US06-06: Automate Phase F End-to-End Acceptance

This commit is contained in:
2026-08-16 21:16:15 +02:00
parent ea65bb764c
commit db4c362b91
7 changed files with 573 additions and 3 deletions

View File

@@ -169,3 +169,42 @@ work_item/scripts/python -m pytest -m phase_e -q
bytes, and recovery after a restart).
Phases AD remain green in the full run above.
### Phase F acceptance gate
Phase F (Epic E06: archive lifecycle) is the only stage that *removes* originals
from the library, and the only one whose storage can walk away in someone's bag.
One command runs the archive fault-injection suites, the black-box archive and
restore API journeys, and the browser suite:
```bash
work_item/scripts/python -m pytest -m phase_f -q
```
- `tests/integration/test_archive_*.py` and `tests/integration/test_restore.py`
drive real files on real filesystems: preflight against a mounted, missing,
swapped, read-only, or full medium; copy-verify-remove and the same-filesystem
move path; and a crash at **every** persisted journal transition in both transfer
modes, asserting that no source is ever removed without a durable, byte-identical
archive copy.
- `tests/e2e/test_phase_f_pipeline.py` drives a real server and a real durable
worker over HTTP: preflight blockers (offline medium, wrong volume, insufficient
capacity, bytes changed after upload), a verified archive whose manifest, hashes,
and path history are checked on the medium itself, a worker killed at each of
`transferring`, `verified`, `removing`, `source_removed`, and `complete`, the
evidence-based recovery that follows, offline deduplication of an exact and a
fuzzy copy while the medium is away, mount return, restore, and a collision that
restores beside its occupant.
- **Archived is not missing.** An unmounted medium leaves its photos
`archived_offline` — still hashed, still in the duplicate indexes, still
previewable through their protected thumbnails — and a rescan neither prunes nor
flags them.
- **Ambiguity is never guessed.** A journal state the medium contradicts stays
`manual`, offers no automatic action, and keeps blocking further archiving until
a human decides.
- `tests/e2e/test_archive_ui.py` covers the browser journeys (preview with
destination identity and reclaimable bytes, blockers and mount instructions,
progress split into transfer/verification/removal, interruption and recovery,
offline browsing, restore, collision, keyboard confirmation, and reload).
Phases AE remain green in the full run above.

View File

@@ -208,9 +208,12 @@ class ArchiveService:
report["blockers"].append(
_issue(
"insufficient_capacity",
# The free-space number is deliberately left out: it drifts between
# two identical preflights, and the token is a digest of this text,
# so quoting it here would invalidate every approval instantly.
f"{report['totals']['bytes']} B plus a "
f"{self._config.archive_free_space_reserve_bytes} B reserve do not fit in "
f"{report['capacity']['free_bytes']} B of free space",
f"{self._config.archive_free_space_reserve_bytes} B reserve do not fit on "
"the medium",
)
)
report["backup"] = self._backup_probe()

View File

@@ -140,9 +140,11 @@ class RestoreService:
report["blockers"].append(
_issue(
"insufficient_capacity",
# No free-space number here: it drifts between two identical
# preflights and the token is a digest of this text (US06-06).
f"{report['totals']['bytes']} B plus a "
f"{self._config.archive_free_space_reserve_bytes} B reserve do not fit in "
f"{report['capacity']['free_bytes']} B of free space",
"the library",
)
)
if not items:

View File

@@ -494,6 +494,16 @@ class ArchiveStack:
self.server.stop()
self.server.start()
def restart_worker(self, *, extra_env: dict[str, str] | None = None) -> None:
"""Replace the worker — a healthy one after a crashed one, by default."""
if self.worker is not None and self.worker.poll() is None:
self.worker.kill()
self.worker.wait(timeout=10)
self.worker = start_worker(
self.seeded,
extra_env={"PHOTO_PIPELINE_ARCHIVE_FREE_SPACE_RESERVE_BYTES": "0", **(extra_env or {})},
)
def stop(self) -> None:
if self.worker is not None:
self.worker.kill()

View File

@@ -0,0 +1,505 @@
"""Phase F end-to-end acceptance (US06-06): archive lifecycle, black box.
Every journey drives a real ``photo_pipeline serve`` child process and a real
durable worker over HTTP — register a medium, preflight it, archive an album,
crash mid-transfer, recover, unmount the medium, rediscover the photos through
their hashes while they are unreachable, mount it again, restore, and collide.
Nothing is reached into: the medium is an ordinary directory whose marker file is
its identity, and unmounting it means taking that marker away, which is what the
application sees when a disk is unplugged.
Three invariants are asserted wherever they apply, because they are what make the
only *removing* stage safe:
- **No source is removed before its archive copy is verified.** Every crash barrier
is checked for the file still being somewhere: either in the library, or on the
medium hashing exactly as recorded.
- **Archived is not missing.** An unmounted medium leaves its photos
``archived_offline``, still hashed, still deduplicable, still previewable.
- **Restoring never overwrites.** A taken name comes back beside its occupant, and
the archived copy stays on the medium.
"""
from __future__ import annotations
import hashlib
import json
import shutil
from pathlib import Path
import httpx
import pytest
from tests.e2e._pipeline_harness import (
ArchiveStack,
mark_uploaded,
seed_album,
session_factory,
wait_until,
)
pytestmark = pytest.mark.phase_f
TIMEOUT = 20
ALBUM = "rome"
MANIFEST = "archive-manifest.jsonl"
# Every persisted transition the transfer can die at, in the order it reaches them.
BARRIERS = ["transferring", "verified", "removing", "source_removed", "complete"]
@pytest.fixture
def stack(tmp_path):
"""An analysed album with verified upload evidence — archivable, nothing else."""
seeded = seed_album(tmp_path)
mark_uploaded(seeded)
running = ArchiveStack(tmp_path, seeded)
try:
yield running
finally:
running.stop()
# ── helpers ──────────────────────────────────────────────────────────────────
def _preflight(stack, location_id: str, **body) -> dict:
response = httpx.post(
f"{stack.base}/api/v1/archive-preflight",
json={"location_id": location_id, **body},
timeout=TIMEOUT,
)
response.raise_for_status()
return response.json()
def _plan(stack, location_id: str, **body) -> dict:
report = _preflight(stack, location_id, **body)
response = httpx.post(
f"{stack.base}/api/v1/archive-plans",
json={"location_id": location_id, "token": report["token"], **body},
timeout=TIMEOUT,
)
response.raise_for_status()
return response.json()
def _apply(stack, plan_id: str) -> httpx.Response:
return httpx.post(f"{stack.base}/api/v1/archive-plans/{plan_id}/apply", timeout=TIMEOUT)
def _plan_state(stack, plan_id: str) -> dict:
return httpx.get(f"{stack.base}/api/v1/archive-plans/{plan_id}", timeout=TIMEOUT).json()
def _await_plan(stack, plan_id: str, states=("complete", "failed"), *, timeout: float = 60) -> dict:
return wait_until(
lambda: (lambda p: p if p.get("state") in states else None)(_plan_state(stack, plan_id)),
timeout=timeout,
)
def _archive_album(stack) -> dict:
"""Register, preflight, plan, apply, and wait for the run to finish."""
location = stack.register()
plan = _plan(stack, location["id"])
_apply(stack, plan["id"]).raise_for_status()
return {"location": location, "plan": _await_plan(stack, plan["id"])}
def _assets(stack) -> dict[str, dict]:
return {asset["id"]: asset for asset in stack.assets()}
def _recovery(stack) -> dict:
return httpx.get(f"{stack.base}/api/v1/archive-recovery", timeout=TIMEOUT).json()
def _resolve(stack) -> dict:
response = httpx.post(f"{stack.base}/api/v1/archive-recovery/resolve", timeout=TIMEOUT)
response.raise_for_status()
return response.json()
def _restore(stack, location_id: str) -> dict:
report = httpx.post(
f"{stack.base}/api/v1/restore-preflight",
json={"location_id": location_id},
timeout=TIMEOUT,
).json()
plan = httpx.post(
f"{stack.base}/api/v1/restore-plans",
json={"location_id": location_id, "token": report["token"]},
timeout=TIMEOUT,
)
plan.raise_for_status()
plan = plan.json()
httpx.post(
f"{stack.base}/api/v1/restore-plans/{plan['id']}/apply", timeout=TIMEOUT
).raise_for_status()
wait_until(
lambda: all(a["availability_state"] == "active" for a in stack.assets()), timeout=60
)
return {"preflight": report, "plan": plan}
def _sha256(path: Path) -> str:
return hashlib.sha256(path.read_bytes()).hexdigest()
def _contents(*roots: Path) -> set[str]:
"""Every photo byte-string reachable anywhere, keyed by hash."""
return {
_sha256(path)
for root in roots
for path in root.rglob("*.jpg")
if path.is_file() and not path.name.startswith(".")
}
def _manifest(stack) -> list[dict]:
path = stack.archive / ALBUM / MANIFEST
if not path.exists():
return []
return [json.loads(line) for line in path.read_text().splitlines() if line.strip()]
# ── preflight blockers ───────────────────────────────────────────────────────
def test_preflight_refuses_an_offline_medium_a_wrong_volume_and_a_full_disk(stack):
stack.start(worker=False)
location = stack.register()
ready = _preflight(stack, location["id"])
assert ready["state"] == "ready"
assert ready["totals"]["assets"] == 2
stack.unmount()
offline = _preflight(stack, location["id"])
assert offline["state"] == "blocked"
assert "location_offline" in {issue["code"] for issue in offline["blockers"]}
# A different disk mounted at the same place is not this medium.
(stack.archive / ArchiveStack.MARKER).write_text('{"media_id": "another-disk"}')
wrong = _preflight(stack, location["id"])
assert "wrong_volume" in {issue["code"] for issue in wrong["blockers"]}
# Nothing has been created, moved, or removed by any of that.
assert stack.plans() == []
assert sorted(p.name for p in (stack.seeded.lib / ALBUM).glob("*.jpg")) == ["a.jpg", "b.jpg"]
def test_preflight_refuses_capacity_it_cannot_prove_and_bytes_it_cannot_vouch_for(tmp_path):
seeded = seed_album(tmp_path)
mark_uploaded(seeded)
stack = ArchiveStack(tmp_path, seeded)
try:
# A reserve larger than any disk: the scope cannot be promised room.
stack.start(
worker=False,
extra_env={"PHOTO_PIPELINE_ARCHIVE_FREE_SPACE_RESERVE_BYTES": str(1 << 62)},
)
location = stack.register()
report = _preflight(stack, location["id"])
assert "insufficient_capacity" in {issue["code"] for issue in report["blockers"]}
# And a plan for a blocked scope is refused rather than half-created.
refused = httpx.post(
f"{stack.base}/api/v1/archive-plans",
json={"location_id": location["id"], "token": report["token"]},
timeout=TIMEOUT,
)
assert refused.status_code == 422
assert refused.json()["error"]["code"] == "blocked"
assert stack.plans() == []
finally:
stack.stop()
def test_an_album_whose_bytes_changed_after_upload_cannot_be_archived(stack):
stack.start(worker=False)
location = stack.register()
(stack.seeded.lib / ALBUM / "a.jpg").write_bytes(b"edited after the upload")
report = _preflight(stack, location["id"])
album = report["albums"][0]
assert album["state"] == "blocked"
assert "partial_scope" in {issue["code"] for issue in album["blockers"]}
assert "bytes_changed" in {
issue["code"] for asset in album["assets"] for issue in asset["blockers"]
}
assert report["state"] == "blocked"
# ── copy, verify, remove ─────────────────────────────────────────────────────
def test_an_archived_album_leaves_the_library_only_after_it_is_verified(stack):
stack.start()
before = _contents(stack.seeded.lib)
hashes = {a["id"]: a["current_sha256"] for a in stack.assets()}
result = _archive_album(stack)
plan = result["plan"]
assert plan["state"] == "complete"
assert {op["journal_state"] for op in plan["operations"]} == {"complete"}
# Same filesystem here, so the transfer took the atomic-move path — recorded as
# what actually happened, not as the plan's guess.
assert all(op["same_filesystem"] for op in plan["operations"])
# The bytes are on the medium, hashing exactly as recorded, and gone from the
# library. Not one photo was lost in between.
assert _contents(stack.archive) == before
assert not list((stack.seeded.lib / ALBUM).glob("*.jpg"))
for asset_id, sha256 in hashes.items():
asset = _assets(stack)[asset_id]
assert asset["current_path"] is None
assert asset["availability_state"] == "archived_online"
assert _sha256(stack.archive / asset["archive_path"]) == sha256
# The medium carries its own record of what it holds.
manifest = _manifest(stack)
assert {entry["asset_id"] for entry in manifest} == set(hashes)
assert {entry["sha256"] for entry in manifest} == set(hashes.values())
assert {entry["media_id"] for entry in manifest} == {result["location"]["media_id"]}
def test_the_archived_state_survives_a_server_restart(stack):
stack.start()
result = _archive_album(stack)
before = _assets(stack)
plan_before = _plan_state(stack, result["plan"]["id"])
stack.restart_server()
assert _assets(stack) == before
assert _plan_state(stack, result["plan"]["id"]) == plan_before
assert {a["availability_state"] for a in stack.assets()} == {"archived_online"}
# ── interruption at every persisted transition ───────────────────────────────
@pytest.mark.parametrize("barrier", BARRIERS)
def test_a_worker_killed_at_each_transition_loses_nothing_and_recovers(tmp_path, barrier):
# One photo, so the crash lands on the only operation and the end state is the
# recovery's own doing rather than a mixture with untouched work.
seeded = seed_album(tmp_path, names=("a.jpg",))
mark_uploaded(seeded)
stack = ArchiveStack(tmp_path, seeded)
try:
# Only the worker carries the crash barrier: it dies the instant this journal
# state is persisted, while the server stays up to be asked what happened.
stack.start(worker=False)
stack.restart_worker(extra_env={"PHOTO_PIPELINE_FAULT_AFTER": barrier})
before = _contents(stack.seeded.lib)
location = stack.register()
plan = _plan(stack, location["id"])
_apply(stack, plan["id"]).raise_for_status()
wait_until(lambda: stack.worker.poll() is not None, timeout=60)
assert stack.worker.returncode in (9, -9), "the worker should have been killed"
# Whatever the crash interrupted, every photo is still readable somewhere.
assert before <= _contents(stack.seeded.lib, stack.archive), f"content lost at {barrier}"
# And nothing was removed that had not been verified first.
for operation in _plan_state(stack, plan["id"])["operations"]:
source = Path(operation["source_path"])
if not source.exists():
archived = Path(operation["destination_path"])
assert archived.exists(), f"{barrier}: source removed without an archive copy"
assert _sha256(archived) == operation["expected_sha256"]
# Recovery is offered from evidence, resolves without a worker, and converges.
verdicts = _recovery(stack)
assert all(v["classification"] != "manual" for v in verdicts["operations"]), verdicts
_resolve(stack)
assert _recovery(stack)["operations"] == []
# Repeating it changes nothing.
assert _resolve(stack) == {"resumed": 0, "completed": 0, "manual": 0}
# Recovery finishes what was durable and re-plans what was not. Before the
# archive copy existed, that means putting the item back to `planned` with the
# original untouched; from `verified` onwards it means completing it.
stack.restart_server()
operation = _plan_state(stack, plan["id"])["operations"][0]
asset = next(iter(stack.assets()))
if barrier == "transferring":
assert operation["journal_state"] == "planned"
assert Path(operation["source_path"]).exists()
assert asset["availability_state"] == "active"
assert _contents(stack.seeded.lib) == before
else:
assert operation["journal_state"] == "complete"
assert not Path(operation["source_path"]).exists()
assert _contents(stack.archive) == before
assert asset["availability_state"] == "archived_online"
assert _sha256(stack.archive / asset["archive_path"]) == asset["current_sha256"]
assert {entry["sha256"] for entry in _manifest(stack)} == before
finally:
stack.stop()
def test_evidence_that_contradicts_the_journal_is_never_guessed(stack):
stack.start(worker=False)
location = stack.register()
plan = _plan(stack, location["id"])
# The journal claims a verified archive copy the medium does not have.
with session_factory(stack.seeded) as sf:
from photo_pipeline.services.archive_journal import ArchiveJournal
journal = ArchiveJournal(sf)
operation = journal.operations(plan["id"])[0]
journal.begin(operation["id"], worker_id="crashed", fencing_token=1)
journal.transition(operation["id"], "verified", fencing_token=1)
verdicts = _recovery(stack)
assert [v["classification"] for v in verdicts["operations"]] == ["manual"]
assert _resolve(stack)["manual"] == 1
# The source is untouched and the unresolved item keeps blocking a new archive.
assert (stack.seeded.lib / ALBUM / "a.jpg").exists()
blocked = _preflight(stack, location["id"])
assert "archive_pending" in {issue["code"] for issue in blocked["blockers"]}
# ── offline identity and deduplication ───────────────────────────────────────
def test_offline_photos_stay_hashed_previewable_and_deduplicable(stack):
stack.start()
result = _archive_album(stack)
archived = _assets(stack)
copy_source = stack.archive / next(iter(archived.values()))["archive_path"]
exact = stack.seeded.lib / "inbox" / "again.jpg"
exact.parent.mkdir(parents=True, exist_ok=True)
shutil.copy2(copy_source, exact)
stack.unmount()
scanned = httpx.post(f"{stack.base}/api/v1/inventory/scan", timeout=60)
scanned.raise_for_status()
# An unmounted medium is not a missing file.
assert scanned.json()["counts"].get("missing") is None
offline = {a["id"]: a for a in stack.assets() if a["id"] in archived}
assert {a["availability_state"] for a in offline.values()} == {"archived_offline"}
assert all(a["current_sha256"] for a in offline.values())
# The new active copy is recognised as the archived photo, not as a new one.
httpx.post(f"{stack.base}/api/v1/duplicates/detect", timeout=60).raise_for_status()
clusters = httpx.get(
f"{stack.base}/api/v1/duplicates/clusters", params={"limit": 50}, timeout=TIMEOUT
).json()["items"]
exact_clusters = [c for c in clusters if c["method"] == "exact"]
assert len(exact_clusters) == 1
detail = httpx.get(
f"{stack.base}/api/v1/duplicates/clusters/{exact_clusters[0]['id']}", timeout=TIMEOUT
).json()
canonical = next(m for m in detail["members"] if m["asset_id"] == detail["canonical_asset_id"])
assert canonical["availability_state"] == "archived_offline"
assert canonical["archive_location"] == result["location"]["name"]
assert canonical["preview"]["state"] == "ready" and canonical["preview"]["protected"]
# And the retained preview really is served while the medium is away.
thumbnail = httpx.get(
f"{stack.base}/api/v1/assets/{canonical['asset_id']}/thumbnail",
params={"size": 1280},
timeout=TIMEOUT,
)
assert thumbnail.status_code == 200
assert thumbnail.headers["content-type"] == "image/webp"
def test_a_fuzzy_offline_match_asks_for_the_medium_instead_of_guessing(stack):
stack.start()
result = _archive_album(stack)
archived = next(iter(_assets(stack).values()))
variant = stack.seeded.lib / "inbox" / "resized.jpg"
variant.parent.mkdir(parents=True, exist_ok=True)
_resize(stack.archive / archived["archive_path"], variant)
stack.unmount()
httpx.post(f"{stack.base}/api/v1/inventory/scan", timeout=60).raise_for_status()
httpx.post(f"{stack.base}/api/v1/duplicates/detect", timeout=60).raise_for_status()
clusters = httpx.get(
f"{stack.base}/api/v1/duplicates/clusters", params={"limit": 50}, timeout=TIMEOUT
).json()["items"]
perceptual = [c for c in clusters if c["method"] == "perceptual"]
assert len(perceptual) == 1
detail = httpx.get(
f"{stack.base}/api/v1/duplicates/clusters/{perceptual[0]['id']}", timeout=TIMEOUT
).json()
# A fuzzy match is never decided automatically, and full-resolution review names
# the medium to mount rather than guessing from the preview.
assert detail["state"] == "open" and detail["requires_confirmation"] is True
assert detail["mount_required"] == [result["location"]["name"]]
def test_mounting_the_medium_again_makes_the_originals_reachable(stack):
stack.start()
result = _archive_album(stack)
stack.unmount()
httpx.post(f"{stack.base}/api/v1/inventory/scan", timeout=60).raise_for_status()
assert {a["availability_state"] for a in stack.assets()} == {"archived_offline"}
# Restoring from a medium that is not there is refused, with its reason.
away = httpx.post(
f"{stack.base}/api/v1/restore-preflight",
json={"location_id": result["location"]["id"]},
timeout=TIMEOUT,
).json()
assert away["state"] == "blocked"
assert "location_offline" in {issue["code"] for issue in away["blockers"]}
stack.remount()
locations = httpx.get(f"{stack.base}/api/v1/archive-locations", timeout=TIMEOUT).json()
assert locations["locations"][0]["state"] == "online"
assert {a["availability_state"] for a in stack.assets()} == {"archived_online"}
# ── restore ──────────────────────────────────────────────────────────────────
def test_restoring_returns_the_bytes_without_losing_identity_or_the_archive(stack):
stack.start()
result = _archive_album(stack)
identities = set(_assets(stack))
hashes = {a["id"]: a["current_sha256"] for a in stack.assets()}
_restore(stack, result["location"]["id"])
restored = _assets(stack)
assert set(restored) == identities # the same photos, not new ones
for asset_id, sha256 in hashes.items():
asset = restored[asset_id]
assert asset["availability_state"] == "active"
assert _sha256(Path(asset["current_path"])) == sha256
# The archive copy is a copy: restoring empties nothing.
assert (stack.archive / asset["archive_path"]).exists()
stack.restart_server()
assert _assets(stack) == restored
def test_a_restore_comes_back_beside_an_occupant_never_over_it(stack):
stack.start()
result = _archive_album(stack)
squatter = stack.seeded.lib / ALBUM / "a.jpg"
squatter.parent.mkdir(parents=True, exist_ok=True)
squatter.write_bytes(b"a different photo lives here now")
report = _restore(stack, result["location"]["id"])["preflight"]
destinations = {item["destination_path"] for item in report["items"]}
assert any("(restored)" in destination for destination in destinations)
assert squatter.read_bytes() == b"a different photo lives here now"
assert (stack.seeded.lib / ALBUM / "a (restored).jpg").exists()
assert {a["availability_state"] for a in stack.assets()} == {"active"}
def _resize(source: Path, destination: Path, scale: float = 0.5) -> None:
from PIL import Image
with Image.open(source) as opened:
opened.resize(
(int(opened.width * scale), int(opened.height * scale)), Image.LANCZOS
).save(destination, quality=95)

View File

@@ -14,6 +14,7 @@ MAP = json.loads((REPO / "tests" / "story_traceability.json").read_text())["stor
PHASE_A_STORIES = {f"US01-0{n}" for n in range(1, 8)}
PHASE_D_STORIES = {f"US04-0{n}" for n in range(1, 7)}
PHASE_E_STORIES = {f"US05-0{n}" for n in range(1, 7)}
PHASE_F_STORIES = {f"US06-0{n}" for n in range(1, 7)}
def test_all_phase_a_stories_are_mapped():
@@ -32,6 +33,13 @@ def test_all_phase_e_stories_are_mapped():
assert PHASE_E_STORIES <= set(MAP)
def test_all_phase_f_stories_are_mapped():
"""US06-06 acceptance: every archive-lifecycle story, destination through
restore, is tied to automated tests — archiving is the only stage that removes
an original."""
assert PHASE_F_STORIES <= set(MAP)
def test_every_mapped_test_file_exists_and_is_nonempty():
for story, files in MAP.items():
assert files, f"{story} maps to no tests"

View File

@@ -140,6 +140,9 @@
],
"US06-05": [
"tests/e2e/test_archive_ui.py"
],
"US06-06": [
"tests/e2e/test_phase_f_pipeline.py"
]
}
}