generated from john/python-template
V4.6 Phase 7: drive ty check to zero and add a blocking quality gate [HIGH-06]
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]>
This commit is contained in:
@@ -0,0 +1,18 @@
|
||||
# Quality gate for V4.6 [HIGH-06]. Both hooks are blocking: a regression in
|
||||
# `ruff check` or `ty check` fails the commit.
|
||||
repos:
|
||||
- repo: local
|
||||
hooks:
|
||||
- id: ruff
|
||||
name: ruff check
|
||||
entry: ruff check
|
||||
language: system
|
||||
types_or: [python, pyi]
|
||||
require_serial: true
|
||||
- id: ty
|
||||
name: ty check
|
||||
entry: ty check
|
||||
language: system
|
||||
types_or: [python, pyi]
|
||||
pass_filenames: false
|
||||
require_serial: true
|
||||
@@ -41,6 +41,7 @@ dev = [
|
||||
[tool.pytest.ini_options]
|
||||
addopts = "--strict-markers -q"
|
||||
asyncio_mode = "strict"
|
||||
asyncio_default_fixture_loop_scope = "function"
|
||||
filterwarnings = [
|
||||
"error:coroutine .* was never awaited:RuntimeWarning",
|
||||
]
|
||||
|
||||
@@ -172,13 +172,13 @@ class Settings(BaseSettings):
|
||||
@cache
|
||||
def get_settings(**kwargs: Any) -> Settings:
|
||||
"""Load cached settings without reading process CLI arguments."""
|
||||
return Settings(_cli_parse_args=False, **kwargs) # pyright: ignore[reportCallIssue]
|
||||
return Settings(_cli_parse_args=False, **kwargs)
|
||||
|
||||
|
||||
def parse_cli_settings(args: Sequence[str] | None = None) -> Settings:
|
||||
"""Load settings with CLI arguments at the executable boundary."""
|
||||
cli_args = True if args is None else list(args)
|
||||
return Settings(_cli_parse_args=cli_args) # pyright: ignore[reportCallIssue]
|
||||
return Settings(_cli_parse_args=cli_args)
|
||||
|
||||
|
||||
LOGGING_CONFIG: dict[str, Any] = {
|
||||
|
||||
@@ -0,0 +1,45 @@
|
||||
"""Typed loader-option wrappers for SQLModel relationship attributes.
|
||||
|
||||
SQLModel declares relationships with their runtime Python type, so
|
||||
``Document.jobs`` is annotated ``list[Job]`` even though at runtime it is an
|
||||
``InstrumentedAttribute``. SQLAlchemy's loader options are typed against
|
||||
``QueryableAttribute``, so every eager-load call site reads as a type error to a
|
||||
static checker even though the code is correct.
|
||||
|
||||
These wrappers put that reinterpretation in one documented place instead of
|
||||
scattering a suppression comment across every eager-load call. Import
|
||||
``selectinload`` and ``defer`` from here rather than from ``sqlalchemy.orm``.
|
||||
|
||||
Multi-level eager loads must keep using the chained form --
|
||||
``selectinload(A.b).selectinload(orm_attribute(B.c))`` -- and not the varargs
|
||||
form ``selectinload(A.b, B.c)``. The two produce the same loader path, but
|
||||
varargs applies the selectin strategy only to the last element while the
|
||||
intermediate falls back to its default strategy. Every relationship here
|
||||
declares ``lazy="raise"``, so the varargs form raises at render time.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
from typing import cast
|
||||
|
||||
from sqlalchemy.orm import defer as _defer
|
||||
from sqlalchemy.orm import selectinload as _selectinload
|
||||
from sqlalchemy.orm.attributes import QueryableAttribute
|
||||
from sqlalchemy.orm.strategy_options import _AbstractLoad
|
||||
|
||||
|
||||
def orm_attribute(attribute: object) -> QueryableAttribute[Any]:
|
||||
"""Reinterpret a SQLModel relationship or field as its ORM descriptor."""
|
||||
return cast("QueryableAttribute[Any]", attribute)
|
||||
|
||||
|
||||
def selectinload(*keys: object) -> _AbstractLoad:
|
||||
"""``sqlalchemy.orm.selectinload`` accepting SQLModel-annotated attributes."""
|
||||
return _selectinload(*(orm_attribute(key) for key in keys))
|
||||
|
||||
|
||||
def defer(*keys: object, raiseload: bool = False) -> _AbstractLoad:
|
||||
"""``sqlalchemy.orm.defer`` accepting SQLModel-annotated attributes."""
|
||||
first, *rest = (orm_attribute(key) for key in keys)
|
||||
return _defer(first, *rest, raiseload=raiseload)
|
||||
@@ -23,6 +23,7 @@ from sqlalchemy import Uuid
|
||||
from sqlalchemy import inspect as sqlalchemy_inspect
|
||||
from sqlalchemy.dialects.postgresql import JSONB
|
||||
from sqlalchemy.exc import NoInspectionAvailable
|
||||
from sqlalchemy.orm.state import InstanceState
|
||||
from sqlalchemy.types import TypeDecorator
|
||||
from sqlmodel import Field
|
||||
from sqlmodel import Relationship
|
||||
@@ -38,7 +39,7 @@ def _loaded_attribute(instance: object, attribute: str) -> Any | None:
|
||||
without catching exceptions indiscriminately.
|
||||
"""
|
||||
try:
|
||||
state = sqlalchemy_inspect(instance)
|
||||
state: InstanceState[Any] = sqlalchemy_inspect(instance, raiseerr=True)
|
||||
except NoInspectionAvailable:
|
||||
return None
|
||||
if attribute in state.unloaded:
|
||||
|
||||
@@ -3,7 +3,6 @@ from contextlib import asynccontextmanager
|
||||
from typing import Annotated
|
||||
|
||||
from fastapi import Depends
|
||||
from sqlalchemy.ext.asyncio import AsyncSessionTransaction
|
||||
from sqlalchemy.ext.asyncio import async_sessionmaker
|
||||
from sqlmodel.ext.asyncio.session import AsyncSession
|
||||
|
||||
@@ -86,16 +85,12 @@ async def transaction_scope(
|
||||
settings: Settings | None = None,
|
||||
database_url: str | None = None,
|
||||
session_factory: SessionFactory | None = None,
|
||||
session: AsyncSession | AsyncSessionTransaction | None = None,
|
||||
) -> AsyncGenerator[AsyncSession | AsyncSessionTransaction]:
|
||||
match session:
|
||||
case AsyncSession() as async_session:
|
||||
if not async_session.in_transaction():
|
||||
session: AsyncSession | None = None,
|
||||
) -> AsyncGenerator[AsyncSession]:
|
||||
if session is not None:
|
||||
if not session.in_transaction():
|
||||
raise RuntimeError("A supplied session must have an active transaction")
|
||||
yield async_session
|
||||
return
|
||||
case AsyncSessionTransaction() as async_transaction:
|
||||
yield async_transaction
|
||||
yield session
|
||||
return
|
||||
|
||||
active_session_factory = session_factory or resolve_session_factory(
|
||||
@@ -106,7 +101,4 @@ async def transaction_scope(
|
||||
yield owned_session
|
||||
|
||||
|
||||
type TransactionScopeDep = Annotated[
|
||||
AsyncSession | AsyncSessionTransaction,
|
||||
Depends(transaction_scope),
|
||||
]
|
||||
type TransactionScopeDep = Annotated[AsyncSession, Depends(transaction_scope)]
|
||||
|
||||
@@ -74,7 +74,10 @@ class _CapturingAsyncClient:
|
||||
try:
|
||||
self.last_body = response.content
|
||||
except httpx.ResponseNotRead:
|
||||
response.stream = _CapturingAsyncByteStream(response.stream, self._capture_body)
|
||||
stream = response.stream
|
||||
if not isinstance(stream, httpx.AsyncByteStream):
|
||||
raise
|
||||
response.stream = _CapturingAsyncByteStream(stream, self._capture_body)
|
||||
return response
|
||||
|
||||
def build_request(self, *args: Any, **kwargs: Any) -> httpx.Request:
|
||||
|
||||
@@ -10,13 +10,14 @@ from uuid import UUID
|
||||
|
||||
from sqlalchemy.exc import IntegrityError
|
||||
from sqlalchemy.ext.asyncio import async_sessionmaker
|
||||
from sqlalchemy.orm import selectinload
|
||||
from sqlmodel import SQLModel
|
||||
from sqlmodel import col
|
||||
from sqlmodel import select
|
||||
from sqlmodel.ext.asyncio.session import AsyncSession
|
||||
|
||||
from ..config import Settings
|
||||
from ..db.loading import orm_attribute
|
||||
from ..db.loading import selectinload
|
||||
from ..db.models import Document
|
||||
from ..db.models import DocumentPerson
|
||||
from ..db.models import DocumentType
|
||||
@@ -189,8 +190,8 @@ class DocumentService(ServiceBase):
|
||||
session=_session,
|
||||
document_id=document_id,
|
||||
options=(
|
||||
selectinload(Document.jobs), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Document.sources), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Document.jobs),
|
||||
selectinload(Document.sources),
|
||||
),
|
||||
suggestion="Re-upload the source document and retry.",
|
||||
)
|
||||
@@ -218,9 +219,9 @@ class DocumentService(ServiceBase):
|
||||
session=_session,
|
||||
document_id=document.id,
|
||||
options=(
|
||||
selectinload(Document.jobs), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Document.sources), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Document.document_people), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Document.jobs),
|
||||
selectinload(Document.sources),
|
||||
selectinload(Document.document_people),
|
||||
),
|
||||
)
|
||||
|
||||
@@ -275,9 +276,9 @@ class DocumentService(ServiceBase):
|
||||
"""List documents with relations needed by the archival table."""
|
||||
async with self._session_scope(session) as _session:
|
||||
query = select(Document).options(
|
||||
selectinload(Document.document_people).selectinload(DocumentPerson.person), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Document.document_people).selectinload(DocumentPerson.role_ref), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Document.document_type_ref), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Document.document_people).selectinload(orm_attribute(DocumentPerson.person)),
|
||||
selectinload(Document.document_people).selectinload(orm_attribute(DocumentPerson.role_ref)),
|
||||
selectinload(Document.document_type_ref),
|
||||
)
|
||||
result = await _session.exec(query)
|
||||
return result.all()
|
||||
@@ -288,11 +289,11 @@ class DocumentService(ServiceBase):
|
||||
query = (
|
||||
select(Document)
|
||||
.options(
|
||||
selectinload(Document.jobs), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Document.sources), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Document.document_people).selectinload(DocumentPerson.person), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Document.document_people).selectinload(DocumentPerson.role_ref), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Document.document_type_ref), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Document.jobs),
|
||||
selectinload(Document.sources),
|
||||
selectinload(Document.document_people).selectinload(orm_attribute(DocumentPerson.person)),
|
||||
selectinload(Document.document_people).selectinload(orm_attribute(DocumentPerson.role_ref)),
|
||||
selectinload(Document.document_type_ref),
|
||||
)
|
||||
.where(Document.id == document_id)
|
||||
.execution_options(populate_existing=True)
|
||||
|
||||
@@ -6,10 +6,12 @@ from pathlib import Path
|
||||
from uuid import UUID
|
||||
|
||||
from sqlalchemy import func
|
||||
from sqlalchemy.orm import selectinload
|
||||
from sqlmodel import col
|
||||
from sqlmodel import select
|
||||
from sqlmodel.ext.asyncio.session import AsyncSession
|
||||
|
||||
from ..db.loading import orm_attribute
|
||||
from ..db.loading import selectinload
|
||||
from ..db.models import ExecutionAttempt
|
||||
from ..db.models import Job
|
||||
from ..db.models import JobSource
|
||||
@@ -64,8 +66,8 @@ class JobService(ServiceBase):
|
||||
query = (
|
||||
select(Job)
|
||||
.options(
|
||||
selectinload(Job.document), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Job.job_sources).selectinload(JobSource.source), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Job.document),
|
||||
selectinload(Job.job_sources).selectinload(orm_attribute(JobSource.source)),
|
||||
)
|
||||
.where(Job.id == job_id)
|
||||
.execution_options(populate_existing=True)
|
||||
@@ -100,13 +102,15 @@ class JobService(ServiceBase):
|
||||
"""Query jobs from the database based on provided filters."""
|
||||
async with self._session_scope(session) as _session:
|
||||
query = select(Job).options(
|
||||
selectinload(Job.document), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Job.job_sources).selectinload(JobSource.source), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Job.document),
|
||||
selectinload(Job.job_sources).selectinload(orm_attribute(JobSource.source)),
|
||||
)
|
||||
if status is not None:
|
||||
query = query.where(Job.status == status)
|
||||
if filename is not None:
|
||||
query = query.where(Job.job_sources.any(JobSource.source.has(Source.filename == filename)))
|
||||
query = query.where(
|
||||
col(Job.job_sources).any(col(JobSource.source).has(col(Source.filename) == filename))
|
||||
)
|
||||
result = await _session.exec(query)
|
||||
return result.all()
|
||||
|
||||
@@ -118,8 +122,8 @@ class JobService(ServiceBase):
|
||||
"""List all jobs in the database with eagerly loaded documents."""
|
||||
async with self._session_scope(session) as _session:
|
||||
query = select(Job).options(
|
||||
selectinload(Job.document), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Job.job_sources).selectinload(JobSource.source), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Job.document),
|
||||
selectinload(Job.job_sources).selectinload(orm_attribute(JobSource.source)),
|
||||
)
|
||||
result = await _session.exec(query)
|
||||
return result.all()
|
||||
@@ -152,8 +156,8 @@ class JobService(ServiceBase):
|
||||
query = (
|
||||
select(Job)
|
||||
.options(
|
||||
selectinload(Job.document), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Job.job_sources).selectinload(JobSource.source), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Job.document),
|
||||
selectinload(Job.job_sources).selectinload(orm_attribute(JobSource.source)),
|
||||
)
|
||||
.where(Job.id == job_id)
|
||||
.execution_options(populate_existing=True)
|
||||
@@ -184,7 +188,7 @@ class JobService(ServiceBase):
|
||||
select(Job)
|
||||
.where(Job.status == JobStatus.QUEUED)
|
||||
# Break ties by id so "next" is stable when two rows share close timestamps.
|
||||
.order_by(Job.date_created, Job.id) # pyright: ignore[reportArgumentType]
|
||||
.order_by(col(Job.date_created), col(Job.id))
|
||||
.limit(1)
|
||||
)
|
||||
if _session.get_bind().dialect.name == "postgresql":
|
||||
@@ -304,7 +308,7 @@ class JobService(ServiceBase):
|
||||
(
|
||||
await session.exec(
|
||||
select(ProcessingArtifact).where(
|
||||
ProcessingArtifact.execution_attempt_id.in_(attempt_ids)
|
||||
col(ProcessingArtifact.execution_attempt_id).in_(attempt_ids)
|
||||
)
|
||||
)
|
||||
).all()
|
||||
@@ -351,7 +355,7 @@ class JobService(ServiceBase):
|
||||
query = (
|
||||
select(Job)
|
||||
.options(
|
||||
selectinload(Job.job_sources).selectinload(JobSource.source), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Job.job_sources).selectinload(orm_attribute(JobSource.source)),
|
||||
)
|
||||
.where(Job.id == job_id)
|
||||
.execution_options(populate_existing=True)
|
||||
@@ -388,7 +392,7 @@ class JobService(ServiceBase):
|
||||
query = (
|
||||
select(Job)
|
||||
.options(
|
||||
selectinload(Job.job_sources).selectinload(JobSource.source), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Job.job_sources).selectinload(orm_attribute(JobSource.source)),
|
||||
)
|
||||
.where(Job.id == job_id)
|
||||
.execution_options(populate_existing=True)
|
||||
|
||||
@@ -10,6 +10,7 @@ from pathlib import Path
|
||||
|
||||
from PIL import Image
|
||||
from PIL import UnidentifiedImageError
|
||||
from PIL.TiffImagePlugin import TiffImageFile
|
||||
|
||||
from transcription.errors import AppError
|
||||
from transcription.errors import ErrorCategory
|
||||
@@ -65,7 +66,7 @@ def normalize_orientation(path: str | Path, *, media_type: str) -> OrientationNo
|
||||
return None
|
||||
|
||||
transpose, rotation = transformation
|
||||
if image.format == "TIFF":
|
||||
if isinstance(image, TiffImageFile):
|
||||
original_width = int(image.tag_v2.get(256, image.width))
|
||||
original_height = int(image.tag_v2.get(257, image.height))
|
||||
# Pillow applies TIFF orientation while decoding; copying freezes those upright pixels.
|
||||
|
||||
@@ -12,7 +12,6 @@ from uuid import UUID
|
||||
|
||||
from sqlalchemy.exc import IntegrityError
|
||||
from sqlalchemy.ext.asyncio import async_sessionmaker
|
||||
from sqlalchemy.orm import selectinload
|
||||
from sqlmodel import SQLModel
|
||||
from sqlmodel import col
|
||||
from sqlmodel import select
|
||||
@@ -20,6 +19,8 @@ from sqlmodel.ext.asyncio.session import AsyncSession
|
||||
|
||||
from ..config import Settings
|
||||
from ..config import get_settings
|
||||
from ..db.loading import orm_attribute
|
||||
from ..db.loading import selectinload
|
||||
from ..db.models import Document
|
||||
from ..db.models import DocumentPerson
|
||||
from ..db.models import Person
|
||||
@@ -144,7 +145,7 @@ class PeopleService(ServiceBase):
|
||||
existing = await _session.get(
|
||||
Person,
|
||||
person.id,
|
||||
options=(selectinload(Person.document_people),), # pyright: ignore[reportArgumentType]
|
||||
options=(selectinload(Person.document_people),),
|
||||
)
|
||||
if existing is None:
|
||||
raise self._not_found(f"Person with id {person.id} not found")
|
||||
@@ -209,8 +210,8 @@ class PeopleService(ServiceBase):
|
||||
query = (
|
||||
select(Person)
|
||||
.options(
|
||||
selectinload(Person.document_people).selectinload(DocumentPerson.document), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Person.document_people).selectinload(DocumentPerson.role_ref), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Person.document_people).selectinload(orm_attribute(DocumentPerson.document)),
|
||||
selectinload(Person.document_people).selectinload(orm_attribute(DocumentPerson.role_ref)),
|
||||
)
|
||||
.where(Person.id == person_id)
|
||||
.execution_options(populate_existing=True)
|
||||
@@ -329,9 +330,9 @@ class PeopleService(ServiceBase):
|
||||
) -> Sequence[DocumentPerson]:
|
||||
async with self._session_scope(session) as _session:
|
||||
query = select(DocumentPerson).options(
|
||||
selectinload(DocumentPerson.document), # pyright: ignore[reportArgumentType]
|
||||
selectinload(DocumentPerson.person), # pyright: ignore[reportArgumentType]
|
||||
selectinload(DocumentPerson.role_ref), # pyright: ignore[reportArgumentType]
|
||||
selectinload(DocumentPerson.document),
|
||||
selectinload(DocumentPerson.person),
|
||||
selectinload(DocumentPerson.role_ref),
|
||||
)
|
||||
if document_id is not None:
|
||||
query = query.where(DocumentPerson.document_id == document_id)
|
||||
|
||||
@@ -12,6 +12,7 @@ from __future__ import annotations
|
||||
from abc import abstractmethod
|
||||
from collections.abc import Sequence
|
||||
from typing import Any
|
||||
from typing import Protocol
|
||||
from uuid import UUID
|
||||
|
||||
from sqlalchemy import func
|
||||
@@ -26,7 +27,23 @@ from ..errors import ErrorCategory
|
||||
from .base import ServiceBase
|
||||
|
||||
|
||||
class RegistryService[ModelT: SQLModel](ServiceBase):
|
||||
class RegistryEntry(Protocol):
|
||||
"""Structural contract every registry table row satisfies.
|
||||
|
||||
Bounding ``RegistryService`` by this protocol rather than by bare ``SQLModel``
|
||||
lets the shared implementation read ``id``/``label``/``normalized_label``/
|
||||
``is_active`` off the model class without suppressions.
|
||||
"""
|
||||
|
||||
id: UUID
|
||||
label: str
|
||||
normalized_label: str
|
||||
is_active: bool
|
||||
|
||||
def __init__(self, /, **data: Any) -> None: ...
|
||||
|
||||
|
||||
class RegistryService[ModelT: RegistryEntry](ServiceBase):
|
||||
"""Generic create/read/update/delete behavior for a registry table.
|
||||
|
||||
Subclasses declare the model, the error type, the user-facing noun, and the
|
||||
|
||||
@@ -25,10 +25,9 @@ from pydantic import TypeAdapter
|
||||
from pydantic import ValidationError
|
||||
from sqlalchemy import func
|
||||
from sqlalchemy import inspect as sqlalchemy_inspect
|
||||
from sqlalchemy import literal
|
||||
from sqlalchemy import tuple_
|
||||
from sqlalchemy.ext.asyncio import async_sessionmaker
|
||||
from sqlalchemy.orm import defer
|
||||
from sqlalchemy.orm import selectinload
|
||||
from sqlmodel import col
|
||||
from sqlmodel import select
|
||||
from sqlmodel.ext.asyncio.session import AsyncSession
|
||||
@@ -55,6 +54,9 @@ from transcription.providers import TransportEvidence
|
||||
from transcription.providers import get_transcription_provider
|
||||
from transcription.providers.evidence import canonical_json_bytes
|
||||
|
||||
from ..db.loading import defer
|
||||
from ..db.loading import orm_attribute
|
||||
from ..db.loading import selectinload
|
||||
from .base import ServiceBase
|
||||
from .normalization import ORIENTATION_PRODUCER
|
||||
from .normalization import ORIENTATION_PRODUCER_VERSION
|
||||
@@ -195,8 +197,8 @@ class SourceService(ServiceBase):
|
||||
query = (
|
||||
select(Source)
|
||||
.options(
|
||||
selectinload(Source.document), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Source.job_sources).selectinload(JobSource.job), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Source.document),
|
||||
selectinload(Source.job_sources).selectinload(orm_attribute(JobSource.job)),
|
||||
)
|
||||
.where(Source.id == source_id)
|
||||
.execution_options(populate_existing=True)
|
||||
@@ -226,11 +228,11 @@ class SourceService(ServiceBase):
|
||||
async with self._session_scope(session) as _session:
|
||||
query = (
|
||||
select(ExecutionAttempt)
|
||||
.options(defer(ExecutionAttempt.transport_body)) # pyright: ignore[reportArgumentType]
|
||||
.options(defer(ExecutionAttempt.transport_body))
|
||||
.where(ExecutionAttempt.job_source_id == job_source_id)
|
||||
.order_by(
|
||||
ExecutionAttempt.attempt_number.desc(), # pyright: ignore[reportAttributeAccessIssue]
|
||||
ExecutionAttempt.id.desc(), # pyright: ignore[reportAttributeAccessIssue]
|
||||
col(ExecutionAttempt.attempt_number).desc(),
|
||||
col(ExecutionAttempt.id).desc(),
|
||||
)
|
||||
.limit(1)
|
||||
)
|
||||
@@ -250,7 +252,7 @@ class SourceService(ServiceBase):
|
||||
async with self._session_scope(session) as _session:
|
||||
source = await self._read_source(session=_session, source_id=source_id)
|
||||
position = (col(Source.page_number), col(Source.id))
|
||||
current = (source.page_number, source_id)
|
||||
current = (literal(source.page_number), literal(source_id))
|
||||
|
||||
previous_query = (
|
||||
select(col(Source.id))
|
||||
@@ -290,8 +292,8 @@ class SourceService(ServiceBase):
|
||||
session=_session,
|
||||
source_id=source_id,
|
||||
options=(
|
||||
selectinload(Source.job_sources), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Source.processing_artifacts), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Source.job_sources),
|
||||
selectinload(Source.processing_artifacts),
|
||||
),
|
||||
)
|
||||
|
||||
@@ -379,7 +381,7 @@ class SourceService(ServiceBase):
|
||||
job_source = await _session.get(
|
||||
JobSource,
|
||||
job_source_id,
|
||||
options=(selectinload(JobSource.source),), # pyright: ignore[reportArgumentType]
|
||||
options=(selectinload(JobSource.source),),
|
||||
)
|
||||
if job_source is None:
|
||||
raise TranscriptionNotFoundError(
|
||||
@@ -444,8 +446,8 @@ class SourceService(ServiceBase):
|
||||
session=_session,
|
||||
source_id=source_id,
|
||||
options=(
|
||||
selectinload(Source.job_sources), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Source.processing_artifacts), # pyright: ignore[reportArgumentType]
|
||||
selectinload(Source.job_sources),
|
||||
selectinload(Source.processing_artifacts),
|
||||
),
|
||||
)
|
||||
|
||||
@@ -511,8 +513,8 @@ class SourceService(ServiceBase):
|
||||
"""List job-source records, optionally filtered by job."""
|
||||
async with self._session_scope(session) as _session:
|
||||
query = select(JobSource).options(
|
||||
selectinload(JobSource.job), # pyright: ignore[reportArgumentType]
|
||||
selectinload(JobSource.source), # pyright: ignore[reportArgumentType]
|
||||
selectinload(JobSource.job),
|
||||
selectinload(JobSource.source),
|
||||
)
|
||||
if job_id is not None:
|
||||
query = query.where(JobSource.job_id == job_id)
|
||||
@@ -720,10 +722,10 @@ class SourceService(ServiceBase):
|
||||
if job_id is not None:
|
||||
query = query.where(ExecutionAttempt.job_id == job_id)
|
||||
query = query.order_by(
|
||||
ExecutionAttempt.job_id,
|
||||
ExecutionAttempt.source_id,
|
||||
ExecutionAttempt.attempt_number,
|
||||
ExecutionAttempt.id,
|
||||
col(ExecutionAttempt.job_id),
|
||||
col(ExecutionAttempt.source_id),
|
||||
col(ExecutionAttempt.attempt_number),
|
||||
col(ExecutionAttempt.id),
|
||||
)
|
||||
return (await _session.exec(query)).all()
|
||||
|
||||
@@ -987,7 +989,7 @@ class SourceService(ServiceBase):
|
||||
query = (
|
||||
select(ProcessingArtifact)
|
||||
.where(ProcessingArtifact.source_id == source_id)
|
||||
.order_by(ProcessingArtifact.created_at, ProcessingArtifact.id)
|
||||
.order_by(col(ProcessingArtifact.created_at), col(ProcessingArtifact.id))
|
||||
.limit(limit)
|
||||
)
|
||||
return (await _session.exec(query)).all()
|
||||
@@ -1003,9 +1005,9 @@ class SourceService(ServiceBase):
|
||||
async with self._session_scope(session) as _session:
|
||||
query = (
|
||||
select(ProcessingArtifact)
|
||||
.options(defer(ProcessingArtifact.inline_payload)) # pyright: ignore[reportArgumentType]
|
||||
.options(defer(ProcessingArtifact.inline_payload))
|
||||
.where(ProcessingArtifact.source_id == source_id)
|
||||
.order_by(ProcessingArtifact.created_at, ProcessingArtifact.id)
|
||||
.order_by(col(ProcessingArtifact.created_at), col(ProcessingArtifact.id))
|
||||
.limit(limit)
|
||||
)
|
||||
return (await _session.exec(query)).all()
|
||||
@@ -1138,10 +1140,10 @@ class SourceService(ServiceBase):
|
||||
async with self._session_scope(session) as _session:
|
||||
query = (
|
||||
select(Source)
|
||||
.join(JobSource, JobSource.source_id == Source.id)
|
||||
.where(JobSource.job_id == job_id)
|
||||
.where(Source.revised_text.is_not(None))
|
||||
.order_by(Source.date_revised) # pyright: ignore[reportArgumentType]
|
||||
.join(JobSource, col(JobSource.source_id) == col(Source.id))
|
||||
.where(col(JobSource.job_id) == job_id)
|
||||
.where(col(Source.revised_text).is_not(None))
|
||||
.order_by(col(Source.date_revised))
|
||||
)
|
||||
result = await _session.exec(query)
|
||||
return result.all()
|
||||
|
||||
@@ -50,7 +50,7 @@ class LinkedPeopleEditor:
|
||||
"""Return the complete staged link set for persistence."""
|
||||
return [DocumentPersonInput(person_id=link.person_id, role_id=link.role_id) for link in self.links]
|
||||
|
||||
@ui.refreshable
|
||||
@ui.refreshable_method
|
||||
def render(self) -> None:
|
||||
ui.label("Linked People").classes("text-sm font-semibold ui-text-primary mt-2")
|
||||
ui.button("Create new person", on_click=lambda: ui.navigate.to("/people/new"), icon="person_add").props(
|
||||
|
||||
@@ -407,7 +407,7 @@ def _render_provider_evidence(
|
||||
|
||||
|
||||
def _artifact_display(artifacts: list[ProcessingArtifact]) -> list[dict[str, object]] | None:
|
||||
payload = [
|
||||
payload: list[dict[str, object]] = [
|
||||
{
|
||||
"id": str(artifact.id),
|
||||
"type": artifact.artifact_type,
|
||||
|
||||
@@ -2,8 +2,10 @@
|
||||
|
||||
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
|
||||
@@ -13,7 +15,7 @@ from transcription.providers.openrouter import OpenRouterTranscriptionProvider
|
||||
|
||||
|
||||
class _FakeChat:
|
||||
def __init__(self, response=None, error: Exception | None = None):
|
||||
def __init__(self, response=None, error: BaseException | None = None):
|
||||
self._response = response
|
||||
self._error = error
|
||||
self.calls = []
|
||||
@@ -26,10 +28,15 @@ class _FakeChat:
|
||||
|
||||
|
||||
class _FakeClient:
|
||||
def __init__(self, response=None, error: Exception | None = None):
|
||||
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."""
|
||||
@@ -37,13 +44,13 @@ class TestOpenRouterProviderInit:
|
||||
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=_FakeClient())
|
||||
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=_FakeClient())
|
||||
provider = OpenRouterTranscriptionProvider(settings=settings, client=_fake_client())
|
||||
assert provider.model == "vendor/custom-model"
|
||||
|
||||
|
||||
@@ -61,7 +68,7 @@ class TestOpenRouterProviderTranscribe:
|
||||
openrouter_http_referer="https://example.test",
|
||||
openrouter_app_title="Transcription App",
|
||||
)
|
||||
provider = OpenRouterTranscriptionProvider(settings=settings, client=client)
|
||||
provider = OpenRouterTranscriptionProvider(settings=settings, client=cast("OpenRouter", client))
|
||||
|
||||
result = await provider.transcribe(
|
||||
prompt_text="Prompt body",
|
||||
@@ -79,7 +86,10 @@ class TestOpenRouterProviderTranscribe:
|
||||
"""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=client)
|
||||
provider = OpenRouterTranscriptionProvider(
|
||||
settings=Settings(openrouter_api_key="test-key"),
|
||||
client=cast("OpenRouter", client),
|
||||
)
|
||||
|
||||
result = await provider.transcribe(
|
||||
prompt_text="Prompt body",
|
||||
@@ -110,7 +120,7 @@ class TestOpenRouterProviderTranscribe:
|
||||
}
|
||||
provider = OpenRouterTranscriptionProvider(
|
||||
settings=Settings(openrouter_api_key="test-key"),
|
||||
client=_FakeClient(response=response),
|
||||
client=_fake_client(response=response),
|
||||
)
|
||||
|
||||
result = await provider.transcribe(
|
||||
@@ -134,7 +144,7 @@ class TestOpenRouterProviderTranscribe:
|
||||
"""Transcribe converts SDK failures to ProviderError."""
|
||||
provider = OpenRouterTranscriptionProvider(
|
||||
settings=Settings(openrouter_api_key="test-key"),
|
||||
client=_FakeClient(error=RuntimeError("network down")),
|
||||
client=_fake_client(error=RuntimeError("network down")),
|
||||
)
|
||||
|
||||
with pytest.raises(ProviderError):
|
||||
@@ -149,7 +159,7 @@ class TestOpenRouterProviderTranscribe:
|
||||
"""Caller and shutdown cancellation must not be relabeled as a timeout."""
|
||||
provider = OpenRouterTranscriptionProvider(
|
||||
settings=Settings(openrouter_api_key="test-key"),
|
||||
client=_FakeClient(error=asyncio.CancelledError()),
|
||||
client=_fake_client(error=asyncio.CancelledError()),
|
||||
)
|
||||
|
||||
with pytest.raises(asyncio.CancelledError):
|
||||
@@ -166,7 +176,7 @@ class TestOpenRouterProviderTranscribe:
|
||||
client = _FakeClient(response=response)
|
||||
provider = OpenRouterTranscriptionProvider(
|
||||
settings=Settings(openrouter_api_key="test-key"),
|
||||
client=client,
|
||||
client=cast("OpenRouter", client),
|
||||
)
|
||||
|
||||
await provider.transcribe(
|
||||
@@ -185,7 +195,7 @@ class TestOpenRouterProviderTranscribe:
|
||||
"""Transcribe raises ProviderResponseError for missing completion text."""
|
||||
provider = OpenRouterTranscriptionProvider(
|
||||
settings=Settings(openrouter_api_key="test-key"),
|
||||
client=_FakeClient(response=SimpleNamespace(choices=[])),
|
||||
client=_fake_client(response=SimpleNamespace(choices=[])),
|
||||
)
|
||||
|
||||
with pytest.raises(ProviderResponseError):
|
||||
@@ -204,7 +214,7 @@ class TestOpenRouterProviderTranscribe:
|
||||
}
|
||||
provider = OpenRouterTranscriptionProvider(
|
||||
settings=Settings(openrouter_api_key="test-key"),
|
||||
client=_FakeClient(response=response),
|
||||
client=_fake_client(response=response),
|
||||
)
|
||||
|
||||
result = await provider.transcribe(
|
||||
|
||||
@@ -14,6 +14,7 @@ from transcription.db.models import JobSource
|
||||
from transcription.db.models import Source
|
||||
from transcription.providers import RequestManifest
|
||||
from transcription.providers import TranscriptionResult
|
||||
from transcription.providers.evidence import SourceEvidenceReference
|
||||
from transcription.providers.evidence import build_software_context
|
||||
from transcription.services import ServiceBundle
|
||||
from transcription.services.documents import DocumentService
|
||||
@@ -62,7 +63,9 @@ def test_orientation_three_is_physically_rotated_and_metadata_removed(tmp_path):
|
||||
with Image.open(path) as source_image, Image.open(io.BytesIO(result.content)) as derivative:
|
||||
assert source_image.getexif()[274] == 3
|
||||
assert derivative.getexif().get(274, 1) == 1
|
||||
assert derivative.getpixel((0, 0))[2] > derivative.getpixel((0, 0))[0]
|
||||
pixel = derivative.getpixel((0, 0))
|
||||
assert isinstance(pixel, tuple)
|
||||
assert pixel[2] > pixel[0]
|
||||
|
||||
|
||||
@pytest.mark.unit
|
||||
@@ -130,7 +133,9 @@ async def test_resolve_provider_input_persists_exact_derivative(default_session_
|
||||
assert provider_input.derivative_id == artifacts[0].id
|
||||
assert provider_input.path.read_bytes() != original
|
||||
assert hashlib.sha256(provider_input.path.read_bytes()).hexdigest() == provider_input.digest_sha256
|
||||
assert artifacts[0].coordinate_metadata["original_orientation"] == 3
|
||||
coordinate_metadata = artifacts[0].coordinate_metadata
|
||||
assert coordinate_metadata is not None
|
||||
assert coordinate_metadata["original_orientation"] == 3
|
||||
|
||||
|
||||
@pytest.mark.integration
|
||||
@@ -219,8 +224,11 @@ async def test_worker_sends_exact_derivative_and_links_attempt_evidence(
|
||||
attempts = await services.sources.list_execution_attempts(source_id=source.id)
|
||||
artifacts = await services.sources.list_processing_artifacts(source_id=source.id)
|
||||
source_reference = captured["source_reference"]
|
||||
assert isinstance(source_reference, SourceEvidenceReference)
|
||||
captured_bytes = captured["bytes"]
|
||||
assert isinstance(captured_bytes, bytes)
|
||||
assert source_path.read_bytes() == original
|
||||
assert hashlib.sha256(captured["bytes"]).hexdigest() == source_reference.digest_sha256
|
||||
assert hashlib.sha256(captured_bytes).hexdigest() == source_reference.digest_sha256
|
||||
assert source_reference.derivative_id is not None
|
||||
assert {artifact.artifact_type for artifact in artifacts} == {
|
||||
"orientation_normalized_model_input",
|
||||
|
||||
@@ -2,6 +2,7 @@ from pathlib import Path
|
||||
from uuid import uuid4
|
||||
|
||||
import pytest
|
||||
from sqlmodel import col
|
||||
from sqlmodel import select
|
||||
|
||||
from transcription.config import Settings
|
||||
@@ -63,7 +64,7 @@ async def test_create_job_for_document_sorts_sources_and_creates_links(async_ses
|
||||
|
||||
sources = (
|
||||
await async_session.exec(
|
||||
select(Source).where(Source.document_id == document.id).order_by(Source.page_number) # pyright: ignore[reportArgumentType]
|
||||
select(Source).where(Source.document_id == document.id).order_by(col(Source.page_number))
|
||||
)
|
||||
).all()
|
||||
assert [source.upload_name for source in sources] == ["A_page.pdf", "b_page.pdf"]
|
||||
@@ -99,7 +100,7 @@ async def test_create_document_job_stores_source_under_document_id_directory(asy
|
||||
|
||||
source = (
|
||||
await async_session.exec(
|
||||
select(Source).where(Source.document_id == result.document_id).order_by(Source.page_number) # pyright: ignore[reportArgumentType]
|
||||
select(Source).where(Source.document_id == result.document_id).order_by(col(Source.page_number))
|
||||
)
|
||||
).first()
|
||||
assert source is not None
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
from uuid import uuid4
|
||||
|
||||
import pytest
|
||||
from pydantic import JsonValue
|
||||
|
||||
from transcription.db.models import Document
|
||||
from transcription.db.models import DocumentPerson
|
||||
@@ -303,8 +304,11 @@ async def test_update_job_source_transcription_persists_provider_json_payloads(d
|
||||
JobSource(job_id=job.id, source_id=source.id, status=JobSourceStatus.PENDING)
|
||||
)
|
||||
|
||||
metadata = {"finish_reason": "stop", "usage": {"input_tokens": 11, "output_tokens": 22, "total_tokens": 33}}
|
||||
raw_payload = {"id": "resp_xyz", "choices": [{"message": {"content": "provider transcript"}}]}
|
||||
metadata: dict[str, JsonValue] = {
|
||||
"finish_reason": "stop",
|
||||
"usage": {"input_tokens": 11, "output_tokens": 22, "total_tokens": 33},
|
||||
}
|
||||
raw_payload: dict[str, JsonValue] = {"id": "resp_xyz", "choices": [{"message": {"content": "provider transcript"}}]}
|
||||
|
||||
await transcriptions.update_job_source_transcription(
|
||||
job_id=job.id,
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
"""Tests for transcription.config — settings loading, provider defaults, and paths."""
|
||||
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
import pytest
|
||||
from pydantic import ValidationError
|
||||
@@ -10,9 +11,9 @@ from transcription.config import Settings
|
||||
from transcription.config import parse_cli_settings
|
||||
|
||||
|
||||
def _make_settings(**overrides) -> Settings:
|
||||
def _make_settings(**overrides: Any) -> Settings:
|
||||
"""Build a Settings instance with a dummy API key unless overridden."""
|
||||
defaults = {"openrouter_api_key": "test-key-abc123", "provider_models": None}
|
||||
defaults: dict[str, Any] = {"openrouter_api_key": "test-key-abc123", "provider_models": None}
|
||||
defaults.update(overrides)
|
||||
return Settings(**defaults)
|
||||
|
||||
@@ -168,6 +169,7 @@ def test_openrouter_client_timeout_tracks_the_configured_budget():
|
||||
|
||||
settings = Settings(openrouter_api_key="test-key", worker_provider_timeout_seconds=123.0)
|
||||
provider = OpenRouterTranscriptionProvider(settings=settings)
|
||||
assert provider._capturing_client is not None
|
||||
timeout = provider._capturing_client._client.timeout
|
||||
|
||||
assert timeout.read == 123.0
|
||||
|
||||
+2
-1
@@ -6,6 +6,7 @@ import pytest
|
||||
import sqlalchemy as sa
|
||||
from sqlalchemy import inspect
|
||||
from sqlalchemy.dialects import postgresql
|
||||
from sqlalchemy.exc import SAWarning
|
||||
from sqlmodel import SQLModel
|
||||
from sqlmodel import select
|
||||
from sqlmodel.ext.asyncio.session import AsyncSession
|
||||
@@ -148,7 +149,7 @@ async def test_create_all_declares_hot_path_indexes(tmp_path):
|
||||
def test_metadata_has_no_unresolvable_table_cycle():
|
||||
"""create_all must be able to order every table, including on PostgreSQL."""
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter("error", sa.exc.SAWarning)
|
||||
warnings.simplefilter("error", SAWarning)
|
||||
ordered = [table.name for table in SQLModel.metadata.sorted_tables]
|
||||
|
||||
assert ordered.index("source") < ordered.index("execution_attempt")
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
"""Tests for the V2 SQLModel persistence layer and relationships."""
|
||||
|
||||
from typing import Any
|
||||
from uuid import UUID
|
||||
|
||||
import pytest
|
||||
@@ -17,8 +18,8 @@ from transcription.db.models import PersonRole
|
||||
from transcription.db.models import Source
|
||||
|
||||
|
||||
def _make_document(**overrides) -> Document:
|
||||
defaults = {
|
||||
def _make_document(**overrides: Any) -> Document:
|
||||
defaults: dict[str, Any] = {
|
||||
"name": "letter bundle",
|
||||
"notes": "Family correspondence",
|
||||
}
|
||||
@@ -51,8 +52,8 @@ def _persist_document(session) -> Document:
|
||||
return document
|
||||
|
||||
|
||||
def _persist_person(session, **overrides) -> Person:
|
||||
defaults = {"full_name": "Ada Lovelace"}
|
||||
def _persist_person(session, **overrides: Any) -> Person:
|
||||
defaults: dict[str, Any] = {"full_name": "Ada Lovelace"}
|
||||
defaults.update(overrides)
|
||||
person = Person(**defaults)
|
||||
session.add(person)
|
||||
@@ -69,8 +70,8 @@ def _persist_job(session, document: Document) -> Job:
|
||||
return job
|
||||
|
||||
|
||||
def _persist_source(session, document: Document, *, page_number: int = 1, **overrides) -> Source:
|
||||
defaults = {
|
||||
def _persist_source(session, document: Document, *, page_number: int = 1, **overrides: Any) -> Source:
|
||||
defaults: dict[str, Any] = {
|
||||
"document_id": document.id,
|
||||
"page_number": page_number,
|
||||
"upload_name": "letter.jpg",
|
||||
@@ -88,8 +89,8 @@ def _persist_source(session, document: Document, *, page_number: int = 1, **over
|
||||
return source
|
||||
|
||||
|
||||
def _persist_job_source(session, job: Job, source: Source, **overrides) -> JobSource:
|
||||
defaults = {
|
||||
def _persist_job_source(session, job: Job, source: Source, **overrides: Any) -> JobSource:
|
||||
defaults: dict[str, Any] = {
|
||||
"job_id": job.id,
|
||||
"source_id": source.id,
|
||||
"status": JobSourceStatus.PENDING,
|
||||
|
||||
@@ -86,7 +86,7 @@ class TestPromptConfiguration:
|
||||
assert execution.temperature == 0.2
|
||||
assert execution.top_p == 0.9
|
||||
with pytest.raises(ValidationError):
|
||||
execution.prompt_name = "changed.md"
|
||||
execution.prompt_name = "changed.md" # ty: ignore[invalid-assignment]
|
||||
|
||||
def test_rejects_prompt_path_traversal_even_with_direct_loader_call(self, tmp_path):
|
||||
outside_prompt = tmp_path / "outside.md"
|
||||
|
||||
@@ -10,6 +10,7 @@ from uuid import uuid4
|
||||
|
||||
import httpx
|
||||
import pytest
|
||||
from pydantic import JsonValue
|
||||
|
||||
from transcription.benchmarking import EditorialAssessment
|
||||
from transcription.benchmarking import score_transcription
|
||||
@@ -33,6 +34,18 @@ from transcription.services.sources import TranscriptionError
|
||||
from transcription.services.sources import transcribe_document_image
|
||||
|
||||
|
||||
def _json_object(value: JsonValue) -> dict[str, JsonValue]:
|
||||
"""Narrow a JSON export member to an object, asserting the export shape."""
|
||||
assert isinstance(value, dict)
|
||||
return value
|
||||
|
||||
|
||||
def _json_array(value: JsonValue) -> list[JsonValue]:
|
||||
"""Narrow a JSON export member to an array, asserting the export shape."""
|
||||
assert isinstance(value, list)
|
||||
return value
|
||||
|
||||
|
||||
class _ChunkedAsyncStream(httpx.AsyncByteStream):
|
||||
def __init__(self, chunks: list[bytes]):
|
||||
self._chunks = chunks
|
||||
@@ -261,9 +274,9 @@ async def test_attempts_are_append_only_and_exported_with_integrity(default_sess
|
||||
)
|
||||
)
|
||||
export = await sources.build_evidence_export(source_id=source.id)
|
||||
assert export["source"]["digest_sha256"] == "a" * 64
|
||||
assert [item["attempt_number"] for item in export["attempts"]] == [1, 2]
|
||||
assert export["artifacts"][0]["id"] == str(artifact.id)
|
||||
assert _json_object(export["source"])["digest_sha256"] == "a" * 64
|
||||
assert [_json_object(item)["attempt_number"] for item in _json_array(export["attempts"])] == [1, 2]
|
||||
assert _json_object(_json_array(export["artifacts"])[0])["id"] == str(artifact.id)
|
||||
assert "file_path" not in json.dumps(export)
|
||||
with pytest.raises(JobDeleteBlockedError):
|
||||
await jobs.delete_job_with_guardrails(job_id=job.id)
|
||||
|
||||
@@ -1,9 +1,11 @@
|
||||
import asyncio
|
||||
import logging
|
||||
from typing import cast
|
||||
|
||||
import pytest
|
||||
|
||||
from transcription.services import ServiceBundle
|
||||
from transcription.services.sources import SourceService
|
||||
from transcription.worker import process_next_queued_job
|
||||
from transcription.worker import run_worker_loop
|
||||
|
||||
@@ -43,7 +45,7 @@ async def test_run_worker_loop_reuses_one_bundle_across_jobs(monkeypatch):
|
||||
nonlocal closed
|
||||
closed = True
|
||||
|
||||
bundle = ServiceBundle(sources=_Sources()) # type: ignore[arg-type]
|
||||
bundle = ServiceBundle(sources=cast("SourceService", _Sources()))
|
||||
monkeypatch.setattr(
|
||||
"transcription.worker.ServiceBundle.from_session_factory",
|
||||
classmethod(lambda _cls, _factory=None, **_kwargs: bundle),
|
||||
@@ -75,7 +77,7 @@ async def test_process_next_closes_provider_for_the_bundle_it_owns(monkeypatch):
|
||||
nonlocal closed
|
||||
closed = True
|
||||
|
||||
bundle = ServiceBundle(sources=_Sources()) # type: ignore[arg-type]
|
||||
bundle = ServiceBundle(sources=cast("SourceService", _Sources()))
|
||||
monkeypatch.setattr(
|
||||
"transcription.worker.ServiceBundle.from_session_factory",
|
||||
classmethod(lambda _cls, _factory=None, **_kwargs: bundle),
|
||||
@@ -101,7 +103,7 @@ async def test_process_next_leaves_a_caller_owned_bundle_open(monkeypatch):
|
||||
nonlocal closed
|
||||
closed = True
|
||||
|
||||
bundle = ServiceBundle(sources=_Sources()) # type: ignore[arg-type]
|
||||
bundle = ServiceBundle(sources=cast("SourceService", _Sources()))
|
||||
|
||||
async def _no_job(*, services, session):
|
||||
_ = (services, session)
|
||||
|
||||
@@ -2,9 +2,9 @@
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from collections.abc import AsyncGenerator
|
||||
from collections.abc import Awaitable
|
||||
from collections.abc import Callable
|
||||
from collections.abc import Generator
|
||||
from datetime import UTC
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
@@ -32,12 +32,13 @@ from transcription.db.models import Source
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def app_client(tmp_path_factory: pytest.TempPathFactory) -> AsyncGenerator[tuple[FastAPI, TestClient]]:
|
||||
def app_client(tmp_path_factory: pytest.TempPathFactory) -> Generator[tuple[FastAPI, TestClient]]:
|
||||
"""Provide a real application and test client backed by in-memory SQLite."""
|
||||
tmp_path = tmp_path_factory.mktemp("ui")
|
||||
database = SqliteSettings(path=str(tmp_path / "ui-tests.db"))
|
||||
settings = Settings(
|
||||
openrouter_api_key="test-key",
|
||||
database=SqliteSettings(path=str(tmp_path / "ui-tests.db")),
|
||||
database=database,
|
||||
environment="test",
|
||||
bootstrap_schema_on_startup=True,
|
||||
upload_dir=tmp_path / "uploads",
|
||||
@@ -48,7 +49,7 @@ def app_client(tmp_path_factory: pytest.TempPathFactory) -> AsyncGenerator[tuple
|
||||
|
||||
with TestClient(app) as client:
|
||||
runtime_path = Path(str(app.state.runtime.engine.url.database)).resolve()
|
||||
expected_path = Path(settings.database.path).resolve()
|
||||
expected_path = Path(database.path).resolve()
|
||||
if runtime_path != expected_path:
|
||||
raise RuntimeError(
|
||||
"Refusing to initialize destructive UI fixtures against "
|
||||
|
||||
@@ -1,12 +1,13 @@
|
||||
"""Tests for the sources page routes and Source model properties."""
|
||||
|
||||
from pathlib import Path
|
||||
from uuid import uuid4
|
||||
|
||||
import pytest
|
||||
from sqlalchemy.orm import selectinload
|
||||
from sqlmodel import select
|
||||
|
||||
from transcription.db import session_scope
|
||||
from transcription.db.loading import selectinload
|
||||
from transcription.db.models import Document
|
||||
from transcription.db.models import Job
|
||||
from transcription.db.models import JobSourceStatus
|
||||
@@ -24,6 +25,7 @@ class TestSourceModelProperties:
|
||||
@pytest.mark.asyncio
|
||||
async def test_source_properties_with_no_job_sources(self):
|
||||
source = Source(
|
||||
document_id=uuid4(),
|
||||
page_number=1,
|
||||
upload_name="page_one.png",
|
||||
filename="stored_page_one.png",
|
||||
|
||||
@@ -7,7 +7,6 @@ import shlex
|
||||
import shutil
|
||||
import subprocess
|
||||
import sys
|
||||
from ctypes import wintypes
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
|
||||
@@ -20,17 +19,16 @@ def show_phase(title: str) -> None:
|
||||
print(f"========== {title} ==========")
|
||||
|
||||
|
||||
if sys.platform == "win32":
|
||||
# `ctypes.wintypes` raises on import off Windows, and `fcntl` does not exist
|
||||
# on Windows, so the two implementations are selected at module level where a
|
||||
# type checker can narrow `sys.platform` and analyze only the live branch.
|
||||
from ctypes import wintypes
|
||||
|
||||
def test_file_unlocked(path: Path) -> bool:
|
||||
if not path.exists():
|
||||
return True
|
||||
|
||||
if os.name == "nt":
|
||||
return _test_file_unlocked_windows(path)
|
||||
|
||||
return _test_file_unlocked_posix(path)
|
||||
|
||||
|
||||
def _test_file_unlocked_windows(path: Path) -> bool:
|
||||
generic_read = 0x80000000
|
||||
generic_write = 0x40000000
|
||||
open_existing = 3
|
||||
@@ -66,10 +64,13 @@ def _test_file_unlocked_windows(path: Path) -> bool:
|
||||
kernel32.CloseHandle(handle)
|
||||
return True
|
||||
|
||||
|
||||
def _test_file_unlocked_posix(path: Path) -> bool:
|
||||
else:
|
||||
import fcntl
|
||||
|
||||
def test_file_unlocked(path: Path) -> bool:
|
||||
if not path.exists():
|
||||
return True
|
||||
|
||||
fd = os.open(path, os.O_RDWR)
|
||||
try:
|
||||
try:
|
||||
|
||||
Reference in New Issue
Block a user