generated from john/python-template
Baseline was 207 diagnostics. Two real bugs were hiding in the noise: - tools/run_destructive_tests.py imported ctypes.wintypes at module scope, which raises on non-Windows, and called fcntl unconditionally. The Windows and POSIX implementations now live under a module-level sys.platform split. - tests/ui/test_sources_page.py constructed Source(...) without document_id. Structural fixes, not suppressions: - New src/transcription/db/loading.py owns the SQLModel-field to QueryableAttribute reinterpretation via orm_attribute()/selectinload()/ defer(). This removed 42 "# pyright: ignore[reportArgumentType]" comments across documents/jobs/people/sources. Its docstring records that selectinload(A.b, B.c) is NOT equivalent to the chained form: varargs applies the selectin strategy only to the last path element, which under lazy="raise" raises InvalidRequestError at render time. - db/session.py transaction_scope no longer accepts or yields AsyncSessionTransaction. No caller ever passed one, sessionmaker.begin() yields an AsyncSession, and the dead branch was latently buggy because services call .exec(). Cleared 7 workflows.py diagnostics. - services/registry.py RegistryService is bound by a new RegistryEntry Protocol instead of bare SQLModel, so the shared implementation can read id/label/normalized_label/is_active. Cleared 9 diagnostics. - Column expressions in sources.py/jobs.py/test_store.py wrap in sqlmodel col(), the idiom already used in registry.py. - read_source_navigation wraps its literal tuple bounds in literal(). - normalization.py narrows with isinstance(image, TiffImageFile) rather than comparing image.format, since tag_v2 is TIFF-only. - linked_people.render uses @ui.refreshable_method, the NiceGUI API for bound methods. - The OpenRouter capturing client re-raises ResponseNotRead when the response stream is not async rather than mis-wrapping it. Tooling gate: - New .pre-commit-config.yaml runs ruff check and ty check as blocking hooks. No pre-commit config previously existed. Negative-tested: injecting a type error fails both hooks. - The last two "# pyright: ignore" comments (config.py) are removed; ty does not honor pyright directives. One "# ty: ignore" remains, in tests/test_prompts.py, where the test deliberately assigns to a frozen field to assert ValidationError. - asyncio_default_fixture_loop_scope is pinned to "function" so pytest-asyncio behavior does not shift on upgrade. Verification: ruff check clean, ty check reports 0 diagnostics, 292 passed and 4 skipped, pre-commit passes and demonstrably fails on a regression, and tools/run_destructive_tests.py runs on Windows. Co-authored-by: Copilot App <[email protected]>
229 lines
8.7 KiB
Python
229 lines
8.7 KiB
Python
"""Tests for transcription.providers.openrouter."""
|
|
|
|
import asyncio
|
|
from types import SimpleNamespace
|
|
from typing import cast
|
|
|
|
import pytest
|
|
from openrouter import OpenRouter
|
|
|
|
from transcription.config import Settings
|
|
from transcription.providers.base import ProviderError
|
|
from transcription.providers.base import ProviderResponseError
|
|
from transcription.providers.openrouter import DEFAULT_OPENROUTER_MODEL
|
|
from transcription.providers.openrouter import OpenRouterTranscriptionProvider
|
|
|
|
|
|
class _FakeChat:
|
|
def __init__(self, response=None, error: BaseException | None = None):
|
|
self._response = response
|
|
self._error = error
|
|
self.calls = []
|
|
|
|
async def send_async(self, **kwargs):
|
|
self.calls.append(kwargs)
|
|
if self._error:
|
|
raise self._error
|
|
return self._response
|
|
|
|
|
|
class _FakeClient:
|
|
def __init__(self, response=None, error: BaseException | None = None):
|
|
self.chat = _FakeChat(response=response, error=error)
|
|
|
|
|
|
def _fake_client(response=None, error: BaseException | None = None) -> OpenRouter:
|
|
"""Return a stub typed as the SDK client the provider declares."""
|
|
return cast("OpenRouter", _FakeClient(response=response, error=error))
|
|
|
|
|
|
@pytest.mark.unit
|
|
class TestOpenRouterProviderInit:
|
|
"""Verify OpenRouter provider initialization behavior."""
|
|
|
|
def test_model_falls_back_to_default_when_unset(self):
|
|
"""Provider uses adapter default model when provider_model is None."""
|
|
settings = Settings(openrouter_api_key="test-key", provider_model=None)
|
|
provider = OpenRouterTranscriptionProvider(settings=settings, client=_fake_client())
|
|
assert provider.model == DEFAULT_OPENROUTER_MODEL
|
|
|
|
def test_model_uses_configured_value(self):
|
|
"""Provider uses configured provider_model when present."""
|
|
settings = Settings(openrouter_api_key="test-key", provider_model="vendor/custom-model")
|
|
provider = OpenRouterTranscriptionProvider(settings=settings, client=_fake_client())
|
|
assert provider.model == "vendor/custom-model"
|
|
|
|
|
|
@pytest.mark.unit
|
|
class TestOpenRouterProviderTranscribe:
|
|
"""Verify OpenRouter request construction and response parsing."""
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_includes_optional_referer_and_title_when_set(self):
|
|
"""Transcribe sends app attribution fields when configured."""
|
|
response = {"model": "vendor/model-a", "choices": [{"message": {"content": "Transcript text"}}]}
|
|
client = _FakeClient(response=response)
|
|
settings = Settings(
|
|
openrouter_api_key="test-key",
|
|
openrouter_http_referer="https://example.test",
|
|
openrouter_app_title="Transcription App",
|
|
)
|
|
provider = OpenRouterTranscriptionProvider(settings=settings, client=cast("OpenRouter", client))
|
|
|
|
result = await provider.transcribe(
|
|
prompt_text="Prompt body",
|
|
image_bytes=b"img-bytes",
|
|
mime_type="image/png",
|
|
)
|
|
|
|
send_call = client.chat.calls[0]
|
|
assert send_call["http_referer"] == "https://example.test"
|
|
assert send_call["x_open_router_title"] == "Transcription App"
|
|
assert result.text == "Transcript text"
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_includes_temperature_and_top_p_when_provided(self):
|
|
"""Transcribe passes configured sampling parameters through to OpenRouter."""
|
|
response = {"model": "vendor/model-a", "choices": [{"message": {"content": "Transcript text"}}]}
|
|
client = _FakeClient(response=response)
|
|
provider = OpenRouterTranscriptionProvider(
|
|
settings=Settings(openrouter_api_key="test-key"),
|
|
client=cast("OpenRouter", client),
|
|
)
|
|
|
|
result = await provider.transcribe(
|
|
prompt_text="Prompt body",
|
|
image_bytes=b"img-bytes",
|
|
mime_type="image/png",
|
|
temperature=0.2,
|
|
top_p=0.85,
|
|
)
|
|
|
|
send_call = client.chat.calls[0]
|
|
assert send_call["temperature"] == 0.2
|
|
assert send_call["top_p"] == 0.85
|
|
assert result.temperature == 0.2
|
|
assert result.top_p == 0.85
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_parses_successful_response_text(self):
|
|
"""Transcribe returns normalized text from a valid response payload."""
|
|
response = {
|
|
"model": "vendor/model-b",
|
|
"choices": [
|
|
{
|
|
"message": {"content": [{"text": "Line 1"}, {"text": "Line 2"}]},
|
|
"finish_reason": "stop",
|
|
}
|
|
],
|
|
"usage": {"prompt_tokens": 10, "completion_tokens": 25, "total_tokens": 35},
|
|
}
|
|
provider = OpenRouterTranscriptionProvider(
|
|
settings=Settings(openrouter_api_key="test-key"),
|
|
client=_fake_client(response=response),
|
|
)
|
|
|
|
result = await provider.transcribe(
|
|
prompt_text="Prompt body",
|
|
image_bytes=b"img-bytes",
|
|
mime_type="image/jpeg",
|
|
)
|
|
|
|
assert result.text == "Line 1\nLine 2"
|
|
assert result.provider == "openrouter"
|
|
assert result.prompt_name is None
|
|
assert result.model == "vendor/model-b"
|
|
assert result.metadata_payload() == {
|
|
"finish_reason": "stop",
|
|
"usage": {"input_tokens": 10, "output_tokens": 25, "total_tokens": 35},
|
|
}
|
|
assert result.raw_api_response == response
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_maps_sdk_exception_to_provider_error(self):
|
|
"""Transcribe converts SDK failures to ProviderError."""
|
|
provider = OpenRouterTranscriptionProvider(
|
|
settings=Settings(openrouter_api_key="test-key"),
|
|
client=_fake_client(error=RuntimeError("network down")),
|
|
)
|
|
|
|
with pytest.raises(ProviderError):
|
|
await provider.transcribe(
|
|
prompt_text="Prompt body",
|
|
image_bytes=b"img-bytes",
|
|
mime_type="image/png",
|
|
)
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_preserves_caller_cancellation(self):
|
|
"""Caller and shutdown cancellation must not be relabeled as a timeout."""
|
|
provider = OpenRouterTranscriptionProvider(
|
|
settings=Settings(openrouter_api_key="test-key"),
|
|
client=_fake_client(error=asyncio.CancelledError()),
|
|
)
|
|
|
|
with pytest.raises(asyncio.CancelledError):
|
|
await provider.transcribe(
|
|
prompt_text="Prompt body",
|
|
image_bytes=b"img-bytes",
|
|
mime_type="image/png",
|
|
)
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_sends_pdf_as_file_content(self):
|
|
"""PDF payloads use OpenRouter's file content contract."""
|
|
response = {"model": "vendor/model-a", "choices": [{"message": {"content": "Transcript text"}}]}
|
|
client = _FakeClient(response=response)
|
|
provider = OpenRouterTranscriptionProvider(
|
|
settings=Settings(openrouter_api_key="test-key"),
|
|
client=cast("OpenRouter", client),
|
|
)
|
|
|
|
await provider.transcribe(
|
|
prompt_text="Prompt body",
|
|
image_bytes=b"pdf-bytes",
|
|
mime_type="application/pdf",
|
|
)
|
|
|
|
content = client.chat.calls[0]["messages"][0]["content"]
|
|
assert content[1]["type"] == "file"
|
|
assert content[1]["file"]["filename"] == "source.pdf"
|
|
assert content[1]["file"]["file_data"].startswith("data:application/pdf;base64,")
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_raises_on_empty_or_invalid_response(self):
|
|
"""Transcribe raises ProviderResponseError for missing completion text."""
|
|
provider = OpenRouterTranscriptionProvider(
|
|
settings=Settings(openrouter_api_key="test-key"),
|
|
client=_fake_client(response=SimpleNamespace(choices=[])),
|
|
)
|
|
|
|
with pytest.raises(ProviderResponseError):
|
|
await provider.transcribe(
|
|
prompt_text="Prompt body",
|
|
image_bytes=b"img-bytes",
|
|
mime_type="image/png",
|
|
)
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_ignores_invalid_token_metadata_without_discarding_transcript(self):
|
|
response = {
|
|
"model": "vendor/model-a",
|
|
"choices": [{"message": {"content": "Transcript text"}}],
|
|
"usage": {"prompt_tokens": -1},
|
|
}
|
|
provider = OpenRouterTranscriptionProvider(
|
|
settings=Settings(openrouter_api_key="test-key"),
|
|
client=_fake_client(response=response),
|
|
)
|
|
|
|
result = await provider.transcribe(
|
|
prompt_text="Prompt body",
|
|
image_bytes=b"img-bytes",
|
|
mime_type="image/png",
|
|
)
|
|
|
|
assert result.text == "Transcript text"
|
|
assert result.metadata_payload() is None
|
|
assert result.raw_api_response == response
|