Skip to content

Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors

Rust

fix(status): count a page with only a foreign-model vector as missing (#1431)

Fabio Akita367d25a0a59e
diff --cc CHANGELOG.md
index 990dcd71,fc3335f1..fc9f766f
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@@ -120,10 -117,12 +120,15 @@@ version in [`docs/changelog/`](docs/cha
ranking. `contradiction_sql` now applies the `not_expired` guard on the target
page, aligning belief input aggregation with the lint's resolved/stale split.
([#1386](https://github.com/akitaonrails/ai-memory/pull/1386))
+- Stopped the LLM contradiction pass from auditing its previous
+ `_lint/report.md` as a knowledge page, which could recycle stale findings or
+ displace a real page from the bounded prompt. ([#1455](https://github.com/akitaonrails/ai-memory/pull/1455))
- Kept the previous backup or OKF export intact when an archive download is interrupted, and publish completed downloads atomically. Successful downloads replace destination symlinks with private files rather than changing their targets or inheriting their permissions. ([#1381](https://github.com/akitaonrails/ai-memory/pull/1381))
+ - Counted a latest page whose only stored vector belongs to another provider,
+ model, or dimension as missing an embedding in `ai-memory status` and the
+ web `/health` page, so the count no longer reads zero after an
+ embedding-model switch.
+ ([#1431](https://github.com/akitaonrails/ai-memory/pull/1431))
- Bounded free-text search before the FTS5 parser sees it. A query of 100k
distinct terms spent ~17.5 s in query preparation alone (and a ~500 KB
document ~59 s end to end), and a NUL byte reached the phrase parser as