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.mdindex 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 persistedArgon2id verifier. A restored database with existing keys now refuses toserve 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, withan explicit end-of-file marker instead of line 0 and matching previews.([#1477](https://github.com/akitaonrails/ai-memory/issues/1477))