Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Rust
Merge origin/release/3.3 and main into release/3.3
AkitaOnRailseaccc926aba0
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 033734d8..b0c151dd 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -13,6 +13,15 @@ version in [`docs/changelog/`](docs/changelog/):### Added+- `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 latesession details. It reuses the existing scorer and A/B reports; it measures@@ -95,22 +104,6 @@ version in [`docs/changelog/`](docs/changelog/):side is upgraded, and nothing showed it. When they differ in major version,the text report adds a warning to upgrade the older side (#1644).-### Fixed--- `memory_query(answer=true)` now validates model-generated citation paths- against the snippets supplied in that request. Unknown paths and paths- shared by distinct page versions withhold the answer, while retrieval hits- remain available with an `answer_unavailable` note. Repeated citations are- deduplicated in model order; the default query path makes no added calls- (#1682).-- `ai-memory write-page` and `restore-page` now print the last eight- characters of the page id instead of the first eight. Page ids are UUIDv7,- so the first eight are a timestamp prefix that every page written within- about a minute shares, and the printed `page_id` was the same for all of- them. The web UI already shortens ids this way (#1693).--## [3.2.3] - 2026-10-24-### Changed- `memory_install_self_routing(compact: true)` and `ai-memory@@ -121,6 +114,7 @@ version in [`docs/changelog/`](docs/changelog/):capture, the untrusted-memory trust rule, and where rules belong) and pointsat the installed `ai-memory-*` Agent Skills for the rest, which it alreadyrequired to be installed (#1672).+- When the native session linked to a workstream is missing from its store,an interactive `ai-memory run <harness>` now also names the newest sessionthis checkout still holds for that harness and the native selector that@@ -141,6 +135,36 @@ version in [`docs/changelog/`](docs/changelog/):and callers such as the reranker named only the first candidate, so a logcould blame the primary for a timeout another candidate caused. Responsebodies are never logged (#1628).++### Fixed++- Codex's own memory-writing agent no longer appears as captured sessions.+ Codex runs a background "memory writing agent" from `$CODEX_HOME/memories`+ (the default `~/.codex/memories`) to consolidate its memory; the hooks+ captured each run as a normal session, so one project of 78 sessions and+ ~2,600 observations existed for work nobody did, and it returned with the+ next run after a purge. Those events are now accepted and stored nowhere,+ recognized by the directory (any `…/.codex/memories`) or by the agent's+ `## Memory Writing Agent` prompt header, and transcript imports+ (`backfill`, the `run` ledger, `recover`) skip them for the same reason+ (#1674).++- `memory_query(answer=true)` now validates model-generated citation paths+ against the snippets supplied in that request. Unknown paths and paths+ shared by distinct page versions withhold the answer, while retrieval hits+ remain available with an `answer_unavailable` note. Repeated citations are+ deduplicated in model order; the default query path makes no added calls+ (#1682).+- `ai-memory write-page` and `restore-page` now print the last eight+ characters of the page id instead of the first eight. Page ids are UUIDv7,+ so the first eight are a timestamp prefix that every page written within+ about a minute shares, and the printed `page_id` was the same for all of+ them. The web UI already shortens ids this way (#1693).++## [3.2.3] - 2026-10-24++### Changed+- `ai-memory hook` and `ai-memory hook-drain` now run on a single-threadedtokio runtime. Both are spawned once per agent event and answer one request,and the multi-threaded default started a worker thread per CPU before the