feat(translation): 8h sweep + drain button + detection probe (#1376)
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
This commit is contained in:
@@ -364,9 +364,49 @@ async def translation_test():
|
||||
return jsonify({"healthy": healthy})
|
||||
|
||||
|
||||
@settings_bp.route("/settings/translation/probe", methods=["POST"])
|
||||
async def translation_probe():
|
||||
"""Diagnostic for the Settings 'Test translation' box: translate a pasted
|
||||
snippet WITHOUT saving anything, returning what Interpreter *detected*
|
||||
(language + confidence) alongside the result. Lets the operator see why a
|
||||
given string was (mis-)detected — e.g. a short English title flagged as
|
||||
another language — so a detection guard can be tuned from real numbers.
|
||||
Read-only: no post is touched. Uses the currently-saved base URL + target."""
|
||||
body = await request.get_json(silent=True)
|
||||
body = body if isinstance(body, dict) else {}
|
||||
text = (body.get("text") or "").strip()
|
||||
if not text:
|
||||
return jsonify({"error": "provide text to translate"}), 400
|
||||
async with get_session() as session:
|
||||
cfg = await ImportSettings.load(session)
|
||||
base_url = (cfg.interpreter_base_url or "").strip()
|
||||
if not base_url:
|
||||
return jsonify({"error": "no Interpreter base URL is set"}), 400
|
||||
target = (cfg.translation_target_lang or "en").strip() or "en"
|
||||
try:
|
||||
res = await asyncio.to_thread(
|
||||
ic.translate, [text], base_url=base_url, target=target,
|
||||
)
|
||||
except ic.InterpreterUnavailable as e:
|
||||
return jsonify({"error": f"Interpreter unavailable: {e}"}), 503
|
||||
except ic.InterpreterBadRequest as e:
|
||||
return jsonify({"error": f"Interpreter rejected the request: {e}"}), 400
|
||||
translations = res.get("translations") or []
|
||||
return jsonify({
|
||||
"target": target,
|
||||
"detected_lang": res.get("detected_lang"),
|
||||
"detected_confidence": res.get("detected_confidence"),
|
||||
"engine": res.get("engine"),
|
||||
"engine_version": res.get("engine_version"),
|
||||
"translated": translations[0] if translations else None,
|
||||
})
|
||||
|
||||
|
||||
@settings_bp.route("/settings/translation/run", methods=["POST"])
|
||||
async def translation_run():
|
||||
"""Enqueue the translate sweep now (the Settings 'Translate now' button)."""
|
||||
"""Enqueue the translate sweep now (the Settings 'Translate now' button).
|
||||
Runs in drain mode — run-until-done — so one press chases the whole
|
||||
untranslated backlog to zero rather than a single 300-post chunk."""
|
||||
async with get_session() as session:
|
||||
cfg = await ImportSettings.load(session)
|
||||
if not cfg.translation_enabled or not (cfg.interpreter_base_url or "").strip():
|
||||
@@ -375,7 +415,7 @@ async def translation_run():
|
||||
), 400
|
||||
from ..tasks.translation import translate_posts
|
||||
|
||||
r = translate_posts.delay()
|
||||
r = translate_posts.delay(drain=True)
|
||||
return jsonify({"celery_task_id": r.id}), 202
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user