Files
FabledCurator/tests/test_api_sources.py
T
bvandeusenandClaude Opus 5 5aa8e3d81b
CI / lint (push) Successful in 2s
CI / extension-version (push) Successful in 2s
Build images / sign-extension (push) Successful in 3s
Build images / build-agent (push) Successful in 6s
CI / frontend-build (push) Successful in 20s
CI / backend-lint-and-test (push) Successful in 33s
Build images / build-web (push) Successful in 1m3s
Build images / smoke-web (push) Skipped
Build images / build-ml (push) Successful in 2m12s
Build images / promote (push) Skipped
CI / integration (push) Successful in 2m16s
fix: a stopped source is not a failing one, and cannot be deep-scanned (4279)
Ebi77 sat in the "1 source is failing" banner for six days with no action
available, reading `stranded by recovery sweep (no terminal status after
time_limit)`. Four things lined up:

1. The membership sweep did its job — saw `former_patron`, disabled the
   source, cleared its failure state. Clean at 02:50.
2. Twenty minutes later a deep scan was armed on it. `/backfill` had a
   credential pre-flight but NO `enabled` guard, while `/check` has carried
   one all along. The two trigger endpoints disagreed, and the ungated one is
   the one that arms the long walk.
3. Without a membership the walk cannot finish, never reaches a terminal
   status, and the recovery sweep strands it with consecutive_failures = 1.
4. Nothing could clear that. A disabled source is never scheduled, so no
   successful run resets the count; `SourceService.update` clears only on an
   explicit disable and it was already disabled; and the banner's Retry routes
   to `/check`, which refuses a disabled source. The card offered a button
   structurally incapable of acting on the only source it was showing.

`failing_sources_clause()` now means "enabled AND erroring". That also settles
a disagreement its two callers already had: the scheduler's count paired it
with `enabled.is_(True)` and `SourceService.list(failing=True)` did not, so
one counted Ebi77 and the other did not — exactly the drift the note above
that function warns about, which is why the test belongs IN the predicate
rather than beside it. The scheduler's now-duplicate clause is dropped so one
place decides.

`/backfill` gains the guard for start/recover/recapture. `stop` stays open on
a disabled source, or arming becomes a one-way door.

Migration 0101 clears failure state on sources that are already disabled — the
predicate fixes what the surfaces report, not what the rows carry, and the
rows are why the operator had no way out (lesson #4202). It matches what
`update` already does on an explicit disable, so rows disabled by any other
path come into line. Enabled sources are untouched: a real failure on a live
source must keep showing, which the second new test pins.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LVjrnpQjRgHdvq95rASoiR
2026-09-21 19:25:42 -04:00

487 lines
17 KiB
Python

import pytest
from backend.app.models import Artist, Source
pytestmark = pytest.mark.integration
@pytest.fixture(autouse=True)
def _stub_preflight_verify(monkeypatch):
"""Backfill/recover arms run a pre-flight credential verify (plan #703 #2)
which for Patreon would hit the network. Default it to 'valid' so the
endpoint tests stay network-free; the dedicated pre-flight tests override
this with a rejection/inconclusive verdict."""
from backend.app.services import download_backends as db_mod
async def _ok(**kwargs):
return (True, "Credentials valid")
monkeypatch.setattr(db_mod, "verify_source_credential", _ok)
@pytest.fixture
async def artist(db):
a = Artist(name="Alice", slug="alice")
db.add(a)
await db.commit()
return a
@pytest.mark.asyncio
async def test_list_failing_filter_returns_only_failing(client, artist, db):
healthy = Source(
artist_id=artist.id, platform="patreon", url="https://p/ok",
enabled=True, consecutive_failures=0,
)
broken = Source(
artist_id=artist.id, platform="pixiv", url="https://p/bad",
enabled=True, consecutive_failures=3, last_error="boom",
)
db.add_all([healthy, broken])
await db.commit()
resp = await client.get("/api/sources?failing=true")
assert resp.status_code == 200
body = await resp.get_json()
assert len(body) == 1
assert body[0]["consecutive_failures"] == 3
assert body[0]["last_error"] == "boom"
@pytest.mark.asyncio
async def test_schedule_status_shape(client):
resp = await client.get("/api/sources/schedule-status")
assert resp.status_code == 200
body = await resp.get_json()
assert set(body) == {
"last_tick_at", "next_due_at", "due_now", "auto_sources",
"failing_sources", "no_access_sources", "total_sources",
"platform_cooldowns",
}
assert isinstance(body["due_now"], int)
assert isinstance(body["auto_sources"], int)
# #387 B3: the front-door ribbon reads these two. Kept in the exact-set
# assertion deliberately — it is what catches a key being renamed out from
# under a consumer, which is how this test earned its keep.
assert isinstance(body["failing_sources"], int)
assert isinstance(body["no_access_sources"], int)
@pytest.mark.asyncio
async def test_create_list_get_delete(client, artist):
create = await client.post("/api/sources", json={
"artist_id": artist.id, "platform": "patreon",
"url": "https://patreon.com/alice",
})
assert create.status_code == 201
created = await create.get_json()
assert created["artist_name"] == "Alice"
sid = created["id"]
listing = await client.get("/api/sources")
assert listing.status_code == 200
assert len(await listing.get_json()) == 1
filtered = await client.get(f"/api/sources?artist_id={artist.id}")
assert filtered.status_code == 200
assert len(await filtered.get_json()) == 1
one = await client.get(f"/api/sources/{sid}")
assert one.status_code == 200
assert (await one.get_json())["id"] == sid
deleted = await client.delete(f"/api/sources/{sid}")
assert deleted.status_code == 204
assert (await client.get(f"/api/sources/{sid}")).status_code == 404
@pytest.mark.asyncio
async def test_create_kicks_off_backfill_for_enabled_source(client, artist, monkeypatch):
"""A new enabled source dispatches its first walk immediately (no waiting
for the next scheduler tick), unless its platform is in cooldown."""
delays: list = []
monkeypatch.setattr(
"backend.app.tasks.download.download_source.delay",
lambda *a, **k: delays.append(a),
)
resp = await client.post("/api/sources", json={
"artist_id": artist.id, "platform": "patreon",
"url": "https://patreon.com/kickoff",
})
assert resp.status_code == 201
sid = (await resp.get_json())["id"]
assert delays == [(sid,)]
@pytest.mark.asyncio
async def test_create_disabled_source_does_not_kick_off(client, artist, monkeypatch):
delays: list = []
monkeypatch.setattr(
"backend.app.tasks.download.download_source.delay",
lambda *a, **k: delays.append(a),
)
resp = await client.post("/api/sources", json={
"artist_id": artist.id, "platform": "patreon",
"url": "https://patreon.com/disabled", "enabled": False,
})
assert resp.status_code == 201
assert delays == []
@pytest.mark.asyncio
async def test_create_rejects_unknown_platform(client, artist):
resp = await client.post("/api/sources", json={
"artist_id": artist.id, "platform": "myspace", "url": "https://m/x",
})
assert resp.status_code == 400
body = await resp.get_json()
assert body["error"] == "unknown_platform"
assert "known" in body
@pytest.mark.asyncio
async def test_create_rejects_bad_config(client, artist):
resp = await client.post("/api/sources", json={
"artist_id": artist.id, "platform": "patreon",
"url": "https://p/a", "config_overrides": [1, 2, 3],
})
assert resp.status_code == 400
assert (await resp.get_json())["error"] == "invalid_config"
@pytest.mark.asyncio
async def test_create_rejects_empty_url(client, artist):
resp = await client.post("/api/sources", json={
"artist_id": artist.id, "platform": "patreon", "url": " ",
})
assert resp.status_code == 400
assert (await resp.get_json())["error"] == "empty_url"
@pytest.mark.asyncio
async def test_create_rejects_unknown_artist(client):
resp = await client.post("/api/sources", json={
"artist_id": 99999, "platform": "patreon", "url": "https://p/a",
})
assert resp.status_code == 404
@pytest.mark.asyncio
async def test_create_duplicate_returns_409_with_existing_id(client, artist):
a = await client.post("/api/sources", json={
"artist_id": artist.id, "platform": "patreon", "url": "https://p/a",
})
first = (await a.get_json())["id"]
b = await client.post("/api/sources", json={
"artist_id": artist.id, "platform": "patreon", "url": "https://p/a",
})
assert b.status_code == 409
body = await b.get_json()
assert body["error"] == "duplicate"
assert body["existing_id"] == first
@pytest.mark.asyncio
async def test_patch_updates_fields(client, artist):
create = await client.post("/api/sources", json={
"artist_id": artist.id, "platform": "patreon", "url": "https://p/a",
})
sid = (await create.get_json())["id"]
patch = await client.patch(f"/api/sources/{sid}", json={"enabled": False})
assert patch.status_code == 200
assert (await patch.get_json())["enabled"] is False
@pytest.mark.asyncio
async def test_get_404(client):
assert (await client.get("/api/sources/99999")).status_code == 404
@pytest.mark.asyncio
async def test_patch_404(client):
assert (await client.patch("/api/sources/99999", json={"enabled": False})).status_code == 404
@pytest.mark.asyncio
async def test_delete_404(client):
assert (await client.delete("/api/sources/99999")).status_code == 404
# --- FC-3d: SourceRecord surfaces consecutive_failures + next_check_at ----
@pytest.mark.asyncio
async def test_create_response_includes_fc3d_fields(client, artist):
resp = await client.post("/api/sources", json={
"artist_id": artist.id, "platform": "patreon",
"url": "https://patreon.com/alice-fc3d-new",
})
assert resp.status_code == 201
body = await resp.get_json()
assert body["consecutive_failures"] == 0
assert body["next_check_at"] is None # never checked yet
@pytest.mark.asyncio
async def test_list_derives_next_check_at_when_last_checked_set(
client, artist, db,
):
from datetime import UTC, datetime
from backend.app.models import Source
src = Source(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice-fc3d-checked", enabled=True,
consecutive_failures=0,
last_checked_at=datetime.now(UTC),
)
db.add(src)
await db.commit()
resp = await client.get("/api/sources")
body = await resp.get_json()
target = next(
r for r in body if r["url"] == "https://patreon.com/alice-fc3d-checked"
)
assert target["next_check_at"] is not None
assert "T" in target["next_check_at"] # ISO 8601
# --- Plan #544: POST /api/sources/{id}/backfill ----------------------------
@pytest.mark.asyncio
async def test_backfill_endpoint_start_and_stop(client, artist, db):
src = Source(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice-backfill", enabled=True,
)
db.add(src)
await db.commit()
sid = src.id
resp = await client.post(f"/api/sources/{sid}/backfill", json={"action": "start"})
assert resp.status_code == 200
body = await resp.get_json()
assert body["backfill_state"] == "running"
# GET reflects the running state.
one = await client.get(f"/api/sources/{sid}")
assert (await one.get_json())["backfill_state"] == "running"
stopped = await client.post(f"/api/sources/{sid}/backfill", json={"action": "stop"})
assert (await stopped.get_json())["backfill_state"] is None
@pytest.mark.asyncio
async def test_backfill_endpoint_refuses_a_disabled_source(client, artist, db):
"""#4279: a source FC deliberately stopped must not be armable for a deep
walk. Arming one is how Ebi77 got a failure nobody could clear — the walk
cannot complete without access, the recovery sweep strands it, and a
disabled source is never scheduled again to reset the count."""
src = Source(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice-stopped", enabled=False,
)
db.add(src)
await db.commit()
for action in ("start", "recover", "recapture"):
resp = await client.post(
f"/api/sources/{src.id}/backfill", json={"action": action},
)
assert resp.status_code == 400, action
assert (await resp.get_json())["error"] == "source_disabled"
@pytest.mark.asyncio
async def test_backfill_stop_still_works_on_a_disabled_source(client, artist, db):
"""Only the ARMING actions are gated. Cancelling a walk on a source that
was disabled mid-backfill must stay available, or the arm becomes a
one-way door."""
src = Source(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice-stopping", enabled=False,
config_overrides={"_backfill_state": "running"},
)
db.add(src)
await db.commit()
resp = await client.post(
f"/api/sources/{src.id}/backfill", json={"action": "stop"},
)
assert resp.status_code == 200
assert (await resp.get_json())["backfill_state"] is None
@pytest.mark.asyncio
async def test_backfill_endpoint_defaults_to_start(client, artist, db):
src = Source(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice-backfill-default", enabled=True,
)
db.add(src)
await db.commit()
resp = await client.post(f"/api/sources/{src.id}/backfill", json={})
body = await resp.get_json()
assert body["backfill_state"] == "running"
@pytest.mark.asyncio
async def test_backfill_endpoint_rejects_bad_action(client, artist, db):
src = Source(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice-backfill-bad", enabled=True,
)
db.add(src)
await db.commit()
bad = await client.post(f"/api/sources/{src.id}/backfill", json={"action": "nope"})
assert bad.status_code == 400
@pytest.mark.asyncio
async def test_backfill_endpoint_404_when_source_missing(client):
resp = await client.post("/api/sources/999999/backfill", json={"action": "start"})
assert resp.status_code == 404
@pytest.mark.asyncio
async def test_backfill_endpoint_recover_arms_bypass(client, artist, db):
"""Plan #697: action='recover' arms a backfill that bypasses the Patreon
seen-ledger; the response exposes backfill_bypass_seen=True so the UI badge
can label it 'Recovering'. Stop clears it."""
src = Source(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice-recover", enabled=True,
)
db.add(src)
await db.commit()
sid = src.id
resp = await client.post(f"/api/sources/{sid}/backfill", json={"action": "recover"})
assert resp.status_code == 200
body = await resp.get_json()
assert body["backfill_state"] == "running"
assert body["backfill_bypass_seen"] is True
stopped = await client.post(f"/api/sources/{sid}/backfill", json={"action": "stop"})
stopped_body = await stopped.get_json()
assert stopped_body["backfill_state"] is None
assert stopped_body["backfill_bypass_seen"] is False
@pytest.mark.asyncio
async def test_backfill_endpoint_recapture_arms_flag(client, artist, db):
"""#830: action='recapture' arms a backfill that re-grabs post bodies/links +
localizes on-disk inline images; the response exposes backfill_recapture=True
(badge 'Recapturing') and NOT backfill_bypass_seen. Stop clears it."""
src = Source(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice-recapture", enabled=True,
)
db.add(src)
await db.commit()
sid = src.id
resp = await client.post(f"/api/sources/{sid}/backfill", json={"action": "recapture"})
assert resp.status_code == 200
body = await resp.get_json()
assert body["backfill_state"] == "running"
assert body["backfill_recapture"] is True
assert body["backfill_bypass_seen"] is False
stopped = await client.post(f"/api/sources/{sid}/backfill", json={"action": "stop"})
stopped_body = await stopped.get_json()
assert stopped_body["backfill_state"] is None
assert stopped_body["backfill_recapture"] is False
# --- Plan #703 #2: pre-flight credential verify on backfill/recover arm -----
@pytest.mark.asyncio
async def test_arm_blocked_when_credential_rejected(client, artist, db, monkeypatch):
"""A definitively-rejected credential refuses the arm (409 + reason) instead
of starting a doomed walk; the source is NOT armed."""
from backend.app.services import download_backends as db_mod
async def _reject(**kwargs):
return (False, "Patreon rejected the credential — cookies expired")
monkeypatch.setattr(db_mod, "verify_source_credential", _reject)
src = Source(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice-preflight", enabled=True,
)
db.add(src)
await db.commit()
sid = src.id
resp = await client.post(f"/api/sources/{sid}/backfill", json={"action": "recover"})
assert resp.status_code == 409
assert "expired" in ((await resp.get_json()).get("detail") or "")
# Not armed.
one = await (await client.get(f"/api/sources/{sid}")).get_json()
assert one["backfill_state"] is None
@pytest.mark.asyncio
async def test_arm_proceeds_when_credential_inconclusive(client, artist, db, monkeypatch):
"""An inconclusive verify (network blip / drift) must NOT block the arm."""
from backend.app.services import download_backends as db_mod
async def _inconclusive(**kwargs):
return (None, "couldn't verify (network)")
monkeypatch.setattr(db_mod, "verify_source_credential", _inconclusive)
src = Source(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice-incon", enabled=True,
)
db.add(src)
await db.commit()
resp = await client.post(f"/api/sources/{src.id}/backfill", json={"action": "start"})
assert resp.status_code == 200
assert (await resp.get_json())["backfill_state"] == "running"
@pytest.mark.asyncio
async def test_stop_never_pre_flights(client, artist, db, monkeypatch):
from backend.app.services import download_backends as db_mod
async def _boom(**kwargs):
raise AssertionError("stop must not pre-flight verify")
monkeypatch.setattr(db_mod, "verify_source_credential", _boom)
src = Source(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice-stop", enabled=True,
)
db.add(src)
await db.commit()
resp = await client.post(f"/api/sources/{src.id}/backfill", json={"action": "stop"})
assert resp.status_code == 200
@pytest.mark.asyncio
async def test_gallery_dl_platform_arm_skips_pre_flight(client, artist, db, monkeypatch):
"""Pre-flight is gated to native-ingester platforms (cheap verify); a
gallery-dl source arms without the slow --simulate probe."""
from backend.app.services import download_backends as db_mod
async def _boom(**kwargs):
raise AssertionError("gallery-dl arm must not pre-flight verify")
monkeypatch.setattr(db_mod, "verify_source_credential", _boom)
src = Source(
artist_id=artist.id, platform="hentaifoundry",
url="https://www.hentai-foundry.com/user/x", enabled=True,
)
db.add(src)
await db.commit()
resp = await client.post(f"/api/sources/{src.id}/backfill", json={"action": "start"})
assert resp.status_code == 200