Files
silo-server/internal/catalog/localize_test.go
39ba284c9d feat(ai): shared AI core — metadata translation, Whisper ASR, per-profile language, on-view translation (#127)
* docs: design + plan for shared AI core, metadata translation, Whisper ASR

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* refactor(ai): shared LLM client, segment translator, and job runner packages

internal/ai/llm: OpenAI-compatible chat client moved out of subtitles/ai,
plus /v1/audio/transcriptions (verbose_json) for the ASR work; one shared
retry/backoff loop for both. internal/ai/translate: the batched indexed-JSON
translation protocol generalized to text segments. internal/ai/jobrunner:
dispatch/heartbeat/reaper/cancel lifecycle extracted behind a minimal store
interface, with a semaphore shareable across job services.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* refactor(subtitles): consume shared AI core

LLMTranslator becomes a thin cue<->segment adapter over aitranslate; the
service delegates dispatch/heartbeat/reaper/cancel to jobrunner; the local
OpenAI client is gone in favor of internal/ai/llm. Behavior (prompts, wire
protocol, job rows, recovery semantics) is unchanged. NewService now takes
the dispatch semaphore so all AI job services can share one bound.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(config): shared ai.* settings, metadata translation job table, localization provenance columns

ai.* connection keys (chat + optional separate ASR endpoint) load with a
fallback to the legacy subtitle_ai.* rows — those are never renamed in SQL
because encrypted values are GCM-bound to their setting key. New toggles:
subtitle_ai.transcribe_enabled, metadata_ai.enabled. Migration adds
metadata_translation_jobs, per-field provenance (provider|ai|manual) on the
localization tables, and media_folders.auto_translate_metadata.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(catalog): localization field provenance with provider/ai/manual precedence

Provider upserts keep manual values and never blank a field with an empty
incoming value; new UpsertAITranslation/UpsertAIOverview methods write AI
fields only over empty or ai-sourced values (force adds provider, never
manual) — all enforced in single-statement SQL. Serving now merges only
non-empty localized fields onto the base item, since localization rows are
legitimately partial (AI rows carry no titles/artwork).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(metadata): AI translation service, refresh auto-fallback, and admin API

internal/metadata/translation: job service over the shared AI core that
expands an item to its season/episode overviews, skips already-localized
fields (zero model calls on repeat runs), batches paragraphs through the
generic translator, and persists per batch with provenance-aware upserts.
MetadataService gains an AutoTranslator seam invoked after each refresh for
libraries with auto_translate_metadata. Admin endpoints under the metadata
curation guard: enqueue, list (poll), cancel; plus a status probe.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(subtitles): Whisper ASR transcribe and transcribe_translate jobs

New WhisperTranscriber: one ffmpeg pass extracts the audio track to 10-min
16kHz mono WAV chunks (temp dir cleaned on every exit path), each chunk goes
to the OpenAI-compatible /v1/audio/transcriptions endpoint (verbose_json,
per-request timeout sized to 3x chunk duration), segment timestamps are
offset and built into wrapped cues. Chunks process playhead-first and stream
live to the requesting session. The transcript is stored as an ordinary
downloaded subtitle (provider 'transcribed'); transcribe_translate chains
the existing translator and stores the translated track as the job result.
Enqueue accepts an optional kind; status reports transcribe_enabled.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(web): AI services settings, metadata translate action, library auto-translate, generate-from-audio

New AI Services admin page hosts the shared endpoint config (reads fall back
to legacy subtitle_ai.* values, writes target ai.*) and the three feature
toggles; the AI card moves out of Subtitles settings. The metadata editor
gains a Translate-with-AI panel with job polling and force/re-translate. The
library form gains the auto-translate toggle (threaded through the libraries
API). The player translate modal gains a From-audio mode that lists audio
tracks and submits transcribe / transcribe_translate jobs.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* style: gofmt import grouping in router and translation tests

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(catalog): per-profile metadata language and viewer-triggered description translation

user_profiles.preferred_metadata_language threads through the access scope
into catalog serving: presentation language now resolves explicit param ->
profile preference -> library metadata language (native API and jellycompat).
ItemDetail gains pending_translation_language when the viewer's language is
missing a localized overview. New metadata_ai.on_view setting (off|button|
auto) gates POST /items/{id}/translate-description: any profile with item
access may request its language, with in-flight dedup and a 15-minute
failure cooldown so page views never hammer a broken endpoint.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(web): on-view description translation with per-profile metadata language

Profile playback settings gain a Metadata language picker (library default
inherit). Detail pages: when the server reports pending_translation_language
and metadata_ai.on_view is 'auto', the description translates on view with a
pulse animation until the refetched detail comes back localized (45s
timeout); in 'button' mode a small Translate chip triggers the same flow.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(web): expose metadata_ai.on_view in AI Services settings

The on-view translation mode had no UI control, so it could only ever be
'off' — viewers got neither the auto translation nor the fallback button.
Adds the off/button/auto selector to the Features card, and the config
loader now warns and falls back to 'off' on a bad row instead of refusing
to start.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(ai): clear configuration hint when the transcription endpoint is chat-only

A blank Transcription base URL falls back to the chat endpoint; chat-only
gateways reject the multipart upload with an opaque 400 that reads like a
pipeline bug. 400/404/405 transcription failures now carry a hint to set a
Whisper-compatible endpoint in AI Services.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(subtitles): wrap ASR cue text by rune count, not bytes

Arabic/Cyrillic/Greek text is 2+ bytes per character in UTF-8, so byte-based
wrapping broke lines at roughly half the intended visual width.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* docs(web): steer transcription base URL hint away from chat-only gateways

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(ai): block chat-only gateways for transcription, add endpoint presets

llm.IsChatOnlyGateway (OpenRouter et al — no timestamped transcription API)
is enforced in three layers: the settings API rejects ai.asr_base_url values
pointing at one, the router disables ASR with a warning when the blank-URL
fallback would land on one, and llm.Transcribe refuses outright. The AI
Services page gains one-click transcription presets (Groq turbo/accurate,
OpenAI, self-hosted speaches) plus the mirrored client-side check, and the
settings API now also validates metadata_ai.on_view.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(subtitles): tighten ASR subtitle sync

Three systematic timing-error sources addressed: cue offsets now use the
segment muxer's exact per-chunk start times (segment_list CSV) instead of
assuming index*chunk_seconds; the audio stream's start delay relative to the
container timeline (common in TS remuxes) is probed via ffprobe and added to
every cue; and the chunk length is now operator-tunable via
subtitle_ai.asr_chunk_seconds (60-600s, default 600) since shorter chunks
bound Whisper's within-chunk timestamp drift. Playhead-first ordering now
pivots on real chunk starts, and a beyond-end playhead starts at the final
chunk instead of restarting from zero.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(ai): tolerate base URLs that already include the /v1 segment

Providers like DeepInfra expose their OpenAI-compatible API under a base
that contains the version segment (api.deepinfra.com/v1/openai); always
appending /v1/... mangled those. endpointURL now appends bare paths when
the base already carries /v1.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(web): prefer self-hosted transcription in presets and hints

Preset order becomes self-hosted (recommended) -> Groq turbo -> Groq
large-v3 -> OpenAI, and the settings hint plus the job-error hint lead with
the self-hosted option. The self-hosted preset now fills the turbo CT2 model
to match the recommended speaches setup.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(subtitles): request VAD and word timestamps for ASR cue accuracy

Without vad_filter, faster-whisper servers report wall-to-wall segment
times: cues linger on screen through silence (verified up to 91s) and
paragraph-length segments become single 400+ char cues. Request
vad_filter=true (skipped for hosted providers that reject non-OpenAI
fields and run VAD server-side) plus timestamp_granularities word+segment,
and rebuild cues from word timings: split at speech pauses, sentence ends,
text capacity, and a 7s max duration; cap word-less segments instead of
trusting their reported end; stretch sub-second cues to a readable minimum.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-06-10 14:58:54 -04:00

110 lines
3.8 KiB
Go

package catalog
import (
"testing"
"github.com/Silo-Server/silo-server/internal/models"
)
func baseItem() *models.MediaItem {
return &models.MediaItem{
ContentID: "c1",
Title: "Base Title",
SortTitle: "Base Title, The",
Overview: "Base overview.",
Tagline: "Base tagline.",
PosterPath: "posters/base.jpg",
PosterThumbhash: "hash-poster",
BackdropPath: "backdrops/base.jpg",
BackdropThumbhash: "hash-backdrop",
LogoPath: "logos/base.png",
}
}
// An AI-created localization row carries only overview/tagline; everything
// else must fall back to the base item rather than be blanked.
func TestApplyItemLocalizationPartialRowFallsBackToBase(t *testing.T) {
loc := &models.MediaItemLocalization{
ContentID: "c1",
Language: "fr",
Overview: "Résumé traduit.",
Tagline: "Slogan traduit.",
}
got := applyItemLocalization(baseItem(), loc)
if got.Overview != "Résumé traduit." || got.Tagline != "Slogan traduit." {
t.Errorf("translated fields not applied: %q / %q", got.Overview, got.Tagline)
}
if got.Title != "Base Title" || got.SortTitle != "Base Title, The" {
t.Errorf("empty localized titles blanked the base: %q / %q", got.Title, got.SortTitle)
}
if got.PosterPath != "posters/base.jpg" || got.PosterThumbhash != "hash-poster" {
t.Errorf("empty localized poster blanked the base: %q / %q", got.PosterPath, got.PosterThumbhash)
}
if got.BackdropPath != "backdrops/base.jpg" || got.LogoPath != "logos/base.png" {
t.Errorf("empty localized artwork blanked the base: %q / %q", got.BackdropPath, got.LogoPath)
}
}
func TestApplyItemLocalizationFullRowOverridesEverything(t *testing.T) {
loc := &models.MediaItemLocalization{
ContentID: "c1",
Language: "fr",
Title: "Titre",
SortTitle: "Titre, Le",
Overview: "Résumé.",
Tagline: "Slogan.",
PosterPath: "posters/fr.jpg",
PosterThumbhash: "hash-fr",
BackdropPath: "backdrops/fr.jpg",
BackdropThumbhash: "hash-fr-bd",
LogoPath: "logos/fr.png",
}
got := applyItemLocalization(baseItem(), loc)
if got.Title != "Titre" || got.Overview != "Résumé." || got.PosterPath != "posters/fr.jpg" ||
got.PosterThumbhash != "hash-fr" || got.LogoPath != "logos/fr.png" {
t.Errorf("full localization not applied: %+v", got)
}
}
func TestApplyItemLocalizationDoesNotMutateBase(t *testing.T) {
item := baseItem()
_ = applyItemLocalization(item, &models.MediaItemLocalization{Title: "Titre"})
if item.Title != "Base Title" {
t.Errorf("base item mutated: %q", item.Title)
}
}
func TestApplyItemLocalizationNilLocalizationClones(t *testing.T) {
item := baseItem()
got := applyItemLocalization(item, nil)
if got == item {
t.Fatal("expected a clone, got the same pointer")
}
if got.Title != item.Title {
t.Errorf("clone differs: %q", got.Title)
}
}
func TestApplySeasonLocalizationPartialRow(t *testing.T) {
season := &models.Season{ContentID: "s1", Title: "Season 1", Overview: "Base.", PosterPath: "p.jpg", PosterThumbhash: "h"}
got := applySeasonLocalization(season, &models.SeasonLocalization{Overview: "Saison résumé."})
if got.Overview != "Saison résumé." {
t.Errorf("overview not applied: %q", got.Overview)
}
if got.Title != "Season 1" || got.PosterPath != "p.jpg" || got.PosterThumbhash != "h" {
t.Errorf("empty fields blanked the base: %+v", got)
}
}
func TestApplyEpisodeLocalizationPartialRow(t *testing.T) {
ep := &models.Episode{ContentID: "e1", Title: "Pilot", Overview: "Base."}
got := applyEpisodeLocalization(ep, &models.EpisodeLocalization{Overview: "Épisode résumé."})
if got.Overview != "Épisode résumé." {
t.Errorf("overview not applied: %q", got.Overview)
}
if got.Title != "Pilot" {
t.Errorf("empty localized title blanked the base: %q", got.Title)
}
}