dataclasses
import json
import os
import unittest
from pathlib import Path
from unittest import mock
from hub_case import HubCase
from test_hub_voice_input import FIXTURES, spoken
WHISPER = Path(os.environ.get("KVB_WHISPER_CLI", "/nonexistent/whisper-cli"))
MODEL = Path(os.environ.get("KVB_WHISPER_MODEL", "/nonexistent/ggml-small-q8_0.bin"))
QUEUED = os.environ.get("KVB_VOICE_INTEGRATION") == "1"
READY = os.access(WHISPER, os.X_OK) and MODEL.is_file()
REASON = (
"real Whisper run: needs KVB_WHISPER_CLI and KVB_WHISPER_MODEL from the operator rows of requirement 013 "
"and KVB_VOICE_INTEGRATION=1, which only the queue.py hold command line sets"
)
@unittest.skipUnless(QUEUED and READY, REASON)
class TestVoiceModel(HubCase):
def test_the_real_model_transcribes_the_german_and_the_english_fixture(self):
speech = self.httpd.hub.speech
with mock.patch.object(speech, "engines", dataclasses.replace(speech.engines, whisper=WHISPER, whisper_model=MODEL)):
for name, words in (("hallo-welt.wav", "hallo welt"), ("hello-world.wav", "hello world")):
with self.subTest(name=name):
status, _, body = self.call("POST", "/api/stt", (FIXTURES / name).read_bytes(), {**self.guard(self.host), "Content-Type": "audio/wav"})
self.assertEqual(status, 200, body)
self.assertEqual(spoken(json.loads(body)["text"]), words)
if __name__ == "__main__":
unittest.main()