mirror of
https://github.com/hanzoai/insights.git
synced 2026-11-03 00:52:32 +00:00
zeekay
19fdf55ceb
A key now opens with what it is allowed to touch. `pk-` is publishable and safe in a browser; `sk-` is secret and never leaves a server. The five marks it replaces all began `ph` -- the upstream's initials -- and they were the last of its brand a customer read back to us, in every SDK snippet. No word rule could reach them, because `ph` is not a word. The marks were also not telling the truth. The constant said `phc_` while every live project token said `hi_`, so the middleware that routes on the constant matched no real token at all. Two spellings existed and one was fiction. Minting now happens in exactly one function and reading in exactly one, so a second spelling has nowhere to live. `phx_` (personal) and `phs_` (project secret) both become `sk-`. The mark now says only that a value is secret; which store holds it is settled by asking. That was already how personal keys worked -- keys minted before the marks carry none, so the store always decided -- and both secret resolvers already returned None on a miss and fell through, so one shared extractor replaces the two that could drift apart. OAuth's access and refresh tokens stay distinguishable as `at-` and `rt-`, because the parser tells them apart before either is looked up, and the domain-verification token becomes `vt-` rather than keeping a sixth mint of its own. `bin/debrand --check` now refuses the marks as a shape, so a seventh cannot be coined. Two rules that were about to rename things that are not ours to spell are bounded: `Lemon` no longer eats `LemonSqueezy`, and the `hog_flow` rules no longer reach a Postgres table, a Datastore table or a route. Keys are stored hashed, so a mark cannot be rewritten in place: the three live project tokens have to be reminted.
112 lines
4.0 KiB
Python
112 lines
4.0 KiB
Python
"""
|
|
Integration tests for audio transcription using the OpenAI SDK through the gateway.
|
|
|
|
Skipped unless OPENAI_API_KEY is set and audio samples exist.
|
|
Run with: pytest tests/integration/test_openai_transcription.py -v
|
|
|
|
Add audio files to tests/integration/audio_samples/ to run these tests.
|
|
"""
|
|
|
|
import os
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
from openai import NotFoundError, OpenAI
|
|
|
|
OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY")
|
|
AUDIO_SAMPLES_DIR = Path(__file__).parent / "audio_samples"
|
|
AUDIO_EXTENSIONS = {".mp3", ".m4a", ".wav", ".webm", ".mp4", ".mpeg", ".mpga", ".oga", ".ogg", ".flac"}
|
|
|
|
skip_without_openai_key = pytest.mark.skipif(not OPENAI_API_KEY, reason="OPENAI_API_KEY not set")
|
|
pytestmark = pytest.mark.xfail(strict=False, reason="OpenAI may be rate-limited or temporarily unavailable")
|
|
|
|
|
|
@pytest.fixture
|
|
def audio_file() -> Path:
|
|
"""Get an audio file from audio_samples, skip if none exist."""
|
|
if not AUDIO_SAMPLES_DIR.exists():
|
|
pytest.skip("audio_samples directory not found")
|
|
files = [f for f in AUDIO_SAMPLES_DIR.iterdir() if f.suffix.lower() in AUDIO_EXTENSIONS]
|
|
if not files:
|
|
pytest.skip("No audio files found in tests/integration/audio_samples/")
|
|
return files[0]
|
|
|
|
|
|
@skip_without_openai_key
|
|
class TestOpenAIAudioTranscription:
|
|
def test_basic_transcription(self, openai_client: OpenAI, audio_file: Path):
|
|
with open(audio_file, "rb") as f:
|
|
response = openai_client.audio.transcriptions.create(
|
|
model="whisper-1",
|
|
file=f,
|
|
)
|
|
|
|
assert response is not None
|
|
assert response.text is not None
|
|
assert len(response.text) > 0
|
|
|
|
def test_transcription_with_language_hint(self, openai_client: OpenAI, audio_file: Path):
|
|
with open(audio_file, "rb") as f:
|
|
response = openai_client.audio.transcriptions.create(
|
|
model="whisper-1",
|
|
file=f,
|
|
language="en",
|
|
)
|
|
|
|
assert response is not None
|
|
assert response.text is not None
|
|
|
|
def test_transcription_with_product_route(self, gateway_url: str, audio_file: Path):
|
|
client = OpenAI(
|
|
api_key="sk-fake_personal_api_key",
|
|
base_url=f"{gateway_url}/llm_gateway/v1",
|
|
)
|
|
|
|
with open(audio_file, "rb") as f:
|
|
response = client.audio.transcriptions.create(
|
|
model="whisper-1",
|
|
file=f,
|
|
)
|
|
|
|
assert response is not None
|
|
assert response.text is not None
|
|
|
|
def test_response_is_text(self, openai_client: OpenAI, audio_file: Path):
|
|
with open(audio_file, "rb") as f:
|
|
response = openai_client.audio.transcriptions.create(
|
|
model="whisper-1",
|
|
file=f,
|
|
)
|
|
|
|
assert isinstance(response.text, str)
|
|
assert len(response.text.strip()) > 0
|
|
|
|
def test_sequential_transcriptions(self, openai_client: OpenAI, audio_file: Path):
|
|
with open(audio_file, "rb") as f:
|
|
response1 = openai_client.audio.transcriptions.create(model="whisper-1", file=f)
|
|
|
|
with open(audio_file, "rb") as f:
|
|
response2 = openai_client.audio.transcriptions.create(model="whisper-1", file=f)
|
|
|
|
assert response1.text is not None
|
|
assert response2.text is not None
|
|
|
|
@pytest.mark.parametrize("model", ["whisper-1", "gpt-4o-transcribe"])
|
|
def test_transcription_models(self, openai_client: OpenAI, audio_file: Path, model: str):
|
|
with open(audio_file, "rb") as f:
|
|
response = openai_client.audio.transcriptions.create(
|
|
model=model,
|
|
file=f,
|
|
)
|
|
|
|
assert response is not None
|
|
assert response.text is not None
|
|
|
|
def test_invalid_model_rejected(self, openai_client: OpenAI, audio_file: Path):
|
|
with open(audio_file, "rb") as f:
|
|
with pytest.raises(NotFoundError):
|
|
openai_client.audio.transcriptions.create(
|
|
model="invalid-model-name",
|
|
file=f,
|
|
)
|