Skip to content

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

Rust

docs(changelog): move a release/3.2 entry out of the frozen [3.1.2] section

AkitaOnRailsfc65a0862981
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 37f39164..7832af1b 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -208,6 +208,13 @@ version in [`docs/changelog/`](docs/changelog/):
relay and wiki sync companions take the same `rustls-webpki` bump.
### Fixed
+- Reserved local-embedding capacity for interactive search queries instead of
+ allowing concurrent page writes and backfill work to occupy every inference
+ slot. Excess queries fall back immediately to non-vector retrieval, and a
+ cancelled request retains its slot until its non-cancellable CPU inference
+ actually ends. An opt-in real-model contention probe records idle,
+ unbounded-load, and bounded-load p50/p95 query latency; hosted embedding
+ providers are unchanged.
- Bound native API-key hashes to their configured pepper with a persisted
Argon2id verifier. A restored database with existing keys now refuses to
serve under a different `[auth].token_pepper` instead of silently making
@@ -283,13 +290,6 @@ version in [`docs/changelog/`](docs/changelog/):
## [3.1.2] - 2026-10-20
### Fixed
-- Reserved local-embedding capacity for interactive search queries instead of
- allowing concurrent page writes and backfill work to occupy every inference
- slot. Excess queries fall back immediately to non-vector retrieval, and a
- cancelled request retains its slot until its non-cancellable CPU inference
- actually ends. An opt-in real-model contention probe records idle,
- unbounded-load, and bounded-load p50/p95 query latency; hosted embedding
- providers are unchanged.
- Reported appended and removed lines in wiki sync conflict summaries, with
an explicit end-of-file marker instead of line 0 and matching previews.
([#1477](https://github.com/akitaonrails/ai-memory/issues/1477))