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>
This commit is contained in:
Kevin Veen-BirkenbachandClaude Opus 5.5 committed 2026-11-14 21:37:26 +00:00
1 parent a2a03995cb
commit a438a2f54e
27 files changed
+861 -149

No files matched your search

+7 -4
View File
@@ -31,13 +31,16 @@ with wave.open(args.output_file, "wb") as out:
"""
FAKE_WHISPER = """
import json, os, sys
argv = sys.argv[1:]
data = sys.stdin.buffer.read()
with open(os.path.join(os.environ["HOME"], "whisper.jsonl"), "a", encoding="utf-8") as log:
log.write(json.dumps({"argv": sys.argv[1:], "sha256": __import__("hashlib").sha256(data).hexdigest()}) + "\\n")
log.write(json.dumps({"argv": argv, "sha256": __import__("hashlib").sha256(data).hexdigest()}) + "\\n")
if b"FAIL" in data:
sys.exit(4)
print(" hello from the [BLANK_AUDIO] mic")
print("second line")
language = argv[argv.index("--language") + 1]
segments = [{"text": " hello from the [BLANK_AUDIO] mic", "tokens": [{"text": "[_BEG_]", "p": 0.1}, {"text": " hello", "p": 0.9}]}, {"text": "second line", "tokens": [{"text": " second", "p": 0.8}]}]
with open(argv[argv.index("--output-file") + 1] + ".json", "w", encoding="utf-8") as out:
json.dump({"result": {"language": "en" if language == "auto" else language}, "transcription": segments}, out)
"""
@@ -53,7 +56,7 @@ def write_engines(base: Path) -> server.Engines:
(voices / f"{model}.onnx").write_bytes(b"onnx")
(voices / f"{model}.onnx.json").write_text(json.dumps(config), encoding="utf-8")
(voices / "broken.onnx").write_bytes(b"onnx")
model = base / "ggml-base.bin"
model = base / "ggml-small-q8_0.bin"
model.write_bytes(b"ggml")
return server.Engines(piper=bin_dir / "piper", voices=voices, operator_voice=OPERATOR_VOICE, whisper=bin_dir / "whisper-cli", whisper_model=model, scratch=scratch, service=server.Service(url="", key=""))