Files
FabledCurator/tests/test_api_settings.py
T
bvandeusenandClaude Opus 5 a05cb66635
CI / lint (push) Failing after 3s
CI / extension-version (push) Successful in 3s
Build images / sign-extension (push) Successful in 4s
Build images / build-agent (push) Successful in 7s
CI / frontend-build (push) Successful in 30s
CI / backend-lint-and-test (push) Successful in 1m8s
Build images / build-web (push) Successful in 1m28s
Build images / smoke-web (push) Skipped
CI / integration (push) Successful in 2m51s
Build images / build-ml (push) Successful in 2m59s
Build images / promote (push) Skipped
fix: variant artwork was dropped as a near-duplicate even at threshold 0 (4223)
The operator reported a 15-image variant pack landing as 3 records, then
reported variants STILL being dropped with phash_threshold at 0 — the floor
of the dial. No setting could have fixed it: at hash_size=8 a pHash is 64
bits of coarse light/dark layout, so two variants sharing a composition
produce the SAME bits. Distance 0 meant "identical hash", not "identical
image", and the dial was simultaneously too coarse to keep variants and too
tight to catch a re-encoded rescale.

The hash no longer decides a merge on its own. find_similar now runs three
gates, cheapest first: the threshold proposes candidates, aspect ratio
(ASPECT_TOL, matching the tier-1 video path) rejects crops and re-canvases,
and a pixel-level confirm on the two files accepts. Every gate fails closed —
unknown dimensions, an unreadable candidate, a hash of the wrong width all
mean "not a duplicate", because too strict keeps a redundant copy the
operator can see while too loose deletes artwork only a source re-walk
returns.

- utils/phash.py: HASH_SIZE 8 -> 16 (256-bit, what ImageRepo always used);
  aspect_matches, fingerprint/fingerprint_path/fingerprints_match (PIL-only,
  mean drift + changed-pixel fraction), find_similar gains `confirm`.
- importer: _pixel_confirmer supplies gate 3 on both dedup sites, lazily and
  cached, so a non-matching import costs no extra I/O.
- 0098: widens image_record.phash to 64 chars and NULLs every value — a
  stored 64-bit hash cannot be compared to a 256-bit one, and backfill_phash
  is NULL-only, keyset-paginated and now on the daily beat, so the library
  re-hashes itself. Dedup degrades to sha256 until it finishes.
- phash_threshold counts bits and the denominator went 64 -> 256, so the
  setting is reset to the new default of 24 (there is no honest carry-over)
  and the slider is rescaled to 0-64.
- gallery_service dup_threshold 8 -> 32: the same fraction of the hash, so
  the Explore rail keeps the variance the operator tuned in on 2026-07-01.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LVjrnpQjRgHdvq95rASoiR
2026-09-21 00:16:14 -04:00

377 lines
13 KiB
Python

import pytest
pytestmark = pytest.mark.integration
@pytest.mark.asyncio
async def test_get_import_settings_defaults(client):
resp = await client.get("/api/settings/import")
assert resp.status_code == 200
body = await resp.get_json()
# Defaults from the migration:
assert body["min_width"] == 0
assert body["min_height"] == 0
assert body["skip_transparent"] is False
assert body["transparency_threshold"] == 0.9
@pytest.mark.asyncio
async def test_patch_import_settings(client):
resp = await client.patch(
"/api/settings/import",
json={"min_width": 500, "skip_transparent": True, "transparency_threshold": 0.7},
)
assert resp.status_code == 200
body = await resp.get_json()
assert body["min_width"] == 500
assert body["skip_transparent"] is True
assert body["transparency_threshold"] == 0.7
@pytest.mark.asyncio
async def test_translation_settings_defaults_and_patch(client):
# #143: translation is OFF by default with NO default host — the operator
# points it at their own Interpreter proxy and enables it.
body = await (await client.get("/api/settings/import")).get_json()
assert body["translation_enabled"] is False
assert body["interpreter_base_url"] == ""
assert body["translation_target_lang"] == "en"
ok = await client.patch("/api/settings/import", json={
"translation_enabled": True,
"interpreter_base_url": "http://interpreter.lan",
})
assert ok.status_code == 200
out = await ok.get_json()
assert out["translation_enabled"] is True
assert out["interpreter_base_url"] == "http://interpreter.lan"
# Type validation.
assert (await client.patch(
"/api/settings/import", json={"translation_enabled": "yes"})).status_code == 400
assert (await client.patch(
"/api/settings/import", json={"interpreter_base_url": 123})).status_code == 400
@pytest.mark.asyncio
async def test_translation_min_confidence_default_and_patch(client):
# #155: the latin-script acceptance floor is an operator-tunable setting,
# default 0.9 (stricter than the old hardcoded 0.8).
body = await (await client.get("/api/settings/import")).get_json()
assert body["translation_min_confidence"] == 0.9
ok = await client.patch(
"/api/settings/import", json={"translation_min_confidence": 0.95}
)
assert ok.status_code == 200
assert (await ok.get_json())["translation_min_confidence"] == 0.95
# Out-of-range + wrong-type are rejected.
assert (await client.patch(
"/api/settings/import", json={"translation_min_confidence": 1.5})).status_code == 400
assert (await client.patch(
"/api/settings/import", json={"translation_min_confidence": "high"})).status_code == 400
@pytest.mark.asyncio
async def test_translation_status_defaults(client):
# Off + no URL → no network health call, healthy False (#143).
body = await (await client.get("/api/settings/translation/status")).get_json()
assert body["enabled"] is False
assert body["base_url_set"] is False
assert body["healthy"] is False
assert "untranslated_count" in body
assert body["active"] is False # no sweep running
assert body["last_run"] is None
@pytest.mark.asyncio
async def test_translation_status_reports_active_and_last_run(client, db):
# A running translate/retranslate TaskRun → active True; the most recent
# finished one → last_run (task basename + status).
from datetime import UTC, datetime
from backend.app.models import TaskRun
db.add(TaskRun(
celery_task_id="r-run", queue="maintenance_long",
task_name="backend.app.tasks.translation.retranslate_posts",
started_at=datetime.now(UTC), status="running",
))
db.add(TaskRun(
celery_task_id="r-done", queue="maintenance_long",
task_name="backend.app.tasks.translation.translate_posts",
started_at=datetime.now(UTC), finished_at=datetime.now(UTC),
status="success",
))
await db.commit()
body = await (await client.get("/api/settings/translation/status")).get_json()
assert body["active"] is True
assert body["last_run"]["task"] == "translate_posts"
assert body["last_run"]["status"] == "success"
@pytest.mark.asyncio
async def test_translation_run_requires_config(client):
resp = await client.post("/api/settings/translation/run")
assert resp.status_code == 400 # disabled / no base URL
@pytest.mark.asyncio
async def test_translation_test_connection(client, monkeypatch):
# Tests a GIVEN url (not the saved one) without persisting anything.
monkeypatch.setattr("backend.app.api.settings.ic.health", lambda *a, **k: True)
resp = await client.post(
"/api/settings/translation/test", json={"base_url": "http://i.lan"})
assert resp.status_code == 200
assert (await resp.get_json())["healthy"] is True
# Empty URL → False, no health call.
empty = await client.post(
"/api/settings/translation/test", json={"base_url": ""})
assert (await empty.get_json())["healthy"] is False
@pytest.mark.asyncio
async def test_translation_run_enqueues_when_configured(client, monkeypatch):
sink = {}
monkeypatch.setattr(
"backend.app.tasks.translation.translate_posts.delay",
lambda *a, **k: sink.update(k) or type("R", (), {"id": "t1"})(),
)
await client.patch("/api/settings/import", json={
"translation_enabled": True, "interpreter_base_url": "http://i.lan",
})
resp = await client.post("/api/settings/translation/run")
assert resp.status_code == 202
assert (await resp.get_json())["celery_task_id"] == "t1"
assert sink["drain"] is True # "Translate now" chases the whole backlog
@pytest.mark.asyncio
async def test_translation_probe_requires_text(client):
resp = await client.post(
"/api/settings/translation/probe", json={"text": " "})
assert resp.status_code == 400
@pytest.mark.asyncio
async def test_translation_probe_requires_base_url(client):
# Text given but no Interpreter URL saved → nothing to probe against.
resp = await client.post(
"/api/settings/translation/probe", json={"text": "hello"})
assert resp.status_code == 400
@pytest.mark.asyncio
async def test_translation_probe_returns_detection(client, monkeypatch):
# The diagnostic surfaces detected language + confidence + result, unsaved.
monkeypatch.setattr(
"backend.app.api.settings.ic.translate",
lambda texts, **k: {
"translations": ["Work in Progress"],
"detected_lang": "de", "detected_confidence": 71.5,
"engine": "llm", "engine_version": "v1",
},
)
await client.patch("/api/settings/import", json={
"translation_enabled": True, "interpreter_base_url": "http://i.lan",
})
resp = await client.post(
"/api/settings/translation/probe", json={"text": "WIP"})
assert resp.status_code == 200
body = await resp.get_json()
assert body["detected_lang"] == "de"
assert body["detected_confidence"] == 71.5
assert body["translated"] == "Work in Progress"
assert body["target"] == "en"
def _fake_retranslate(monkeypatch, sink):
# Record the kwargs the endpoint enqueues with, return a fake AsyncResult.
monkeypatch.setattr(
"backend.app.tasks.translation.retranslate_posts.delay",
lambda *a, **k: sink.update(k) or type("R", (), {"id": "r1"})(),
)
@pytest.mark.asyncio
async def test_translation_retranslate_requires_config(client):
# Disabled → 400 even with an explicit scope (no reset is enqueued).
resp = await client.post(
"/api/settings/translation/retranslate", json={"all": True})
assert resp.status_code == 400
@pytest.mark.asyncio
async def test_translation_retranslate_requires_target(client, monkeypatch):
# 'all' must be explicit: an empty body is a 400, so a stray call can't
# wipe every translation.
_fake_retranslate(monkeypatch, {})
await client.patch("/api/settings/import", json={
"translation_enabled": True, "interpreter_base_url": "http://i.lan",
})
resp = await client.post("/api/settings/translation/retranslate")
assert resp.status_code == 400
@pytest.mark.asyncio
async def test_translation_retranslate_artist_scope(client, monkeypatch):
sink = {}
_fake_retranslate(monkeypatch, sink)
await client.patch("/api/settings/import", json={
"translation_enabled": True, "interpreter_base_url": "http://i.lan",
})
resp = await client.post(
"/api/settings/translation/retranslate", json={"artist_id": 7})
assert resp.status_code == 202
assert (await resp.get_json())["celery_task_id"] == "r1"
assert sink["artist_ids"] == [7]
@pytest.mark.asyncio
async def test_translation_retranslate_all_scope(client, monkeypatch):
sink = {}
_fake_retranslate(monkeypatch, sink)
await client.patch("/api/settings/import", json={
"translation_enabled": True, "interpreter_base_url": "http://i.lan",
})
resp = await client.post(
"/api/settings/translation/retranslate", json={"all": True})
assert resp.status_code == 202
assert sink["artist_ids"] is None
@pytest.mark.asyncio
async def test_translation_retranslate_bad_artist_id(client):
resp = await client.post(
"/api/settings/translation/retranslate", json={"artist_id": "abc"})
assert resp.status_code == 400
@pytest.mark.asyncio
async def test_patch_rejects_non_object(client):
resp = await client.patch("/api/settings/import", json=[1, 2, 3])
assert resp.status_code == 400
@pytest.mark.asyncio
async def test_import_settings_phash_threshold_default(client):
resp = await client.get("/api/settings/import")
assert resp.status_code == 200
assert (await resp.get_json())["phash_threshold"] == 24
@pytest.mark.asyncio
async def test_patch_phash_threshold(client):
resp = await client.patch(
"/api/settings/import", json={"phash_threshold": 4}
)
assert resp.status_code == 200
assert (await resp.get_json())["phash_threshold"] == 4
@pytest.mark.asyncio
async def test_patch_phash_threshold_rejects_negative(client):
resp = await client.patch(
"/api/settings/import", json={"phash_threshold": -1}
)
assert resp.status_code == 400
@pytest.mark.asyncio
async def test_system_stats_shape(client):
resp = await client.get("/api/system/stats")
assert resp.status_code == 200
body = await resp.get_json()
for key in ("total_images", "total_tags", "storage_bytes", "subscription_count", "tasks", "active_batch"):
assert key in body
for status in ("pending", "queued", "processing", "complete", "skipped", "failed"):
assert status in body["tasks"]
# --- FC-3d: scheduling knobs ----------------------------------------------
@pytest.mark.asyncio
async def test_get_includes_scheduling_defaults(client):
resp = await client.get("/api/settings/import")
body = await resp.get_json()
assert body["download_schedule_default_seconds"] == 28800
assert body["download_event_retention_days"] == 90
assert body["download_failure_warning_threshold"] == 5
@pytest.mark.asyncio
async def test_patch_scheduling_defaults(client):
resp = await client.patch("/api/settings/import", json={
"download_schedule_default_seconds": 7200,
"download_event_retention_days": 30,
"download_failure_warning_threshold": 3,
})
assert resp.status_code == 200
body = await resp.get_json()
assert body["download_schedule_default_seconds"] == 7200
assert body["download_event_retention_days"] == 30
assert body["download_failure_warning_threshold"] == 3
@pytest.mark.asyncio
async def test_patch_rejects_below_min_interval(client):
resp = await client.patch(
"/api/settings/import",
json={"download_schedule_default_seconds": 30},
)
assert resp.status_code == 400
@pytest.mark.asyncio
async def test_patch_rejects_above_max_interval(client):
resp = await client.patch(
"/api/settings/import",
json={"download_schedule_default_seconds": 90000},
)
assert resp.status_code == 400
@pytest.mark.asyncio
async def test_patch_rejects_zero_retention_days(client):
resp = await client.patch(
"/api/settings/import",
json={"download_event_retention_days": 0},
)
assert resp.status_code == 400
@pytest.mark.asyncio
async def test_patch_rejects_zero_failure_threshold(client):
resp = await client.patch(
"/api/settings/import",
json={"download_failure_warning_threshold": 0},
)
assert resp.status_code == 400
@pytest.mark.asyncio
async def test_system_stats_integrity_counts(client, db):
from backend.app.models import ImageRecord
base = "stats_" + "0" * 56
for i, status in enumerate(
["ok", "ok", "corrupt", "failed_verification"]
):
db.add(ImageRecord(
path=f"/images/i/{i}.jpg", sha256=base + f"{i:02d}",
size_bytes=1, mime="image/jpeg", width=1, height=1,
origin="imported_filesystem", integrity_status=status,
))
await db.commit()
resp = await client.get("/api/system/stats")
assert resp.status_code == 200
body = await resp.get_json()
integ = body["integrity"]
assert integ["ok"] >= 2
assert integ["corrupt"] >= 1
assert integ["failed_verification"] >= 1
assert "unknown" in integ