Step 5 implemented

pyproject.toml

@@ -12,6 +12,8 @@ description = "Historical document transcription system"
 readme = "README.md"
 requires-python = ">=3.12"
 dependencies = [
+    "fastapi>=0.138.0",
+    "nicegui>=3.13.0",
     "openrouter>=0.7.0",
     "pydantic>=2.13.4",
     "pydantic-settings>=2.9.1",

src/transcription/api/__init__.py

@@ -0,0 +1 @@
+"""API route modules for the transcription app."""

src/transcription/api/health.py

@@ -0,0 +1,16 @@
+"""Health endpoint routes."""
+
+from fastapi import APIRouter
+
+router = APIRouter()
+
+
+def healthz() -> dict[str, str]:
+    """Return a simple health status payload."""
+    return {"status": "ok"}
+
+
+@router.get("/healthz")
+def healthz_route() -> dict[str, str]:
+    """Route wrapper for health status payload."""
+    return healthz()

src/transcription/app.py

@@ -0,0 +1,61 @@
+"""Application factory and lifespan wiring for the transcription app."""
+
+from __future__ import annotations
+
+from contextlib import asynccontextmanager
+from threading import Event, Thread
+
+from fastapi import FastAPI
+
+from transcription.api.health import router as health_router
+from transcription.config import get_settings, setup_logging
+from transcription.db import create_all
+from transcription.ui import register_pages
+from transcription.worker import run_worker_loop
+
+
+def _start_worker(app: FastAPI) -> None:
+    stop_event = Event()
+    worker_thread = Thread(
+        target=run_worker_loop,
+        kwargs={"stop_event": stop_event, "poll_interval_seconds": 1.0},
+        daemon=True,
+    )
+    worker_thread.start()
+    app.state.worker_stop_event = stop_event
+    app.state.worker_thread = worker_thread
+
+
+def _stop_worker(app: FastAPI) -> None:
+    stop_event = getattr(app.state, "worker_stop_event", None)
+    worker_thread = getattr(app.state, "worker_thread", None)
+
+    if stop_event is not None:
+        stop_event.set()
+    if worker_thread is not None:
+        worker_thread.join(timeout=2.0)
+
+
+@asynccontextmanager
+async def _lifespan(app: FastAPI):
+    setup_logging()
+    create_all()
+
+    settings = get_settings()
+    settings.upload_dir.mkdir(parents=True, exist_ok=True)
+    settings.prompt_dir.mkdir(parents=True, exist_ok=True)
+
+    _start_worker(app)
+    try:
+        yield
+    finally:
+        _stop_worker(app)
+
+
+def create_app() -> FastAPI:
+    """Create and configure the FastAPI application."""
+    app = FastAPI(title="Transcription", lifespan=_lifespan)
+    register_pages(app)
+    app.include_router(health_router)
+    return app
+

src/transcription/ui/__init__.py

@@ -0,0 +1,16 @@
+"""UI page registration exports."""
+
+from fastapi import FastAPI
+from nicegui import ui
+
+from transcription.ui.jobs_page import register_page as register_jobs_page
+from transcription.ui.upload_page import register_page as register_upload_page
+
+
+def register_pages(app: FastAPI) -> None:
+    """Register all NiceGUI pages and mount them onto the FastAPI app."""
+    register_upload_page()
+    register_jobs_page()
+    ui.run_with(app, mount_path="/ui", show_welcome_message=False)
+
+

src/transcription/ui/jobs_page.py

@@ -0,0 +1,135 @@
+"""Jobs list and detail page registration."""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from uuid import UUID
+
+from nicegui import ui
+from sqlmodel import select
+
+from transcription.db import get_session
+from transcription.models import Document, Job, Transcript
+
+
+@dataclass(frozen=True)
+class JobView:
+    """Read model for rendering job rows in the UI."""
+
+    id: UUID
+    status: str
+    created_at: str
+    updated_at: str
+
+
+def fetch_jobs() -> list[JobView]:
+    """Return jobs for display in most-recent-first order."""
+    with get_session() as session:
+        jobs = session.exec(select(Job).order_by(Job.created_at.desc())).all()
+        return [
+            JobView(
+                id=job.id,
+                status=job.status.value,
+                created_at=job.created_at.isoformat(),
+                updated_at=job.updated_at.isoformat(),
+            )
+            for job in jobs
+        ]
+
+
+def fetch_job_detail(job_id: UUID) -> tuple[Job | None, Document | None, Transcript | None]:
+    """Return job, document, and transcript for detail view."""
+    with get_session() as session:
+        job = session.get(Job, job_id)
+        if job is None:
+            return None, None, None
+        document = session.get(Document, job.document_id)
+        transcript = session.exec(select(Transcript).where(Transcript.job_id == job.id)).first()
+        return job, document, transcript
+
+
+def register_page() -> None:
+    """Register jobs list and detail routes."""
+
+    @ui.page("/jobs")
+    def jobs_page() -> None:
+        ui.label("Transcription Jobs")
+        status = ui.label("Ready")
+        table_container = ui.column()
+
+        def render_table() -> None:
+            table_container.clear()
+            jobs = fetch_jobs()
+            with table_container:
+                if not jobs:
+                    ui.label("No jobs yet.")
+                    return
+                rows = [
+                    {
+                        "id": str(job.id),
+                        "status": job.status,
+                        "created_at": job.created_at,
+                        "updated_at": job.updated_at,
+                    }
+                    for job in jobs
+                ]
+                ui.table(
+                    columns=[
+                        {"name": "id", "label": "Job ID", "field": "id"},
+                        {"name": "status", "label": "Status", "field": "status"},
+                        {"name": "created_at", "label": "Created", "field": "created_at"},
+                        {"name": "updated_at", "label": "Updated", "field": "updated_at"},
+                    ],
+                    rows=rows,
+                    row_key="id",
+                )
+                for row in rows:
+                    ui.link(f"Open {row['id']}", f"/jobs/{row['id']}")
+
+        def refresh() -> None:
+            status.text = "Refreshing..."
+            try:
+                render_table()
+                status.text = "Refreshed"
+            except Exception as exc:  # noqa: BLE001
+                status.text = f"Refresh failed: {exc}"
+
+        ui.button("Refresh", on_click=refresh)
+        render_table()
+        ui.link("Back to upload", "/")
+
+    @ui.page("/jobs/{job_id}")
+    def job_detail_page(job_id: str) -> None:
+        ui.label("Job Detail")
+        try:
+            parsed_id = UUID(job_id)
+        except ValueError:
+            ui.label("Invalid job id")
+            ui.link("Back to jobs", "/jobs")
+            return
+
+        job, document, transcript = fetch_job_detail(parsed_id)
+        if job is None:
+            ui.label("Job not found")
+            ui.link("Back to jobs", "/jobs")
+            return
+
+        ui.label(f"Job ID: {job.id}")
+        ui.label(f"Status: {job.status.value}")
+        ui.label(f"Created: {job.created_at.isoformat()}")
+        ui.label(f"Updated: {job.updated_at.isoformat()}")
+
+        if document is not None:
+            ui.label(f"Filename: {document.filename}")
+            ui.label(f"File path: {document.file_path}")
+
+        if transcript is None:
+            ui.label("Transcript not available yet.")
+        elif transcript.text:
+            ui.label("Transcript:")
+            ui.markdown(transcript.text)
+        elif transcript.error_detail:
+            ui.label("Failure detail:")
+            ui.label(transcript.error_detail)
+
+        ui.link("Back to jobs", "/jobs")

src/transcription/ui/upload_page.py

@@ -0,0 +1,62 @@
+"""Upload page registration and handlers."""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+
+from nicegui import ui
+from nicegui.events import UploadEventArguments
+
+from transcription.services.upload import UploadError, UploadJobResult, create_upload_job
+
+
+@dataclass
+class UploadPageState:
+    """Simple state container for upload page feedback."""
+
+    loading: bool = False
+    message: str = ""
+
+
+def accepted_upload_types() -> str:
+    """Return accepted file type string for upload input."""
+    return ".jpg,.jpeg,.png,.tif,.tiff,.pdf"
+
+
+def submit_upload(*, filename: str, file_bytes: bytes) -> UploadJobResult:
+    """Create an upload job from incoming file data."""
+    return create_upload_job(filename=filename, file_bytes=file_bytes)
+
+
+def register_page() -> None:
+    """Register the upload page route."""
+
+    @ui.page("/")
+    def upload_page() -> None:
+        state = UploadPageState()
+        status_label = ui.label("Upload a document to start transcription.")
+
+        def on_upload(event: UploadEventArguments) -> None:
+            state.loading = True
+            status_label.text = "Uploading..."
+            try:
+                payload = event.content.read()
+                result = submit_upload(filename=event.name, file_bytes=payload)
+                state.message = f"Created job {result.job_id}"
+                status_label.text = state.message
+                ui.notify(state.message, type="positive")
+            except UploadError as exc:
+                state.message = str(exc)
+                status_label.text = f"Upload failed: {state.message}"
+                ui.notify(f"Upload failed: {state.message}", type="negative")
+            finally:
+                state.loading = False
+
+        ui.upload(
+            on_upload=on_upload,
+            auto_upload=True,
+            label="Select document file",
+        ).props(f"accept={accepted_upload_types()}")
+
+        with ui.row():
+            ui.link("View jobs", "/ui/jobs")

tests/api/test_health.py

@@ -0,0 +1,21 @@
+"""Tests for transcription.api.health."""
+
+from fastapi import FastAPI
+from fastapi.testclient import TestClient
+
+from transcription.api.health import router
+
+
+class TestHealthEndpoint:
+    """Verify /healthz endpoint behavior."""
+
+    def test_healthz_returns_ok_status(self):
+        """GET /healthz returns a healthy status payload."""
+        app = FastAPI()
+        app.include_router(router)
+        client = TestClient(app)
+
+        response = client.get("/healthz")
+
+        assert response.status_code == 200
+        assert response.json() == {"status": "ok"}

tests/artifacts/transcriptions/Omie_Writes_Home.pdf.txt

@@ -13,11 +13,8 @@ original envelope with its 2 cent stamp. The letter has a number of references t
 children. Peter was Louis; Polly was Edith; and the 'little black rascal' referred to Maurice.
 Miss Saville was the nurse at the Nome Hospital that was mentioned in the article by Inez in
 the family newsletter two years ago.
-
 Nome Alaska August 26, 1923
-
 My Dear Ethel et al.
-
 I don't know when I did write or when you did
 but I am going to write now however and never
 the less. But I wish I could talk (I can yet but I
@@ -26,7 +23,6 @@ and Polly sit up and listen and that little black
 rascal of yours would fairly sparkle with
 listening. Can't I see him listening now to all the
 yarns we told last summer?
-[photo of people on a frozen body of water with icebergs and a boat]
 You see, we-Miss Saville and I, took a trip north
 on the Buford and it was very interesting. We
 went north thru the Bering Strait into the Arctic and as far as the Ice Pack. There the captain
@@ -37,13 +33,13 @@ along the icebergs and the walrus were 'heisted' on board by the use of the cran
 tons of freight and the beasts were so huge that they made the pulleys just creak. They were
 over 12 feet long, as big around as three cows, had no feet but toenails on their flippers or
 flappers, no head but their body just suddenly ended with a hole for a mouth and big bristles
+
 all around it similar to a currycomb in coarseness; no ears but huge tusks of ivory. They are
 the most repulsive looking animals imaginable and tho I have always read about them I never
 expect such disagreeable looking creatures. They had a rough brown hairy skin and some of
 them looked warty. They must have weighed two ton at least. Ere we got them back to Nome
 to the natives they were getting extremely odiferous—in fact, you could scarcely stay on the
 ship with any degree of comfort unless you had per chance lost your sense of smell.
-
 Then we went north to a few minutes beyond the 70th degree of latitude and thot for awhile
 we would go to Wrangell Island where some men from Steffonsons ship were supposed to be
 stranded but we didn't get there and instead stopped at a small native village at Cape Serdz in
@@ -58,7 +54,6 @@ comfortable. The babies were in fur skins with the fur inside and they looked li
 bears with faces. I guess they had never seen white women, not so many at one time anyway.
 We went ashore in 2 life boats and a launch pulling them. On the launch was a six piece band
 playing and the rear of the last life boat was the movie man. 'Twas very thrilling.
-
 The other place we stopped was at Whalen, a trading post in Siberia. There these 'towerists'
 went wild. They rushed helter-skelter, hither and thither, here and there, trying to find
 something to buy. Prices raised right before your eyes. One would but something for $1.00
@@ -72,21 +67,19 @@ come down and the natives capture them. There was more junk brot aboard than bag
 do believe. And they say that at the first stop it was worse than here. The red flag was flying
 over Whalen and the Russian soldiers were there—a few, one or two or three, I forget the
 number.
-
 We got home yesterday morning at 5 a.m. but missed the first lighter in so had to stay out
 until 2:30. The girls had prepared a big meal for us and invited up the Hartfords and then let
 us talk. Miss Saville talked quite a bit. Any how if you folks don't like this I don't care, it is
 all I had to write about and I know Buster'ud listen anyway and I'd soak ole Peter's head if he
 didn't and Polly would in my lap and I don't know much about the youngest one of yours so
 likely he would be squawling. But we did surely enjoy our trip and were gone just long enuf.
+
 I expect there were 150 passengers on board and almost or more of the crew and helpers. We
 had a stateroom down next to the kitchen and 'twas pretty fierce for odor at times.
-
 I have had jobs nearly all summer but not very much in them. Next week, September 4,
 school opens. I wish they would wait for a week but you know these school men. Wouldn't
 make any special difference I suppose for I would just fritter away the time but still one likes
 to postpone the inevitable.
-
 I just now stopped and re-read your letter and it sure was a bird. I don't especially blame Ray
 for reading over your shoulder. It would seem, then that you have bright children. Maybe
 they do know something about Geography. But it is ridiculous to speak of Louis finishing the
@@ -95,19 +88,13 @@ am rather afraid he doesn't know much. I quite remember your little timid Mauric
 he shifted his affection from his Aunt Om and yelled and howled and screamed steadily for a
 week while his mother went to S.S. Ask him is he recalls this little interview. Do you suppose
 he does?
-
 Ever hear from Zen? or Inez? They don't seem to be very writing inclined tho Zen has done
 well this year. Even sent me a telegram a few weeks ago. Well, if anything else ever happens,
 I'll write again. Don't suppose it ever will, tho.
-
 Lots of love to all,
-
 Ome
-
 Reprinted from Cochran Chronicles, Volume 9, Number 1, November 1986
-
 © JECFA 1986
-
 Up
 
 jecochranclan.org ~ Contact webmaster

tests/artifacts/transcriptions/Rod_Moser_Letter_-_p1.jpg.txt

@@ -2,29 +2,29 @@ source: Rod Moser Letter - p1.jpg
 provider: openrouter
 model: google/gemini-2.5-flash
 ---
-JOHN ISBILL R. T. MOSER
+JOHN ISBILL R.T. MOSER
-
 ISBILL & MOSER
 DEALERS IN
 GENERAL MERCHANDISE
 
-Vonore, Tenn. [Janu]ary 27 – 1913
+Vonore, Tenn. January 27- 1913-
-Dear [Much Au][illegible]
+
-Has at hour a
+Dear Much Aunt Aduian
-few nigh [ago I] said a
+How are hour [sic] a
-letter f[rom] your folks, so
+few nights ago r [and] said a
-I [decide]d to [write] you
+letter from your folks, So
-a few lines myself &
+I decided to write you
-I am continuously a
+a few lines myself ok
-trip out just next summer
+I am contemplate [sic] a
- & I [want] [lo]t [of figures?] to go
+trip out west next summer
+r [and] want one of Aldons to go
 where I am.
 We are getting
-up in years & unmarried
+up in years r [and] remarrie[d]
-so you see the object o[f]
+So you are the object of
-my trip is to get a wife
+my trip, is to get a wife
-If th[ere] is any old maids
+to put in any old maid
-or widows out there I
+or widows out there, I
 want you to kiss them
-at my [hand] and my at them
+at my [illegible] or at them
 as soon as I get them

tests/test_app.py

@@ -0,0 +1,75 @@
+"""Tests for transcription.app."""
+
+import pytest
+from fastapi import FastAPI
+from fastapi.testclient import TestClient
+
+from transcription.app import create_app
+
+
+@pytest.mark.unit
+class TestAppFactory:
+    """Verify FastAPI app factory wiring."""
+
+    def test_create_app_returns_fastapi_instance(self):
+        """create_app returns a FastAPI application instance."""
+        app = create_app()
+        assert isinstance(app, FastAPI)
+
+
+@pytest.mark.integration
+class TestAppLifespan:
+    """Verify startup and shutdown lifecycle behavior."""
+
+    def test_startup_initializes_runtime_dependencies(self, monkeypatch):
+        """Startup initializes logging, schema, directories, and worker resources."""
+        calls = []
+
+        monkeypatch.setattr("transcription.app.setup_logging", lambda: calls.append("logging"))
+        monkeypatch.setattr("transcription.app.create_all", lambda: calls.append("schema"))
+        monkeypatch.setattr("transcription.app._start_worker", lambda _app: calls.append("start_worker"))
+        monkeypatch.setattr("transcription.app._stop_worker", lambda _app: calls.append("stop_worker"))
+
+        class _Dir:
+            def mkdir(self, parents: bool, exist_ok: bool):
+                calls.append("mkdir")
+
+        class _Settings:
+            upload_dir = _Dir()
+            prompt_dir = _Dir()
+
+        monkeypatch.setattr("transcription.app.get_settings", lambda: _Settings())
+
+        app = create_app()
+        with TestClient(app):
+            pass
+
+        assert "logging" in calls
+        assert "schema" in calls
+        assert "mkdir" in calls
+        assert "start_worker" in calls
+
+    def test_shutdown_stops_worker_resources(self, monkeypatch):
+        """Shutdown signals and stops worker resources cleanly."""
+        calls = []
+
+        monkeypatch.setattr("transcription.app.setup_logging", lambda: None)
+        monkeypatch.setattr("transcription.app.create_all", lambda: None)
+        monkeypatch.setattr("transcription.app._start_worker", lambda _app: calls.append("start_worker"))
+        monkeypatch.setattr("transcription.app._stop_worker", lambda _app: calls.append("stop_worker"))
+
+        class _Dir:
+            def mkdir(self, parents: bool, exist_ok: bool):
+                return None
+
+        class _Settings:
+            upload_dir = _Dir()
+            prompt_dir = _Dir()
+
+        monkeypatch.setattr("transcription.app.get_settings", lambda: _Settings())
+
+        app = create_app()
+        with TestClient(app):
+            pass
+
+        assert calls == ["start_worker", "stop_worker"]

tests/ui/test_jobs_page.py

@@ -0,0 +1,95 @@
+"""Tests for transcription.ui.jobs_page."""
+
+from uuid import uuid4
+
+import pytest
+
+from transcription.models import Document, Job, Transcript
+from transcription.ui.jobs_page import fetch_job_detail, fetch_jobs
+
+
+@pytest.mark.integration
+class TestJobsListBehavior:
+    """Verify job list data and rendering helpers."""
+
+    def test_fetch_jobs_returns_job_view_rows(self, session, monkeypatch):
+        """fetch_jobs returns normalized JobView rows for UI consumption."""
+        document = Document(filename="letter.jpg", file_path="uploads/letter.jpg")
+        session.add(document)
+        session.commit()
+        session.refresh(document)
+
+        job = Job(document_id=document.id)
+        session.add(job)
+        session.commit()
+
+        class _SessionContext:
+            def __enter__(self):
+                return session
+
+            def __exit__(self, exc_type, exc, tb):
+                return False
+
+        monkeypatch.setattr("transcription.ui.jobs_page.get_session", lambda: _SessionContext())
+
+        rows = fetch_jobs()
+
+        assert len(rows) == 1
+        assert rows[0].id == job.id
+        assert rows[0].status == "queued"
+
+
+@pytest.mark.integration
+class TestJobDetailBehavior:
+    """Verify job detail retrieval behavior."""
+
+    def test_fetch_job_detail_returns_related_records_when_present(self, session, monkeypatch):
+        """fetch_job_detail returns job, document, and transcript when available."""
+        document = Document(filename="typed.jpg", file_path="uploads/typed.jpg")
+        session.add(document)
+        session.commit()
+        session.refresh(document)
+
+        job = Job(document_id=document.id)
+        session.add(job)
+        session.commit()
+        session.refresh(job)
+
+        transcript = Transcript(job_id=job.id, text="Transcript text")
+        session.add(transcript)
+        session.commit()
+
+        class _SessionContext:
+            def __enter__(self):
+                return session
+
+            def __exit__(self, exc_type, exc, tb):
+                return False
+
+        monkeypatch.setattr("transcription.ui.jobs_page.get_session", lambda: _SessionContext())
+
+        fetched_job, fetched_document, fetched_transcript = fetch_job_detail(job.id)
+
+        assert fetched_job is not None
+        assert fetched_document is not None
+        assert fetched_transcript is not None
+        assert fetched_job.id == job.id
+        assert fetched_document.id == document.id
+        assert fetched_transcript.job_id == job.id
+
+    def test_fetch_job_detail_returns_nones_for_missing_job(self, session, monkeypatch):
+        """fetch_job_detail returns triple None when job does not exist."""
+        class _SessionContext:
+            def __enter__(self):
+                return session
+
+            def __exit__(self, exc_type, exc, tb):
+                return False
+
+        monkeypatch.setattr("transcription.ui.jobs_page.get_session", lambda: _SessionContext())
+
+        fetched_job, fetched_document, fetched_transcript = fetch_job_detail(uuid4())
+
+        assert fetched_job is None
+        assert fetched_document is None
+        assert fetched_transcript is None

tests/ui/test_pages_registration.py

@@ -0,0 +1,26 @@
+"""Tests for UI page registration wiring."""
+
+from fastapi import FastAPI
+from fastapi.testclient import TestClient
+import pytest
+
+from transcription.ui import register_pages
+
+
+@pytest.mark.integration
+class TestPageRegistration:
+    """Verify page registration and route wiring."""
+
+    def test_register_pages_adds_expected_routes(self):
+        """register_pages wires upload and jobs routes into the app."""
+        app = FastAPI()
+        register_pages(app)
+        app.add_api_route("/healthz", lambda: {"status": "ok"}, methods=["GET"])
+
+        client = TestClient(app)
+        ui_response = client.get("/ui")
+        health_response = client.get("/healthz")
+
+        assert ui_response.status_code == 200
+        assert health_response.status_code == 200
+        assert health_response.json() == {"status": "ok"}

tests/ui/test_upload_page.py

@@ -0,0 +1,53 @@
+"""Tests for transcription.ui.upload_page."""
+
+from pathlib import Path
+from uuid import uuid4
+
+import pytest
+
+from transcription.services.upload import UploadError, UploadJobResult
+from transcription.ui import upload_page
+
+
+@pytest.mark.unit
+class TestUploadPageBehavior:
+    """Verify upload page helper and submission behavior."""
+
+    def test_accepted_upload_types_contains_supported_extensions(self):
+        """accepted_upload_types includes all MVP-supported upload extensions."""
+        accepted = upload_page.accepted_upload_types()
+        assert ".jpg" in accepted
+        assert ".jpeg" in accepted
+        assert ".png" in accepted
+        assert ".tif" in accepted
+        assert ".tiff" in accepted
+        assert ".pdf" in accepted
+
+    def test_submit_upload_calls_upload_service(self, monkeypatch):
+        """submit_upload delegates file persistence and job creation to upload service."""
+        expected = UploadJobResult(
+            document_id=uuid4(),
+            job_id=uuid4(),
+            stored_path=Path("uploads/mock.jpg"),
+            original_filename="mock.jpg",
+        )
+
+        def fake_create_upload_job(*, filename: str, file_bytes: bytes):
+            assert filename == "mock.jpg"
+            assert file_bytes == b"bytes"
+            return expected
+
+        monkeypatch.setattr(upload_page, "create_upload_job", fake_create_upload_job)
+
+        result = upload_page.submit_upload(filename="mock.jpg", file_bytes=b"bytes")
+        assert result == expected
+
+    def test_submit_upload_surfaces_upload_error(self, monkeypatch):
+        """submit_upload raises UploadError for invalid upload payloads."""
+        def fake_create_upload_job(*, filename: str, file_bytes: bytes):
+            raise UploadError("invalid payload")
+
+        monkeypatch.setattr(upload_page, "create_upload_job", fake_create_upload_job)
+
+        with pytest.raises(UploadError):
+            upload_page.submit_upload(filename="bad.jpg", file_bytes=b"")