Post translation via Interpreter (milestone 143) #201

Merged
bvandeusen merged 7 commits from dev into main 2026-07-07 13:05:18 -04:00
4 changed files with 291 additions and 2 deletions
Showing only changes of commit 7a4de7278d - Show all commits
+55 -2
View File
@@ -1,12 +1,23 @@
"""Settings API: import filters, system stats."""
import asyncio
import secrets
from quart import Blueprint, jsonify, request
from sqlalchemy import func, select
from sqlalchemy import func, or_, select
from ..extensions import get_session
from ..models import AppSetting, Artist, ImageRecord, ImportBatch, ImportSettings, ImportTask, Tag
from ..models import (
AppSetting,
Artist,
ImageRecord,
ImportBatch,
ImportSettings,
ImportTask,
Post,
Tag,
)
from ..services import interpreter_client as ic
settings_bp = Blueprint("settings", __name__, url_prefix="/api")
@@ -285,3 +296,45 @@ async def rotate_extension_api_key():
row.value = new_value
await session.commit()
return jsonify({"key": new_value})
# --- Translation (#143): live status + manual "Translate now" --------------
@settings_bp.route("/settings/translation/status", methods=["GET"])
async def translation_status():
"""For the Settings card: is it on, is a URL set, is the service reachable,
and how many posts still await translation. Health runs the sync client in a
thread so the event loop isn't blocked."""
async with get_session() as session:
cfg = await ImportSettings.load(session)
untranslated = (await session.execute(
select(func.count(Post.id))
.where(Post.translated_source_lang.is_(None))
.where(or_(
Post.post_title.is_not(None), Post.description.is_not(None),
))
)).scalar_one()
base_url = (cfg.interpreter_base_url or "").strip()
healthy = await asyncio.to_thread(ic.health, base_url) if base_url else False
return jsonify({
"enabled": cfg.translation_enabled,
"base_url_set": bool(base_url),
"healthy": healthy,
"untranslated_count": int(untranslated),
})
@settings_bp.route("/settings/translation/run", methods=["POST"])
async def translation_run():
"""Enqueue the translate sweep now (the Settings 'Translate now' button)."""
async with get_session() as session:
cfg = await ImportSettings.load(session)
if not cfg.translation_enabled or not (cfg.interpreter_base_url or "").strip():
return jsonify(
{"error": "translation is disabled or no base URL is set"}
), 400
from ..tasks.translation import translate_posts
r = translate_posts.delay()
return jsonify({"celery_task_id": r.id}), 202
+8
View File
@@ -35,6 +35,7 @@ def make_celery() -> Celery:
"backend.app.tasks.backup",
"backend.app.tasks.admin",
"backend.app.tasks.library_audit",
"backend.app.tasks.translation",
],
)
app.conf.update(
@@ -63,6 +64,9 @@ def make_celery() -> Celery:
"backend.app.tasks.backup.*": {"queue": "maintenance_long"},
"backend.app.tasks.admin.*": {"queue": "maintenance_long"},
"backend.app.tasks.library_audit.*": {"queue": "maintenance_long"},
# Translation backfill hits the LLM (~16s/item) → the long lane so it
# never starves the quick self-healing sweeps (#143).
"backend.app.tasks.translation.*": {"queue": "maintenance_long"},
},
# Heavy ML tasks need fair dispatch — see ImageRepo's precedent.
task_acks_late=True,
@@ -161,6 +165,10 @@ def make_celery() -> Celery:
"task": "backend.app.tasks.ml.prune_presentation_reviews",
"schedule": 86400.0, # retention: drop resolved review flags >30d
},
"translate-posts-daily": {
"task": "backend.app.tasks.translation.translate_posts",
"schedule": 86400.0, # no-op unless translation configured + healthy
},
"snapshot-head-metrics-daily": {
"task": "backend.app.tasks.maintenance.snapshot_head_metrics",
"schedule": 86400.0,
+101
View File
@@ -0,0 +1,101 @@
"""Post-text translation Celery task (milestone 143).
Backfills non-English post title/description to the target language via the
self-hosted Interpreter LAN service, storing the result + engine_version so
viewing is instant and re-runs are cache-fast. Sync (Celery workers are sync),
same pattern as the other backfill sweeps. No-op unless translation is enabled,
a base URL is set, and the service is healthy.
"""
import logging
from datetime import UTC, datetime
from celery.exceptions import SoftTimeLimitExceeded
from sqlalchemy import or_, select
from ..celery_app import celery
from ..models import ImportSettings, Post
from ..services import interpreter_client as ic
from ..utils.text import html_to_plain
from ._sync_engine import sync_session_factory as _sync_session_factory
log = logging.getLogger(__name__)
# Bound one run's work so it commits progress rather than dying at the time
# limit; the rest resumes next cycle (idempotent — only untranslated posts are
# picked, so an interrupted run just re-runs = rule-89 recovery).
_MAX_POSTS_PER_RUN = 300
@celery.task(
name="backend.app.tasks.translation.translate_posts",
soft_time_limit=1800, time_limit=2100,
)
def translate_posts() -> str:
"""Translate untranslated non-English post title/description (default target
en) via Interpreter. Per-post [title, description] batch → per-post detected
language. Passthrough / already-target posts are marked handled (source ==
target) with no stored translation. 503 or a connection error interrupts the
run (retry next cycle); 400 stops it (fix config); posts done so far stay
committed. No-op unless configured + healthy. Returns a summary string."""
SessionLocal = _sync_session_factory()
with SessionLocal() as session:
cfg = ImportSettings.load_sync(session)
if not cfg.translation_enabled or not cfg.interpreter_base_url.strip():
return "disabled"
base_url = cfg.interpreter_base_url.strip()
target = (cfg.translation_target_lang or "en").strip() or "en"
if not ic.health(base_url):
return "interpreter unavailable"
posts = session.execute(
select(Post)
.where(Post.translated_source_lang.is_(None))
.where(or_(
Post.post_title.is_not(None), Post.description.is_not(None),
))
.limit(_MAX_POSTS_PER_RUN)
).scalars().all()
translated = 0
try:
for post in posts:
translated += _translate_one(session, post, base_url, target)
session.commit() # per-post → an interrupted run keeps progress
except ic.InterpreterUnavailable:
session.rollback()
return f"interrupted (service down) — translated={translated}"
except ic.InterpreterBadRequest as e:
session.rollback()
log.warning("translate_posts bad request: %s", e)
return f"stopped (bad request) — translated={translated}"
except SoftTimeLimitExceeded:
return f"time limit — translated={translated}"
return f"translated={translated} scanned={len(posts)}"
def _translate_one(session, post, base_url: str, target: str) -> int:
"""Translate one post's title/description in place. Returns 1 if it stored a
translation, 0 for passthrough/empty (which still marks the post handled)."""
title = (post.post_title or "").strip()
desc = (html_to_plain(post.description) if post.description else "") or ""
desc = desc.strip()
fields: list[tuple[str, str]] = []
if title:
fields.append(("title", title))
if desc:
fields.append(("desc", desc))
if not fields:
post.translated_source_lang = target # nothing to translate → handled
return 0
res = ic.translate([t for _, t in fields], base_url=base_url, target=target)
detected = res["detected_lang"] or target
if detected == target or res["engine"] == "none":
post.translated_source_lang = target # already target language → handled
return 0
by_field = {f: res["translations"][i] for i, (f, _) in enumerate(fields)}
post.post_title_translated = by_field.get("title")
post.description_translated = by_field.get("desc")
post.translated_source_lang = detected
post.translation_engine_version = res["engine_version"]
post.translated_at = datetime.now(UTC)
return 1
+127
View File
@@ -0,0 +1,127 @@
"""translate_posts sweep (#143) — integration, with a stubbed Interpreter client
and the task's session factory pointed at the test's db_sync."""
import pytest
from sqlalchemy import select
from backend.app.models import Artist, ImportSettings, Post
from backend.app.tasks.translation import translate_posts
pytestmark = pytest.mark.integration
class _Ctx:
def __init__(self, s):
self.s = s
def __enter__(self):
return self.s
def __exit__(self, *a):
return False
def _sf(db_sync):
class _SM:
def __call__(self):
return _Ctx(db_sync)
return _SM()
def _artist(db):
a = Artist(name="A", slug="a")
db.add(a)
db.flush()
return a
def _post(db, artist_id, *, title=None, desc=None, ext="p1"):
p = Post(
artist_id=artist_id, external_post_id=ext,
post_title=title, description=desc,
)
db.add(p)
db.flush()
return p
def _enable(db, url="http://i.lan"):
cfg = db.execute(
select(ImportSettings).where(ImportSettings.id == 1)
).scalar_one()
cfg.translation_enabled = True
cfg.interpreter_base_url = url
db.flush()
def _patch(monkeypatch, db_sync):
monkeypatch.setattr(
"backend.app.tasks.translation._sync_session_factory",
lambda: _sf(db_sync),
)
def test_translate_posts_stores_translation(db_sync, monkeypatch):
_patch(monkeypatch, db_sync)
monkeypatch.setattr("backend.app.tasks.translation.ic.health", lambda *a, **k: True)
monkeypatch.setattr(
"backend.app.tasks.translation.ic.translate",
lambda texts, **k: {
"translations": [f"EN:{t}" for t in texts],
"detected_lang": "ja", "engine": "llm", "engine_version": "v1",
},
)
a = _artist(db_sync)
p = _post(db_sync, a.id, title="ねこ", desc="かわいい")
_enable(db_sync)
db_sync.commit()
assert "translated=1" in translate_posts()
db_sync.refresh(p)
assert p.post_title_translated == "EN:ねこ"
assert p.description_translated == "EN:かわいい"
assert p.translated_source_lang == "ja"
assert p.translation_engine_version == "v1"
def test_translate_posts_passthrough_english_marks_handled(db_sync, monkeypatch):
_patch(monkeypatch, db_sync)
monkeypatch.setattr("backend.app.tasks.translation.ic.health", lambda *a, **k: True)
monkeypatch.setattr(
"backend.app.tasks.translation.ic.translate",
lambda texts, **k: {
"translations": list(texts), "detected_lang": "en",
"engine": "none", "engine_version": None,
},
)
a = _artist(db_sync)
p = _post(db_sync, a.id, title="hello world", ext="p2")
_enable(db_sync)
db_sync.commit()
translate_posts()
db_sync.refresh(p)
assert p.translated_source_lang == "en" # marked handled...
assert p.post_title_translated is None # ...but nothing to show
def test_translate_posts_disabled_is_noop(db_sync, monkeypatch):
_patch(monkeypatch, db_sync)
a = _artist(db_sync)
p = _post(db_sync, a.id, title="ねこ", ext="p3")
db_sync.commit() # translation_enabled defaults False
assert translate_posts() == "disabled"
db_sync.refresh(p)
assert p.translated_source_lang is None
def test_translate_posts_service_down_leaves_untranslated(db_sync, monkeypatch):
_patch(monkeypatch, db_sync)
monkeypatch.setattr("backend.app.tasks.translation.ic.health", lambda *a, **k: False)
a = _artist(db_sync)
p = _post(db_sync, a.id, title="ねこ", ext="p4")
_enable(db_sync)
db_sync.commit()
assert translate_posts() == "interpreter unavailable"
db_sync.refresh(p)
assert p.translated_source_lang is None # will retry next run