14ffc91dfb
* feat(metadata): expand provider image cache queue * fix(metadata): harden provider image cache queue Addresses bug-review feedback from Codex/CodeRabbit on the metadata image cache pipeline. All findings validated against the code before fixing; false positives (rows/connection deadlock, PhotoSourcePath merge coupling) were confirmed non-issues and left unchanged. - Honor metadata.cache_images for the background processor. The cache_metadata_images task was registered whenever S3 was configured, so merely enabling object storage downloaded the entire provider-artwork catalog even with caching disabled. Add ImageCacheProcessor.SetEnabled, gate RunOnce/RunUntilIdle on it, and wire it (with hot reload) from cfg.Metadata.CacheImages in main.go. - Guard terminal job updates with lease ownership. EnqueueBatch can repurpose a running row with a new source; MarkSucceeded/MarkFailed keyed on id alone let a stale worker finalize the replacement job and drop the new artwork. Thread locked_by through and add status='running' AND locked_by=$n guards. - Avoid uploading stale jobs onto the live artwork key. Verify the target still references the job's source (CurrentTargetSourcePath) before CacheImage, so a job whose source an admin/refresh already replaced cannot overwrite the deterministic storage object. - COALESCE nullable external IDs in EnqueueExistingProviderArtwork. A NULL tmdb_id/tvdb_id/imdb_id on any candidate failed the scan and aborted the whole cache run; matches the existing item_repo pattern. - Stop re-downloading the catalog every 30 days. Discovery now skips targets whose *_path is already a cached relative path, making the cached row the durable dedup marker instead of the prunable job row. - Decouple catalog sweeps from queue draining. RunOnce no longer runs discovery per batch; RunUntilIdle sweeps only when the queue drains and throttles full sweeps to every 15m, so idle installs stop full-scanning every entity table each minute. - Requeue claimed-but-unstarted jobs on cancellation. Acquire the semaphore before spawning workers and RequeueClaimed any jobs not yet started, instead of leaving them locked until the 15m lease expires. - Skip the backoff sleep after the final upload attempt in putObjectWithRetry (saves ~1.5s on permanent failures). - Add the s3/file/local/upload/generated exclusion to the seasons and episodes backfill in migration 20260617184537 for consistency with the later migration (the bad backfill was inert downstream, but the asymmetry is removed). 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
88 lines
3.1 KiB
SQL
88 lines
3.1 KiB
SQL
-- +goose Up
|
|
ALTER TABLE public.seasons
|
|
ADD COLUMN IF NOT EXISTS poster_source_path text NOT NULL DEFAULT '';
|
|
|
|
ALTER TABLE public.episodes
|
|
ADD COLUMN IF NOT EXISTS still_source_path text NOT NULL DEFAULT '';
|
|
|
|
UPDATE public.seasons
|
|
SET poster_source_path = poster_path
|
|
WHERE poster_source_path = ''
|
|
AND poster_path LIKE '%://%'
|
|
AND lower(poster_path) NOT LIKE ALL (ARRAY['s3://%', 'file://%', 'local://%', 'upload://%', 'generated://%']);
|
|
|
|
UPDATE public.episodes
|
|
SET still_source_path = still_path
|
|
WHERE still_source_path = ''
|
|
AND still_path LIKE '%://%'
|
|
AND lower(still_path) NOT LIKE ALL (ARRAY['s3://%', 'file://%', 'local://%', 'upload://%', 'generated://%']);
|
|
|
|
CREATE TABLE public.metadata_image_cache_jobs (
|
|
id bigserial PRIMARY KEY,
|
|
target_type text NOT NULL,
|
|
target_content_id text NOT NULL,
|
|
series_id text NOT NULL,
|
|
source_path text NOT NULL,
|
|
provider_id text NOT NULL,
|
|
provider_content_id text NOT NULL,
|
|
content_type text NOT NULL DEFAULT 'series',
|
|
image_type text NOT NULL,
|
|
season_number integer,
|
|
episode_number integer,
|
|
status text NOT NULL DEFAULT 'queued',
|
|
attempt_count integer NOT NULL DEFAULT 0,
|
|
next_attempt_at timestamp with time zone NOT NULL DEFAULT now(),
|
|
locked_at timestamp with time zone,
|
|
locked_by text NOT NULL DEFAULT '',
|
|
last_error text NOT NULL DEFAULT '',
|
|
created_at timestamp with time zone NOT NULL DEFAULT now(),
|
|
updated_at timestamp with time zone NOT NULL DEFAULT now(),
|
|
completed_at timestamp with time zone,
|
|
CONSTRAINT metadata_image_cache_jobs_target_check
|
|
CHECK (target_type IN ('season', 'episode')),
|
|
CONSTRAINT metadata_image_cache_jobs_image_type_check
|
|
CHECK (image_type IN ('poster', 'still')),
|
|
CONSTRAINT metadata_image_cache_jobs_status_check
|
|
CHECK (status IN ('queued', 'running', 'succeeded', 'failed')),
|
|
CONSTRAINT metadata_image_cache_jobs_shape_check CHECK (
|
|
(
|
|
target_type = 'season'
|
|
AND image_type = 'poster'
|
|
AND season_number IS NOT NULL
|
|
AND episode_number IS NULL
|
|
)
|
|
OR (
|
|
target_type = 'episode'
|
|
AND image_type = 'still'
|
|
AND season_number IS NOT NULL
|
|
AND episode_number IS NOT NULL
|
|
)
|
|
),
|
|
CONSTRAINT metadata_image_cache_jobs_target_unique
|
|
UNIQUE (target_type, target_content_id, image_type)
|
|
);
|
|
|
|
CREATE INDEX metadata_image_cache_jobs_due_idx
|
|
ON public.metadata_image_cache_jobs (next_attempt_at, id)
|
|
WHERE status = 'queued';
|
|
|
|
CREATE INDEX metadata_image_cache_jobs_running_lease_idx
|
|
ON public.metadata_image_cache_jobs (locked_at, id)
|
|
WHERE status = 'running';
|
|
|
|
CREATE INDEX metadata_image_cache_jobs_series_idx
|
|
ON public.metadata_image_cache_jobs (series_id, status);
|
|
|
|
CREATE INDEX metadata_image_cache_jobs_succeeded_retention_idx
|
|
ON public.metadata_image_cache_jobs (completed_at, id)
|
|
WHERE status = 'succeeded';
|
|
|
|
-- +goose Down
|
|
DROP TABLE IF EXISTS public.metadata_image_cache_jobs;
|
|
|
|
ALTER TABLE public.episodes
|
|
DROP COLUMN IF EXISTS still_source_path;
|
|
|
|
ALTER TABLE public.seasons
|
|
DROP COLUMN IF EXISTS poster_source_path;
|