ffdbdbaf07
Throughput: translate_posts now runs every 8h (was daily) as the steady-state cadence for newly-imported posts, and the Settings "Translate now" button runs it in drain mode (run-until-done, no reset) so one press clears the whole untranslated backlog instead of a single 300-post chunk. The interrupt/backoff re-enqueue now preserves the drain flag so a bulk drain resumes cleanly after an Interpreter restart. Misdetection groundwork: surface the detector's confidence from the Interpreter client (it was in the detectedLanguage payload but discarded) and add a read-only "Test translation" box — POST /settings/translation/ probe + TranslationCard UI — that shows detected language + confidence + engine + result for pasted text, without saving. Lets the operator see why a short/abbreviation-heavy English title gets mis-detected so the detection guard (min-length + confidence floor) can be tuned from real numbers. The guard itself follows once the mis-detected cases are probed. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CgZP9v2otxVJymiYsnVuMy
357 lines
12 KiB
Python
357 lines
12 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_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"] == 10
|
|
|
|
|
|
@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
|