Skip to content

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

Rust

Merge current release 3.1 into owned-session purge contribution

Vinicius Miguel9c504e8597b1
diff --cc CHANGELOG.md
index 758a51e3,ea4e8d10..270384aa
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@@ -12,9 -12,51 +12,54 @@@ version in [`docs/changelog/`](docs/cha
## [Unreleased]
### Added
+- Added optional human-session session inspection and owned purging, gated by the
+ `session-management` build feature and runtime switch. Reused existing human
+ authentication, authorization, and SQLite storage. (#1231)
+ - Added `ai-memory search --global`, which searches the wiki pages of every
+ project from the terminal instead of only the current one. Each hit shows
+ its `workspace/project` in the text output and carries `workspace` and
+ `project` fields in `--json`. The flag cannot be combined with
+ `--workspace` or `--project`, and a search without it still resolves its
+ scope from the current directory. The server side is `GET /admin/search`
+ with no `workspace`/`project`: its hits now include `workspace` and
+ `project` next to the fields they already had, and the route stays
+ root-only on a multi-user server. Global search covers wiki pages only;
+ raw observations and a search limited to one workspace are not part of
+ this change. (#1253)
+ - Added kind and tier filters to the web search. The search page in `/web`
+ has "Kind" and "Tier" selects, and `/web/search` accepts `kind` and `tier`
+ for both a project search and a cross-project one. Every retrieval stream
+ applies the filter in its own query, so other kinds cannot crowd out a rare
+ one, a filtered search asks the streams for no more candidates than an
+ unfiltered one, and the reranker scores only pages the filter keeps. Kind
+ and tier both ignore case, a nonstandard kind is flagged on an empty
+ result, and "Search all projects" keeps the filters. An unknown `tier` is
+ a 400. (#1248)
+
+ ### Fixed
+ - Fixed Windows capture dropping the body of file and shell tool events
+ the client had kept. With `[capture] ignore_paths` active, server
+ re-inspection compiled a POSIX never-match sentinel and treated the
+ policy as invalid, so a kept Read or Bash became metadata-only. The
+ sentinel now follows the event cwd's path flavor. (#1250)
+ - Fixed `GET /admin/sessions/by-agent`, and so `ai-memory doctor` and
+ `ai-memory backfill`, taking minutes on a large project (178 s for 780
+ sessions over 185k observations). Without planner statistics SQLite
+ answered each session's capture probe from the project-wide index and
+ rescanned the whole project once per session; the probe now always uses the
+ session index (0.3 s on the same store). The session list and session
+ detail reads behind `/web`, `/api/v1` and `memory_read_session_observations`
+ ran the same per-session probes and are pinned the same way. (#1257)
+ - Fixed pages written by an auto-improvement approval, a batch write or a
+ checkpoint restore getting no embedding. An approval (through
+ `pending-writes approve`, the `memory_auto_improve` tool,
+ `POST /admin/auto-improve` or the scheduler), the batch writes behind
+ consolidation, the forget sweep, dream and bootstrap, and
+ `ai-memory restore-page` wrote and indexed the page but never embedded
+ it, so it stayed out of the vector stream of hybrid search until an
+ embedding backfill ran, which by default is only at the next server
+ start. These paths now embed each written page the same way
+ `memory_write_page` does. (#1258)
## [3.0.0] - 2026-10-13