The choice is unchanged and now better argued: a deployment does not announce which language its notes are in, so any stemmer picked here is the wrong one somewhere — and applying the wrong one does not fail loudly, it quietly stops finding things. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
2bf7de1a43
commit
f2f375d824
2 files changed
+8
-5
No files matched your search
@@ -29,9 +29,12 @@ CREATE TABLE memory_notes (
|
||||
-- Touched on every write, so retention measures how long a note has gone
|
||||
-- unrefreshed rather than how old it is.
|
||||
updated_at BIGINT NOT NULL,
|
||||
-- 'simple' rather than a language configuration: these are an agent's own
|
||||
-- notes, in whatever language it chose, and stemming English rules over
|
||||
-- Turkish text would quietly stop finding things.
|
||||
-- 'simple' rather than a language configuration. These are an agent's own
|
||||
-- notes, in whatever language it chose, and a deployment does not announce
|
||||
-- which that is — so any stemmer picked here is the wrong one somewhere.
|
||||
-- Applying English rules to text that is not English does not fail loudly:
|
||||
-- it quietly stops finding things, which is the worst way for a search to
|
||||
-- be wrong.
|
||||
search tsvector GENERATED ALWAYS AS (
|
||||
to_tsvector('simple', coalesce(key, '') || ' ' || coalesce(text, '') || ' ' || coalesce(tags, ''))
|
||||
) STORED,
|
||||
|
||||
Reference in new issue
Block a user