ruff and settings

src/transcription/api/errors.py

@@ -4,10 +4,13 @@ from __future__ import annotations
 
 import logging
 
-from fastapi import FastAPI, Request
+from fastapi import FastAPI
+from fastapi import Request
 from fastapi.responses import JSONResponse
 
-from transcription.errors import AppError, ErrorCategory, build_error_envelope
+from transcription.errors import AppError
+from transcription.errors import ErrorCategory
+from transcription.errors import build_error_envelope
 
 logger = logging.getLogger(__name__)
 

src/transcription/app.py

@@ -3,21 +3,20 @@
 from __future__ import annotations
 
 from contextlib import asynccontextmanager
-from threading import Event, Thread
+from threading import Event
+from threading import Thread
 
 from fastapi import FastAPI
 
-from transcription.api.errors import register_error_handlers
-from transcription.api.health import router as health_router
-from transcription.config import get_settings, setup_logging
-from transcription.db import (
-    create_all,
-    dispose_database_runtime,
-    initialize_database_runtime,
-    should_bootstrap_schema,
-)
-from transcription.ui import register_pages
-from transcription.worker import run_worker_loop
+from .api.errors import register_error_handlers
+from .api.health import router as health_router
+from .config import get_settings
+from .config import setup_logging
+from .db import cleanup_database
+from .db import create_all
+from .db import get_engine
+from .ui import register_pages
+from .worker import run_worker_loop
 
 
 def _start_worker(app: FastAPI) -> None:
@@ -25,7 +24,7 @@ def _start_worker(app: FastAPI) -> None:
     worker_thread = Thread(
         target=run_worker_loop,
         kwargs={
-            "engine": app.state.db_runtime.engine,
+            "engine": app.state.db_conn,
             "stop_event": stop_event,
             "poll_interval_seconds": 1.0,
         },
@@ -52,10 +51,11 @@ async def _lifespan(app: FastAPI):
 
     settings = get_settings()
     app.state.settings = settings
-    app.state.db_runtime = initialize_database_runtime(settings=settings)
+    engine = get_engine()
+    app.state.db_conn = engine
 
-    if should_bootstrap_schema(settings):
-        create_all(engine=app.state.db_runtime.engine)
+    if settings.should_bootstrap_schema:
+        create_all(engine=engine)
 
     settings.upload_dir.mkdir(parents=True, exist_ok=True)
     settings.prompt_dir.mkdir(parents=True, exist_ok=True)
@@ -65,7 +65,7 @@ async def _lifespan(app: FastAPI):
         yield
     finally:
         _stop_worker(app)
-        dispose_database_runtime()
+        cleanup_database()
 
 
 def create_app() -> FastAPI:
@@ -75,4 +75,3 @@ def create_app() -> FastAPI:
     register_pages(app)
     app.include_router(health_router)
     return app
-

src/transcription/config.py

@@ -5,14 +5,16 @@ once at startup. Provider-specific defaults (model names, base URLs)
 are resolved by the provider adapters, not here.
 """
 
-import logging
 import logging.config
+from contextvars import ContextVar
 from enum import StrEnum
-from functools import lru_cache
 from pathlib import Path
 from typing import Literal
 
-from pydantic_settings import BaseSettings, SettingsConfigDict
+from pydantic_settings import BaseSettings
+from pydantic_settings import SettingsConfigDict
+
+logger = logging.getLogger(__name__)
 
 
 class Provider(StrEnum):
@@ -48,6 +50,24 @@ class Settings(BaseSettings):
     worker_max_retries: int = 0
     worker_retry_backoff_seconds: float = 0.0
 
+    @property
+    def should_bootstrap_schema(self) -> bool:
+        """Return whether startup should auto-create schema for this environment."""
+        if self.bootstrap_schema_on_startup is not None:
+            return self.bootstrap_schema_on_startup
+        return self.environment in {"development", "test"}
+
+
+_settings: ContextVar[Settings | None] = ContextVar("settings", default=None)
+
+
+def get_settings() -> Settings:
+    settings = _settings.get()
+    if settings is None:
+        settings = Settings()  # pyright: ignore[reportCallIssue]
+        _settings.set(settings)
+    return settings
+
 
 LOGGING_CONFIG: dict[str, object] = {
     "version": 1,
@@ -69,18 +89,17 @@ LOGGING_CONFIG: dict[str, object] = {
         "level": "INFO",
         "handlers": ["console"],
     },
+    "loggers": {
+        "transcription": {
+            "level": "DEBUG",
+            "handlers": ["console"],
+            "propagate": False,
+        }
+    },
 }
 
 
-@lru_cache(maxsize=1)
-def get_settings() -> Settings:
-    """Return the singleton Settings instance.
-
-    Cached so the entire application shares one validated config.
-    """
-    return Settings()
-
-
 def setup_logging() -> None:
     """Configure root logging once at startup."""
     logging.config.dictConfig(LOGGING_CONFIG)
+    logger.debug("Logging configured")

src/transcription/db.py

@@ -7,70 +7,44 @@ startup/shutdown behavior is predictable and lifespan-managed.
 import contextlib
 import logging
 from collections.abc import Generator
-from dataclasses import dataclass
+from functools import cache
 
-from sqlalchemy import inspect, text
+from sqlalchemy import inspect
+from sqlalchemy import text
 from sqlalchemy.engine import Engine
-from sqlmodel import Session, SQLModel, create_engine
+from sqlmodel import Session
+from sqlmodel import SQLModel
+from sqlmodel import create_engine
 
-from transcription.config import Settings, get_settings
+from .config import Settings
+from .config import get_settings
 
 logger = logging.getLogger(__name__)
 
 
-@dataclass(frozen=True)
-class DatabaseRuntime:
-    """Process-level database runtime resources."""
-
-    engine: Engine
-
-
-_runtime: DatabaseRuntime | None = None
-
-
 def _build_engine(settings: Settings) -> Engine:
     connect_args: dict[str, object] = {}
     if settings.database_url.startswith("sqlite"):
         connect_args["check_same_thread"] = False
     return create_engine(
-        settings.database_url,
+        url=settings.database_url,
         echo=False,
         connect_args=connect_args,
     )
 
 
-def initialize_database_runtime(*, settings: Settings | None = None) -> DatabaseRuntime:
-    """Initialize and cache the process database runtime once."""
-    global _runtime
-
-    if _runtime is not None:
-        return _runtime
-
-    runtime_settings = settings or get_settings()
-    _runtime = DatabaseRuntime(engine=_build_engine(runtime_settings))
-    return _runtime
+@cache
+def get_engine() -> Engine:
+    """Return a new SQLAlchemy engine for the current settings."""
+    settings = get_settings()
+    logger.debug("Creating new SQLAlchemy engine for database_url=%s", settings.database_url)
+    return _build_engine(settings)
 
 
-def get_database_runtime() -> DatabaseRuntime:
-    """Return initialized database runtime, creating it if needed."""
-    if _runtime is None:
-        return initialize_database_runtime()
-    return _runtime
-
-
-def dispose_database_runtime() -> None:
-    """Dispose process database runtime resources."""
-    global _runtime
-    if _runtime is not None:
-        _runtime.engine.dispose()
-    _runtime = None
-
-
-def should_bootstrap_schema(settings: Settings) -> bool:
-    """Return whether startup should auto-create schema for this environment."""
-    if settings.bootstrap_schema_on_startup is not None:
-        return settings.bootstrap_schema_on_startup
-    return settings.environment in {"development", "test"}
+def cleanup_database() -> None:
+    """Cleanup database runtime resources."""
+    engine = get_engine()
+    engine.dispose()
 
 
 def create_all(*, engine: Engine | None = None) -> None:
@@ -78,9 +52,10 @@ def create_all(*, engine: Engine | None = None) -> None:
     # Import models so SQLModel metadata is fully registered before bootstrap.
     from transcription import models as _models  # noqa: F401
 
-    active_engine = engine or get_database_runtime().engine
+    active_engine = engine or get_engine()
     SQLModel.metadata.create_all(active_engine)
     _ensure_sqlite_compat_columns(active_engine)
+    logger.debug("Database schema bootstrap complete for database_url=%s", active_engine.url)
 
 
 def _ensure_sqlite_compat_columns(engine: Engine) -> None:
@@ -100,17 +75,13 @@ def _ensure_sqlite_compat_columns(engine: Engine) -> None:
     columns = {column["name"] for column in inspector.get_columns("job")}
     if "retry_count" not in columns:
         with engine.begin() as connection:
-            connection.execute(
-                text("ALTER TABLE job ADD COLUMN retry_count INTEGER NOT NULL DEFAULT 0")
-            )
-        logger.warning(
-            "Applied SQLite compatibility schema patch table=job column=retry_count default=0"
-        )
+            connection.execute(text("ALTER TABLE job ADD COLUMN retry_count INTEGER NOT NULL DEFAULT 0"))
+        logger.warning("Applied SQLite compatibility schema patch table=job column=retry_count default=0")
 
 
 @contextlib.contextmanager
 def get_session(*, engine: Engine | None = None) -> Generator[Session]:
     """Yield a database session and ensure cleanup."""
-    active_engine = engine or get_database_runtime().engine
+    active_engine = engine or get_engine()
     with Session(active_engine) as session:
         yield session

src/transcription/errors.py

@@ -3,7 +3,8 @@
 from __future__ import annotations
 
 from dataclasses import dataclass
-from datetime import datetime, timezone
+from datetime import UTC
+from datetime import datetime
 from enum import StrEnum
 from uuid import uuid4
 
@@ -64,7 +65,7 @@ def build_error_envelope(error: AppError) -> ErrorEnvelope:
         category=error.category.value,
         message=error.message,
         suggestion=error.suggestion,
-        timestamp=datetime.now(timezone.utc).isoformat(),
+        timestamp=datetime.now(UTC).isoformat(),
     )
 
 

src/transcription/models.py

@@ -4,12 +4,16 @@ Three models capture the MVP lifecycle:
   Document  ->  one-to-many  ->  Job  ->  one-to-one  ->  Transcript
 """
 
-from datetime import datetime, timezone
+from datetime import UTC
+from datetime import datetime
 from enum import StrEnum
 from typing import Optional
-from uuid import UUID, uuid4
+from uuid import UUID
+from uuid import uuid4
 
-from sqlmodel import Field, Relationship, SQLModel
+from sqlmodel import Field
+from sqlmodel import Relationship
+from sqlmodel import SQLModel
 
 
 class JobStatus(StrEnum):
@@ -26,7 +30,7 @@ class Document(SQLModel, table=True):
     filename: str
     file_path: str
     uploaded_at: datetime = Field(
-        default_factory=lambda: datetime.now(timezone.utc),
+        default_factory=lambda: datetime.now(UTC),
     )
 
     # --- relationships ---
@@ -41,10 +45,10 @@ class Job(SQLModel, table=True):
     status: JobStatus = Field(default=JobStatus.QUEUED)
     retry_count: int = Field(default=0, ge=0)
     created_at: datetime = Field(
-        default_factory=lambda: datetime.now(timezone.utc),
+        default_factory=lambda: datetime.now(UTC),
     )
     updated_at: datetime = Field(
-        default_factory=lambda: datetime.now(timezone.utc),
+        default_factory=lambda: datetime.now(UTC),
     )
 
     # --- relationships ---
@@ -60,7 +64,7 @@ class Transcript(SQLModel, table=True):
     text: str | None = None
     error_detail: str | None = None
     created_at: datetime = Field(
-        default_factory=lambda: datetime.now(timezone.utc),
+        default_factory=lambda: datetime.now(UTC),
     )
 
     # --- relationships ---

src/transcription/providers/__init__.py

@@ -1,13 +1,13 @@
 """Provider exports and factory for transcription adapters."""
 
-from transcription.config import Provider, Settings, get_settings
-from transcription.providers.base import (
-    ProviderAuthError,
-    ProviderError,
-    ProviderResponseError,
-    TranscriptionProvider,
-    TranscriptionResult,
-)
+from transcription.config import Provider
+from transcription.config import Settings
+from transcription.config import get_settings
+from transcription.providers.base import ProviderAuthError
+from transcription.providers.base import ProviderError
+from transcription.providers.base import ProviderResponseError
+from transcription.providers.base import TranscriptionProvider
+from transcription.providers.base import TranscriptionResult
 from transcription.providers.openrouter import OpenRouterTranscriptionProvider
 
 
@@ -21,11 +21,11 @@ def get_transcription_provider(*, settings: Settings | None = None) -> Transcrip
 
 
 __all__ = [
+    "OpenRouterTranscriptionProvider",
     "ProviderAuthError",
     "ProviderError",
     "ProviderResponseError",
     "TranscriptionProvider",
     "TranscriptionResult",
-    "OpenRouterTranscriptionProvider",
     "get_transcription_provider",
 ]

src/transcription/providers/openrouter.py

@@ -9,13 +9,12 @@ from typing import Any
 
 from openrouter import OpenRouter
 
-from transcription.config import Settings, get_settings
-from transcription.providers.base import (
-    ProviderAuthError,
-    ProviderError,
-    ProviderResponseError,
-    TranscriptionResult,
-)
+from transcription.config import Settings
+from transcription.config import get_settings
+from transcription.providers.base import ProviderAuthError
+from transcription.providers.base import ProviderError
+from transcription.providers.base import ProviderResponseError
+from transcription.providers.base import TranscriptionResult
 
 logger = logging.getLogger(__name__)
 
@@ -55,7 +54,7 @@ class OpenRouterTranscriptionProvider:
                 http_referer=request.http_referer,
                 x_open_router_title=request.x_open_router_title,
             )
-        except Exception as exc:  # noqa: BLE001
+        except Exception as exc:
             message = str(exc).lower()
             if "401" in message or "auth" in message or "api key" in message:
                 raise ProviderAuthError("OpenRouter authentication failed") from exc
@@ -111,10 +110,7 @@ class OpenRouterTranscriptionProvider:
             parts: list[str] = []
             for item in content:
                 text_part = None
-                if isinstance(item, dict):
-                    text_part = item.get("text")
-                else:
-                    text_part = self._get_optional_attr(item, "text")
+                text_part = item.get("text") if isinstance(item, dict) else self._get_optional_attr(item, "text")
 
                 if isinstance(text_part, str) and text_part.strip():
                     parts.append(text_part.strip())

src/transcription/services/__init__.py

@@ -1,30 +1,25 @@
 """Service layer exports."""
 
-from transcription.services.transcription import (
-    DEFAULT_PROMPT_FILE,
-    PromptLoadError,
-    TranscriptionError,
-    load_image_payload,
-    load_prompt_text,
-    transcribe_document_image,
-)
-from transcription.services.upload import (
-    SUPPORTED_UPLOAD_EXTENSIONS,
-    UploadError,
-    UploadJobResult,
-    create_upload_job,
-)
+from transcription.services.transcription import DEFAULT_PROMPT_FILE
+from transcription.services.transcription import PromptLoadError
+from transcription.services.transcription import TranscriptionError
+from transcription.services.transcription import load_image_payload
+from transcription.services.transcription import load_prompt_text
+from transcription.services.transcription import transcribe_document_image
+from transcription.services.upload import SUPPORTED_UPLOAD_EXTENSIONS
+from transcription.services.upload import UploadError
+from transcription.services.upload import UploadJobResult
+from transcription.services.upload import create_upload_job
 
 __all__ = [
     "DEFAULT_PROMPT_FILE",
+    "SUPPORTED_UPLOAD_EXTENSIONS",
     "PromptLoadError",
     "TranscriptionError",
-    "load_image_payload",
-    "load_prompt_text",
-    "transcribe_document_image",
-    "SUPPORTED_UPLOAD_EXTENSIONS",
     "UploadError",
     "UploadJobResult",
     "create_upload_job",
+    "load_image_payload",
+    "load_prompt_text",
+    "transcribe_document_image",
 ]
-

src/transcription/services/transcription.py

@@ -6,16 +6,16 @@ import logging
 import mimetypes
 from pathlib import Path
 
-from transcription.config import Settings, get_settings
-from transcription.errors import AppError, ErrorCategory
-from transcription.providers import (
-    ProviderAuthError,
-    ProviderError,
-    ProviderResponseError,
-    TranscriptionProvider,
-    TranscriptionResult,
-    get_transcription_provider,
-)
+from transcription.config import Settings
+from transcription.config import get_settings
+from transcription.errors import AppError
+from transcription.errors import ErrorCategory
+from transcription.providers import ProviderAuthError
+from transcription.providers import ProviderError
+from transcription.providers import ProviderResponseError
+from transcription.providers import TranscriptionProvider
+from transcription.providers import TranscriptionResult
+from transcription.providers import get_transcription_provider
 
 logger = logging.getLogger(__name__)
 

src/transcription/services/upload.py

@@ -5,14 +5,19 @@ from __future__ import annotations
 import logging
 from dataclasses import dataclass
 from pathlib import Path
-from uuid import UUID, uuid4
+from uuid import UUID
+from uuid import uuid4
 
 from sqlmodel import Session
 
-from transcription.config import Settings, get_settings
+from transcription.config import Settings
+from transcription.config import get_settings
 from transcription.db import get_session
-from transcription.errors import AppError, ErrorCategory
-from transcription.models import Document, Job, JobStatus
+from transcription.errors import AppError
+from transcription.errors import ErrorCategory
+from transcription.models import Document
+from transcription.models import Job
+from transcription.models import JobStatus
 
 logger = logging.getLogger(__name__)
 
@@ -69,7 +74,7 @@ def create_upload_job(
                     original_filename=filename,
                     stored_path=stored_path,
                 )
-    except Exception as exc:  # noqa: BLE001
+    except Exception as exc:
         _best_effort_delete(stored_path)
         raise UploadError(
             "Failed to create upload database records",

src/transcription/ui/__init__.py

@@ -12,5 +12,3 @@ def register_pages(app: FastAPI) -> None:
     register_upload_page()
     register_jobs_page()
     ui.run_with(app, mount_path="/ui", show_welcome_message=False)
-
-

src/transcription/ui/error_presenter.py

@@ -4,7 +4,9 @@ from __future__ import annotations
 
 from nicegui import ui
 
-from transcription.errors import AppError, ErrorCategory, classify_unexpected_error
+from transcription.errors import AppError
+from transcription.errors import ErrorCategory
+from transcription.errors import classify_unexpected_error
 
 
 def to_app_error(exc: Exception, *, operation: str) -> AppError:

src/transcription/ui/jobs_page.py

@@ -9,8 +9,11 @@ from nicegui import ui
 from sqlmodel import select
 
 from transcription.db import get_session
-from transcription.models import Document, Job, Transcript
-from transcription.ui.error_presenter import show_error, summarize_error
+from transcription.models import Document
+from transcription.models import Job
+from transcription.models import Transcript
+from transcription.ui.error_presenter import show_error
+from transcription.ui.error_presenter import summarize_error
 
 
 @dataclass(frozen=True)

src/transcription/ui/upload_page.py

@@ -7,8 +7,11 @@ from dataclasses import dataclass
 from nicegui import ui
 from nicegui.events import UploadEventArguments
 
-from transcription.services.upload import UploadError, UploadJobResult, create_upload_job
-from transcription.ui.error_presenter import show_error, summarize_error
+from transcription.services.upload import UploadError
+from transcription.services.upload import UploadJobResult
+from transcription.services.upload import create_upload_job
+from transcription.ui.error_presenter import show_error
+from transcription.ui.error_presenter import summarize_error
 
 
 @dataclass

src/transcription/worker.py

@@ -4,17 +4,26 @@ from __future__ import annotations
 
 import logging
 import time
-from datetime import datetime, timezone
+from datetime import UTC
+from datetime import datetime
 from threading import Event
 
 from pydantic import ValidationError
 from sqlalchemy.engine import Engine
-from sqlmodel import Session, select
+from sqlmodel import Session
+from sqlmodel import select
 
-from transcription.config import Settings, get_settings
+from transcription.config import Settings
+from transcription.config import get_settings
 from transcription.db import get_session
-from transcription.errors import AppError, ErrorCategory, classify_unexpected_error, format_error_detail
-from transcription.models import Document, Job, JobStatus, Transcript
+from transcription.errors import AppError
+from transcription.errors import ErrorCategory
+from transcription.errors import classify_unexpected_error
+from transcription.errors import format_error_detail
+from transcription.models import Document
+from transcription.models import Job
+from transcription.models import JobStatus
+from transcription.models import Transcript
 from transcription.services.transcription import transcribe_document_image
 
 logger = logging.getLogger(__name__)
@@ -43,7 +52,7 @@ def _process_next_queued_job(*, session: Session) -> bool:
 
     logger.info("Picked queued job operation=worker.pick job_id=%s", job.id)
     job.status = JobStatus.PROCESSING
-    job.updated_at = datetime.now(timezone.utc)
+    job.updated_at = datetime.now(UTC)
     session.add(job)
     session.commit()
     session.refresh(job)
@@ -68,7 +77,7 @@ def _process_next_queued_job(*, session: Session) -> bool:
         result = transcribe_document_image(document.file_path)
         _upsert_transcript(session=session, job_id=job.id, text=result.text, error_detail=None)
         job.status = JobStatus.TRANSCRIBED
-        job.updated_at = datetime.now(timezone.utc)
+        job.updated_at = datetime.now(UTC)
         session.add(job)
         session.commit()
         logger.info(
@@ -77,7 +86,7 @@ def _process_next_queued_job(*, session: Session) -> bool:
             document.id,
             result.provider,
         )
-    except Exception as exc:  # noqa: BLE001
+    except Exception as exc:
         error = exc if isinstance(exc, AppError) else classify_unexpected_error(exc, operation="worker.process_job")
         settings = _get_worker_settings()
         if _should_retry(job=job, error=error, settings=settings):
@@ -131,7 +140,7 @@ def _requeue_for_retry(*, session: Session, job: Job, error: AppError, settings:
     _upsert_transcript(session=session, job_id=job.id, text=None, error_detail=format_error_detail(error))
     job.retry_count += 1
     job.status = JobStatus.QUEUED
-    job.updated_at = datetime.now(timezone.utc)
+    job.updated_at = datetime.now(UTC)
     session.add(job)
     session.commit()
     if settings.worker_retry_backoff_seconds > 0:
@@ -141,7 +150,7 @@ def _requeue_for_retry(*, session: Session, job: Job, error: AppError, settings:
 def _finalize_failed_job(*, session: Session, job: Job, error: AppError) -> None:
     _upsert_transcript(session=session, job_id=job.id, text=None, error_detail=format_error_detail(error))
     job.status = JobStatus.FAILED
-    job.updated_at = datetime.now(timezone.utc)
+    job.updated_at = datetime.now(UTC)
     session.add(job)
     session.commit()