feat(translation): tunable acceptance floor (0.90) + per-post sticky override (#155)
The gate at a fixed 0.80 couldn't catch the real pain: Interpreter (fresh == cached, verified by probe) confidently mis-detects short ASCII English like "... WIP Part 1" as German at 0.86 — above the floor — so it was accepted and a re-translate reproduced it. Confidence alone can't separate the 0.86 collision (genuine German lands there too), and single-word mis-flags sit at a confident 1.0 no floor catches. Two operator-approved levers: - Acceptance floor is now a live Settings value (ImportSettings. translation_min_confidence, default 0.90; surfaced in the Translation card), so it's tunable without a redeploy. _accept takes the threshold as a parameter. - Per-post sticky override (Post.translation_override: auto/force/original). 'force' stores a translation even below the floor (rescue a skipped legit-foreign title); 'original' keeps the original and clears any stored translation (kill a confident mis-flag no floor catches). The sweep honors it on every run and _reset_translations skips 'original', so the choice survives a Re-translate-all. POST /api/posts/<id>/translation-override applies it immediately (translate now when the service is up, else queue for the sweep). UI: PostTranslationControl on the posts-feed card. Migration 0084 (both columns + a CHECK on the override). The feed + provenance serializers expose translation_override. With a stricter floor the rollback finally works: raise it -> Re-translate all -> the 0.86 mis-flags are rejected and restored to the original; force / keep-original handle the residual either way. Tests: gate thresholds against the param (0.86 rejected at 0.90, explicit-floor cases); sweep force/original + re-translate-skips-original; override endpoint (validation, original clears, force queues when disabled, feed exposes it); settings min_confidence default/save/validate. 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:
@@ -314,6 +314,41 @@ def test_translate_posts_accepts_low_confidence_cjk(db_sync, monkeypatch):
|
||||
assert p.translated_source_lang == "zh"
|
||||
|
||||
|
||||
def test_translate_posts_force_override_translates_below_floor(db_sync, monkeypatch):
|
||||
# override='force' stores the translation even below the confidence floor —
|
||||
# rescuing a legitimately-foreign title the gate would otherwise skip.
|
||||
_patch(monkeypatch, db_sync)
|
||||
_mock_lang(monkeypatch, lang="de", conf=0.42) # below the 0.90 default floor
|
||||
a = _artist(db_sync)
|
||||
p = _post(db_sync, a.id, title="Kurz", ext="p1")
|
||||
p.translation_override = "force"
|
||||
_enable(db_sync)
|
||||
db_sync.commit()
|
||||
|
||||
translate_posts()
|
||||
db_sync.refresh(p)
|
||||
assert p.post_title_translated == "EN:Kurz" # forced through despite 0.42
|
||||
assert p.translated_source_lang == "de"
|
||||
|
||||
|
||||
def test_translate_posts_original_override_keeps_original(db_sync, monkeypatch):
|
||||
# override='original' never translates — even a confident (0.98) detection is
|
||||
# kept as the original. The sweep marks it handled (== target) and stores
|
||||
# nothing; Interpreter isn't consulted for the decision.
|
||||
_patch(monkeypatch, db_sync)
|
||||
_mock_lang(monkeypatch, lang="de", conf=0.98) # would be accepted under auto
|
||||
a = _artist(db_sync)
|
||||
p = _post(db_sync, a.id, title="Das Mädchen", ext="p1")
|
||||
p.translation_override = "original"
|
||||
_enable(db_sync)
|
||||
db_sync.commit()
|
||||
|
||||
translate_posts()
|
||||
db_sync.refresh(p)
|
||||
assert p.post_title_translated is None # kept original
|
||||
assert p.translated_source_lang == "en" # marked handled
|
||||
|
||||
|
||||
def _mock_new_model(monkeypatch, *, ver="v2"):
|
||||
"""Interpreter is up and translates with a NEW engine version."""
|
||||
monkeypatch.setattr("backend.app.tasks.translation.ic.health", lambda *a, **k: True)
|
||||
@@ -344,6 +379,25 @@ def test_retranslate_resets_and_reruns(db_sync, monkeypatch):
|
||||
assert p.translation_engine_version == "v2"
|
||||
|
||||
|
||||
def test_retranslate_leaves_keep_original_posts(db_sync, monkeypatch):
|
||||
# A 'keep original' post survives a Re-translate-all: _reset_translations skips
|
||||
# override='original', so it stays handled + untranslated instead of being
|
||||
# re-run (which would re-introduce the mis-flag the operator killed).
|
||||
_patch(monkeypatch, db_sync)
|
||||
_mock_new_model(monkeypatch)
|
||||
a = _artist(db_sync)
|
||||
p = _post(db_sync, a.id, title="ねこ", ext="p1")
|
||||
p.translation_override = "original"
|
||||
p.translated_source_lang = "en" # handled by a prior 'keep original' apply
|
||||
_enable(db_sync)
|
||||
db_sync.commit()
|
||||
|
||||
retranslate_posts(artist_ids=[a.id])
|
||||
db_sync.refresh(p)
|
||||
assert p.translated_source_lang == "en" # not reset
|
||||
assert p.post_title_translated is None # not re-translated
|
||||
|
||||
|
||||
def test_retranslate_artist_scope_leaves_others(db_sync, monkeypatch):
|
||||
# Scoping to one artist must not touch another artist's translations.
|
||||
_patch(monkeypatch, db_sync)
|
||||
|
||||
Reference in New Issue
Block a user