migrations/2026-05-11-000000_normalize_entity_types/down.sql

@@ -0,0 +1,6 @@
+-- Irreversible: we collapsed multiple raw entity_type strings to
+-- canonical forms and don't have a per-row record of the original.
+-- The down migration is intentionally a no-op (the rewritten values
+-- are still semantically correct), and the up migration is safe to
+-- re-run because every UPDATE is conditional on `!= canonical`.
+SELECT 1;

migrations/2026-05-11-000000_normalize_entity_types/up.sql

@@ -0,0 +1,43 @@
+-- Canonicalize `entities.entity_type` so legacy rows from before
+-- `normalize_entity_type` landed in upsert_entity stop polluting
+-- client-side filters. Mirrors the synonym map in
+-- `src/database/knowledge_dao.rs::normalize_entity_type`:
+--   person  ← person | people | human | individual | contact
+--   place   ← place  | location | venue | site | area | landmark
+--   event   ← event  | occasion | activity | celebration
+--   thing   ← thing  | object | item | product
+-- Types outside the synonym set (e.g. "friend", "family") are not
+-- recognized as canonical and get a lowercase+trim pass instead, so
+-- at minimum case variants collapse.
+--
+-- `UPDATE OR IGNORE` skips rows that would violate UNIQUE(name,
+-- entity_type) after the rewrite. Two rows like ("Sarah", "person")
+-- + ("Sarah", "Person") would otherwise collide — the duplicate
+-- survives unchanged so the curator can merge it via the curation
+-- UI rather than have the migration silently delete data.
+
+UPDATE OR IGNORE entities
+SET entity_type = 'person'
+WHERE LOWER(TRIM(entity_type)) IN ('person', 'people', 'human', 'individual', 'contact')
+  AND entity_type != 'person';
+
+UPDATE OR IGNORE entities
+SET entity_type = 'place'
+WHERE LOWER(TRIM(entity_type)) IN ('place', 'location', 'venue', 'site', 'area', 'landmark')
+  AND entity_type != 'place';
+
+UPDATE OR IGNORE entities
+SET entity_type = 'event'
+WHERE LOWER(TRIM(entity_type)) IN ('event', 'occasion', 'activity', 'celebration')
+  AND entity_type != 'event';
+
+UPDATE OR IGNORE entities
+SET entity_type = 'thing'
+WHERE LOWER(TRIM(entity_type)) IN ('thing', 'object', 'item', 'product')
+  AND entity_type != 'thing';
+
+-- Anything left ("Friend" vs "friend") gets a lowercase+trim sweep
+-- so at least case variants of the same custom type collapse.
+UPDATE OR IGNORE entities
+SET entity_type = LOWER(TRIM(entity_type))
+WHERE entity_type != LOWER(TRIM(entity_type));