move_detect/cloud/migrations/2026-07-17-p1-9-p3-2b.sql

-- ===========================================================================
-- Migration: P1-9 (event dedup) + P3-2b (site-scoped access control)
--            + retention / rate-limit reap indexes
--
-- Apply ONCE to an EXISTING move_detect database. A FRESH install already has
-- all of this via schema.sql — do NOT run this on a database created from the
-- current schema.sql.
--
-- RUN IN THREE PARTS, IN ORDER. Part C (the events.site backfill) MUST run
-- AFTER Part B has set devices.site — otherwise it matches 0 rows and every
-- historical event stays site=NULL and DISAPPEARS from a scoped operator's
-- dashboard the moment you scope a user. Do not skip Part C.
--
-- How to run: phpMyAdmin -> your DB -> "SQL" tab. MySQL (unlike MariaDB) has no
-- "ADD COLUMN IF NOT EXISTS": if a column/index already exists, that ONE
-- statement errors — skip it and run the rest.
-- ===========================================================================

-- ===========================================================================
-- PART A — schema changes (safe to run as-is)
-- ===========================================================================

-- A1) devices.site — the access-control site each device belongs to.
ALTER TABLE devices
    ADD COLUMN site VARCHAR(64) NULL AFTER name,
    ADD KEY ix_devices_site (site);

-- A2) events.site — denormalized from devices.site at ingest, for the dashboard's
--     site-scoped event list.
ALTER TABLE events
    ADD COLUMN site VARCHAR(64) NULL AFTER device_id,
    ADD KEY ix_events_site_occurred_at (site, occurred_at);

-- A3) events.event_uuid — edge-generated idempotency key (P1-9). The UNIQUE key
--     makes a re-sent event collide (dedup) instead of duplicating. MySQL allows
--     multiple NULLs in a UNIQUE index, so legacy rows without a uuid are fine.
ALTER TABLE events
    ADD COLUMN event_uuid CHAR(32) NULL AFTER event_id,
    ADD UNIQUE KEY uq_events_uuid (event_uuid);

-- A4) event_snapshots.created_at index — PdoSnapshotRepository::purgeOlderThan()
--     runs "SELECT ... WHERE created_at < ?" inside live ingest requests. Without
--     this index it full-scans the snapshot table on every triggered purge.
ALTER TABLE event_snapshots
    ADD KEY ix_event_snapshots_created (created_at);

-- A5) event_snapshots (event_id, content_hash) UNIQUE — lets the ingest dedup path
--     re-store an event's MISSING snapshots idempotently (a re-sent event carries
--     the same re-encoded bytes = same content_hash, so a duplicate/racing store
--     collides instead of writing a second copy). If this fails on "Duplicate
--     entry", the table already has duplicate (event_id, content_hash) rows —
--     remove the dups, then re-run this one statement.
ALTER TABLE event_snapshots
    ADD UNIQUE KEY uq_event_snapshots_event_hash (event_id, content_hash);

-- A6) rate_limits.window_start index — the reap "DELETE ... WHERE window_start < ?"
--     cannot use the (rate_key, window_start) PRIMARY KEY (window_start is the
--     trailing column), so it full-scans and locks rows on the pre-auth hot path.
ALTER TABLE rate_limits
    ADD KEY ix_rate_limits_window (window_start);

-- ===========================================================================
-- PART B — provisioning (EDIT the values for your deployment, then run).
--          Assign every device to its site here; the backfill in Part C reads it.
-- ===========================================================================
--   UPDATE devices SET site = 'factory-a' WHERE device_id = 'pi-1';
--   UPDATE devices SET site = 'factory-b' WHERE device_id = 'pi-2';
--   -- ... one row per device ...

-- ===========================================================================
-- PART C — backfill historical events from their device's site.
--          RUN THIS ONLY AFTER Part B. Re-run it whenever you add/relabel a
--          device's site so its past events reappear for scoped operators.
-- ===========================================================================
UPDATE events e
    JOIN devices d ON d.device_id = e.device_id
    SET e.site = d.site
    WHERE e.site IS NULL AND d.site IS NOT NULL;

-- ===========================================================================
-- PART D — scope dashboard users (run AFTER Part C, so scoped users immediately
--          see their backfilled history). NULL = global operator; '' is NOT
--          global (matches nothing — an accidental blank fails closed).
-- ===========================================================================
--   UPDATE users SET site_scope = 'factory-a' WHERE username = 'operator-a';

-- ---- Verification (run these; each must confirm the object/state) -----------
--   SHOW COLUMNS FROM devices LIKE 'site';
--   SHOW COLUMNS FROM events  LIKE 'site';
--   SHOW COLUMNS FROM events  LIKE 'event_uuid';
--   SHOW INDEX FROM events          WHERE Key_name = 'uq_events_uuid';
--   SHOW INDEX FROM event_snapshots WHERE Key_name = 'ix_event_snapshots_created';
--   SHOW INDEX FROM event_snapshots WHERE Key_name = 'uq_event_snapshots_event_hash';
--   SHOW INDEX FROM rate_limits     WHERE Key_name = 'ix_rate_limits_window';
-- Events still unscoped after Part C (expect 0, or only rows whose device has no
-- site assigned yet — go back and finish Part B for those devices):
--   SELECT COUNT(*) FROM events e JOIN devices d ON d.device_id = e.device_id
--     WHERE e.site IS NULL AND d.site IS NOT NULL;