US06-05: Operate Archive and Restore in the Browser (#81)

tests/e2e/_pipeline_harness.py

@@ -393,6 +393,115 @@ def mark_upload_ready(seeded: Seeded, *, unverified: tuple[str, ...] = ()) -> No
             session.commit()
 
 
+# ── Phase F: an archivable album and a mountable fake medium ─────────────────
+
+
+def mark_uploaded(seeded: Seeded, *, album: str = "rome") -> None:
+    """Give every seeded photo the verified upload evidence archiving requires.
+
+    Archiving refuses anything Immich is not proven to hold, and that proof is an
+    upload batch — recorded here as fixture state so the archive journeys do not
+    have to re-run an upload they are not testing.
+    """
+    from sqlalchemy import select
+
+    from photo_pipeline.models import Asset, UploadBatch, UploadItem
+    from photo_pipeline.services.hashing import sha256_file
+
+    with session_factory(seeded) as sf:
+        with sf() as session:
+            batch_id = str(uuid.uuid4())
+            session.add(
+                UploadBatch(
+                    id=batch_id,
+                    album=album,
+                    folder=str(seeded.lib / album),
+                    album_name=album,
+                    state="succeeded",
+                    preflight_token="v1:e2e",
+                    outcome_state="verified",
+                    created_at=NOW,
+                )
+            )
+            for asset in session.scalars(select(Asset)):
+                if not asset.current_path:
+                    continue
+                session.add(
+                    UploadItem(
+                        batch_id=batch_id,
+                        asset_id=asset.id,
+                        path=asset.current_path,
+                        sha256=sha256_file(asset.current_path),
+                        sha1="0" * 40,
+                        state="sent",
+                        outcome="uploaded",
+                    )
+                )
+            session.commit()
+
+
+class ArchiveStack:
+    """A seeded, archivable library plus the server, the worker, and a fake medium.
+
+    The medium is an ordinary directory whose marker file makes it identifiable;
+    ``unmount()`` takes that marker away, which is exactly what the application sees
+    when an external disk is unplugged.
+    """
+
+    MARKER = ".photo-pipeline-archive.json"
+
+    def __init__(self, tmp_path: Path, seeded: Seeded) -> None:
+        self.tmp_path = tmp_path
+        self.seeded = seeded
+        self.archive = tmp_path / "archive"
+        self.archive.mkdir(exist_ok=True)
+        self.server: Server | None = None
+        self.worker: subprocess.Popen | None = None
+        self.base = ""
+
+    def start(self, *, worker: bool = True, extra_env: dict[str, str] | None = None) -> "ArchiveStack":
+        env = {"PHOTO_PIPELINE_ARCHIVE_FREE_SPACE_RESERVE_BYTES": "0", **(extra_env or {})}
+        self.server = Server(self.seeded, extra_env=env).start()
+        self.base = self.server.base
+        if worker:
+            self.worker = start_worker(self.seeded, extra_env=env)
+        return self
+
+    def register(self, name: str = "external") -> dict:
+        response = httpx.post(
+            f"{self.base}/api/v1/archive-locations",
+            json={"name": name, "root": str(self.archive)},
+            timeout=20,
+        )
+        response.raise_for_status()
+        return response.json()
+
+    def unmount(self) -> None:
+        (self.archive / self.MARKER).rename(self.archive / f"{self.MARKER}.away")
+
+    def remount(self) -> None:
+        (self.archive / f"{self.MARKER}.away").rename(self.archive / self.MARKER)
+
+    def plans(self) -> list[dict]:
+        return httpx.get(f"{self.base}/api/v1/archive-plans", timeout=20).json()["plans"]
+
+    def assets(self) -> list[dict]:
+        return httpx.get(
+            f"{self.base}/api/v1/inventory/assets", params={"limit": 200}, timeout=20
+        ).json()["items"]
+
+    def restart_server(self) -> None:
+        self.server.stop()
+        self.server.start()
+
+    def stop(self) -> None:
+        if self.worker is not None:
+            self.worker.kill()
+            self.worker.wait(timeout=10)
+        if self.server is not None:
+            self.server.stop()
+
+
 class UploadStack:
     """A seeded, upload-ready library plus the server, worker, and fake Immich."""
 

tests/e2e/test_archive_ui.py

@@ -0,0 +1,302 @@
+"""Browser journeys for the archive view (US06-05).
+
+Archiving is the only stage that removes originals, so these journeys check the
+two things a browser must never get wrong about it: that the preview names exactly
+what would leave and where it would go, and that nothing offers an action the
+server would refuse. The medium is a real directory whose marker makes it
+identifiable; unmounting it is what an unplugged disk looks like from here.
+
+Nothing is mocked inside the browser: the transfer runs in the real worker process
+and the assertions read the filesystem afterwards.
+"""
+
+from __future__ import annotations
+
+import pytest
+from playwright.sync_api import expect
+
+from tests.e2e._pipeline_harness import (
+    ArchiveStack,
+    mark_uploaded,
+    seed_album,
+    session_factory,
+    wait_until,
+)
+
+pytestmark = pytest.mark.phase_f  # part of the Phase F acceptance gate (US06-06)
+
+TIMEOUT = 10
+RUN_TIMEOUT = 30_000
+
+
+@pytest.fixture
+def stack(tmp_path):
+    seeded = seed_album(tmp_path)
+    mark_uploaded(seeded)
+    running = ArchiveStack(tmp_path, seeded)
+    try:
+        yield running
+    finally:
+        running.stop()
+
+
+def _open(page, stack) -> None:
+    page.goto(f"{stack.base}/app/#/archive")
+    page.get_by_test_id("archive-locations").wait_for()
+
+
+def _archive(page, stack) -> None:
+    """Confirm the archive and wait for the worker to finish the run."""
+    _open(page, stack)
+    page.get_by_test_id("start-archive").click()
+    expect(page.get_by_test_id("detail-state")).to_have_text("complete", timeout=RUN_TIMEOUT)
+
+
+def _archived_paths(stack) -> list[str]:
+    return sorted(p.name for p in (stack.archive / "rome").glob("*.jpg"))
+
+
+# ── preview and confirmation ─────────────────────────────────────────────────
+
+
+def test_the_preview_names_the_scope_destination_and_reclaimable_bytes(page, stack):
+    errors = []
+    page.on("console", lambda m: errors.append(m.text) if m.type == "error" else None)
+    stack.start(worker=False)
+    location = stack.register()
+    _open(page, stack)
+
+    row = page.get_by_test_id("location-row").first
+    expect(row.get_by_test_id("location-label")).to_have_text("external")
+    expect(row.get_by_test_id("location-media")).to_have_text(location["media_id"])
+    expect(row.get_by_test_id("location-state")).to_have_text("online")
+
+    album = page.get_by_test_id("archive-album-row").first
+    expect(album.get_by_test_id("album-name")).to_have_text("rome")
+    expect(album.get_by_test_id("album-destination")).to_have_text(str(stack.archive / "rome"))
+    expect(album.get_by_test_id("album-assets")).to_have_text("2")
+    expect(album.get_by_test_id("album-state")).to_have_text("ready")
+    # Same filesystem here, so the transfer method is the move path — and it is
+    # named, because copy-verify-remove and move fail differently.
+    expect(album.get_by_test_id("album-method")).to_contain_text("move")
+
+    expect(page.get_by_test_id("destination-identity")).to_contain_text(location["media_id"])
+    expect(page.get_by_test_id("capacity")).to_contain_text("reserve")
+    expect(page.get_by_test_id("start-archive")).to_contain_text("Archive 1 album(s) · reclaim")
+    expect(page.get_by_test_id("start-archive")).to_be_enabled()
+    assert stack.plans() == [], "previewing may not create anything"
+    assert errors == [], f"console errors: {errors}"
+
+
+def test_an_offline_medium_blocks_the_confirmation_and_says_what_to_mount(page, stack):
+    stack.start(worker=False)
+    location = stack.register()
+    stack.unmount()
+    _open(page, stack)
+
+    expect(page.get_by_test_id("location-state")).to_have_text("offline")
+    expect(page.get_by_test_id("preflight-blocker").first).to_have_attribute(
+        "data-code", "location_offline"
+    )
+    instruction = page.get_by_test_id("mount-instruction")
+    expect(instruction).to_contain_text("external")
+    expect(instruction).to_contain_text(location["media_id"])
+    expect(page.get_by_test_id("start-archive")).to_be_disabled()
+
+
+def test_an_unuploaded_album_is_blocked_with_its_reason(page, stack):
+    # No upload evidence at all: archiving would remove the only copy.
+    seeded = stack.seeded
+    with session_factory(seeded) as sf:
+        from sqlalchemy import delete
+
+        from photo_pipeline.models import UploadItem
+
+        with sf() as session:
+            session.execute(delete(UploadItem))
+            session.commit()
+    stack.start(worker=False)
+    stack.register()
+    _open(page, stack)
+
+    expect(page.get_by_test_id("album-state")).to_have_text("blocked")
+    expect(page.get_by_test_id("album-blocker").first).to_have_attribute(
+        "data-code", "partial_scope"
+    )
+    expect(page.get_by_test_id("start-archive")).to_be_disabled()
+
+
+# ── running, progress, reload ────────────────────────────────────────────────
+
+
+def test_a_confirmed_archive_runs_and_separates_transfer_verify_and_removal(page, stack):
+    stack.start()
+    stack.register()
+    _archive(page, stack)
+
+    expect(page.get_by_test_id("count-complete")).to_have_text("complete: 2")
+    expect(page.get_by_test_id("count-failed")).to_have_text("failed: 0")
+    expect(page.get_by_test_id("count-transfer")).to_have_text("transfer: 0")
+    expect(page.get_by_test_id("count-verified")).to_have_text("verified: 0")
+    expect(page.get_by_test_id("count-removing")).to_have_text("removing: 0")
+    expect(page.get_by_test_id("operation-phase").first).to_have_text("complete")
+
+    # The library really lost the originals and the medium really holds them.
+    assert _archived_paths(stack) == ["a.jpg", "b.jpg"]
+    assert not (stack.seeded.lib / "rome" / "a.jpg").exists()
+    assert {a["availability_state"] for a in stack.assets()} == {"archived_online"}
+
+
+def test_the_run_survives_a_reload_because_the_state_is_the_servers(page, stack):
+    stack.start()
+    stack.register()
+    _archive(page, stack)
+
+    page.reload()
+    page.get_by_test_id("plan-detail").wait_for()
+    expect(page.get_by_test_id("detail-state")).to_have_text("complete")
+    expect(page.get_by_test_id("count-complete")).to_have_text("complete: 2")
+    # And the run stays addressable by its own URL.
+    plan_id = stack.plans()[0]["id"]
+    page.goto(f"{stack.base}/app/#/archive?plan={plan_id}")
+    expect(page.get_by_test_id("plan-detail")).to_have_attribute("data-plan", plan_id)
+
+
+# ── recovery ─────────────────────────────────────────────────────────────────
+
+
+def test_an_interrupted_transfer_is_shown_with_evidence_and_a_safe_action(page, stack):
+    stack.start(worker=False)
+    stack.register()
+    _open(page, stack)
+    page.get_by_test_id("start-archive").click()
+    expect(page.get_by_test_id("archive-result")).to_be_visible()
+    # No worker ran, so every item is still planned; leave one mid-transfer as a
+    # crash would: intent recorded, nothing published, source intact.
+    _interrupt(stack)
+
+    page.reload()
+    page.get_by_test_id("archive-recovery").wait_for()
+    row = page.get_by_test_id("recovery-row").first
+    expect(row).to_have_attribute("data-classification", "resumable")
+    expect(row.get_by_test_id("recovery-reason")).to_contain_text("source present")
+    page.get_by_test_id("resolve-recovery").click()
+    expect(page.get_by_test_id("archive-recovery")).to_have_count(0)
+    assert (stack.seeded.lib / "rome" / "a.jpg").exists(), "recovery may not move anything"
+
+
+def test_ambiguous_evidence_offers_no_action_at_all(page, stack):
+    stack.start(worker=False)
+    stack.register()
+    _open(page, stack)
+    page.get_by_test_id("start-archive").click()
+    expect(page.get_by_test_id("archive-result")).to_be_visible()
+    # Journal says the copy is verified, but the medium holds nothing: no evidence
+    # supports either finishing or retrying this item.
+    _interrupt(stack, state="verified")
+
+    page.reload()
+    page.get_by_test_id("archive-recovery").wait_for()
+    expect(page.get_by_test_id("recovery-row").first).to_have_attribute(
+        "data-classification", "manual"
+    )
+    expect(page.get_by_test_id("recovery-manual")).to_be_visible()
+    expect(page.get_by_test_id("resolve-recovery")).to_have_count(0)
+    expect(page.get_by_test_id("no-safe-recovery")).to_be_visible()
+
+
+def _interrupt(stack, *, state: str = "transferring") -> None:
+    """Leave the plan's first operation in a non-terminal journal state."""
+    with session_factory(stack.seeded) as sf:
+        from photo_pipeline.services.archive_journal import ArchiveJournal
+
+        journal = ArchiveJournal(sf)
+        plan_id = stack.plans()[0]["id"]
+        operation = journal.operations(plan_id)[0]
+        journal.begin(operation["id"], worker_id="crashed", fencing_token=1)
+        if state != "transferring":
+            journal.transition(operation["id"], state, fencing_token=1)
+
+
+# ── offline browsing and restore ─────────────────────────────────────────────
+
+
+def test_archived_photos_stay_browsable_while_the_medium_is_away(page, stack):
+    stack.start()
+    stack.register()
+    _archive(page, stack)
+    stack.unmount()
+
+    page.reload()
+    page.get_by_test_id("archived-assets").wait_for()
+    row = page.get_by_test_id("archived-row").first
+    expect(row.get_by_test_id("archived-availability")).to_have_text("archived · medium away")
+    expect(row.get_by_test_id("archived-path")).to_contain_text("rome/")
+    expect(row.get_by_test_id("archived-medium")).to_have_text("external")
+    expect(page.get_by_test_id("mount-instruction")).to_contain_text("external")
+    # The retained protected preview is served even though the original is gone.
+    preview = row.get_by_test_id("archived-preview")
+    assert preview.evaluate("img => img.complete && img.naturalWidth > 0")
+    # Restoring is impossible right now, and says so instead of failing later.
+    expect(page.get_by_test_id("start-restore")).to_be_disabled()
+
+
+def test_restoring_brings_the_photos_back_without_losing_identity(page, stack):
+    stack.start()
+    stack.register()
+    _archive(page, stack)
+    before = {asset["id"] for asset in stack.assets()}
+
+    page.reload()
+    page.get_by_test_id("restore").wait_for()
+    expect(page.get_by_test_id("restore-row").first.get_by_test_id("restore-destination")).to_contain_text(
+        str(stack.seeded.lib / "rome")
+    )
+    page.get_by_test_id("start-restore").click()
+    wait_until(
+        lambda: all(a["availability_state"] == "active" for a in stack.assets()),
+        timeout=30,
+    )
+
+    assert {asset["id"] for asset in stack.assets()} == before  # same identities
+    assert (stack.seeded.lib / "rome" / "a.jpg").exists()
+    assert _archived_paths(stack) == ["a.jpg", "b.jpg"]  # the archive copy stays
+
+
+def test_a_taken_name_is_restored_beside_it_never_over_it(page, stack):
+    stack.start()
+    stack.register()
+    _archive(page, stack)
+    squatter = stack.seeded.lib / "rome" / "a.jpg"
+    squatter.parent.mkdir(parents=True, exist_ok=True)
+    squatter.write_bytes(b"a different photo now lives here")
+
+    page.reload()
+    page.get_by_test_id("restore").wait_for()
+    destinations = page.get_by_test_id("restore-destination").all_inner_texts()
+    assert any("(restored)" in text for text in destinations), destinations
+
+    page.get_by_test_id("start-restore").click()
+    wait_until(
+        lambda: all(a["availability_state"] == "active" for a in stack.assets()),
+        timeout=30,
+    )
+    assert squatter.read_bytes() == b"a different photo now lives here"
+    assert (stack.seeded.lib / "rome" / "a (restored).jpg").exists()
+
+
+# ── keyboard ─────────────────────────────────────────────────────────────────
+
+
+def test_the_whole_archive_can_be_confirmed_from_the_keyboard(page, stack):
+    stack.start()
+    stack.register()
+    _open(page, stack)
+
+    button = page.get_by_test_id("start-archive")
+    button.focus()
+    expect(button).to_be_focused()
+    page.keyboard.press("Enter")
+
+    expect(page.get_by_test_id("detail-state")).to_have_text("complete", timeout=RUN_TIMEOUT)
+    assert _archived_paths(stack) == ["a.jpg", "b.jpg"]