Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Rust
chore: reconcile release/3.3 after v3.2.4
AkitaOnRailsc596e5302e91
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 84779186..21c7260e 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -11,20 +11,16 @@ version in [`docs/changelog/`](docs/changelog/):## [Unreleased]-## [3.2.4] - 2026-10-25+### Added-### Security--- A restricted project now stays closed when its access-mode or grant query- fails. The common authorization resolver previously degraded these store- failures to an open project, so an unrelated authenticated user could gain- access during a database fault. Unknown projects and forward-unknown access- modes retain their compatibility behavior, and normal root, creator and- grant access is unchanged.-- Human-auth endpoints now log unexpected store and task failures server-side- and return a stable `authentication unavailable` response. Login and- recovery previously returned raw SQLite or task error text before the caller- authenticated; password-change conflicts also no longer expose store errors.+- `GET /admin/status` and `ai-memory status --json` now carry a+ `consolidation` block: the queue counts plus up to 20 `failed_sessions`+ (`session_id`, `attempts`, `failed_at_us`, scrubbed `last_error`), newest+ first. A consolidation run that gives up after its retries now has a+ machine-readable record with the session ids needed to re-run it, instead of+ only a journal line and the `/health` panel's count — which also resets with+ the process. The web health panel's own view stays counts-only, and an older+ server's status shape is unchanged (#1692).- Added the bundled `coding-v1` retrieval-evaluation corpus for offline checksof decision rationale, resolved-error causes, correction evidence, and late@@ -101,6 +97,7 @@ version in [`docs/changelog/`](docs/changelog/):provider behind an LLM fallback chain can spend the whole fixed budget on oneslow 503 before the next candidate answers, and every such query then keepsits pre-rerank order. ([#1614](https://github.com/akitaonrails/ai-memory/issues/1614))+- `ai-memory status` now shows the client's version next to the server's: a`ai-memory X (client)` line under `ai-memory X (server)`, and `version` inthe JSON `client` object. In a split install (native client and hooks, the@@ -140,6 +137,21 @@ version in [`docs/changelog/`](docs/changelog/):could blame the primary for a timeout another candidate caused. Responsebodies are never logged (#1628).+## [3.2.4] - 2026-10-25++### Security++- A restricted project now stays closed when its access-mode or grant query+ fails. The common authorization resolver previously degraded these store+ failures to an open project, so an unrelated authenticated user could gain+ access during a database fault. Unknown projects and forward-unknown access+ modes retain their compatibility behavior, and normal root, creator and+ grant access is unchanged.+- Human-auth endpoints now log unexpected store and task failures server-side+ and return a stable `authentication unavailable` response. Login and+ recovery previously returned raw SQLite or task error text before the caller+ authenticated; password-change conflicts also no longer expose store errors.+### Fixed- `ai-memory move-session` now refuses explicitly empty scope flags