Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Rust
Merge land/1518
AkitaOnRails8e505177ebfe
diff --cc CHANGELOG.mdindex 74c26781,3e2db75d..a6d816b6--- a/CHANGELOG.md+++ b/CHANGELOG.md@@@ -223,40 -223,12 +223,46 @@@ version in [`docs/changelog/`](docs/charelay and wiki sync companions take the same `rustls-webpki` bump.### Fixed+- Memory health no longer counts a link from a superseded or TTL-expired page+ version as a reference. A page whose only inbound link was removed by a later+ edit was reported as linked, because the old version's `links` row survives+ the edit and is repointed at the new latest id, so the orphan count and+ detail list disagreed with the page's own backlinks.+ ([#1526](https://github.com/akitaonrails/ai-memory/pull/1526))++- A `title:` or `body:` search filter whose term carries a second colon, such+ as `title:10:30`, now keeps its column. FTS5 read the inner `10` as a column+ name and rejected the whole expression, so the query degraded to the quoted+ bag of words: the filter was dropped and every column was searched for the+ literal word `title`.+ ([#1521](https://github.com/akitaonrails/ai-memory/pull/1521))+- `memory_query` no longer discards `as_of` on a global query. An explicit+ `global` with `as_of` is now refused, as the error message always claimed,+ and a repo on `[recall] default_global` no longer broadens an `as_of` query+ to global and answers it with present-day rows.+ ([#1519](https://github.com/akitaonrails/ai-memory/pull/1519))++- A `429` or `5xx` from a token endpoint is now a transient provider error+ rather than an auth failure. The Copilot token exchange, which GitHub+ rate-limits per account, and the shared `openai-oauth`/OIDC refresh both+ reported throttling as a credential problem, so the fallback chain stopped+ instead of trying the next provider and the operator was told to log in+ again for a grant that was never rejected.+ ([#1520](https://github.com/akitaonrails/ai-memory/pull/1520))++- The Gemini embedder now cuts a long input to the same 8 KB head as the+ OpenAI, Copilot and local embedders. It sent the whole page, while the+ default `gemini-embedding-001` takes at most 2,048 input tokens, and a+ refused page embedding is only logged, so a long page could end up with no+ vector. Voyage is unchanged: its API shortens an over-long input itself.+ ([#1513](https://github.com/akitaonrails/ai-memory/pull/1513))++ - `memory_auto_improve` now reports an exhausted implicit queue — every+ completed session already has a review run — as invalid params rather than an+ internal error, matching `memory_consolidate` for the same dead end. A client+ no longer reads the routine end of the queue as a server fault and retries it.+ ([#1518](https://github.com/akitaonrails/ai-memory/pull/1518))+- Reserved local-embedding capacity for interactive search queries instead ofallowing concurrent page writes and backfill work to occupy every inferenceslot. Excess queries fall back immediately to non-vector retrieval, and a