-- Migration 015: transcripts become SHARED public-content storage (ADR-021).
--
-- The per-user transcripts table from 001 (PK videos.id, user_id NOT NULL, RLS
-- FORCEd in 003) was dead: no application code ever read or wrote it — only the
-- transcript_status columns on `videos` (007) carried fetch outcomes. ADR-021
-- repurposes it as the single shared store of public caption content, keyed by
-- the cross-user dedup key (provider, provider_video_id) — the video's public
-- identity, not Tapir's per-user videos.id — so re-analysis never re-fetches
-- from YouTube (ADR-010/014).
--
-- It holds ONLY public caption content + the video's public id (nothing
-- user-identifying), so it is deliberately NOT RLS-scoped: no user_id, no
-- policy, no FORCE. This is the single, intentional exception to the ADR-012
-- isolation boundary; rls_test.go asserts the boundary is exactly here and
-- nowhere else. Dropping the old table drops its RLS policy with it; it held no
-- real data, so drop+recreate loses nothing.
DROP TABLE transcripts;

CREATE TABLE transcripts (
    provider          TEXT NOT NULL,
    provider_video_id TEXT NOT NULL,
    source            TEXT NOT NULL, -- 'captions' (content set) | 'none' (no captions; content NULL)
    language          TEXT,
    content           TEXT,
    fetched_at        TIMESTAMPTZ NOT NULL DEFAULT NOW(),
    PRIMARY KEY (provider, provider_video_id)
);

COMMENT ON TABLE transcripts IS
    'Shared public caption content keyed by (provider, provider_video_id). NOT RLS-scoped — public content only, de-facto cross-user dedup (ADR-021).';